Czech & Turkish character set

This commit is contained in:
erew123 authored and GitHub committed 2024-07-22 09:42:22 +01:00
1 parent a9fc8699d8
commit f1c53866ba
1 file changed
+3 -2
+3 -2
View File
@@ -953,7 +953,8 @@
cleanedText = cleanedText.replace(/\\.\\s'/g, ".'");
cleanedText = cleanedText.replace(/(?<!\\w)\['\]+(?!\\w)/g, '');
cleanedText = cleanedText.replace(/"/g, "'");
cleanedText = cleanedText.replace(/[^a-zA-Z0-9\s.,;:!?\-'"$À-ÿ\u0400-\u04FF\u0150\u0151\u0170\u0171\u0900-\u097F\u2018\u2019\u201C\u201D\u2026\u3001\u3002\u3040-\u309F\u30A0-\u30FF\u4E00-\u9FFF\u3400-\u4DBF\uF900-\uFAFF\u0600-\u06FF\u0750-\u077F\uFB50-\uFDFF\uFE70-\uFEFF\uAC00-\uD7A3\u1100-\u11FF\u3130-\u318F\uFF01\uFF0c\uFF1A\uFF1B\uFF1F]/g, '');
//cleanedText = cleanedText.replace(/[^a-zA-Z0-9\s.,;:!?\-'"$À-ÿ\u0400-\u04FF\u0150\u0151\u0170\u0171\u0900-\u097F\u2018\u2019\u201C\u201D\u2026\u3001\u3002\u3040-\u309F\u30A0-\u30FF\u4E00-\u9FFF\u3400-\u4DBF\uF900-\uFAFF\u0600-\u06FF\u0750-\u077F\uFB50-\uFDFF\uFE70-\uFEFF\uAC00-\uD7A3\u1100-\u11FF\u3130-\u318F\uFF01\uFF0c\uFF1A\uFF1B\uFF1F]/g, '');
cleanedText = cleanedText.replace(/[^a-zA-Z0-9\s.,;:!?\-'"$À-ÿ\u00C0-\u017F\u0400-\u04FF\u0150\u0151\u0170\u0171\u0900-\u097F\u2018\u2019\u201C\u201D\u2026\u3001\u3002\u3040-\u309F\u30A0-\u30FF\u4E00-\u9FFF\u3400-\u4DBF\uF900-\uFAFF\u0600-\u06FF\u0750-\u077F\uFB50-\uFDFF\uFE70-\uFEFF\uAC00-\uD7A3\u1100-\u11FF\u3130-\u318F\uFF01\uFF0c\uFF1A\uFF1B\uFF1F\u011E\u011F\u0130\u0131\u015E\u015F\u00E7\u00C7\u00F6\u00D6]/g, '');
cleanedText = cleanedText.replace(/-\\s/g, '; ');
cleanedText = cleanedText.replace(/--/g, '; ');
// Split by Fullwidth/CJK punctuation regardless of if there are spaces behind them
@@ -2292,4 +2293,4 @@
</script>
</body>
</html>
</html>