Tesseract Platform

import org.bytedeco.javacpp.*;
import org.bytedeco.tesseract.*;
import org.bytedeco.leptonica.*;
import static org.bytedeco.tesseract.global.tesseract.*;
import static org.bytedeco.leptonica.global.leptonica.*;

import org.bytedeco.javacpp.*;
import org.bytedeco.leptonica.*;
import org.bytedeco.tesseract.*;
import static org.bytedeco.leptonica.global.leptonica.*;
import static org.bytedeco.tesseract.global.tesseract.*;

public class BasicOCR {
    public static void main(String[] args) {
        TessBaseAPI api = new TessBaseAPI();
        
        // Initialize tesseract with English language
        if (api.Init(null, "eng") != 0) {
            System.err.println("Could not initialize tesseract.");
            return;
        }
        
        // Load image using Leptonica
        PIX image = pixRead("image.png");
        api.SetImage(image);
        
        // Extract text
        BytePointer outText = api.GetUTF8Text();
        System.out.println("OCR Result: " + outText.getString());
        
        // Cleanup
        api.End();
        outText.deallocate();
        image.close();
    }
}

public class TessBaseAPI {
    // Initialization
    public TessBaseAPI();
    public static native @Cast("const char*") BytePointer Version();
    public int Init(String datapath, String language, int oem);
    public int Init(String datapath, String language);
    public void End();
    
    // Image Processing  
    public void SetImage(PIX pix);
    public void SetImage(byte[] imagedata, int width, int height, int bytes_per_pixel, int bytes_per_line);
    public void SetRectangle(int left, int top, int width, int height);
    public PIX GetThresholdedImage();
    
    // Recognition
    public int Recognize(ETEXT_DESC monitor);
    public native @Cast("char*") BytePointer TesseractRect(@Cast("const unsigned char*") byte[] imagedata, int bytes_per_pixel, int bytes_per_line, 
                              int left, int top, int width, int height);
    
    // Text Output
    public native @Cast("char*") BytePointer GetUTF8Text();
    public native @Cast("char*") BytePointer GetHOCRText(int page_number);
    public native @Cast("char*") BytePointer GetTSVText(int page_number);
    public int MeanTextConf();
    public int[] AllWordConfidences();
}

public class PageIterator {
    public void Begin();
    public boolean Next(int level);
    public boolean BoundingBox(int level, int[] left, int[] top, int[] right, int[] bottom);
    public boolean Baseline(int level, int[] x1, int[] y1, int[] x2, int[] y2);
    public PIX GetBinaryImage(int level);
    public int BlockType();
    public void Orientation(int[] orientation, int[] writing_direction, 
                          int[] textline_order, float[] deskew_angle);
}

public class ResultIterator extends LTRResultIterator {
    public String GetUTF8Text(int level);
    public float Confidence(int level);
    public boolean ParagraphIsLtr();
    public String WordFontAttributes(boolean[] is_bold, boolean[] is_italic, 
                                   boolean[] is_underlined, boolean[] is_monospace, 
                                   boolean[] is_serif, boolean[] is_smallcaps, 
                                   int[] pointsize, int[] font_id);
}

public abstract class TessResultRenderer {
    public void insert(TessResultRenderer next);
    public boolean BeginDocument(String title);
    public boolean AddImage(TessBaseAPI api);
    public boolean EndDocument();
    public String file_extension();
}

// Concrete renderer classes
public class TessTextRenderer extends TessResultRenderer;
public class TessHOcrRenderer extends TessResultRenderer;
public class TessPDFRenderer extends TessResultRenderer;
public class TessAltoRenderer extends TessResultRenderer;
public class TessTsvRenderer extends TessResultRenderer;

public class TessBaseAPI {
    public PageIterator AnalyseLayout();
    public BOXA GetRegions(PIXA[] pixa);
    public BOXA GetTextlines(PIXA[] pixa, int[][] blockids);
    public BOXA GetWords(PIXA[] pixa);
    public BOXA GetComponentImages(int level, boolean text_only, PIXA[] pixa, int[][] blockids);
}

// Layout analysis constants
public static final int PSM_AUTO = 3;           // Fully automatic page segmentation
public static final int PSM_SINGLE_COLUMN = 4; // Single column of text
public static final int PSM_SINGLE_BLOCK = 6;  // Single uniform block of text
public static final int PSM_SINGLE_LINE = 7;   // Single text line

public class TessBaseAPI {
    // Parameter Management
    public boolean SetVariable(String name, String value);
    public boolean GetIntVariable(String name, int[] value);
    public boolean GetBoolVariable(String name, boolean[] value);
    public boolean GetDoubleVariable(String name, double[] value);
    public String GetStringVariable(String name);
    
    // Page Segmentation
    public void SetPageSegMode(int mode);
    public int GetPageSegMode();
    
    // OCR Engine Mode
    public static final int OEM_TESSERACT_ONLY = 0;
    public static final int OEM_LSTM_ONLY = 1; 
    public static final int OEM_DEFAULT = 3;
}

public class TessBaseAPI {
    public String GetInitLanguagesAsString();
    public void GetLoadedLanguagesAsVector(StringVector langs);
    public void GetAvailableLanguagesAsVector(StringVector langs);
}

// Language initialization examples:
// "eng" - English
// "fra" - French  
// "deu" - German
// "chi_sim" - Simplified Chinese
// "ara" - Arabic
// "eng+fra+deu" - Multiple languages

// Progress monitoring and cancellation
public class ETEXT_DESC {
    public short progress();           // Progress percentage (0-100)
    public boolean more_to_come();     // More processing pending
    public boolean ocr_alive();        // OCR engine active
    public byte err_code();            // Error code
    public void set_deadline_msecs(int deadline_msecs);
    public boolean deadline_exceeded();
}

// Unicode character handling
public class UNICHAR {
    public UNICHAR(String utf8_str, int len);
    public UNICHAR(int unicode);
    public int first_uni();            // Get first character as UCS-4
    public int utf8_len();             // Get UTF-8 byte length
    public String utf8_str();          // Get UTF-8 string
    public static int[] UTF8ToUTF32(String utf8_str);
    public static String UTF32ToUTF8(int[] str32);
}

// Collection types
public class StringVector {
    public StringVector();
    public long size();
    public String get(long i);
    public StringVector put(long i, String value);
    public StringVector push_back(String value);
    public void clear();
}

// Page hierarchy levels for iteration
public static final int RIL_BLOCK = 0;     // Block level
public static final int RIL_PARA = 1;      // Paragraph level  
public static final int RIL_TEXTLINE = 2;  // Text line level
public static final int RIL_WORD = 3;      // Word level
public static final int RIL_SYMBOL = 4;    // Character/symbol level

// Layout block types
public static final int PT_UNKNOWN = 0;        // Unknown block type
public static final int PT_FLOWING_TEXT = 1;   // Flowing text
public static final int PT_HEADING_TEXT = 2;   // Heading text
public static final int PT_PULLOUT_TEXT = 3;   // Pull-out text
public static final int PT_EQUATION = 4;       // Mathematical equation
public static final int PT_TABLE = 6;          // Table
public static final int PT_VERTICAL_TEXT = 7;  // Vertical text
public static final int PT_CAPTION_TEXT = 8;   // Caption text
public static final int PT_FLOWING_IMAGE = 9;  // Flowing image
public static final int PT_NOISE = 14;         // Noise/artifacts