mirror/tesseract
1
0
Fork 0
mirror of https://github.com/tesseract-ocr/tesseract.git synced 2024-11-24 02:59:07 +08:00
Code Issues Actions 10 Packages Projects Releases Wiki Activity

Remove code which is wrong in combination with NFC

Browse Source 
See comments in https://github.com/tesseract-ocr/tesseract/pull/3420.

Signed-off-by: Stefan Weil <sw@weilnetz.de>
This commit is contained in:
Stefan Weil 2021-10-27 18:51:08 +02:00
parent 5cee9a0cec
commit 5cc649e5f9
1 changed files with 0 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
src/training/pango/ligature_table.cpp
View File

@ -4,7 +4,6 @@
* conditional on codepoint support by a specified font
* (if specified).
* Author: Ranjith Unnikrishnan
* Created: Mon Nov 18 2013
*
* (C) Copyright 2013, Google Inc.
* Licensed under the Apache License, Version 2.0 (the "License");
@ -72,11 +71,6 @@ void LigatureTable::Init() {
icu::Normalizer::normalize(unicode_lig8, UNORM_NFC, 0, normed8_result, status);
std::string normed8;
normed8_result.toUTF8String(normed8);
// The icu::Normalizer maps the "LONG S T" ligature to "st". Correct that
// here manually so that AddLigatures() will work as desired.
if (lig8 == "\uFB05") {
normed8 = "ſt";
}
int lig_length = lig8.length();
int norm_length = normed8.size();
if (normed8 != lig8 && lig_length > 1 && norm_length > 1) {