From 7f261bb5e9ba69d7834dfd88729192d385771218 Mon Sep 17 00:00:00 2001 From: erew123 <35898566+erew123@users.noreply.github.com> Date: Wed, 21 Feb 2024 12:24:11 +0000 Subject: [PATCH] Attempt to allow Chinese character set through --- script.py | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/script.py b/script.py index 53cfef1..0971fba 100644 --- a/script.py +++ b/script.py @@ -663,7 +663,7 @@ def output_modifier(string, state): # Replace multiple exclamation marks, question marks, or other punctuation with a single instance cleaned_part = re.sub(r"([!?.])\1+", r"\1", part) # Further clean to remove any other unwanted characters - cleaned_part = re.sub(r'[^a-zA-Z0-9\s\.,;:!?\-\'"\u0100-\u017F\u0400-\u04FFÀ-ÿ\u0150\u0151\u0170\u0171\$]', '', cleaned_part) + cleaned_part = re.sub(r'[^a-zA-Z0-9\s\.,;:!?\-\'"\u0100-\u017F\u0400-\u04FFÀ-ÿ\u0150\u0151\u0170\u0171\u4E00-\u9FFF\u3400-\u4DBF\u20000-\u2A6DF\$]', '', cleaned_part) # Remove all newline characters (single or multiple) cleaned_part = re.sub(r"\n+", " ", cleaned_part) @@ -690,7 +690,7 @@ def output_modifier(string, state): # Replace multiple instances of certain punctuation marks with a single instance cleaned_part = re.sub(r"([!?.])\1+", r"\1", cleaned_part) # Further clean to remove any other unwanted characters - cleaned_part = re.sub(r'[^a-zA-Z0-9\s\.,;:!?\-\'"\u0100-\u017F\u0400-\u04FFÀ-ÿ\u0150\u0151\u0170\u0171\$]', '', cleaned_part) + cleaned_part = re.sub(r'[^a-zA-Z0-9\s\.,;:!?\-\'"\u0100-\u017F\u0400-\u04FFÀ-ÿ\u0150\u0151\u0170\u0171\u4E00-\u9FFF\u3400-\u4DBF\u20000-\u2A6DF\$]', '', cleaned_part) # Remove all newline characters (single or multiple) cleaned_part = re.sub(r"\n+", " ", cleaned_part) # Process the part and give it a non-character name if being used vai API or standalone.