Mirrors/PowerToys
1
0
Fork 0
mirror of https://github.com/microsoft/PowerToys.git synced 2026-04-09 20:57:22 +02:00
Code Issues Packages Projects Releases Wiki Activity

[TextExtractor] Add space between CJK words and non-CJK (#20926)

Browse Source 
* [TextExtractor] add space between CJK words and non-CJK
This commit is contained in:
Weijie Zhao
2022-10-20 23:21:46 +08:00
committed by GitHub
parent d4083abee2
commit d17ac2bf79
1 changed files with 15 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

15
src/modules/PowerOCR/PowerOCR/Helpers/ImageMethods.cs
View File

@@ -10,6 +10,7 @@ using System.Globalization;
using System.IO; using System.IO;
using System.Linq; using System.Linq;
using System.Text; using System.Text;
using System.Text.RegularExpressions;
using System.Threading.Tasks; using System.Threading.Tasks;
using System.Windows; using System.Windows;
using System.Windows.Input; using System.Windows.Input;
@@ -146,11 +147,25 @@ internal class ImageMethods
} }
else else
{ {
var cjkRegex = new Regex(@"\p{IsCJKUnifiedIdeographs}");
foreach (OcrLine ocrLine in ocrResult.Lines) foreach (OcrLine ocrLine in ocrResult.Lines)
{ {
bool isBeginning = true;
bool isCJKPrev = false;
foreach (OcrWord ocrWord in ocrLine.Words) foreach (OcrWord ocrWord in ocrLine.Words)
{ {
bool isCJK = cjkRegex.IsMatch(ocrWord.Text);
// Use spaces to separate non-CJK words.
if (!isBeginning && (!isCJK || !isCJKPrev))
{
_ = text.Append(' ');
}
_ = text.Append(ocrWord.Text); _ = text.Append(ocrWord.Text);
isCJKPrev = isCJK;
isBeginning = false;
} }
text.Append(Environment.NewLine); text.Append(Environment.NewLine);