renun/siyuan
1
0
Fork 0
mirror of https://github.com/siyuan-note/siyuan.git synced 2025-02-28 05:32:52 +00:00
Code Issues Actions Packages Projects Releases Wiki Activity

🎨 OCR 结果剔除不可见字符

Browse Source
This commit is contained in:
Liang Ding
2023-01-18 00:39:42 +08:00
parent ca2a27c964
commit 6d4aa07bc7
1 changed files with 1 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
kernel/util/tesseract.go
View File

@@ -89,9 +89,7 @@ func Tesseract(imgAbsPath string) string {
}
ret := string(output)
ret = strings.ReplaceAll(ret, "\r", "")
ret = strings.ReplaceAll(ret, "\n", "")
ret = strings.ReplaceAll(ret, "\t", " ")
ret = gulu.Str.RemoveInvisible(ret)
reg := regexp.MustCompile("\\s{2,}")
ret = reg.ReplaceAllString(ret, " ")
msg := fmt.Sprintf("OCR [%s] [%s]", info.Name(), ret)