Add getWords API

nguyenq · Dec 5, 2015 · ba52362 · ba52362
1 parent 80b4feb
commit ba52362
Show file tree

Hide file tree

Showing 6 changed files with 131 additions and 117 deletions.
diff --git a/src/main/java/net/sourceforge/tess4j/ITesseract.java b/src/main/java/net/sourceforge/tess4j/ITesseract.java
@@ -219,9 +219,18 @@ public enum RenderedFormat {
      * Gets segmented regions.
      *
      * @param bi input image
-     * @param level TessPageIteratorLevel enum
-     * @return
+     * @param pageIteratorLevel TessPageIteratorLevel enum
+     * @return list of <code>Rectangle</code>
      * @throws TesseractException
      */
-    List<Rectangle> getSegmentedRegions(BufferedImage bi, int level) throws TesseractException;
+    List<Rectangle> getSegmentedRegions(BufferedImage bi, int pageIteratorLevel) throws TesseractException;
+
+    /**
+     * Gets recognized words at specific page iterator level.
+     * 
+     * @param bi input image
+     * @param pageIteratorLevel TessPageIteratorLevel enum
+     * @return list of <code>Word</code>
+     */
+    List<Word> getWords(BufferedImage bi, int pageIteratorLevel);
 }
diff --git a/src/main/java/net/sourceforge/tess4j/Tesseract.java b/src/main/java/net/sourceforge/tess4j/Tesseract.java
@@ -22,6 +22,7 @@
 import java.awt.image.*;
 import java.io.*;
 import java.nio.ByteBuffer;
+import java.nio.IntBuffer;
 import java.util.*;
 import javax.imageio.IIOImage;
 import net.sourceforge.lept4j.Box;
@@ -32,6 +33,8 @@
 
 import net.sourceforge.tess4j.ITessAPI.TessBaseAPI;
 import net.sourceforge.tess4j.ITessAPI.TessOcrEngineMode;
+import net.sourceforge.tess4j.ITessAPI.TessPageIterator;
+import net.sourceforge.tess4j.ITessAPI.TessResultIterator;
 import net.sourceforge.tess4j.ITessAPI.TessResultRenderer;
 
 import net.sourceforge.tess4j.util.ImageIOHelper;
@@ -568,20 +571,20 @@ private void createDocuments(String filename, TessResultRenderer renderer) throw
      * Gets segmented regions.
      *
      * @param bi input image
-     * @param level TessPageIteratorLevel enum
-     * @return
+     * @param pageIteratorLevel TessPageIteratorLevel enum
+     * @return list of <code>Rectangle</code>
      * @throws TesseractException
      */
     @Override
-    public List<Rectangle> getSegmentedRegions(BufferedImage bi, int level) throws TesseractException {
+    public List<Rectangle> getSegmentedRegions(BufferedImage bi, int pageIteratorLevel) throws TesseractException {
         init();
         setTessVariables();
 
         try {
             List<Rectangle> list = new ArrayList<Rectangle>();
             setImage(bi, null);
 
-            Boxa boxes = api.TessBaseAPIGetComponentImages(handle, level, TRUE, null, null);
+            Boxa boxes = api.TessBaseAPIGetComponentImages(handle, pageIteratorLevel, TRUE, null, null);
             Leptonica leptInstance = Leptonica.INSTANCE;
             int boxCount = leptInstance.boxaGetCount(boxes);
             for (int i = 0; i < boxCount; i++) {
@@ -602,6 +605,53 @@ public List<Rectangle> getSegmentedRegions(BufferedImage bi, int level) throws T
         }
     }
 
