commit fcc8861aa2623957440e4cf2343e9a823b9dcbb2 Author: Joshua Sigona Date: Thu Jan 14 00:25:59 2021 +0900 D4DJ leaderboard parsing bot diff --git a/d4dj/.classpath b/d4dj/.classpath new file mode 100644 index 0000000..1247f9f --- /dev/null +++ b/d4dj/.classpath @@ -0,0 +1,27 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/d4dj/.project b/d4dj/.project new file mode 100644 index 0000000..0876206 --- /dev/null +++ b/d4dj/.project @@ -0,0 +1,23 @@ + + + d4dj + + + + + + org.eclipse.jdt.core.javabuilder + + + + + org.eclipse.m2e.core.maven2Builder + + + + + + org.eclipse.jdt.core.javanature + org.eclipse.m2e.core.maven2Nature + + diff --git a/d4dj/.settings/org.eclipse.core.resources.prefs b/d4dj/.settings/org.eclipse.core.resources.prefs new file mode 100644 index 0000000..f9fe345 --- /dev/null +++ b/d4dj/.settings/org.eclipse.core.resources.prefs @@ -0,0 +1,4 @@ +eclipse.preferences.version=1 +encoding//src/main/java=UTF-8 +encoding//src/test/java=UTF-8 +encoding/=UTF-8 diff --git a/d4dj/.settings/org.eclipse.jdt.core.prefs b/d4dj/.settings/org.eclipse.jdt.core.prefs new file mode 100644 index 0000000..a3b98fd --- /dev/null +++ b/d4dj/.settings/org.eclipse.jdt.core.prefs @@ -0,0 +1,8 @@ +eclipse.preferences.version=1 +org.eclipse.jdt.core.compiler.codegen.targetPlatform=1.7 +org.eclipse.jdt.core.compiler.compliance=1.7 +org.eclipse.jdt.core.compiler.problem.enablePreviewFeatures=disabled +org.eclipse.jdt.core.compiler.problem.forbiddenReference=warning +org.eclipse.jdt.core.compiler.problem.reportPreviewFeatures=ignore +org.eclipse.jdt.core.compiler.release=disabled +org.eclipse.jdt.core.compiler.source=1.7 diff --git a/d4dj/.settings/org.eclipse.m2e.core.prefs b/d4dj/.settings/org.eclipse.m2e.core.prefs new file mode 100644 index 0000000..f897a7f --- /dev/null +++ b/d4dj/.settings/org.eclipse.m2e.core.prefs @@ -0,0 +1,4 @@ +activeProfiles= +eclipse.preferences.version=1 +resolveWorkspaceProjects=true +version=1 diff --git a/d4dj/imgtest1.png b/d4dj/imgtest1.png new file mode 100644 index 0000000..c375ebd Binary files /dev/null and b/d4dj/imgtest1.png differ diff --git a/d4dj/imgtest2.png b/d4dj/imgtest2.png new file mode 100644 index 0000000..f1652bd Binary files /dev/null and b/d4dj/imgtest2.png differ diff --git a/d4dj/imgtest3.png b/d4dj/imgtest3.png new file mode 100644 index 0000000..389262b Binary files /dev/null and b/d4dj/imgtest3.png differ diff --git a/d4dj/imgtest4.png b/d4dj/imgtest4.png new file mode 100644 index 0000000..b907e78 Binary files /dev/null and b/d4dj/imgtest4.png differ diff --git a/d4dj/imgtest5.png b/d4dj/imgtest5.png new file mode 100644 index 0000000..59f2a46 Binary files /dev/null and b/d4dj/imgtest5.png differ diff --git a/d4dj/pom.xml b/d4dj/pom.xml new file mode 100644 index 0000000..8309852 --- /dev/null +++ b/d4dj/pom.xml @@ -0,0 +1,86 @@ + + + + 4.0.0 + + d4dj + d4dj + 0.0.1-SNAPSHOT + + d4dj + + http://www.example.com + + + UTF-8 + 1.7 + 1.7 + + + + + junit + junit + 4.11 + test + + + net.sourceforge.tess4j + tess4j + 3.2.1 + + + org.apache.httpcomponents + httpclient + 4.5.13 + + + + + + + + + + maven-clean-plugin + 3.1.0 + + + + maven-resources-plugin + 3.0.2 + + + maven-compiler-plugin + 3.8.0 + + + maven-surefire-plugin + 2.22.1 + + + maven-jar-plugin + 3.0.2 + + + maven-install-plugin + 2.5.2 + + + maven-deploy-plugin + 2.8.2 + + + + maven-site-plugin + 3.7.1 + + + maven-project-info-reports-plugin + 3.0.0 + + + + + diff --git a/d4dj/src/main/java/com/recognition/software/jdeskew/ImageDeskew.java b/d4dj/src/main/java/com/recognition/software/jdeskew/ImageDeskew.java new file mode 100644 index 0000000..a730eda --- /dev/null +++ b/d4dj/src/main/java/com/recognition/software/jdeskew/ImageDeskew.java @@ -0,0 +1,180 @@ +/** + * JDeskew + */ +package com.recognition.software.jdeskew; + +import net.sourceforge.tess4j.util.LoggHelper; +import org.slf4j.LoggerFactory; + +import java.awt.image.BufferedImage; + +public class ImageDeskew { + + private static final org.slf4j.Logger logger = LoggerFactory.getLogger(new LoggHelper().toString()); + + /** + * Representation of a line in the image. + */ + public class HoughLine { + + // count of points in the line + public int count = 0; + // index in matrix. + public int index = 0; + // the line is represented as all x, y that solve y * cos(alpha) - x * + // sin(alpha) = d + public double alpha; + public double d; + } + + // the source image + private BufferedImage cImage; + // the range of angles to search for lines + private double cAlphaStart = -20; + private double cAlphaStep = 0.2; + private int cSteps = 40 * 5; + // pre-calculation of sin and cos + private double[] cSinA; + private double[] cCosA; + // range of d + private double cDMin; + private double cDStep = 1.0; + private int cDCount; + // count of points that fit in a line + private int[] cHMatrix; + + /** + * Constructor. + * + * @param image + */ + public ImageDeskew(BufferedImage image) { + this.cImage = image; + } + + /** + * Calculates the skew angle of the image cImage. + * + * @return + */ + public double getSkewAngle() { + ImageDeskew.HoughLine[] hl; + double sum = 0.0; + int count = 0; + + // perform Hough Transformation + calc(); + // top 20 of the detected lines in the image + hl = getTop(20); + + if (hl.length >= 20) { + // average angle of the lines + for (int i = 0; i < 19; i++) { + sum += hl[i].alpha; + count++; + } + return (sum / count); + } else { + return 0.0d; + } + } + + // calculate the count lines in the image with most points + private ImageDeskew.HoughLine[] getTop(int count) { + + ImageDeskew.HoughLine[] hl = new ImageDeskew.HoughLine[count]; + for (int i = 0; i < count; i++) { + hl[i] = new ImageDeskew.HoughLine(); + } + + ImageDeskew.HoughLine tmp; + + for (int i = 0; i < (this.cHMatrix.length - 1); i++) { + if (this.cHMatrix[i] > hl[count - 1].count) { + hl[count - 1].count = this.cHMatrix[i]; + hl[count - 1].index = i; + int j = count - 1; + while ((j > 0) && (hl[j].count > hl[j - 1].count)) { + tmp = hl[j]; + hl[j] = hl[j - 1]; + hl[j - 1] = tmp; + j--; + } + } + } + + int alphaIndex; + int dIndex; + + for (int i = 0; i < count; i++) { + dIndex = hl[i].index / cSteps; // integer division, no + // remainder + alphaIndex = hl[i].index - dIndex * cSteps; + hl[i].alpha = getAlpha(alphaIndex); + hl[i].d = dIndex + cDMin; + } + + return hl; + } + + // Hough Transformation + private void calc() { + int hMin = (int) ((this.cImage.getHeight()) / 4.0); + int hMax = (int) ((this.cImage.getHeight()) * 3.0 / 4.0); + init(); + + for (int y = hMin; y < hMax; y++) { + for (int x = 1; x < (this.cImage.getWidth() - 2); x++) { + // only lower edges are considered + if (ImageUtil.isBlack(this.cImage, x, y)) { + if (!ImageUtil.isBlack(this.cImage, x, y + 1)) { + calc(x, y); + } + } + } + } + + } + + // calculate all lines through the point (x,y) + private void calc(int x, int y) { + double d; + int dIndex; + int index; + + for (int alpha = 0; alpha < (this.cSteps - 1); alpha++) { + d = y * this.cCosA[alpha] - x * this.cSinA[alpha]; + dIndex = (int) (d - this.cDMin); + index = dIndex * this.cSteps + alpha; + try { + this.cHMatrix[index] += 1; + } catch (Exception e) { + logger.warn("", e); + } + } + } + + private void init() { + + double angle; + + // pre-calculation of sin and cos + this.cSinA = new double[this.cSteps - 1]; + this.cCosA = new double[this.cSteps - 1]; + + for (int i = 0; i < (this.cSteps - 1); i++) { + angle = getAlpha(i) * Math.PI / 180.0; + this.cSinA[i] = Math.sin(angle); + this.cCosA[i] = Math.cos(angle); + } + + // range of d + this.cDMin = -this.cImage.getWidth(); + this.cDCount = (int) (2.0 * ((this.cImage.getWidth() + this.cImage.getHeight())) / this.cDStep); + this.cHMatrix = new int[this.cDCount * this.cSteps]; + } + + public double getAlpha(int index) { + return this.cAlphaStart + (index * this.cAlphaStep); + } +} diff --git a/d4dj/src/main/java/com/recognition/software/jdeskew/ImageUtil.java b/d4dj/src/main/java/com/recognition/software/jdeskew/ImageUtil.java new file mode 100644 index 0000000..099523d --- /dev/null +++ b/d4dj/src/main/java/com/recognition/software/jdeskew/ImageUtil.java @@ -0,0 +1,138 @@ +/** + * JDeskew + */ +package com.recognition.software.jdeskew; + +import java.awt.Color; +import java.awt.Graphics2D; +import java.awt.RenderingHints; +import java.awt.geom.AffineTransform; +import java.awt.image.BufferedImage; +import java.awt.image.WritableRaster; + +import net.sourceforge.tess4j.util.LoggHelper; +import org.slf4j.Logger; +import org.slf4j.LoggerFactory; + +public class ImageUtil { + + private static final Logger logger = LoggerFactory.getLogger(new LoggHelper().toString()); + + /** + * Whether the pixel is black. + * + * @param image source image + * @param x + * @param y + * @return + */ + public static boolean isBlack(BufferedImage image, int x, int y) { + if (image.getType() == BufferedImage.TYPE_BYTE_BINARY) { + WritableRaster raster = image.getRaster(); + int pixelRGBValue = raster.getSample(x, y, 0); + return pixelRGBValue == 0; + } + + int luminanceValue = 140; + return isBlack(image, x, y, luminanceValue); + } + + /** + * Whether the pixel is black. + * + * @param image source image + * @param x + * @param y + * @param luminanceCutOff + * @return + */ + public static boolean isBlack(BufferedImage image, int x, int y, int luminanceCutOff) { + int pixelRGBValue; + int r; + int g; + int b; + double luminance = 0.0; + + // return white on areas outside of image boundaries + if (x < 0 || y < 0 || x > image.getWidth() || y > image.getHeight()) { + return false; + } + + try { + pixelRGBValue = image.getRGB(x, y); + r = (pixelRGBValue >> 16) & 0xff; + g = (pixelRGBValue >> 8) & 0xff; + b = (pixelRGBValue) & 0xff; + luminance = (r * 0.299) + (g * 0.587) + (b * 0.114); + } catch (Exception e) { + logger.warn("", e); + } + + return luminance < luminanceCutOff; + } + + /** + * Rotates image. + * + * @param image source image + * @param angle by degrees + * @param cx x-coordinate of pivot point + * @param cy y-coordinate of pivot point + * @return rotated image + */ + public static BufferedImage rotate(BufferedImage image, double angle, int cx, int cy) { + int width = image.getWidth(null); + int height = image.getHeight(null); + + int minX, minY, maxX, maxY; + minX = minY = maxX = maxY = 0; + + int[] corners = {0, 0, width, 0, width, height, 0, height}; + + double theta = Math.toRadians(angle); + for (int i = 0; i < corners.length; i += 2) { + int x = (int) (Math.cos(theta) * (corners[i] - cx) + - Math.sin(theta) * (corners[i + 1] - cy) + cx); + int y = (int) (Math.sin(theta) * (corners[i] - cx) + + Math.cos(theta) * (corners[i + 1] - cy) + cy); + + if (x > maxX) { + maxX = x; + } + + if (x < minX) { + minX = x; + } + + if (y > maxY) { + maxY = y; + } + + if (y < minY) { + minY = y; + } + + } + + cx = (cx - minX); + cy = (cy - minY); + + BufferedImage bi = new BufferedImage((maxX - minX), (maxY - minY), + image.getType()); + Graphics2D g2 = bi.createGraphics(); + g2.setRenderingHint(RenderingHints.KEY_INTERPOLATION, + RenderingHints.VALUE_INTERPOLATION_BICUBIC); + + g2.setBackground(Color.white); + g2.fillRect(0, 0, bi.getWidth(), bi.getHeight()); + + AffineTransform at = new AffineTransform(); + at.rotate(theta, cx, cy); + + g2.setTransform(at); + g2.drawImage(image, -minX, -minY, null); + g2.dispose(); + + return bi; + } +} diff --git a/d4dj/src/main/java/d4dj/d4dj/App.java b/d4dj/src/main/java/d4dj/d4dj/App.java new file mode 100644 index 0000000..3de17ea --- /dev/null +++ b/d4dj/src/main/java/d4dj/d4dj/App.java @@ -0,0 +1,177 @@ +package d4dj.d4dj; + +import java.awt.Image; +import java.awt.Point; +import java.awt.Rectangle; +import java.awt.image.BufferedImage; +import java.io.File; +import java.io.IOException; +import java.io.InputStream; +import java.io.UnsupportedEncodingException; +import java.util.ArrayList; +import java.util.Arrays; +import java.util.List; +import java.util.Scanner; + +import javax.imageio.ImageIO; + +import org.apache.http.HttpEntity; +import org.apache.http.HttpResponse; +import org.apache.http.NameValuePair; +import org.apache.http.client.HttpClient; +import org.apache.http.client.entity.UrlEncodedFormEntity; +import org.apache.http.client.methods.HttpPost; +import org.apache.http.impl.client.HttpClients; +import org.apache.http.message.BasicNameValuePair; +import org.json.JSONObject; + +import net.sourceforge.tess4j.Tesseract; +import net.sourceforge.tess4j.TesseractException; +import sig.utils.ImageUtils; +class SubmitThread implements Runnable{ + String name,description,points; + int event,rank; + + SubmitThread(String name,String description,String points,int event,int rank) { + this.name=name; + this.description=description; + this.points=points; + this.event=event; + this.rank=rank; + } + + @Override + public void run() { + HttpClient httpclient = HttpClients.createDefault(); + HttpPost httppost = new HttpPost("http://projectdivar.com/eventsubmit"); + List params = new ArrayList(); + params.add(new BasicNameValuePair("eventid", Integer.toString(7))); + params.add(new BasicNameValuePair("rank", Integer.toString(rank))); + params.add(new BasicNameValuePair("name", name)); + params.add(new BasicNameValuePair("description", description)); + params.add(new BasicNameValuePair("points", points)); + try { + httppost.setEntity(new UrlEncodedFormEntity(params, "UTF-8")); + } catch (UnsupportedEncodingException e) { + e.printStackTrace(); + } + + //Execute and get the response. + HttpResponse response = null; + try { + response = httpclient.execute(httppost); + } catch (IOException e) { + e.printStackTrace(); + } + HttpEntity entity = response.getEntity(); + + if (entity != null) { + try (InputStream instream = entity.getContent()) { + Scanner s = new Scanner(instream).useDelimiter("\\A"); + String result = s.hasNext() ? s.next() : ""; + System.out.println(result); + instream.close(); + } catch (UnsupportedOperationException | IOException e) { + e.printStackTrace(); + } + } + } +} +public class App +{ + public static void main( String[] args ) + { + /* + Tesseract tesseract = new Tesseract(); + tesseract.setDatapath("C:\\Users\\sigon\\eclipse-workspace\\d4djRankReaderBot\\d4dj\\tessdata"); + try { + tesseract.setLanguage("jpn"); + //tesseract.setLanguage("eng"); + String finaldata = tesseract.doOCR(new File("imgtest5.png")); + Thread.sleep(500); + System.out.println(finaldata); + } catch (TesseractException | InterruptedException e) { + e.printStackTrace(); + }*/ + + Tesseract tesseract = new Tesseract(); + tesseract.setTessVariable("tessedit_write_images", "true"); + tesseract.setDatapath("C:\\Users\\sigon\\eclipse-workspace\\d4djRankReaderBot\\d4dj\\tessdata"); + + + Rectangle[] namepositions = new Rectangle[] {new Rectangle(475,263,316,36),new Rectangle(475,384,316,36),new Rectangle(475,510,316,36),new Rectangle(475,636,316,36)}; + Rectangle[] descriptions = new Rectangle[] {new Rectangle(475,328,544,36),new Rectangle(475,452,544,36),new Rectangle(475,576,544,36),new Rectangle(475,700,544,36)}; + Rectangle[] pointpositions = new Rectangle[] {new Rectangle(1042,317,200,34),new Rectangle(1042,442,200,34),new Rectangle(1042,566,200,34),new Rectangle(1042,688,200,34)}; + Point[] offsets = new Point[] {new Point(0,0),new Point(0,-2),new Point(0,-1),new Point(0,5),new Point(0,20)}; + + String[][] namedata = new String[5][4]; + String[][] descriptiondata = new String[5][4]; + String[][] pointdata = new String[5][4]; + + while (true) { + File f = new File("C:\\Users\\sigon\\Pictures\\MEmu Photo\\Screenshots"); + //System.out.println(Arrays.deepToString(f.listFiles())); + + if (f.listFiles().length==5) { + //New files found! + + + //Grab the first 5 files and try to parse them. + File[] list = f.listFiles(); + for (int i=0;i<5;i++) { + try { + BufferedImage img = ImageUtils.toBufferedImage(ImageIO.read(list[i])); + //ImageIO.write(img,"png",new File("debug/img"+)) + for (int j=0;j<4;j++) { + tesseract.setLanguage("jpn"); + //ImageIO.write(img.getSubimage(namepositions[j].x+offsets[j].x,namepositions[j].y+offsets[j].y,namepositions[j].width,namepositions[j].height),"png",new File("debug/img"+i+"_"+j+"_0.png")); + //ImageIO.write(img.getSubimage(descriptions[j].x+offsets[j].x,descriptions[j].y+offsets[j].y,descriptions[j].width,descriptions[j].height),"png",new File("debug/img"+i+"_"+j+"_1.png")); + //ImageIO.write(img.getSubimage(pointpositions[j].x+offsets[j].x,pointpositions[j].y+offsets[j].y,pointpositions[j].width,pointpositions[j].height),"png",new File("debug/img"+i+"_"+j+"_2.png")); + String name = tesseract.doOCR(img,new Rectangle(namepositions[j].x+offsets[i].x,namepositions[j].y+offsets[i].y,namepositions[j].width,namepositions[j].height)); + String description = tesseract.doOCR(img,new Rectangle(descriptions[j].x+offsets[i].x,descriptions[j].y+offsets[i].y,descriptions[j].width,descriptions[j].height)); + tesseract.setLanguage("eng"); + String points = tesseract.doOCR(img,new Rectangle(pointpositions[j].x+offsets[i].x,pointpositions[j].y+offsets[i].y,pointpositions[j].width,pointpositions[j].height)); + + namedata[i][j]=name; + descriptiondata[i][j]=description; + pointdata[i][j]=points; + } + } catch (IOException | TesseractException e) { + e.printStackTrace(); + } + } + + + for (File ff : list) { + ff.delete(); + } + + // Request parameters and other properties. + for (int i=0;i<20;i++) { + new Thread( + new SubmitThread(namedata[i/4][i%4],descriptiondata[i/4][i%4],pointdata[i/4][i%4].replaceAll(" ","").replaceAll("\\.",""),7,i+1)) + .start(); + } + } else { + if (f.listFiles().length>5) { + File[] list = f.listFiles(); + for (File ff : list) { + ff.delete(); + } + } + } + + /*System.out.println(Arrays.deepToString(namedata)); + System.out.println(Arrays.deepToString(descriptiondata)); + System.out.println(Arrays.deepToString(pointdata));*/ + + + + try { + Thread.sleep(10000); + } catch (InterruptedException e) { + e.printStackTrace(); + } + } + } +} diff --git a/d4dj/src/main/java/org/json/CDL.java b/d4dj/src/main/java/org/json/CDL.java new file mode 100644 index 0000000..6a82764 --- /dev/null +++ b/d4dj/src/main/java/org/json/CDL.java @@ -0,0 +1,284 @@ +package org.json; + +/* +Copyright (c) 2002 JSON.org + +Permission is hereby granted, free of charge, to any person obtaining a copy +of this software and associated documentation files (the "Software"), to deal +in the Software without restriction, including without limitation the rights +to use, copy, modify, merge, publish, distribute, sublicense, and/or sell +copies of the Software, and to permit persons to whom the Software is +furnished to do so, subject to the following conditions: + +The above copyright notice and this permission notice shall be included in all +copies or substantial portions of the Software. + +The Software shall be used for Good, not Evil. + +THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR +IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, +FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE +AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER +LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, +OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE +SOFTWARE. +*/ + +/** + * This provides static methods to convert comma delimited text into a + * JSONArray, and to convert a JSONArray into comma delimited text. Comma + * delimited text is a very popular format for data interchange. It is + * understood by most database, spreadsheet, and organizer programs. + *

+ * Each row of text represents a row in a table or a data record. Each row + * ends with a NEWLINE character. Each row contains one or more values. + * Values are separated by commas. A value can contain any character except + * for comma, unless is is wrapped in single quotes or double quotes. + *

+ * The first row usually contains the names of the columns. + *

+ * A comma delimited list can be converted into a JSONArray of JSONObjects. + * The names for the elements in the JSONObjects can be taken from the names + * in the first row. + * @author JSON.org + * @version 2016-05-01 + */ +public class CDL { + + /** + * Get the next value. The value can be wrapped in quotes. The value can + * be empty. + * @param x A JSONTokener of the source text. + * @return The value string, or null if empty. + * @throws JSONException if the quoted string is badly formed. + */ + private static String getValue(JSONTokener x) throws JSONException { + char c; + char q; + StringBuffer sb; + do { + c = x.next(); + } while (c == ' ' || c == '\t'); + switch (c) { + case 0: + return null; + case '"': + case '\'': + q = c; + sb = new StringBuffer(); + for (;;) { + c = x.next(); + if (c == q) { + //Handle escaped double-quote + if(x.next() != '\"') + { + x.back(); + break; + } + } + if (c == 0 || c == '\n' || c == '\r') { + throw x.syntaxError("Missing close quote '" + q + "'."); + } + sb.append(c); + } + return sb.toString(); + case ',': + x.back(); + return ""; + default: + x.back(); + return x.nextTo(','); + } + } + + /** + * Produce a JSONArray of strings from a row of comma delimited values. + * @param x A JSONTokener of the source text. + * @return A JSONArray of strings. + * @throws JSONException + */ + public static JSONArray rowToJSONArray(JSONTokener x) throws JSONException { + JSONArray ja = new JSONArray(); + for (;;) { + String value = getValue(x); + char c = x.next(); + if (value == null || + (ja.length() == 0 && value.length() == 0 && c != ',')) { + return null; + } + ja.put(value); + for (;;) { + if (c == ',') { + break; + } + if (c != ' ') { + if (c == '\n' || c == '\r' || c == 0) { + return ja; + } + throw x.syntaxError("Bad character '" + c + "' (" + + (int)c + ")."); + } + c = x.next(); + } + } + } + + /** + * Produce a JSONObject from a row of comma delimited text, using a + * parallel JSONArray of strings to provides the names of the elements. + * @param names A JSONArray of names. This is commonly obtained from the + * first row of a comma delimited text file using the rowToJSONArray + * method. + * @param x A JSONTokener of the source text. + * @return A JSONObject combining the names and values. + * @throws JSONException + */ + public static JSONObject rowToJSONObject(JSONArray names, JSONTokener x) + throws JSONException { + JSONArray ja = rowToJSONArray(x); + return ja != null ? ja.toJSONObject(names) : null; + } + + /** + * Produce a comma delimited text row from a JSONArray. Values containing + * the comma character will be quoted. Troublesome characters may be + * removed. + * @param ja A JSONArray of strings. + * @return A string ending in NEWLINE. + */ + public static String rowToString(JSONArray ja) { + StringBuilder sb = new StringBuilder(); + for (int i = 0; i < ja.length(); i += 1) { + if (i > 0) { + sb.append(','); + } + Object object = ja.opt(i); + if (object != null) { + String string = object.toString(); + if (string.length() > 0 && (string.indexOf(',') >= 0 || + string.indexOf('\n') >= 0 || string.indexOf('\r') >= 0 || + string.indexOf(0) >= 0 || string.charAt(0) == '"')) { + sb.append('"'); + int length = string.length(); + for (int j = 0; j < length; j += 1) { + char c = string.charAt(j); + if (c >= ' ' && c != '"') { + sb.append(c); + } + } + sb.append('"'); + } else { + sb.append(string); + } + } + } + sb.append('\n'); + return sb.toString(); + } + + /** + * Produce a JSONArray of JSONObjects from a comma delimited text string, + * using the first row as a source of names. + * @param string The comma delimited text. + * @return A JSONArray of JSONObjects. + * @throws JSONException + */ + public static JSONArray toJSONArray(String string) throws JSONException { + return toJSONArray(new JSONTokener(string)); + } + + /** + * Produce a JSONArray of JSONObjects from a comma delimited text string, + * using the first row as a source of names. + * @param x The JSONTokener containing the comma delimited text. + * @return A JSONArray of JSONObjects. + * @throws JSONException + */ + public static JSONArray toJSONArray(JSONTokener x) throws JSONException { + return toJSONArray(rowToJSONArray(x), x); + } + + /** + * Produce a JSONArray of JSONObjects from a comma delimited text string + * using a supplied JSONArray as the source of element names. + * @param names A JSONArray of strings. + * @param string The comma delimited text. + * @return A JSONArray of JSONObjects. + * @throws JSONException + */ + public static JSONArray toJSONArray(JSONArray names, String string) + throws JSONException { + return toJSONArray(names, new JSONTokener(string)); + } + + /** + * Produce a JSONArray of JSONObjects from a comma delimited text string + * using a supplied JSONArray as the source of element names. + * @param names A JSONArray of strings. + * @param x A JSONTokener of the source text. + * @return A JSONArray of JSONObjects. + * @throws JSONException + */ + public static JSONArray toJSONArray(JSONArray names, JSONTokener x) + throws JSONException { + if (names == null || names.length() == 0) { + return null; + } + JSONArray ja = new JSONArray(); + for (;;) { + JSONObject jo = rowToJSONObject(names, x); + if (jo == null) { + break; + } + ja.put(jo); + } + if (ja.length() == 0) { + return null; + } + return ja; + } + + + /** + * Produce a comma delimited text from a JSONArray of JSONObjects. The + * first row will be a list of names obtained by inspecting the first + * JSONObject. + * @param ja A JSONArray of JSONObjects. + * @return A comma delimited text. + * @throws JSONException + */ + public static String toString(JSONArray ja) throws JSONException { + JSONObject jo = ja.optJSONObject(0); + if (jo != null) { + JSONArray names = jo.names(); + if (names != null) { + return rowToString(names) + toString(names, ja); + } + } + return null; + } + + /** + * Produce a comma delimited text from a JSONArray of JSONObjects using + * a provided list of names. The list of names is not included in the + * output. + * @param names A JSONArray of strings. + * @param ja A JSONArray of JSONObjects. + * @return A comma delimited text. + * @throws JSONException + */ + public static String toString(JSONArray names, JSONArray ja) + throws JSONException { + if (names == null || names.length() == 0) { + return null; + } + StringBuffer sb = new StringBuffer(); + for (int i = 0; i < ja.length(); i += 1) { + JSONObject jo = ja.optJSONObject(i); + if (jo != null) { + sb.append(rowToString(jo.toJSONArray(names))); + } + } + return sb.toString(); + } +} diff --git a/d4dj/src/main/java/org/json/Cookie.java b/d4dj/src/main/java/org/json/Cookie.java new file mode 100644 index 0000000..348dc68 --- /dev/null +++ b/d4dj/src/main/java/org/json/Cookie.java @@ -0,0 +1,169 @@ +package org.json; + +/* +Copyright (c) 2002 JSON.org + +Permission is hereby granted, free of charge, to any person obtaining a copy +of this software and associated documentation files (the "Software"), to deal +in the Software without restriction, including without limitation the rights +to use, copy, modify, merge, publish, distribute, sublicense, and/or sell +copies of the Software, and to permit persons to whom the Software is +furnished to do so, subject to the following conditions: + +The above copyright notice and this permission notice shall be included in all +copies or substantial portions of the Software. + +The Software shall be used for Good, not Evil. + +THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR +IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, +FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE +AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER +LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, +OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE +SOFTWARE. +*/ + +/** + * Convert a web browser cookie specification to a JSONObject and back. + * JSON and Cookies are both notations for name/value pairs. + * @author JSON.org + * @version 2015-12-09 + */ +public class Cookie { + + /** + * Produce a copy of a string in which the characters '+', '%', '=', ';' + * and control characters are replaced with "%hh". This is a gentle form + * of URL encoding, attempting to cause as little distortion to the + * string as possible. The characters '=' and ';' are meta characters in + * cookies. By convention, they are escaped using the URL-encoding. This is + * only a convention, not a standard. Often, cookies are expected to have + * encoded values. We encode '=' and ';' because we must. We encode '%' and + * '+' because they are meta characters in URL encoding. + * @param string The source string. + * @return The escaped result. + */ + public static String escape(String string) { + char c; + String s = string.trim(); + int length = s.length(); + StringBuilder sb = new StringBuilder(length); + for (int i = 0; i < length; i += 1) { + c = s.charAt(i); + if (c < ' ' || c == '+' || c == '%' || c == '=' || c == ';') { + sb.append('%'); + sb.append(Character.forDigit((char)((c >>> 4) & 0x0f), 16)); + sb.append(Character.forDigit((char)(c & 0x0f), 16)); + } else { + sb.append(c); + } + } + return sb.toString(); + } + + + /** + * Convert a cookie specification string into a JSONObject. The string + * will contain a name value pair separated by '='. The name and the value + * will be unescaped, possibly converting '+' and '%' sequences. The + * cookie properties may follow, separated by ';', also represented as + * name=value (except the secure property, which does not have a value). + * The name will be stored under the key "name", and the value will be + * stored under the key "value". This method does not do checking or + * validation of the parameters. It only converts the cookie string into + * a JSONObject. + * @param string The cookie specification string. + * @return A JSONObject containing "name", "value", and possibly other + * members. + * @throws JSONException + */ + public static JSONObject toJSONObject(String string) throws JSONException { + String name; + JSONObject jo = new JSONObject(); + Object value; + JSONTokener x = new JSONTokener(string); + jo.put("name", x.nextTo('=')); + x.next('='); + jo.put("value", x.nextTo(';')); + x.next(); + while (x.more()) { + name = unescape(x.nextTo("=;")); + if (x.next() != '=') { + if (name.equals("secure")) { + value = Boolean.TRUE; + } else { + throw x.syntaxError("Missing '=' in cookie parameter."); + } + } else { + value = unescape(x.nextTo(';')); + x.next(); + } + jo.put(name, value); + } + return jo; + } + + + /** + * Convert a JSONObject into a cookie specification string. The JSONObject + * must contain "name" and "value" members. + * If the JSONObject contains "expires", "domain", "path", or "secure" + * members, they will be appended to the cookie specification string. + * All other members are ignored. + * @param jo A JSONObject + * @return A cookie specification string + * @throws JSONException + */ + public static String toString(JSONObject jo) throws JSONException { + StringBuilder sb = new StringBuilder(); + + sb.append(escape(jo.getString("name"))); + sb.append("="); + sb.append(escape(jo.getString("value"))); + if (jo.has("expires")) { + sb.append(";expires="); + sb.append(jo.getString("expires")); + } + if (jo.has("domain")) { + sb.append(";domain="); + sb.append(escape(jo.getString("domain"))); + } + if (jo.has("path")) { + sb.append(";path="); + sb.append(escape(jo.getString("path"))); + } + if (jo.optBoolean("secure")) { + sb.append(";secure"); + } + return sb.toString(); + } + + /** + * Convert %hh sequences to single characters, and + * convert plus to space. + * @param string A string that may contain + * + (plus) and + * %hh sequences. + * @return The unescaped string. + */ + public static String unescape(String string) { + int length = string.length(); + StringBuilder sb = new StringBuilder(length); + for (int i = 0; i < length; ++i) { + char c = string.charAt(i); + if (c == '+') { + c = ' '; + } else if (c == '%' && i + 2 < length) { + int d = JSONTokener.dehexchar(string.charAt(i + 1)); + int e = JSONTokener.dehexchar(string.charAt(i + 2)); + if (d >= 0 && e >= 0) { + c = (char)(d * 16 + e); + i += 2; + } + } + sb.append(c); + } + return sb.toString(); + } +} diff --git a/d4dj/src/main/java/org/json/CookieList.java b/d4dj/src/main/java/org/json/CookieList.java new file mode 100644 index 0000000..7a5628e --- /dev/null +++ b/d4dj/src/main/java/org/json/CookieList.java @@ -0,0 +1,89 @@ +package org.json; + +/* +Copyright (c) 2002 JSON.org + +Permission is hereby granted, free of charge, to any person obtaining a copy +of this software and associated documentation files (the "Software"), to deal +in the Software without restriction, including without limitation the rights +to use, copy, modify, merge, publish, distribute, sublicense, and/or sell +copies of the Software, and to permit persons to whom the Software is +furnished to do so, subject to the following conditions: + +The above copyright notice and this permission notice shall be included in all +copies or substantial portions of the Software. + +The Software shall be used for Good, not Evil. + +THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR +IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, +FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE +AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER +LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, +OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE +SOFTWARE. +*/ + +import java.util.Iterator; + +/** + * Convert a web browser cookie list string to a JSONObject and back. + * @author JSON.org + * @version 2015-12-09 + */ +public class CookieList { + + /** + * Convert a cookie list into a JSONObject. A cookie list is a sequence + * of name/value pairs. The names are separated from the values by '='. + * The pairs are separated by ';'. The names and the values + * will be unescaped, possibly converting '+' and '%' sequences. + * + * To add a cookie to a cooklist, + * cookielistJSONObject.put(cookieJSONObject.getString("name"), + * cookieJSONObject.getString("value")); + * @param string A cookie list string + * @return A JSONObject + * @throws JSONException + */ + public static JSONObject toJSONObject(String string) throws JSONException { + JSONObject jo = new JSONObject(); + JSONTokener x = new JSONTokener(string); + while (x.more()) { + String name = Cookie.unescape(x.nextTo('=')); + x.next('='); + jo.put(name, Cookie.unescape(x.nextTo(';'))); + x.next(); + } + return jo; + } + + /** + * Convert a JSONObject into a cookie list. A cookie list is a sequence + * of name/value pairs. The names are separated from the values by '='. + * The pairs are separated by ';'. The characters '%', '+', '=', and ';' + * in the names and values are replaced by "%hh". + * @param jo A JSONObject + * @return A cookie list string + * @throws JSONException + */ + public static String toString(JSONObject jo) throws JSONException { + boolean b = false; + Iterator keys = jo.keys(); + String string; + StringBuilder sb = new StringBuilder(); + while (keys.hasNext()) { + string = keys.next(); + if (!jo.isNull(string)) { + if (b) { + sb.append(';'); + } + sb.append(Cookie.escape(string)); + sb.append("="); + sb.append(Cookie.escape(jo.getString(string))); + b = true; + } + } + return sb.toString(); + } +} diff --git a/d4dj/src/main/java/org/json/HTTP.java b/d4dj/src/main/java/org/json/HTTP.java new file mode 100644 index 0000000..fafdfad --- /dev/null +++ b/d4dj/src/main/java/org/json/HTTP.java @@ -0,0 +1,164 @@ +package org.json; + +/* +Copyright (c) 2002 JSON.org + +Permission is hereby granted, free of charge, to any person obtaining a copy +of this software and associated documentation files (the "Software"), to deal +in the Software without restriction, including without limitation the rights +to use, copy, modify, merge, publish, distribute, sublicense, and/or sell +copies of the Software, and to permit persons to whom the Software is +furnished to do so, subject to the following conditions: + +The above copyright notice and this permission notice shall be included in all +copies or substantial portions of the Software. + +The Software shall be used for Good, not Evil. + +THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR +IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, +FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE +AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER +LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, +OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE +SOFTWARE. +*/ + +import java.util.Iterator; +import java.util.Locale; + +/** + * Convert an HTTP header to a JSONObject and back. + * @author JSON.org + * @version 2015-12-09 + */ +public class HTTP { + + /** Carriage return/line feed. */ + public static final String CRLF = "\r\n"; + + /** + * Convert an HTTP header string into a JSONObject. It can be a request + * header or a response header. A request header will contain + * 

{
+     *    Method: "POST" (for example),
+     *    "Request-URI": "/" (for example),
+     *    "HTTP-Version": "HTTP/1.1" (for example)
+     * }
+ * A response header will contain + * 
{
+     *    "HTTP-Version": "HTTP/1.1" (for example),
+     *    "Status-Code": "200" (for example),
+     *    "Reason-Phrase": "OK" (for example)
+     * }
+ * In addition, the other parameters in the header will be captured, using + * the HTTP field names as JSON names, so that 
+     *    Date: Sun, 26 May 2002 18:06:04 GMT
+     *    Cookie: Q=q2=PPEAsg--; B=677gi6ouf29bn&b=2&f=s
+     *    Cache-Control: no-cache
+ * become + * 
{...
+     *    Date: "Sun, 26 May 2002 18:06:04 GMT",
+     *    Cookie: "Q=q2=PPEAsg--; B=677gi6ouf29bn&b=2&f=s",
+     *    "Cache-Control": "no-cache",
+     * ...}
+ * It does no further checking or conversion. It does not parse dates. + * It does not do '%' transforms on URLs. + * @param string An HTTP header string. + * @return A JSONObject containing the elements and attributes + * of the XML string. + * @throws JSONException + */ + public static JSONObject toJSONObject(String string) throws JSONException { + JSONObject jo = new JSONObject(); + HTTPTokener x = new HTTPTokener(string); + String token; + + token = x.nextToken(); + if (token.toUpperCase(Locale.ROOT).startsWith("HTTP")) { + +// Response + + jo.put("HTTP-Version", token); + jo.put("Status-Code", x.nextToken()); + jo.put("Reason-Phrase", x.nextTo('\0')); + x.next(); + + } else { + +// Request + + jo.put("Method", token); + jo.put("Request-URI", x.nextToken()); + jo.put("HTTP-Version", x.nextToken()); + } + +// Fields + + while (x.more()) { + String name = x.nextTo(':'); + x.next(':'); + jo.put(name, x.nextTo('\0')); + x.next(); + } + return jo; + } + + + /** + * Convert a JSONObject into an HTTP header. A request header must contain + * 
{
+     *    Method: "POST" (for example),
+     *    "Request-URI": "/" (for example),
+     *    "HTTP-Version": "HTTP/1.1" (for example)
+     * }
+ * A response header must contain + * 
{
+     *    "HTTP-Version": "HTTP/1.1" (for example),
+     *    "Status-Code": "200" (for example),
+     *    "Reason-Phrase": "OK" (for example)
+     * }
+ * Any other members of the JSONObject will be output as HTTP fields. + * The result will end with two CRLF pairs. + * @param jo A JSONObject + * @return An HTTP header string. + * @throws JSONException if the object does not contain enough + * information. + */ + public static String toString(JSONObject jo) throws JSONException { + Iterator keys = jo.keys(); + String string; + StringBuilder sb = new StringBuilder(); + if (jo.has("Status-Code") && jo.has("Reason-Phrase")) { + sb.append(jo.getString("HTTP-Version")); + sb.append(' '); + sb.append(jo.getString("Status-Code")); + sb.append(' '); + sb.append(jo.getString("Reason-Phrase")); + } else if (jo.has("Method") && jo.has("Request-URI")) { + sb.append(jo.getString("Method")); + sb.append(' '); + sb.append('"'); + sb.append(jo.getString("Request-URI")); + sb.append('"'); + sb.append(' '); + sb.append(jo.getString("HTTP-Version")); + } else { + throw new JSONException("Not enough material for an HTTP header."); + } + sb.append(CRLF); + while (keys.hasNext()) { + string = keys.next(); + if (!"HTTP-Version".equals(string) && !"Status-Code".equals(string) && + !"Reason-Phrase".equals(string) && !"Method".equals(string) && + !"Request-URI".equals(string) && !jo.isNull(string)) { + sb.append(string); + sb.append(": "); + sb.append(jo.getString(string)); + sb.append(CRLF); + } + } + sb.append(CRLF); + return sb.toString(); + } +} diff --git a/d4dj/src/main/java/org/json/HTTPTokener.java b/d4dj/src/main/java/org/json/HTTPTokener.java new file mode 100644 index 0000000..55f48ff --- /dev/null +++ b/d4dj/src/main/java/org/json/HTTPTokener.java @@ -0,0 +1,77 @@ +package org.json; + +/* +Copyright (c) 2002 JSON.org + +Permission is hereby granted, free of charge, to any person obtaining a copy +of this software and associated documentation files (the "Software"), to deal +in the Software without restriction, including without limitation the rights +to use, copy, modify, merge, publish, distribute, sublicense, and/or sell +copies of the Software, and to permit persons to whom the Software is +furnished to do so, subject to the following conditions: + +The above copyright notice and this permission notice shall be included in all +copies or substantial portions of the Software. + +The Software shall be used for Good, not Evil. + +THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR +IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, +FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE +AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER +LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, +OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE +SOFTWARE. +*/ + +/** + * The HTTPTokener extends the JSONTokener to provide additional methods + * for the parsing of HTTP headers. + * @author JSON.org + * @version 2015-12-09 + */ +public class HTTPTokener extends JSONTokener { + + /** + * Construct an HTTPTokener from a string. + * @param string A source string. + */ + public HTTPTokener(String string) { + super(string); + } + + + /** + * Get the next token or string. This is used in parsing HTTP headers. + * @throws JSONException + * @return A String. + */ + public String nextToken() throws JSONException { + char c; + char q; + StringBuilder sb = new StringBuilder(); + do { + c = next(); + } while (Character.isWhitespace(c)); + if (c == '"' || c == '\'') { + q = c; + for (;;) { + c = next(); + if (c < ' ') { + throw syntaxError("Unterminated string."); + } + if (c == q) { + return sb.toString(); + } + sb.append(c); + } + } + for (;;) { + if (c == 0 || Character.isWhitespace(c)) { + return sb.toString(); + } + sb.append(c); + c = next(); + } + } +} diff --git a/d4dj/src/main/java/org/json/JSONArray.java b/d4dj/src/main/java/org/json/JSONArray.java new file mode 100644 index 0000000..2446fd6 --- /dev/null +++ b/d4dj/src/main/java/org/json/JSONArray.java @@ -0,0 +1,1200 @@ +package org.json; + +/* + Copyright (c) 2002 JSON.org + + Permission is hereby granted, free of charge, to any person obtaining a copy + of this software and associated documentation files (the "Software"), to deal + in the Software without restriction, including without limitation the rights + to use, copy, modify, merge, publish, distribute, sublicense, and/or sell + copies of the Software, and to permit persons to whom the Software is + furnished to do so, subject to the following conditions: + + The above copyright notice and this permission notice shall be included in all + copies or substantial portions of the Software. + + The Software shall be used for Good, not Evil. + + THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE + AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER + LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, + OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE + SOFTWARE. + */ + +import java.io.IOException; +import java.io.StringWriter; +import java.io.Writer; +import java.lang.reflect.Array; +import java.math.BigDecimal; +import java.math.BigInteger; +import java.util.ArrayList; +import java.util.Collection; +import java.util.Iterator; +import java.util.List; +import java.util.Map; + +/** + * A JSONArray is an ordered sequence of values. Its external text form is a + * string wrapped in square brackets with commas separating the values. The + * internal form is an object having get and opt + * methods for accessing the values by index, and put methods for + * adding or replacing values. The values can be any of these types: + * Boolean, JSONArray, JSONObject, + * Number, String, or the + * JSONObject.NULL object. + *

+ * The constructor can convert a JSON text into a Java object. The + * toString method converts to JSON text. + *

+ * A get method returns a value if one can be found, and throws an + * exception if one cannot be found. An opt method returns a + * default value instead of throwing an exception, and so is useful for + * obtaining optional values. + *

+ * The generic get() and opt() methods return an + * object which you can cast or query for type. There are also typed + * get and opt methods that do type checking and type + * coercion for you. + *

+ * The texts produced by the toString methods strictly conform to + * JSON syntax rules. The constructors are more forgiving in the texts they will + * accept: + *

