|
tesseract 3.04.01
|
#include <renderer.h>
Public Member Functions | |
| TessHOcrRenderer (const char *outputbase, bool font_info) | |
| TessHOcrRenderer (const char *outputbase) | |
Protected Member Functions | |
| virtual bool | BeginDocumentHandler () |
| virtual bool | AddImageHandler (TessBaseAPI *api) |
| virtual bool | EndDocumentHandler () |
Renders tesseract output into an hocr text string
Definition at line 151 of file renderer.h.
| tesseract::TessHOcrRenderer::TessHOcrRenderer | ( | const char * | outputbase, |
| bool | font_info | ||
| ) | [explicit] |
Definition at line 135 of file renderer.cpp.
: TessResultRenderer(outputbase, "hocr") { font_info_ = font_info; }
| tesseract::TessHOcrRenderer::TessHOcrRenderer | ( | const char * | outputbase | ) | [explicit] |
Definition at line 130 of file renderer.cpp.
: TessResultRenderer(outputbase, "hocr") { font_info_ = false; }
| bool tesseract::TessHOcrRenderer::AddImageHandler | ( | TessBaseAPI * | api | ) | [protected, virtual] |
Implements tesseract::TessResultRenderer.
Definition at line 172 of file renderer.cpp.
{
char* hocr = api->GetHOCRText(imagenum());
if (hocr == NULL) return false;
AppendString(hocr);
delete[] hocr;
return true;
}
| bool tesseract::TessHOcrRenderer::BeginDocumentHandler | ( | ) | [protected, virtual] |
Reimplemented from tesseract::TessResultRenderer.
Definition at line 140 of file renderer.cpp.
{
AppendString(
"<?xml version=\"1.0\" encoding=\"UTF-8\"?>\n"
"<!DOCTYPE html PUBLIC \"-//W3C//DTD XHTML 1.0 Transitional//EN\"\n"
" \"http://www.w3.org/TR/xhtml1/DTD/xhtml1-transitional.dtd\">\n"
"<html xmlns=\"http://www.w3.org/1999/xhtml\" xml:lang=\"en\" "
"lang=\"en\">\n <head>\n <title>");
AppendString(title());
AppendString(
"</title>\n"
"<meta http-equiv=\"Content-Type\" content=\"text/html;"
"charset=utf-8\" />\n"
" <meta name='ocr-system' content='tesseract " TESSERACT_VERSION_STR
"' />\n"
" <meta name='ocr-capabilities' content='ocr_page ocr_carea ocr_par"
" ocr_line ocrx_word");
if (font_info_)
AppendString(
" ocrp_lang ocrp_dir ocrp_font ocrp_fsize ocrp_wconf");
AppendString(
"'/>\n"
"</head>\n<body>\n");
return true;
}
| bool tesseract::TessHOcrRenderer::EndDocumentHandler | ( | ) | [protected, virtual] |
Reimplemented from tesseract::TessResultRenderer.
Definition at line 166 of file renderer.cpp.
{
AppendString(" </body>\n</html>\n");
return true;
}