Skip to content

FIX html escape regex #394

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 2 commits into from
Aug 29, 2023
Merged

FIX html escape regex #394

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
e181734
FIX html escape regex
Wauplin Aug 29, 2023
3e20700
doc
Wauplin Aug 29, 2023
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
10 changes: 5 additions & 5 deletions src/doc_builder/convert_md_to_mdx.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -22,6 +22,11 @@


_re_doctest_flags = re.compile(r"^(>>>.*\S)(\s+)# doctest:\s+\+[A-Z_]+\s*$", flags=re.MULTILINE)
_re_lt_html = re.compile(r"<(((!(DOCTYPE|--))|((\/\s*)?[a-z]+))[^>]*?)>", re.IGNORECASE)
_re_lcub_svelte = re.compile(
r"<(Question|Tip|Added|Changed|Deprecated|DocNotebookDropdown|CourseFloatingBanner|FrameworkSwitch|audio|PipelineIcon|PipelineTag)(((?!<(Question|Tip|Added|Changed|Deprecated|DocNotebookDropdown|CourseFloatingBanner|FrameworkSwitch|audio|PipelineIcon|PipelineTag)).)*)>|&amp;lcub;(#if|:else}|/if})",
re.DOTALL,
)


def convert_md_to_mdx(md_text, page_info):
Expand Down Expand Up @@ -68,18 +73,13 @@ def convert_special_chars(text):
"""
Convert { and < that have special meanings in MDX.
"""
_re_lcub_svelte = re.compile(
r"<(Question|Tip|Added|Changed|Deprecated|DocNotebookDropdown|CourseFloatingBanner|FrameworkSwitch|audio|PipelineIcon|PipelineTag)(((?!<(Question|Tip|Added|Changed|Deprecated|DocNotebookDropdown|CourseFloatingBanner|FrameworkSwitch|audio|PipelineIcon|PipelineTag)).)*)>|&amp;lcub;(#if|:else}|/if})",
re.DOTALL,
)
text = text.replace("{", "&amp;lcub;")
# We don't want to escape `{` that are part of svelte syntax
text = _re_lcub_svelte.sub(lambda match: match[0].replace("&amp;lcub;", "{"), text)
# We don't want to replace those by the HTML code, so we temporarily set them at LTHTML
# source is a special tag, it can be standalone (html tag) or closing (doc tag)

# Temporarily replace all valid HTML tags with LTHTML
_re_lt_html = re.compile(r"<(((!(DOCTYPE|--))|((\/\s*)?\w+))[^>]*?)>", re.DOTALL)
text = re.sub(_re_lt_html, r"LTHTML\1>", text)
# Encode remaining < symbols
text = text.replace("<", "&amp;lt;")
Expand Down
10 changes: 10 additions & 0 deletions tests/test_convert_md_to_mdx.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -122,6 +122,16 @@ def test_convert_special_chars(self):
comment = "<!-- comment -->"
self.assertEqual(convert_special_chars(comment), comment)

comment = "<!-- multi line\ncomment -->"
self.assertEqual(convert_special_chars(comment), comment)

# Regression test for https://github.com/huggingface/doc-builder/pull/394
# '<' must not be considered an HTML tag before a number
self.assertEqual(
convert_special_chars("something <5MB something else -> here"),
"something &amp;lt;5MB something else -> here",
)

def test_convert_img_links(self):
page_info = {"package_name": "transformers", "version": "v4.10.0", "language": "fr"}

Expand Down