tesseract v5.3.3.20231005
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 () const
 
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)
 
virtual bool BeginDocumentHandler ()
 
virtual bool AddImageHandler (TessBaseAPI *api)=0
 
virtual bool EndDocumentHandler ()
 
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 165 of file renderer.h.

Constructor & Destructor Documentation

◆ TessHOcrRenderer() [1/2]

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

Definition at line 497 of file hocrrenderer.cpp.

498 : TessResultRenderer(outputbase, "hocr") {
499 font_info_ = font_info;
500}
TessResultRenderer(const char *outputbase, const char *extension)
Definition: renderer.cpp:33

◆ TessHOcrRenderer() [2/2]

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

Definition at line 492 of file hocrrenderer.cpp.

493 : TessResultRenderer(outputbase, "hocr") {
494 font_info_ = false;
495}

Member Function Documentation

◆ AddImageHandler()

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

Implements tesseract::TessResultRenderer.

Definition at line 535 of file hocrrenderer.cpp.

535 {
536 const std::unique_ptr<const char[]> hocr(api->GetHOCRText(imagenum()));
537 if (hocr == nullptr) {
538 return false;
539 }
540
541 AppendString(hocr.get());
542
543 return true;
544}
void AppendString(const char *s)
Definition: renderer.cpp:111

◆ BeginDocumentHandler()

bool tesseract::TessHOcrRenderer::BeginDocumentHandler ( )
overrideprotectedvirtual

Reimplemented from tesseract::TessResultRenderer.

Definition at line 502 of file hocrrenderer.cpp.

502 {
504 "<?xml version=\"1.0\" encoding=\"UTF-8\"?>\n"
505 "<!DOCTYPE html PUBLIC \"-//W3C//DTD XHTML 1.0 Transitional//EN\"\n"
506 " \"http://www.w3.org/TR/xhtml1/DTD/xhtml1-transitional.dtd\">\n"
507 "<html xmlns=\"http://www.w3.org/1999/xhtml\" xml:lang=\"en\" "
508 "lang=\"en\">\n <head>\n <title>");
511 "</title>\n"
512 " <meta http-equiv=\"Content-Type\" content=\"text/html;"
513 "charset=utf-8\"/>\n"
514 " <meta name='ocr-system' content='tesseract " TESSERACT_VERSION_STR
515 "' />\n"
516 " <meta name='ocr-capabilities' content='ocr_page ocr_carea ocr_par"
517 " ocr_line ocrx_word ocrp_wconf");
518 if (font_info_) {
519 AppendString(" ocrp_lang ocrp_dir ocrp_font ocrp_fsize");
520 }
522 "'/>\n"
523 " </head>\n"
524 " <body>\n");
525
526 return true;
527}
const char * title() const
Definition: renderer.h:87

◆ EndDocumentHandler()

bool tesseract::TessHOcrRenderer::EndDocumentHandler ( )
overrideprotectedvirtual

Reimplemented from tesseract::TessResultRenderer.

Definition at line 529 of file hocrrenderer.cpp.

529 {
530 AppendString(" </body>\n</html>\n");
531
532 return true;
533}

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