    + *
  • An extra , (comma) may appear just + * before the closing bracket.
    • + *
  • The null value will be inserted when there is , + *  (comma) elision.
    • + *
  • Strings may be quoted with ' (single + * quote).
    • + *
  • Strings do not need to be quoted at all if they do not begin with a quote + * or single quote, and if they do not contain leading or trailing spaces, and + * if they do not contain any of these characters: + * { } [ ] / \ : , # and if they do not look like numbers and + * if they are not the reserved words true, false, or + * null.
    • + *
+ * + * @author JSON.org + * @version 2016-08/15 + */ +public class JSONArray implements Iterable { + + /** + * The arrayList where the JSONArray's properties are kept. + */ + private final ArrayList myArrayList; + + /** + * Construct an empty JSONArray. + */ + public JSONArray() { + this.myArrayList = new ArrayList(); + } + + /** + * Construct a JSONArray from a JSONTokener. + * + * @param x + * A JSONTokener + * @throws JSONException + * If there is a syntax error. + */ + public JSONArray(JSONTokener x) throws JSONException { + this(); + if (x.nextClean() != '[') { + throw x.syntaxError("A JSONArray text must start with '['"); + } + if (x.nextClean() != ']') { + x.back(); + for (;;) { + if (x.nextClean() == ',') { + x.back(); + this.myArrayList.add(JSONObject.NULL); + } else { + x.back(); + this.myArrayList.add(x.nextValue()); + } + switch (x.nextClean()) { + case ',': + if (x.nextClean() == ']') { + return; + } + x.back(); + break; + case ']': + return; + default: + throw x.syntaxError("Expected a ',' or ']'"); + } + } + } + } + + /** + * Construct a JSONArray from a source JSON text. + * + * @param source + * A string that begins with [ (left + * bracket) and ends with ] + *  (right bracket). + * @throws JSONException + * If there is a syntax error. + */ + public JSONArray(String source) throws JSONException { + this(new JSONTokener(source)); + } + + /** + * Construct a JSONArray from a Collection. + * + * @param collection + * A Collection. + */ + public JSONArray(Collection collection) { + this.myArrayList = new ArrayList(); + if (collection != null) { + for (Object o: collection){ + this.myArrayList.add(JSONObject.wrap(o)); + } + } + } + + /** + * Construct a JSONArray from an array + * + * @throws JSONException + * If not an array. + */ + public JSONArray(Object array) throws JSONException { + this(); + if (array.getClass().isArray()) { + int length = Array.getLength(array); + for (int i = 0; i < length; i += 1) { + this.put(JSONObject.wrap(Array.get(array, i))); + } + } else { + throw new JSONException( + "JSONArray initial value should be a string or collection or array."); + } + } + + @Override + public Iterator iterator() { + return myArrayList.iterator(); + } + + /** + * Get the object value associated with an index. + * + * @param index + * The index must be between 0 and length() - 1. + * @return An object value. + * @throws JSONException + * If there is no value for the index. + */ + public Object get(int index) throws JSONException { + Object object = this.opt(index); + if (object == null) { + throw new JSONException("JSONArray[" + index + "] not found."); + } + return object; + } + + /** + * Get the boolean value associated with an index. The string values "true" + * and "false" are converted to boolean. + * + * @param index + * The index must be between 0 and length() - 1. + * @return The truth. + * @throws JSONException + * If there is no value for the index or if the value is not + * convertible to boolean. + */ + public boolean getBoolean(int index) throws JSONException { + Object object = this.get(index); + if (object.equals(Boolean.FALSE) + || (object instanceof String && ((String) object) + .equalsIgnoreCase("false"))) { + return false; + } else if (object.equals(Boolean.TRUE) + || (object instanceof String && ((String) object) + .equalsIgnoreCase("true"))) { + return true; + } + throw new JSONException("JSONArray[" + index + "] is not a boolean."); + } + + /** + * Get the double value associated with an index. + * + * @param index + * The index must be between 0 and length() - 1. + * @return The value. + * @throws JSONException + * If the key is not found or if the value cannot be converted + * to a number. + */ + public double getDouble(int index) throws JSONException { + Object object = this.get(index); + try { + return object instanceof Number ? ((Number) object).doubleValue() + : Double.parseDouble((String) object); + } catch (Exception e) { + throw new JSONException("JSONArray[" + index + "] is not a number."); + } + } + + /** + * Get the enum value associated with an index. + * + * @param clazz + * The type of enum to retrieve. + * @param index + * The index must be between 0 and length() - 1. + * @return The enum value at the index location + * @throws JSONException + * if the key is not found or if the value cannot be converted + * to an enum. + */ + public > E getEnum(Class clazz, int index) throws JSONException { + E val = optEnum(clazz, index); + if(val==null) { + // JSONException should really take a throwable argument. + // If it did, I would re-implement this with the Enum.valueOf + // method and place any thrown exception in the JSONException + throw new JSONException("JSONObject[" + JSONObject.quote(Integer.toString(index)) + + "] is not an enum of type " + JSONObject.quote(clazz.getSimpleName()) + + "."); + } + return val; + } + + /** + * Get the BigDecimal value associated with an index. + * + * @param index + * The index must be between 0 and length() - 1. + * @return The value. + * @throws JSONException + * If the key is not found or if the value cannot be converted + * to a BigDecimal. + */ + public BigDecimal getBigDecimal (int index) throws JSONException { + Object object = this.get(index); + try { + return new BigDecimal(object.toString()); + } catch (Exception e) { + throw new JSONException("JSONArray[" + index + + "] could not convert to BigDecimal."); + } + } + + /** + * Get the BigInteger value associated with an index. + * + * @param index + * The index must be between 0 and length() - 1. + * @return The value. + * @throws JSONException + * If the key is not found or if the value cannot be converted + * to a BigInteger. + */ + public BigInteger getBigInteger (int index) throws JSONException { + Object object = this.get(index); + try { + return new BigInteger(object.toString()); + } catch (Exception e) { + throw new JSONException("JSONArray[" + index + + "] could not convert to BigInteger."); + } + } + + /** + * Get the int value associated with an index. + * + * @param index + * The index must be between 0 and length() - 1. + * @return The value. + * @throws JSONException + * If the key is not found or if the value is not a number. + */ + public int getInt(int index) throws JSONException { + Object object = this.get(index); + try { + return object instanceof Number ? ((Number) object).intValue() + : Integer.parseInt((String) object); + } catch (Exception e) { + throw new JSONException("JSONArray[" + index + "] is not a number."); + } + } + + /** + * Get the JSONArray associated with an index. + * + * @param index + * The index must be between 0 and length() - 1. + * @return A JSONArray value. + * @throws JSONException + * If there is no value for the index. or if the value is not a + * JSONArray + */ + public JSONArray getJSONArray(int index) throws JSONException { + Object object = this.get(index); + if (object instanceof JSONArray) { + return (JSONArray) object; + } + throw new JSONException("JSONArray[" + index + "] is not a JSONArray."); + } + + /** + * Get the JSONObject associated with an index. + * + * @param index + * subscript + * @return A JSONObject value. + * @throws JSONException + * If there is no value for the index or if the value is not a + * JSONObject + */ + public JSONObject getJSONObject(int index) throws JSONException { + Object object = this.get(index); + if (object instanceof JSONObject) { + return (JSONObject) object; + } + throw new JSONException("JSONArray[" + index + "] is not a JSONObject."); + } + + /** + * Get the long value associated with an index. + * + * @param index + * The index must be between 0 and length() - 1. + * @return The value. + * @throws JSONException + * If the key is not found or if the value cannot be converted + * to a number. + */ + public long getLong(int index) throws JSONException { + Object object = this.get(index); + try { + return object instanceof Number ? ((Number) object).longValue() + : Long.parseLong((String) object); + } catch (Exception e) { + throw new JSONException("JSONArray[" + index + "] is not a number."); + } + } + + /** + * Get the string associated with an index. + * + * @param index + * The index must be between 0 and length() - 1. + * @return A string value. + * @throws JSONException + * If there is no string value for the index. + */ + public String getString(int index) throws JSONException { + Object object = this.get(index); + if (object instanceof String) { + return (String) object; + } + throw new JSONException("JSONArray[" + index + "] not a string."); + } + + /** + * Determine if the value is null. + * + * @param index + * The index must be between 0 and length() - 1. + * @return true if the value at the index is null, or if there is no value. + */ + public boolean isNull(int index) { + return JSONObject.NULL.equals(this.opt(index)); + } + + /** + * Make a string from the contents of this JSONArray. The + * separator string is inserted between each element. Warning: + * This method assumes that the data structure is acyclical. + * + * @param separator + * A string that will be inserted between the elements. + * @return a string. + * @throws JSONException + * If the array contains an invalid number. + */ + public String join(String separator) throws JSONException { + int len = this.length(); + StringBuilder sb = new StringBuilder(); + + for (int i = 0; i < len; i += 1) { + if (i > 0) { + sb.append(separator); + } + sb.append(JSONObject.valueToString(this.myArrayList.get(i))); + } + return sb.toString(); + } + + /** + * Get the number of elements in the JSONArray, included nulls. + * + * @return The length (or size). + */ + public int length() { + return this.myArrayList.size(); + } + + /** + * Get the optional object value associated with an index. + * + * @param index + * The index must be between 0 and length() - 1. + * @return An object value, or null if there is no object at that index. + */ + public Object opt(int index) { + return (index < 0 || index >= this.length()) ? null : this.myArrayList + .get(index); + } + + /** + * Get the optional boolean value associated with an index. It returns false + * if there is no value at that index, or if the value is not Boolean.TRUE + * or the String "true". + * + * @param index + * The index must be between 0 and length() - 1. + * @return The truth. + */ + public boolean optBoolean(int index) { + return this.optBoolean(index, false); + } + + /** + * Get the optional boolean value associated with an index. It returns the + * defaultValue if there is no value at that index or if it is not a Boolean + * or the String "true" or "false" (case insensitive). + * + * @param index + * The index must be between 0 and length() - 1. + * @param defaultValue + * A boolean default. + * @return The truth. + */ + public boolean optBoolean(int index, boolean defaultValue) { + try { + return this.getBoolean(index); + } catch (Exception e) { + return defaultValue; + } + } + + /** + * Get the optional double value associated with an index. NaN is returned + * if there is no value for the index, or if the value is not a number and + * cannot be converted to a number. + * + * @param index + * The index must be between 0 and length() - 1. + * @return The value. + */ + public double optDouble(int index) { + return this.optDouble(index, Double.NaN); + } + + /** + * Get the optional double value associated with an index. The defaultValue + * is returned if there is no value for the index, or if the value is not a + * number and cannot be converted to a number. + * + * @param index + * subscript + * @param defaultValue + * The default value. + * @return The value. + */ + public double optDouble(int index, double defaultValue) { + try { + return this.getDouble(index); + } catch (Exception e) { + return defaultValue; + } + } + + /** + * Get the optional int value associated with an index. Zero is returned if + * there is no value for the index, or if the value is not a number and + * cannot be converted to a number. + * + * @param index + * The index must be between 0 and length() - 1. + * @return The value. + */ + public int optInt(int index) { + return this.optInt(index, 0); + } + + /** + * Get the optional int value associated with an index. The defaultValue is + * returned if there is no value for the index, or if the value is not a + * number and cannot be converted to a number. + * + * @param index + * The index must be between 0 and length() - 1. + * @param defaultValue + * The default value. + * @return The value. + */ + public int optInt(int index, int defaultValue) { + try { + return this.getInt(index); + } catch (Exception e) { + return defaultValue; + } + } + + /** + * Get the enum value associated with a key. + * + * @param clazz + * The type of enum to retrieve. + * @param index + * The index must be between 0 and length() - 1. + * @return The enum value at the index location or null if not found + */ + public > E optEnum(Class clazz, int index) { + return this.optEnum(clazz, index, null); + } + + /** + * Get the enum value associated with a key. + * + * @param clazz + * The type of enum to retrieve. + * @param index + * The index must be between 0 and length() - 1. + * @param defaultValue + * The default in case the value is not found + * @return The enum value at the index location or defaultValue if + * the value is not found or cannot be assigned to clazz + */ + public > E optEnum(Class clazz, int index, E defaultValue) { + try { + Object val = this.opt(index); + if (JSONObject.NULL.equals(val)) { + return defaultValue; + } + if (clazz.isAssignableFrom(val.getClass())) { + // we just checked it! + @SuppressWarnings("unchecked") + E myE = (E) val; + return myE; + } + return Enum.valueOf(clazz, val.toString()); + } catch (IllegalArgumentException e) { + return defaultValue; + } catch (NullPointerException e) { + return defaultValue; + } + } + + + /** + * Get the optional BigInteger value associated with an index. The + * defaultValue is returned if there is no value for the index, or if the + * value is not a number and cannot be converted to a number. + * + * @param index + * The index must be between 0 and length() - 1. + * @param defaultValue + * The default value. + * @return The value. + */ + public BigInteger optBigInteger(int index, BigInteger defaultValue) { + try { + return this.getBigInteger(index); + } catch (Exception e) { + return defaultValue; + } + } + + /** + * Get the optional BigDecimal value associated with an index. The + * defaultValue is returned if there is no value for the index, or if the + * value is not a number and cannot be converted to a number. + * + * @param index + * The index must be between 0 and length() - 1. + * @param defaultValue + * The default value. + * @return The value. + */ + public BigDecimal optBigDecimal(int index, BigDecimal defaultValue) { + try { + return this.getBigDecimal(index); + } catch (Exception e) { + return defaultValue; + } + } + + /** + * Get the optional JSONArray associated with an index. + * + * @param index + * subscript + * @return A JSONArray value, or null if the index has no value, or if the + * value is not a JSONArray. + */ + public JSONArray optJSONArray(int index) { + Object o = this.opt(index); + return o instanceof JSONArray ? (JSONArray) o : null; + } + + /** + * Get the optional JSONObject associated with an index. Null is returned if + * the key is not found, or null if the index has no value, or if the value + * is not a JSONObject. + * + * @param index + * The index must be between 0 and length() - 1. + * @return A JSONObject value. + */ + public JSONObject optJSONObject(int index) { + Object o = this.opt(index); + return o instanceof JSONObject ? (JSONObject) o : null; + } + + /** + * Get the optional long value associated with an index. Zero is returned if + * there is no value for the index, or if the value is not a number and + * cannot be converted to a number. + * + * @param index + * The index must be between 0 and length() - 1. + * @return The value. + */ + public long optLong(int index) { + return this.optLong(index, 0); + } + + /** + * Get the optional long value associated with an index. The defaultValue is + * returned if there is no value for the index, or if the value is not a + * number and cannot be converted to a number. + * + * @param index + * The index must be between 0 and length() - 1. + * @param defaultValue + * The default value. + * @return The value. + */ + public long optLong(int index, long defaultValue) { + try { + return this.getLong(index); + } catch (Exception e) { + return defaultValue; + } + } + + /** + * Get the optional string value associated with an index. It returns an + * empty string if there is no value at that index. If the value is not a + * string and is not null, then it is coverted to a string. + * + * @param index + * The index must be between 0 and length() - 1. + * @return A String value. + */ + public String optString(int index) { + return this.optString(index, ""); + } + + /** + * Get the optional string associated with an index. The defaultValue is + * returned if the key is not found. + * + * @param index + * The index must be between 0 and length() - 1. + * @param defaultValue + * The default value. + * @return A String value. + */ + public String optString(int index, String defaultValue) { + Object object = this.opt(index); + return JSONObject.NULL.equals(object) ? defaultValue : object + .toString(); + } + + /** + * Append a boolean value. This increases the array's length by one. + * + * @param value + * A boolean value. + * @return this. + */ + public JSONArray put(boolean value) { + this.put(value ? Boolean.TRUE : Boolean.FALSE); + return this; + } + + /** + * Put a value in the JSONArray, where the value will be a JSONArray which + * is produced from a Collection. + * + * @param value + * A Collection value. + * @return this. + */ + public JSONArray put(Collection value) { + this.put(new JSONArray(value)); + return this; + } + + /** + * Append a double value. This increases the array's length by one. + * + * @param value + * A double value. + * @throws JSONException + * if the value is not finite. + * @return this. + */ + public JSONArray put(double value) throws JSONException { + Double d = new Double(value); + JSONObject.testValidity(d); + this.put(d); + return this; + } + + /** + * Append an int value. This increases the array's length by one. + * + * @param value + * An int value. + * @return this. + */ + public JSONArray put(int value) { + this.put(new Integer(value)); + return this; + } + + /** + * Append an long value. This increases the array's length by one. + * + * @param value + * A long value. + * @return this. + */ + public JSONArray put(long value) { + this.put(new Long(value)); + return this; + } + + /** + * Put a value in the JSONArray, where the value will be a JSONObject which + * is produced from a Map. + * + * @param value + * A Map value. + * @return this. + */ + public JSONArray put(Map value) { + this.put(new JSONObject(value)); + return this; + } + + /** + * Append an object value. This increases the array's length by one. + * + * @param value + * An object value. The value should be a Boolean, Double, + * Integer, JSONArray, JSONObject, Long, or String, or the + * JSONObject.NULL object. + * @return this. + */ + public JSONArray put(Object value) { + this.myArrayList.add(value); + return this; + } + + /** + * Put or replace a boolean value in the JSONArray. If the index is greater + * than the length of the JSONArray, then null elements will be added as + * necessary to pad it out. + * + * @param index + * The subscript. + * @param value + * A boolean value. + * @return this. + * @throws JSONException + * If the index is negative. + */ + public JSONArray put(int index, boolean value) throws JSONException { + this.put(index, value ? Boolean.TRUE : Boolean.FALSE); + return this; + } + + /** + * Put a value in the JSONArray, where the value will be a JSONArray which + * is produced from a Collection. + * + * @param index + * The subscript. + * @param value + * A Collection value. + * @return this. + * @throws JSONException + * If the index is negative or if the value is not finite. + */ + public JSONArray put(int index, Collection value) throws JSONException { + this.put(index, new JSONArray(value)); + return this; + } + + /** + * Put or replace a double value. If the index is greater than the length of + * the JSONArray, then null elements will be added as necessary to pad it + * out. + * + * @param index + * The subscript. + * @param value + * A double value. + * @return this. + * @throws JSONException + * If the index is negative or if the value is not finite. + */ + public JSONArray put(int index, double value) throws JSONException { + this.put(index, new Double(value)); + return this; + } + + /** + * Put or replace an int value. If the index is greater than the length of + * the JSONArray, then null elements will be added as necessary to pad it + * out. + * + * @param index + * The subscript. + * @param value + * An int value. + * @return this. + * @throws JSONException + * If the index is negative. + */ + public JSONArray put(int index, int value) throws JSONException { + this.put(index, new Integer(value)); + return this; + } + + /** + * Put or replace a long value. If the index is greater than the length of + * the JSONArray, then null elements will be added as necessary to pad it + * out. + * + * @param index + * The subscript. + * @param value + * A long value. + * @return this. + * @throws JSONException + * If the index is negative. + */ + public JSONArray put(int index, long value) throws JSONException { + this.put(index, new Long(value)); + return this; + } + + /** + * Put a value in the JSONArray, where the value will be a JSONObject that + * is produced from a Map. + * + * @param index + * The subscript. + * @param value + * The Map value. + * @return this. + * @throws JSONException + * If the index is negative or if the the value is an invalid + * number. + */ + public JSONArray put(int index, Map value) throws JSONException { + this.put(index, new JSONObject(value)); + return this; + } + + /** + * Put or replace an object value in the JSONArray. If the index is greater + * than the length of the JSONArray, then null elements will be added as + * necessary to pad it out. + * + * @param index + * The subscript. + * @param value + * The value to put into the array. The value should be a + * Boolean, Double, Integer, JSONArray, JSONObject, Long, or + * String, or the JSONObject.NULL object. + * @return this. + * @throws JSONException + * If the index is negative or if the the value is an invalid + * number. + */ + public JSONArray put(int index, Object value) throws JSONException { + JSONObject.testValidity(value); + if (index < 0) { + throw new JSONException("JSONArray[" + index + "] not found."); + } + if (index < this.length()) { + this.myArrayList.set(index, value); + } else { + while (index != this.length()) { + this.put(JSONObject.NULL); + } + this.put(value); + } + return this; + } + + /** + * Creates a JSONPointer using an initialization string and tries to + * match it to an item within this JSONArray. For example, given a + * JSONArray initialized with this document: + * 
+     * [
+     *     {"b":"c"}
+     * ]
+     *
+ * and this JSONPointer string: + * 
+     * "/0/b"
+     *
+ * Then this method will return the String "c" + * A JSONPointerException may be thrown from code called by this method. + * + * @param jsonPointer string that can be used to create a JSONPointer + * @return the item matched by the JSONPointer, otherwise null + */ + public Object query(String jsonPointer) { + return new JSONPointer(jsonPointer).queryFrom(this); + } + + /** + * Queries and returns a value from this object using {@code jsonPointer}, or + * returns null if the query fails due to a missing key. + * + * @param jsonPointer the string representation of the JSON pointer + * @return the queried value or {@code null} + * @throws IllegalArgumentException if {@code jsonPointer} has invalid syntax + */ + public Object optQuery(String jsonPointer) { + JSONPointer pointer = new JSONPointer(jsonPointer); + try { + return pointer.queryFrom(this); + } catch (JSONPointerException e) { + return null; + } + } + + /** + * Remove an index and close the hole. + * + * @param index + * The index of the element to be removed. + * @return The value that was associated with the index, or null if there + * was no value. + */ + public Object remove(int index) { + return index >= 0 && index < this.length() + ? this.myArrayList.remove(index) + : null; + } + + /** + * Determine if two JSONArrays are similar. + * They must contain similar sequences. + * + * @param other The other JSONArray + * @return true if they are equal + */ + public boolean similar(Object other) { + if (!(other instanceof JSONArray)) { + return false; + } + int len = this.length(); + if (len != ((JSONArray)other).length()) { + return false; + } + for (int i = 0; i < len; i += 1) { + Object valueThis = this.get(i); + Object valueOther = ((JSONArray)other).get(i); + if (valueThis instanceof JSONObject) { + if (!((JSONObject)valueThis).similar(valueOther)) { + return false; + } + } else if (valueThis instanceof JSONArray) { + if (!((JSONArray)valueThis).similar(valueOther)) { + return false; + } + } else if (!valueThis.equals(valueOther)) { + return false; + } + } + return true; + } + + /** + * Produce a JSONObject by combining a JSONArray of names with the values of + * this JSONArray. + * + * @param names + * A JSONArray containing a list of key strings. These will be + * paired with the values. + * @return A JSONObject, or null if there are no names or if this JSONArray + * has no values. + * @throws JSONException + * If any of the names are null. + */ + public JSONObject toJSONObject(JSONArray names) throws JSONException { + if (names == null || names.length() == 0 || this.length() == 0) { + return null; + } + JSONObject jo = new JSONObject(); + for (int i = 0; i < names.length(); i += 1) { + jo.put(names.getString(i), this.opt(i)); + } + return jo; + } + + /** + * Make a JSON text of this JSONArray. For compactness, no unnecessary + * whitespace is added. If it is not possible to produce a syntactically + * correct JSON text then null will be returned instead. This could occur if + * the array contains an invalid number. + *

+ * Warning: This method assumes that the data structure is acyclical. + * + * @return a printable, displayable, transmittable representation of the + * array. + */ + public String toString() { + try { + return this.toString(0); + } catch (Exception e) { + return null; + } + } + + /** + * Make a prettyprinted JSON text of this JSONArray. Warning: This method + * assumes that the data structure is acyclical. + * + * @param indentFactor + * The number of spaces to add to each level of indentation. + * @return a printable, displayable, transmittable representation of the + * object, beginning with [ (left + * bracket) and ending with ] + *  (right bracket). + * @throws JSONException + */ + public String toString(int indentFactor) throws JSONException { + StringWriter sw = new StringWriter(); + synchronized (sw.getBuffer()) { + return this.write(sw, indentFactor, 0).toString(); + } + } + + /** + * Write the contents of the JSONArray as JSON text to a writer. For + * compactness, no whitespace is added. + *

+ * Warning: This method assumes that the data structure is acyclical. + * + * @return The writer. + * @throws JSONException + */ + public Writer write(Writer writer) throws JSONException { + return this.write(writer, 0, 0); + } + + /** + * Write the contents of the JSONArray as JSON text to a writer. For + * compactness, no whitespace is added. + *

+ * Warning: This method assumes that the data structure is acyclical. + * + * @param writer + * Writes the serialized JSON + * @param indentFactor + * The number of spaces to add to each level of indentation. + * @param indent + * The indention of the top level. + * @return The writer. + * @throws JSONException + */ + public Writer write(Writer writer, int indentFactor, int indent) + throws JSONException { + try { + boolean commanate = false; + int length = this.length(); + writer.write('['); + + if (length == 1) { + JSONObject.writeValue(writer, this.myArrayList.get(0), + indentFactor, indent); + } else if (length != 0) { + final int newindent = indent + indentFactor; + + for (int i = 0; i < length; i += 1) { + if (commanate) { + writer.write(','); + } + if (indentFactor > 0) { + writer.write('\n'); + } + JSONObject.indent(writer, newindent); + JSONObject.writeValue(writer, this.myArrayList.get(i), + indentFactor, newindent); + commanate = true; + } + if (indentFactor > 0) { + writer.write('\n'); + } + JSONObject.indent(writer, indent); + } + writer.write(']'); + return writer; + } catch (IOException e) { + throw new JSONException(e); + } + } + + /** + * Returns a java.util.List containing all of the elements in this array. + * If an element in the array is a JSONArray or JSONObject it will also + * be converted. + *

+ * Warning: This method assumes that the data structure is acyclical. + * + * @return a java.util.List containing the elements of this array + */ + public List toList() { + List results = new ArrayList(this.myArrayList.size()); + for (Object element : this.myArrayList) { + if (element == null || JSONObject.NULL.equals(element)) { + results.add(null); + } else if (element instanceof JSONArray) { + results.add(((JSONArray) element).toList()); + } else if (element instanceof JSONObject) { + results.add(((JSONObject) element).toMap()); + } else { + results.add(element); + } + } + return results; + } +} diff --git a/d4dj/src/main/java/org/json/JSONException.java b/d4dj/src/main/java/org/json/JSONException.java new file mode 100644 index 0000000..72542df --- /dev/null +++ b/d4dj/src/main/java/org/json/JSONException.java @@ -0,0 +1,45 @@ +package org.json; + +/** + * The JSONException is thrown by the JSON.org classes when things are amiss. + * + * @author JSON.org + * @version 2015-12-09 + */ +public class JSONException extends RuntimeException { + /** Serialization ID */ + private static final long serialVersionUID = 0; + + /** + * Constructs a JSONException with an explanatory message. + * + * @param message + * Detail about the reason for the exception. + */ + public JSONException(final String message) { + super(message); + } + + /** + * Constructs a JSONException with an explanatory message and cause. + * + * @param message + * Detail about the reason for the exception. + * @param cause + * The cause. + */ + public JSONException(final String message, final Throwable cause) { + super(message, cause); + } + + /** + * Constructs a new JSONException with the specified cause. + * + * @param cause + * The cause. + */ + public JSONException(final Throwable cause) { + super(cause.getMessage(), cause); + } + +} diff --git a/d4dj/src/main/java/org/json/JSONML.java b/d4dj/src/main/java/org/json/JSONML.java new file mode 100644 index 0000000..82853a9 --- /dev/null +++ b/d4dj/src/main/java/org/json/JSONML.java @@ -0,0 +1,552 @@ +package org.json; + +/* +Copyright (c) 2008 JSON.org + +Permission is hereby granted, free of charge, to any person obtaining a copy +of this software and associated documentation files (the "Software"), to deal +in the Software without restriction, including without limitation the rights +to use, copy, modify, merge, publish, distribute, sublicense, and/or sell +copies of the Software, and to permit persons to whom the Software is +furnished to do so, subject to the following conditions: + +The above copyright notice and this permission notice shall be included in all +copies or substantial portions of the Software. + +The Software shall be used for Good, not Evil. + +THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR +IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, +FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE +AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER +LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, +OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE +SOFTWARE. +*/ + +import java.util.Iterator; + + +/** + * This provides static methods to convert an XML text into a JSONArray or + * JSONObject, and to covert a JSONArray or JSONObject into an XML text using + * the JsonML transform. + * + * @author JSON.org + * @version 2016-01-30 + */ +public class JSONML { + /** + * Parse XML values and store them in a JSONArray. + * @param x The XMLTokener containing the source string. + * @param arrayForm true if array form, false if object form. + * @param ja The JSONArray that is containing the current tag or null + * if we are at the outermost level. + * @param keepStrings Don't type-convert text nodes and attibute values + * @return A JSONArray if the value is the outermost tag, otherwise null. + * @throws JSONException + */ + private static Object parse( + XMLTokener x, + boolean arrayForm, + JSONArray ja, + boolean keepStrings + ) throws JSONException { + String attribute; + char c; + String closeTag = null; + int i; + JSONArray newja = null; + JSONObject newjo = null; + Object token; + String tagName = null; + +// Test for and skip past these forms: +// +// +// +// + + while (true) { + if (!x.more()) { + throw x.syntaxError("Bad XML"); + } + token = x.nextContent(); + if (token == XML.LT) { + token = x.nextToken(); + if (token instanceof Character) { + if (token == XML.SLASH) { + +// Close tag "); + } else { + x.back(); + } + } else if (c == '[') { + token = x.nextToken(); + if (token.equals("CDATA") && x.next() == '[') { + if (ja != null) { + ja.put(x.nextCDATA()); + } + } else { + throw x.syntaxError("Expected 'CDATA['"); + } + } else { + i = 1; + do { + token = x.nextMeta(); + if (token == null) { + throw x.syntaxError("Missing '>' after ' 0); + } + } else if (token == XML.QUEST) { + +// "); + } else { + throw x.syntaxError("Misshaped tag"); + } + +// Open tag < + + } else { + if (!(token instanceof String)) { + throw x.syntaxError("Bad tagName '" + token + "'."); + } + tagName = (String)token; + newja = new JSONArray(); + newjo = new JSONObject(); + if (arrayForm) { + newja.put(tagName); + if (ja != null) { + ja.put(newja); + } + } else { + newjo.put("tagName", tagName); + if (ja != null) { + ja.put(newjo); + } + } + token = null; + for (;;) { + if (token == null) { + token = x.nextToken(); + } + if (token == null) { + throw x.syntaxError("Misshaped tag"); + } + if (!(token instanceof String)) { + break; + } + +// attribute = value + + attribute = (String)token; + if (!arrayForm && ("tagName".equals(attribute) || "childNode".equals(attribute))) { + throw x.syntaxError("Reserved attribute."); + } + token = x.nextToken(); + if (token == XML.EQ) { + token = x.nextToken(); + if (!(token instanceof String)) { + throw x.syntaxError("Missing value"); + } + newjo.accumulate(attribute, keepStrings ? XML.unescape((String)token) :XML.stringToValue((String)token)); + token = null; + } else { + newjo.accumulate(attribute, ""); + } + } + if (arrayForm && newjo.length() > 0) { + newja.put(newjo); + } + +// Empty tag <.../> + + if (token == XML.SLASH) { + if (x.nextToken() != XML.GT) { + throw x.syntaxError("Misshaped tag"); + } + if (ja == null) { + if (arrayForm) { + return newja; + } + return newjo; + } + +// Content, between <...> and + + } else { + if (token != XML.GT) { + throw x.syntaxError("Misshaped tag"); + } + closeTag = (String)parse(x, arrayForm, newja, keepStrings); + if (closeTag != null) { + if (!closeTag.equals(tagName)) { + throw x.syntaxError("Mismatched '" + tagName + + "' and '" + closeTag + "'"); + } + tagName = null; + if (!arrayForm && newja.length() > 0) { + newjo.put("childNodes", newja); + } + if (ja == null) { + if (arrayForm) { + return newja; + } + return newjo; + } + } + } + } + } else { + if (ja != null) { + ja.put(token instanceof String + ? keepStrings ? XML.unescape((String)token) :XML.stringToValue((String)token) + : token); + } + } + } + } + + + /** + * Convert a well-formed (but not necessarily valid) XML string into a + * JSONArray using the JsonML transform. Each XML tag is represented as + * a JSONArray in which the first element is the tag name. If the tag has + * attributes, then the second element will be JSONObject containing the + * name/value pairs. If the tag contains children, then strings and + * JSONArrays will represent the child tags. + * Comments, prologs, DTDs, and <[ [ ]]> are ignored. + * @param string The source string. + * @return A JSONArray containing the structured data from the XML string. + * @throws JSONException Thrown on error converting to a JSONArray + */ + public static JSONArray toJSONArray(String string) throws JSONException { + return (JSONArray)parse(new XMLTokener(string), true, null, false); + } + + + /** + * Convert a well-formed (but not necessarily valid) XML string into a + * JSONArray using the JsonML transform. Each XML tag is represented as + * a JSONArray in which the first element is the tag name. If the tag has + * attributes, then the second element will be JSONObject containing the + * name/value pairs. If the tag contains children, then strings and + * JSONArrays will represent the child tags. + * As opposed to toJSONArray this method does not attempt to convert + * any text node or attribute value to any type + * but just leaves it as a string. + * Comments, prologs, DTDs, and <[ [ ]]> are ignored. + * @param string The source string. + * @param keepStrings If true, then values will not be coerced into boolean + * or numeric values and will instead be left as strings + * @return A JSONArray containing the structured data from the XML string. + * @throws JSONException Thrown on error converting to a JSONArray + */ + public static JSONArray toJSONArray(String string, boolean keepStrings) throws JSONException { + return (JSONArray)parse(new XMLTokener(string), true, null, keepStrings); + } + + + /** + * Convert a well-formed (but not necessarily valid) XML string into a + * JSONArray using the JsonML transform. Each XML tag is represented as + * a JSONArray in which the first element is the tag name. If the tag has + * attributes, then the second element will be JSONObject containing the + * name/value pairs. If the tag contains children, then strings and + * JSONArrays will represent the child content and tags. + * As opposed to toJSONArray this method does not attempt to convert + * any text node or attribute value to any type + * but just leaves it as a string. + * Comments, prologs, DTDs, and <[ [ ]]> are ignored. + * @param x An XMLTokener. + * @param keepStrings If true, then values will not be coerced into boolean + * or numeric values and will instead be left as strings + * @return A JSONArray containing the structured data from the XML string. + * @throws JSONException Thrown on error converting to a JSONArray + */ + public static JSONArray toJSONArray(XMLTokener x, boolean keepStrings) throws JSONException { + return (JSONArray)parse(x, true, null, keepStrings); + } + + + /** + * Convert a well-formed (but not necessarily valid) XML string into a + * JSONArray using the JsonML transform. Each XML tag is represented as + * a JSONArray in which the first element is the tag name. If the tag has + * attributes, then the second element will be JSONObject containing the + * name/value pairs. If the tag contains children, then strings and + * JSONArrays will represent the child content and tags. + * Comments, prologs, DTDs, and <[ [ ]]> are ignored. + * @param x An XMLTokener. + * @return A JSONArray containing the structured data from the XML string. + * @throws JSONException Thrown on error converting to a JSONArray + */ + public static JSONArray toJSONArray(XMLTokener x) throws JSONException { + return (JSONArray)parse(x, true, null, false); + } + + + /** + * Convert a well-formed (but not necessarily valid) XML string into a + * JSONObject using the JsonML transform. Each XML tag is represented as + * a JSONObject with a "tagName" property. If the tag has attributes, then + * the attributes will be in the JSONObject as properties. If the tag + * contains children, the object will have a "childNodes" property which + * will be an array of strings and JsonML JSONObjects. + + * Comments, prologs, DTDs, and <[ [ ]]> are ignored. + * @param string The XML source text. + * @return A JSONObject containing the structured data from the XML string. + * @throws JSONException Thrown on error converting to a JSONObject + */ + public static JSONObject toJSONObject(String string) throws JSONException { + return (JSONObject)parse(new XMLTokener(string), false, null, false); + } + + + /** + * Convert a well-formed (but not necessarily valid) XML string into a + * JSONObject using the JsonML transform. Each XML tag is represented as + * a JSONObject with a "tagName" property. If the tag has attributes, then + * the attributes will be in the JSONObject as properties. If the tag + * contains children, the object will have a "childNodes" property which + * will be an array of strings and JsonML JSONObjects. + + * Comments, prologs, DTDs, and <[ [ ]]> are ignored. + * @param string The XML source text. + * @param keepStrings If true, then values will not be coerced into boolean + * or numeric values and will instead be left as strings + * @return A JSONObject containing the structured data from the XML string. + * @throws JSONException Thrown on error converting to a JSONObject + */ + public static JSONObject toJSONObject(String string, boolean keepStrings) throws JSONException { + return (JSONObject)parse(new XMLTokener(string), false, null, keepStrings); + } + + + /** + * Convert a well-formed (but not necessarily valid) XML string into a + * JSONObject using the JsonML transform. Each XML tag is represented as + * a JSONObject with a "tagName" property. If the tag has attributes, then + * the attributes will be in the JSONObject as properties. If the tag + * contains children, the object will have a "childNodes" property which + * will be an array of strings and JsonML JSONObjects. + + * Comments, prologs, DTDs, and <[ [ ]]> are ignored. + * @param x An XMLTokener of the XML source text. + * @return A JSONObject containing the structured data from the XML string. + * @throws JSONException Thrown on error converting to a JSONObject + */ + public static JSONObject toJSONObject(XMLTokener x) throws JSONException { + return (JSONObject)parse(x, false, null, false); + } + + + /** + * Convert a well-formed (but not necessarily valid) XML string into a + * JSONObject using the JsonML transform. Each XML tag is represented as + * a JSONObject with a "tagName" property. If the tag has attributes, then + * the attributes will be in the JSONObject as properties. If the tag + * contains children, the object will have a "childNodes" property which + * will be an array of strings and JsonML JSONObjects. + + * Comments, prologs, DTDs, and <[ [ ]]> are ignored. + * @param x An XMLTokener of the XML source text. + * @param keepStrings If true, then values will not be coerced into boolean + * or numeric values and will instead be left as strings + * @return A JSONObject containing the structured data from the XML string. + * @throws JSONException Thrown on error converting to a JSONObject + */ + public static JSONObject toJSONObject(XMLTokener x, boolean keepStrings) throws JSONException { + return (JSONObject)parse(x, false, null, keepStrings); + } + + + /** + * Reverse the JSONML transformation, making an XML text from a JSONArray. + * @param ja A JSONArray. + * @return An XML string. + * @throws JSONException Thrown on error converting to a string + */ + public static String toString(JSONArray ja) throws JSONException { + int i; + JSONObject jo; + String key; + Iterator keys; + int length; + Object object; + StringBuilder sb = new StringBuilder(); + String tagName; + String value; + +// Emit = length) { + sb.append('/'); + sb.append('>'); + } else { + sb.append('>'); + do { + object = ja.get(i); + i += 1; + if (object != null) { + if (object instanceof String) { + sb.append(XML.escape(object.toString())); + } else if (object instanceof JSONObject) { + sb.append(toString((JSONObject)object)); + } else if (object instanceof JSONArray) { + sb.append(toString((JSONArray)object)); + } else { + sb.append(object.toString()); + } + } + } while (i < length); + sb.append('<'); + sb.append('/'); + sb.append(tagName); + sb.append('>'); + } + return sb.toString(); + } + + /** + * Reverse the JSONML transformation, making an XML text from a JSONObject. + * The JSONObject must contain a "tagName" property. If it has children, + * then it must have a "childNodes" property containing an array of objects. + * The other properties are attributes with string values. + * @param jo A JSONObject. + * @return An XML string. + * @throws JSONException Thrown on error converting to a string + */ + public static String toString(JSONObject jo) throws JSONException { + StringBuilder sb = new StringBuilder(); + int i; + JSONArray ja; + String key; + Iterator keys; + int length; + Object object; + String tagName; + String value; + +//Emit '); + } else { + sb.append('>'); + length = ja.length(); + for (i = 0; i < length; i += 1) { + object = ja.get(i); + if (object != null) { + if (object instanceof String) { + sb.append(XML.escape(object.toString())); + } else if (object instanceof JSONObject) { + sb.append(toString((JSONObject)object)); + } else if (object instanceof JSONArray) { + sb.append(toString((JSONArray)object)); + } else { + sb.append(object.toString()); + } + } + } + sb.append('<'); + sb.append('/'); + sb.append(tagName); + sb.append('>'); + } + return sb.toString(); + } +} diff --git a/d4dj/src/main/java/org/json/JSONObject.java b/d4dj/src/main/java/org/json/JSONObject.java new file mode 100644 index 0000000..1eab694 --- /dev/null +++ b/d4dj/src/main/java/org/json/JSONObject.java @@ -0,0 +1,1938 @@ +package org.json; + +/* + Copyright (c) 2002 JSON.org + + Permission is hereby granted, free of charge, to any person obtaining a copy + of this software and associated documentation files (the "Software"), to deal + in the Software without restriction, including without limitation the rights + to use, copy, modify, merge, publish, distribute, sublicense, and/or sell + copies of the Software, and to permit persons to whom the Software is + furnished to do so, subject to the following conditions: + + The above copyright notice and this permission notice shall be included in all + copies or substantial portions of the Software. + + The Software shall be used for Good, not Evil. + + THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE + AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER + LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, + OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE + SOFTWARE. + */ + +import java.io.IOException; +import java.io.StringWriter; +import java.io.Writer; +import java.lang.reflect.Field; +import java.lang.reflect.Method; +import java.lang.reflect.Modifier; +import java.math.BigDecimal; +import java.math.BigInteger; +import java.util.Collection; +import java.util.Enumeration; +import java.util.HashMap; +import java.util.Iterator; +import java.util.Locale; +import java.util.Map; +import java.util.Map.Entry; +import java.util.ResourceBundle; +import java.util.Set; + +/** + * A JSONObject is an unordered collection of name/value pairs. Its external + * form is a string wrapped in curly braces with colons between the names and + * values, and commas between the values and names. The internal form is an + * object having get and opt methods for accessing + * the values by name, and put methods for adding or replacing + * values by name. The values can be any of these types: Boolean, + * JSONArray, JSONObject, Number, + * String, or the JSONObject.NULL object. A + * JSONObject constructor can be used to convert an external form JSON text + * into an internal form whose values can be retrieved with the + * get and opt methods, or to convert values into a + * JSON text using the put and toString methods. A + * get method returns a value if one can be found, and throws an + * exception if one cannot be found. An opt method returns a + * default value instead of throwing an exception, and so is useful for + * obtaining optional values. + *

+ * The generic get() and opt() methods return an + * object, which you can cast or query for type. There are also typed + * get and opt methods that do type checking and type + * coercion for you. The opt methods differ from the get methods in that they + * do not throw. Instead, they return a specified value, such as null. + *

+ * The put methods add or replace values in an object. For + * example, + * + * 

+ * myString = new JSONObject()
+ *         .put("JSON", "Hello, World!").toString();
+ *
+ * + * produces the string {"JSON": "Hello, World"}. + *

+ * The texts produced by the toString methods strictly conform to + * the JSON syntax rules. The constructors are more forgiving in the texts they + * will accept: + *