+    /**
+     * Gets recognized words at specific page iterator level.
+     *
+     * @param bi input image
+     * @param pageIteratorLevel TessPageIteratorLevel enum
+     * @return list of <code>Word</code>
+     */
+    public List<Word> getWords(BufferedImage bi, int pageIteratorLevel) {
+        this.init();
+        this.setTessVariables();
+
+        List<Word> words = new ArrayList<Word>();
+
+        try {
+            setImage(bi, null);
+
+            api.TessBaseAPIRecognize(handle, null);
+            TessResultIterator ri = api.TessBaseAPIGetIterator(handle);
+            TessPageIterator pi = api.TessResultIteratorGetPageIterator(ri);
+            api.TessPageIteratorBegin(pi);
+
+            do {
+                Pointer ptr = api.TessResultIteratorGetUTF8Text(ri, pageIteratorLevel);
+                String text = ptr.getString(0);
+                api.TessDeleteText(ptr);
+                float confidence = api.TessResultIteratorConfidence(ri, pageIteratorLevel);
+                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();
+                Word word = new Word(text, confidence, new Rectangle(left, top, right - left, bottom - top));
+                words.add(word);
+            } while (api.TessPageIteratorNext(pi, pageIteratorLevel) == TRUE);
+
+            return words;
+        } catch (Exception e) {
+            return words;
+        } finally {
+            dispose();
+        }
+    }
+
     /**
      * Releases all of the native resources used by this instance.
      */

diff --git a/src/main/java/net/sourceforge/tess4j/Tesseract1.java b/src/main/java/net/sourceforge/tess4j/Tesseract1.java
@@ -22,6 +22,7 @@
 import java.awt.image.*;
 import java.io.*;
 import java.nio.ByteBuffer;
+import java.nio.IntBuffer;
 import java.util.*;
 import javax.imageio.IIOImage;
 import net.sourceforge.lept4j.Box;
@@ -536,20 +537,20 @@ private void createDocuments(String filename, TessResultRenderer renderer) throw
      * Gets segmented regions.
      *
      * @param bi input image
-     * @param level TessPageIteratorLevel enum
-     * @return
+     * @param pageIteratorLevel TessPageIteratorLevel enum
+     * @return list of <code>Rectangle</code>
      * @throws TesseractException
      */
     @Override
-    public List<Rectangle> getSegmentedRegions(BufferedImage bi, int level) throws TesseractException {
+    public List<Rectangle> getSegmentedRegions(BufferedImage bi, int pageIteratorLevel) throws TesseractException {
         init();
         setTessVariables();
 
         try {
             List<Rectangle> list = new ArrayList<Rectangle>();
             setImage(bi, null);
 
-            Boxa boxes = TessBaseAPIGetComponentImages(handle, level, TRUE, null, null);
+            Boxa boxes = TessBaseAPIGetComponentImages(handle, pageIteratorLevel, TRUE, null, null);
             int boxCount = Leptonica1.boxaGetCount(boxes);
             for (int i = 0; i < boxCount; i++) {
                 Box box = Leptonica1.boxaGetBox(boxes, i, L_CLONE);
@@ -569,6 +570,53 @@ public List<Rectangle> getSegmentedRegions(BufferedImage bi, int level) throws T
         }
     }
 
+    /**
+     * Gets recognized words at specific page iterator level.
+     *
+     * @param bi input image
+     * @param pageIteratorLevel TessPageIteratorLevel enum
+     * @return list of <code>Word</code>
+     */
+    public List<Word> getWords(BufferedImage bi, int pageIteratorLevel) {
+        this.init();
+        this.setTessVariables();
+
+        List<Word> words = new ArrayList<Word>();
+
+        try {
+            setImage(bi, null);
+
+            TessBaseAPIRecognize(handle, null);
+            TessResultIterator ri = TessBaseAPIGetIterator(handle);
+            TessPageIterator pi = TessResultIteratorGetPageIterator(ri);
+            TessPageIteratorBegin(pi);
+
+            do {
+                Pointer ptr = TessResultIteratorGetUTF8Text(ri, pageIteratorLevel);
+                String text = ptr.getString(0);
+                TessAPI1.TessDeleteText(ptr);
+                float confidence = TessResultIteratorConfidence(ri, pageIteratorLevel);
+                IntBuffer leftB = IntBuffer.allocate(1);
+                IntBuffer topB = IntBuffer.allocate(1);
+                IntBuffer rightB = IntBuffer.allocate(1);
+                IntBuffer bottomB = IntBuffer.allocate(1);
+                TessPageIteratorBoundingBox(pi, pageIteratorLevel, leftB, topB, rightB, bottomB);
+                int left = leftB.get();
+                int top = topB.get();
+                int right = rightB.get();
+                int bottom = bottomB.get();
+                Word word = new Word(text, confidence, new Rectangle(left, top, right - left, bottom - top));
+                words.add(word);
+            } while (TessPageIteratorNext(pi, pageIteratorLevel) == TRUE);
+
+            return words;
+        } catch (Exception e) {
+            return words;
+        } finally {
+            dispose();
+        }
+    }
+
     /**
      * Releases all of the native resources used by this instance.
      */

