mirror/tesseract
1
0
Fork 0
mirror of https://github.com/tesseract-ocr/tesseract.git synced 2024-12-18 11:28:51 +08:00
Code Issues Actions 10 Packages Projects Releases Wiki Activity

Merge pull request #2268 from Shreeshrii/grapheme

Browse Source 
Remove test for Word started with a combiner
This commit is contained in:
zdenop 2019-02-25 20:59:40 +01:00 committed by GitHub
commit 9ddf267907
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 6 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

11
src/training/validate_grapheme.cpp
View File

@ -15,11 +15,12 @@ bool ValidateGrapheme::ConsumeGraphemeIfValid() {
char32 ch = codes_[codes_used_].second;
const bool is_combiner =
cc == CharClass::kCombiner || cc == CharClass::kVirama;
// Reject easily detected badly formed sequences.
if (prev_cc == CharClass::kWhitespace && is_combiner) {
if (report_errors_) tprintf("Word started with a combiner:0x%x\n", ch);
return false;
}
// TODO: Reject easily detected badly formed sequences.
// https://github.com/tesseract-ocr/tesseract/pull/2266#issuecomment-467114751
// if (prev_cc == CharClass::kWhitespace && is_combiner) {
// if (report_errors_) tprintf("Word started with a combiner:0x%x\n", ch);
// return false;
//}
if (prev_cc == CharClass::kVirama && cc == CharClass::kVirama) {
if (report_errors_)
tprintf("Two grapheme links in a row:0x%x 0x%x\n", prev_ch, ch);