    + *
  • An extra , (comma) may appear just + * before the closing brace.
    • + *
  • Strings may be quoted with ' (single + * quote).
    • + *
  • Strings do not need to be quoted at all if they do not begin with a + * quote or single quote, and if they do not contain leading or trailing + * spaces, and if they do not contain any of these characters: + * { } [ ] / \ : , # and if they do not look like numbers and + * if they are not the reserved words true, false, + * or null.
    • + *
+ * + * @author JSON.org + * @version 2016-08-15 + */ +public class JSONObject { + /** + * JSONObject.NULL is equivalent to the value that JavaScript calls null, + * whilst Java's null is equivalent to the value that JavaScript calls + * undefined. + */ + private static final class Null { + + /** + * There is only intended to be a single instance of the NULL object, + * so the clone method returns itself. + * + * @return NULL. + */ + @Override + protected final Object clone() { + return this; + } + + /** + * A Null object is equal to the null value and to itself. + * + * @param object + * An object to test for nullness. + * @return true if the object parameter is the JSONObject.NULL object or + * null. + */ + @Override + public boolean equals(Object object) { + return object == null || object == this; + } + + /** + * Get the "null" string value. + * + * @return The string "null". + */ + @Override + public String toString() { + return "null"; + } + } + + /** + * The map where the JSONObject's properties are kept. + */ + private final Map map; + + /** + * It is sometimes more convenient and less ambiguous to have a + * NULL object than to use Java's null value. + * JSONObject.NULL.equals(null) returns true. + * JSONObject.NULL.toString() returns "null". + */ + public static final Object NULL = new Null(); + + /** + * Construct an empty JSONObject. + */ + public JSONObject() { + this.map = new HashMap(); + } + + /** + * Construct a JSONObject from a subset of another JSONObject. An array of + * strings is used to identify the keys that should be copied. Missing keys + * are ignored. + * + * @param jo + * A JSONObject. + * @param names + * An array of strings. + */ + public JSONObject(JSONObject jo, String[] names) { + this(); + for (int i = 0; i < names.length; i += 1) { + try { + this.putOnce(names[i], jo.opt(names[i])); + } catch (Exception ignore) { + } + } + } + + /** + * Construct a JSONObject from a JSONTokener. + * + * @param x + * A JSONTokener object containing the source string. + * @throws JSONException + * If there is a syntax error in the source string or a + * duplicated key. + */ + public JSONObject(JSONTokener x) throws JSONException { + this(); + char c; + String key; + + if (x.nextClean() != '{') { + throw x.syntaxError("A JSONObject text must begin with '{'"); + } + for (;;) { + c = x.nextClean(); + switch (c) { + case 0: + throw x.syntaxError("A JSONObject text must end with '}'"); + case '}': + return; + default: + x.back(); + key = x.nextValue().toString(); + } + +// The key is followed by ':'. + + c = x.nextClean(); + if (c != ':') { + throw x.syntaxError("Expected a ':' after a key"); + } + this.putOnce(key, x.nextValue()); + +// Pairs are separated by ','. + + switch (x.nextClean()) { + case ';': + case ',': + if (x.nextClean() == '}') { + return; + } + x.back(); + break; + case '}': + return; + default: + throw x.syntaxError("Expected a ',' or '}'"); + } + } + } + + /** + * Construct a JSONObject from a Map. + * + * @param map + * A map object that can be used to initialize the contents of + * the JSONObject. + */ + public JSONObject(Map map) { + this.map = new HashMap(); + if (map != null) { + for (final Entry e : map.entrySet()) { + final Object value = e.getValue(); + if (value != null) { + this.map.put(String.valueOf(e.getKey()), wrap(value)); + } + } + } + } + + /** + * Construct a JSONObject from an Object using bean getters. It reflects on + * all of the public methods of the object. For each of the methods with no + * parameters and a name starting with "get" or + * "is" followed by an uppercase letter, the method is invoked, + * and a key and the value returned from the getter method are put into the + * new JSONObject. + * + * The key is formed by removing the "get" or "is" + * prefix. If the second remaining character is not upper case, then the + * first character is converted to lower case. + * + * For example, if an object has a method named "getName", and + * if the result of calling object.getName() is + * "Larry Fine", then the JSONObject will contain + * "name": "Larry Fine". + * + * @param bean + * An object that has getter methods that should be used to make + * a JSONObject. + */ + public JSONObject(Object bean) { + this(); + this.populateMap(bean); + } + + /** + * Construct a JSONObject from an Object, using reflection to find the + * public members. The resulting JSONObject's keys will be the strings from + * the names array, and the values will be the field values associated with + * those keys in the object. If a key is not found or not visible, then it + * will not be copied into the new JSONObject. + * + * @param object + * An object that has fields that should be used to make a + * JSONObject. + * @param names + * An array of strings, the names of the fields to be obtained + * from the object. + */ + public JSONObject(Object object, String names[]) { + this(); + Class c = object.getClass(); + for (int i = 0; i < names.length; i += 1) { + String name = names[i]; + try { + this.putOpt(name, c.getField(name).get(object)); + } catch (Exception ignore) { + } + } + } + + /** + * Construct a JSONObject from a source JSON text string. This is the most + * commonly used JSONObject constructor. + * + * @param source + * A string beginning with { (left + * brace) and ending with } + *  (right brace). + * @exception JSONException + * If there is a syntax error in the source string or a + * duplicated key. + */ + public JSONObject(String source) throws JSONException { + this(new JSONTokener(source)); + } + + /** + * Construct a JSONObject from a ResourceBundle. + * + * @param baseName + * The ResourceBundle base name. + * @param locale + * The Locale to load the ResourceBundle for. + * @throws JSONException + * If any JSONExceptions are detected. + */ + public JSONObject(String baseName, Locale locale) throws JSONException { + this(); + ResourceBundle bundle = ResourceBundle.getBundle(baseName, locale, + Thread.currentThread().getContextClassLoader()); + +// Iterate through the keys in the bundle. + + Enumeration keys = bundle.getKeys(); + while (keys.hasMoreElements()) { + Object key = keys.nextElement(); + if (key != null) { + +// Go through the path, ensuring that there is a nested JSONObject for each +// segment except the last. Add the value using the last segment's name into +// the deepest nested JSONObject. + + String[] path = ((String) key).split("\\."); + int last = path.length - 1; + JSONObject target = this; + for (int i = 0; i < last; i += 1) { + String segment = path[i]; + JSONObject nextTarget = target.optJSONObject(segment); + if (nextTarget == null) { + nextTarget = new JSONObject(); + target.put(segment, nextTarget); + } + target = nextTarget; + } + target.put(path[last], bundle.getString((String) key)); + } + } + } + + /** + * Accumulate values under a key. It is similar to the put method except + * that if there is already an object stored under the key then a JSONArray + * is stored under the key to hold all of the accumulated values. If there + * is already a JSONArray, then the new value is appended to it. In + * contrast, the put method replaces the previous value. + * + * If only one value is accumulated that is not a JSONArray, then the result + * will be the same as using put. But if multiple values are accumulated, + * then the result will be like append. + * + * @param key + * A key string. + * @param value + * An object to be accumulated under the key. + * @return this. + * @throws JSONException + * If the value is an invalid number or if the key is null. + */ + public JSONObject accumulate(String key, Object value) throws JSONException { + testValidity(value); + Object object = this.opt(key); + if (object == null) { + this.put(key, + value instanceof JSONArray ? new JSONArray().put(value) + : value); + } else if (object instanceof JSONArray) { + ((JSONArray) object).put(value); + } else { + this.put(key, new JSONArray().put(object).put(value)); + } + return this; + } + + /** + * Append values to the array under a key. If the key does not exist in the + * JSONObject, then the key is put in the JSONObject with its value being a + * JSONArray containing the value parameter. If the key was already + * associated with a JSONArray, then the value parameter is appended to it. + * + * @param key + * A key string. + * @param value + * An object to be accumulated under the key. + * @return this. + * @throws JSONException + * If the key is null or if the current value associated with + * the key is not a JSONArray. + */ + public JSONObject append(String key, Object value) throws JSONException { + testValidity(value); + Object object = this.opt(key); + if (object == null) { + this.put(key, new JSONArray().put(value)); + } else if (object instanceof JSONArray) { + this.put(key, ((JSONArray) object).put(value)); + } else { + throw new JSONException("JSONObject[" + key + + "] is not a JSONArray."); + } + return this; + } + + /** + * Produce a string from a double. The string "null" will be returned if the + * number is not finite. + * + * @param d + * A double. + * @return A String. + */ + public static String doubleToString(double d) { + if (Double.isInfinite(d) || Double.isNaN(d)) { + return "null"; + } + +// Shave off trailing zeros and decimal point, if possible. + + String string = Double.toString(d); + if (string.indexOf('.') > 0 && string.indexOf('e') < 0 + && string.indexOf('E') < 0) { + while (string.endsWith("0")) { + string = string.substring(0, string.length() - 1); + } + if (string.endsWith(".")) { + string = string.substring(0, string.length() - 1); + } + } + return string; + } + + /** + * Get the value object associated with a key. + * + * @param key + * A key string. + * @return The object associated with the key. + * @throws JSONException + * if the key is not found. + */ + public Object get(String key) throws JSONException { + if (key == null) { + throw new JSONException("Null key."); + } + Object object = this.opt(key); + if (object == null) { + throw new JSONException("JSONObject[" + quote(key) + "] not found."); + } + return object; + } + + /** + * Get the enum value associated with a key. + * + * @param clazz + * The type of enum to retrieve. + * @param key + * A key string. + * @return The enum value associated with the key + * @throws JSONException + * if the key is not found or if the value cannot be converted + * to an enum. + */ + public > E getEnum(Class clazz, String key) throws JSONException { + E val = optEnum(clazz, key); + if(val==null) { + // JSONException should really take a throwable argument. + // If it did, I would re-implement this with the Enum.valueOf + // method and place any thrown exception in the JSONException + throw new JSONException("JSONObject[" + quote(key) + + "] is not an enum of type " + quote(clazz.getSimpleName()) + + "."); + } + return val; + } + + /** + * Get the boolean value associated with a key. + * + * @param key + * A key string. + * @return The truth. + * @throws JSONException + * if the value is not a Boolean or the String "true" or + * "false". + */ + public boolean getBoolean(String key) throws JSONException { + Object object = this.get(key); + if (object.equals(Boolean.FALSE) + || (object instanceof String && ((String) object) + .equalsIgnoreCase("false"))) { + return false; + } else if (object.equals(Boolean.TRUE) + || (object instanceof String && ((String) object) + .equalsIgnoreCase("true"))) { + return true; + } + throw new JSONException("JSONObject[" + quote(key) + + "] is not a Boolean."); + } + + /** + * Get the BigInteger value associated with a key. + * + * @param key + * A key string. + * @return The numeric value. + * @throws JSONException + * if the key is not found or if the value cannot + * be converted to BigInteger. + */ + public BigInteger getBigInteger(String key) throws JSONException { + Object object = this.get(key); + try { + return new BigInteger(object.toString()); + } catch (Exception e) { + throw new JSONException("JSONObject[" + quote(key) + + "] could not be converted to BigInteger."); + } + } + + /** + * Get the BigDecimal value associated with a key. + * + * @param key + * A key string. + * @return The numeric value. + * @throws JSONException + * if the key is not found or if the value + * cannot be converted to BigDecimal. + */ + public BigDecimal getBigDecimal(String key) throws JSONException { + Object object = this.get(key); + try { + return new BigDecimal(object.toString()); + } catch (Exception e) { + throw new JSONException("JSONObject[" + quote(key) + + "] could not be converted to BigDecimal."); + } + } + + /** + * Get the double value associated with a key. + * + * @param key + * A key string. + * @return The numeric value. + * @throws JSONException + * if the key is not found or if the value is not a Number + * object and cannot be converted to a number. + */ + public double getDouble(String key) throws JSONException { + Object object = this.get(key); + try { + return object instanceof Number ? ((Number) object).doubleValue() + : Double.parseDouble((String) object); + } catch (Exception e) { + throw new JSONException("JSONObject[" + quote(key) + + "] is not a number."); + } + } + + /** + * Get the int value associated with a key. + * + * @param key + * A key string. + * @return The integer value. + * @throws JSONException + * if the key is not found or if the value cannot be converted + * to an integer. + */ + public int getInt(String key) throws JSONException { + Object object = this.get(key); + try { + return object instanceof Number ? ((Number) object).intValue() + : Integer.parseInt((String) object); + } catch (Exception e) { + throw new JSONException("JSONObject[" + quote(key) + + "] is not an int."); + } + } + + /** + * Get the JSONArray value associated with a key. + * + * @param key + * A key string. + * @return A JSONArray which is the value. + * @throws JSONException + * if the key is not found or if the value is not a JSONArray. + */ + public JSONArray getJSONArray(String key) throws JSONException { + Object object = this.get(key); + if (object instanceof JSONArray) { + return (JSONArray) object; + } + throw new JSONException("JSONObject[" + quote(key) + + "] is not a JSONArray."); + } + + /** + * Get the JSONObject value associated with a key. + * + * @param key + * A key string. + * @return A JSONObject which is the value. + * @throws JSONException + * if the key is not found or if the value is not a JSONObject. + */ + public JSONObject getJSONObject(String key) throws JSONException { + Object object = this.get(key); + if (object instanceof JSONObject) { + return (JSONObject) object; + } + throw new JSONException("JSONObject[" + quote(key) + + "] is not a JSONObject."); + } + + /** + * Get the long value associated with a key. + * + * @param key + * A key string. + * @return The long value. + * @throws JSONException + * if the key is not found or if the value cannot be converted + * to a long. + */ + public long getLong(String key) throws JSONException { + Object object = this.get(key); + try { + return object instanceof Number ? ((Number) object).longValue() + : Long.parseLong((String) object); + } catch (Exception e) { + throw new JSONException("JSONObject[" + quote(key) + + "] is not a long."); + } + } + + /** + * Get an array of field names from a JSONObject. + * + * @return An array of field names, or null if there are no names. + */ + public static String[] getNames(JSONObject jo) { + int length = jo.length(); + if (length == 0) { + return null; + } + Iterator iterator = jo.keys(); + String[] names = new String[length]; + int i = 0; + while (iterator.hasNext()) { + names[i] = iterator.next(); + i += 1; + } + return names; + } + + /** + * Get an array of field names from an Object. + * + * @return An array of field names, or null if there are no names. + */ + public static String[] getNames(Object object) { + if (object == null) { + return null; + } + Class klass = object.getClass(); + Field[] fields = klass.getFields(); + int length = fields.length; + if (length == 0) { + return null; + } + String[] names = new String[length]; + for (int i = 0; i < length; i += 1) { + names[i] = fields[i].getName(); + } + return names; + } + + /** + * Get the string associated with a key. + * + * @param key + * A key string. + * @return A string which is the value. + * @throws JSONException + * if there is no string value for the key. + */ + public String getString(String key) throws JSONException { + Object object = this.get(key); + if (object instanceof String) { + return (String) object; + } + throw new JSONException("JSONObject[" + quote(key) + "] not a string."); + } + + /** + * Determine if the JSONObject contains a specific key. + * + * @param key + * A key string. + * @return true if the key exists in the JSONObject. + */ + public boolean has(String key) { + return this.map.containsKey(key); + } + + /** + * Increment a property of a JSONObject. If there is no such property, + * create one with a value of 1. If there is such a property, and if it is + * an Integer, Long, Double, or Float, then add one to it. + * + * @param key + * A key string. + * @return this. + * @throws JSONException + * If there is already a property with this name that is not an + * Integer, Long, Double, or Float. + */ + public JSONObject increment(String key) throws JSONException { + Object value = this.opt(key); + if (value == null) { + this.put(key, 1); + } else if (value instanceof BigInteger) { + this.put(key, ((BigInteger)value).add(BigInteger.ONE)); + } else if (value instanceof BigDecimal) { + this.put(key, ((BigDecimal)value).add(BigDecimal.ONE)); + } else if (value instanceof Integer) { + this.put(key, (Integer) value + 1); + } else if (value instanceof Long) { + this.put(key, (Long) value + 1); + } else if (value instanceof Double) { + this.put(key, (Double) value + 1); + } else if (value instanceof Float) { + this.put(key, (Float) value + 1); + } else { + throw new JSONException("Unable to increment [" + quote(key) + "]."); + } + return this; + } + + /** + * Determine if the value associated with the key is null or if there is no + * value. + * + * @param key + * A key string. + * @return true if there is no value associated with the key or if the value + * is the JSONObject.NULL object. + */ + public boolean isNull(String key) { + return JSONObject.NULL.equals(this.opt(key)); + } + + /** + * Get an enumeration of the keys of the JSONObject. + * + * @return An iterator of the keys. + */ + public Iterator keys() { + return this.keySet().iterator(); + } + + /** + * Get a set of keys of the JSONObject. + * + * @return A keySet. + */ + public Set keySet() { + return this.map.keySet(); + } + + /** + * Get the number of keys stored in the JSONObject. + * + * @return The number of keys in the JSONObject. + */ + public int length() { + return this.map.size(); + } + + /** + * Produce a JSONArray containing the names of the elements of this + * JSONObject. + * + * @return A JSONArray containing the key strings, or null if the JSONObject + * is empty. + */ + public JSONArray names() { + JSONArray ja = new JSONArray(); + Iterator keys = this.keys(); + while (keys.hasNext()) { + ja.put(keys.next()); + } + return ja.length() == 0 ? null : ja; + } + + /** + * Produce a string from a Number. + * + * @param number + * A Number + * @return A String. + * @throws JSONException + * If n is a non-finite number. + */ + public static String numberToString(Number number) throws JSONException { + if (number == null) { + throw new JSONException("Null pointer"); + } + testValidity(number); + + // Shave off trailing zeros and decimal point, if possible. + + String string = number.toString(); + if (string.indexOf('.') > 0 && string.indexOf('e') < 0 + && string.indexOf('E') < 0) { + while (string.endsWith("0")) { + string = string.substring(0, string.length() - 1); + } + if (string.endsWith(".")) { + string = string.substring(0, string.length() - 1); + } + } + return string; + } + + /** + * Get an optional value associated with a key. + * + * @param key + * A key string. + * @return An object which is the value, or null if there is no value. + */ + public Object opt(String key) { + return key == null ? null : this.map.get(key); + } + + /** + * Get the enum value associated with a key. + * + * @param clazz + * The type of enum to retrieve. + * @param key + * A key string. + * @return The enum value associated with the key or null if not found + */ + public > E optEnum(Class clazz, String key) { + return this.optEnum(clazz, key, null); + } + + /** + * Get the enum value associated with a key. + * + * @param clazz + * The type of enum to retrieve. + * @param key + * A key string. + * @param defaultValue + * The default in case the value is not found + * @return The enum value associated with the key or defaultValue + * if the value is not found or cannot be assigned to clazz + */ + public > E optEnum(Class clazz, String key, E defaultValue) { + try { + Object val = this.opt(key); + if (NULL.equals(val)) { + return defaultValue; + } + if (clazz.isAssignableFrom(val.getClass())) { + // we just checked it! + @SuppressWarnings("unchecked") + E myE = (E) val; + return myE; + } + return Enum.valueOf(clazz, val.toString()); + } catch (IllegalArgumentException e) { + return defaultValue; + } catch (NullPointerException e) { + return defaultValue; + } + } + + /** + * Get an optional boolean associated with a key. It returns false if there + * is no such key, or if the value is not Boolean.TRUE or the String "true". + * + * @param key + * A key string. + * @return The truth. + */ + public boolean optBoolean(String key) { + return this.optBoolean(key, false); + } + + /** + * Get an optional boolean associated with a key. It returns the + * defaultValue if there is no such key, or if it is not a Boolean or the + * String "true" or "false" (case insensitive). + * + * @param key + * A key string. + * @param defaultValue + * The default. + * @return The truth. + */ + public boolean optBoolean(String key, boolean defaultValue) { + try { + return this.getBoolean(key); + } catch (Exception e) { + return defaultValue; + } + } + + /** + * Get an optional double associated with a key, or NaN if there is no such + * key or if its value is not a number. If the value is a string, an attempt + * will be made to evaluate it as a number. + * + * @param key + * A string which is the key. + * @return An object which is the value. + */ + public double optDouble(String key) { + return this.optDouble(key, Double.NaN); + } + + /** + * Get an optional BigInteger associated with a key, or the defaultValue if + * there is no such key or if its value is not a number. If the value is a + * string, an attempt will be made to evaluate it as a number. + * + * @param key + * A key string. + * @param defaultValue + * The default. + * @return An object which is the value. + */ + public BigInteger optBigInteger(String key, BigInteger defaultValue) { + try { + return this.getBigInteger(key); + } catch (Exception e) { + return defaultValue; + } + } + + /** + * Get an optional BigDecimal associated with a key, or the defaultValue if + * there is no such key or if its value is not a number. If the value is a + * string, an attempt will be made to evaluate it as a number. + * + * @param key + * A key string. + * @param defaultValue + * The default. + * @return An object which is the value. + */ + public BigDecimal optBigDecimal(String key, BigDecimal defaultValue) { + try { + return this.getBigDecimal(key); + } catch (Exception e) { + return defaultValue; + } + } + + /** + * Get an optional double associated with a key, or the defaultValue if + * there is no such key or if its value is not a number. If the value is a + * string, an attempt will be made to evaluate it as a number. + * + * @param key + * A key string. + * @param defaultValue + * The default. + * @return An object which is the value. + */ + public double optDouble(String key, double defaultValue) { + try { + return this.getDouble(key); + } catch (Exception e) { + return defaultValue; + } + } + + /** + * Get an optional int value associated with a key, or zero if there is no + * such key or if the value is not a number. If the value is a string, an + * attempt will be made to evaluate it as a number. + * + * @param key + * A key string. + * @return An object which is the value. + */ + public int optInt(String key) { + return this.optInt(key, 0); + } + + /** + * Get an optional int value associated with a key, or the default if there + * is no such key or if the value is not a number. If the value is a string, + * an attempt will be made to evaluate it as a number. + * + * @param key + * A key string. + * @param defaultValue + * The default. + * @return An object which is the value. + */ + public int optInt(String key, int defaultValue) { + try { + return this.getInt(key); + } catch (Exception e) { + return defaultValue; + } + } + + /** + * Get an optional JSONArray associated with a key. It returns null if there + * is no such key, or if its value is not a JSONArray. + * + * @param key + * A key string. + * @return A JSONArray which is the value. + */ + public JSONArray optJSONArray(String key) { + Object o = this.opt(key); + return o instanceof JSONArray ? (JSONArray) o : null; + } + + /** + * Get an optional JSONObject associated with a key. It returns null if + * there is no such key, or if its value is not a JSONObject. + * + * @param key + * A key string. + * @return A JSONObject which is the value. + */ + public JSONObject optJSONObject(String key) { + Object object = this.opt(key); + return object instanceof JSONObject ? (JSONObject) object : null; + } + + /** + * Get an optional long value associated with a key, or zero if there is no + * such key or if the value is not a number. If the value is a string, an + * attempt will be made to evaluate it as a number. + * + * @param key + * A key string. + * @return An object which is the value. + */ + public long optLong(String key) { + return this.optLong(key, 0); + } + + /** + * Get an optional long value associated with a key, or the default if there + * is no such key or if the value is not a number. If the value is a string, + * an attempt will be made to evaluate it as a number. + * + * @param key + * A key string. + * @param defaultValue + * The default. + * @return An object which is the value. + */ + public long optLong(String key, long defaultValue) { + try { + return this.getLong(key); + } catch (Exception e) { + return defaultValue; + } + } + + /** + * Get an optional string associated with a key. It returns an empty string + * if there is no such key. If the value is not a string and is not null, + * then it is converted to a string. + * + * @param key + * A key string. + * @return A string which is the value. + */ + public String optString(String key) { + return this.optString(key, ""); + } + + /** + * Get an optional string associated with a key. It returns the defaultValue + * if there is no such key. + * + * @param key + * A key string. + * @param defaultValue + * The default. + * @return A string which is the value. + */ + public String optString(String key, String defaultValue) { + Object object = this.opt(key); + return NULL.equals(object) ? defaultValue : object.toString(); + } + + private void populateMap(Object bean) { + Class klass = bean.getClass(); + +// If klass is a System class then set includeSuperClass to false. + + boolean includeSuperClass = klass.getClassLoader() != null; + + Method[] methods = includeSuperClass ? klass.getMethods() : klass + .getDeclaredMethods(); + for (int i = 0; i < methods.length; i += 1) { + try { + Method method = methods[i]; + if (Modifier.isPublic(method.getModifiers())) { + String name = method.getName(); + String key = ""; + if (name.startsWith("get")) { + if ("getClass".equals(name) + || "getDeclaringClass".equals(name)) { + key = ""; + } else { + key = name.substring(3); + } + } else if (name.startsWith("is")) { + key = name.substring(2); + } + if (key.length() > 0 + && Character.isUpperCase(key.charAt(0)) + && method.getParameterTypes().length == 0) { + if (key.length() == 1) { + key = key.toLowerCase(Locale.ROOT); + } else if (!Character.isUpperCase(key.charAt(1))) { + key = key.substring(0, 1).toLowerCase(Locale.ROOT) + + key.substring(1); + } + + Object result = method.invoke(bean, (Object[]) null); + if (result != null) { + this.map.put(key, wrap(result)); + } + } + } + } catch (Exception ignore) { + } + } + } + + /** + * Put a key/boolean pair in the JSONObject. + * + * @param key + * A key string. + * @param value + * A boolean which is the value. + * @return this. + * @throws JSONException + * If the key is null. + */ + public JSONObject put(String key, boolean value) throws JSONException { + this.put(key, value ? Boolean.TRUE : Boolean.FALSE); + return this; + } + + /** + * Put a key/value pair in the JSONObject, where the value will be a + * JSONArray which is produced from a Collection. + * + * @param key + * A key string. + * @param value + * A Collection value. + * @return this. + * @throws JSONException + */ + public JSONObject put(String key, Collection value) throws JSONException { + this.put(key, new JSONArray(value)); + return this; + } + + /** + * Put a key/double pair in the JSONObject. + * + * @param key + * A key string. + * @param value + * A double which is the value. + * @return this. + * @throws JSONException + * If the key is null or if the number is invalid. + */ + public JSONObject put(String key, double value) throws JSONException { + this.put(key, new Double(value)); + return this; + } + + /** + * Put a key/int pair in the JSONObject. + * + * @param key + * A key string. + * @param value + * An int which is the value. + * @return this. + * @throws JSONException + * If the key is null. + */ + public JSONObject put(String key, int value) throws JSONException { + this.put(key, new Integer(value)); + return this; + } + + /** + * Put a key/long pair in the JSONObject. + * + * @param key + * A key string. + * @param value + * A long which is the value. + * @return this. + * @throws JSONException + * If the key is null. + */ + public JSONObject put(String key, long value) throws JSONException { + this.put(key, new Long(value)); + return this; + } + + /** + * Put a key/value pair in the JSONObject, where the value will be a + * JSONObject which is produced from a Map. + * + * @param key + * A key string. + * @param value + * A Map value. + * @return this. + * @throws JSONException + */ + public JSONObject put(String key, Map value) throws JSONException { + this.put(key, new JSONObject(value)); + return this; + } + + /** + * Put a key/value pair in the JSONObject. If the value is null, then the + * key will be removed from the JSONObject if it is present. + * + * @param key + * A key string. + * @param value + * An object which is the value. It should be of one of these + * types: Boolean, Double, Integer, JSONArray, JSONObject, Long, + * String, or the JSONObject.NULL object. + * @return this. + * @throws JSONException + * If the value is non-finite number or if the key is null. + */ + public JSONObject put(String key, Object value) throws JSONException { + if (key == null) { + throw new NullPointerException("Null key."); + } + if (value != null) { + testValidity(value); + this.map.put(key, value); + } else { + this.remove(key); + } + return this; + } + + /** + * Put a key/value pair in the JSONObject, but only if the key and the value + * are both non-null, and only if there is not already a member with that + * name. + * + * @param key string + * @param value object + * @return this. + * @throws JSONException + * if the key is a duplicate + */ + public JSONObject putOnce(String key, Object value) throws JSONException { + if (key != null && value != null) { + if (this.opt(key) != null) { + throw new JSONException("Duplicate key \"" + key + "\""); + } + this.put(key, value); + } + return this; + } + + /** + * Put a key/value pair in the JSONObject, but only if the key and the value + * are both non-null. + * + * @param key + * A key string. + * @param value + * An object which is the value. It should be of one of these + * types: Boolean, Double, Integer, JSONArray, JSONObject, Long, + * String, or the JSONObject.NULL object. + * @return this. + * @throws JSONException + * If the value is a non-finite number. + */ + public JSONObject putOpt(String key, Object value) throws JSONException { + if (key != null && value != null) { + this.put(key, value); + } + return this; + } + + /** + * Creates a JSONPointer using an intialization string and tries to + * match it to an item within this JSONObject. For example, given a + * JSONObject initialized with this document: + * 
+     * {
+     *     "a":{"b":"c"}
+     * }
+     *
+ * and this JSONPointer string: + * 
+     * "/a/b"
+     *
+ * Then this method will return the String "c". + * A JSONPointerException may be thrown from code called by this method. + * + * @param jsonPointer string that can be used to create a JSONPointer + * @return the item matched by the JSONPointer, otherwise null + */ + public Object query(String jsonPointer) { + return new JSONPointer(jsonPointer).queryFrom(this); + } + + /** + * Queries and returns a value from this object using {@code jsonPointer}, or + * returns null if the query fails due to a missing key. + * + * @param jsonPointer the string representation of the JSON pointer + * @return the queried value or {@code null} + * @throws IllegalArgumentException if {@code jsonPointer} has invalid syntax + */ + public Object optQuery(String jsonPointer) { + JSONPointer pointer = new JSONPointer(jsonPointer); + try { + return pointer.queryFrom(this); + } catch (JSONPointerException e) { + return null; + } + } + + /** + * Produce a string in double quotes with backslash sequences in all the + * right places. A backslash will be inserted within = '\u0080' && c < '\u00a0') + || (c >= '\u2000' && c < '\u2100')) { + w.write("\\u"); + hhhh = Integer.toHexString(c); + w.write("0000", 0, 4 - hhhh.length()); + w.write(hhhh); + } else { + w.write(c); + } + } + } + w.write('"'); + return w; + } + + /** + * Remove a name and its value, if present. + * + * @param key + * The name to be removed. + * @return The value that was associated with the name, or null if there was + * no value. + */ + public Object remove(String key) { + return this.map.remove(key); + } + + /** + * Determine if two JSONObjects are similar. + * They must contain the same set of names which must be associated with + * similar values. + * + * @param other The other JSONObject + * @return true if they are equal + */ + public boolean similar(Object other) { + try { + if (!(other instanceof JSONObject)) { + return false; + } + Set set = this.keySet(); + if (!set.equals(((JSONObject)other).keySet())) { + return false; + } + Iterator iterator = set.iterator(); + while (iterator.hasNext()) { + String name = iterator.next(); + Object valueThis = this.get(name); + Object valueOther = ((JSONObject)other).get(name); + if (valueThis instanceof JSONObject) { + if (!((JSONObject)valueThis).similar(valueOther)) { + return false; + } + } else if (valueThis instanceof JSONArray) { + if (!((JSONArray)valueThis).similar(valueOther)) { + return false; + } + } else if (!valueThis.equals(valueOther)) { + return false; + } + } + return true; + } catch (Throwable exception) { + return false; + } + } + + /** + * Try to convert a string into a number, boolean, or null. If the string + * can't be converted, return the string. + * + * @param string + * A String. + * @return A simple JSON value. + */ + public static Object stringToValue(String string) { + if (string.equals("")) { + return string; + } + if (string.equalsIgnoreCase("true")) { + return Boolean.TRUE; + } + if (string.equalsIgnoreCase("false")) { + return Boolean.FALSE; + } + if (string.equalsIgnoreCase("null")) { + return JSONObject.NULL; + } + + /* + * If it might be a number, try converting it. If a number cannot be + * produced, then the value will just be a string. + */ + + char initial = string.charAt(0); + if ((initial >= '0' && initial <= '9') || initial == '-') { + try { + if (string.indexOf('.') > -1 || string.indexOf('e') > -1 + || string.indexOf('E') > -1 + || "-0".equals(string)) { + Double d = Double.valueOf(string); + if (!d.isInfinite() && !d.isNaN()) { + return d; + } + } else { + Long myLong = new Long(string); + if (string.equals(myLong.toString())) { + if (myLong.longValue() == myLong.intValue()) { + return Integer.valueOf(myLong.intValue()); + } + return myLong; + } + } + } catch (Exception ignore) { + } + } + return string; + } + + /** + * Throw an exception if the object is a NaN or infinite number. + * + * @param o + * The object to test. + * @throws JSONException + * If o is a non-finite number. + */ + public static void testValidity(Object o) throws JSONException { + if (o != null) { + if (o instanceof Double) { + if (((Double) o).isInfinite() || ((Double) o).isNaN()) { + throw new JSONException( + "JSON does not allow non-finite numbers."); + } + } else if (o instanceof Float) { + if (((Float) o).isInfinite() || ((Float) o).isNaN()) { + throw new JSONException( + "JSON does not allow non-finite numbers."); + } + } + } + } + + /** + * Produce a JSONArray containing the values of the members of this + * JSONObject. + * + * @param names + * A JSONArray containing a list of key strings. This determines + * the sequence of the values in the result. + * @return A JSONArray of values. + * @throws JSONException + * If any of the values are non-finite numbers. + */ + public JSONArray toJSONArray(JSONArray names) throws JSONException { + if (names == null || names.length() == 0) { + return null; + } + JSONArray ja = new JSONArray(); + for (int i = 0; i < names.length(); i += 1) { + ja.put(this.opt(names.getString(i))); + } + return ja; + } + + /** + * Make a JSON text of this JSONObject. For compactness, no whitespace is + * added. If this would not result in a syntactically correct JSON text, + * then null will be returned instead. + *

+ * Warning: This method assumes that the data structure is acyclical. + * + * @return a printable, displayable, portable, transmittable representation + * of the object, beginning with { (left + * brace) and ending with } (right + * brace). + */ + @Override + public String toString() { + try { + return this.toString(0); + } catch (Exception e) { + return null; + } + } + + /** + * Make a prettyprinted JSON text of this JSONObject. + *

+ * Warning: This method assumes that the data structure is acyclical. + * + * @param indentFactor + * The number of spaces to add to each level of indentation. + * @return a printable, displayable, portable, transmittable representation + * of the object, beginning with { (left + * brace) and ending with } (right + * brace). + * @throws JSONException + * If the object contains an invalid number. + */ + public String toString(int indentFactor) throws JSONException { + StringWriter w = new StringWriter(); + synchronized (w.getBuffer()) { + return this.write(w, indentFactor, 0).toString(); + } + } + + /** + * Make a JSON text of an Object value. If the object has an + * value.toJSONString() method, then that method will be used to produce the + * JSON text. The method is required to produce a strictly conforming text. + * If the object does not contain a toJSONString method (which is the most + * common case), then a text will be produced by other means. If the value + * is an array or Collection, then a JSONArray will be made from it and its + * toJSONString method will be called. If the value is a MAP, then a + * JSONObject will be made from it and its toJSONString method will be + * called. Otherwise, the value's toString method will be called, and the + * result will be quoted. + * + *

+ * Warning: This method assumes that the data structure is acyclical. + * + * @param value + * The value to be serialized. + * @return a printable, displayable, transmittable representation of the + * object, beginning with { (left + * brace) and ending with } (right + * brace). + * @throws JSONException + * If the value is or contains an invalid number. + */ + public static String valueToString(Object value) throws JSONException { + if (value == null || value.equals(null)) { + return "null"; + } + if (value instanceof JSONString) { + Object object; + try { + object = ((JSONString) value).toJSONString(); + } catch (Exception e) { + throw new JSONException(e); + } + if (object instanceof String) { + return (String) object; + } + throw new JSONException("Bad value from toJSONString: " + object); + } + if (value instanceof Number) { + // not all Numbers may match actual JSON Numbers. i.e. Fractions or Complex + final String numberAsString = numberToString((Number) value); + try { + // Use the BigDecimal constructor for it's parser to validate the format. + new BigDecimal(numberAsString); + // Close enough to a JSON number that we will return it unquoted + return numberAsString; + } catch (NumberFormatException ex){ + // The Number value is not a valid JSON number. + // Instead we will quote it as a string + return quote(numberAsString); + } + } + if (value instanceof Boolean || value instanceof JSONObject + || value instanceof JSONArray) { + return value.toString(); + } + if (value instanceof Map) { + Map map = (Map) value; + return new JSONObject(map).toString(); + } + if (value instanceof Collection) { + Collection coll = (Collection) value; + return new JSONArray(coll).toString(); + } + if (value.getClass().isArray()) { + return new JSONArray(value).toString(); + } + if(value instanceof Enum){ + return quote(((Enum)value).name()); + } + return quote(value.toString()); + } + + /** + * Wrap an object, if necessary. If the object is null, return the NULL + * object. If it is an array or collection, wrap it in a JSONArray. If it is + * a map, wrap it in a JSONObject. If it is a standard property (Double, + * String, et al) then it is already wrapped. Otherwise, if it comes from + * one of the java packages, turn it into a string. And if it doesn't, try + * to wrap it in a JSONObject. If the wrapping fails, then null is returned. + * + * @param object + * The object to wrap + * @return The wrapped value + */ + public static Object wrap(Object object) { + try { + if (object == null) { + return NULL; + } + if (object instanceof JSONObject || object instanceof JSONArray + || NULL.equals(object) || object instanceof JSONString + || object instanceof Byte || object instanceof Character + || object instanceof Short || object instanceof Integer + || object instanceof Long || object instanceof Boolean + || object instanceof Float || object instanceof Double + || object instanceof String || object instanceof BigInteger + || object instanceof BigDecimal || object instanceof Enum) { + return object; + } + + if (object instanceof Collection) { + Collection coll = (Collection) object; + return new JSONArray(coll); + } + if (object.getClass().isArray()) { + return new JSONArray(object); + } + if (object instanceof Map) { + Map map = (Map) object; + return new JSONObject(map); + } + Package objectPackage = object.getClass().getPackage(); + String objectPackageName = objectPackage != null ? objectPackage + .getName() : ""; + if (objectPackageName.startsWith("java.") + || objectPackageName.startsWith("javax.") + || object.getClass().getClassLoader() == null) { + return object.toString(); + } + return new JSONObject(object); + } catch (Exception exception) { + return null; + } + } + + /** + * Write the contents of the JSONObject as JSON text to a writer. For + * compactness, no whitespace is added. + *

+ * Warning: This method assumes that the data structure is acyclical. + * + * @return The writer. + * @throws JSONException + */ + public Writer write(Writer writer) throws JSONException { + return this.write(writer, 0, 0); + } + + static final Writer writeValue(Writer writer, Object value, + int indentFactor, int indent) throws JSONException, IOException { + if (value == null || value.equals(null)) { + writer.write("null"); + } else if (value instanceof JSONString) { + Object o; + try { + o = ((JSONString) value).toJSONString(); + } catch (Exception e) { + throw new JSONException(e); + } + writer.write(o != null ? o.toString() : quote(value.toString())); + } else if (value instanceof Number) { + // not all Numbers may match actual JSON Numbers. i.e. fractions or Imaginary + final String numberAsString = numberToString((Number) value); + try { + // Use the BigDecimal constructor for it's parser to validate the format. + @SuppressWarnings("unused") + BigDecimal testNum = new BigDecimal(numberAsString); + // Close enough to a JSON number that we will use it unquoted + writer.write(numberAsString); + } catch (NumberFormatException ex){ + // The Number value is not a valid JSON number. + // Instead we will quote it as a string + quote(numberAsString, writer); + } + } else if (value instanceof Boolean) { + writer.write(value.toString()); + } else if (value instanceof Enum) { + writer.write(quote(((Enum)value).name())); + } else if (value instanceof JSONObject) { + ((JSONObject) value).write(writer, indentFactor, indent); + } else if (value instanceof JSONArray) { + ((JSONArray) value).write(writer, indentFactor, indent); + } else if (value instanceof Map) { + Map map = (Map) value; + new JSONObject(map).write(writer, indentFactor, indent); + } else if (value instanceof Collection) { + Collection coll = (Collection) value; + new JSONArray(coll).write(writer, indentFactor, indent); + } else if (value.getClass().isArray()) { + new JSONArray(value).write(writer, indentFactor, indent); + } else { + quote(value.toString(), writer); + } + return writer; + } + + static final void indent(Writer writer, int indent) throws IOException { + for (int i = 0; i < indent; i += 1) { + writer.write(' '); + } + } + + /** + * Write the contents of the JSONObject as JSON text to a writer. For + * compactness, no whitespace is added. + *

+ * Warning: This method assumes that the data structure is acyclical. + * + * @param writer + * Writes the serialized JSON + * @param indentFactor + * The number of spaces to add to each level of indentation. + * @param indent + * The indention of the top level. + * @return The writer. + * @throws JSONException + */ + public Writer write(Writer writer, int indentFactor, int indent) + throws JSONException { + try { + boolean commanate = false; + final int length = this.length(); + Iterator keys = this.keys(); + writer.write('{'); + + if (length == 1) { + Object key = keys.next(); + writer.write(quote(key.toString())); + writer.write(':'); + if (indentFactor > 0) { + writer.write(' '); + } + writeValue(writer, this.map.get(key), indentFactor, indent); + } else if (length != 0) { + final int newindent = indent + indentFactor; + while (keys.hasNext()) { + Object key = keys.next(); + if (commanate) { + writer.write(','); + } + if (indentFactor > 0) { + writer.write('\n'); + } + indent(writer, newindent); + writer.write(quote(key.toString())); + writer.write(':'); + if (indentFactor > 0) { + writer.write(' '); + } + writeValue(writer, this.map.get(key), indentFactor, newindent); + commanate = true; + } + if (indentFactor > 0) { + writer.write('\n'); + } + indent(writer, indent); + } + writer.write('}'); + return writer; + } catch (IOException exception) { + throw new JSONException(exception); + } + } + + /** + * Returns a java.util.Map containing all of the entries in this object. + * If an entry in the object is a JSONArray or JSONObject it will also + * be converted. + *

+ * Warning: This method assumes that the data structure is acyclical. + * + * @return a java.util.Map containing the entries of this object + */ + public Map toMap() { + Map results = new HashMap(); + for (Entry entry : this.map.entrySet()) { + Object value; + if (entry.getValue() == null || NULL.equals(entry.getValue())) { + value = null; + } else if (entry.getValue() instanceof JSONObject) { + value = ((JSONObject) entry.getValue()).toMap(); + } else if (entry.getValue() instanceof JSONArray) { + value = ((JSONArray) entry.getValue()).toList(); + } else { + value = entry.getValue(); + } + results.put(entry.getKey(), value); + } + return results; + } +} diff --git a/d4dj/src/main/java/org/json/JSONPointer.java b/d4dj/src/main/java/org/json/JSONPointer.java new file mode 100644 index 0000000..82de7f9 --- /dev/null +++ b/d4dj/src/main/java/org/json/JSONPointer.java @@ -0,0 +1,267 @@ +package org.json; + +import static java.lang.String.format; + +import java.io.UnsupportedEncodingException; +import java.net.URLDecoder; +import java.net.URLEncoder; +import java.util.*; + +/* +Copyright (c) 2002 JSON.org + +Permission is hereby granted, free of charge, to any person obtaining a copy +of this software and associated documentation files (the "Software"), to deal +in the Software without restriction, including without limitation the rights +to use, copy, modify, merge, publish, distribute, sublicense, and/or sell +copies of the Software, and to permit persons to whom the Software is +furnished to do so, subject to the following conditions: + +The above copyright notice and this permission notice shall be included in all +copies or substantial portions of the Software. + +The Software shall be used for Good, not Evil. + +THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR +IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, +FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE +AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER +LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, +OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE +SOFTWARE. +*/ + +/** + * A JSON Pointer is a simple query language defined for JSON documents by + * RFC 6901. + * + * In a nutshell, JSONPointer allows the user to navigate into a JSON document + * using strings, and retrieve targeted objects, like a simple form of XPATH. + * Path segments are separated by the '/' char, which signifies the root of + * the document when it appears as the first char of the string. Array + * elements are navigated using ordinals, counting from 0. JSONPointer strings + * may be extended to any arbitrary number of segments. If the navigation + * is successful, the matched item is returned. A matched item may be a + * JSONObject, a JSONArray, or a JSON value. If the JSONPointer string building + * fails, an appropriate exception is thrown. If the navigation fails to find + * a match, a JSONPointerException is thrown. + * + * @author JSON.org + * @version 2016-05-14 + */ +public class JSONPointer { + + // used for URL encoding and decoding + private static final String ENCODING = "utf-8"; + + /** + * This class allows the user to build a JSONPointer in steps, using + * exactly one segment in each step. + */ + public static class Builder { + + // Segments for the eventual JSONPointer string + private final List refTokens = new ArrayList(); + + /** + * Creates a {@code JSONPointer} instance using the tokens previously set using the + * {@link #append(String)} method calls. + */ + public JSONPointer build() { + return new JSONPointer(refTokens); + } + + /** + * Adds an arbitary token to the list of reference tokens. It can be any non-null value. + * + * Unlike in the case of JSON string or URI fragment representation of JSON pointers, the + * argument of this method MUST NOT be escaped. If you want to query the property called + * {@code "a~b"} then you should simply pass the {@code "a~b"} string as-is, there is no + * need to escape it as {@code "a~0b"}. + * + * @param token the new token to be appended to the list + * @return {@code this} + * @throws NullPointerException if {@code token} is null + */ + public Builder append(String token) { + if (token == null) { + throw new NullPointerException("token cannot be null"); + } + refTokens.add(token); + return this; + } + + /** + * Adds an integer to the reference token list. Although not necessarily, mostly this token will + * denote an array index. + * + * @param arrayIndex the array index to be added to the token list + * @return {@code this} + */ + public Builder append(int arrayIndex) { + refTokens.add(String.valueOf(arrayIndex)); + return this; + } + } + + /** + * Static factory method for {@link Builder}. Example usage: + * + * 


+     * JSONPointer pointer = JSONPointer.builder()
+     *       .append("obj")
+     *       .append("other~key").append("another/key")
+     *       .append("\"")
+     *       .append(0)
+     *       .build();
+     *
+ * + * @return a builder instance which can be used to construct a {@code JSONPointer} instance by chained + * {@link Builder#append(String)} calls. + */ + public static Builder builder() { + return new Builder(); + } + + // Segments for the JSONPointer string + private final List refTokens; + + /** + * Pre-parses and initializes a new {@code JSONPointer} instance. If you want to + * evaluate the same JSON Pointer on different JSON documents then it is recommended + * to keep the {@code JSONPointer} instances due to performance considerations. + * + * @param pointer the JSON String or URI Fragment representation of the JSON pointer. + * @throws IllegalArgumentException if {@code pointer} is not a valid JSON pointer + */ + public JSONPointer(String pointer) { + if (pointer == null) { + throw new NullPointerException("pointer cannot be null"); + } + if (pointer.isEmpty() || pointer.equals("#")) { + refTokens = Collections.emptyList(); + return; + } + if (pointer.startsWith("#/")) { + pointer = pointer.substring(2); + try { + pointer = URLDecoder.decode(pointer, ENCODING); + } catch (UnsupportedEncodingException e) { + throw new RuntimeException(e); + } + } else if (pointer.startsWith("/")) { + pointer = pointer.substring(1); + } else { + throw new IllegalArgumentException("a JSON pointer should start with '/' or '#/'"); + } + refTokens = new ArrayList(); + for (String token : pointer.split("/")) { + refTokens.add(unescape(token)); + } + } + + public JSONPointer(List refTokens) { + this.refTokens = new ArrayList(refTokens); + } + + private String unescape(String token) { + return token.replace("~1", "/").replace("~0", "~") + .replace("\\\"", "\"") + .replace("\\\\", "\\"); + } + + /** + * Evaluates this JSON Pointer on the given {@code document}. The {@code document} + * is usually a {@link JSONObject} or a {@link JSONArray} instance, but the empty + * JSON Pointer ({@code ""}) can be evaluated on any JSON values and in such case the + * returned value will be {@code document} itself. + * + * @param document the JSON document which should be the subject of querying. + * @return the result of the evaluation + * @throws JSONPointerException if an error occurs during evaluation + */ + public Object queryFrom(Object document) { + if (refTokens.isEmpty()) { + return document; + } + Object current = document; + for (String token : refTokens) { + if (current instanceof JSONObject) { + current = ((JSONObject) current).opt(unescape(token)); + } else if (current instanceof JSONArray) { + current = readByIndexToken(current, token); + } else { + throw new JSONPointerException(format( + "value [%s] is not an array or object therefore its key %s cannot be resolved", current, + token)); + } + } + return current; + } + + /** + * Matches a JSONArray element by ordinal position + * @param current the JSONArray to be evaluated + * @param indexToken the array index in string form + * @return the matched object. If no matching item is found a + * JSONPointerException is thrown + */ + private Object readByIndexToken(Object current, String indexToken) { + try { + int index = Integer.parseInt(indexToken); + JSONArray currentArr = (JSONArray) current; + if (index >= currentArr.length()) { + throw new JSONPointerException(format("index %d is out of bounds - the array has %d elements", index, + currentArr.length())); + } + return currentArr.get(index); + } catch (NumberFormatException e) { + throw new JSONPointerException(format("%s is not an array index", indexToken), e); + } + } + + /** + * Returns a string representing the JSONPointer path value using string + * representation + */ + @Override + public String toString() { + StringBuilder rval = new StringBuilder(""); + for (String token: refTokens) { + rval.append('/').append(escape(token)); + } + return rval.toString(); + } + + /** + * Escapes path segment values to an unambiguous form. + * The escape char to be inserted is '~'. The chars to be escaped + * are ~, which maps to ~0, and /, which maps to ~1. Backslashes + * and double quote chars are also escaped. + * @param token the JSONPointer segment value to be escaped + * @return the escaped value for the token + */ + private String escape(String token) { + return token.replace("~", "~0") + .replace("/", "~1") + .replace("\\", "\\\\") + .replace("\"", "\\\""); + } + + /** + * Returns a string representing the JSONPointer path value using URI + * fragment identifier representation + */ + public String toURIFragment() { + try { + StringBuilder rval = new StringBuilder("#"); + for (String token : refTokens) { + rval.append('/').append(URLEncoder.encode(token, ENCODING)); + } + return rval.toString(); + } catch (UnsupportedEncodingException e) { + throw new RuntimeException(e); + } + } + +} diff --git a/d4dj/src/main/java/org/json/JSONPointerException.java b/d4dj/src/main/java/org/json/JSONPointerException.java new file mode 100644 index 0000000..0ce1aeb --- /dev/null +++ b/d4dj/src/main/java/org/json/JSONPointerException.java @@ -0,0 +1,45 @@ +package org.json; + +/* +Copyright (c) 2002 JSON.org + +Permission is hereby granted, free of charge, to any person obtaining a copy +of this software and associated documentation files (the "Software"), to deal +in the Software without restriction, including without limitation the rights +to use, copy, modify, merge, publish, distribute, sublicense, and/or sell +copies of the Software, and to permit persons to whom the Software is +furnished to do so, subject to the following conditions: + +The above copyright notice and this permission notice shall be included in all +copies or substantial portions of the Software. + +The Software shall be used for Good, not Evil. + +THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR +IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, +FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE +AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER +LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, +OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE +SOFTWARE. +*/ + +/** + * The JSONPointerException is thrown by {@link JSONPointer} if an error occurs + * during evaluating a pointer. + * + * @author JSON.org + * @version 2016-05-13 + */ +public class JSONPointerException extends JSONException { + private static final long serialVersionUID = 8872944667561856751L; + + public JSONPointerException(String message) { + super(message); + } + + public JSONPointerException(String message, Throwable cause) { + super(message, cause); + } + +} diff --git a/d4dj/src/main/java/org/json/JSONString.java b/d4dj/src/main/java/org/json/JSONString.java new file mode 100644 index 0000000..1f2d77d --- /dev/null +++ b/d4dj/src/main/java/org/json/JSONString.java @@ -0,0 +1,18 @@ +package org.json; +/** + * The JSONString interface allows a toJSONString() + * method so that a class can change the behavior of + * JSONObject.toString(), JSONArray.toString(), + * and JSONWriter.value(Object). The + * toJSONString method will be used instead of the default behavior + * of using the Object's toString() method and quoting the result. + */ +public interface JSONString { + /** + * The toJSONString method allows a class to produce its own JSON + * serialization. + * + * @return A strictly syntactically correct JSON text. + */ + public String toJSONString(); +} diff --git a/d4dj/src/main/java/org/json/JSONStringer.java b/d4dj/src/main/java/org/json/JSONStringer.java new file mode 100644 index 0000000..3ce1d55 --- /dev/null +++ b/d4dj/src/main/java/org/json/JSONStringer.java @@ -0,0 +1,78 @@ +package org.json; + +/* +Copyright (c) 2006 JSON.org + +Permission is hereby granted, free of charge, to any person obtaining a copy +of this software and associated documentation files (the "Software"), to deal +in the Software without restriction, including without limitation the rights +to use, copy, modify, merge, publish, distribute, sublicense, and/or sell +copies of the Software, and to permit persons to whom the Software is +furnished to do so, subject to the following conditions: + +The above copyright notice and this permission notice shall be included in all +copies or substantial portions of the Software. + +The Software shall be used for Good, not Evil. + +THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR +IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, +FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE +AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER +LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, +OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE +SOFTWARE. +*/ + +import java.io.StringWriter; + +/** + * JSONStringer provides a quick and convenient way of producing JSON text. + * The texts produced strictly conform to JSON syntax rules. No whitespace is + * added, so the results are ready for transmission or storage. Each instance of + * JSONStringer can produce one JSON text. + *

+ * A JSONStringer instance provides a value method for appending + * values to the + * text, and a key + * method for adding keys before values in objects. There are array + * and endArray methods that make and bound array values, and + * object and endObject methods which make and bound + * object values. All of these methods return the JSONWriter instance, + * permitting cascade style. For example, 

+ * myString = new JSONStringer()
+ *     .object()
+ *         .key("JSON")
+ *         .value("Hello, World!")
+ *     .endObject()
+ *     .toString();
which produces the string 
+ * {"JSON":"Hello, World!"}
+ *

+ * The first method called must be array or object. + * There are no methods for adding commas or colons. JSONStringer adds them for + * you. Objects and arrays can be nested up to 20 levels deep. + *