diff --git a/...est/java/net/sourceforge/tess4j/Word.java → ...ain/java/net/sourceforge/tess4j/Word.java b/...est/java/net/sourceforge/tess4j/Word.java → ...ain/java/net/sourceforge/tess4j/Word.java
@@ -18,7 +18,7 @@
 import java.awt.Rectangle;
 
 /**
- * Encapsulates Tesseract results.
+ * Encapsulates Tesseract OCR results.
  */
 class Word {
 

diff --git a/src/test/java/net/sourceforge/tess4j/Tesseract1Test.java b/src/test/java/net/sourceforge/tess4j/Tesseract1Test.java
@@ -202,7 +202,7 @@ public void testDoOCR_SkewedImage() throws Exception {
     }
 
     /**
-     * Test of createDocuments method, of class Tesseract.
+     * Test of createDocuments method, of class Tesseract1.
      *
      * @throws java.lang.Exception
      */
@@ -219,25 +219,22 @@ public void testCreateDocuments() throws Exception {
     }
 
     /**
-     * Test of extending Tesseract1.
+     * Test of getWords method, of class Tesseract1.
      *
      * @throws Exception while processing image.
      */
     @Test
-    public void testExtendingTesseract1() throws Exception {
-        logger.info("Extends Tesseract1");
+    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 <lazy> #90 dog";
         String[] expResults = expResult.split("\\s");
 
-        Tess1Extension instance1 = new Tess1Extension();
-        instance1.setDatapath(new File(datapath).getPath());
         int pageIteratorLevel = TessPageIteratorLevel.RIL_WORD;
-        logger.info("PageIteratorLevel: "
-                + Utils.getConstantName(pageIteratorLevel, TessPageIteratorLevel.class));
+        logger.info("PageIteratorLevel: " + Utils.getConstantName(pageIteratorLevel, TessPageIteratorLevel.class));
         BufferedImage bi = ImageIO.read(imageFile);
-        List<Word> result = instance1.getWords(bi, pageIteratorLevel);
+        List<Word> result = instance.getWords(bi, pageIteratorLevel);
 
         // print the complete result
         for (Word word : result) {
@@ -252,53 +249,11 @@ public void testExtendingTesseract1() throws Exception {
         assertArrayEquals(expResults, text.toArray());
     }
 
-    class Tess1Extension extends Tesseract1 {
-
-        public List<Word> getWords(BufferedImage bi, int pageIteratorLevel) {
-            this.init();
-            this.setTessVariables();
-
-            List<Word> words = new ArrayList<Word>();
-            try {
-                setImage(bi, null);
-
-                TessBaseAPIRecognize(this.getHandle(), null);
-                TessResultIterator ri = TessBaseAPIGetIterator(this.getHandle());
-                TessPageIterator pi = TessResultIteratorGetPageIterator(ri);
-                TessPageIteratorBegin(pi);
-
-                do {
-                    Pointer ptr = TessResultIteratorGetUTF8Text(ri, pageIteratorLevel);
-                    String text = ptr.getString(0);
-                    TessAPI1.TessDeleteText(ptr);
-                    float confidence = TessResultIteratorConfidence(ri, pageIteratorLevel);
-                    IntBuffer leftB = IntBuffer.allocate(1);
-                    IntBuffer topB = IntBuffer.allocate(1);
-                    IntBuffer rightB = IntBuffer.allocate(1);
-                    IntBuffer bottomB = IntBuffer.allocate(1);
-                    TessPageIteratorBoundingBox(pi, pageIteratorLevel, leftB, topB, rightB, bottomB);
-                    int left = leftB.get();
-                    int top = topB.get();
-                    int right = rightB.get();
-                    int bottom = bottomB.get();
-                    Word word = new Word(text, confidence, new Rectangle(left, top, right - left, bottom - top));
-                    words.add(word);
-                } while (TessPageIteratorNext(pi, pageIteratorLevel) == TRUE);
-
-                return words;
-            } catch (Exception e) {
-                return words;
-            } finally {
-                this.dispose();
-            }
-        }
-    }
-
     /**
      * Test of getSegmentedRegions method, of class Tesseract1.
      */
     @Test
-    public void testGetRegions() throws Exception {
+    public void testGetSegmentedRegions() throws Exception {
         logger.info("getRegions at given TessPageIteratorLevel");
         File imageFile = new File(testResourcesDataPath, "eurotext.png");
         BufferedImage bi = ImageIO.read(imageFile);

