Mirrors/SubtitleEdit
1
0
Fork 0
mirror of https://github.com/SubtitleEdit/subtitleedit.git synced 2025-01-31 21:11:39 +01:00
Code Issues Projects Releases Wiki Activity

More CJK detect

Browse Source
This commit is contained in:
niksedk 2022-01-25 13:54:47 +01:00
parent 8e3aebe4ab
commit 122ba7c1a6
1 changed files with 10 additions and 7 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

17
src/libse/Common/TextLengthCalculator/CalcCJK.cs
View File

@ -64,7 +64,7 @@ namespace Nikse.SubtitleEdit.Core.Common.TextLengthCalculator
else if (ChineseFullWidthPunctuations.Contains(ch) ||
LanguageAutoDetect.JapaneseLetters.Contains(ch) ||
LanguageAutoDetect.KoreanLetters.Contains(ch) ||
IsCjk(ch))
IsCjk(ch))
{
count++;
}
@ -82,14 +82,17 @@ namespace Nikse.SubtitleEdit.Core.Common.TextLengthCalculator
public const string JapaneseHalfWidthCharacters = "｡｢｣､･ｦｧｨｩｪｫｬｭｮｯｰｱｲｳｴｵｶｷｸｹｺｻｼｽｾｿﾀﾁﾂﾃﾄﾅﾆﾇﾈﾉﾊﾋﾌﾍﾎﾏﾐﾑﾒﾓﾔﾕﾖﾗﾘﾙﾚﾛﾜﾝﾞﾟ";
public const string ChineseFullWidthPunctuations = "，。、：；？！…“”—‘’（）【】「」『』〔〕《》〈〉";
public static readonly Regex CjkCharRegex = new Regex(@"\p{IsCJKUnifiedIdeographs}", RegexOptions.Compiled);
public static readonly Regex CjkCharRegex = new Regex(@"\p{IsHangulJamo}|" +
@"\p{IsCJKRadicalsSupplement}|" +
@"\p{IsCJKSymbolsandPunctuation}|" +
@"\p{IsEnclosedCJKLettersandMonths}|" +
@"\p{IsCJKCompatibility}|" +
@"\p{IsCJKUnifiedIdeographsExtensionA}|" +
@"\p{IsCJKUnifiedIdeographs}|" +
@"\p{IsHangulSyllables}|" +
@"\p{IsCJKCompatibilityForms}", RegexOptions.Compiled);
public static bool IsCjk(char c)
{
if (c == '。' || c == '，')
{
return true;
}
return CjkCharRegex.IsMatch(c.ToString());
}
}