+ * This can sometimes be easier than using a JSONObject to build a string. + * @author JSON.org + * @version 2015-12-09 + */ +public class JSONStringer extends JSONWriter { + /** + * Make a fresh JSONStringer. It can be used to build one JSON text. + */ + public JSONStringer() { + super(new StringWriter()); + } + + /** + * Return the JSON text. This method is used to obtain the product of the + * JSONStringer instance. It will return null if there was a + * problem in the construction of the JSON text (such as the calls to + * array were not properly balanced with calls to + * endArray). + * @return The JSON text. + */ + public String toString() { + return this.mode == 'd' ? this.writer.toString() : null; + } +} diff --git a/d4dj/src/main/java/org/json/JSONTokener.java b/d4dj/src/main/java/org/json/JSONTokener.java new file mode 100644 index 0000000..d0b197d --- /dev/null +++ b/d4dj/src/main/java/org/json/JSONTokener.java @@ -0,0 +1,475 @@ +package org.json; + +import java.io.BufferedReader; +import java.io.IOException; +import java.io.InputStream; +import java.io.InputStreamReader; +import java.io.Reader; +import java.io.StringReader; + +/* +Copyright (c) 2002 JSON.org + +Permission is hereby granted, free of charge, to any person obtaining a copy +of this software and associated documentation files (the "Software"), to deal +in the Software without restriction, including without limitation the rights +to use, copy, modify, merge, publish, distribute, sublicense, and/or sell +copies of the Software, and to permit persons to whom the Software is +furnished to do so, subject to the following conditions: + +The above copyright notice and this permission notice shall be included in all +copies or substantial portions of the Software. + +The Software shall be used for Good, not Evil. + +THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR +IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, +FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE +AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER +LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, +OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE +SOFTWARE. +*/ + +/** + * A JSONTokener takes a source string and extracts characters and tokens from + * it. It is used by the JSONObject and JSONArray constructors to parse + * JSON source strings. + * @author JSON.org + * @version 2014-05-03 + */ +public class JSONTokener { + + private long character; + private boolean eof; + private long index; + private long line; + private char previous; + private Reader reader; + private boolean usePrevious; + + + /** + * Construct a JSONTokener from a Reader. + * + * @param reader A reader. + */ + public JSONTokener(Reader reader) { + this.reader = reader.markSupported() + ? reader + : new BufferedReader(reader); + this.eof = false; + this.usePrevious = false; + this.previous = 0; + this.index = 0; + this.character = 1; + this.line = 1; + } + + + /** + * Construct a JSONTokener from an InputStream. + * @param inputStream The source. + */ + public JSONTokener(InputStream inputStream) { + this(new InputStreamReader(inputStream)); + } + + + /** + * Construct a JSONTokener from a string. + * + * @param s A source string. + */ + public JSONTokener(String s) { + this(new StringReader(s)); + } + + + /** + * Back up one character. This provides a sort of lookahead capability, + * so that you can test for a digit or letter before attempting to parse + * the next number or identifier. + * @throws JSONException Thrown if trying to step back more than 1 step + * or if already at the start of the string + */ + public void back() throws JSONException { + if (this.usePrevious || this.index <= 0) { + throw new JSONException("Stepping back two steps is not supported"); + } + this.index -= 1; + this.character -= 1; + this.usePrevious = true; + this.eof = false; + } + + + /** + * Get the hex value of a character (base16). + * @param c A character between '0' and '9' or between 'A' and 'F' or + * between 'a' and 'f'. + * @return An int between 0 and 15, or -1 if c was not a hex digit. + */ + public static int dehexchar(char c) { + if (c >= '0' && c <= '9') { + return c - '0'; + } + if (c >= 'A' && c <= 'F') { + return c - ('A' - 10); + } + if (c >= 'a' && c <= 'f') { + return c - ('a' - 10); + } + return -1; + } + + /** + * @return true if at the end of the file and we didn't step back + */ + public boolean end() { + return this.eof && !this.usePrevious; + } + + + /** + * Determine if the source string still contains characters that next() + * can consume. + * @return true if not yet at the end of the source. + * @throws JSONException thrown if there is an error stepping forward + * or backward while checking for more data. + */ + public boolean more() throws JSONException { + this.next(); + if (this.end()) { + return false; + } + this.back(); + return true; + } + + + /** + * Get the next character in the source string. + * + * @return The next character, or 0 if past the end of the source string. + * @throws JSONException Thrown if there is an error reading the source string. + */ + public char next() throws JSONException { + int c; + if (this.usePrevious) { + this.usePrevious = false; + c = this.previous; + } else { + try { + c = this.reader.read(); + } catch (IOException exception) { + throw new JSONException(exception); + } + + if (c <= 0) { // End of stream + this.eof = true; + c = 0; + } + } + this.index += 1; + if (this.previous == '\r') { + this.line += 1; + this.character = c == '\n' ? 0 : 1; + } else if (c == '\n') { + this.line += 1; + this.character = 0; + } else { + this.character += 1; + } + this.previous = (char) c; + return this.previous; + } + + + /** + * Consume the next character, and check that it matches a specified + * character. + * @param c The character to match. + * @return The character. + * @throws JSONException if the character does not match. + */ + public char next(char c) throws JSONException { + char n = this.next(); + if (n != c) { + throw this.syntaxError("Expected '" + c + "' and instead saw '" + + n + "'"); + } + return n; + } + + + /** + * Get the next n characters. + * + * @param n The number of characters to take. + * @return A string of n characters. + * @throws JSONException + * Substring bounds error if there are not + * n characters remaining in the source string. + */ + public String next(int n) throws JSONException { + if (n == 0) { + return ""; + } + + char[] chars = new char[n]; + int pos = 0; + + while (pos < n) { + chars[pos] = this.next(); + if (this.end()) { + throw this.syntaxError("Substring bounds error"); + } + pos += 1; + } + return new String(chars); + } + + + /** + * Get the next char in the string, skipping whitespace. + * @throws JSONException Thrown if there is an error reading the source string. + * @return A character, or 0 if there are no more characters. + */ + public char nextClean() throws JSONException { + for (;;) { + char c = this.next(); + if (c == 0 || c > ' ') { + return c; + } + } + } + + + /** + * Return the characters up to the next close quote character. + * Backslash processing is done. The formal JSON format does not + * allow strings in single quotes, but an implementation is allowed to + * accept them. + * @param quote The quoting character, either + * " (double quote) or + * ' (single quote). + * @return A String. + * @throws JSONException Unterminated string. + */ + public String nextString(char quote) throws JSONException { + char c; + StringBuilder sb = new StringBuilder(); + for (;;) { + c = this.next(); + switch (c) { + case 0: + case '\n': + case '\r': + throw this.syntaxError("Unterminated string"); + case '\\': + c = this.next(); + switch (c) { + case 'b': + sb.append('\b'); + break; + case 't': + sb.append('\t'); + break; + case 'n': + sb.append('\n'); + break; + case 'f': + sb.append('\f'); + break; + case 'r': + sb.append('\r'); + break; + case 'u': + try { + sb.append((char)Integer.parseInt(this.next(4), 16)); + } catch (NumberFormatException e) { + throw this.syntaxError("Illegal escape.", e); + } + break; + case '"': + case '\'': + case '\\': + case '/': + sb.append(c); + break; + default: + throw this.syntaxError("Illegal escape."); + } + break; + default: + if (c == quote) { + return sb.toString(); + } + sb.append(c); + } + } + } + + + /** + * Get the text up but not including the specified character or the + * end of line, whichever comes first. + * @param delimiter A delimiter character. + * @return A string. + * @throws JSONException Thrown if there is an error while searching + * for the delimiter + */ + public String nextTo(char delimiter) throws JSONException { + StringBuilder sb = new StringBuilder(); + for (;;) { + char c = this.next(); + if (c == delimiter || c == 0 || c == '\n' || c == '\r') { + if (c != 0) { + this.back(); + } + return sb.toString().trim(); + } + sb.append(c); + } + } + + + /** + * Get the text up but not including one of the specified delimiter + * characters or the end of line, whichever comes first. + * @param delimiters A set of delimiter characters. + * @return A string, trimmed. + * @throws JSONException Thrown if there is an error while searching + * for the delimiter + */ + public String nextTo(String delimiters) throws JSONException { + char c; + StringBuilder sb = new StringBuilder(); + for (;;) { + c = this.next(); + if (delimiters.indexOf(c) >= 0 || c == 0 || + c == '\n' || c == '\r') { + if (c != 0) { + this.back(); + } + return sb.toString().trim(); + } + sb.append(c); + } + } + + + /** + * Get the next value. The value can be a Boolean, Double, Integer, + * JSONArray, JSONObject, Long, or String, or the JSONObject.NULL object. + * @throws JSONException If syntax error. + * + * @return An object. + */ + public Object nextValue() throws JSONException { + char c = this.nextClean(); + String string; + + switch (c) { + case '"': + case '\'': + return this.nextString(c); + case '{': + this.back(); + return new JSONObject(this); + case '[': + this.back(); + return new JSONArray(this); + } + + /* + * Handle unquoted text. This could be the values true, false, or + * null, or it can be a number. An implementation (such as this one) + * is allowed to also accept non-standard forms. + * + * Accumulate characters until we reach the end of the text or a + * formatting character. + */ + + StringBuilder sb = new StringBuilder(); + while (c >= ' ' && ",:]}/\\\"[{;=#".indexOf(c) < 0) { + sb.append(c); + c = this.next(); + } + this.back(); + + string = sb.toString().trim(); + if ("".equals(string)) { + throw this.syntaxError("Missing value"); + } + return JSONObject.stringToValue(string); + } + + + /** + * Skip characters until the next character is the requested character. + * If the requested character is not found, no characters are skipped. + * @param to A character to skip to. + * @return The requested character, or zero if the requested character + * is not found. + * @throws JSONException Thrown if there is an error while searching + * for the to character + */ + public char skipTo(char to) throws JSONException { + char c; + try { + long startIndex = this.index; + long startCharacter = this.character; + long startLine = this.line; + this.reader.mark(1000000); + do { + c = this.next(); + if (c == 0) { + this.reader.reset(); + this.index = startIndex; + this.character = startCharacter; + this.line = startLine; + return c; + } + } while (c != to); + } catch (IOException exception) { + throw new JSONException(exception); + } + this.back(); + return c; + } + + + /** + * Make a JSONException to signal a syntax error. + * + * @param message The error message. + * @return A JSONException object, suitable for throwing + */ + public JSONException syntaxError(String message) { + return new JSONException(message + this.toString()); + } + + /** + * Make a JSONException to signal a syntax error. + * + * @param message The error message. + * @param causedBy The throwable that caused the error. + * @return A JSONException object, suitable for throwing + */ + public JSONException syntaxError(String message, Throwable causedBy) { + return new JSONException(message + this.toString(), causedBy); + } + + /** + * Make a printable string of this JSONTokener. + * + * @return " at {index} [character {character} line {line}]" + */ + @Override + public String toString() { + return " at " + this.index + " [character " + this.character + " line " + + this.line + "]"; + } +} diff --git a/d4dj/src/main/java/org/json/JSONWriter.java b/d4dj/src/main/java/org/json/JSONWriter.java new file mode 100644 index 0000000..b7c8ea8 --- /dev/null +++ b/d4dj/src/main/java/org/json/JSONWriter.java @@ -0,0 +1,326 @@ +package org.json; + +import java.io.IOException; + +/* +Copyright (c) 2006 JSON.org + +Permission is hereby granted, free of charge, to any person obtaining a copy +of this software and associated documentation files (the "Software"), to deal +in the Software without restriction, including without limitation the rights +to use, copy, modify, merge, publish, distribute, sublicense, and/or sell +copies of the Software, and to permit persons to whom the Software is +furnished to do so, subject to the following conditions: + +The above copyright notice and this permission notice shall be included in all +copies or substantial portions of the Software. + +The Software shall be used for Good, not Evil. + +THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR +IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, +FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE +AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER +LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, +OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE +SOFTWARE. +*/ + +/** + * JSONWriter provides a quick and convenient way of producing JSON text. + * The texts produced strictly conform to JSON syntax rules. No whitespace is + * added, so the results are ready for transmission or storage. Each instance of + * JSONWriter can produce one JSON text. + *

+ * A JSONWriter instance provides a value method for appending + * values to the + * text, and a key + * method for adding keys before values in objects. There are array + * and endArray methods that make and bound array values, and + * object and endObject methods which make and bound + * object values. All of these methods return the JSONWriter instance, + * permitting a cascade style. For example, 

+ * new JSONWriter(myWriter)
+ *     .object()
+ *         .key("JSON")
+ *         .value("Hello, World!")
+ *     .endObject();
which writes 
+ * {"JSON":"Hello, World!"}
+ *

+ * The first method called must be array or object. + * There are no methods for adding commas or colons. JSONWriter adds them for + * you. Objects and arrays can be nested up to 200 levels deep. + *

+ * This can sometimes be easier than using a JSONObject to build a string. + * @author JSON.org + * @version 2016-08-08 + */ +public class JSONWriter { + private static final int maxdepth = 200; + + /** + * The comma flag determines if a comma should be output before the next + * value. + */ + private boolean comma; + + /** + * The current mode. Values: + * 'a' (array), + * 'd' (done), + * 'i' (initial), + * 'k' (key), + * 'o' (object). + */ + protected char mode; + + /** + * The object/array stack. + */ + private final JSONObject stack[]; + + /** + * The stack top index. A value of 0 indicates that the stack is empty. + */ + private int top; + + /** + * The writer that will receive the output. + */ + protected Appendable writer; + + /** + * Make a fresh JSONWriter. It can be used to build one JSON text. + */ + public JSONWriter(Appendable w) { + this.comma = false; + this.mode = 'i'; + this.stack = new JSONObject[maxdepth]; + this.top = 0; + this.writer = w; + } + + /** + * Append a value. + * @param string A string value. + * @return this + * @throws JSONException If the value is out of sequence. + */ + private JSONWriter append(String string) throws JSONException { + if (string == null) { + throw new JSONException("Null pointer"); + } + if (this.mode == 'o' || this.mode == 'a') { + try { + if (this.comma && this.mode == 'a') { + this.writer.append(','); + } + this.writer.append(string); + } catch (IOException e) { + throw new JSONException(e); + } + if (this.mode == 'o') { + this.mode = 'k'; + } + this.comma = true; + return this; + } + throw new JSONException("Value out of sequence."); + } + + /** + * Begin appending a new array. All values until the balancing + * endArray will be appended to this array. The + * endArray method must be called to mark the array's end. + * @return this + * @throws JSONException If the nesting is too deep, or if the object is + * started in the wrong place (for example as a key or after the end of the + * outermost array or object). + */ + public JSONWriter array() throws JSONException { + if (this.mode == 'i' || this.mode == 'o' || this.mode == 'a') { + this.push(null); + this.append("["); + this.comma = false; + return this; + } + throw new JSONException("Misplaced array."); + } + + /** + * End something. + * @param mode Mode + * @param c Closing character + * @return this + * @throws JSONException If unbalanced. + */ + private JSONWriter end(char mode, char c) throws JSONException { + if (this.mode != mode) { + throw new JSONException(mode == 'a' + ? "Misplaced endArray." + : "Misplaced endObject."); + } + this.pop(mode); + try { + this.writer.append(c); + } catch (IOException e) { + throw new JSONException(e); + } + this.comma = true; + return this; + } + + /** + * End an array. This method most be called to balance calls to + * array. + * @return this + * @throws JSONException If incorrectly nested. + */ + public JSONWriter endArray() throws JSONException { + return this.end('a', ']'); + } + + /** + * End an object. This method most be called to balance calls to + * object. + * @return this + * @throws JSONException If incorrectly nested. + */ + public JSONWriter endObject() throws JSONException { + return this.end('k', '}'); + } + + /** + * Append a key. The key will be associated with the next value. In an + * object, every value must be preceded by a key. + * @param string A key string. + * @return this + * @throws JSONException If the key is out of place. For example, keys + * do not belong in arrays or if the key is null. + */ + public JSONWriter key(String string) throws JSONException { + if (string == null) { + throw new JSONException("Null key."); + } + if (this.mode == 'k') { + try { + this.stack[this.top - 1].putOnce(string, Boolean.TRUE); + if (this.comma) { + this.writer.append(','); + } + this.writer.append(JSONObject.quote(string)); + this.writer.append(':'); + this.comma = false; + this.mode = 'o'; + return this; + } catch (IOException e) { + throw new JSONException(e); + } + } + throw new JSONException("Misplaced key."); + } + + + /** + * Begin appending a new object. All keys and values until the balancing + * endObject will be appended to this object. The + * endObject method must be called to mark the object's end. + * @return this + * @throws JSONException If the nesting is too deep, or if the object is + * started in the wrong place (for example as a key or after the end of the + * outermost array or object). + */ + public JSONWriter object() throws JSONException { + if (this.mode == 'i') { + this.mode = 'o'; + } + if (this.mode == 'o' || this.mode == 'a') { + this.append("{"); + this.push(new JSONObject()); + this.comma = false; + return this; + } + throw new JSONException("Misplaced object."); + + } + + + /** + * Pop an array or object scope. + * @param c The scope to close. + * @throws JSONException If nesting is wrong. + */ + private void pop(char c) throws JSONException { + if (this.top <= 0) { + throw new JSONException("Nesting error."); + } + char m = this.stack[this.top - 1] == null ? 'a' : 'k'; + if (m != c) { + throw new JSONException("Nesting error."); + } + this.top -= 1; + this.mode = this.top == 0 + ? 'd' + : this.stack[this.top - 1] == null + ? 'a' + : 'k'; + } + + /** + * Push an array or object scope. + * @param jo The scope to open. + * @throws JSONException If nesting is too deep. + */ + private void push(JSONObject jo) throws JSONException { + if (this.top >= maxdepth) { + throw new JSONException("Nesting too deep."); + } + this.stack[this.top] = jo; + this.mode = jo == null ? 'a' : 'k'; + this.top += 1; + } + + + /** + * Append either the value true or the value + * false. + * @param b A boolean. + * @return this + * @throws JSONException + */ + public JSONWriter value(boolean b) throws JSONException { + return this.append(b ? "true" : "false"); + } + + /** + * Append a double value. + * @param d A double. + * @return this + * @throws JSONException If the number is not finite. + */ + public JSONWriter value(double d) throws JSONException { + return this.value(new Double(d)); + } + + /** + * Append a long value. + * @param l A long. + * @return this + * @throws JSONException + */ + public JSONWriter value(long l) throws JSONException { + return this.append(Long.toString(l)); + } + + + /** + * Append an object value. + * @param object The object to append. It can be null, or a Boolean, Number, + * String, JSONObject, or JSONArray, or an object that implements JSONString. + * @return this + * @throws JSONException If the value is out of sequence. + */ + public JSONWriter value(Object object) throws JSONException { + return this.append(JSONObject.valueToString(object)); + } +} diff --git a/d4dj/src/main/java/org/json/Property.java b/d4dj/src/main/java/org/json/Property.java new file mode 100644 index 0000000..73ddb12 --- /dev/null +++ b/d4dj/src/main/java/org/json/Property.java @@ -0,0 +1,72 @@ +package org.json; + +/* +Copyright (c) 2002 JSON.org + +Permission is hereby granted, free of charge, to any person obtaining a copy +of this software and associated documentation files (the "Software"), to deal +in the Software without restriction, including without limitation the rights +to use, copy, modify, merge, publish, distribute, sublicense, and/or sell +copies of the Software, and to permit persons to whom the Software is +furnished to do so, subject to the following conditions: + +The above copyright notice and this permission notice shall be included in all +copies or substantial portions of the Software. + +The Software shall be used for Good, not Evil. + +THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR +IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, +FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE +AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER +LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, +OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE +SOFTWARE. +*/ + +import java.util.Enumeration; +import java.util.Iterator; +import java.util.Properties; + +/** + * Converts a Property file data into JSONObject and back. + * @author JSON.org + * @version 2015-05-05 + */ +public class Property { + /** + * Converts a property file object into a JSONObject. The property file object is a table of name value pairs. + * @param properties java.util.Properties + * @return JSONObject + * @throws JSONException + */ + public static JSONObject toJSONObject(java.util.Properties properties) throws JSONException { + JSONObject jo = new JSONObject(); + if (properties != null && !properties.isEmpty()) { + Enumeration enumProperties = properties.propertyNames(); + while(enumProperties.hasMoreElements()) { + String name = (String)enumProperties.nextElement(); + jo.put(name, properties.getProperty(name)); + } + } + return jo; + } + + /** + * Converts the JSONObject into a property file object. + * @param jo JSONObject + * @return java.util.Properties + * @throws JSONException + */ + public static Properties toProperties(JSONObject jo) throws JSONException { + Properties properties = new Properties(); + if (jo != null) { + Iterator keys = jo.keys(); + while (keys.hasNext()) { + String name = keys.next(); + properties.put(name, jo.getString(name)); + } + } + return properties; + } +} diff --git a/d4dj/src/main/java/org/json/XML.java b/d4dj/src/main/java/org/json/XML.java new file mode 100644 index 0000000..78dd6a0 --- /dev/null +++ b/d4dj/src/main/java/org/json/XML.java @@ -0,0 +1,621 @@ +package org.json; + +/* +Copyright (c) 2015 JSON.org + +Permission is hereby granted, free of charge, to any person obtaining a copy +of this software and associated documentation files (the "Software"), to deal +in the Software without restriction, including without limitation the rights +to use, copy, modify, merge, publish, distribute, sublicense, and/or sell +copies of the Software, and to permit persons to whom the Software is +furnished to do so, subject to the following conditions: + +The above copyright notice and this permission notice shall be included in all +copies or substantial portions of the Software. + +The Software shall be used for Good, not Evil. + +THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR +IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, +FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE +AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER +LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, +OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE +SOFTWARE. +*/ + +import java.util.Iterator; + +/** + * This provides static methods to convert an XML text into a JSONObject, and to + * covert a JSONObject into an XML text. + * + * @author JSON.org + * @version 2016-08-10 + */ +@SuppressWarnings("boxing") +public class XML { + /** The Character '&'. */ + public static final Character AMP = '&'; + + /** The Character '''. */ + public static final Character APOS = '\''; + + /** The Character '!'. */ + public static final Character BANG = '!'; + + /** The Character '='. */ + public static final Character EQ = '='; + + /** The Character '>'. */ + public static final Character GT = '>'; + + /** The Character '<'. */ + public static final Character LT = '<'; + + /** The Character '?'. */ + public static final Character QUEST = '?'; + + /** The Character '"'. */ + public static final Character QUOT = '"'; + + /** The Character '/'. */ + public static final Character SLASH = '/'; + + /** + * Creates an iterator for navigating Code Points in a string instead of + * characters. Once Java7 support is dropped, this can be replaced with + * + * string.codePoints() + * + * which is available in Java8 and above. + * + * @see http://stackoverflow.com/a/21791059/6030888 + */ + private static Iterable codePointIterator(final String string) { + return new Iterable() { + @Override + public Iterator iterator() { + return new Iterator() { + private int nextIndex = 0; + private int length = string.length(); + + @Override + public boolean hasNext() { + return this.nextIndex < this.length; + } + + @Override + public Integer next() { + int result = string.codePointAt(this.nextIndex); + this.nextIndex += Character.charCount(result); + return result; + } + + @Override + public void remove() { + throw new UnsupportedOperationException(); + } + }; + } + }; + } + + /** + * Replace special characters with XML escapes: + * + * 

+     * & (ampersand) is replaced by &amp;
+     * < (less than) is replaced by &lt;
+     * > (greater than) is replaced by &gt;
+     * " (double quote) is replaced by &quot;
+     * ' (single quote / apostrophe) is replaced by &apos;
+     *
+ * + * @param string + * The string to be escaped. + * @return The escaped string. + */ + public static String escape(String string) { + StringBuilder sb = new StringBuilder(string.length()); + for (final int cp : codePointIterator(string)) { + switch (cp) { + case '&': + sb.append("&"); + break; + case '<': + sb.append("<"); + break; + case '>': + sb.append(">"); + break; + case '"': + sb.append("""); + break; + case '\'': + sb.append("'"); + break; + default: + if (mustEscape(cp)) { + sb.append("&#x"); + sb.append(Integer.toHexString(cp)); + sb.append(";"); + } else { + sb.appendCodePoint(cp); + } + } + } + return sb.toString(); + } + + /** + * @param cp code point to test + * @return true if the code point is not valid for an XML + */ + private static boolean mustEscape(int cp) { + /* Valid range from https://www.w3.org/TR/REC-xml/#charsets + * + * #x9 | #xA | #xD | [#x20-#xD7FF] | [#xE000-#xFFFD] | [#x10000-#x10FFFF] + * + * any Unicode character, excluding the surrogate blocks, FFFE, and FFFF. + */ + // isISOControl is true when (cp >= 0 && cp <= 0x1F) || (cp >= 0x7F && cp <= 0x9F) + // all ISO control characters are out of range except tabs and new lines + return (Character.isISOControl(cp) + && cp != 0x9 + && cp != 0xA + && cp != 0xD + ) || !( + // valid the range of acceptable characters that aren't control + (cp >= 0x20 && cp <= 0xD7FF) + || (cp >= 0xE000 && cp <= 0xFFFD) + || (cp >= 0x10000 && cp <= 0x10FFFF) + ) + ; + } + + /** + * Removes XML escapes from the string. + * + * @param string + * string to remove escapes from + * @return string with converted entities + */ + public static String unescape(String string) { + StringBuilder sb = new StringBuilder(string.length()); + for (int i = 0, length = string.length(); i < length; i++) { + char c = string.charAt(i); + if (c == '&') { + final int semic = string.indexOf(';', i); + if (semic > i) { + final String entity = string.substring(i + 1, semic); + if (entity.charAt(0) == '#') { + int cp; + if (entity.charAt(1) == 'x') { + // hex encoded unicode + cp = Integer.parseInt(entity.substring(2), 16); + } else { + // decimal encoded unicode + cp = Integer.parseInt(entity.substring(1)); + } + sb.appendCodePoint(cp); + } else { + if ("quot".equalsIgnoreCase(entity)) { + sb.append('"'); + } else if ("amp".equalsIgnoreCase(entity)) { + sb.append('&'); + } else if ("apos".equalsIgnoreCase(entity)) { + sb.append('\''); + } else if ("lt".equalsIgnoreCase(entity)) { + sb.append('<'); + } else if ("gt".equalsIgnoreCase(entity)) { + sb.append('>'); + } else { + sb.append('&').append(entity).append(';'); + } + } + // skip past the entity we just parsed. + i += entity.length() + 1; + } else { + // this shouldn't happen in most cases since the parser + // errors on unclosed enties. + sb.append(c); + } + } else { + // not part of an entity + sb.append(c); + } + } + return sb.toString(); + } + + /** + * Throw an exception if the string contains whitespace. Whitespace is not + * allowed in tagNames and attributes. + * + * @param string + * A string. + * @throws JSONException Thrown if the string contains whitespace or is empty. + */ + public static void noSpace(String string) throws JSONException { + int i, length = string.length(); + if (length == 0) { + throw new JSONException("Empty string."); + } + for (i = 0; i < length; i += 1) { + if (Character.isWhitespace(string.charAt(i))) { + throw new JSONException("'" + string + + "' contains a space character."); + } + } + } + + /** + * Scan the content following the named tag, attaching it to the context. + * + * @param x + * The XMLTokener containing the source string. + * @param context + * The JSONObject that will include the new material. + * @param name + * The tag name. + * @return true if the close tag is processed. + * @throws JSONException + */ + private static boolean parse(XMLTokener x, JSONObject context, String name, boolean keepStrings) + throws JSONException { + char c; + int i; + JSONObject jsonobject = null; + String string; + String tagName; + Object token; + + // Test for and skip past these forms: + // + // + // + // + // Report errors for these forms: + // <> + // <= + // << + + token = x.nextToken(); + + // "); + return false; + } + x.back(); + } else if (c == '[') { + token = x.nextToken(); + if ("CDATA".equals(token)) { + if (x.next() == '[') { + string = x.nextCDATA(); + if (string.length() > 0) { + context.accumulate("content", string); + } + return false; + } + } + throw x.syntaxError("Expected 'CDATA['"); + } + i = 1; + do { + token = x.nextMeta(); + if (token == null) { + throw x.syntaxError("Missing '>' after ' 0); + return false; + } else if (token == QUEST) { + + // "); + return false; + } else if (token == SLASH) { + + // Close tag + if (x.nextToken() != GT) { + throw x.syntaxError("Misshaped tag"); + } + if (jsonobject.length() > 0) { + context.accumulate(tagName, jsonobject); + } else { + context.accumulate(tagName, ""); + } + return false; + + } else if (token == GT) { + // Content, between <...> and + for (;;) { + token = x.nextContent(); + if (token == null) { + if (tagName != null) { + throw x.syntaxError("Unclosed tag " + tagName); + } + return false; + } else if (token instanceof String) { + string = (String) token; + if (string.length() > 0) { + jsonobject.accumulate("content", + keepStrings ? unescape(string) : stringToValue(string)); + } + + } else if (token == LT) { + // Nested element + if (parse(x, jsonobject, tagName,keepStrings)) { + if (jsonobject.length() == 0) { + context.accumulate(tagName, ""); + } else if (jsonobject.length() == 1 + && jsonobject.opt("content") != null) { + context.accumulate(tagName, + jsonobject.opt("content")); + } else { + context.accumulate(tagName, jsonobject); + } + return false; + } + } + } + } else { + throw x.syntaxError("Misshaped tag"); + } + } + } + } + + /** + * This method is the same as {@link JSONObject.stringToValue(String)} + * except that this also tries to unescape String values. + * + * @param string String to convert + * @return JSON value of this string or the string + */ + public static Object stringToValue(String string) { + Object ret = JSONObject.stringToValue(string); + if(ret instanceof String){ + return unescape((String)ret); + } + return ret; + } + + /** + * Convert a well-formed (but not necessarily valid) XML string into a + * JSONObject. Some information may be lost in this transformation because + * JSON is a data format and XML is a document format. XML uses elements, + * attributes, and content text, while JSON uses unordered collections of + * name/value pairs and arrays of values. JSON does not does not like to + * distinguish between elements and attributes. Sequences of similar + * elements are represented as JSONArrays. Content text may be placed in a + * "content" member. Comments, prologs, DTDs, and <[ [ ]]> + * are ignored. + * + * @param string + * The source string. + * @return A JSONObject containing the structured data from the XML string. + * @throws JSONException Thrown if there is an errors while parsing the string + */ + public static JSONObject toJSONObject(String string) throws JSONException { + return toJSONObject(string, false); + } + + + /** + * Convert a well-formed (but not necessarily valid) XML string into a + * JSONObject. Some information may be lost in this transformation because + * JSON is a data format and XML is a document format. XML uses elements, + * attributes, and content text, while JSON uses unordered collections of + * name/value pairs and arrays of values. JSON does not does not like to + * distinguish between elements and attributes. Sequences of similar + * elements are represented as JSONArrays. Content text may be placed in a + * "content" member. Comments, prologs, DTDs, and <[ [ ]]> + * are ignored. + * + * All values are converted as strings, for 1, 01, 29.0 will not be coerced to + * numbers but will instead be the exact value as seen in the XML document. + * + * @param string + * The source string. + * @param keepStrings If true, then values will not be coerced into boolean + * or numeric values and will instead be left as strings + * @return A JSONObject containing the structured data from the XML string. + * @throws JSONException Thrown if there is an errors while parsing the string + */ + public static JSONObject toJSONObject(String string, boolean keepStrings) throws JSONException { + JSONObject jo = new JSONObject(); + XMLTokener x = new XMLTokener(string); + while (x.more() && x.skipPast("<")) { + parse(x, jo, null, keepStrings); + } + return jo; + } + /** + * Convert a JSONObject into a well-formed, element-normal XML string. + * + * @param object + * A JSONObject. + * @return A string. + * @throws JSONException Thrown if there is an error parsing the string + */ + public static String toString(Object object) throws JSONException { + return toString(object, null); + } + + /** + * Convert a JSONObject into a well-formed, element-normal XML string. + * + * @param object + * A JSONObject. + * @param tagName + * The optional name of the enclosing tag. + * @return A string. + * @throws JSONException Thrown if there is an error parsing the string + */ + public static String toString(Object object, String tagName) + throws JSONException { + StringBuilder sb = new StringBuilder(); + JSONArray ja; + JSONObject jo; + String key; + Iterator keys; + String string; + Object value; + + if (object instanceof JSONObject) { + + // Emit + if (tagName != null) { + sb.append('<'); + sb.append(tagName); + sb.append('>'); + } + + // Loop thru the keys. + jo = (JSONObject) object; + keys = jo.keys(); + while (keys.hasNext()) { + key = keys.next(); + value = jo.opt(key); + if (value == null) { + value = ""; + } else if (value.getClass().isArray()) { + value = new JSONArray(value); + } + string = value instanceof String ? (String) value : null; + + // Emit content in body + if ("content".equals(key)) { + if (value instanceof JSONArray) { + ja = (JSONArray) value; + int i = 0; + for (Object val : ja) { + if (i > 0) { + sb.append('\n'); + } + sb.append(escape(val.toString())); + i++; + } + } else { + sb.append(escape(value.toString())); + } + + // Emit an array of similar keys + + } else if (value instanceof JSONArray) { + ja = (JSONArray) value; + for (Object val : ja) { + if (val instanceof JSONArray) { + sb.append('<'); + sb.append(key); + sb.append('>'); + sb.append(toString(val)); + sb.append("'); + } else { + sb.append(toString(val, key)); + } + } + } else if ("".equals(value)) { + sb.append('<'); + sb.append(key); + sb.append("/>"); + + // Emit a new tag + + } else { + sb.append(toString(value, key)); + } + } + if (tagName != null) { + + // Emit the close tag + sb.append("'); + } + return sb.toString(); + + } + + if (object != null) { + if (object.getClass().isArray()) { + object = new JSONArray(object); + } + + if (object instanceof JSONArray) { + ja = (JSONArray) object; + for (Object val : ja) { + // XML does not have good support for arrays. If an array + // appears in a place where XML is lacking, synthesize an + // element. + sb.append(toString(val, tagName == null ? "array" : tagName)); + } + return sb.toString(); + } + } + + string = (object == null) ? "null" : escape(object.toString()); + return (tagName == null) ? "\"" + string + "\"" + : (string.length() == 0) ? "<" + tagName + "/>" : "<" + tagName + + ">" + string + ""; + + } +} diff --git a/d4dj/src/main/java/org/json/XMLTokener.java b/d4dj/src/main/java/org/json/XMLTokener.java new file mode 100644 index 0000000..e45e747 --- /dev/null +++ b/d4dj/src/main/java/org/json/XMLTokener.java @@ -0,0 +1,365 @@ +package org.json; + +/* +Copyright (c) 2002 JSON.org + +Permission is hereby granted, free of charge, to any person obtaining a copy +of this software and associated documentation files (the "Software"), to deal +in the Software without restriction, including without limitation the rights +to use, copy, modify, merge, publish, distribute, sublicense, and/or sell +copies of the Software, and to permit persons to whom the Software is +furnished to do so, subject to the following conditions: + +The above copyright notice and this permission notice shall be included in all +copies or substantial portions of the Software. + +The Software shall be used for Good, not Evil. + +THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR +IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, +FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE +AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER +LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, +OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE +SOFTWARE. +*/ + +/** + * The XMLTokener extends the JSONTokener to provide additional methods + * for the parsing of XML texts. + * @author JSON.org + * @version 2015-12-09 + */ +public class XMLTokener extends JSONTokener { + + + /** The table of entity values. It initially contains Character values for + * amp, apos, gt, lt, quot. + */ + public static final java.util.HashMap entity; + + static { + entity = new java.util.HashMap(8); + entity.put("amp", XML.AMP); + entity.put("apos", XML.APOS); + entity.put("gt", XML.GT); + entity.put("lt", XML.LT); + entity.put("quot", XML.QUOT); + } + + /** + * Construct an XMLTokener from a string. + * @param s A source string. + */ + public XMLTokener(String s) { + super(s); + } + + /** + * Get the text in the CDATA block. + * @return The string up to the ]]>. + * @throws JSONException If the ]]> is not found. + */ + public String nextCDATA() throws JSONException { + char c; + int i; + StringBuilder sb = new StringBuilder(); + for (;;) { + c = next(); + if (end()) { + throw syntaxError("Unclosed CDATA"); + } + sb.append(c); + i = sb.length() - 3; + if (i >= 0 && sb.charAt(i) == ']' && + sb.charAt(i + 1) == ']' && sb.charAt(i + 2) == '>') { + sb.setLength(i); + return sb.toString(); + } + } + } + + + /** + * Get the next XML outer token, trimming whitespace. There are two kinds + * of tokens: the '<' character which begins a markup tag, and the content + * text between markup tags. + * + * @return A string, or a '<' Character, or null if there is no more + * source text. + * @throws JSONException + */ + public Object nextContent() throws JSONException { + char c; + StringBuilder sb; + do { + c = next(); + } while (Character.isWhitespace(c)); + if (c == 0) { + return null; + } + if (c == '<') { + return XML.LT; + } + sb = new StringBuilder(); + for (;;) { + if (c == '<' || c == 0) { + back(); + return sb.toString().trim(); + } + if (c == '&') { + sb.append(nextEntity(c)); + } else { + sb.append(c); + } + c = next(); + } + } + + + /** + * Return the next entity. These entities are translated to Characters: + * & ' > < ". + * @param ampersand An ampersand character. + * @return A Character or an entity String if the entity is not recognized. + * @throws JSONException If missing ';' in XML entity. + */ + public Object nextEntity(char ampersand) throws JSONException { + StringBuilder sb = new StringBuilder(); + for (;;) { + char c = next(); + if (Character.isLetterOrDigit(c) || c == '#') { + sb.append(Character.toLowerCase(c)); + } else if (c == ';') { + break; + } else { + throw syntaxError("Missing ';' in XML entity: &" + sb); + } + } + String string = sb.toString(); + Object object = entity.get(string); + return object != null ? object : ampersand + string + ";"; + } + + + /** + * Returns the next XML meta token. This is used for skipping over + * and structures. + * @return Syntax characters (< > / = ! ?) are returned as + * Character, and strings and names are returned as Boolean. We don't care + * what the values actually are. + * @throws JSONException If a string is not properly closed or if the XML + * is badly structured. + */ + public Object nextMeta() throws JSONException { + char c; + char q; + do { + c = next(); + } while (Character.isWhitespace(c)); + switch (c) { + case 0: + throw syntaxError("Misshaped meta tag"); + case '<': + return XML.LT; + case '>': + return XML.GT; + case '/': + return XML.SLASH; + case '=': + return XML.EQ; + case '!': + return XML.BANG; + case '?': + return XML.QUEST; + case '"': + case '\'': + q = c; + for (;;) { + c = next(); + if (c == 0) { + throw syntaxError("Unterminated string"); + } + if (c == q) { + return Boolean.TRUE; + } + } + default: + for (;;) { + c = next(); + if (Character.isWhitespace(c)) { + return Boolean.TRUE; + } + switch (c) { + case 0: + case '<': + case '>': + case '/': + case '=': + case '!': + case '?': + case '"': + case '\'': + back(); + return Boolean.TRUE; + } + } + } + } + + + /** + * Get the next XML Token. These tokens are found inside of angle + * brackets. It may be one of these characters: / > = ! ? or it + * may be a string wrapped in single quotes or double quotes, or it may be a + * name. + * @return a String or a Character. + * @throws JSONException If the XML is not well formed. + */ + public Object nextToken() throws JSONException { + char c; + char q; + StringBuilder sb; + do { + c = next(); + } while (Character.isWhitespace(c)); + switch (c) { + case 0: + throw syntaxError("Misshaped element"); + case '<': + throw syntaxError("Misplaced '<'"); + case '>': + return XML.GT; + case '/': + return XML.SLASH; + case '=': + return XML.EQ; + case '!': + return XML.BANG; + case '?': + return XML.QUEST; + +// Quoted string + + case '"': + case '\'': + q = c; + sb = new StringBuilder(); + for (;;) { + c = next(); + if (c == 0) { + throw syntaxError("Unterminated string"); + } + if (c == q) { + return sb.toString(); + } + if (c == '&') { + sb.append(nextEntity(c)); + } else { + sb.append(c); + } + } + default: + +// Name + + sb = new StringBuilder(); + for (;;) { + sb.append(c); + c = next(); + if (Character.isWhitespace(c)) { + return sb.toString(); + } + switch (c) { + case 0: + return sb.toString(); + case '>': + case '/': + case '=': + case '!': + case '?': + case '[': + case ']': + back(); + return sb.toString(); + case '<': + case '"': + case '\'': + throw syntaxError("Bad character in a name"); + } + } + } + } + + + /** + * Skip characters until past the requested string. + * If it is not found, we are left at the end of the source with a result of false. + * @param to A string to skip past. + * @throws JSONException + */ + public boolean skipPast(String to) throws JSONException { + boolean b; + char c; + int i; + int j; + int offset = 0; + int length = to.length(); + char[] circle = new char[length]; + + /* + * First fill the circle buffer with as many characters as are in the + * to string. If we reach an early end, bail. + */ + + for (i = 0; i < length; i += 1) { + c = next(); + if (c == 0) { + return false; + } + circle[i] = c; + } + + /* We will loop, possibly for all of the remaining characters. */ + + for (;;) { + j = offset; + b = true; + + /* Compare the circle buffer with the to string. */ + + for (i = 0; i < length; i += 1) { + if (circle[j] != to.charAt(i)) { + b = false; + break; + } + j += 1; + if (j >= length) { + j -= length; + } + } + + /* If we exit the loop with b intact, then victory is ours. */ + + if (b) { + return true; + } + + /* Get the next character. If there isn't one, then defeat is ours. */ + + c = next(); + if (c == 0) { + return false; + } + /* + * Shove the character in the circle buffer and advance the + * circle offset. The offset is mod n. + */ + circle[offset] = c; + offset += 1; + if (offset >= length) { + offset -= length; + } + } + } +} diff --git a/d4dj/src/main/java/sig/utils/Audio.java b/d4dj/src/main/java/sig/utils/Audio.java new file mode 100644 index 0000000..8e7006c --- /dev/null +++ b/d4dj/src/main/java/sig/utils/Audio.java @@ -0,0 +1,219 @@ +package sig.utils; +import java.util.ArrayList; +import java.util.List; + +import javax.sound.sampled.AudioSystem; +import javax.sound.sampled.BooleanControl; +import javax.sound.sampled.CompoundControl; +import javax.sound.sampled.Control; +import javax.sound.sampled.Control.Type; +import javax.sound.sampled.FloatControl; +import javax.sound.sampled.Line; +import javax.sound.sampled.LineUnavailableException; +import javax.sound.sampled.Mixer; +import javax.sound.sampled.Mixer.Info; + +public class Audio { + + public static void main(String[] args) throws Exception { + System.out.println(getHierarchyInfo()); + System.out.println(getMasterOutputVolume()); + } + + public static void setMasterOutputVolume(float value) { + if (value < 0 || value > 1) + throw new IllegalArgumentException( + "Volume can only be set to a value from 0 to 1. Given value is illegal: " + value); + Line line = getMasterOutputLine(); + if (line == null) throw new RuntimeException("Master output port not found"); + boolean opened = open(line); + try { + FloatControl control = getVolumeControl(line); + if (control == null) + throw new RuntimeException("Volume control not found in master port: " + toString(line)); + control.setValue(value); + } finally { + if (opened) line.close(); + } + } + + public static Float getMasterOutputVolume() { + Line line = getMasterOutputLine(); + if (line == null) return null; + boolean opened = open(line); + try { + FloatControl control = getVolumeControl(line); + if (control == null) return null; + return control.getValue(); + } finally { + if (opened) line.close(); + } + } + + public static void setMasterOutputMute(boolean value) { + Line line = getMasterOutputLine(); + if (line == null) throw new RuntimeException("Master output port not found"); + boolean opened = open(line); + try { + BooleanControl control = getMuteControl(line); + if (control == null) + throw new RuntimeException("Mute control not found in master port: " + toString(line)); + control.setValue(value); + } finally { + if (opened) line.close(); + } + } + + public static Boolean getMasterOutputMute() { + Line line = getMasterOutputLine(); + if (line == null) return null; + boolean opened = open(line); + try { + BooleanControl control = getMuteControl(line); + if (control == null) return null; + return control.getValue(); + } finally { + if (opened) line.close(); + } + } + + public static Line getMasterOutputLine() { + for (Mixer mixer : getMixers()) { + for (Line line : getAvailableOutputLines(mixer)) { + if (line.getLineInfo().toString().contains("Master")) return line; + } + } + return null; + } + + public static FloatControl getVolumeControl(Line line) { + if (!line.isOpen()) throw new RuntimeException("Line is closed: " + toString(line)); + return (FloatControl) findControl(FloatControl.Type.VOLUME, line.getControls()); + } + + public static BooleanControl getMuteControl(Line line) { + if (!line.isOpen()) throw new RuntimeException("Line is closed: " + toString(line)); + return (BooleanControl) findControl(BooleanControl.Type.MUTE, line.getControls()); + } + + private static Control findControl(Type type, Control... controls) { + if (controls == null || controls.length == 0) return null; + for (Control control : controls) { + if (control.getType().equals(type)) return control; + if (control instanceof CompoundControl) { + CompoundControl compoundControl = (CompoundControl) control; + Control member = findControl(type, compoundControl.getMemberControls()); + if (member != null) return member; + } + } + return null; + } + + public static List getMixers() { + Info[] infos = AudioSystem.getMixerInfo(); + List mixers = new ArrayList(infos.length); + for (Info info : infos) { + Mixer mixer = AudioSystem.getMixer(info); + mixers.add(mixer); + } + return mixers; + } + + public static List getAvailableOutputLines(Mixer mixer) { + return getAvailableLines(mixer, mixer.getTargetLineInfo()); + } + + public static List getAvailableInputLines(Mixer mixer) { + return getAvailableLines(mixer, mixer.getSourceLineInfo()); + } + + private static List getAvailableLines(Mixer mixer, Line.Info[] lineInfos) { + List lines = new ArrayList(lineInfos.length); + for (Line.Info lineInfo : lineInfos) { + Line line; + line = getLineIfAvailable(mixer, lineInfo); + if (line != null) lines.add(line); + } + return lines; + } + + public static Line getLineIfAvailable(Mixer mixer, Line.Info lineInfo) { + try { + return mixer.getLine(lineInfo); + } catch (LineUnavailableException ex) { + return null; + } + } + + public static String getHierarchyInfo() { + StringBuilder sb = new StringBuilder(); + for (Mixer mixer : getMixers()) { + sb.append("Mixer: ").append(toString(mixer)).append("\n"); + + for (Line line : getAvailableOutputLines(mixer)) { + sb.append(" OUT: ").append(toString(line)).append("\n"); + boolean opened = open(line); + for (Control control : line.getControls()) { + sb.append(" Control: ").append(toString(control)).append("\n"); + if (control instanceof CompoundControl) { + CompoundControl compoundControl = (CompoundControl) control; + for (Control subControl : compoundControl.getMemberControls()) { + sb.append(" Sub-Control: ").append(toString(subControl)).append("\n"); + } + } + } + if (opened) line.close(); + } + + for (Line line : getAvailableOutputLines(mixer)) { + sb.append(" IN: ").append(toString(line)).append("\n"); + boolean opened = open(line); + for (Control control : line.getControls()) { + sb.append(" Control: ").append(toString(control)).append("\n"); + if (control instanceof CompoundControl) { + CompoundControl compoundControl = (CompoundControl) control; + for (Control subControl : compoundControl.getMemberControls()) { + sb.append(" Sub-Control: ").append(toString(subControl)).append("\n"); + } + } + } + if (opened) line.close(); + } + + sb.append("\n"); + } + return sb.toString(); + } + + public static boolean open(Line line) { + if (line.isOpen()) return false; + try { + line.open(); + } catch (LineUnavailableException ex) { + return false; + } + return true; + } + + public static String toString(Control control) { + if (control == null) return null; + return control.toString() + " (" + control.getType().toString() + ")"; + } + + public static String toString(Line line) { + if (line == null) return null; + Line.Info info = line.getLineInfo(); + return info.toString();// + " (" + line.getClass().getSimpleName() + ")"; + } + + public static String toString(Mixer mixer) { + if (mixer == null) return null; + StringBuilder sb = new StringBuilder(); + Info info = mixer.getMixerInfo(); + sb.append(info.getName()); + sb.append(" (").append(info.getDescription()).append(")"); + sb.append(mixer.isOpen() ? " [open]" : " [closed]"); + return sb.toString(); + } + +} \ No newline at end of file diff --git a/d4dj/src/main/java/sig/utils/DebugUtils.java b/d4dj/src/main/java/sig/utils/DebugUtils.java new file mode 100644 index 0000000..f318564 --- /dev/null +++ b/d4dj/src/main/java/sig/utils/DebugUtils.java @@ -0,0 +1,17 @@ +package sig.utils; + + +public class DebugUtils { + public static void showStackTrace() { + System.out.println("Trace:"+getStackTrace()); + } + + public static String getStackTrace() { + StackTraceElement[] stacktrace = new Throwable().getStackTrace(); + StringBuilder stack = new StringBuilder("Mini stack tracer:"); + for (int i=0;i0) { + AttributedString as = new AttributedString(message); + as.addAttribute(TextAttribute.FONT, font); + as.addAttribute(TextAttribute.KERNING,TextAttribute.KERNING_ON); + as.addAttribute(TextAttribute.WIDTH,TextAttribute.WIDTH_EXTENDED); + as.addAttribute(TextAttribute.TRACKING,0.5); + g.setColor(shadow_color); + Graphics2D g2 = (Graphics2D) g; + FontRenderContext frc = g2.getFontMetrics(font).getFontRenderContext(); + GlyphVector gv = font.createGlyphVector(frc, message); + Shape shape = gv.getOutline((int)(x+xoffset),(int)(y+yoffset)); + g2.setClip(null); + g2.setStroke(new BasicStroke(font_thickness + outline_thickness*2)); + g2.setColor(shadow_color); + g2.setRenderingHint( + RenderingHints.KEY_ANTIALIASING, + RenderingHints.VALUE_ANTIALIAS_ON); + g2.draw(shape); + GlyphVector gv2 = font.createGlyphVector(frc, message); + Shape shape2 = gv2.getOutline((int)(x+xoffset),(int)(y+yoffset)); + g2.setClip(null); + g2.setStroke(new BasicStroke(font_thickness)); + g2.setColor(text_color); + g2.setRenderingHint( + RenderingHints.KEY_ANTIALIASING, + RenderingHints.VALUE_ANTIALIAS_ON); + g2.draw(shape2); + g2.setColor(text_color); + g2.drawString(as.getIterator(),(int)(x+xoffset),(int)(y+yoffset)); + } + } + public static void drawHealthbar(Graphics g, Rectangle bounds, double pct, Color healthbarcol) { + g.setColor(Color.BLACK); + g.draw3DRect((int)bounds.getX(), (int)bounds.getY(), (int)bounds.getWidth(), (int)bounds.getHeight(), true); + g.setColor(healthbarcol); + g.fill3DRect((int)bounds.getX()+1, (int)bounds.getY()+1, (int)(bounds.getWidth()*pct)-1, (int)bounds.getHeight()-1, true); + } + + public static Color convertStringToColor(String s) { + String[] split = s.split(","); + if (split.length==3) { + return new Color( + Math.min(Math.abs(Integer.parseInt(split[0])),255), + Math.min(Math.abs(Integer.parseInt(split[1])),255), + Math.min(Math.abs(Integer.parseInt(split[2])),255)); + } else + if (split.length==4) { + return new Color( + Math.min(Math.abs(Integer.parseInt(split[0])),255), + Math.min(Math.abs(Integer.parseInt(split[1])),255), + Math.min(Math.abs(Integer.parseInt(split[2])),255), + Math.min(Math.abs(Integer.parseInt(split[3])),255)); + } else { + System.out.println("WARNING! Invalid Color string specified ("+s+")."); + return null; + } + } + + public static void drawImage(Graphics g, Image img, double x, double y, Color blend_col, ImageObserver source) { + BufferedImage tmp = new BufferedImage(img.getWidth(source),img.getHeight(source),BufferedImage.TYPE_INT_ARGB); + Graphics2D g2 = tmp.createGraphics(); + g2.drawImage(img, 0, 0, null); + g2.setComposite(AlphaComposite.SrcAtop); + g2.setColor(blend_col); + g2.fillRect(0, 0, img.getWidth(source), img.getHeight(source)); + g2.dispose(); + g.drawImage(tmp,(int)x,(int)y,source); + } + + public static void drawImageScaled(Graphics g, Image img, double x, double y, double xsize, double ysize, Color blend_col, ImageObserver source) { + BufferedImage tmp = new BufferedImage(img.getWidth(source),img.getHeight(source),BufferedImage.TYPE_INT_ARGB); + Graphics2D g2 = tmp.createGraphics(); + g2.drawImage(img, 0, 0, null); + g2.setComposite(AlphaComposite.SrcAtop); + g2.setColor(blend_col); + g2.fillRect(0, 0, img.getWidth(source), img.getHeight(source)); + g2.dispose(); + g.drawImage(tmp,(int)x,(int)y,(int)xsize,(int)ysize,source); + } + + public static Color invertColor(Color c) { + return new Color(255-c.getRed(),255-c.getGreen(),255-c.getBlue(),255); + } +} diff --git a/d4dj/src/main/java/sig/utils/FileUtils.java b/d4dj/src/main/java/sig/utils/FileUtils.java new file mode 100644 index 0000000..0b80e54 --- /dev/null +++ b/d4dj/src/main/java/sig/utils/FileUtils.java @@ -0,0 +1,380 @@ +package sig.utils; +import java.io.BufferedReader; +import java.io.File; +import java.io.FileInputStream; +import java.io.FileOutputStream; +import java.io.FileReader; +import java.io.FileWriter; +import java.io.IOException; +import java.io.InputStream; +import java.io.InputStreamReader; +import java.io.OutputStream; +import java.io.OutputStreamWriter; +import java.io.PrintWriter; +import java.io.Reader; +import java.io.Writer; +import java.net.ConnectException; +import java.net.HttpURLConnection; +import java.net.URL; +import java.net.URLEncoder; +import java.nio.channels.Channels; +import java.nio.channels.FileChannel; +import java.nio.channels.ReadableByteChannel; +import java.nio.charset.Charset; +import java.nio.charset.StandardCharsets; +import java.util.ArrayList; +import java.util.HashMap; +import java.util.List; + +import org.json.JSONArray; +import org.json.JSONException; +import org.json.JSONObject; + +public class FileUtils { + public static String[] readFromFile(String filename) { + File file = new File(filename); + //System.out.println(file.getAbsolutePath()); + List contents= new ArrayList(); + if (file.exists()) { + try( + //FileReader fw = new FileReader(filename); + InputStream in = new FileInputStream(filename); + Reader reader = new InputStreamReader(in,StandardCharsets.UTF_8); + BufferedReader bw = new BufferedReader(reader);) + { + String readline = bw.readLine(); + do { + if (readline!=null) { + //System.out.println(readline); + contents.add(readline); + readline = bw.readLine(); + }} while (readline!=null); + in.close(); + reader.close(); + bw.close(); + } catch (IOException e) { + e.printStackTrace(); + } + } + return contents.toArray(new String[contents.size()]); + } + + private static String readAll(Reader rd) throws IOException { + StringBuilder sb = new StringBuilder(); + int cp; + while ((cp = rd.read()) != -1) { + sb.append((char) cp); + } + return sb.toString(); + } + + private static String readFilter(Reader rd, HashMap channel_ids) throws IOException { + StringBuilder sb = new StringBuilder(); + boolean allowed=false; + boolean quotation_mark=false; + boolean endquotation_mark=false; + boolean foundChannel=false; + boolean nextBrace=false; + boolean outputStuff=false; + String numb = ""; + int braceCount=0; + int channelCount=0; + int vals=0; + int cp; + while ((cp = rd.read()) != -1) { + if (braceCount==0) { + allowed=true; + } else + if (braceCount==1 && !quotation_mark){ + quotation_mark=true; + numb=""; + allowed=false; + } else + if (!endquotation_mark) { + if ((char)cp >= '0' && + (char)cp <= '9') { + allowed=false; + numb+=(char)cp; + } else { + allowed=false; + endquotation_mark=true; + try { + if (channel_ids.containsKey(Long.parseLong(numb))) { + if (channelCount>=1) { + sb.append(","); + } + sb.append("\""+numb+"\""); + foundChannel=true; + System.out.println("Found channel "+numb); + outputStuff=true; + } + } catch (NumberFormatException e) { + + } + } + } else + if (!nextBrace && foundChannel) { + allowed=true; + if ((char)cp == '{') { + nextBrace=true; + } + } else + if (foundChannel) { + allowed=true; + if (braceCount==1) { + allowed=false; + channelCount++; + quotation_mark=false; + endquotation_mark=false; + foundChannel=false; + nextBrace=false; + } + } else { + allowed=false; + if (braceCount==1) { + allowed=false; + quotation_mark=false; + endquotation_mark=false; + foundChannel=false; + nextBrace=false; + } + } + + /*if (outputStuff && vals++<1000) { + System.out.print((char)cp); + }*/ + if ((char)cp == '{') { + braceCount++; + //System.out.println("Brace count is "+braceCount+"."); + } else + if ((char)cp == '}') { + braceCount--; + //System.out.println("Brace count is "+braceCount+"."); + } + + if (allowed) { + sb.append((char) cp); + } + } + sb.append("}"); + //System.out.println("============="); + //System.out.println(sb.toString()); + return sb.toString(); + } + + public static JSONObject readJsonFromUrlWithFilter(String url, HashMap filter) throws IOException, JSONException { + return readJsonFromUrlWithFilter(url,filter,null,false); + } + + public static JSONObject readJsonFromFileWithFilter(String file, HashMap filter) throws IOException, JSONException { + InputStream is = new FileInputStream(new File(file)); + try { + BufferedReader rd = new BufferedReader(new InputStreamReader(is, Charset.forName("UTF-8"))); + String jsonText = readFilter(rd,filter); + JSONObject json = new JSONObject(jsonText); + jsonText=null; + return json; + } finally { + is.close(); + } + } + + public static JSONObject readJsonFromUrlWithFilter(String url, HashMap filter, String file, boolean writeToFile) throws IOException, JSONException { + InputStream is = new URL(url).openStream(); + try { + BufferedReader rd = new BufferedReader(new InputStreamReader(is, Charset.forName("UTF-8"))); + String jsonText = readFilter(rd,filter); + if (writeToFile) { + writetoFile(new String[]{jsonText},file); + } + JSONObject json = new JSONObject(jsonText); + return json; + } finally { + is.close(); + } + } + + public static JSONObject readJsonFromUrl(String url) throws IOException, JSONException { + return readJsonFromUrl(url,null,false); + } + + public static JSONArray readJsonArrayFromUrl(String url) throws IOException, JSONException { + return readJsonArrayFromUrl(url,null,false); + } + + public static JSONObject readJsonFromFile(String file) throws IOException, JSONException { + InputStream is = new FileInputStream(new File(file)); + try { + BufferedReader rd = new BufferedReader(new InputStreamReader(is, Charset.forName("UTF-8"))); + String jsonText = readAll(rd); + JSONObject json = new JSONObject(jsonText); + jsonText=null; + return json; + } finally { + is.close(); + } + } + + public static JSONObject readJsonFromUrl(String url, String file, boolean writeToFile) throws IOException, JSONException { + try { + InputStream is = new URL(url).openStream(); + BufferedReader rd = new BufferedReader(new InputStreamReader(is, Charset.forName("UTF-8"))); + String jsonText = readAll(rd); + if (writeToFile) { + writetoFile(new String[]{jsonText},file); + } + JSONObject json = new JSONObject(jsonText); + is.close(); + return json; + } catch (IOException e) { + return new JSONObject("{}"); + } + } + + public static JSONArray readJsonArrayFromUrl(String url, String file, boolean writeToFile) throws IOException, JSONException { + URL obj = new URL(url); + HttpURLConnection con = (HttpURLConnection) obj.openConnection(); + con.setRequestMethod("GET"); + int responseCode = con.getResponseCode(); + System.out.println("GET Response Code :: " + responseCode); + if (responseCode == HttpURLConnection.HTTP_OK) { // success + BufferedReader in = new BufferedReader(new InputStreamReader( + con.getInputStream())); + String inputLine; + StringBuffer response = new StringBuffer(); + + while ((inputLine = in.readLine()) != null) { + response.append(inputLine); + } + in.close(); + + // print result + System.out.println(response); + + return new JSONArray(response.toString()); + } else { + System.out.println("GET request not worked"); + return new JSONArray("[]"); + } + } + + public static void logToFile(String message, String filename) { + logToFile(message,filename,false); + } + + public static void logToFile(String message, String filename, boolean outputToChatLog) { + File file = new File(filename); + try { + + if (!file.exists()) { + file.createNewFile(); + } + OutputStream out = new FileOutputStream(file,true); + Writer writer = new OutputStreamWriter(out, StandardCharsets.UTF_8); + PrintWriter pw = new PrintWriter(writer); + + pw.println(message); + pw.flush(); + pw.close(); + } catch (IOException e) { + e.printStackTrace(); + } + } + + public static void writetoFile(String[] data, String filename) { + File file = new File(filename); + try { + + if (!file.exists()) { + file.createNewFile(); + } + + FileWriter fw = new FileWriter(file,false); + PrintWriter pw = new PrintWriter(fw); + + for (String s : data) { + pw.println(s); + } + pw.flush(); + pw.close(); + } catch (IOException e) { + e.printStackTrace(); + } + } + + public static void copyFile(File source, File dest) throws IOException { + FileChannel sourceChannel = null; + FileChannel destChannel = null; + try { + sourceChannel = new FileInputStream(source).getChannel(); + destChannel = new FileOutputStream(dest).getChannel(); + destChannel.transferFrom(sourceChannel, 0, sourceChannel.size()); + }finally{ + sourceChannel.close(); + destChannel.close(); + } + } + + public static void copyFileDir(File sourcedir, File destdir) throws IOException { + FileChannel sourceChannel = null; + FileChannel destChannel = null; + destdir.mkdirs(); + try { + if (sourcedir.exists()) { + for (String name : sourcedir.list()) { + File f = new File(sourcedir,name); + sourceChannel = new FileInputStream(f).getChannel(); + destChannel = new FileOutputStream(new File(destdir,name)).getChannel(); + destChannel.transferFrom(sourceChannel, 0, sourceChannel.size()); + sourceChannel.close(); + destChannel.close(); + } + } + } + finally{ + + } + } + + public static void deleteFile(File filename) { + File file = filename; + if (file.exists()) { + //System.out.println("Trying to delete "+file); + if (file.isDirectory()) { + for (String name : file.list()) { + File f = new File(file,name); + deleteFile(f); + } + } + file.delete(); + //System.out.println(file+" deleted"); + } + } + + public static void deleteFile(String filename) { + File file = new File(filename); + deleteFile(file); + } + + + public static void downloadFileFromUrl(String url, String file) throws IOException, JSONException { + File filer = new File(file); + filer.createNewFile(); + + URL website = new URL(url); + HttpURLConnection connection = (HttpURLConnection) website.openConnection(); + /*for (String s : connection.getHeaderFields().keySet()) { + System.out.println(s+": "+connection.getHeaderFields().get(s)); + }*/ + connection.setRequestMethod("GET"); + //connection.setRequestProperty("Content-Type", "application/json"); + try { + ReadableByteChannel rbc = Channels.newChannel(connection.getInputStream()); + FileOutputStream fos = new FileOutputStream(file); + fos.getChannel().transferFrom(rbc, 0, Long.MAX_VALUE); + fos.close(); + } catch (ConnectException e) { + System.out.println("Failed to connect, moving on..."); + } + } +} diff --git a/d4dj/src/main/java/sig/utils/GithubUtils.java b/d4dj/src/main/java/sig/utils/GithubUtils.java new file mode 100644 index 0000000..7cd1579 --- /dev/null +++ b/d4dj/src/main/java/sig/utils/GithubUtils.java @@ -0,0 +1,35 @@ +package sig.utils; + +import java.io.IOException; +import java.util.Arrays; + +import org.json.JSONArray; +import org.json.JSONException; +import org.json.JSONObject; + +public class GithubUtils { + public static int getSizeOfFileFromLatestGithubCommit(String filename) { + try { + JSONObject data = FileUtils.readJsonFromUrl("https://api.github.com/repos/sigonasr2/sigIRCv2"); + String url = data.getString("commits_url").replace("{/sha}", ""); + JSONArray data_array = FileUtils.readJsonArrayFromUrl(url); + JSONObject dat = data_array.getJSONObject(0); + JSONObject datapoint1 = dat.getJSONObject("commit"); + datapoint1 = datapoint1.getJSONObject("tree"); + url = datapoint1.getString("url"); + data = FileUtils.readJsonFromUrl(url); + data_array = data.getJSONArray("tree"); + for (int i=0;i=0) { + String piece1 = sourcestring.substring(0,pos); + String piece2 = sourcestring.substring(pos+findstring.length(),sourcestring.length()); + //basemsg = basemsg.replaceFirst(e.getEmoteName(),e.getSpaceFiller()); + sourcestring = piece1+replacestring+piece2; + } + return sourcestring; + } + + public static boolean isAlphanumeric(String str) { + return str.matches("^[a-zA-Z0-9!\\-.?'\":,\\+ ]+$"); + } + + public static boolean isNumeric(String str) + { + if (str.length()>0) { + return str.matches("-?\\d+(\\.\\d+)?"); //match a number with optional '-' and decimal. + } else { + return false; + } + } + + public static boolean isInteger(String s, int radix) { + if(s.isEmpty()) return false; + for(int i = 0; i < s.length(); i++) { + if(i == 0 && s.charAt(i) == '-') { + if(s.length() == 1) return false; + else continue; + } + if(Character.digit(s.charAt(i),radix) < 0) return false; + } + return true; + } + + public static String convertSecondsToTimeFormat(int seconds) { + StringBuilder sb = new StringBuilder(); + int sec = seconds%60; + int min = (seconds/60)%60; + int hrs = (seconds/3600)%24; + if (hrs>0) { + if (hrs>=10) { + sb.append(hrs); + } else { + sb.append(0); + sb.append(hrs); + } + sb.append(":"); + } + if (min>=10) { + sb.append(min); + } else { + sb.append(0); + sb.append(min); + } + sb.append(":"); + if (sec>=10) { + sb.append(sec); + } else { + sb.append(0); + sb.append(sec); + } + return sb.toString(); + } + + /** + * Converts a three CSV value to RGB value. + */ + public static Color convertStringToColor(String col) { + String[] split = col.split(","); + return new Color(Integer.parseInt(split[0]),Integer.parseInt(split[1]),Integer.parseInt(split[2])); + } +} diff --git a/d4dj/src/main/java/sig/utils/TimeUtils.java b/d4dj/src/main/java/sig/utils/TimeUtils.java new file mode 100644 index 0000000..b0be37f --- /dev/null +++ b/d4dj/src/main/java/sig/utils/TimeUtils.java @@ -0,0 +1,32 @@ +package sig.utils; + +import java.text.DecimalFormat; +import java.util.Calendar; +import java.util.Date; + + +public class TimeUtils { + public static String GetTimeDifferenceFromCurrentDate(Date pastDate) { + long totalseconds = (Calendar.getInstance().getTimeInMillis()-pastDate.getTime())/1000; + //System.out.println("Total Seconds: "+totalseconds); + long seconds = (long)(totalseconds); + long minutes = (long)(seconds/60); + long hours = (long)(minutes/60); + long days = (long)(hours/24); + StringBuilder string = new StringBuilder(); + DecimalFormat df = new DecimalFormat("00"); + if (days>0) { + string.append(days); + } + if (hours>0) { + string.append(((string.length()>0)?":":"")+(hours%24)); + } + if (minutes>0) { + string.append(((string.length()>0)?":":"")+df.format((minutes%60))); + } + if (seconds>0) { + string.append(((string.length()>0)?":":"")+df.format((seconds%60))); + } + return string.toString(); + } +} diff --git a/d4dj/src/main/resources/readme.html b/d4dj/src/main/resources/readme.html new file mode 100644 index 0000000..8b27db3 --- /dev/null +++ b/d4dj/src/main/resources/readme.html @@ -0,0 +1,124 @@ + + + + Tess4J - Java Wrapper for Tesseract OCR API + + +
+

