Remove Tesseract parameter "include_page_breaks" and use FF by default

Now Tesseract adds a page break (normally form feed) by default.

It is still possible to suppress page breaks by setting an empty
page_separator.

Signed-off-by: Stefan Weil <[email protected]>

Author: stweil

api/renderer.cpp

@@ -132,10 +132,8 @@ bool TessTextRenderer::AddImageHandler(TessBaseAPI* api) {
 
   AppendString(utf8.get());
 
-  bool pageBreak = false;
-  api->GetBoolVariable("include_page_breaks", &pageBreak);
   const char* pageSeparator = api->GetStringVariable("page_separator");
-  if (pageBreak) {
+  if (pageSeparator != nullptr && *pageSeparator != '\0') {
     AppendString(pageSeparator);
   }
 

ccmain/tesseractclass.cpp

@@ -505,10 +505,6 @@ Tesseract::Tesseract()
                  this->params()),
       BOOL_MEMBER(preserve_interword_spaces, false,
                   "Preserve multiple interword spaces", this->params()),
-      BOOL_MEMBER(include_page_breaks, FALSE,
-                  "Include page separator string in output text after each "
-                  "image/page.",
-                  this->params()),
       STRING_MEMBER(page_separator, "\f",
                     "Page separator (default is form feed control character)",
                     this->params()),

ccmain/tesseractclass.h

@@ -1103,9 +1103,6 @@ class Tesseract : public Wordrec {
   INT_VAR_H(tessedit_parallelize, 0, "Run in parallel where possible");
   BOOL_VAR_H(preserve_interword_spaces, false,
              "Preserve multiple interword spaces");
-  BOOL_VAR_H(include_page_breaks, false,
-             "Include page separator string in output text after each "
-             "image/page.");
   STRING_VAR_H(page_separator, "\f",
                "Page separator (default is form feed control character)");