From fb863c97a9c8e9c05874af6f6fbd77923cc6f6e9 Mon Sep 17 00:00:00 2001
From: Stefan Weil <sw@weilnetz.de>
Date: Fri, 19 May 2017 20:56:55 +0200
Subject: [PATCH] UNICHARSET: Add missing initialization

The member variable default_sid_ was used without being initialized.

Valgrind report for `tesseract --oem 1 hello.png hello`:

    Conditional jump or move depends on uninitialised value(s)
       at 0x14352E: BITS16::set_bit(unsigned char, unsigned char) (bits16.h:50)
       by 0x143E27: WERD::set_flag(WERD_FLAGS, unsigned char) (werd.h:129)
       by 0x27D053: WERD_RES::SetupWordScript(UNICHARSET const&) (pageres.cpp:381)
       by 0x27CAFD: WERD_RES::SetupForRecognition(UNICHARSET const&, tesseract::Tesseract*, Pix*, int, TBOX const*, bool, bool, bool, ROW*, BLOCK const*) (pageres.cpp:316)
       by 0x145903: tesseract::Tesseract::SetupWordPassN(int, tesseract::WordData*) (control.cpp:182)
       by 0x145780: tesseract::Tesseract::SetupAllWordsPassN(int, TBOX const*, char const*, PAGE_RES*, GenericVector<tesseract::WordData>*) (control.cpp:168)
       by 0x146293: tesseract::Tesseract::recog_all_words(PAGE_RES*, ETEXT_DESC*, TBOX const*, char const*, int) (control.cpp:336)
       by 0x12F356: tesseract::TessBaseAPI::Recognize(ETEXT_DESC*) (baseapi.cpp:878)
       by 0x13036D: tesseract::TessBaseAPI::ProcessPage(Pix*, int, char const*, char const*, int, tesseract::TessResultRenderer*) (baseapi.cpp:1184)
       by 0x13014A: tesseract::TessBaseAPI::ProcessPagesInternal(char const*, char const*, int, tesseract::TessResultRenderer*) (baseapi.cpp:1140)
       by 0x12FBCE: tesseract::TessBaseAPI::ProcessPages(char const*, char const*, int, tesseract::TessResultRenderer*) (baseapi.cpp:1040)
       by 0x12C3DF: main (tesseractmain.cpp:515)
     Uninitialised value was created by a heap allocation
       at 0x4C2C21F: operator new(unsigned long) (vg_replace_malloc.c:334)
       by 0x12D88B: tesseract::TessBaseAPI::Init(char const*, int, char const*, tesseract::OcrEngineMode, char**, int, GenericVector<STRING> const*, GenericVector<STRING> const*, bool, bool (*)(STRING const&, GenericVector<char>*)) (baseapi.cpp:320)
       by 0x12D6DA: tesseract::TessBaseAPI::Init(char const*, char const*, tesseract::OcrEngineMode, char**, int, GenericVector<STRING> const*, GenericVector<STRING> const*, bool) (baseapi.cpp:284)
       by 0x12C088: main (tesseractmain.cpp:440)

Signed-off-by: Stefan Weil <sw@weilnetz.de>
---
 ccutil/unicharset.h | 1 +
 1 file changed, 1 insertion(+)

diff --git a/ccutil/unicharset.h b/ccutil/unicharset.h
index 716147eebd..a2e4e3b76d 100644
--- a/ccutil/unicharset.h
+++ b/ccutil/unicharset.h
@@ -292,6 +292,7 @@ class UNICHARSET {
     katakana_sid_ = 0;
     thai_sid_ = 0;
     hangul_sid_ = 0;
+    default_sid_ = 0;
   }
 
   // Return the size of the set (the number of different UNICHAR it holds).