+ Tess4J +

+

+ DESCRIPTION +

+

+ Tess4J is a JNA wrapper for Tesseract OCR + API; it provides character recognition support for common image formats, + multi-page images, and PDF documents. The library has been developed and tested + on Windows and Linux. +

+

+ Tess4J is released and distributed under the + Apache License, v2.0. Its official homepage is at + http://tess4j.sourceforge.net. +

+

+ SOFTWARE REQUIREMENTS +

+

+ Java Runtime Environment, + JNA, and JAI-ImageIO + are required. Apache Maven and + JUnit are used for program building and unit testing. The Tesseract DLLs + were built with VS2019 (v142) and therefore depend on the + Visual C++ 2019 Redistributable Packages. +

+

+ INSTRUCTIONS +

+

+ Tesseract 5.0.0 and Leptonica 1.79 (via Lept4J) 32- and 64-bit + DLLs, language data for English, and sample images are bundled with the library. + Language data packs for + Tesseract should be decompressed and placed into the tessdata folder. +

+

+ The Linux shared object library (libtesseract.so) equivalent to the + DLL is available in Tesseract 5.0.0, which can be built from the source with the instructions given in Tesseract Wiki. +

+

+ To unit test, at the command line, execute: +

+
+

+ mvn test +

+
+

+ Support for PDF documents is available through either + GPL Ghostscript, which should be installed and included + in system path, or PDFBox, if Ghostscript is not available. +

+

+ Images to be OCRed should be scanned at resolution from at least 200 DPI (dot per + inch) to 400 DPI in monochrome (black&white) or grayscale. Scanning at higher + resolutions will not necessarily result in better recognition accuracy. The actual + success rates depend greatly on the quality of the scanned image. The typical settings + for scanning are 300 DPI and 1 bpp (bit per pixel) black&white or 8 bpp grayscale + uncompressed TIFF or PNG format. PNG is usually smaller in size than other image + formats and still keeps high quality due to its employing lossless data compression + algorithms; TIFF has the advantage of the ability to contain multiple images (pages) + in a file. +

+

+ Several built-in functions are also provided for merging several images or PDF files + into a single one for convenient OCR operations, or for splitting a PDF file into + smaller ones if it is too large, which can cause out-of-memory exceptions. +

+

+ CODE EXAMPLES +

+

+ The following code example shows common usage of the library. Make sure tessdata + folder is populated with appropriate language data files and the .jar + files are in the classpath. On Windows, the DLLs will be automatically extracted + from tess4j.jar to the default temporary directory and loaded. +

+
+ 
+package net.sourceforge.tess4j.example;
+
+import java.io.File;
+import net.sourceforge.tess4j.*;
+
+public class TesseractExample {
+    public static void main(String[] args) {
+        // ImageIO.scanForPlugins(); // for server environment
+        File imageFile = new File("eurotext.tif");
+        ITesseract instance = new Tesseract(); // JNA Interface Mapping
+        // ITesseract instance = new Tesseract1(); // JNA Direct Mapping
+        // File tessDataFolder = LoadLibs.extractTessResources("tessdata"); // Maven build only; only English data bundled
+        // instance.setDatapath(tessDataFolder.getPath());
+
+        try {
+            String result = instance.doOCR(imageFile);
+            System.out.println(result);
+        } catch (TesseractException e) {
+            System.err.println(e.getMessage());
+        }
+    }
+}
+
+
+

