From c2e84c460612c290f3cc76e6ed69cba518ae0d5a Mon Sep 17 00:00:00 2001
From: "david.eger@gmail.com"
 <david.eger@gmail.com@d0cd1f9f-072b-0410-8dd7-cf729c803f20>
Date: Tue, 6 Mar 2012 21:18:16 +0000
Subject: [PATCH] Fix two issues with GetHOCRText(): + make it not seg-fault if
 called without calling SetInputName(). + make it not leak memory (thank you
 valgrind)

http://code.google.com/p/tesseract-ocr/issues/detail?id=463



git-svn-id: https://tesseract-ocr.googlecode.com/svn/trunk@699 d0cd1f9f-072b-0410-8dd7-cf729c803f20
---
 api/baseapi.cpp | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/api/baseapi.cpp b/api/baseapi.cpp
index 07dc78d0..b570cd45 100644
--- a/api/baseapi.cpp
+++ b/api/baseapi.cpp
@@ -950,7 +950,7 @@ char* TessBaseAPI::GetHOCRText(int page_number) {
 
   hocr_str.add_str_int("<div class='ocr_page' id='page_", page_id);
   hocr_str += "' title='image \"";
-  hocr_str += *input_file_;
+  hocr_str += input_file_ ? *input_file_ : "unknown";
   hocr_str.add_str_int("\"; bbox ", rect_left_);
   hocr_str.add_str_int(" ", rect_top_);
   hocr_str.add_str_int(" ", rect_width_);
@@ -1013,6 +1013,7 @@ char* TessBaseAPI::GetHOCRText(int page_number) {
           hocr_str += grapheme;
         }
       }
+      delete []grapheme;
       res_it->Next(RIL_SYMBOL);
     } while (!res_it->Empty(RIL_BLOCK) && !res_it->IsAtBeginningOf(RIL_WORD));
     if (italic) hocr_str += "</em>";
-- 
GitLab