PAGE XML renderer / export

CMakeLists.txt

@@ -740,6 +740,7 @@ set(TESSERACT_SRC
     src/api/capi.cpp
     src/api/renderer.cpp
     src/api/altorenderer.cpp
+    src/api/pagerenderer.cpp
     src/api/hocrrenderer.cpp
     src/api/lstmboxrenderer.cpp
     src/api/pdfrenderer.cpp
@@ -764,6 +765,7 @@ set(TESSERACT_CONFIGS
     tessdata/configs/lstmbox
     tessdata/configs/lstmdebug
     tessdata/configs/makebox
+    tessdata/configs/page
     tessdata/configs/pdf
     tessdata/configs/quiet
     tessdata/configs/rebox

Makefile.am

@@ -113,6 +113,7 @@ libtesseract_la_LDFLAGS += -version-info $(GENERIC_LIBRARY_VERSION)
 
 libtesseract_la_SOURCES = src/api/baseapi.cpp
 libtesseract_la_SOURCES += src/api/altorenderer.cpp
+libtesseract_la_SOURCES += src/api/pagerenderer.cpp
 libtesseract_la_SOURCES += src/api/capi.cpp
 libtesseract_la_SOURCES += src/api/hocrrenderer.cpp
 libtesseract_la_SOURCES += src/api/lstmboxrenderer.cpp

README.md

@@ -36,7 +36,7 @@ Tesseract has **unicode (UTF-8) support**, and can **recognize [more than 100 la
 
 Tesseract supports **[various image formats](https://tesseract-ocr.github.io/tessdoc/InputFormats)** including PNG, JPEG and TIFF.
 
-Tesseract supports **various output formats**: plain text, hOCR (HTML), PDF, invisible-text-only PDF, TSV and ALTO.
+Tesseract supports **various output formats**: plain text, hOCR (HTML), PDF, invisible-text-only PDF, TSV, ALTO and PAGE.
 
 You should note that in many cases, in order to get better OCR results, you'll need to **[improve the quality](https://tesseract-ocr.github.io/tessdoc/ImproveQuality.html) of the image** you are giving Tesseract.
 

doc/tesseract.1.asc

@@ -104,6 +104,10 @@ OPTIONS
 
   * *alto* -- Output in ALTO format ('OUTPUTBASE'`.xml`).
   * *hocr* -- Output in hOCR format ('OUTPUTBASE'`.hocr`).
+  * *page* -- Output in PAGE format ('OUTPUTBASE'`.page.xml`).
+              The output can be customized with the flags:
+              page_xml_polygon -- Create polygons instead of bounding boxes (default: true)
+              page_xml_level -- Create the PAGE file on  0=linelevel or 1=wordlevel (default: 0)
   * *pdf* -- Output PDF ('OUTPUTBASE'`.pdf`).
   * *tsv* -- Output TSV ('OUTPUTBASE'`.tsv`).
   * *txt* -- Output plain text ('OUTPUTBASE'`.txt`).

include/tesseract/baseapi.h

@@ -550,6 +550,18 @@ class TESS_API TessBaseAPI {
    */
   char *GetAltoText(int page_number);
 
+   /**
+   * Make an XML-formatted string with PAGE markup from the internal
+   * data structures.
+   */
+  char *GetPAGEText(ETEXT_DESC *monitor, int page_number);
+
+  /**
+   * Make an XML-formatted string with PAGE markup from the internal
+   * data structures.
+   */
+  char *GetPAGEText(int page_number);
+
   /**
    * Make a TSV-formatted string from the internal data structures.
    * page_number is 0-based but will appear in the output as 1-based.

include/tesseract/renderer.h

@@ -198,6 +198,23 @@ class TESS_API TessAltoRenderer : public TessResultRenderer {
   bool begin_document;
 };
 
+/**
+ * Renders Tesseract output into a PAGE XML text string
+ */
+class TESS_API TessPAGERenderer : public TessResultRenderer {
+public:
+  explicit TessPAGERenderer(const char *outputbase);
+
+protected:
+  bool BeginDocumentHandler() override;
+  bool AddImageHandler(TessBaseAPI *api) override;
+  bool EndDocumentHandler() override;
+
+private:
+  bool begin_document;
+};
+
+
 /**
  * Renders Tesseract output into a TSV string
  */

src/api/capi.cpp

@@ -68,6 +68,10 @@ TessResultRenderer *TessAltoRendererCreate(const char *outputbase) {
   return new tesseract::TessAltoRenderer(outputbase);
 }
 
+TessResultRenderer *TessPAGERendererCreate(const char *outputbase) {
+  return new tesseract::TessPAGERenderer(outputbase);
+}
+
 TessResultRenderer *TessTsvRendererCreate(const char *outputbase) {
   return new tesseract::TessTsvRenderer(outputbase);
 }
@@ -420,6 +424,10 @@ char *TessBaseAPIGetAltoText(TessBaseAPI *handle, int page_number) {
   return handle->GetAltoText(page_number);
 }
 
+char *TessBaseAPIGetPAGEText(TessBaseAPI *handle, int page_number) {
+  return handle->GetPAGEText(page_number);
+}
+
 char *TessBaseAPIGetTsvText(TessBaseAPI *handle, int page_number) {
   return handle->GetTSVText(page_number);
 }