+ DOCUMENTATIONS +

+

+ Please visit the website for the library's documentations +

+
+
+ + diff --git a/d4dj/src/main/resources/tessdata/configs/alto b/d4dj/src/main/resources/tessdata/configs/alto new file mode 100644 index 0000000..0dd12a7 --- /dev/null +++ b/d4dj/src/main/resources/tessdata/configs/alto @@ -0,0 +1 @@ +tessedit_create_alto 1 diff --git a/d4dj/src/main/resources/tessdata/configs/api_config b/d4dj/src/main/resources/tessdata/configs/api_config new file mode 100644 index 0000000..5cd6ec0 --- /dev/null +++ b/d4dj/src/main/resources/tessdata/configs/api_config @@ -0,0 +1 @@ +tessedit_zero_rejection T diff --git a/d4dj/src/main/resources/tessdata/configs/bazaar b/d4dj/src/main/resources/tessdata/configs/bazaar new file mode 100644 index 0000000..1b2ee83 --- /dev/null +++ b/d4dj/src/main/resources/tessdata/configs/bazaar @@ -0,0 +1,4 @@ +load_system_dawg F +load_freq_dawg F +user_words_suffix user-words +user_patterns_suffix user-patterns diff --git a/d4dj/src/main/resources/tessdata/configs/digits b/d4dj/src/main/resources/tessdata/configs/digits new file mode 100644 index 0000000..6a329f8 --- /dev/null +++ b/d4dj/src/main/resources/tessdata/configs/digits @@ -0,0 +1 @@ +tessedit_char_whitelist 0123456789-. diff --git a/d4dj/src/main/resources/tessdata/configs/hocr b/d4dj/src/main/resources/tessdata/configs/hocr new file mode 100644 index 0000000..5ab372e --- /dev/null +++ b/d4dj/src/main/resources/tessdata/configs/hocr @@ -0,0 +1,2 @@ +tessedit_create_hocr 1 +hocr_font_info 0 diff --git a/d4dj/src/main/resources/tessdata/configs/lstmbox b/d4dj/src/main/resources/tessdata/configs/lstmbox new file mode 100644 index 0000000..a6f2ced --- /dev/null +++ b/d4dj/src/main/resources/tessdata/configs/lstmbox @@ -0,0 +1 @@ +tessedit_create_lstmbox 1 diff --git a/d4dj/src/main/resources/tessdata/configs/pdf b/d4dj/src/main/resources/tessdata/configs/pdf new file mode 100644 index 0000000..59645d7 --- /dev/null +++ b/d4dj/src/main/resources/tessdata/configs/pdf @@ -0,0 +1 @@ +tessedit_create_pdf 1 diff --git a/d4dj/src/main/resources/tessdata/configs/quiet b/d4dj/src/main/resources/tessdata/configs/quiet new file mode 100644 index 0000000..35b59a9 --- /dev/null +++ b/d4dj/src/main/resources/tessdata/configs/quiet @@ -0,0 +1 @@ +debug_file /dev/null diff --git a/d4dj/src/main/resources/tessdata/configs/tsv b/d4dj/src/main/resources/tessdata/configs/tsv new file mode 100644 index 0000000..dc52478 --- /dev/null +++ b/d4dj/src/main/resources/tessdata/configs/tsv @@ -0,0 +1 @@ +tessedit_create_tsv 1 diff --git a/d4dj/src/main/resources/tessdata/configs/txt b/d4dj/src/main/resources/tessdata/configs/txt new file mode 100644 index 0000000..5046f0b --- /dev/null +++ b/d4dj/src/main/resources/tessdata/configs/txt @@ -0,0 +1,3 @@ +# This config file should be used with other cofig files which creates renderers. +# usage example: tesseract eurotext.tif eurotext txt hocr pdf +tessedit_create_txt 1 diff --git a/d4dj/src/main/resources/tessdata/configs/unlv b/d4dj/src/main/resources/tessdata/configs/unlv new file mode 100644 index 0000000..d2e22f5 --- /dev/null +++ b/d4dj/src/main/resources/tessdata/configs/unlv @@ -0,0 +1,2 @@ +tessedit_write_unlv 1 +unlv_tilde_crunching T diff --git a/d4dj/src/main/resources/tessdata/configs/wordstrbox b/d4dj/src/main/resources/tessdata/configs/wordstrbox new file mode 100644 index 0000000..38cd41c --- /dev/null +++ b/d4dj/src/main/resources/tessdata/configs/wordstrbox @@ -0,0 +1 @@ +tessedit_create_wordstrbox 1 diff --git a/d4dj/src/main/resources/tessdata/eng.traineddata b/d4dj/src/main/resources/tessdata/eng.traineddata new file mode 100644 index 0000000..bbef467 Binary files /dev/null and b/d4dj/src/main/resources/tessdata/eng.traineddata differ diff --git a/d4dj/src/main/resources/tessdata/osd.traineddata b/d4dj/src/main/resources/tessdata/osd.traineddata new file mode 100644 index 0000000..527457c Binary files /dev/null and b/d4dj/src/main/resources/tessdata/osd.traineddata differ diff --git a/d4dj/src/main/resources/tessdata/pdf.ttf b/d4dj/src/main/resources/tessdata/pdf.ttf new file mode 100644 index 0000000..8affa23 Binary files /dev/null and b/d4dj/src/main/resources/tessdata/pdf.ttf differ diff --git a/d4dj/src/main/resources/versionchanges.txt b/d4dj/src/main/resources/versionchanges.txt new file mode 100644 index 0000000..78904ca --- /dev/null +++ b/d4dj/src/main/resources/versionchanges.txt @@ -0,0 +1,199 @@ +Tess4J Change Summary + +Version 0.1 - initial release (14 Aug 2010): +- Java JNA-based wrapper for Tesseract OCR DLL 2.04 +- Support uncompressed, binary TIFF images + +Version 0.2 (16 Aug 2010): +- Add support for more image formats (PNG, BMP, GIF, PDF, JPEG) +- Add support for compressed, grayscale and colored images + +Version 0.3 (22 Aug 2010): +- Include API support for BufferedImage +- Clean up codes. Remove unsupported API and files +- Document the API + +Version 0.3.1 (26 Aug 2010): +- Send only pixel data, not whole image data, to Tesseract engine, to fix a bug that has erroneously put some words at beginning of line towards end of line + +Version 0.4 (1 Nov 2010): +- Add JNA Direct Mapping calls, which can provide performance near that of custom JNI + +Version 1.0 (30 October 2012): +- Upgrade to Tesseract 3.02 (r798), which is not backward compatible with Tesseract 2.04. +- Implement a new JNA wrapper for the new Tesseract OCR API +- Add more unit test cases +- Update documentation + +Version 1.1 (3 March 2013) +- Update Tesseract DLL to r828 +- Additional API methods, image helper methods, and unit test cases +- Improve handling of Unicode character encoding +- Fix memory leaks +- Add support for determining skew angle and image rotation + +Version 1.2 (22 September 2013) +- Update Tesseract DLL to r866 +- More efficient OCR of multiple images +- Various minor improvements +- Update JNA to v4.0 + +Version 1.3 (31 May 2014) +- Update JNA to v4.1.0 +- Update Ghost4J to v0.5.1 +- Refactoring +- Bundle Tesseract and Leptonica 64-bit DLLs + +Version 1.4 (18 January 2015) +- Refactor to reduce code duplication +- Embed Windows native resources in JAR +- Autoload Windows native libraries + +Version 1.4.1 (24 January 2015) +- Enable use of jna.library.path system property for user-customizable path + +Version 1.5 (13 March 2015) +- Add UNLV zone file support +- Refactor + +Version 2.0 (29 March 2015) +- Upgrade to Tesseract 3.03 (r1050), which is compatible with Tesseract 3.03RC on Linux +- Refactor Tesseract class for extensibility and thread-safety +- Update English language data for Tesseract 3.02 + +Version 3.0 (25 December 2015) +- Upgrade to Tesseract 3.04 (953523b) +- Include Lept4J library +- Incorporate slf4j and logback libraries for logging +- Make GhostScript calls thread safe + +Version 3.1 (21 March 2016) +- Update Tesseract to 3.04.01 (4ef68a0) +- Use Lept4J-1.1.2 (Leptonica 1.72) +- Update JNA to 4.2.2 +- Update Ghost4J to 1.0.1 +- Delete ResultRenderer after use to release PDF file handler + +Version 3.2 (15 May 2016) +- Revert JNA to 4.1.0 due to "Invalid calling convention 63" errors invoking GhostScript via Ghost4J on Linux +- Update Lept4J to 1.2.2 (Leptonica 1.73) +- Recompile Tesseract 3.04.01 DLL against Leptonica 1.73 +- Update GhostScript Windows binary to 9.19 + +Version 3.2.1 (29 May 2016) +- Properly release Box and Boxa resources +- Update Lept4J to 1.2.3 + +Version 3.2.2 (16 February 2017) +- Update GhostScript to 9.20 +- Fix possible NPE with PDF-related codes +- Update dependencies +- Additional image utility methods + +Version 3.3.0 (16 February 2017) +- Upgrade to Tesseract 3.05 (2ca5d0a) +- Update Lept4J to 1.3.0 (Leptonica 1.74.1) + +Version 3.3.1 (23 March 2017) +- Update Lept4J to 1.3.1 +- Update other dependencies + +Version 3.4.0 (1 June 2017) +- Upgrade to Tesseract 3.05.01 (2158661) +- Update Lept4J to 1.4.0 +- Add support for jboss-vfs protocol + +Version 3.4.1 (22 September 2017) +- Not extract/copy native resource if it exists and has same file size +- Update Tesseract 3.05.01 (e2e79c4); link against Leptonica 1.74.4 +- Update Lept4J to 1.6.1 + +Version 3.4.2 (14 November 2017) +- Update Lept4J to 1.6.2 +- Update GhostScript to 9.22 +- Improve handling of PDF files in multi-threaded environment +- Lift limits on number of pages in PDF +- Use TESSDATA_PREFIX environment variable by default, if defined + +Version 3.4.3 (14 January 2018) +- Not extract/copy resource if it exists and has same file size + +Version 3.4.4 (22 February 2018) +- Exclude logback.xml from JAR +- Add image rotate and deskew methods +- Update Lept4J to 1.6.3 + +Version 3.4.5 (21 March 2018) +- Remove GS DLL due to license incompatibility +- Use PDFBox + +Version 3.4.6 (25 March 2018) +- Update PDFBox dependencies + +Version 3.4.7 (16 April 2018) +- Update dependencies for Java 9 fixes + +Version 3.4.8 (2 May 2018) +- Fix a path issue when extracting resources from JAR to temp directory on Windows server + +Version 4.0.0 (28 April 2018) +- Upgrade to Tesseract 4.0.0-beta.1 (45bb942) +- Update Lept4J to 1.9.3 (Leptonica 1.75.3) + +Version 4.0.1 (2 May 2018) +- Fix a path issue when extracting resources from JAR to temp directory on Windows server + +Version 4.0.2 (3 May 2018) +- Replace JNA string constant Platform.RESOURCE_PREFIX +- Update jai-imageio url +- Update Lept4J to 1.9.4 + +Version 4.1.0 (20 July 2018) +- Upgrade to Tesseract 4.0.0-beta.3 (b502bbf) +- Update Lept4J to 1.10.0 +- Improve handling of PDF +- Refactor + +Version 4.1.1 (28 July 2018) +- Properly dispose of resources and temporary image files +- Clean up code and test output resources +- Fix NPE in Java 10 + +Version 4.2.0 (11 August 2018) +- Upgrade to Tesseract 4.0.0-beta.4 (fd49206) + +Version 4.2.1 (11 August 2018) +- Recompile using JDK8 to avoid NoSuchMethodError: Method flip() does not exist in class java.nio.ByteBuffer +- Use explicit cast for compatibility with covariant return type on JDK 9's ByteBuffer methods, e.g., flip() + +Version 4.2.2 (3 September 2018) +- Fix Invalid memory access exception due of incorrect bit depth value + +Version 4.2.3 (17 October 2018) +- Update pdfbox dependencies + +Version 4.3.0 (29 October 2018) +- Upgrade to Tesseract 4.0.0 (5131699) + +Version 4.3.1 (26 December 2018) +- Fix Windows build +- Improve RenderedImage to ByteBuffer conversion + +Version 4.4.0 (13 July 2019) +- Upgrade to Tesseract 4.1.0 (5280bbc) +- Upgrade to Leptonica 1.78.0 (lept4j-1.12.2) +- Update dependencies + +Version 4.4.1 (7 October 2019) +- Use tessdata_fast data +- Use Native.loadLibrary method for backward compatibility with older JNA versions + +Version 4.5.0 (27 December 2019) +- Upgrade to Tesseract 4.1.1 (7510304) + +Version 4.5.1 (3 January 2020) +- Update Leptonica 1.79.0 (lept4j-1.13.0) +- Fix Permission denied issue with Ghostscript 9.50 + +Version 5.0.0-SNAPSHOT (11 July 2020) +- Upgrade to Tesseract 5.0.0-alpha (135c8a4) \ No newline at end of file diff --git a/d4dj/src/main/resources/win32-x86-64/libtesseract500.dll b/d4dj/src/main/resources/win32-x86-64/libtesseract500.dll new file mode 100644 index 0000000..085a03e Binary files /dev/null and b/d4dj/src/main/resources/win32-x86-64/libtesseract500.dll differ diff --git a/d4dj/src/main/resources/win32-x86/libtesseract500.dll b/d4dj/src/main/resources/win32-x86/libtesseract500.dll new file mode 100644 index 0000000..b472138 Binary files /dev/null and b/d4dj/src/main/resources/win32-x86/libtesseract500.dll differ diff --git a/d4dj/src/test/java/d4dj/d4dj/AppTest.java b/d4dj/src/test/java/d4dj/d4dj/AppTest.java new file mode 100644 index 0000000..bdfe7f8 --- /dev/null +++ b/d4dj/src/test/java/d4dj/d4dj/AppTest.java @@ -0,0 +1,20 @@ +package d4dj.d4dj; + +import static org.junit.Assert.assertTrue; + +import org.junit.Test; + +/** + * Unit test for simple App. + */ +public class AppTest +{ + /** + * Rigorous Test :-) + */ + @Test + public void shouldAnswerWithTrue() + { + assertTrue( true ); + } +} diff --git a/d4dj/src/test/java/net/sourceforge/tess4j/ProgressMonitor.java b/d4dj/src/test/java/net/sourceforge/tess4j/ProgressMonitor.java new file mode 100644 index 0000000..95b3496 --- /dev/null +++ b/d4dj/src/test/java/net/sourceforge/tess4j/ProgressMonitor.java @@ -0,0 +1,75 @@ +/** + * Copyright @ 2014 Quan Nguyen + * + * Licensed under the Apache License, Version 2.0 (the "License"); you may not + * use this file except in compliance with the License. You may obtain a copy of + * the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, WITHOUT + * WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the + * License for the specific language governing permissions and limitations under + * the License. + */ +package net.sourceforge.tess4j; + +import com.sun.jna.Pointer; +import net.sourceforge.tess4j.util.LoggHelper; +import org.slf4j.Logger; +import org.slf4j.LoggerFactory; + +import static net.sourceforge.tess4j.ITessAPI.TRUE; + +class ProgressMonitor extends Thread { + + ITessAPI.ETEXT_DESC monitor; + StringBuilder outputMessage = new StringBuilder(); + + private static final Logger logger = LoggerFactory.getLogger(new LoggHelper().toString()); + + public ProgressMonitor(ITessAPI.ETEXT_DESC monitor) { + this.monitor = monitor; + } + + public String getMessage() { + return outputMessage.toString(); + } + + @Override + public void run() { + try { + while (true) { + logger.info("ocr alive: " + (monitor.ocr_alive == TRUE)); + logger.info("progress: " + monitor.progress); + outputMessage.append(monitor.more_to_come); + if (monitor.progress >= 100) { + break; + } + Thread.sleep(100); + } + } catch (Exception ioe) { + ioe.printStackTrace(); + } + } + + /** + * Cancels OCR operation. + */ + public void cancel() { + monitor.cancel = new ITessAPI.CANCEL_FUNC() { + @Override + public boolean invoke(Pointer cancel_this, int words) { + return true; + } + }; + } + + /** + * Resets cancel flag. + */ + public void reset() { + monitor.cancel = null; + } +} diff --git a/d4dj/src/test/java/net/sourceforge/tess4j/TessAPI1Test.java b/d4dj/src/test/java/net/sourceforge/tess4j/TessAPI1Test.java new file mode 100644 index 0000000..7b2cfac --- /dev/null +++ b/d4dj/src/test/java/net/sourceforge/tess4j/TessAPI1Test.java @@ -0,0 +1,704 @@ +/** + * Copyright @ 2012 Quan Nguyen + * + * Licensed under the Apache License, Version 2.0 (the "License"); you may not + * use this file except in compliance with the License. You may obtain a copy of + * the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, WITHOUT + * WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the + * License for the specific language governing permissions and limitations under + * the License. + */ +package net.sourceforge.tess4j; + +import static org.junit.Assert.assertArrayEquals; + +import java.awt.image.BufferedImage; +import java.io.BufferedReader; +import java.io.File; +import java.io.FileInputStream; +import java.io.FileReader; +import java.nio.ByteBuffer; +import java.nio.FloatBuffer; +import java.nio.IntBuffer; +import java.util.Arrays; + +import javax.imageio.ImageIO; + +import net.sourceforge.tess4j.util.LoggHelper; +import net.sourceforge.tess4j.util.Utils; +import net.sourceforge.tess4j.util.ImageIOHelper; + +import com.ochafik.lang.jnaerator.runtime.NativeSize; +import com.sun.jna.NativeLong; + +import org.junit.After; +import org.junit.AfterClass; +import org.junit.Before; +import org.junit.BeforeClass; +import org.junit.Test; + +import com.sun.jna.Pointer; +import com.sun.jna.StringArray; +import com.sun.jna.ptr.PointerByReference; +import net.sourceforge.lept4j.Box; +import net.sourceforge.lept4j.Boxa; +import static net.sourceforge.lept4j.ILeptonica.L_CLONE; +import net.sourceforge.lept4j.Leptonica1; +import net.sourceforge.lept4j.Pix; +import net.sourceforge.lept4j.util.LeptUtils; + +import net.sourceforge.tess4j.ITessAPI.*; +import org.slf4j.Logger; +import org.slf4j.LoggerFactory; + +import static net.sourceforge.tess4j.ITessAPI.FALSE; +import static net.sourceforge.tess4j.ITessAPI.TRUE; +import static org.junit.Assert.assertEquals; +import static org.junit.Assert.assertTrue; + +public class TessAPI1Test { + + private static final Logger logger = LoggerFactory.getLogger(new LoggHelper().toString()); + private final String datapath = "src/main/resources/tessdata"; + private final String testResourcesDataPath = "src/test/resources/test-data"; + String language = "eng"; + String expOCRResult = "The (quick) [brown] {fox} jumps!\nOver the $43,456.78 #90 dog"; + + TessBaseAPI handle; + + @BeforeClass + public static void setUpClass() throws Exception { + } + + @AfterClass + public static void tearDownClass() throws Exception { + } + + @Before + public void setUp() { + handle = TessAPI1.TessBaseAPICreate(); + } + + @After + public void tearDown() { + TessAPI1.TessBaseAPIDelete(handle); + } + + /** + * Test of TessBaseAPIRect method, of class TessAPI1. + * + * @throws Exception while processing the image + */ + @Test + public void testTessBaseAPIRect() throws Exception { + logger.info("TessBaseAPIRect"); + String expResult = expOCRResult; + File tiff = new File(this.testResourcesDataPath, "eurotext.tif"); + BufferedImage image = ImageIO.read(tiff); // require jai-imageio lib to read TIFF + ByteBuffer buf = ImageIOHelper.convertImageData(image); + int bpp = image.getColorModel().getPixelSize(); + int bytespp = bpp / 8; + int bytespl = (int) Math.ceil(image.getWidth() * bpp / 8.0); + TessAPI1.TessBaseAPIInit3(handle, datapath, language); + TessAPI1.TessBaseAPISetPageSegMode(handle, TessPageSegMode.PSM_AUTO); + Pointer utf8Text = TessAPI1.TessBaseAPIRect(handle, buf, bytespp, bytespl, 0, 0, image.getWidth(), image.getHeight()); + String result = utf8Text.getString(0); + TessAPI1.TessDeleteText(utf8Text); + logger.info(result); + assertEquals(expResult, result.substring(0, expResult.length())); + } + + /** + * Test of TessBaseAPIGetUTF8Text method, of class TessAPI1. + * + * @throws Exception while processing the image + */ + @Test + public void testTessBaseAPIGetUTF8Text() throws Exception { + logger.info("TessBaseAPIGetUTF8Text"); + String expResult = expOCRResult; + File tiff = new File(this.testResourcesDataPath, "eurotext.tif"); + BufferedImage image = ImageIO.read(new FileInputStream(tiff)); // require jai-imageio lib to read TIFF + ByteBuffer buf = ImageIOHelper.convertImageData(image); + int bpp = image.getColorModel().getPixelSize(); + int bytespp = bpp / 8; + int bytespl = (int) Math.ceil(image.getWidth() * bpp / 8.0); + TessAPI1.TessBaseAPIInit3(handle, datapath, language); + TessAPI1.TessBaseAPISetPageSegMode(handle, TessPageSegMode.PSM_AUTO); + TessAPI1.TessBaseAPISetImage(handle, buf, image.getWidth(), image.getHeight(), bytespp, bytespl); + TessAPI1.TessBaseAPISetRectangle(handle, 0, 0, 1024, 800); + Pointer utf8Text = TessAPI1.TessBaseAPIGetUTF8Text(handle); + String result = utf8Text.getString(0); + TessAPI1.TessDeleteText(utf8Text); + logger.info(result); + assertTrue(result.startsWith(expResult)); + } + + /** + * Test of TessBaseAPIGetUTF8Text method, of class TessAPI1. + * + * @throws java.lang.Exception + */ + @Test + public void testTessBaseAPIGetUTF8Text_Pix() throws Exception { + logger.info("TessBaseAPIGetUTF8Text_Pix"); + String expResult = expOCRResult; + File tiff = new File(this.testResourcesDataPath, "eurotext.tif"); + Pix pix = Leptonica1.pixRead(tiff.getPath()); + TessAPI1.TessBaseAPIInit3(handle, datapath, language); + TessAPI1.TessBaseAPISetImage2(handle, pix); + Pointer utf8Text = TessAPI1.TessBaseAPIGetUTF8Text(handle); + String result = utf8Text.getString(0); + TessAPI1.TessDeleteText(utf8Text); + logger.info(result); + + //release Pix resource + PointerByReference pRef = new PointerByReference(); + pRef.setValue(pix.getPointer()); + Leptonica1.pixDestroy(pRef); + + assertTrue(result.startsWith(expResult)); + } + + /** + * Test of TessBaseAPIGetComponentImages method, of class TessAPI1. + * + * @throws java.lang.Exception + */ + @Test + public void testTessBaseAPIGetComponentImages() throws Exception { + logger.info("TessBaseAPIGetComponentImages"); + File image = new File(this.testResourcesDataPath, "eurotext.png"); + int expResult = 12; // number of lines in the test image + Pix pix = Leptonica1.pixRead(image.getPath()); + TessAPI1.TessBaseAPIInit3(handle, datapath, language); + TessAPI1.TessBaseAPISetImage2(handle, pix); + PointerByReference pixa = null; + PointerByReference blockids = null; + Boxa boxes = TessAPI1.TessBaseAPIGetComponentImages(handle, TessPageIteratorLevel.RIL_TEXTLINE, TRUE, pixa, blockids); +// boxes = TessAPI1.TessBaseAPIGetRegions(handle, pixa); // equivalent to TessPageIteratorLevel.RIL_BLOCK + int boxCount = Leptonica1.boxaGetCount(boxes); + for (int i = 0; i < boxCount; i++) { + Box box = Leptonica1.boxaGetBox(boxes, i, L_CLONE); + if (box == null) { + continue; + } + TessAPI1.TessBaseAPISetRectangle(handle, box.x, box.y, box.w, box.h); + Pointer utf8Text = TessAPI1.TessBaseAPIGetUTF8Text(handle); + String ocrResult = utf8Text.getString(0); + TessAPI1.TessDeleteText(utf8Text); + int conf = TessAPI1.TessBaseAPIMeanTextConf(handle); + System.out.print(String.format("Box[%d]: x=%d, y=%d, w=%d, h=%d, confidence: %d, text: %s", i, box.x, box.y, box.w, box.h, conf, ocrResult)); + LeptUtils.dispose(box); + } + + // release Pix and Boxa resources + LeptUtils.dispose(pix); + LeptUtils.dispose(boxes); + + assertEquals(expResult, boxCount); + } + + /** + * Test of TessVersion method, of class TessAPI1. + */ + @Test + public void testTessVersion() { + logger.info("TessVersion"); + String expResult = "5.0.0"; + String result = TessAPI1.TessVersion(); + logger.info(result); + assertTrue(result.startsWith(expResult)); + } + + /** + * Test of TessBaseAPISetVariable method, of class TessAPI1. + */ + @Test + public void testTessBaseAPISetVariable() { + logger.info("TessBaseAPISetVariable"); + String name = "tessedit_create_hocr"; + String value = "1"; + int expResult = 1; + int result = TessAPI1.TessBaseAPISetVariable(handle, name, value); + assertEquals(expResult, result); + } + + /** + * Test of TessBaseAPIGetBoolVariable method, of class TessAPI1. + */ + @Test + public void testTessBaseAPIGetBoolVariable() { + logger.info("TessBaseAPIGetBoolVariable"); + String name = "tessedit_create_hocr"; + TessAPI1.TessBaseAPISetVariable(handle, name, "1"); + IntBuffer value = IntBuffer.allocate(1); + int result = -1; + if (TessAPI1.TessBaseAPIGetBoolVariable(handle, "tessedit_create_hocr", value) == TRUE) { + result = value.get(0); + } + int expResult = 1; + assertEquals(expResult, result); + } + + /** + * Test of TessBaseAPIPrintVariables method, of class TessAPI1. + * + * @throws Exception while persisting variables into a file. + */ + @Test + public void testTessBaseAPIPrintVariablesToFile() throws Exception { + logger.info("TessBaseAPIPrintVariablesToFile"); + String var = "tessedit_char_whitelist"; + String value = "0123456789"; + TessAPI1.TessBaseAPISetVariable(handle, var, value); + String filename = "printvar.txt"; + TessAPI1.TessBaseAPIPrintVariablesToFile(handle, filename); // will crash if not invoked after some method + File file = new File(filename); + BufferedReader input = new BufferedReader(new FileReader(file)); + StringBuilder strB = new StringBuilder(); + String line; + String EOL = System.getProperty("line.separator"); + while ((line = input.readLine()) != null) { + strB.append(line).append(EOL); + } + input.close(); + file.delete(); + assertTrue(strB.toString().contains(var + "\t" + value)); + } + + /** + * Test of TessBaseAPIInit4 method, of class TessAPI1. + */ + @Test + public void testTessBaseAPIInit4() { + logger.info("TessBaseAPIInit4"); + int oem = TessOcrEngineMode.OEM_DEFAULT; + PointerByReference configs = null; + int configs_size = 0; + // disable loading dictionaries + String[] args = new String[]{"load_system_dawg", "load_freq_dawg"}; + StringArray sarray = new StringArray(args); + PointerByReference vars_vec = new PointerByReference(); + vars_vec.setPointer(sarray); + + args = new String[]{"F", "F"}; + sarray = new StringArray(args); + PointerByReference vars_values = new PointerByReference(); + vars_values.setPointer(sarray); + + NativeSize vars_vec_size = new NativeSize(args.length); + + int expResult = 0; + int result = TessAPI1.TessBaseAPIInit4(handle, datapath, language, oem, configs, configs_size, vars_vec, vars_values, vars_vec_size, FALSE); + assertEquals(expResult, result); + } + + /** + * Test of TessBaseAPIGetInitLanguagesAsString method, of class TessAPI1. + */ + @Test + public void testTessBaseAPIGetInitLanguagesAsString() { + logger.info("TessBaseAPIGetInitLanguagesAsString"); + String expResult = ""; + String result = TessAPI1.TessBaseAPIGetInitLanguagesAsString(handle); + assertEquals(expResult, result); + } + + /** + * Test of TessBaseAPIGetLoadedLanguagesAsVector method, of class TessAPI1. + */ + @Test + public void testTessBaseAPIGetLoadedLanguagesAsVector() { + logger.info("TessBaseAPIGetLoadedLanguagesAsVector"); + TessAPI1.TessBaseAPIInit3(handle, datapath, language); + String[] expResult = {"eng"}; + String[] result = TessAPI1.TessBaseAPIGetLoadedLanguagesAsVector(handle).getPointer().getStringArray(0); + assertArrayEquals(expResult, result); + } + + /** + * Test of TessBaseAPIGetAvailableLanguagesAsVector method, of class + * TessAPI1. + */ + @Test + public void testTessBaseAPIGetAvailableLanguagesAsVector() { + logger.info("TessBaseAPIGetAvailableLanguagesAsVector"); + TessAPI1.TessBaseAPIInit3(handle, datapath, language); + String[] expResult = {"eng"}; + String[] result = TessAPI1.TessBaseAPIGetAvailableLanguagesAsVector(handle).getPointer().getStringArray(0); + assertTrue(Arrays.asList(result).containsAll(Arrays.asList(expResult))); + } + + /** + * Test of TessBaseAPIGetHOCRText method, of class TessAPI1. + * + * @throws Exception while getting ocr text from image. + */ + @Test + public void testTessBaseAPIGetHOCRText() throws Exception { + logger.info("TessBaseAPIGetHOCRText"); + File tiff = new File(this.testResourcesDataPath, "eurotext.tif"); + BufferedImage image = ImageIO.read(new FileInputStream(tiff)); // require jai-imageio lib to read TIFF + ByteBuffer buf = ImageIOHelper.convertImageData(image); + int bpp = image.getColorModel().getPixelSize(); + int bytespp = bpp / 8; + int bytespl = (int) Math.ceil(image.getWidth() * bpp / 8.0); + TessAPI1.TessBaseAPISetPageSegMode(handle, TessPageSegMode.PSM_AUTO); + TessAPI1.TessBaseAPIInit3(handle, datapath, language); + TessAPI1.TessBaseAPISetImage(handle, buf, image.getWidth(), image.getHeight(), bytespp, bytespl); + int page_number = 0; + Pointer utf8Text = TessAPI1.TessBaseAPIGetHOCRText(handle, page_number); + String result = utf8Text.getString(0); + TessAPI1.TessDeleteText(utf8Text); + assertTrue(result.contains("
")); + + // WordStr Box output + textPtr = TessAPI1.TessBaseAPIGetWordStrBoxText(handle, page_number); + result = textPtr.getString(0); + TessAPI1.TessDeleteText(textPtr); + assertTrue(result.contains("WordStr")); + + // TSV output + textPtr = TessAPI1.TessBaseAPIGetTsvText(handle, page_number); + result = textPtr.getString(0); + TessAPI1.TessDeleteText(textPtr); + assertTrue(result.contains("1\t")); + + // LSTM Box output + textPtr = TessAPI1.TessBaseAPIGetLSTMBoxText(handle, page_number); + result = textPtr.getString(0); + TessAPI1.TessDeleteText(textPtr); + assertTrue(result.contains("\t")); + } + + /** + * Test of TessBaseAPIAnalyseLayout method, of class TessAPI1. + * + * @throws java.lang.Exception + */ + @Test + public void testTessBaseAPIAnalyseLayout() throws Exception { + logger.info("TessBaseAPIAnalyseLayout"); + File image = new File(testResourcesDataPath, "eurotext.png"); + int expResult = 12; // number of lines in the test image + Pix pix = Leptonica1.pixRead(image.getPath()); + TessAPI1.TessBaseAPIInit3(handle, datapath, language); + TessAPI1.TessBaseAPISetImage2(handle, pix); + int pageIteratorLevel = TessPageIteratorLevel.RIL_TEXTLINE; + logger.info("PageIteratorLevel: " + Utils.getConstantName(pageIteratorLevel, TessPageIteratorLevel.class)); + int i = 0; + TessPageIterator pi = TessAPI1.TessBaseAPIAnalyseLayout(handle); + + do { + IntBuffer leftB = IntBuffer.allocate(1); + IntBuffer topB = IntBuffer.allocate(1); + IntBuffer rightB = IntBuffer.allocate(1); + IntBuffer bottomB = IntBuffer.allocate(1); + TessAPI1.TessPageIteratorBoundingBox(pi, pageIteratorLevel, leftB, topB, rightB, bottomB); + int left = leftB.get(); + int top = topB.get(); + int right = rightB.get(); + int bottom = bottomB.get(); + logger.info(String.format("Box[%d]: x=%d, y=%d, w=%d, h=%d", i++, left, top, right - left, bottom - top)); + } while (TessAPI1.TessPageIteratorNext(pi, pageIteratorLevel) == TRUE); + TessAPI1.TessPageIteratorDelete(pi); + PointerByReference pRef = new PointerByReference(); + pRef.setValue(pix.getPointer()); + Leptonica1.pixDestroy(pRef); + assertEquals(expResult, i); + } + + /** + * Test of TessBaseAPIDetectOrientationScript method, of class TessAPI1. + * + * @throws java.lang.Exception + */ + @Test + public void testTessBaseAPIDetectOrientationScript() throws Exception { + logger.info("TessBaseAPIDetectOrientationScript"); + File image = new File(testResourcesDataPath, "eurotext90.png"); + int expResult = TRUE; + Pix pix = Leptonica1.pixRead(image.getPath()); + TessAPI1.TessBaseAPIInit3(handle, datapath, "osd"); + TessAPI1.TessBaseAPISetImage2(handle, pix); + + IntBuffer orient_degB = IntBuffer.allocate(1); + FloatBuffer orient_confB = FloatBuffer.allocate(1); + PointerByReference script_nameB = new PointerByReference(); + FloatBuffer script_confB = FloatBuffer.allocate(1); + + int result = TessAPI1.TessBaseAPIDetectOrientationScript(handle, orient_degB, orient_confB, script_nameB, script_confB); + if (result == TRUE) { + int orient_deg = orient_degB.get(); + float orient_conf = orient_confB.get(); + String script_name = script_nameB.getValue().getString(0); + float script_conf = script_confB.get(); + logger.info(String.format("OrientationScript: orient_deg=%d, orient_conf=%f, script_name=%s, script_conf=%f", orient_deg, orient_conf, script_name, script_conf)); + } + + PointerByReference pRef = new PointerByReference(); + pRef.setValue(pix.getPointer()); + Leptonica1.pixDestroy(pRef); + assertEquals(expResult, result); + } + + /** + * Test of Orientation and script detection (OSD). + * + * @throws Exception while processing the image. + */ + @Test + public void testOSD() throws Exception { + logger.info("OSD"); + int expResult = TessPageSegMode.PSM_AUTO_OSD; + IntBuffer orientation = IntBuffer.allocate(1); + IntBuffer direction = IntBuffer.allocate(1); + IntBuffer order = IntBuffer.allocate(1); + FloatBuffer deskew_angle = FloatBuffer.allocate(1); + File imageFile = new File(this.testResourcesDataPath, "eurotext90.png"); + BufferedImage image = ImageIO.read(new FileInputStream(imageFile)); + ByteBuffer buf = ImageIOHelper.convertImageData(image); + int bpp = image.getColorModel().getPixelSize(); + int bytespp = bpp / 8; + int bytespl = (int) Math.ceil(image.getWidth() * bpp / 8.0); + TessAPI1.TessBaseAPIInit3(handle, datapath, language); + TessAPI1.TessBaseAPISetPageSegMode(handle, expResult); + int actualResult = TessAPI1.TessBaseAPIGetPageSegMode(handle); + logger.info("PSM: " + Utils.getConstantName(actualResult, TessPageSegMode.class)); + TessAPI1.TessBaseAPISetImage(handle, buf, image.getWidth(), image.getHeight(), bytespp, bytespl); + int success = TessAPI1.TessBaseAPIRecognize(handle, null); + if (success == 0) { + TessAPI1.TessPageIterator pi = TessAPI1.TessBaseAPIAnalyseLayout(handle); + TessAPI1.TessPageIteratorOrientation(pi, orientation, direction, order, deskew_angle); + logger.info(String.format( + "Orientation: %s\nWritingDirection: %s\nTextlineOrder: %s\nDeskew angle: %.4f\n", + Utils.getConstantName(orientation.get(), TessOrientation.class), + Utils.getConstantName(direction.get(), TessWritingDirection.class), + Utils.getConstantName(order.get(), TessTextlineOrder.class), + deskew_angle.get())); + } + assertEquals(expResult, actualResult); + } + + /** + * Test of ResultIterator and PageIterator. + * + * @throws Exception + */ + @Test + public void testResultIterator() throws Exception { + logger.info("TessBaseAPIGetIterator"); + File tiff = new File(this.testResourcesDataPath, "eurotext.tif"); + BufferedImage image = ImageIO.read(new FileInputStream(tiff)); // require jai-imageio lib to read TIFF + ByteBuffer buf = ImageIOHelper.convertImageData(image); + int bpp = image.getColorModel().getPixelSize(); + int bytespp = bpp / 8; + int bytespl = (int) Math.ceil(image.getWidth() * bpp / 8.0); + TessAPI1.TessBaseAPIInit3(handle, datapath, language); + TessAPI1.TessBaseAPISetPageSegMode(handle, TessPageSegMode.PSM_AUTO); + TessAPI1.TessBaseAPISetImage(handle, buf, image.getWidth(), image.getHeight(), bytespp, bytespl); + ETEXT_DESC monitor = new ETEXT_DESC(); + ITessAPI.TimeVal timeout = new ITessAPI.TimeVal(); + timeout.tv_sec = new NativeLong(0L); // time > 0 causes blank ouput + monitor.end_time = timeout; + ProgressMonitor pmo = new ProgressMonitor(monitor); + pmo.start(); + TessAPI1.TessBaseAPIRecognize(handle, monitor); + logger.info("Message: " + pmo.getMessage()); + TessResultIterator ri = TessAPI1.TessBaseAPIGetIterator(handle); + TessPageIterator pi = TessAPI1.TessResultIteratorGetPageIterator(ri); + TessAPI1.TessPageIteratorBegin(pi); + logger.info("Bounding boxes:\nchar(s) left top right bottom confidence font-attributes"); + int level = TessPageIteratorLevel.RIL_WORD; + + // int height = image.getHeight(); + do { + Pointer ptr = TessAPI1.TessResultIteratorGetUTF8Text(ri, level); + String word = ptr.getString(0); + TessAPI1.TessDeleteText(ptr); + float confidence = TessAPI1.TessResultIteratorConfidence(ri, level); + IntBuffer leftB = IntBuffer.allocate(1); + IntBuffer topB = IntBuffer.allocate(1); + IntBuffer rightB = IntBuffer.allocate(1); + IntBuffer bottomB = IntBuffer.allocate(1); + TessAPI1.TessPageIteratorBoundingBox(pi, level, leftB, topB, rightB, bottomB); + int left = leftB.get(); + int top = topB.get(); + int right = rightB.get(); + int bottom = bottomB.get(); + System.out.print(String.format("%s %d %d %d %d %f", word, left, top, right, bottom, confidence)); + // logger.info(String.format("%s %d %d %d %d", str, left, height - bottom, right, height - top)); // + // training box coordinates + + IntBuffer boldB = IntBuffer.allocate(1); + IntBuffer italicB = IntBuffer.allocate(1); + IntBuffer underlinedB = IntBuffer.allocate(1); + IntBuffer monospaceB = IntBuffer.allocate(1); + IntBuffer serifB = IntBuffer.allocate(1); + IntBuffer smallcapsB = IntBuffer.allocate(1); + IntBuffer pointSizeB = IntBuffer.allocate(1); + IntBuffer fontIdB = IntBuffer.allocate(1); + String fontName = TessAPI1.TessResultIteratorWordFontAttributes(ri, boldB, italicB, underlinedB, + monospaceB, serifB, smallcapsB, pointSizeB, fontIdB); + boolean bold = boldB.get() == TRUE; + boolean italic = italicB.get() == TRUE; + boolean underlined = underlinedB.get() == TRUE; + boolean monospace = monospaceB.get() == TRUE; + boolean serif = serifB.get() == TRUE; + boolean smallcaps = smallcapsB.get() == TRUE; + int pointSize = pointSizeB.get(); + int fontId = fontIdB.get(); + logger.info(String.format(" font: %s, size: %d, font id: %d, bold: %b," + + " italic: %b, underlined: %b, monospace: %b, serif: %b, smallcap: %b", fontName, pointSize, + fontId, bold, italic, underlined, monospace, serif, smallcaps)); + } while (TessAPI1.TessPageIteratorNext(pi, level) == TRUE); +// TessAPI1.TessPageIteratorDelete(pi); + TessAPI1.TessResultIteratorDelete(ri); + + assertTrue(true); + } + + /** + * Test of ChoiceIterator. + * + * @throws Exception + */ + @Test + public void testChoiceIterator() throws Exception { + logger.info("TessResultIteratorGetChoiceIterator"); + String filename = String.format("%s/%s", this.testResourcesDataPath, "eurotext.tif"); + File tiff = new File(filename); + BufferedImage image = ImageIO.read(new FileInputStream(tiff)); // require jai-imageio lib to read TIFF + ByteBuffer buf = ImageIOHelper.convertImageData(image); + int bpp = image.getColorModel().getPixelSize(); + int bytespp = bpp / 8; + int bytespl = (int) Math.ceil(image.getWidth() * bpp / 8.0); + TessAPI1.TessBaseAPIInit3(handle, datapath, language); + TessAPI1.TessBaseAPISetImage(handle, buf, image.getWidth(), image.getHeight(), bytespp, bytespl); + TessAPI1.TessBaseAPISetVariable(handle, "save_blob_choices", "T"); + TessAPI1.TessBaseAPISetRectangle(handle, 37, 228, 548, 31); + ETEXT_DESC monitor = new ETEXT_DESC(); + ProgressMonitor pmo = new ProgressMonitor(monitor); + pmo.start(); + TessAPI1.TessBaseAPIRecognize(handle, monitor); + logger.info("Message: " + pmo.getMessage()); + TessResultIterator ri = TessAPI1.TessBaseAPIGetIterator(handle); + int level = TessPageIteratorLevel.RIL_SYMBOL; + + if (ri != null) { + do { + Pointer symbol = TessAPI1.TessResultIteratorGetUTF8Text(ri, level); + float conf = TessAPI1.TessResultIteratorConfidence(ri, level); + if (symbol != null) { + logger.info(String.format("symbol %s, conf: %f", symbol.getString(0), conf)); + boolean indent = false; + TessChoiceIterator ci = TessAPI1.TessResultIteratorGetChoiceIterator(ri); + do { + if (indent) { + System.out.print("\t"); + } + System.out.print("\t- "); + String choice = TessAPI1.TessChoiceIteratorGetUTF8Text(ci); + logger.info(String.format("%s conf: %f", choice, TessAPI1.TessChoiceIteratorConfidence(ci))); + indent = true; + } while (TessAPI1.TessChoiceIteratorNext(ci) == TessAPI1.TRUE); + TessAPI1.TessChoiceIteratorDelete(ci); + } + logger.info("---------------------------------------------"); + TessAPI1.TessDeleteText(symbol); + } while (TessAPI1.TessResultIteratorNext(ri, level) == TessAPI1.TRUE); + TessAPI1.TessResultIteratorDelete(ri); + } + + assertTrue(true); + } + + /** + * Test of ResultRenderer method, of class TessAPI1. + * + * @throws java.lang.Exception + */ + @Test + public void testResultRenderer() throws Exception { + logger.info("TessResultRenderer"); + String image = String.format("%s/%s", this.testResourcesDataPath, "eurotext.tif"); + String output = "capi-test.txt"; + int set_only_init_params = ITessAPI.FALSE; + int oem = TessOcrEngineMode.OEM_DEFAULT; + PointerByReference configs = null; + int configs_size = 0; + + String[] params = {"load_system_dawg", "tessedit_char_whitelist"}; + String vals[] = {"F", ""}; //0123456789-.IThisalotfpnex + PointerByReference vars_vec = new PointerByReference(); + vars_vec.setPointer(new StringArray(params)); + PointerByReference vars_values = new PointerByReference(); + vars_values.setPointer(new StringArray(vals)); + NativeSize vars_vec_size = new NativeSize(params.length); + + TessAPI1.TessBaseAPISetOutputName(handle, output); + + int rc = TessAPI1.TessBaseAPIInit4(handle, datapath, language, + oem, configs, configs_size, vars_vec, vars_values, vars_vec_size, set_only_init_params); + + if (rc != 0) { + TessAPI1.TessBaseAPIDelete(handle); + logger.error("Could not initialize tesseract."); + return; + } + + String outputbase = "target/test-classes/test-results/ResultRenderer1"; + TessResultRenderer renderer = TessAPI1.TessHOcrRendererCreate(outputbase); + TessAPI1.TessResultRendererInsert(renderer, TessAPI1.TessBoxTextRendererCreate(outputbase)); + TessAPI1.TessResultRendererInsert(renderer, TessAPI1.TessTextRendererCreate(outputbase)); + String dataPath = TessAPI1.TessBaseAPIGetDatapath(handle); + TessAPI1.TessResultRendererInsert(renderer, TessAPI1.TessPDFRendererCreate(outputbase, dataPath, FALSE)); + int result = TessAPI1.TessBaseAPIProcessPages(handle, image, null, 0, renderer); + +// if (result == FALSE) { +// logger.error("Error during processing."); +// return; +// } + while ((renderer = TessAPI1.TessResultRendererNext(renderer)) != null) { + String ext = TessAPI1.TessResultRendererExtention(renderer).getString(0); + logger.info(String.format("TessResultRendererExtention: %s\nTessResultRendererTitle: %s\nTessResultRendererImageNum: %d", + ext, + TessAPI1.TessResultRendererTitle(renderer).getString(0), + TessAPI1.TessResultRendererImageNum(renderer))); + } + + TessAPI1.TessDeleteResultRenderer(renderer); + assertTrue(new File(outputbase + ".pdf").exists()); + } +} diff --git a/d4dj/src/test/java/net/sourceforge/tess4j/TessAPIImpl.java b/d4dj/src/test/java/net/sourceforge/tess4j/TessAPIImpl.java new file mode 100644 index 0000000..4c24b3a --- /dev/null +++ b/d4dj/src/test/java/net/sourceforge/tess4j/TessAPIImpl.java @@ -0,0 +1,695 @@ +/* + * Copyright @ 2017 Quan Nguyen + * + * Licensed under the Apache License, Version 2.0 (the "License"); + * you may not use this file except in compliance with the License. + * You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ +package net.sourceforge.tess4j; + +import com.ochafik.lang.jnaerator.runtime.NativeSize; +import com.sun.jna.Pointer; +import com.sun.jna.ptr.IntByReference; +import com.sun.jna.ptr.PointerByReference; +import java.nio.ByteBuffer; +import java.nio.DoubleBuffer; +import java.nio.FloatBuffer; +import java.nio.IntBuffer; +import net.sourceforge.lept4j.Boxa; +import net.sourceforge.lept4j.Pix; + +public class TessAPIImpl implements TessAPI { + + public TessAPI getInstance() { + return TessAPI.INSTANCE; + } + + public void TessAPIEndPage() { + } + + public void TessAPIRelease() { + } + + @Override + public String TessVersion() { + throw new UnsupportedOperationException("Not supported yet."); + } + + @Override + public void TessDeleteText(Pointer text) { + throw new UnsupportedOperationException("Not supported yet."); + } + + @Override + public void TessDeleteTextArray(PointerByReference arr) { + throw new UnsupportedOperationException("Not supported yet."); + } + + @Override + public void TessDeleteIntArray(IntBuffer arr) { + throw new UnsupportedOperationException("Not supported yet."); + } + + @Override + public ITessAPI.TessResultRenderer TessTextRendererCreate(String outputbase) { + throw new UnsupportedOperationException("Not supported yet."); + } + + @Override + public ITessAPI.TessResultRenderer TessHOcrRendererCreate(String outputbase) { + throw new UnsupportedOperationException("Not supported yet."); + } + + @Override + public ITessAPI.TessResultRenderer TessHOcrRendererCreate2(String outputbase, int font_info) { + throw new UnsupportedOperationException("Not supported yet."); + } + + @Override + public ITessAPI.TessResultRenderer TessPDFRendererCreate(String outputbase, String datadir, int textonly) { + throw new UnsupportedOperationException("Not supported yet."); + } + + @Override + public ITessAPI.TessResultRenderer TessUnlvRendererCreate(String outputbase) { + throw new UnsupportedOperationException("Not supported yet."); + } + + @Override + public ITessAPI.TessResultRenderer TessBoxTextRendererCreate(String outputbase) { + throw new UnsupportedOperationException("Not supported yet."); + } + + @Override + public void TessDeleteResultRenderer(ITessAPI.TessResultRenderer renderer) { + throw new UnsupportedOperationException("Not supported yet."); + } + + @Override + public void TessResultRendererInsert(ITessAPI.TessResultRenderer renderer, ITessAPI.TessResultRenderer next) { + throw new UnsupportedOperationException("Not supported yet."); + } + + @Override + public ITessAPI.TessResultRenderer TessResultRendererNext(ITessAPI.TessResultRenderer renderer) { + throw new UnsupportedOperationException("Not supported yet."); + } + + @Override + public int TessResultRendererBeginDocument(ITessAPI.TessResultRenderer renderer, String title) { + throw new UnsupportedOperationException("Not supported yet."); + } + + @Override + public int TessResultRendererAddImage(ITessAPI.TessResultRenderer renderer, PointerByReference api) { + throw new UnsupportedOperationException("Not supported yet."); + } + + @Override + public int TessResultRendererEndDocument(ITessAPI.TessResultRenderer renderer) { + throw new UnsupportedOperationException("Not supported yet."); + } + + @Override + public Pointer TessResultRendererExtention(ITessAPI.TessResultRenderer renderer) { + throw new UnsupportedOperationException("Not supported yet."); + } + + @Override + public Pointer TessResultRendererTitle(ITessAPI.TessResultRenderer renderer) { + throw new UnsupportedOperationException("Not supported yet."); + } + + @Override + public int TessResultRendererImageNum(ITessAPI.TessResultRenderer renderer) { + throw new UnsupportedOperationException("Not supported yet."); + } + + @Override + public ITessAPI.TessBaseAPI TessBaseAPICreate() { + throw new UnsupportedOperationException("Not supported yet."); + } + + @Override + public void TessBaseAPIDelete(ITessAPI.TessBaseAPI handle) { + throw new UnsupportedOperationException("Not supported yet."); + } + + @Override + public void TessBaseAPISetInputName(ITessAPI.TessBaseAPI handle, String name) { + throw new UnsupportedOperationException("Not supported yet."); + } + + @Override + public String TessBaseAPIGetInputName(ITessAPI.TessBaseAPI handle) { + throw new UnsupportedOperationException("Not supported yet."); + } + + @Override + public void TessBaseAPISetInputImage(ITessAPI.TessBaseAPI handle, Pix pix) { + throw new UnsupportedOperationException("Not supported yet."); + } + + @Override + public Pix TessBaseAPIGetInputImage(ITessAPI.TessBaseAPI handle) { + throw new UnsupportedOperationException("Not supported yet."); + } + + @Override + public int TessBaseAPIGetSourceYResolution(ITessAPI.TessBaseAPI handle) { + throw new UnsupportedOperationException("Not supported yet."); + } + + @Override + public String TessBaseAPIGetDatapath(ITessAPI.TessBaseAPI handle) { + throw new UnsupportedOperationException("Not supported yet."); + } + + @Override + public void TessBaseAPISetOutputName(ITessAPI.TessBaseAPI handle, String name) { + throw new UnsupportedOperationException("Not supported yet."); + } + + @Override + public int TessBaseAPISetVariable(ITessAPI.TessBaseAPI handle, String name, String value) { + throw new UnsupportedOperationException("Not supported yet."); + } + + @Override + public int TessBaseAPIGetIntVariable(ITessAPI.TessBaseAPI handle, String name, IntBuffer value) { + throw new UnsupportedOperationException("Not supported yet."); + } + + @Override + public int TessBaseAPIGetBoolVariable(ITessAPI.TessBaseAPI handle, String name, IntBuffer value) { + throw new UnsupportedOperationException("Not supported yet."); + } + + @Override + public int TessBaseAPIGetDoubleVariable(ITessAPI.TessBaseAPI handle, String name, DoubleBuffer value) { + throw new UnsupportedOperationException("Not supported yet."); + } + + @Override + public String TessBaseAPIGetStringVariable(ITessAPI.TessBaseAPI handle, String name) { + throw new UnsupportedOperationException("Not supported yet."); + } + + @Override + public void TessBaseAPIPrintVariablesToFile(ITessAPI.TessBaseAPI handle, String filename) { + throw new UnsupportedOperationException("Not supported yet."); + } + + @Override + public int TessBaseAPIInit1(ITessAPI.TessBaseAPI handle, String datapath, String language, int oem, PointerByReference configs, int configs_size) { + throw new UnsupportedOperationException("Not supported yet."); + } + + @Override + public int TessBaseAPIInit2(ITessAPI.TessBaseAPI handle, String datapath, String language, int oem) { + throw new UnsupportedOperationException("Not supported yet."); + } + + @Override + public int TessBaseAPIInit3(ITessAPI.TessBaseAPI handle, String datapath, String language) { + throw new UnsupportedOperationException("Not supported yet."); + } + + @Override + public int TessBaseAPIInit4(ITessAPI.TessBaseAPI handle, String datapath, String language, int oem, PointerByReference configs, int configs_size, PointerByReference vars_vec, PointerByReference vars_values, NativeSize vars_vec_size, int set_only_non_debug_params) { + throw new UnsupportedOperationException("Not supported yet."); + } + + @Override + public String TessBaseAPIGetInitLanguagesAsString(ITessAPI.TessBaseAPI handle) { + throw new UnsupportedOperationException("Not supported yet."); + } + + @Override + public PointerByReference TessBaseAPIGetLoadedLanguagesAsVector(ITessAPI.TessBaseAPI handle) { + throw new UnsupportedOperationException("Not supported yet."); + } + + @Override + public PointerByReference TessBaseAPIGetAvailableLanguagesAsVector(ITessAPI.TessBaseAPI handle) { + throw new UnsupportedOperationException("Not supported yet."); + } + + @Override + public int TessBaseAPIInitLangMod(ITessAPI.TessBaseAPI handle, String datapath, String language) { + throw new UnsupportedOperationException("Not supported yet."); + } + + @Override + public void TessBaseAPIInitForAnalysePage(ITessAPI.TessBaseAPI handle) { + throw new UnsupportedOperationException("Not supported yet."); + } + + @Override + public void TessBaseAPIReadConfigFile(ITessAPI.TessBaseAPI handle, String filename, int init_only) { + throw new UnsupportedOperationException("Not supported yet."); + } + + @Override + public void TessBaseAPISetPageSegMode(ITessAPI.TessBaseAPI handle, int mode) { + throw new UnsupportedOperationException("Not supported yet."); + } + + @Override + public int TessBaseAPIGetPageSegMode(ITessAPI.TessBaseAPI handle) { + throw new UnsupportedOperationException("Not supported yet."); + } + + @Override + public Pointer TessBaseAPIRect(ITessAPI.TessBaseAPI handle, ByteBuffer imagedata, int bytes_per_pixel, int bytes_per_line, int left, int top, int width, int height) { + throw new UnsupportedOperationException("Not supported yet."); + } + + @Override + public void TessBaseAPIClearAdaptiveClassifier(ITessAPI.TessBaseAPI handle) { + throw new UnsupportedOperationException("Not supported yet."); + } + + @Override + public void TessBaseAPISetImage(ITessAPI.TessBaseAPI handle, ByteBuffer imagedata, int width, int height, int bytes_per_pixel, int bytes_per_line) { + throw new UnsupportedOperationException("Not supported yet."); + } + + @Override + public void TessBaseAPISetImage2(ITessAPI.TessBaseAPI handle, Pix pix) { + throw new UnsupportedOperationException("Not supported yet."); + } + + @Override + public void TessBaseAPISetSourceResolution(ITessAPI.TessBaseAPI handle, int ppi) { + throw new UnsupportedOperationException("Not supported yet."); + } + + @Override + public void TessBaseAPISetRectangle(ITessAPI.TessBaseAPI handle, int left, int top, int width, int height) { + throw new UnsupportedOperationException("Not supported yet."); + } + + @Override + public Pix TessBaseAPIGetThresholdedImage(ITessAPI.TessBaseAPI handle) { + throw new UnsupportedOperationException("Not supported yet."); + } + + @Override + public Boxa TessBaseAPIGetRegions(ITessAPI.TessBaseAPI handle, PointerByReference pixa) { + throw new UnsupportedOperationException("Not supported yet."); + } + + @Override + public Boxa TessBaseAPIGetTextlines(ITessAPI.TessBaseAPI handle, PointerByReference pixa, PointerByReference blockids) { + throw new UnsupportedOperationException("Not supported yet."); + } + + @Override + public Boxa TessBaseAPIGetTextlines1(ITessAPI.TessBaseAPI handle, int raw_image, int raw_padding, PointerByReference pixa, PointerByReference blockids, PointerByReference paraids) { + throw new UnsupportedOperationException("Not supported yet."); + } + + @Override + public Boxa TessBaseAPIGetStrips(ITessAPI.TessBaseAPI handle, PointerByReference pixa, PointerByReference blockids) { + throw new UnsupportedOperationException("Not supported yet."); + } + + @Override + public Boxa TessBaseAPIGetWords(ITessAPI.TessBaseAPI handle, PointerByReference pixa) { + throw new UnsupportedOperationException("Not supported yet."); + } + + @Override + public Boxa TessBaseAPIGetConnectedComponents(ITessAPI.TessBaseAPI handle, PointerByReference cc) { + throw new UnsupportedOperationException("Not supported yet."); + } + + @Override + public Boxa TessBaseAPIGetComponentImages(ITessAPI.TessBaseAPI handle, int level, int text_only, PointerByReference pixa, PointerByReference blockids) { + throw new UnsupportedOperationException("Not supported yet."); + } + + @Override + public Boxa TessBaseAPIGetComponentImages1(ITessAPI.TessBaseAPI handle, int level, int text_only, int raw_image, int raw_padding, PointerByReference pixa, PointerByReference blockids, PointerByReference paraids) { + throw new UnsupportedOperationException("Not supported yet."); + } + + @Override + public int TessBaseAPIGetThresholdedImageScaleFactor(ITessAPI.TessBaseAPI handle) { + throw new UnsupportedOperationException("Not supported yet."); + } + + @Override + public ITessAPI.TessPageIterator TessBaseAPIAnalyseLayout(ITessAPI.TessBaseAPI handle) { + throw new UnsupportedOperationException("Not supported yet."); + } + + @Override + public int TessBaseAPIRecognize(ITessAPI.TessBaseAPI handle, ITessAPI.ETEXT_DESC monitor) { + throw new UnsupportedOperationException("Not supported yet."); + } + + @Override + public int TessBaseAPIRecognizeForChopTest(ITessAPI.TessBaseAPI handle, ITessAPI.ETEXT_DESC monitor) { + throw new UnsupportedOperationException("Not supported yet."); + } + + @Override + public ITessAPI.TessResultIterator TessBaseAPIGetIterator(ITessAPI.TessBaseAPI handle) { + throw new UnsupportedOperationException("Not supported yet."); + } + + @Override + public ITessAPI.TessMutableIterator TessBaseAPIGetMutableIterator(ITessAPI.TessBaseAPI handle) { + throw new UnsupportedOperationException("Not supported yet."); + } + + @Override + public int TessBaseAPIProcessPages(ITessAPI.TessBaseAPI handle, String filename, String retry_config, int timeout_millisec, ITessAPI.TessResultRenderer renderer) { + throw new UnsupportedOperationException("Not supported yet."); + } + + @Override + public int TessBaseAPIProcessPage(ITessAPI.TessBaseAPI handle, Pix pix, int page_index, String filename, String retry_config, int timeout_millisec, ITessAPI.TessResultRenderer renderer) { + throw new UnsupportedOperationException("Not supported yet."); + } + + @Override + public Pointer TessBaseAPIGetUTF8Text(ITessAPI.TessBaseAPI handle) { + throw new UnsupportedOperationException("Not supported yet."); + } + + @Override + public Pointer TessBaseAPIGetHOCRText(ITessAPI.TessBaseAPI handle, int page_number) { + throw new UnsupportedOperationException("Not supported yet."); + } + + @Override + public Pointer TessBaseAPIGetBoxText(ITessAPI.TessBaseAPI handle, int page_number) { + throw new UnsupportedOperationException("Not supported yet."); + } + + @Override + public Pointer TessBaseAPIGetUNLVText(ITessAPI.TessBaseAPI handle) { + throw new UnsupportedOperationException("Not supported yet."); + } + + @Override + public int TessBaseAPIMeanTextConf(ITessAPI.TessBaseAPI handle) { + throw new UnsupportedOperationException("Not supported yet."); + } + + @Override + public IntByReference TessBaseAPIAllWordConfidences(ITessAPI.TessBaseAPI handle) { + throw new UnsupportedOperationException("Not supported yet."); + } + + @Override + public int TessBaseAPIAdaptToWordStr(ITessAPI.TessBaseAPI handle, int mode, String wordstr) { + throw new UnsupportedOperationException("Not supported yet."); + } + + @Override + public void TessBaseAPIClear(ITessAPI.TessBaseAPI handle) { + throw new UnsupportedOperationException("Not supported yet."); + } + + @Override + public void TessBaseAPIEnd(ITessAPI.TessBaseAPI handle) { + throw new UnsupportedOperationException("Not supported yet."); + } + + @Override + public int TessBaseAPIIsValidWord(ITessAPI.TessBaseAPI handle, String word) { + throw new UnsupportedOperationException("Not supported yet."); + } + + @Override + public int TessBaseAPIGetTextDirection(ITessAPI.TessBaseAPI handle, IntBuffer out_offset, FloatBuffer out_slope) { + throw new UnsupportedOperationException("Not supported yet."); + } + + @Override + public void TessBaseAPIClearPersistentCache(ITessAPI.TessBaseAPI handle) { + throw new UnsupportedOperationException("Not supported yet."); + } + + @Override + public int TessBaseAPIDetectOrientationScript(TessBaseAPI handle, IntBuffer orient_deg, FloatBuffer orient_conf, PointerByReference script_name, FloatBuffer script_conf) { + throw new UnsupportedOperationException("Not supported yet."); + } + + @Override + public String TessBaseAPIGetUnichar(ITessAPI.TessBaseAPI handle, int unichar_id) { + throw new UnsupportedOperationException("Not supported yet."); + } + + @Override + public void TessPageIteratorDelete(ITessAPI.TessPageIterator handle) { + throw new UnsupportedOperationException("Not supported yet."); + } + + @Override + public ITessAPI.TessPageIterator TessPageIteratorCopy(ITessAPI.TessPageIterator handle) { + throw new UnsupportedOperationException("Not supported yet."); + } + + @Override + public void TessPageIteratorBegin(ITessAPI.TessPageIterator handle) { + throw new UnsupportedOperationException("Not supported yet."); + } + + @Override + public int TessPageIteratorNext(ITessAPI.TessPageIterator handle, int level) { + throw new UnsupportedOperationException("Not supported yet."); + } + + @Override + public int TessPageIteratorIsAtBeginningOf(ITessAPI.TessPageIterator handle, int level) { + throw new UnsupportedOperationException("Not supported yet."); + } + + @Override + public int TessPageIteratorIsAtFinalElement(ITessAPI.TessPageIterator handle, int level, int element) { + throw new UnsupportedOperationException("Not supported yet."); + } + + @Override + public int TessPageIteratorBoundingBox(ITessAPI.TessPageIterator handle, int level, IntBuffer left, IntBuffer top, IntBuffer right, IntBuffer bottom) { + throw new UnsupportedOperationException("Not supported yet."); + } + + @Override + public int TessPageIteratorBlockType(ITessAPI.TessPageIterator handle) { + throw new UnsupportedOperationException("Not supported yet."); + } + + @Override + public Pix TessPageIteratorGetBinaryImage(ITessAPI.TessPageIterator handle, int level) { + throw new UnsupportedOperationException("Not supported yet."); + } + + @Override + public Pix TessPageIteratorGetImage(ITessAPI.TessPageIterator handle, int level, int padding, Pix original_image, IntBuffer left, IntBuffer top) { + throw new UnsupportedOperationException("Not supported yet."); + } + + @Override + public int TessPageIteratorBaseline(ITessAPI.TessPageIterator handle, int level, IntBuffer x1, IntBuffer y1, IntBuffer x2, IntBuffer y2) { + throw new UnsupportedOperationException("Not supported yet."); + } + + @Override + public void TessPageIteratorOrientation(ITessAPI.TessPageIterator handle, IntBuffer orientation, IntBuffer writing_direction, IntBuffer textline_order, FloatBuffer deskew_angle) { + throw new UnsupportedOperationException("Not supported yet."); + } + + @Override + public void TessPageIteratorParagraphInfo(ITessAPI.TessPageIterator handle, IntBuffer justification, IntBuffer is_list_item, IntBuffer is_crown, IntBuffer first_line_indent) { + throw new UnsupportedOperationException("Not supported yet."); + } + + @Override + public void TessResultIteratorDelete(ITessAPI.TessResultIterator handle) { + throw new UnsupportedOperationException("Not supported yet."); + } + + @Override + public ITessAPI.TessResultIterator TessResultIteratorCopy(ITessAPI.TessResultIterator handle) { + throw new UnsupportedOperationException("Not supported yet."); + } + + @Override + public ITessAPI.TessPageIterator TessResultIteratorGetPageIterator(ITessAPI.TessResultIterator handle) { + throw new UnsupportedOperationException("Not supported yet."); + } + + @Override + public ITessAPI.TessPageIterator TessResultIteratorGetPageIteratorConst(ITessAPI.TessResultIterator handle) { + throw new UnsupportedOperationException("Not supported yet."); + } + + @Override + public int TessResultIteratorNext(ITessAPI.TessResultIterator handle, int level) { + throw new UnsupportedOperationException("Not supported yet."); + } + + @Override + public Pointer TessResultIteratorGetUTF8Text(ITessAPI.TessResultIterator handle, int level) { + throw new UnsupportedOperationException("Not supported yet."); + } + + @Override + public float TessResultIteratorConfidence(ITessAPI.TessResultIterator handle, int level) { + throw new UnsupportedOperationException("Not supported yet."); + } + + @Override + public String TessResultIteratorWordRecognitionLanguage(ITessAPI.TessResultIterator handle) { + throw new UnsupportedOperationException("Not supported yet."); + } + + @Override + public String TessResultIteratorWordFontAttributes(ITessAPI.TessResultIterator handle, IntBuffer is_bold, IntBuffer is_italic, IntBuffer is_underlined, IntBuffer is_monospace, IntBuffer is_serif, IntBuffer is_smallcaps, IntBuffer pointsize, IntBuffer font_id) { + throw new UnsupportedOperationException("Not supported yet."); + } + + @Override + public int TessResultIteratorWordIsFromDictionary(ITessAPI.TessResultIterator handle) { + throw new UnsupportedOperationException("Not supported yet."); + } + + @Override + public int TessResultIteratorWordIsNumeric(ITessAPI.TessResultIterator handle) { + throw new UnsupportedOperationException("Not supported yet."); + } + + @Override + public int TessResultIteratorSymbolIsSuperscript(ITessAPI.TessResultIterator handle) { + throw new UnsupportedOperationException("Not supported yet."); + } + + @Override + public int TessResultIteratorSymbolIsSubscript(ITessAPI.TessResultIterator handle) { + throw new UnsupportedOperationException("Not supported yet."); + } + + @Override + public int TessResultIteratorSymbolIsDropcap(ITessAPI.TessResultIterator handle) { + throw new UnsupportedOperationException("Not supported yet."); + } + + @Override + public ITessAPI.TessChoiceIterator TessResultIteratorGetChoiceIterator(ITessAPI.TessResultIterator handle) { + throw new UnsupportedOperationException("Not supported yet."); + } + + @Override + public void TessChoiceIteratorDelete(ITessAPI.TessChoiceIterator handle) { + throw new UnsupportedOperationException("Not supported yet."); + } + + @Override + public int TessChoiceIteratorNext(ITessAPI.TessChoiceIterator handle) { + throw new UnsupportedOperationException("Not supported yet."); + } + + @Override + public String TessChoiceIteratorGetUTF8Text(ITessAPI.TessChoiceIterator handle) { + throw new UnsupportedOperationException("Not supported yet."); + } + + @Override + public float TessChoiceIteratorConfidence(ITessAPI.TessChoiceIterator handle) { + throw new UnsupportedOperationException("Not supported yet."); + } + + @Override + public ETEXT_DESC TessMonitorCreate() { + throw new UnsupportedOperationException("Not supported yet."); + } + + @Override + public void TessMonitorDelete(ETEXT_DESC monitor) { + throw new UnsupportedOperationException("Not supported yet."); + } + + @Override + public void TessMonitorSetCancelFunc(ETEXT_DESC monitor, TessCancelFunc cancelFunc) { + throw new UnsupportedOperationException("Not supported yet."); + } + + @Override + public void TessMonitorSetCancelThis(ETEXT_DESC monitor, Pointer cancelThis) { + throw new UnsupportedOperationException("Not supported yet."); + } + + @Override + public Pointer TessMonitorGetCancelThis(ETEXT_DESC monitor) { + throw new UnsupportedOperationException("Not supported yet."); + } + + @Override + public void TessMonitorSetProgressFunc(ETEXT_DESC monitor, TessProgressFunc progressFunc) { + throw new UnsupportedOperationException("Not supported yet."); + } + + @Override + public int TessMonitorGetProgress(ETEXT_DESC monitor) { + throw new UnsupportedOperationException("Not supported yet."); + } + + @Override + public void TessMonitorSetDeadlineMSecs(ETEXT_DESC monitor, int deadline) { + throw new UnsupportedOperationException("Not supported yet."); + } + + @Override + public TessResultRenderer TessAltoRendererCreate(String outputbase) { + throw new UnsupportedOperationException("Not supported yet."); + } + + @Override + public Pointer TessBaseAPIGetAltoText(TessBaseAPI handle, int page_number) { + throw new UnsupportedOperationException("Not supported yet."); + } + + @Override + public TessResultRenderer TessLSTMBoxRendererCreate(String outputbase) { + throw new UnsupportedOperationException("Not supported yet."); + } + + @Override + public TessResultRenderer TessWordStrBoxRendererCreate(String outputbase) { + throw new UnsupportedOperationException("Not supported yet."); + } + + @Override + public Pointer TessBaseAPIGetLSTMBoxText(TessBaseAPI handle, int page_number) { + throw new UnsupportedOperationException("Not supported yet."); + } + + @Override + public Pointer TessBaseAPIGetWordStrBoxText(TessBaseAPI handle, int page_number) { + throw new UnsupportedOperationException("Not supported yet."); + } + + @Override + public TessResultRenderer TessTsvRendererCreate(String outputbase) { + throw new UnsupportedOperationException("Not supported yet."); + } + + @Override + public Pointer TessBaseAPIGetTsvText(TessBaseAPI handle, int page_number) { + throw new UnsupportedOperationException("Not supported yet."); + } +} diff --git a/d4dj/src/test/java/net/sourceforge/tess4j/TessAPITest.java b/d4dj/src/test/java/net/sourceforge/tess4j/TessAPITest.java new file mode 100644 index 0000000..8c07e0c --- /dev/null +++ b/d4dj/src/test/java/net/sourceforge/tess4j/TessAPITest.java @@ -0,0 +1,711 @@ +/** + * Copyright @ 2012 Quan Nguyen + * + * Licensed under the Apache License, Version 2.0 (the "License"); you may not + * use this file except in compliance with the License. You may obtain a copy of + * the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, WITHOUT + * WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the + * License for the specific language governing permissions and limitations under + * the License. + */ +package net.sourceforge.tess4j; + +import static org.junit.Assert.assertArrayEquals; + +import java.awt.image.BufferedImage; +import java.io.BufferedReader; +import java.io.File; +import java.io.FileInputStream; +import java.io.FileReader; +import java.nio.ByteBuffer; +import java.nio.FloatBuffer; +import java.nio.IntBuffer; +import java.util.Arrays; + +import javax.imageio.ImageIO; + +import net.sourceforge.tess4j.util.ImageIOHelper; +import net.sourceforge.tess4j.util.LoggHelper; +import net.sourceforge.tess4j.util.Utils; + +import org.junit.After; +import org.junit.AfterClass; +import org.junit.Before; +import org.junit.BeforeClass; +import org.junit.Test; + +import com.ochafik.lang.jnaerator.runtime.NativeSize; +import com.sun.jna.NativeLong; +import com.sun.jna.Pointer; +import com.sun.jna.StringArray; +import com.sun.jna.ptr.PointerByReference; +import net.sourceforge.lept4j.Box; +import net.sourceforge.lept4j.Boxa; +import static net.sourceforge.lept4j.ILeptonica.L_CLONE; +import net.sourceforge.lept4j.Leptonica; +import net.sourceforge.lept4j.Pix; +import net.sourceforge.lept4j.util.LeptUtils; + +import net.sourceforge.tess4j.ITessAPI.*; +import org.slf4j.Logger; +import org.slf4j.LoggerFactory; + +import static net.sourceforge.tess4j.ITessAPI.FALSE; +import static net.sourceforge.tess4j.ITessAPI.TRUE; +import static org.junit.Assert.assertEquals; +import static org.junit.Assert.assertTrue; + +public class TessAPITest { + + private static final Logger logger = LoggerFactory.getLogger(new LoggHelper().toString()); + private final String datapath = "src/main/resources/tessdata"; + private final String testResourcesDataPath = "src/test/resources/test-data"; + String language = "eng"; + String expOCRResult = "The (quick) [brown] {fox} jumps!\nOver the $43,456.78 #90 dog"; + + TessAPI api; + TessBaseAPI handle; + + @BeforeClass + public static void setUpClass() throws Exception { + } + + @AfterClass + public static void tearDownClass() throws Exception { + } + + @Before + public void setUp() { + api = new TessAPIImpl().getInstance(); + handle = api.TessBaseAPICreate(); + } + + @After + public void tearDown() { + api.TessBaseAPIDelete(handle); + } + + /** + * Test of TessBaseAPIRect method, of class TessAPI. + * + * @throws Exception while processing the image + */ + @Test + public void testTessBaseAPIRect() throws Exception { + logger.info("TessBaseAPIRect"); + String expResult = expOCRResult; + File tiff = new File(this.testResourcesDataPath, "eurotext.tif"); + BufferedImage image = ImageIO.read(tiff); // require jai-imageio lib to read TIFF + ByteBuffer buf = ImageIOHelper.convertImageData(image); + int bpp = image.getColorModel().getPixelSize(); + int bytespp = bpp / 8; + int bytespl = (int) Math.ceil(image.getWidth() * bpp / 8.0); + api.TessBaseAPIInit3(handle, datapath, language); + api.TessBaseAPISetPageSegMode(handle, TessPageSegMode.PSM_AUTO); + Pointer utf8Text = api.TessBaseAPIRect(handle, buf, bytespp, bytespl, 0, 0, 1024, 800); + String result = utf8Text.getString(0); + api.TessDeleteText(utf8Text); + logger.info(result); + assertTrue(result.startsWith(expResult)); + } + + /** + * Test of TessBaseAPIGetUTF8Text method, of class TessAPI. + * + * @throws Exception while processing the image + */ + @Test + public void testTessBaseAPIGetUTF8Text() throws Exception { + logger.info("TessBaseAPIGetUTF8Text"); + String expResult = expOCRResult; + File tiff = new File(this.testResourcesDataPath, "eurotext.tif"); + BufferedImage image = ImageIO.read(new FileInputStream(tiff)); // require jai-imageio lib to read TIFF + ByteBuffer buf = ImageIOHelper.convertImageData(image); + int bpp = image.getColorModel().getPixelSize(); + int bytespp = bpp / 8; + int bytespl = (int) Math.ceil(image.getWidth() * bpp / 8.0); + api.TessBaseAPIInit3(handle, datapath, language); + api.TessBaseAPISetPageSegMode(handle, TessPageSegMode.PSM_AUTO); + api.TessBaseAPISetImage(handle, buf, image.getWidth(), image.getHeight(), bytespp, bytespl); + api.TessBaseAPISetRectangle(handle, 0, 0, 1024, 800); + Pointer utf8Text = api.TessBaseAPIGetUTF8Text(handle); + String result = utf8Text.getString(0); + api.TessDeleteText(utf8Text); + logger.info(result); + assertTrue(result.startsWith(expResult)); + } + + /** + * Test of TessBaseAPIGetUTF8Text method, of class TessAPI. + * + * @throws java.lang.Exception + */ + @Test + public void testTessBaseAPIGetUTF8Text_Pix() throws Exception { + logger.info("TessBaseAPIGetUTF8Text_Pix"); + String expResult = expOCRResult; + File tiff = new File(this.testResourcesDataPath, "eurotext.tif"); + Leptonica leptInstance = Leptonica.INSTANCE; + Pix pix = leptInstance.pixRead(tiff.getPath()); + api.TessBaseAPIInit3(handle, datapath, language); + api.TessBaseAPISetImage2(handle, pix); + Pointer utf8Text = api.TessBaseAPIGetUTF8Text(handle); + String result = utf8Text.getString(0); + api.TessDeleteText(utf8Text); + logger.info(result); + + //release Pix resource + PointerByReference pRef = new PointerByReference(); + pRef.setValue(pix.getPointer()); + leptInstance.pixDestroy(pRef); + + assertTrue(result.startsWith(expResult)); + } + + /** + * Test of TessBaseAPIGetComponentImages method, of class TessAPI. + * + * @throws java.lang.Exception + */ + @Test + public void testTessBaseAPIGetComponentImages() throws Exception { + logger.info("TessBaseAPIGetComponentImages"); + File image = new File(this.testResourcesDataPath, "eurotext.png"); + int expResult = 12; // number of lines in the test image + Leptonica leptInstance = Leptonica.INSTANCE; + Pix pix = leptInstance.pixRead(image.getPath()); + api.TessBaseAPIInit3(handle, datapath, language); + api.TessBaseAPISetImage2(handle, pix); + PointerByReference pixa = null; + PointerByReference blockids = null; + Boxa boxes = api.TessBaseAPIGetComponentImages(handle, TessPageIteratorLevel.RIL_TEXTLINE, TRUE, pixa, blockids); +// boxes = api.TessBaseAPIGetRegions(handle, pixa); // equivalent to TessPageIteratorLevel.RIL_BLOCK + int boxCount = leptInstance.boxaGetCount(boxes); + for (int i = 0; i < boxCount; i++) { + Box box = leptInstance.boxaGetBox(boxes, i, L_CLONE); + if (box == null) { + continue; + } + api.TessBaseAPISetRectangle(handle, box.x, box.y, box.w, box.h); + Pointer utf8Text = api.TessBaseAPIGetUTF8Text(handle); + String ocrResult = utf8Text.getString(0); + api.TessDeleteText(utf8Text); + int conf = api.TessBaseAPIMeanTextConf(handle); + System.out.print(String.format("Box[%d]: x=%d, y=%d, w=%d, h=%d, confidence: %d, text: %s", i, box.x, box.y, box.w, box.h, conf, ocrResult)); + LeptUtils.dispose(box); + } + + // release Pix and Boxa resources + LeptUtils.dispose(pix); + LeptUtils.dispose(boxes); + + assertEquals(expResult, boxCount); + } + + /** + * Test of TessVersion method, of class TessAPI. + */ + @Test + public void testTessVersion() { + logger.info("TessVersion"); + String expResult = "5.0.0"; + String result = api.TessVersion(); + logger.info(result); + assertTrue(result.startsWith(expResult)); + } + + /** + * Test of TessBaseAPISetVariable method, of class TessAPI. + */ + @Test + public void testTessBaseAPISetVariable() { + logger.info("TessBaseAPISetVariable"); + String name = "tessedit_create_hocr"; + String value = "1"; + int expResult = 1; + int result = api.TessBaseAPISetVariable(handle, name, value); + assertEquals(expResult, result); + } + + /** + * Test of TessBaseAPIGetBoolVariable method, of class TessAPI. + */ + @Test + public void testTessBaseAPIGetBoolVariable() { + logger.info("TessBaseAPIGetBoolVariable"); + String name = "tessedit_create_hocr"; + api.TessBaseAPISetVariable(handle, name, "1"); + IntBuffer value = IntBuffer.allocate(1); + int result = -1; + if (api.TessBaseAPIGetBoolVariable(handle, "tessedit_create_hocr", value) == TRUE) { + result = value.get(0); + } + int expResult = 1; + assertEquals(expResult, result); + } + + /** + * Test of TessBaseAPIPrintVariables method, of class TessAPI. + * + * @throws Exception while persisting variables to file + */ + @Test + public void testTessBaseAPIPrintVariablesToFile() throws Exception { + logger.info("TessBaseAPIPrintVariablesToFile"); + String var = "tessedit_char_whitelist"; + String value = "0123456789"; + api.TessBaseAPISetVariable(handle, var, value); + String filename = "printvar.txt"; + api.TessBaseAPIPrintVariablesToFile(handle, filename); // will crash if not invoked after some method + File file = new File(filename); + BufferedReader input = new BufferedReader(new FileReader(file)); + StringBuilder strB = new StringBuilder(); + String line; + String EOL = System.getProperty("line.separator"); + while ((line = input.readLine()) != null) { + strB.append(line).append(EOL); + } + input.close(); + file.delete(); + assertTrue(strB.toString().contains(var + "\t" + value)); + } + + /** + * Test of TessBaseAPIInit4 method, of class TessAPI. + */ + @Test + public void testTessBaseAPIInit4() { + logger.info("TessBaseAPIInit4"); + int oem = TessOcrEngineMode.OEM_DEFAULT; + PointerByReference configs = null; + int configs_size = 0; + // disable loading dictionaries + String[] args = new String[]{"load_system_dawg", "load_freq_dawg"}; + StringArray sarray = new StringArray(args); + PointerByReference vars_vec = new PointerByReference(); + vars_vec.setPointer(sarray); + + args = new String[]{"F", "F"}; + sarray = new StringArray(args); + PointerByReference vars_values = new PointerByReference(); + vars_values.setPointer(sarray); + + NativeSize vars_vec_size = new NativeSize(args.length); + + int expResult = 0; + int result = api.TessBaseAPIInit4(handle, datapath, language, oem, configs, configs_size, vars_vec, vars_values, vars_vec_size, FALSE); + assertEquals(expResult, result); + } + + /** + * Test of TessBaseAPIGetInitLanguagesAsString method, of class TessAPI. + */ + @Test + public void testTessBaseAPIGetInitLanguagesAsString() { + logger.info("TessBaseAPIGetInitLanguagesAsString"); + String expResult = ""; + String result = api.TessBaseAPIGetInitLanguagesAsString(handle); + assertEquals(expResult, result); + } + + /** + * Test of TessBaseAPIGetLoadedLanguagesAsVector method, of class TessAPI. + */ + @Test + public void testTessBaseAPIGetLoadedLanguagesAsVector() { + logger.info("TessBaseAPIGetLoadedLanguagesAsVector"); + api.TessBaseAPIInit3(handle, datapath, language); + String[] expResult = {"eng"}; + String[] result = api.TessBaseAPIGetLoadedLanguagesAsVector(handle).getPointer().getStringArray(0); + assertArrayEquals(expResult, result); + } + + /** + * Test of TessBaseAPIGetAvailableLanguagesAsVector method, of class + * TessAPI. + */ + @Test + public void testTessBaseAPIGetAvailableLanguagesAsVector() { + logger.info("TessBaseAPIGetAvailableLanguagesAsVector"); + api.TessBaseAPIInit3(handle, datapath, language); + String[] expResult = {"eng"}; + String[] result = api.TessBaseAPIGetAvailableLanguagesAsVector(handle).getPointer().getStringArray(0); + assertTrue(Arrays.asList(result).containsAll(Arrays.asList(expResult))); + } + + /** + * Test of TessBaseAPIGetHOCRText method, of class TessAPI. + * + * @throws Exception while getting hocr text + */ + @Test + public void testTessBaseAPIGetHOCRText() throws Exception { + logger.info("TessBaseAPIGetHOCRText"); + String filename = String.format("%s/%s", this.testResourcesDataPath, "eurotext.tif"); + File tiff = new File(filename); + BufferedImage image = ImageIO.read(new FileInputStream(tiff)); // require jai-imageio lib to read TIFF + ByteBuffer buf = ImageIOHelper.convertImageData(image); + int bpp = image.getColorModel().getPixelSize(); + int bytespp = bpp / 8; + int bytespl = (int) Math.ceil(image.getWidth() * bpp / 8.0); + api.TessBaseAPISetPageSegMode(handle, TessPageSegMode.PSM_AUTO); + api.TessBaseAPIInit3(handle, datapath, language); + api.TessBaseAPISetImage(handle, buf, image.getWidth(), image.getHeight(), bytespp, bytespl); + int page_number = 0; + Pointer utf8Text = api.TessBaseAPIGetHOCRText(handle, page_number); + String result = utf8Text.getString(0); + api.TessDeleteText(utf8Text); + assertTrue(result.contains("