diff --git a/src/test/java/net/sourceforge/tess4j/TesseractTest.java b/src/test/java/net/sourceforge/tess4j/TesseractTest.java
@@ -235,24 +235,22 @@ public void testCreateDocuments() throws Exception {
     }
 
     /**
-     * Test of extending Tesseract.
+     * Test of getWords method, of class Tesseract.
      *
      * @throws java.lang.Exception
      */
     @Test
-    public void testExtendingTesseract() throws Exception {
-        logger.info("Extends Tesseract");
+    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 <lazy> #90 dog";
         String[] expResults = expResult.split("\\s");
 
-        TessExtension instance1 = new TessExtension();
-        instance1.setDatapath(new File(datapath).getPath());
         int pageIteratorLevel = TessPageIteratorLevel.RIL_WORD;
         logger.info("PageIteratorLevel: " + Utils.getConstantName(pageIteratorLevel, TessPageIteratorLevel.class));
         BufferedImage bi = ImageIO.read(imageFile);
-        List<Word> result = instance1.getWords(bi, pageIteratorLevel);
+        List<Word> result = instance.getWords(bi, pageIteratorLevel);
 
         //print the complete result
         for (Word word : result) {
@@ -267,57 +265,11 @@ public void testExtendingTesseract() throws Exception {
         assertArrayEquals(expResults, text.toArray());
     }
 
-    /**
-     * Extends Tesseract.
-     */
-    class TessExtension extends Tesseract {
-
-        public List<Word> getWords(BufferedImage bi, int pageIteratorLevel) {
-            this.init();
-            this.setTessVariables();
-
-            List<Word> words = new ArrayList<Word>();
-            try {
-                setImage(bi, null);
-
-                TessAPI api = this.getAPI();
-                api.TessBaseAPIRecognize(this.getHandle(), null);
-                TessResultIterator ri = api.TessBaseAPIGetIterator(this.getHandle());
-                TessPageIterator pi = api.TessResultIteratorGetPageIterator(ri);
-                api.TessPageIteratorBegin(pi);
-
-                do {
-                    Pointer ptr = api.TessResultIteratorGetUTF8Text(ri, pageIteratorLevel);
-                    String text = ptr.getString(0);
-                    api.TessDeleteText(ptr);
-                    float confidence = api.TessResultIteratorConfidence(ri, pageIteratorLevel);
-                    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();
-                    Word word = new Word(text, confidence, new Rectangle(left, top, right - left, bottom - top));
-                    words.add(word);
-                } while (api.TessPageIteratorNext(pi, pageIteratorLevel) == TRUE);
-
-                return words;
-            } catch (Exception e) {
-                return words;
-            } finally {
-                this.dispose();
-            }
-        }
-    }
-
     /**
      * Test of getSegmentedRegions method, of class Tesseract.
      */
     @Test
-    public void testGetRegions() throws Exception {
+    public void testGetSegmentedRegions() throws Exception {
         logger.info("getRegions at given TessPageIteratorLevel");
         File imageFile = new File(testResourcesDataPath, "eurotext.png");
         BufferedImage bi = ImageIO.read(imageFile);