stop cleaning common chinese punctuations
This commit is contained in:
1 parent
5eab3d28df
commit
558aed1888
3 files changed
+6
-6
No files matched your search
@@ -927,7 +927,7 @@
|
||||
cleanedText = cleanedText.replace(/\\.\\s'/g, ".'");
|
||||
cleanedText = cleanedText.replace(/(?<!\\w)\['\]+(?!\\w)/g, '');
|
||||
cleanedText = cleanedText.replace(/"/g, "'");
|
||||
cleanedText = cleanedText.replace(/[^a-zA-Z0-9\s.,;:!?\-'"$À-ÿ\u0400-\u04FF\u0150\u0151\u0170\u0171\u0900-\u097F\u3040-\u309F\u30A0-\u30FF\u4E00-\u9FFF\u3400-\u4DBF\uF900-\uFAFF\u0600-\u06FF\u0750-\u077F\uFB50-\uFDFF\uFE70-\uFEFF\uAC00-\uD7A3\u1100-\u11FF\u3130-\u318F]/g, '');
|
||||
cleanedText = cleanedText.replace(/[^a-zA-Z0-9\s.,;:!?\-'"$À-ÿ\u0400-\u04FF\u0150\u0151\u0170\u0171\u0900-\u097F\u2018\u2019\u201C\u201D\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(/-\\s/g, '; ');
|
||||
cleanedText = cleanedText.replace(/--/g, '; ');
|
||||
let sentences = cleanedText.split(/(?<=\[.!?:\])\\s+/);
|
||||
|
||||
Reference in new issue
Block a user