")); + + // WordStr Box output + textPtr = api.TessBaseAPIGetWordStrBoxText(handle, page_number); + result = textPtr.getString(0); + api.TessDeleteText(textPtr); + assertTrue(result.contains("WordStr")); + + // TSV output + textPtr = api.TessBaseAPIGetTsvText(handle, page_number); + result = textPtr.getString(0); + api.TessDeleteText(textPtr); + assertTrue(result.contains("1\t")); + + // LSTM Box output + textPtr = api.TessBaseAPIGetLSTMBoxText(handle, page_number); + result = textPtr.getString(0); + api.TessDeleteText(textPtr); + assertTrue(result.contains("\t")); + } + + /** + * Test of TessBaseAPIAnalyseLayout method, of class TessAPI. + * + * @throws java.lang.Exception + */ + @Test + public void testTessBaseAPIAnalyseLayout() throws Exception { + logger.info("TessBaseAPIAnalyseLayout"); + File image = new File(testResourcesDataPath, "eurotext.png"); + int expResult = 12; // number of lines in the test image + Leptonica leptInstance = Leptonica.INSTANCE; + Pix pix = leptInstance.pixRead(image.getPath()); + api.TessBaseAPIInit3(handle, datapath, language); + api.TessBaseAPISetImage2(handle, pix); + int pageIteratorLevel = TessPageIteratorLevel.RIL_TEXTLINE; + logger.info("PageIteratorLevel: " + Utils.getConstantName(pageIteratorLevel, TessPageIteratorLevel.class)); + int i = 0; + TessPageIterator pi = api.TessBaseAPIAnalyseLayout(handle); + + do { + IntBuffer leftB = IntBuffer.allocate(1); + IntBuffer topB = IntBuffer.allocate(1); + IntBuffer rightB = IntBuffer.allocate(1); + IntBuffer bottomB = IntBuffer.allocate(1); + api.TessPageIteratorBoundingBox(pi, pageIteratorLevel, leftB, topB, rightB, bottomB); + int left = leftB.get(); + int top = topB.get(); + int right = rightB.get(); + int bottom = bottomB.get(); + logger.info(String.format("Box[%d]: x=%d, y=%d, w=%d, h=%d", i++, left, top, right - left, bottom - top)); + } while (api.TessPageIteratorNext(pi, pageIteratorLevel) == TRUE); + api.TessPageIteratorDelete(pi); + PointerByReference pRef = new PointerByReference(); + pRef.setValue(pix.getPointer()); + leptInstance.pixDestroy(pRef); + assertEquals(expResult, i); + } + + /** + * Test of TessBaseAPIDetectOrientationScript method, of class TessAPI. + * + * @throws java.lang.Exception + */ + @Test + public void testTessBaseAPIDetectOrientationScript() throws Exception { + logger.info("TessBaseAPIDetectOrientationScript"); + File image = new File(testResourcesDataPath, "eurotext90.png"); + int expResult = TRUE; + Leptonica leptInstance = Leptonica.INSTANCE; + Pix pix = leptInstance.pixRead(image.getPath()); + api.TessBaseAPIInit3(handle, datapath, "osd"); + api.TessBaseAPISetImage2(handle, pix); + + IntBuffer orient_degB = IntBuffer.allocate(1); + FloatBuffer orient_confB = FloatBuffer.allocate(1); + PointerByReference script_nameB = new PointerByReference(); + FloatBuffer script_confB = FloatBuffer.allocate(1); + + int result = api.TessBaseAPIDetectOrientationScript(handle, orient_degB, orient_confB, script_nameB, script_confB); + if (result == TRUE) { + int orient_deg = orient_degB.get(); + float orient_conf = orient_confB.get(); + String script_name = script_nameB.getValue().getString(0); + float script_conf = script_confB.get(); + logger.info(String.format("OrientationScript: orient_deg=%d, orient_conf=%f, script_name=%s, script_conf=%f", orient_deg, orient_conf, script_name, script_conf)); + } + + PointerByReference pRef = new PointerByReference(); + pRef.setValue(pix.getPointer()); + leptInstance.pixDestroy(pRef); + assertEquals(expResult, result); + } + + /** + * Test of Orientation and script detection (OSD). + * + * @throws Exception while processing image + */ + @Test + public void testOSD() throws Exception { + logger.info("OSD"); + int expResult = TessPageSegMode.PSM_AUTO_OSD; + IntBuffer orientation = IntBuffer.allocate(1); + IntBuffer direction = IntBuffer.allocate(1); + IntBuffer order = IntBuffer.allocate(1); + FloatBuffer deskew_angle = FloatBuffer.allocate(1); + File imageFile = new File(this.testResourcesDataPath, "eurotext90.png"); + BufferedImage image = ImageIO.read(new FileInputStream(imageFile)); + ByteBuffer buf = ImageIOHelper.convertImageData(image); + int bpp = image.getColorModel().getPixelSize(); + int bytespp = bpp / 8; + int bytespl = (int) Math.ceil(image.getWidth() * bpp / 8.0); + api.TessBaseAPIInit3(handle, datapath, language); + api.TessBaseAPISetPageSegMode(handle, TessPageSegMode.PSM_AUTO_OSD); + int actualResult = api.TessBaseAPIGetPageSegMode(handle); + logger.info("PSM: " + Utils.getConstantName(actualResult, TessPageSegMode.class)); + api.TessBaseAPISetImage(handle, buf, image.getWidth(), image.getHeight(), bytespp, bytespl); + int success = api.TessBaseAPIRecognize(handle, null); + if (success == 0) { + TessPageIterator pi = api.TessBaseAPIAnalyseLayout(handle); + api.TessPageIteratorOrientation(pi, orientation, direction, order, deskew_angle); + logger.info(String.format( + "Orientation: %s\nWritingDirection: %s\nTextlineOrder: %s\nDeskew angle: %.4f\n", + Utils.getConstantName(orientation.get(), TessOrientation.class), + Utils.getConstantName(direction.get(), TessWritingDirection.class), + Utils.getConstantName(order.get(), TessTextlineOrder.class), + deskew_angle.get())); + } + assertEquals(expResult, actualResult); + } + + /** + * Test of ResultIterator and PageIterator. + * + * @throws Exception + */ + @Test + public void testResultIterator() throws Exception { + logger.info("TessBaseAPIGetIterator"); + File tiff = new File(this.testResourcesDataPath, "eurotext.tif"); + BufferedImage image = ImageIO.read(new FileInputStream(tiff)); // require jai-imageio lib to read TIFF + ByteBuffer buf = ImageIOHelper.convertImageData(image); + int bpp = image.getColorModel().getPixelSize(); + int bytespp = bpp / 8; + int bytespl = (int) Math.ceil(image.getWidth() * bpp / 8.0); + api.TessBaseAPIInit3(handle, datapath, language); + api.TessBaseAPISetPageSegMode(handle, TessPageSegMode.PSM_AUTO); + api.TessBaseAPISetImage(handle, buf, image.getWidth(), image.getHeight(), bytespp, bytespl); + ETEXT_DESC monitor = new ETEXT_DESC(); + TimeVal timeout = new TimeVal(); + timeout.tv_sec = new NativeLong(0L); // time > 0 causes blank ouput + monitor.end_time = timeout; + ProgressMonitor pmo = new ProgressMonitor(monitor); + pmo.start(); + api.TessBaseAPIRecognize(handle, monitor); + logger.info("Message: " + pmo.getMessage()); + TessResultIterator ri = api.TessBaseAPIGetIterator(handle); + TessPageIterator pi = api.TessResultIteratorGetPageIterator(ri); + api.TessPageIteratorBegin(pi); + logger.info("Bounding boxes:\nchar(s) left top right bottom confidence font-attributes"); + int level = TessPageIteratorLevel.RIL_WORD; + + // int height = image.getHeight(); + do { + Pointer ptr = api.TessResultIteratorGetUTF8Text(ri, level); + String word = ptr.getString(0); + api.TessDeleteText(ptr); + float confidence = api.TessResultIteratorConfidence(ri, level); + IntBuffer leftB = IntBuffer.allocate(1); + IntBuffer topB = IntBuffer.allocate(1); + IntBuffer rightB = IntBuffer.allocate(1); + IntBuffer bottomB = IntBuffer.allocate(1); + api.TessPageIteratorBoundingBox(pi, level, leftB, topB, rightB, bottomB); + int left = leftB.get(); + int top = topB.get(); + int right = rightB.get(); + int bottom = bottomB.get(); + System.out.print(String.format("%s %d %d %d %d %f", word, left, top, right, bottom, confidence)); + // logger.info(String.format("%s %d %d %d %d", str, left, height - bottom, right, height - top)); // + // training box coordinates + + IntBuffer boldB = IntBuffer.allocate(1); + IntBuffer italicB = IntBuffer.allocate(1); + IntBuffer underlinedB = IntBuffer.allocate(1); + IntBuffer monospaceB = IntBuffer.allocate(1); + IntBuffer serifB = IntBuffer.allocate(1); + IntBuffer smallcapsB = IntBuffer.allocate(1); + IntBuffer pointSizeB = IntBuffer.allocate(1); + IntBuffer fontIdB = IntBuffer.allocate(1); + String fontName = api.TessResultIteratorWordFontAttributes(ri, boldB, italicB, underlinedB, monospaceB, + serifB, smallcapsB, pointSizeB, fontIdB); + boolean bold = boldB.get() == TRUE; + boolean italic = italicB.get() == TRUE; + boolean underlined = underlinedB.get() == TRUE; + boolean monospace = monospaceB.get() == TRUE; + boolean serif = serifB.get() == TRUE; + boolean smallcaps = smallcapsB.get() == TRUE; + int pointSize = pointSizeB.get(); + int fontId = fontIdB.get(); + logger.info(String.format(" font: %s, size: %d, font id: %d, bold: %b," + + " italic: %b, underlined: %b, monospace: %b, serif: %b, smallcap: %b", fontName, pointSize, + fontId, bold, italic, underlined, monospace, serif, smallcaps)); + } while (api.TessPageIteratorNext(pi, level) == TRUE); +// api.TessPageIteratorDelete(pi); + api.TessResultIteratorDelete(ri); + + assertTrue(true); + } + + /** + * Test of ChoiceIterator. + * + * @throws Exception + */ + @Test + public void testChoiceIterator() throws Exception { + logger.info("TessResultIteratorGetChoiceIterator"); + String filename = String.format("%s/%s", this.testResourcesDataPath, "eurotext.tif"); + File tiff = new File(filename); + BufferedImage image = ImageIO.read(new FileInputStream(tiff)); // require jai-imageio lib to read TIFF + ByteBuffer buf = ImageIOHelper.convertImageData(image); + int bpp = image.getColorModel().getPixelSize(); + int bytespp = bpp / 8; + int bytespl = (int) Math.ceil(image.getWidth() * bpp / 8.0); + api.TessBaseAPIInit3(handle, datapath, language); + api.TessBaseAPISetImage(handle, buf, image.getWidth(), image.getHeight(), bytespp, bytespl); + api.TessBaseAPISetVariable(handle, "save_blob_choices", "T"); + api.TessBaseAPISetRectangle(handle, 37, 228, 548, 31); + ETEXT_DESC monitor = new ETEXT_DESC(); + ProgressMonitor pmo = new ProgressMonitor(monitor); + pmo.start(); + api.TessBaseAPIRecognize(handle, monitor); + logger.info("Message: " + pmo.getMessage()); + TessResultIterator ri = api.TessBaseAPIGetIterator(handle); + int level = TessPageIteratorLevel.RIL_SYMBOL; + + if (ri != null) { + do { + Pointer symbol = api.TessResultIteratorGetUTF8Text(ri, level); + float conf = api.TessResultIteratorConfidence(ri, level); + if (symbol != null) { + logger.info(String.format("symbol %s, conf: %f", symbol.getString(0), conf)); + boolean indent = false; + TessChoiceIterator ci = api.TessResultIteratorGetChoiceIterator(ri); + do { + if (indent) { + System.out.print("\t"); + } + System.out.print("\t- "); + String choice = api.TessChoiceIteratorGetUTF8Text(ci); + logger.info(String.format("%s conf: %f", choice, api.TessChoiceIteratorConfidence(ci))); + indent = true; + } while (api.TessChoiceIteratorNext(ci) == ITessAPI.TRUE); + api.TessChoiceIteratorDelete(ci); + } + logger.info("---------------------------------------------"); + api.TessDeleteText(symbol); + } while (api.TessResultIteratorNext(ri, level) == ITessAPI.TRUE); + api.TessResultIteratorDelete(ri); + } + + assertTrue(true); + } + + /** + * Test of ResultRenderer method, of class TessAPI. + * + * @throws java.lang.Exception + */ + @Test + public void testResultRenderer() throws Exception { + logger.info("TessResultRenderer"); + String image = String.format("%s/%s", this.testResourcesDataPath, "eurotext.tif"); + String output = "capi-test.txt"; + int set_only_init_params = FALSE; + int oem = TessOcrEngineMode.OEM_DEFAULT; + PointerByReference configs = null; + int configs_size = 0; + + String[] params = {"load_system_dawg", "tessedit_char_whitelist"}; + String vals[] = {"F", ""}; //0123456789-.IThisalotfpnex + PointerByReference vars_vec = new PointerByReference(); + vars_vec.setPointer(new StringArray(params)); + PointerByReference vars_values = new PointerByReference(); + vars_values.setPointer(new StringArray(vals)); + NativeSize vars_vec_size = new NativeSize(params.length); + + api.TessBaseAPISetOutputName(handle, output); + + int rc = api.TessBaseAPIInit4(handle, datapath, language, + oem, configs, configs_size, vars_vec, vars_values, vars_vec_size, set_only_init_params); + + if (rc != 0) { + api.TessBaseAPIDelete(handle); + logger.error("Could not initialize tesseract."); + return; + } + + String outputbase = "target/test-classes/test-results/ResultRenderer"; + TessResultRenderer renderer = api.TessHOcrRendererCreate(outputbase); + api.TessResultRendererInsert(renderer, api.TessBoxTextRendererCreate(outputbase)); + api.TessResultRendererInsert(renderer, api.TessTextRendererCreate(outputbase)); + String dataPath = api.TessBaseAPIGetDatapath(handle); + api.TessResultRendererInsert(renderer, api.TessPDFRendererCreate(outputbase, dataPath, FALSE)); + int result = api.TessBaseAPIProcessPages(handle, image, null, 0, renderer); + + if (result == FALSE) { + logger.error("Error during processing."); + return; + } + + while ((renderer = api.TessResultRendererNext(renderer)) != null) { + String ext = api.TessResultRendererExtention(renderer).getString(0); + logger.info(String.format("TessResultRendererExtention: %s\nTessResultRendererTitle: %s\nTessResultRendererImageNum: %d", + ext, + api.TessResultRendererTitle(renderer).getString(0), + api.TessResultRendererImageNum(renderer))); + } + + api.TessDeleteResultRenderer(renderer); + assertTrue(new File(outputbase + ".pdf").exists()); + } +} diff --git a/d4dj/src/test/java/net/sourceforge/tess4j/Tesseract1Test.java b/d4dj/src/test/java/net/sourceforge/tess4j/Tesseract1Test.java new file mode 100644 index 0000000..10db584 --- /dev/null +++ b/d4dj/src/test/java/net/sourceforge/tess4j/Tesseract1Test.java @@ -0,0 +1,336 @@ +/** + * Copyright @ 2010 Quan Nguyen + * + * Licensed under the Apache License, Version 2.0 (the "License"); you may not + * use this file except in compliance with the License. You may obtain a copy of + * the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, WITHOUT + * WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the + * License for the specific language governing permissions and limitations under + * the License. + */ +package net.sourceforge.tess4j; + +import java.awt.Rectangle; +import java.awt.image.BufferedImage; +import java.io.File; +import java.util.ArrayList; +import java.util.List; +import java.util.Arrays; +import javax.imageio.ImageIO; + +import net.sourceforge.tess4j.util.ImageHelper; +import net.sourceforge.tess4j.util.LoggHelper; +import net.sourceforge.tess4j.util.Utils; + +import net.sourceforge.tess4j.ITesseract.RenderedFormat; +import net.sourceforge.tess4j.ITessAPI.TessPageIteratorLevel; + +import com.recognition.software.jdeskew.ImageDeskew; +import java.awt.Graphics2D; +import java.util.HashMap; +import java.util.Map; + +import static org.junit.Assert.*; +import org.junit.After; +import org.junit.AfterClass; +import org.junit.Before; +import org.junit.BeforeClass; +import org.junit.Test; + +import org.slf4j.Logger; +import org.slf4j.LoggerFactory; + +public class Tesseract1Test { + + private static final Logger logger = LoggerFactory.getLogger(new LoggHelper().toString()); + static final double MINIMUM_DESKEW_THRESHOLD = 0.05d; + ITesseract instance; + + private final String datapath = "src/main/resources/tessdata"; + private final String testResourcesDataPath = "src/test/resources/test-data"; + + @BeforeClass + public static void setUpClass() throws Exception { + } + + @AfterClass + public static void tearDownClass() throws Exception { + } + + @Before + public void setUp() { + instance = new Tesseract1(); + instance.setDatapath(new File(datapath).getPath()); + } + + @After + public void tearDown() { + } + + /** + * Test of doOCR method, of class Tesseract1. + * + * @throws Exception while processing image. + */ + @Test + public void testDoOCR_File() throws Exception { + logger.info("doOCR on a PNG image"); + File imageFile = new File(this.testResourcesDataPath, "eurotext.png"); + String expResult = "The (quick) [brown] {fox} jumps!\nOver the $43,456.78 #90 dog"; + String result = instance.doOCR(imageFile); + logger.info(result); + assertEquals(expResult, result.substring(0, expResult.length())); + } + + /** + * Test of doOCR method, of class Tesseract. + * + * @throws java.lang.Exception + */ + @Test + public void testDoOCR_UNLV_Zone_File() throws Exception { + logger.info("doOCR on a PNG image with UNLV zone file .uzn"); + //UNLV zone format: left top width height label + String filename = String.format("%s/%s", this.testResourcesDataPath, "eurotext_unlv.png"); + File imageFile = new File(filename); + String expResult = "& duck/goose, as 12.5% of E-mail\n\n" + + "from aspammer@website.com is spam.\n\n" + + "The (quick) [brown] {fox} jumps!\n" + + "Over the $43,456.78 #90 dog"; + String result = instance.doOCR(imageFile); + logger.info(result); + assertEquals(expResult, result.trim().replace('—', '-')); + } + + /** + * Test of doOCR method, of class Tesseract. + * + * @throws java.lang.Exception + */ + @Test + public void testDoOCR_File_With_Configs() throws Exception { + logger.info("doOCR with configs"); + File imageFile = new File(this.testResourcesDataPath, "eurotext.png"); + String expResult = "[-0123456789.\n ]+"; + List configs = Arrays.asList("digits"); + instance.setConfigs(configs); + String result = instance.doOCR(imageFile); + logger.info(result); + assertTrue(result.matches(expResult)); + } + + /** + * Test of doOCR method, of class Tesseract1. + * + * @throws Exception while processing image. + */ + @Test + public void testDoOCR_File_Rectangle() throws Exception { + logger.info("doOCR on a BMP image with bounding rectangle"); + File imageFile = new File(this.testResourcesDataPath, "eurotext.bmp"); + Rectangle rect = new Rectangle(0, 0, 1024, 800); // define an equal or smaller region of interest on the image + String expResult = "The (quick) [brown] {fox} jumps!\nOver the $43,456.78 #90 dog"; + String result = instance.doOCR(imageFile, rect); + logger.info(result); + assertEquals(expResult, result.substring(0, expResult.length())); + } + + /** + * Test of doOCR method, of class Tesseract1. + * + * @throws Exception while processing image. + */ + @Test + public void testDoOCR_PDF() throws Exception { + logger.info("doOCR on a PDF document"); + File inputFile = new File(this.testResourcesDataPath, "eurotext.pdf"); + String expResult = "The (quick) [brown] {fox} jumps!\nOver the $43,456.78 #90 dog"; + String result = instance.doOCR(inputFile, null); + logger.info(result); + assertEquals(expResult, result.substring(0, expResult.length())); + } + + /** + * Test of doOCR method, of class Tesseract1. + * + * @throws Exception while processing image. + */ + @Test + public void testDoOCR_BufferedImage() throws Exception { + logger.info("doOCR on a buffered image of a PNG"); + File imageFile = new File(this.testResourcesDataPath, "eurotext.png"); + BufferedImage bi = ImageIO.read(imageFile); + String expResult = "The (quick) [brown] {fox} jumps!\nOver the $43,456.78 #90 dog"; + + Map types = new HashMap<>(); + types.put("TYPE_INT_RGB", BufferedImage.TYPE_INT_RGB); + types.put("TYPE_INT_ARGB", BufferedImage.TYPE_INT_ARGB); +// types.put("TYPE_INT_ARGB_PRE", BufferedImage.TYPE_INT_ARGB_PRE); +// types.put("TYPE_INT_BGR", BufferedImage.TYPE_INT_BGR); +// types.put("TYPE_3BYTE_BGR", BufferedImage.TYPE_3BYTE_BGR); +// types.put("TYPE_4BYTE_ABGR", BufferedImage.TYPE_4BYTE_ABGR); +// types.put("TYPE_4BYTE_ABGR_PRE", BufferedImage.TYPE_4BYTE_ABGR_PRE); +// types.put("TYPE_USHORT_565_RGB", BufferedImage.TYPE_USHORT_565_RGB); +// types.put("TYPE_USHORT_555_RGB", BufferedImage.TYPE_USHORT_555_RGB); +// types.put("TYPE_BYTE_GRAY", BufferedImage.TYPE_BYTE_GRAY); +// types.put("TYPE_USHORT_GRAY", BufferedImage.TYPE_USHORT_GRAY); +// types.put("TYPE_BYTE_BINARY", BufferedImage.TYPE_BYTE_BINARY); +// types.put("TYPE_BYTE_INDEXED", BufferedImage.TYPE_BYTE_INDEXED); + + for (Map.Entry entry : types.entrySet()) { + if (entry.getValue() == bi.getType()) { + String result = instance.doOCR(bi); + logger.info("BufferedImage type: " + entry.getKey() + " (Original)"); + logger.info(result); + logger.info(""); + assertEquals(expResult, result.substring(0, expResult.length())); + } else { + BufferedImage imageWithType = new BufferedImage(bi.getWidth(), bi.getHeight(), entry.getValue()); + Graphics2D g = imageWithType.createGraphics(); + g.drawImage(bi, 0, 0, null); + g.dispose(); + + String result = instance.doOCR(imageWithType); + logger.info("BufferedImage type: " + entry.getKey()); + logger.info(result); + logger.info(""); + assertEquals(expResult, result.substring(0, expResult.length())); + } + } + } + + /** + * Test of deskew algorithm. + * + * @throws Exception while processing image. + */ + @Test + public void testDoOCR_SkewedImage() throws Exception { + logger.info("doOCR on a skewed PNG image"); + File imageFile = new File(this.testResourcesDataPath, "eurotext_deskew.png"); + BufferedImage bi = ImageIO.read(imageFile); + ImageDeskew id = new ImageDeskew(bi); + double imageSkewAngle = id.getSkewAngle(); // determine skew angle + if ((imageSkewAngle > MINIMUM_DESKEW_THRESHOLD || imageSkewAngle < -(MINIMUM_DESKEW_THRESHOLD))) { + bi = ImageHelper.rotateImage(bi, -imageSkewAngle); // deskew image + } + + String expResult = "The (quick) [brown] {fox} jumps!\nOver the $43,456.78 #90 dog"; + String result = instance.doOCR(bi); + logger.info(result); + assertEquals(expResult, result.substring(0, expResult.length())); + } + + /** + * Test of createDocuments method, of class Tesseract1. + * + * @throws java.lang.Exception + */ + @Test + public void testCreateDocuments() throws Exception { + logger.info("createDocuments for an image"); + File imageFile1 = new File(this.testResourcesDataPath, "eurotext.pdf"); + File imageFile2 = new File(this.testResourcesDataPath, "eurotext.png"); + String outputbase1 = "target/test-classes/test-results/docrenderer1-1"; + String outputbase2 = "target/test-classes/test-results/docrenderer1-2"; + List formats = new ArrayList(Arrays.asList(RenderedFormat.HOCR, RenderedFormat.PDF, RenderedFormat.TEXT)); + instance.createDocuments(new String[]{imageFile1.getPath(), imageFile2.getPath()}, new String[]{outputbase1, outputbase2}, formats); + assertTrue(new File(outputbase1 + ".pdf").exists()); + } + + /** + * Test of getWords method, of class Tesseract1. + * + * @throws java.lang.Exception + */ + @Test + public void testGetWords() throws Exception { + logger.info("getWords"); + File imageFile = new File(this.testResourcesDataPath, "eurotext.tif"); + + String expResult = "The (quick) [brown] {fox} jumps!\nOver the $43,456.78 #90 dog"; + String[] expResults = expResult.split("\\s"); + + int pageIteratorLevel = TessPageIteratorLevel.RIL_WORD; + logger.info("PageIteratorLevel: " + Utils.getConstantName(pageIteratorLevel, TessPageIteratorLevel.class)); + BufferedImage bi = ImageIO.read(imageFile); + List result = instance.getWords(bi, pageIteratorLevel); + + // print the complete results + for (Word word : result) { + logger.info(word.toString()); + } + + List text = new ArrayList(); + for (Word word : result.subList(0, expResults.length)) { + text.add(word.getText().trim()); + } + + assertArrayEquals(expResults, text.toArray()); + } + + /** + * Test of getSegmentedRegions method, of class Tesseract1. + * + * @throws java.lang.Exception + */ + @Test + public void testGetSegmentedRegions() throws Exception { + logger.info("getSegmentedRegions at given TessPageIteratorLevel"); + File imageFile = new File(testResourcesDataPath, "eurotext.png"); + BufferedImage bi = ImageIO.read(imageFile); + int level = TessPageIteratorLevel.RIL_SYMBOL; + logger.info("PageIteratorLevel: " + Utils.getConstantName(level, TessPageIteratorLevel.class)); + List result = instance.getSegmentedRegions(bi, level); + for (int i = 0; i < result.size(); i++) { + Rectangle rect = result.get(i); + logger.info(String.format("Box[%d]: x=%d, y=%d, w=%d, h=%d", i, rect.x, rect.y, rect.width, rect.height)); + } + + assertTrue(result.size() > 0); + } + + /** + * Test of createDocumentsWithResults method, of class Tesseract1. + * + * @throws java.lang.Exception + */ + @Test + public void testCreateDocumentsWithResults() throws Exception { + logger.info("createDocumentsWithResults for multiple images at given TessPageIteratorLevel"); + File imageFile1 = new File(this.testResourcesDataPath, "eurotext.pdf"); + File imageFile2 = new File(this.testResourcesDataPath, "eurotext.png"); + String outputbase1 = "target/test-classes/test-results/docrenderer1-3"; + String outputbase2 = "target/test-classes/test-results/docrenderer1-4"; + List formats = new ArrayList(Arrays.asList(RenderedFormat.HOCR, RenderedFormat.PDF, RenderedFormat.TEXT)); + List results = instance.createDocumentsWithResults(new String[]{imageFile1.getPath(), imageFile2.getPath()}, new String[]{outputbase1, outputbase2}, formats, TessPageIteratorLevel.RIL_WORD); + assertTrue(new File(outputbase1 + ".pdf").exists()); + assertEquals(2, results.size()); + // Not work on Linux because unable to load pdf.ttf +// assertTrue(results.get(0).getConfidence() > 0); +// assertEquals(66, results.get(0).getWords().size()); + } + + /** + * Test of createDocumentsWithResults method, of class Tesseract1. + * + * @throws java.lang.Exception + */ + @Test + public void testCreateDocumentsWithResults1() throws Exception { + logger.info("createDocumentsWithResults for a buffered image at given TessPageIteratorLevel"); + File imageFile = new File(this.testResourcesDataPath, "eurotext.tif"); + BufferedImage bi = ImageIO.read(imageFile); + String outputbase = "target/test-classes/test-results/docrenderer-5"; + List formats = new ArrayList(Arrays.asList(RenderedFormat.HOCR, RenderedFormat.PDF, RenderedFormat.TEXT)); + OCRResult result = instance.createDocumentsWithResults(bi, imageFile.getName(), outputbase, formats, TessPageIteratorLevel.RIL_WORD); + assertTrue(new File(outputbase + ".pdf").exists()); + assertTrue(result.getConfidence() > 0); + assertEquals(66, result.getWords().size()); + } +} diff --git a/d4dj/src/test/java/net/sourceforge/tess4j/TesseractTest.java b/d4dj/src/test/java/net/sourceforge/tess4j/TesseractTest.java new file mode 100644 index 0000000..e6d1532 --- /dev/null +++ b/d4dj/src/test/java/net/sourceforge/tess4j/TesseractTest.java @@ -0,0 +1,341 @@ +/** + * Copyright @ 2010 Quan Nguyen + * + * Licensed under the Apache License, Version 2.0 (the "License"); you may not + * use this file except in compliance with the License. You may obtain a copy of + * the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, WITHOUT + * WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the + * License for the specific language governing permissions and limitations under + * the License. + */ +package net.sourceforge.tess4j; + +import java.awt.Rectangle; +import java.awt.Graphics2D; +import java.awt.image.BufferedImage; +import java.io.File; +import java.util.List; +import java.util.ArrayList; +import java.util.Arrays; +import java.util.Map; +import java.util.HashMap; +import javax.imageio.ImageIO; + +import net.sourceforge.tess4j.util.ImageHelper; +import net.sourceforge.tess4j.util.LoggHelper; +import net.sourceforge.tess4j.util.Utils; + +import net.sourceforge.tess4j.ITesseract.RenderedFormat; +import net.sourceforge.tess4j.ITessAPI.TessPageIteratorLevel; + +import com.recognition.software.jdeskew.ImageDeskew; + +import static org.junit.Assert.*; +import org.junit.After; +import org.junit.AfterClass; +import org.junit.Before; +import org.junit.BeforeClass; +import org.junit.Test; + +import org.slf4j.Logger; +import org.slf4j.LoggerFactory; + +public class TesseractTest { + + private static final Logger logger = LoggerFactory.getLogger(new LoggHelper().toString()); + static final double MINIMUM_DESKEW_THRESHOLD = 0.05d; + ITesseract instance; + + private final String datapath = "src/main/resources/tessdata"; + private final String testResourcesDataPath = "src/test/resources/test-data"; + + @BeforeClass + public static void setUpClass() throws Exception { + } + + @AfterClass + public static void tearDownClass() throws Exception { + } + + @Before + public void setUp() { + instance = new Tesseract(); + instance.setDatapath(new File(datapath).getPath()); + } + + @After + public void tearDown() { + } + + /** + * Test of doOCR method, of class Tesseract. + * + * @throws Exception while processing image. + */ + @Test + public void testDoOCR_File() throws Exception { + logger.info("doOCR on a PNG image"); + File imageFile = new File(this.testResourcesDataPath, "eurotext.png"); + String expResult = "The (quick) [brown] {fox} jumps!\nOver the $43,456.78 #90 dog"; + String result = instance.doOCR(imageFile); + logger.info(result); + assertEquals(expResult, result.substring(0, expResult.length())); + } + + /** + * Test of doOCR method, of class Tesseract. + * + * @throws java.lang.Exception + */ + @Test + public void testDoOCR_UNLV_Zone_File() throws Exception { + logger.info("doOCR on a PNG image with UNLV zone file .uzn"); + //UNLV zone format: left top width height label + String filename = String.format("%s/%s", this.testResourcesDataPath, "eurotext_unlv.png"); + File imageFile = new File(filename); + String expResult = "& duck/goose, as 12.5% of E-mail\n\n" + + "from aspammer@website.com is spam.\n\n" + + "The (quick) [brown] {fox} jumps!\n" + + "Over the $43,456.78 #90 dog"; + String result = instance.doOCR(imageFile); + logger.info(result); + assertEquals(expResult, result.trim().replace('—', '-')); + } + + /** + * Test of doOCR method, of class Tesseract. + * + * @throws java.lang.Exception + */ + @Test + public void testDoOCR_File_With_Configs() throws Exception { + logger.info("doOCR with configs"); + File imageFile = new File(this.testResourcesDataPath, "eurotext.png"); + String expResult = "[-0123456789.\n ]+"; + List configs = Arrays.asList("digits"); + instance.setConfigs(configs); + String result = instance.doOCR(imageFile); + logger.info(result); + assertTrue(result.matches(expResult)); + instance.setConfigs(null); // since Tesseract instance is a singleton, clear configs so the effects do not carry on into subsequent runs. + } + + /** + * Test of doOCR method, of class Tesseract. + * + * @throws Exception while processing image. + */ + @Test + public void testDoOCR_File_Rectangle() throws Exception { + logger.info("doOCR on a BMP image with bounding rectangle"); + File imageFile = new File(this.testResourcesDataPath, "eurotext.bmp"); + Rectangle rect = new Rectangle(0, 0, 1024, 800); // define an equal or smaller region of interest on the image + String expResult = "The (quick) [brown] {fox} jumps!\nOver the $43,456.78 #90 dog"; + String result = instance.doOCR(imageFile, rect); + logger.info(result); + assertEquals(expResult, result.substring(0, expResult.length())); + } + + /** + * Test of doOCR method, of class Tesseract. + * + * @throws Exception while processing image. + */ + @Test + public void testDoOCR_PDF() throws Exception { + logger.info("doOCR on a PDF document"); + File inputFile = new File(this.testResourcesDataPath, "eurotext.pdf"); + String expResult = "The (quick) [brown] {fox} jumps!\nOver the $43,456.78 #90 dog"; + try { + String result = instance.doOCR(inputFile, null); + logger.info(result); + assertEquals(expResult, result.substring(0, expResult.length())); + } catch (TesseractException e) { + logger.error("Exception-Message: '{}'. Imagefile: '{}'", e.getMessage(), inputFile.getAbsoluteFile(), e); + fail(); + } + } + + /** + * Test of doOCR method, of class Tesseract. + * + * @throws Exception while processing image. + */ + @Test + public void testDoOCR_BufferedImage() throws Exception { + logger.info("doOCR on a buffered image of a PNG"); + File imageFile = new File(this.testResourcesDataPath, "eurotext.png"); + BufferedImage bi = ImageIO.read(imageFile); + String expResult = "The (quick) [brown] {fox} jumps!\nOver the $43,456.78 #90 dog"; + + Map types = new HashMap<>(); + types.put("TYPE_INT_RGB", BufferedImage.TYPE_INT_RGB); + types.put("TYPE_INT_ARGB", BufferedImage.TYPE_INT_ARGB); + types.put("TYPE_INT_ARGB_PRE", BufferedImage.TYPE_INT_ARGB_PRE); + types.put("TYPE_INT_BGR", BufferedImage.TYPE_INT_BGR); + types.put("TYPE_3BYTE_BGR", BufferedImage.TYPE_3BYTE_BGR); + types.put("TYPE_4BYTE_ABGR", BufferedImage.TYPE_4BYTE_ABGR); + types.put("TYPE_4BYTE_ABGR_PRE", BufferedImage.TYPE_4BYTE_ABGR_PRE); + types.put("TYPE_USHORT_565_RGB", BufferedImage.TYPE_USHORT_565_RGB); + types.put("TYPE_USHORT_555_RGB", BufferedImage.TYPE_USHORT_555_RGB); + types.put("TYPE_BYTE_GRAY", BufferedImage.TYPE_BYTE_GRAY); + types.put("TYPE_USHORT_GRAY", BufferedImage.TYPE_USHORT_GRAY); + types.put("TYPE_BYTE_BINARY", BufferedImage.TYPE_BYTE_BINARY); + types.put("TYPE_BYTE_INDEXED", BufferedImage.TYPE_BYTE_INDEXED); + + for (Map.Entry entry : types.entrySet()) { + if (entry.getValue() == bi.getType()) { + String result = instance.doOCR(bi); + logger.info("BufferedImage type: " + entry.getKey() + " (Original)"); + logger.info(result); + logger.info(""); + assertEquals(expResult, result.substring(0, expResult.length())); + } else { + BufferedImage imageWithType = new BufferedImage(bi.getWidth(), bi.getHeight(), entry.getValue()); + Graphics2D g = imageWithType.createGraphics(); + g.drawImage(bi, 0, 0, null); + g.dispose(); + + String result = instance.doOCR(imageWithType); + logger.info("BufferedImage type: " + entry.getKey()); + logger.info(result); + logger.info(""); + assertEquals(expResult, result.substring(0, expResult.length())); + } + } + } + + /** + * Test of deskew algorithm. + * + * @throws Exception while processing image. + */ + @Test + public void testDoOCR_SkewedImage() throws Exception { + logger.info("doOCR on a skewed PNG image"); + File imageFile = new File(this.testResourcesDataPath, "eurotext_deskew.png"); + BufferedImage bi = ImageIO.read(imageFile); + ImageDeskew id = new ImageDeskew(bi); + double imageSkewAngle = id.getSkewAngle(); // determine skew angle + if ((imageSkewAngle > MINIMUM_DESKEW_THRESHOLD || imageSkewAngle < -(MINIMUM_DESKEW_THRESHOLD))) { + bi = ImageHelper.rotateImage(bi, -imageSkewAngle); // deskew image + } + + String expResult = "The (quick) [brown] {fox} jumps!\nOver the $43,456.78 #90 dog"; + String result = instance.doOCR(bi); + logger.info(result); + assertEquals(expResult, result.substring(0, expResult.length())); + } + + /** + * Test of createDocuments method, of class Tesseract. + * + * @throws java.lang.Exception + */ + @Test + public void testCreateDocuments() throws Exception { + logger.info("createDocuments for multiple images"); + File imageFile1 = new File(this.testResourcesDataPath, "eurotext.pdf"); + File imageFile2 = new File(this.testResourcesDataPath, "eurotext.png"); + String outputbase1 = "target/test-classes/test-results/docrenderer-1"; + String outputbase2 = "target/test-classes/test-results/docrenderer-2"; + List formats = new ArrayList(Arrays.asList(RenderedFormat.HOCR, RenderedFormat.PDF, RenderedFormat.TEXT)); + instance.createDocuments(new String[]{imageFile1.getPath(), imageFile2.getPath()}, new String[]{outputbase1, outputbase2}, formats); + assertTrue(new File(outputbase1 + ".pdf").exists()); + } + + /** + * Test of getWords method, of class Tesseract. + * + * @throws java.lang.Exception + */ + @Test + public void testGetWords() throws Exception { + logger.info("getWords"); + File imageFile = new File(this.testResourcesDataPath, "eurotext.tif"); + + String expResult = "The (quick) [brown] {fox} jumps!\nOver the $43,456.78 #90 dog"; + String[] expResults = expResult.split("\\s"); + + int pageIteratorLevel = TessPageIteratorLevel.RIL_WORD; + logger.info("PageIteratorLevel: " + Utils.getConstantName(pageIteratorLevel, TessPageIteratorLevel.class)); + BufferedImage bi = ImageIO.read(imageFile); + List result = instance.getWords(bi, pageIteratorLevel); + + //print the complete results + for (Word word : result) { + logger.info(word.toString()); + } + + List text = new ArrayList(); + for (Word word : result.subList(0, expResults.length)) { + text.add(word.getText().trim()); + } + + assertArrayEquals(expResults, text.toArray()); + } + + /** + * Test of getSegmentedRegions method, of class Tesseract. + * + * @throws java.lang.Exception + */ + @Test + public void testGetSegmentedRegions() throws Exception { + logger.info("getSegmentedRegions at given TessPageIteratorLevel"); + File imageFile = new File(testResourcesDataPath, "eurotext.png"); + BufferedImage bi = ImageIO.read(imageFile); + int level = TessPageIteratorLevel.RIL_SYMBOL; + logger.info("PageIteratorLevel: " + Utils.getConstantName(level, TessPageIteratorLevel.class)); + List result = instance.getSegmentedRegions(bi, level); + for (int i = 0; i < result.size(); i++) { + Rectangle rect = result.get(i); + logger.info(String.format("Box[%d]: x=%d, y=%d, w=%d, h=%d", i, rect.x, rect.y, rect.width, rect.height)); + } + + assertTrue(result.size() > 0); + } + + /** + * Test of createDocumentsWithResults method, of class Tesseract. + * + * @throws java.lang.Exception + */ + @Test + public void testCreateDocumentsWithResults() throws Exception { + logger.info("createDocumentsWithResults for multiple images at given TessPageIteratorLevel"); + File imageFile1 = new File(this.testResourcesDataPath, "eurotext.pdf"); + File imageFile2 = new File(this.testResourcesDataPath, "eurotext.png"); + String outputbase1 = "target/test-classes/test-results/docrenderer-3"; + String outputbase2 = "target/test-classes/test-results/docrenderer-4"; + List formats = new ArrayList(Arrays.asList(RenderedFormat.HOCR, RenderedFormat.PDF, RenderedFormat.TEXT)); + List results = instance.createDocumentsWithResults(new String[]{imageFile1.getPath(), imageFile2.getPath()}, new String[]{outputbase1, outputbase2}, formats, TessPageIteratorLevel.RIL_WORD); + assertTrue(new File(outputbase1 + ".pdf").exists()); + assertEquals(2, results.size()); + assertTrue(results.get(0).getConfidence() > 0); + assertEquals(66, results.get(0).getWords().size()); + } + + /** + * Test of createDocumentsWithResults method, of class Tesseract. + * + * @throws java.lang.Exception + */ + @Test + public void testCreateDocumentsWithResults1() throws Exception { + logger.info("createDocumentsWithResults for a buffered image at given TessPageIteratorLevel"); + File imageFile = new File(this.testResourcesDataPath, "eurotext.tif"); + BufferedImage bi = ImageIO.read(imageFile); + String outputbase = "target/test-classes/test-results/docrenderer-5"; + List formats = new ArrayList(Arrays.asList(RenderedFormat.HOCR, RenderedFormat.PDF, RenderedFormat.TEXT)); + OCRResult result = instance.createDocumentsWithResults(bi, imageFile.getName(), outputbase, formats, TessPageIteratorLevel.RIL_WORD); + assertTrue(new File(outputbase + ".pdf").exists()); + assertTrue(result.getConfidence() > 0); + assertEquals(66, result.getWords().size()); + } +} diff --git a/d4dj/src/test/java/net/sourceforge/tess4j/TestFolderExtraction.java b/d4dj/src/test/java/net/sourceforge/tess4j/TestFolderExtraction.java new file mode 100644 index 0000000..7e20851 --- /dev/null +++ b/d4dj/src/test/java/net/sourceforge/tess4j/TestFolderExtraction.java @@ -0,0 +1,79 @@ +/** + * Copyright @ 2008 Quan Nguyen + * + * Licensed under the Apache License, Version 2.0 (the "License"); you may not + * use this file except in compliance with the License. You may obtain a copy of + * the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, WITHOUT + * WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the + * License for the specific language governing permissions and limitations under + * the License. + */ + +package net.sourceforge.tess4j; + +import static org.junit.Assert.assertTrue; + +import java.io.File; +import java.net.URISyntaxException; +import java.net.URL; + +import net.sourceforge.tess4j.util.LoadLibs; +import net.sourceforge.tess4j.util.LoggHelper; + +import org.junit.Test; +import org.slf4j.Logger; +import org.slf4j.LoggerFactory; + +public class TestFolderExtraction { + + private static final Logger logger = LoggerFactory.getLogger(new LoggHelper().toString()); + + @Test + public void testFolderExtraction() { + File tessDataFolder = null; + + try { + /** + * Loads the image from resources. + */ + String filename = String.format("%s/%s", "/test-data", "eurotext.pdf"); + URL defaultImage = getClass().getResource(filename); + File imageFile = new File(defaultImage.toURI()); + + /** + * Extracts tessdata folder into a temp folder. + */ + logger.info("Loading the tessdata folder into a temporary folder."); + tessDataFolder = LoadLibs.extractTessResources("tessdata"); + + /** + * Gets tesseract instance and sets data path. + */ + ITesseract instance = new Tesseract(); + + if (tessDataFolder != null) { + logger.info(tessDataFolder.getAbsolutePath()); + instance.setDatapath(tessDataFolder.getPath()); + } + + /** + * Performs OCR on the image. + */ + String result = instance.doOCR(imageFile); + logger.info(result); + } catch (TesseractException e) { + logger.error(e.getMessage()); + logger.error(e.getMessage(), e); + } catch (URISyntaxException e) { + logger.error(e.getMessage(), e); + } + + // checks if tessdata folder exists + assertTrue(tessDataFolder != null && tessDataFolder.exists()); + } +} diff --git a/d4dj/src/test/java/net/sourceforge/tess4j/util/ImageIOHelperTest.java b/d4dj/src/test/java/net/sourceforge/tess4j/util/ImageIOHelperTest.java new file mode 100644 index 0000000..a2f310e --- /dev/null +++ b/d4dj/src/test/java/net/sourceforge/tess4j/util/ImageIOHelperTest.java @@ -0,0 +1,195 @@ +/* + * Copyright @ 2008 Quan Nguyen + * + * Licensed under the Apache License, Version 2.0 (the "License"); + * you may not use this file except in compliance with the License. + * You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ +package net.sourceforge.tess4j.util; + +import com.recognition.software.jdeskew.ImageDeskew; +import java.awt.image.BufferedImage; +import java.io.File; +import java.io.IOException; +import java.util.List; +import java.util.Map; +import javax.imageio.IIOImage; +import javax.imageio.ImageIO; +import org.junit.After; +import org.junit.AfterClass; +import org.junit.Before; +import org.junit.BeforeClass; +import org.junit.Test; +import static org.junit.Assert.*; +import org.slf4j.Logger; +import org.slf4j.LoggerFactory; + +public class ImageIOHelperTest { + + private static final Logger logger = LoggerFactory.getLogger(new LoggHelper().toString()); + private static final String TEST_RESOURCES_DATA_PATH = "src/test/resources/test-data/"; + private static final String TEST_RESOURCES_RESULTS_PATH = "src/test/resources/test-results/"; + private static final double MINIMUM_DESKEW_THRESHOLD = 0.05d; + + public ImageIOHelperTest() { + } + + @BeforeClass + public static void setUpClass() { + } + + @AfterClass + public static void tearDownClass() { + } + + @Before + public void setUp() { + } + + @After + public void tearDown() { + } + + /** + * Test of createTiffFiles method, of class ImageIOHelper. + * @throws java.lang.Exception + */ + @Test + public void testCreateTiffFiles_File_int() throws Exception { + logger.info("createTiffFiles"); + File imageFile = new File(TEST_RESOURCES_DATA_PATH, "eurotext.png"); + int index = 0; + int expResult = 1; + List result = ImageIOHelper.createTiffFiles(imageFile, index); + assertEquals(expResult, result.size()); + + // cleanup + for (File f : result) { + f.delete(); + } + } + + /** + * Test of getImageFileFormat method, of class ImageIOHelper. + */ + @Test + public void testGetImageFileFormat() { + logger.info("getImageFileFormat"); + File imageFile = new File(TEST_RESOURCES_DATA_PATH, "eurotext.png"); + String expResult = "png"; + String result = ImageIOHelper.getImageFileFormat(imageFile); + assertEquals(expResult, result); + } + + /** + * Test of getImageFile method, of class ImageIOHelper. + * @throws java.lang.Exception + */ + @Test + public void testGetImageFile() throws Exception { + logger.info("getImageFile"); + File inputFile = new File(TEST_RESOURCES_DATA_PATH, "eurotext.png"); + File expResult = new File(TEST_RESOURCES_DATA_PATH, "eurotext.png"); + File result = ImageIOHelper.getImageFile(inputFile); + assertEquals(expResult, result); + } + + /** + * Test of getImageList method, of class ImageIOHelper. + * @throws java.lang.Exception + */ + @Test + public void testGetImageList() throws Exception { + logger.info("getImageList"); + File imageFile = new File(TEST_RESOURCES_DATA_PATH, "eurotext.pdf"); + int expResult = 1; + List result = ImageIOHelper.getImageList(imageFile); + assertEquals(expResult, result.size()); + } + + /** + * Test of getIIOImageList method, of class ImageIOHelper. + * @throws java.lang.Exception + */ + @Test + public void testGetIIOImageList_File() throws Exception { + logger.info("getIIOImageList"); + File imageFile = new File(TEST_RESOURCES_DATA_PATH, "eurotext.pdf"); + int expResult = 1; + List result = ImageIOHelper.getIIOImageList(imageFile); + assertEquals(expResult, result.size()); + } + + /** + * Test of getIIOImageList method, of class ImageIOHelper. + * @throws java.lang.Exception + */ + @Test + public void testGetIIOImageList_BufferedImage() throws Exception { + logger.info("getIIOImageList"); + File imageFile = new File(TEST_RESOURCES_DATA_PATH, "eurotext.png"); + BufferedImage bi = ImageIO.read(imageFile); + int expResult = 1; + List result = ImageIOHelper.getIIOImageList(bi); + assertEquals(expResult, result.size()); + } + + /** + * Test of mergeTiff method, of class ImageIOHelper. + * @throws java.lang.Exception + */ + @Test + public void testMergeTiff_FileArr_File() throws Exception { + logger.info("mergeTiff"); + File imageFile1 = new File(TEST_RESOURCES_DATA_PATH, "eurotext.png"); // filesize: 14,854 bytes + File imageFile2 = new File(TEST_RESOURCES_DATA_PATH, "eurotext_deskew.png"); // filesize: 204,383 bytes + File[] inputImages = {imageFile1, imageFile2}; + File outputTiff = new File(TEST_RESOURCES_RESULTS_PATH, "mergedTiff.tif"); + long expResult = 224337L; // filesize: 224,337 bytes + ImageIOHelper.mergeTiff(inputImages, outputTiff); + assertEquals(expResult, outputTiff.length()); + } + + /** + * Test of deskewImage method, of class ImageIOHelper. + * @throws java.lang.Exception + */ + @Test + public void testDeskewImage() throws Exception { + logger.info("deskewImage"); + File imageFile = new File(TEST_RESOURCES_DATA_PATH, "eurotext_deskew.png"); + double minimumDeskewThreshold = MINIMUM_DESKEW_THRESHOLD; + double initAngle = new ImageDeskew(ImageIO.read(imageFile)).getSkewAngle(); + File result = ImageIOHelper.deskewImage(imageFile, minimumDeskewThreshold); + double resultAngle = new ImageDeskew(ImageIO.read(result)).getSkewAngle(); + assertTrue(Math.abs(resultAngle) < Math.abs(initAngle)); + // cleanup + result.delete(); + } + + /** + * Test of readImageData method, of class ImageIOHelper. + * @throws java.io.IOException + */ + @Test + public void testReadImageData() throws IOException { + logger.info("readImageData"); + File imageFile = new File(TEST_RESOURCES_DATA_PATH, "eurotext.png"); + List oimages = ImageIOHelper.getIIOImageList(imageFile); + IIOImage oimage = oimages.get(0); + int expResultDpiX = 300; + int expResultDpiY = 300; + Map result = ImageIOHelper.readImageData(oimage); + assertEquals(String.valueOf(expResultDpiX), result.get("dpiX")); + assertEquals(String.valueOf(expResultDpiY), result.get("dpiY")); + } + +} diff --git a/d4dj/src/test/java/net/sourceforge/tess4j/util/PdfUtilitiesTest.java b/d4dj/src/test/java/net/sourceforge/tess4j/util/PdfUtilitiesTest.java new file mode 100644 index 0000000..f731d08 --- /dev/null +++ b/d4dj/src/test/java/net/sourceforge/tess4j/util/PdfUtilitiesTest.java @@ -0,0 +1,117 @@ +/* + * Copyright 2014 Quan Nguyen. + * + * Licensed under the Apache License, Version 2.0 (the "License"); + * you may not use this file except in compliance with the License. + * You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ +package net.sourceforge.tess4j.util; + +import org.junit.Test; +import org.slf4j.Logger; +import org.slf4j.LoggerFactory; + +import java.io.File; +import java.io.IOException; + +import static org.junit.Assert.assertEquals; +import static org.junit.Assert.assertTrue; +import org.junit.Before; + +public class PdfUtilitiesTest { + + private static final Logger logger = LoggerFactory.getLogger(new LoggHelper().toString()); + private static final String TEST_RESOURCES_DATA_PATH = "src/test/resources/test-data/"; + private static final String TEST_RESOURCES_RESULTS_PATH = "src/test/resources/test-results/"; + + @Before + public void setUp() { + System.setProperty(PdfUtilities.PDF_LIBRARY, PdfUtilities.PDFBOX); // Note: comment out to test Ghostscript + } + + /** + * Test of convertPdf2Tiff method, of class PdfUtilities. + * + * @throws java.lang.Exception + */ + @Test + public void testConvertPdf2Tiff() throws Exception { + logger.info("convertPdf2Tiff"); + File inputPdfFile = new File(TEST_RESOURCES_DATA_PATH, "eurotext.pdf"); + File result = PdfUtilities.convertPdf2Tiff(inputPdfFile); + result.deleteOnExit(); + assertTrue(result.exists()); + } + + /** + * Test of convertPdf2Png method, of class PdfUtilities. + * + * @throws java.io.IOException + */ + @Test + public void testConvertPdf2Png() throws IOException { + logger.info("convertPdf2Png"); + File inputPdfFile = new File(TEST_RESOURCES_DATA_PATH, "eurotext.pdf"); + File[] results = PdfUtilities.convertPdf2Png(inputPdfFile); + assertTrue(results.length > 0); + + //clean up + File parentDir = results[0].getParentFile(); + for (File result : results) { + result.delete(); + } + parentDir.delete(); + } + + /** + * Test of splitPdf method, of class PdfUtilities. + */ + @Test + public void testSplitPdf() { + logger.info("splitPdf"); + File inputPdfFile = new File(String.format("%s/%s", TEST_RESOURCES_DATA_PATH, "multipage-pdf.pdf")); + File outputPdfFile = new File(String.format("%s/%s", TEST_RESOURCES_RESULTS_PATH, "multipage-pdf_splitted.pdf")); + int startPage = 2; + int endPage = 3; + int expResult = 2; + PdfUtilities.splitPdf(inputPdfFile, outputPdfFile, startPage, endPage); + int pageCount = PdfUtilities.getPdfPageCount(outputPdfFile); + assertEquals(expResult, pageCount); + } + + /** + * Test of getPdfPageCount method, of class PdfUtilities. + */ + @Test + public void testGetPdfPageCount() { + logger.info("getPdfPageCount"); + File inputPdfFile = new File(TEST_RESOURCES_DATA_PATH, "multipage-pdf.pdf"); + int expResult = 5; + int result = PdfUtilities.getPdfPageCount(inputPdfFile); + assertEquals(expResult, result); + } + + /** + * Test of mergePdf method, of class PdfUtilities. + */ + @Test + public void testMergePdf() { + logger.info("mergePdf"); + File pdfPartOne = new File(String.format("%s/%s", TEST_RESOURCES_DATA_PATH, "eurotext.pdf")); + File pdfPartTwo = new File(String.format("%s/%s", TEST_RESOURCES_DATA_PATH, "multipage-pdf.pdf")); + int expResult = 6; + File outputPdfFile = new File(String.format("%s/%s", TEST_RESOURCES_RESULTS_PATH, "multipage-pdf_merged.pdf")); + File[] inputPdfFiles = {pdfPartOne, pdfPartTwo}; + PdfUtilities.mergePdf(inputPdfFiles, outputPdfFile); + assertEquals(expResult, PdfUtilities.getPdfPageCount(outputPdfFile)); + } + +} diff --git a/d4dj/src/test/resources/log4j.properties b/d4dj/src/test/resources/log4j.properties new file mode 100644 index 0000000..5fe42d8 --- /dev/null +++ b/d4dj/src/test/resources/log4j.properties @@ -0,0 +1,9 @@ +# Set root logger level to DEBUG and its only appender to A1. +log4j.rootLogger=DEBUG, A1 + +# A1 is set to be a ConsoleAppender. +log4j.appender.A1=org.apache.log4j.ConsoleAppender + +# A1 uses PatternLayout. +log4j.appender.A1.layout=org.apache.log4j.PatternLayout +log4j.appender.A1.layout.ConversionPattern=%-4r [%t] %-5p %c %x - %m%n diff --git a/d4dj/src/test/resources/logback-test.xml b/d4dj/src/test/resources/logback-test.xml new file mode 100644 index 0000000..f0c557f --- /dev/null +++ b/d4dj/src/test/resources/logback-test.xml @@ -0,0 +1,15 @@ + + + + + + %d{HH:mm:ss.SSS} [%thread] %-5level %logger{36} - %msg%n + + + + + + + + + diff --git a/d4dj/src/test/resources/test-data/eurotext.bmp b/d4dj/src/test/resources/test-data/eurotext.bmp new file mode 100644 index 0000000..be05080 Binary files /dev/null and b/d4dj/src/test/resources/test-data/eurotext.bmp differ diff --git a/d4dj/src/test/resources/test-data/eurotext.pdf b/d4dj/src/test/resources/test-data/eurotext.pdf new file mode 100644 index 0000000..eac4388 Binary files /dev/null and b/d4dj/src/test/resources/test-data/eurotext.pdf differ diff --git a/d4dj/src/test/resources/test-data/eurotext.png b/d4dj/src/test/resources/test-data/eurotext.png new file mode 100644 index 0000000..e5c324e Binary files /dev/null and b/d4dj/src/test/resources/test-data/eurotext.png differ diff --git a/d4dj/src/test/resources/test-data/eurotext.tif b/d4dj/src/test/resources/test-data/eurotext.tif new file mode 100644 index 0000000..92791da Binary files /dev/null and b/d4dj/src/test/resources/test-data/eurotext.tif differ diff --git a/d4dj/src/test/resources/test-data/eurotext90.png b/d4dj/src/test/resources/test-data/eurotext90.png new file mode 100644 index 0000000..0e1d718 Binary files /dev/null and b/d4dj/src/test/resources/test-data/eurotext90.png differ diff --git a/d4dj/src/test/resources/test-data/eurotext_deskew.png b/d4dj/src/test/resources/test-data/eurotext_deskew.png new file mode 100644 index 0000000..dfa06bd Binary files /dev/null and b/d4dj/src/test/resources/test-data/eurotext_deskew.png differ diff --git a/d4dj/src/test/resources/test-data/eurotext_unlv.png b/d4dj/src/test/resources/test-data/eurotext_unlv.png new file mode 100644 index 0000000..e5c324e Binary files /dev/null and b/d4dj/src/test/resources/test-data/eurotext_unlv.png differ diff --git a/d4dj/src/test/resources/test-data/eurotext_unlv.uzn b/d4dj/src/test/resources/test-data/eurotext_unlv.uzn new file mode 100644 index 0000000..878c8de --- /dev/null +++ b/d4dj/src/test/resources/test-data/eurotext_unlv.uzn @@ -0,0 +1,3 @@ +97 162 747 50 ThirdLine +97 209 828 55 FourthLine +92 56 810 107 First2Lines \ No newline at end of file diff --git a/d4dj/src/test/resources/test-data/multipage-pdf.pdf b/d4dj/src/test/resources/test-data/multipage-pdf.pdf new file mode 100644 index 0000000..fa1eade Binary files /dev/null and b/d4dj/src/test/resources/test-data/multipage-pdf.pdf differ diff --git a/d4dj/src/test/resources/test-results/.gitignore b/d4dj/src/test/resources/test-results/.gitignore new file mode 100644 index 0000000..86d0cb2 --- /dev/null +++ b/d4dj/src/test/resources/test-results/.gitignore @@ -0,0 +1,4 @@ +# Ignore everything in this directory +* +# Except this file +!.gitignore \ No newline at end of file diff --git a/d4dj/target/classes/com/recognition/software/jdeskew/ImageDeskew$HoughLine.class b/d4dj/target/classes/com/recognition/software/jdeskew/ImageDeskew$HoughLine.class new file mode 100644 index 0000000..1d2c5d7 Binary files /dev/null and b/d4dj/target/classes/com/recognition/software/jdeskew/ImageDeskew$HoughLine.class differ diff --git a/d4dj/target/classes/com/recognition/software/jdeskew/ImageDeskew.class b/d4dj/target/classes/com/recognition/software/jdeskew/ImageDeskew.class new file mode 100644 index 0000000..58ba997 Binary files /dev/null and b/d4dj/target/classes/com/recognition/software/jdeskew/ImageDeskew.class differ diff --git a/d4dj/target/classes/com/recognition/software/jdeskew/ImageUtil.class b/d4dj/target/classes/com/recognition/software/jdeskew/ImageUtil.class new file mode 100644 index 0000000..7f368a3 Binary files /dev/null and b/d4dj/target/classes/com/recognition/software/jdeskew/ImageUtil.class differ diff --git a/d4dj/target/classes/d4dj/d4dj/App.class b/d4dj/target/classes/d4dj/d4dj/App.class new file mode 100644 index 0000000..cafa0f7 Binary files /dev/null and b/d4dj/target/classes/d4dj/d4dj/App.class differ diff --git a/d4dj/target/classes/d4dj/d4dj/SubmitThread.class b/d4dj/target/classes/d4dj/d4dj/SubmitThread.class new file mode 100644 index 0000000..4ccb13d Binary files /dev/null and b/d4dj/target/classes/d4dj/d4dj/SubmitThread.class differ diff --git a/d4dj/target/classes/org/json/CDL.class b/d4dj/target/classes/org/json/CDL.class new file mode 100644 index 0000000..ae66f90 Binary files /dev/null and b/d4dj/target/classes/org/json/CDL.class differ diff --git a/d4dj/target/classes/org/json/Cookie.class b/d4dj/target/classes/org/json/Cookie.class new file mode 100644 index 0000000..7799866 Binary files /dev/null and b/d4dj/target/classes/org/json/Cookie.class differ diff --git a/d4dj/target/classes/org/json/CookieList.class b/d4dj/target/classes/org/json/CookieList.class new file mode 100644 index 0000000..80c3d23 Binary files /dev/null and b/d4dj/target/classes/org/json/CookieList.class differ diff --git a/d4dj/target/classes/org/json/HTTP.class b/d4dj/target/classes/org/json/HTTP.class new file mode 100644 index 0000000..f30cdca Binary files /dev/null and b/d4dj/target/classes/org/json/HTTP.class differ diff --git a/d4dj/target/classes/org/json/HTTPTokener.class b/d4dj/target/classes/org/json/HTTPTokener.class new file mode 100644 index 0000000..f9e5bcd Binary files /dev/null and b/d4dj/target/classes/org/json/HTTPTokener.class differ diff --git a/d4dj/target/classes/org/json/JSONArray.class b/d4dj/target/classes/org/json/JSONArray.class new file mode 100644 index 0000000..582da02 Binary files /dev/null and b/d4dj/target/classes/org/json/JSONArray.class differ diff --git a/d4dj/target/classes/org/json/JSONException.class b/d4dj/target/classes/org/json/JSONException.class new file mode 100644 index 0000000..56f8570 Binary files /dev/null and b/d4dj/target/classes/org/json/JSONException.class differ diff --git a/d4dj/target/classes/org/json/JSONML.class b/d4dj/target/classes/org/json/JSONML.class new file mode 100644 index 0000000..7b0e1b5 Binary files /dev/null and b/d4dj/target/classes/org/json/JSONML.class differ diff --git a/d4dj/target/classes/org/json/JSONObject$Null.class b/d4dj/target/classes/org/json/JSONObject$Null.class new file mode 100644 index 0000000..d424879 Binary files /dev/null and b/d4dj/target/classes/org/json/JSONObject$Null.class differ diff --git a/d4dj/target/classes/org/json/JSONObject.class b/d4dj/target/classes/org/json/JSONObject.class new file mode 100644 index 0000000..cccd217 Binary files /dev/null and b/d4dj/target/classes/org/json/JSONObject.class differ diff --git a/d4dj/target/classes/org/json/JSONPointer$Builder.class b/d4dj/target/classes/org/json/JSONPointer$Builder.class new file mode 100644 index 0000000..f9b727f Binary files /dev/null and b/d4dj/target/classes/org/json/JSONPointer$Builder.class differ diff --git a/d4dj/target/classes/org/json/JSONPointer.class b/d4dj/target/classes/org/json/JSONPointer.class new file mode 100644 index 0000000..ac03153 Binary files /dev/null and b/d4dj/target/classes/org/json/JSONPointer.class differ diff --git a/d4dj/target/classes/org/json/JSONPointerException.class b/d4dj/target/classes/org/json/JSONPointerException.class new file mode 100644 index 0000000..d1f812a Binary files /dev/null and b/d4dj/target/classes/org/json/JSONPointerException.class differ diff --git a/d4dj/target/classes/org/json/JSONString.class b/d4dj/target/classes/org/json/JSONString.class new file mode 100644 index 0000000..f891964 Binary files /dev/null and b/d4dj/target/classes/org/json/JSONString.class differ diff --git a/d4dj/target/classes/org/json/JSONStringer.class b/d4dj/target/classes/org/json/JSONStringer.class new file mode 100644 index 0000000..2e8c293 Binary files /dev/null and b/d4dj/target/classes/org/json/JSONStringer.class differ diff --git a/d4dj/target/classes/org/json/JSONTokener.class b/d4dj/target/classes/org/json/JSONTokener.class new file mode 100644 index 0000000..c06c2b1 Binary files /dev/null and b/d4dj/target/classes/org/json/JSONTokener.class differ diff --git a/d4dj/target/classes/org/json/JSONWriter.class b/d4dj/target/classes/org/json/JSONWriter.class new file mode 100644 index 0000000..c288399 Binary files /dev/null and b/d4dj/target/classes/org/json/JSONWriter.class differ diff --git a/d4dj/target/classes/org/json/Property.class b/d4dj/target/classes/org/json/Property.class new file mode 100644 index 0000000..2202081 Binary files /dev/null and b/d4dj/target/classes/org/json/Property.class differ diff --git a/d4dj/target/classes/org/json/XML$1$1.class b/d4dj/target/classes/org/json/XML$1$1.class new file mode 100644 index 0000000..7971cab Binary files /dev/null and b/d4dj/target/classes/org/json/XML$1$1.class differ diff --git a/d4dj/target/classes/org/json/XML$1.class b/d4dj/target/classes/org/json/XML$1.class new file mode 100644 index 0000000..b1397d0 Binary files /dev/null and b/d4dj/target/classes/org/json/XML$1.class differ diff --git a/d4dj/target/classes/org/json/XML.class b/d4dj/target/classes/org/json/XML.class new file mode 100644 index 0000000..b194106 Binary files /dev/null and b/d4dj/target/classes/org/json/XML.class differ diff --git a/d4dj/target/classes/org/json/XMLTokener.class b/d4dj/target/classes/org/json/XMLTokener.class new file mode 100644 index 0000000..7bb49ad Binary files /dev/null and b/d4dj/target/classes/org/json/XMLTokener.class differ diff --git a/d4dj/target/classes/readme.html b/d4dj/target/classes/readme.html new file mode 100644 index 0000000..8b27db3 --- /dev/null +++ b/d4dj/target/classes/readme.html @@ -0,0 +1,124 @@ + + + + Tess4J - Java Wrapper for Tesseract OCR API + + +
+

