All Classes Namespaces Files Functions Variables Typedefs Enumerations Enumerator Friends Macros Modules Pages
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 151 of file renderer.h.

Constructor & Destructor Documentation

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

Definition at line 135 of file renderer.cpp.

136  : TessResultRenderer(outputbase, "hocr") {
137  font_info_ = font_info;
138 }
TessResultRenderer(const char *outputbase, const char *extension)
Definition: renderer.cpp:16
tesseract::TessHOcrRenderer::TessHOcrRenderer ( const char *  outputbase)
explicit

Definition at line 130 of file renderer.cpp.

131  : TessResultRenderer(outputbase, "hocr") {
132  font_info_ = false;
133 }
TessResultRenderer(const char *outputbase, const char *extension)
Definition: renderer.cpp:16

Member Function Documentation

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

Implements tesseract::TessResultRenderer.

Definition at line 172 of file renderer.cpp.

172  {
173  char* hocr = api->GetHOCRText(imagenum());
174  if (hocr == NULL) return false;
175 
176  AppendString(hocr);
177  delete[] hocr;
178 
179  return true;
180 }
void AppendString(const char *s)
Definition: renderer.cpp:83
#define NULL
Definition: host.h:144
bool tesseract::TessHOcrRenderer::BeginDocumentHandler ( )
protectedvirtual

Reimplemented from tesseract::TessResultRenderer.

Definition at line 140 of file renderer.cpp.

140  {
141  AppendString(
142  "<?xml version=\"1.0\" encoding=\"UTF-8\"?>\n"
143  "<!DOCTYPE html PUBLIC \"-//W3C//DTD XHTML 1.0 Transitional//EN\"\n"
144  " \"http://www.w3.org/TR/xhtml1/DTD/xhtml1-transitional.dtd\">\n"
145  "<html xmlns=\"http://www.w3.org/1999/xhtml\" xml:lang=\"en\" "
146  "lang=\"en\">\n <head>\n <title>\n");
147  AppendString(title());
148  AppendString(
149  "</title>\n"
150  "<meta http-equiv=\"Content-Type\" content=\"text/html;"
151  "charset=utf-8\" />\n"
152  " <meta name='ocr-system' content='tesseract " TESSERACT_VERSION_STR
153  "' />\n"
154  " <meta name='ocr-capabilities' content='ocr_page ocr_carea ocr_par"
155  " ocr_line ocrx_word");
156  if (font_info_)
157  AppendString(
158  " ocrp_lang ocrp_dir ocrp_font ocrp_fsize ocrp_wconf");
159  AppendString(
160  "'/>\n"
161  "</head>\n<body>\n");
162 
163  return true;
164 }
void AppendString(const char *s)
Definition: renderer.cpp:83
const char * title() const
Definition: renderer.h:80
#define TESSERACT_VERSION_STR
Definition: baseapi.h:23
bool tesseract::TessHOcrRenderer::EndDocumentHandler ( )
protectedvirtual

Reimplemented from tesseract::TessResultRenderer.

Definition at line 166 of file renderer.cpp.

166  {
167  AppendString(" </body>\n</html>\n");
168 
169  return true;
170 }
void AppendString(const char *s)
Definition: renderer.cpp:83

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