tretrauit/swordfish
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

fix(tesseract/regex): add workaround for é, á and d

Browse Source
This commit is contained in:
tretrauit 2024-02-01 00:08:32 +07:00
parent e598e34d45
commit 5ae36d7f2a
1 changed files with 2 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
swordfish/src/tesseract/utils.rs
View File

@ -170,6 +170,8 @@ pub fn regexify_text(text: &String) -> String {
ascii_text.push_str("[Il!1i]");
} else if ['o', 'c'].contains(&c) {
ascii_text.push_str("[oc]");
} else if ['é', 'á', 'd'].contains(&c) {
ascii_text.push_str("[éád]");
} else if ['.'].contains(&c) {
if prev_chars.len() > 3 {
let prev_char = prev_chars[prev_chars.len() - 1];