+ Tess4J +

+

+ DESCRIPTION +

+

+ Tess4J is a JNA wrapper for Tesseract OCR + API; it provides character recognition support for common image formats, + multi-page images, and PDF documents. The library has been developed and tested + on Windows and Linux. +

+

+ Tess4J is released and distributed under the + Apache License, v2.0. Its official homepage is at + http://tess4j.sourceforge.net. +

+

+ SOFTWARE REQUIREMENTS +

+

+ Java Runtime Environment, + JNA, and JAI-ImageIO + are required. Apache Maven and + JUnit are used for program building and unit testing. The Tesseract DLLs + were built with VS2019 (v142) and therefore depend on the + Visual C++ 2019 Redistributable Packages. +

+

+ INSTRUCTIONS +

+

+ Tesseract 5.0.0 and Leptonica 1.79 (via Lept4J) 32- and 64-bit + DLLs, language data for English, and sample images are bundled with the library. + Language data packs for + Tesseract should be decompressed and placed into the tessdata folder. +

+

+ The Linux shared object library (libtesseract.so) equivalent to the + DLL is available in Tesseract 5.0.0, which can be built from the source with the instructions given in Tesseract Wiki. +

+

+ To unit test, at the command line, execute: +

+
+

+ mvn test +

+
+

+ Support for PDF documents is available through either + GPL Ghostscript, which should be installed and included + in system path, or PDFBox, if Ghostscript is not available. +

+

+ Images to be OCRed should be scanned at resolution from at least 200 DPI (dot per + inch) to 400 DPI in monochrome (black&white) or grayscale. Scanning at higher + resolutions will not necessarily result in better recognition accuracy. The actual + success rates depend greatly on the quality of the scanned image. The typical settings + for scanning are 300 DPI and 1 bpp (bit per pixel) black&white or 8 bpp grayscale + uncompressed TIFF or PNG format. PNG is usually smaller in size than other image + formats and still keeps high quality due to its employing lossless data compression + algorithms; TIFF has the advantage of the ability to contain multiple images (pages) + in a file. +

+

+ Several built-in functions are also provided for merging several images or PDF files + into a single one for convenient OCR operations, or for splitting a PDF file into + smaller ones if it is too large, which can cause out-of-memory exceptions. +

+

+ CODE EXAMPLES +

+

+ The following code example shows common usage of the library. Make sure tessdata + folder is populated with appropriate language data files and the .jar + files are in the classpath. On Windows, the DLLs will be automatically extracted + from tess4j.jar to the default temporary directory and loaded. +

+
+ 
+package net.sourceforge.tess4j.example;
+
+import java.io.File;
+import net.sourceforge.tess4j.*;
+
+public class TesseractExample {
+    public static void main(String[] args) {
+        // ImageIO.scanForPlugins(); // for server environment
+        File imageFile = new File("eurotext.tif");
+        ITesseract instance = new Tesseract(); // JNA Interface Mapping
+        // ITesseract instance = new Tesseract1(); // JNA Direct Mapping
+        // File tessDataFolder = LoadLibs.extractTessResources("tessdata"); // Maven build only; only English data bundled
+        // instance.setDatapath(tessDataFolder.getPath());
+
+        try {
+            String result = instance.doOCR(imageFile);
+            System.out.println(result);
+        } catch (TesseractException e) {
+            System.err.println(e.getMessage());
+        }
+    }
+}
+
+
+

+ DOCUMENTATIONS +

+

+ Please visit the website for the library's documentations +

+
+
+ + diff --git a/d4dj/target/classes/sig/utils/Audio.class b/d4dj/target/classes/sig/utils/Audio.class new file mode 100644 index 0000000..a5b86f5 Binary files /dev/null and b/d4dj/target/classes/sig/utils/Audio.class differ diff --git a/d4dj/target/classes/sig/utils/DebugUtils.class b/d4dj/target/classes/sig/utils/DebugUtils.class new file mode 100644 index 0000000..bc8f429 Binary files /dev/null and b/d4dj/target/classes/sig/utils/DebugUtils.class differ diff --git a/d4dj/target/classes/sig/utils/DrawUtils.class b/d4dj/target/classes/sig/utils/DrawUtils.class new file mode 100644 index 0000000..8d2d7be Binary files /dev/null and b/d4dj/target/classes/sig/utils/DrawUtils.class differ diff --git a/d4dj/target/classes/sig/utils/FileUtils.class b/d4dj/target/classes/sig/utils/FileUtils.class new file mode 100644 index 0000000..c750f91 Binary files /dev/null and b/d4dj/target/classes/sig/utils/FileUtils.class differ diff --git a/d4dj/target/classes/sig/utils/GithubUtils.class b/d4dj/target/classes/sig/utils/GithubUtils.class new file mode 100644 index 0000000..e4f6717 Binary files /dev/null and b/d4dj/target/classes/sig/utils/GithubUtils.class differ diff --git a/d4dj/target/classes/sig/utils/ImageUtils.class b/d4dj/target/classes/sig/utils/ImageUtils.class new file mode 100644 index 0000000..1de6ff9 Binary files /dev/null and b/d4dj/target/classes/sig/utils/ImageUtils.class differ diff --git a/d4dj/target/classes/sig/utils/JavaUtils.class b/d4dj/target/classes/sig/utils/JavaUtils.class new file mode 100644 index 0000000..de26b87 Binary files /dev/null and b/d4dj/target/classes/sig/utils/JavaUtils.class differ diff --git a/d4dj/target/classes/sig/utils/ReflectUtils.class b/d4dj/target/classes/sig/utils/ReflectUtils.class new file mode 100644 index 0000000..6507d49 Binary files /dev/null and b/d4dj/target/classes/sig/utils/ReflectUtils.class differ diff --git a/d4dj/target/classes/sig/utils/SoundUtils.class b/d4dj/target/classes/sig/utils/SoundUtils.class new file mode 100644 index 0000000..3f6c921 Binary files /dev/null and b/d4dj/target/classes/sig/utils/SoundUtils.class differ diff --git a/d4dj/target/classes/sig/utils/TextUtils.class b/d4dj/target/classes/sig/utils/TextUtils.class new file mode 100644 index 0000000..cf6898c Binary files /dev/null and b/d4dj/target/classes/sig/utils/TextUtils.class differ diff --git a/d4dj/target/classes/sig/utils/TimeUtils.class b/d4dj/target/classes/sig/utils/TimeUtils.class new file mode 100644 index 0000000..e03ac1f Binary files /dev/null and b/d4dj/target/classes/sig/utils/TimeUtils.class differ diff --git a/d4dj/target/classes/tessdata/configs/alto b/d4dj/target/classes/tessdata/configs/alto new file mode 100644 index 0000000..0dd12a7 --- /dev/null +++ b/d4dj/target/classes/tessdata/configs/alto @@ -0,0 +1 @@ +tessedit_create_alto 1 diff --git a/d4dj/target/classes/tessdata/configs/api_config b/d4dj/target/classes/tessdata/configs/api_config new file mode 100644 index 0000000..5cd6ec0 --- /dev/null +++ b/d4dj/target/classes/tessdata/configs/api_config @@ -0,0 +1 @@ +tessedit_zero_rejection T diff --git a/d4dj/target/classes/tessdata/configs/bazaar b/d4dj/target/classes/tessdata/configs/bazaar new file mode 100644 index 0000000..1b2ee83 --- /dev/null +++ b/d4dj/target/classes/tessdata/configs/bazaar @@ -0,0 +1,4 @@ +load_system_dawg F +load_freq_dawg F +user_words_suffix user-words +user_patterns_suffix user-patterns diff --git a/d4dj/target/classes/tessdata/configs/digits b/d4dj/target/classes/tessdata/configs/digits new file mode 100644 index 0000000..6a329f8 --- /dev/null +++ b/d4dj/target/classes/tessdata/configs/digits @@ -0,0 +1 @@ +tessedit_char_whitelist 0123456789-. diff --git a/d4dj/target/classes/tessdata/configs/hocr b/d4dj/target/classes/tessdata/configs/hocr new file mode 100644 index 0000000..5ab372e --- /dev/null +++ b/d4dj/target/classes/tessdata/configs/hocr @@ -0,0 +1,2 @@ +tessedit_create_hocr 1 +hocr_font_info 0 diff --git a/d4dj/target/classes/tessdata/configs/lstmbox b/d4dj/target/classes/tessdata/configs/lstmbox new file mode 100644 index 0000000..a6f2ced --- /dev/null +++ b/d4dj/target/classes/tessdata/configs/lstmbox @@ -0,0 +1 @@ +tessedit_create_lstmbox 1 diff --git a/d4dj/target/classes/tessdata/configs/pdf b/d4dj/target/classes/tessdata/configs/pdf new file mode 100644 index 0000000..59645d7 --- /dev/null +++ b/d4dj/target/classes/tessdata/configs/pdf @@ -0,0 +1 @@ +tessedit_create_pdf 1 diff --git a/d4dj/target/classes/tessdata/configs/quiet b/d4dj/target/classes/tessdata/configs/quiet new file mode 100644 index 0000000..35b59a9 --- /dev/null +++ b/d4dj/target/classes/tessdata/configs/quiet @@ -0,0 +1 @@ +debug_file /dev/null diff --git a/d4dj/target/classes/tessdata/configs/tsv b/d4dj/target/classes/tessdata/configs/tsv new file mode 100644 index 0000000..dc52478 --- /dev/null +++ b/d4dj/target/classes/tessdata/configs/tsv @@ -0,0 +1 @@ +tessedit_create_tsv 1 diff --git a/d4dj/target/classes/tessdata/configs/txt b/d4dj/target/classes/tessdata/configs/txt new file mode 100644 index 0000000..5046f0b --- /dev/null +++ b/d4dj/target/classes/tessdata/configs/txt @@ -0,0 +1,3 @@ +# This config file should be used with other cofig files which creates renderers. +# usage example: tesseract eurotext.tif eurotext txt hocr pdf +tessedit_create_txt 1 diff --git a/d4dj/target/classes/tessdata/configs/unlv b/d4dj/target/classes/tessdata/configs/unlv new file mode 100644 index 0000000..d2e22f5 --- /dev/null +++ b/d4dj/target/classes/tessdata/configs/unlv @@ -0,0 +1,2 @@ +tessedit_write_unlv 1 +unlv_tilde_crunching T diff --git a/d4dj/target/classes/tessdata/configs/wordstrbox b/d4dj/target/classes/tessdata/configs/wordstrbox new file mode 100644 index 0000000..38cd41c --- /dev/null +++ b/d4dj/target/classes/tessdata/configs/wordstrbox @@ -0,0 +1 @@ +tessedit_create_wordstrbox 1 diff --git a/d4dj/target/classes/tessdata/eng.traineddata b/d4dj/target/classes/tessdata/eng.traineddata new file mode 100644 index 0000000..bbef467 Binary files /dev/null and b/d4dj/target/classes/tessdata/eng.traineddata differ diff --git a/d4dj/target/classes/tessdata/osd.traineddata b/d4dj/target/classes/tessdata/osd.traineddata new file mode 100644 index 0000000..527457c Binary files /dev/null and b/d4dj/target/classes/tessdata/osd.traineddata differ diff --git a/d4dj/target/classes/tessdata/pdf.ttf b/d4dj/target/classes/tessdata/pdf.ttf new file mode 100644 index 0000000..8affa23 Binary files /dev/null and b/d4dj/target/classes/tessdata/pdf.ttf differ diff --git a/d4dj/target/classes/versionchanges.txt b/d4dj/target/classes/versionchanges.txt new file mode 100644 index 0000000..78904ca --- /dev/null +++ b/d4dj/target/classes/versionchanges.txt @@ -0,0 +1,199 @@ +Tess4J Change Summary + +Version 0.1 - initial release (14 Aug 2010): +- Java JNA-based wrapper for Tesseract OCR DLL 2.04 +- Support uncompressed, binary TIFF images + +Version 0.2 (16 Aug 2010): +- Add support for more image formats (PNG, BMP, GIF, PDF, JPEG) +- Add support for compressed, grayscale and colored images + +Version 0.3 (22 Aug 2010): +- Include API support for BufferedImage +- Clean up codes. Remove unsupported API and files +- Document the API + +Version 0.3.1 (26 Aug 2010): +- Send only pixel data, not whole image data, to Tesseract engine, to fix a bug that has erroneously put some words at beginning of line towards end of line + +Version 0.4 (1 Nov 2010): +- Add JNA Direct Mapping calls, which can provide performance near that of custom JNI + +Version 1.0 (30 October 2012): +- Upgrade to Tesseract 3.02 (r798), which is not backward compatible with Tesseract 2.04. +- Implement a new JNA wrapper for the new Tesseract OCR API +- Add more unit test cases +- Update documentation + +Version 1.1 (3 March 2013) +- Update Tesseract DLL to r828 +- Additional API methods, image helper methods, and unit test cases +- Improve handling of Unicode character encoding +- Fix memory leaks +- Add support for determining skew angle and image rotation + +Version 1.2 (22 September 2013) +- Update Tesseract DLL to r866 +- More efficient OCR of multiple images +- Various minor improvements +- Update JNA to v4.0 + +Version 1.3 (31 May 2014) +- Update JNA to v4.1.0 +- Update Ghost4J to v0.5.1 +- Refactoring +- Bundle Tesseract and Leptonica 64-bit DLLs + +Version 1.4 (18 January 2015) +- Refactor to reduce code duplication +- Embed Windows native resources in JAR +- Autoload Windows native libraries + +Version 1.4.1 (24 January 2015) +- Enable use of jna.library.path system property for user-customizable path + +Version 1.5 (13 March 2015) +- Add UNLV zone file support +- Refactor + +Version 2.0 (29 March 2015) +- Upgrade to Tesseract 3.03 (r1050), which is compatible with Tesseract 3.03RC on Linux +- Refactor Tesseract class for extensibility and thread-safety +- Update English language data for Tesseract 3.02 + +Version 3.0 (25 December 2015) +- Upgrade to Tesseract 3.04 (953523b) +- Include Lept4J library +- Incorporate slf4j and logback libraries for logging +- Make GhostScript calls thread safe + +Version 3.1 (21 March 2016) +- Update Tesseract to 3.04.01 (4ef68a0) +- Use Lept4J-1.1.2 (Leptonica 1.72) +- Update JNA to 4.2.2 +- Update Ghost4J to 1.0.1 +- Delete ResultRenderer after use to release PDF file handler + +Version 3.2 (15 May 2016) +- Revert JNA to 4.1.0 due to "Invalid calling convention 63" errors invoking GhostScript via Ghost4J on Linux +- Update Lept4J to 1.2.2 (Leptonica 1.73) +- Recompile Tesseract 3.04.01 DLL against Leptonica 1.73 +- Update GhostScript Windows binary to 9.19 + +Version 3.2.1 (29 May 2016) +- Properly release Box and Boxa resources +- Update Lept4J to 1.2.3 + +Version 3.2.2 (16 February 2017) +- Update GhostScript to 9.20 +- Fix possible NPE with PDF-related codes +- Update dependencies +- Additional image utility methods + +Version 3.3.0 (16 February 2017) +- Upgrade to Tesseract 3.05 (2ca5d0a) +- Update Lept4J to 1.3.0 (Leptonica 1.74.1) + +Version 3.3.1 (23 March 2017) +- Update Lept4J to 1.3.1 +- Update other dependencies + +Version 3.4.0 (1 June 2017) +- Upgrade to Tesseract 3.05.01 (2158661) +- Update Lept4J to 1.4.0 +- Add support for jboss-vfs protocol + +Version 3.4.1 (22 September 2017) +- Not extract/copy native resource if it exists and has same file size +- Update Tesseract 3.05.01 (e2e79c4); link against Leptonica 1.74.4 +- Update Lept4J to 1.6.1 + +Version 3.4.2 (14 November 2017) +- Update Lept4J to 1.6.2 +- Update GhostScript to 9.22 +- Improve handling of PDF files in multi-threaded environment +- Lift limits on number of pages in PDF +- Use TESSDATA_PREFIX environment variable by default, if defined + +Version 3.4.3 (14 January 2018) +- Not extract/copy resource if it exists and has same file size + +Version 3.4.4 (22 February 2018) +- Exclude logback.xml from JAR +- Add image rotate and deskew methods +- Update Lept4J to 1.6.3 + +Version 3.4.5 (21 March 2018) +- Remove GS DLL due to license incompatibility +- Use PDFBox + +Version 3.4.6 (25 March 2018) +- Update PDFBox dependencies + +Version 3.4.7 (16 April 2018) +- Update dependencies for Java 9 fixes + +Version 3.4.8 (2 May 2018) +- Fix a path issue when extracting resources from JAR to temp directory on Windows server + +Version 4.0.0 (28 April 2018) +- Upgrade to Tesseract 4.0.0-beta.1 (45bb942) +- Update Lept4J to 1.9.3 (Leptonica 1.75.3) + +Version 4.0.1 (2 May 2018) +- Fix a path issue when extracting resources from JAR to temp directory on Windows server + +Version 4.0.2 (3 May 2018) +- Replace JNA string constant Platform.RESOURCE_PREFIX +- Update jai-imageio url +- Update Lept4J to 1.9.4 + +Version 4.1.0 (20 July 2018) +- Upgrade to Tesseract 4.0.0-beta.3 (b502bbf) +- Update Lept4J to 1.10.0 +- Improve handling of PDF +- Refactor + +Version 4.1.1 (28 July 2018) +- Properly dispose of resources and temporary image files +- Clean up code and test output resources +- Fix NPE in Java 10 + +Version 4.2.0 (11 August 2018) +- Upgrade to Tesseract 4.0.0-beta.4 (fd49206) + +Version 4.2.1 (11 August 2018) +- Recompile using JDK8 to avoid NoSuchMethodError: Method flip() does not exist in class java.nio.ByteBuffer +- Use explicit cast for compatibility with covariant return type on JDK 9's ByteBuffer methods, e.g., flip() + +Version 4.2.2 (3 September 2018) +- Fix Invalid memory access exception due of incorrect bit depth value + +Version 4.2.3 (17 October 2018) +- Update pdfbox dependencies + +Version 4.3.0 (29 October 2018) +- Upgrade to Tesseract 4.0.0 (5131699) + +Version 4.3.1 (26 December 2018) +- Fix Windows build +- Improve RenderedImage to ByteBuffer conversion + +Version 4.4.0 (13 July 2019) +- Upgrade to Tesseract 4.1.0 (5280bbc) +- Upgrade to Leptonica 1.78.0 (lept4j-1.12.2) +- Update dependencies + +Version 4.4.1 (7 October 2019) +- Use tessdata_fast data +- Use Native.loadLibrary method for backward compatibility with older JNA versions + +Version 4.5.0 (27 December 2019) +- Upgrade to Tesseract 4.1.1 (7510304) + +Version 4.5.1 (3 January 2020) +- Update Leptonica 1.79.0 (lept4j-1.13.0) +- Fix Permission denied issue with Ghostscript 9.50 + +Version 5.0.0-SNAPSHOT (11 July 2020) +- Upgrade to Tesseract 5.0.0-alpha (135c8a4) \ No newline at end of file diff --git a/d4dj/target/classes/win32-x86-64/libtesseract500.dll b/d4dj/target/classes/win32-x86-64/libtesseract500.dll new file mode 100644 index 0000000..085a03e Binary files /dev/null and b/d4dj/target/classes/win32-x86-64/libtesseract500.dll differ diff --git a/d4dj/target/classes/win32-x86/libtesseract500.dll b/d4dj/target/classes/win32-x86/libtesseract500.dll new file mode 100644 index 0000000..b472138 Binary files /dev/null and b/d4dj/target/classes/win32-x86/libtesseract500.dll differ diff --git a/d4dj/target/test-classes/d4dj/d4dj/AppTest.class b/d4dj/target/test-classes/d4dj/d4dj/AppTest.class new file mode 100644 index 0000000..762b5aa Binary files /dev/null and b/d4dj/target/test-classes/d4dj/d4dj/AppTest.class differ diff --git a/d4dj/target/test-classes/log4j.properties b/d4dj/target/test-classes/log4j.properties new file mode 100644 index 0000000..5fe42d8 --- /dev/null +++ b/d4dj/target/test-classes/log4j.properties @@ -0,0 +1,9 @@ +# Set root logger level to DEBUG and its only appender to A1. +log4j.rootLogger=DEBUG, A1 + +# A1 is set to be a ConsoleAppender. +log4j.appender.A1=org.apache.log4j.ConsoleAppender + +# A1 uses PatternLayout. +log4j.appender.A1.layout=org.apache.log4j.PatternLayout +log4j.appender.A1.layout.ConversionPattern=%-4r [%t] %-5p %c %x - %m%n diff --git a/d4dj/target/test-classes/logback-test.xml b/d4dj/target/test-classes/logback-test.xml new file mode 100644 index 0000000..f0c557f --- /dev/null +++ b/d4dj/target/test-classes/logback-test.xml @@ -0,0 +1,15 @@ + + + + + + %d{HH:mm:ss.SSS} [%thread] %-5level %logger{36} - %msg%n + + + + + + + + + diff --git a/d4dj/target/test-classes/net/sourceforge/tess4j/ProgressMonitor$1.class b/d4dj/target/test-classes/net/sourceforge/tess4j/ProgressMonitor$1.class new file mode 100644 index 0000000..8ead91a Binary files /dev/null and b/d4dj/target/test-classes/net/sourceforge/tess4j/ProgressMonitor$1.class differ diff --git a/d4dj/target/test-classes/net/sourceforge/tess4j/ProgressMonitor.class b/d4dj/target/test-classes/net/sourceforge/tess4j/ProgressMonitor.class new file mode 100644 index 0000000..3d861af Binary files /dev/null and b/d4dj/target/test-classes/net/sourceforge/tess4j/ProgressMonitor.class differ diff --git a/d4dj/target/test-classes/net/sourceforge/tess4j/TessAPI1Test.class b/d4dj/target/test-classes/net/sourceforge/tess4j/TessAPI1Test.class new file mode 100644 index 0000000..ba74bde Binary files /dev/null and b/d4dj/target/test-classes/net/sourceforge/tess4j/TessAPI1Test.class differ diff --git a/d4dj/target/test-classes/net/sourceforge/tess4j/TessAPIImpl.class b/d4dj/target/test-classes/net/sourceforge/tess4j/TessAPIImpl.class new file mode 100644 index 0000000..a678ce6 Binary files /dev/null and b/d4dj/target/test-classes/net/sourceforge/tess4j/TessAPIImpl.class differ diff --git a/d4dj/target/test-classes/net/sourceforge/tess4j/TessAPITest.class b/d4dj/target/test-classes/net/sourceforge/tess4j/TessAPITest.class new file mode 100644 index 0000000..4763e84 Binary files /dev/null and b/d4dj/target/test-classes/net/sourceforge/tess4j/TessAPITest.class differ diff --git a/d4dj/target/test-classes/net/sourceforge/tess4j/Tesseract1Test.class b/d4dj/target/test-classes/net/sourceforge/tess4j/Tesseract1Test.class new file mode 100644 index 0000000..cba8f2b Binary files /dev/null and b/d4dj/target/test-classes/net/sourceforge/tess4j/Tesseract1Test.class differ diff --git a/d4dj/target/test-classes/net/sourceforge/tess4j/TesseractTest.class b/d4dj/target/test-classes/net/sourceforge/tess4j/TesseractTest.class new file mode 100644 index 0000000..83b54ce Binary files /dev/null and b/d4dj/target/test-classes/net/sourceforge/tess4j/TesseractTest.class differ diff --git a/d4dj/target/test-classes/net/sourceforge/tess4j/TestFolderExtraction.class b/d4dj/target/test-classes/net/sourceforge/tess4j/TestFolderExtraction.class new file mode 100644 index 0000000..2472b2e Binary files /dev/null and b/d4dj/target/test-classes/net/sourceforge/tess4j/TestFolderExtraction.class differ diff --git a/d4dj/target/test-classes/net/sourceforge/tess4j/util/ImageIOHelperTest.class b/d4dj/target/test-classes/net/sourceforge/tess4j/util/ImageIOHelperTest.class new file mode 100644 index 0000000..9d5d025 Binary files /dev/null and b/d4dj/target/test-classes/net/sourceforge/tess4j/util/ImageIOHelperTest.class differ diff --git a/d4dj/target/test-classes/net/sourceforge/tess4j/util/PdfUtilitiesTest.class b/d4dj/target/test-classes/net/sourceforge/tess4j/util/PdfUtilitiesTest.class new file mode 100644 index 0000000..4f49464 Binary files /dev/null and b/d4dj/target/test-classes/net/sourceforge/tess4j/util/PdfUtilitiesTest.class differ diff --git a/d4dj/target/test-classes/test-data/eurotext.bmp b/d4dj/target/test-classes/test-data/eurotext.bmp new file mode 100644 index 0000000..be05080 Binary files /dev/null and b/d4dj/target/test-classes/test-data/eurotext.bmp differ diff --git a/d4dj/target/test-classes/test-data/eurotext.pdf b/d4dj/target/test-classes/test-data/eurotext.pdf new file mode 100644 index 0000000..eac4388 Binary files /dev/null and b/d4dj/target/test-classes/test-data/eurotext.pdf differ diff --git a/d4dj/target/test-classes/test-data/eurotext.png b/d4dj/target/test-classes/test-data/eurotext.png new file mode 100644 index 0000000..e5c324e Binary files /dev/null and b/d4dj/target/test-classes/test-data/eurotext.png differ diff --git a/d4dj/target/test-classes/test-data/eurotext.tif b/d4dj/target/test-classes/test-data/eurotext.tif new file mode 100644 index 0000000..92791da Binary files /dev/null and b/d4dj/target/test-classes/test-data/eurotext.tif differ diff --git a/d4dj/target/test-classes/test-data/eurotext90.png b/d4dj/target/test-classes/test-data/eurotext90.png new file mode 100644 index 0000000..0e1d718 Binary files /dev/null and b/d4dj/target/test-classes/test-data/eurotext90.png differ diff --git a/d4dj/target/test-classes/test-data/eurotext_deskew.png b/d4dj/target/test-classes/test-data/eurotext_deskew.png new file mode 100644 index 0000000..dfa06bd Binary files /dev/null and b/d4dj/target/test-classes/test-data/eurotext_deskew.png differ diff --git a/d4dj/target/test-classes/test-data/eurotext_unlv.png b/d4dj/target/test-classes/test-data/eurotext_unlv.png new file mode 100644 index 0000000..e5c324e Binary files /dev/null and b/d4dj/target/test-classes/test-data/eurotext_unlv.png differ diff --git a/d4dj/target/test-classes/test-data/eurotext_unlv.uzn b/d4dj/target/test-classes/test-data/eurotext_unlv.uzn new file mode 100644 index 0000000..878c8de --- /dev/null +++ b/d4dj/target/test-classes/test-data/eurotext_unlv.uzn @@ -0,0 +1,3 @@ +97 162 747 50 ThirdLine +97 209 828 55 FourthLine +92 56 810 107 First2Lines \ No newline at end of file diff --git a/d4dj/target/test-classes/test-data/multipage-pdf.pdf b/d4dj/target/test-classes/test-data/multipage-pdf.pdf new file mode 100644 index 0000000..fa1eade Binary files /dev/null and b/d4dj/target/test-classes/test-data/multipage-pdf.pdf differ diff --git a/d4dj/tessdata b/d4dj/tessdata new file mode 160000 index 0000000..4767ea9 --- /dev/null +++ b/d4dj/tessdata @@ -0,0 +1 @@ +Subproject commit 4767ea922bcc460e70b87b1d303ebdfed0897da8