tesseract  4.1.1
tesseract::TessHOcrRenderer Class Reference

#include <renderer.h>

Inheritance diagram for tesseract::TessHOcrRenderer:
tesseract::TessResultRenderer

Public Member Functions

 TessHOcrRenderer (const char *outputbase, bool font_info)
 
 TessHOcrRenderer (const char *outputbase)
 
- Public Member Functions inherited from tesseract::TessResultRenderer
virtual ~TessResultRenderer ()
 
void insert (TessResultRenderer *next)
 
TessResultRenderernext ()
 
bool BeginDocument (const char *title)
 
bool AddImage (TessBaseAPI *api)
 
bool EndDocument ()
 
const char * file_extension () const
 
const char * title () const
 
bool happy ()
 
int imagenum () const
 

Protected Member Functions

bool BeginDocumentHandler () override
 
bool AddImageHandler (TessBaseAPI *api) override
 
bool EndDocumentHandler () override
 
- Protected Member Functions inherited from tesseract::TessResultRenderer
 TessResultRenderer (const char *outputbase, const char *extension)
 
void AppendString (const char *s)
 
void AppendData (const char *s, int len)
 

Detailed Description

Renders tesseract output into an hocr text string

Definition at line 167 of file renderer.h.

Constructor & Destructor Documentation

◆ TessHOcrRenderer() [1/2]

tesseract::TessHOcrRenderer::TessHOcrRenderer ( const char *  outputbase,
bool  font_info 
)
explicit

Definition at line 379 of file hocrrenderer.cpp.

380  : TessResultRenderer(outputbase, "hocr") {
381  font_info_ = font_info;
382 }
TessResultRenderer(const char *outputbase, const char *extension)
Definition: renderer.cpp:33

◆ TessHOcrRenderer() [2/2]

tesseract::TessHOcrRenderer::TessHOcrRenderer ( const char *  outputbase)
explicit

Definition at line 374 of file hocrrenderer.cpp.

375  : TessResultRenderer(outputbase, "hocr") {
376  font_info_ = false;
377 }
TessResultRenderer(const char *outputbase, const char *extension)
Definition: renderer.cpp:33

Member Function Documentation

◆ AddImageHandler()

bool tesseract::TessHOcrRenderer::AddImageHandler ( TessBaseAPI api)
overrideprotectedvirtual

Implements tesseract::TessResultRenderer.

Definition at line 415 of file hocrrenderer.cpp.

415  {
416  const std::unique_ptr<const char[]> hocr(api->GetHOCRText(imagenum()));
417  if (hocr == nullptr) return false;
418 
419  AppendString(hocr.get());
420 
421  return true;
422 }
void AppendString(const char *s)
Definition: renderer.cpp:102

◆ BeginDocumentHandler()

bool tesseract::TessHOcrRenderer::BeginDocumentHandler ( )
overrideprotectedvirtual

Reimplemented from tesseract::TessResultRenderer.

Definition at line 384 of file hocrrenderer.cpp.

384  {
385  AppendString(
386  "<?xml version=\"1.0\" encoding=\"UTF-8\"?>\n"
387  "<!DOCTYPE html PUBLIC \"-//W3C//DTD XHTML 1.0 Transitional//EN\"\n"
388  " \"http://www.w3.org/TR/xhtml1/DTD/xhtml1-transitional.dtd\">\n"
389  "<html xmlns=\"http://www.w3.org/1999/xhtml\" xml:lang=\"en\" "
390  "lang=\"en\">\n <head>\n <title>");
391  AppendString(title());
392  AppendString(
393  "</title>\n"
394  " <meta http-equiv=\"Content-Type\" content=\"text/html;"
395  "charset=utf-8\"/>\n"
396  " <meta name='ocr-system' content='tesseract " PACKAGE_VERSION
397  "' />\n"
398  " <meta name='ocr-capabilities' content='ocr_page ocr_carea ocr_par"
399  " ocr_line ocrx_word ocrp_wconf");
400  if (font_info_) AppendString(" ocrp_lang ocrp_dir ocrp_font ocrp_fsize");
401  AppendString(
402  "'/>\n"
403  " </head>\n"
404  " <body>\n");
405 
406  return true;
407 }
const char * title() const
Definition: renderer.h:88
void AppendString(const char *s)
Definition: renderer.cpp:102

◆ EndDocumentHandler()

bool tesseract::TessHOcrRenderer::EndDocumentHandler ( )
overrideprotectedvirtual

Reimplemented from tesseract::TessResultRenderer.

Definition at line 409 of file hocrrenderer.cpp.

409  {
410  AppendString(" </body>\n</html>\n");
411 
412  return true;
413 }
void AppendString(const char *s)
Definition: renderer.cpp:102

The documentation for this class was generated from the following files: