tesseract  4.00.00dev
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
 
int imagenum () const
 

Protected Member Functions

virtual bool BeginDocumentHandler ()
 
virtual bool AddImageHandler (TessBaseAPI *api)
 
virtual bool EndDocumentHandler ()
 
- 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 152 of file renderer.h.

Constructor & Destructor Documentation

◆ TessHOcrRenderer() [1/2]

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

Definition at line 153 of file renderer.cpp.

154  : TessResultRenderer(outputbase, "hocr") {
155  font_info_ = font_info;
156 }
TessResultRenderer(const char *outputbase, const char *extension)
Definition: renderer.cpp:33

◆ TessHOcrRenderer() [2/2]

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

Definition at line 148 of file renderer.cpp.

149  : TessResultRenderer(outputbase, "hocr") {
150  font_info_ = false;
151 }
TessResultRenderer(const char *outputbase, const char *extension)
Definition: renderer.cpp:33

Member Function Documentation

◆ AddImageHandler()

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

Implements tesseract::TessResultRenderer.

Definition at line 190 of file renderer.cpp.

190  {
191  const std::unique_ptr<const char[]> hocr(api->GetHOCRText(imagenum()));
192  if (hocr == NULL) return false;
193 
194  AppendString(hocr.get());
195 
196  return true;
197 }
void AppendString(const char *s)
Definition: renderer.cpp:102

◆ BeginDocumentHandler()

bool tesseract::TessHOcrRenderer::BeginDocumentHandler ( )
protectedvirtual

Reimplemented from tesseract::TessResultRenderer.

Definition at line 158 of file renderer.cpp.

158  {
159  AppendString(
160  "<?xml version=\"1.0\" encoding=\"UTF-8\"?>\n"
161  "<!DOCTYPE html PUBLIC \"-//W3C//DTD XHTML 1.0 Transitional//EN\"\n"
162  " \"http://www.w3.org/TR/xhtml1/DTD/xhtml1-transitional.dtd\">\n"
163  "<html xmlns=\"http://www.w3.org/1999/xhtml\" xml:lang=\"en\" "
164  "lang=\"en\">\n <head>\n <title>");
165  AppendString(title());
166  AppendString(
167  "</title>\n"
168  "<meta http-equiv=\"Content-Type\" content=\"text/html;"
169  "charset=utf-8\" />\n"
170  " <meta name='ocr-system' content='tesseract " TESSERACT_VERSION_STR
171  "' />\n"
172  " <meta name='ocr-capabilities' content='ocr_page ocr_carea ocr_par"
173  " ocr_line ocrx_word");
174  if (font_info_)
175  AppendString(
176  " ocrp_lang ocrp_dir ocrp_font ocrp_fsize ocrp_wconf");
177  AppendString(
178  "'/>\n"
179  "</head>\n<body>\n");
180 
181  return true;
182 }
#define TESSERACT_VERSION_STR
Definition: baseapi.h:23
void AppendString(const char *s)
Definition: renderer.cpp:102
const char * title() const
Definition: renderer.h:81

◆ EndDocumentHandler()

bool tesseract::TessHOcrRenderer::EndDocumentHandler ( )
protectedvirtual

Reimplemented from tesseract::TessResultRenderer.

Definition at line 184 of file renderer.cpp.

184  {
185  AppendString(" </body>\n</html>\n");
186 
187  return true;
188 }
void AppendString(const char *s)
Definition: renderer.cpp:102

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