andre/gpt_academic
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

修复匹配单个美元符号的问题

Browse Source
This commit is contained in:
w_xiaolizu
2023-06-18 21:01:38 +08:00
parent 2333b4e8ef
commit 5ad71f39da
1 changed files with 7 additions and 13 deletions
Download Patch File Download Diff File Expand all files Collapse all files

20
toolbox.py
View File

@ -311,13 +311,6 @@ def markdown_convertion(txt):
} }
find_equation_pattern = r'<script type="math/tex(?:.*?)>(.*?)</script>' find_equation_pattern = r'<script type="math/tex(?:.*?)>(.*?)</script>'
def tex2mathml_catch_exception(content, *args, **kwargs):
try:
content = tex2mathml(content, *args, **kwargs)
except:
content = content
return content
def replace_math_no_render(match): def replace_math_no_render(match):
content = match.group(1) content = match.group(1)
if 'mode=display' in match.group(0): if 'mode=display' in match.group(0):
@ -333,10 +326,10 @@ def markdown_convertion(txt):
content = content.replace('\\begin{aligned}', '\\begin{array}') content = content.replace('\\begin{aligned}', '\\begin{array}')
content = content.replace('\\end{aligned}', '\\end{array}') content = content.replace('\\end{aligned}', '\\end{array}')
content = content.replace('&', ' ') content = content.replace('&', ' ')
content = tex2mathml_catch_exception(content, display="block") content = tex2mathml(content, display="block")
return content return content
else: else:
return tex2mathml_catch_exception(content) return tex2mathml(content)
def markdown_bug_hunt(content): def markdown_bug_hunt(content):
""" """
@ -356,17 +349,18 @@ def markdown_convertion(txt):
else: else:
return False return False
if ('$' in txt) and no_code(txt): # 有$标识的公式符号，且没有代码段```的标识 if ('$$' in txt) and no_code(txt): # 有$标识的公式符号，且没有代码段```的标识
# convert everything to html format # convert everything to html format
split = markdown.markdown(text='---') split = markdown.markdown(text='---')
convert_stage_1 = markdown.markdown(text=txt, extensions=['mdx_math', 'fenced_code', 'tables', 'sane_lists'], txt = re.sub(r'\$\$((?:.|\n)*?)\$\$', lambda match: '$$' + re.sub(r'\n+', '</br>', match.group(1)) + '$$', txt)
extension_configs=markdown_extension_configs) convert_stage_1 = markdown.markdown(text=txt, extensions=['mdx_math', 'fenced_code', 'tables', 'sane_lists'], extension_configs=markdown_extension_configs)
convert_stage_1 = markdown_bug_hunt(convert_stage_1) convert_stage_1 = markdown_bug_hunt(convert_stage_1)
# re.DOTALL: Make the '.' special character match any character at all, including a newline; without this flag, '.' will match anything except a newline. Corresponds to the inline flag (?s). # re.DOTALL: Make the '.' special character match any character at all, including a newline; without this flag, '.' will match anything except a newline. Corresponds to the inline flag (?s).
# 1. convert to easy-to-copy tex (do not render math) # 1. convert to easy-to-copy tex (do not render math)
convert_stage_2_1, n = re.subn(find_equation_pattern, replace_math_no_render, convert_stage_1, flags=re.DOTALL) convert_stage_2_1, n = re.subn(find_equation_pattern, replace_math_no_render, convert_stage_1, flags=re.DOTALL)
# 2. convert to rendered equation # 2. convert to rendered equation
convert_stage_2_2, n = re.subn(find_equation_pattern, replace_math_render, convert_stage_1, flags=re.DOTALL) convert_stage_1_resp = convert_stage_1.replace('</br>', '')
convert_stage_2_2, n = re.subn(find_equation_pattern, replace_math_render, convert_stage_1_resp, flags=re.DOTALL)
# cat them together # cat them together
return pre + convert_stage_2_1 + f'{split}' + convert_stage_2_2 + suf return pre + convert_stage_2_1 + f'{split}' + convert_stage_2_2 + suf
else: else: