CERBERUS/awesome-python
1
0
Fork 0
mirror of https://github.com/vinta/awesome-python.git synced 2026-08-27 04:07:39 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 3

feat: replace regex README parser with markdown-it-py AST parser

Browse source 
Introduce parse_readme() which uses MarkdownIt to build a full AST
instead of line-by-line regex matching. The function splits the document
at the thematic break, groups nodes by h2 heading, extracts category
descriptions from leading italic paragraphs, and separates the
Categories, Resources, and Contributing sections cleanly.

Add markdown-it-py==4.0.0 (+ mdurl) as a runtime dependency to support
the new parser.

Tests cover section counts, names, slugs, descriptions, content
presence, boundary conditions (no separator, no description), and mixed
description markup.

Co-Authored-By: Claude <noreply@anthropic.com>
This commit is contained in:
Vinta Chen 2026-03-18 17:21:49 +08:00
parent 5fa7c7d1a6
commit 1c67c9f0e6
No known key found for this signature in database
GPG key ID: B93DE4F003C33630
4 changed files with 325 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

23
uv.lock generated
View file

@ -22,6 +22,7 @@ dependencies = [
{ name = "httpx" },
{ name = "jinja2" },
{ name = "markdown" },
{ name = "markdown-it-py" },
]
[package.dev-dependencies]
@ -35,6 +36,7 @@ requires-dist = [
{ name = "httpx", specifier = "==0.28.1" },
{ name = "jinja2", specifier = "==3.1.6" },
{ name = "markdown", specifier = "==3.10.2" },
{ name = "markdown-it-py", specifier = "==4.0.0" },
]
[package.metadata.requires-dev]
@ -137,6 +139,18 @@ wheels = [
{ url = "https://files.pythonhosted.org/packages/de/1f/77fa3081e4f66ca3576c896ae5d31c3002ac6607f9747d2e3aa49227e464/markdown-3.10.2-py3-none-any.whl", hash = "sha256:e91464b71ae3ee7afd3017d9f358ef0baf158fd9a298db92f1d4761133824c36", size = 108180, upload-time = "2026-02-09T14:57:25.787Z" },
]
[[package]]
name = "markdown-it-py"
version = "4.0.0"
source = { registry = "https://pypi.org/simple" }
dependencies = [
{ name = "mdurl" },
]
sdist = { url = "https://files.pythonhosted.org/packages/5b/f5/4ec618ed16cc4f8fb3b701563655a69816155e79e24a17b651541804721d/markdown_it_py-4.0.0.tar.gz", hash = "sha256:cb0a2b4aa34f932c007117b194e945bd74e0ec24133ceb5bac59009cda1cb9f3", size = 73070, upload-time = "2025-08-11T12:57:52.854Z" }
wheels = [
{ url = "https://files.pythonhosted.org/packages/94/54/e7d793b573f298e1c9013b8c4dade17d481164aa517d1d7148619c2cedbf/markdown_it_py-4.0.0-py3-none-any.whl", hash = "sha256:87327c59b172c5011896038353a81343b6754500a08cd7a4973bb48c6d578147", size = 87321, upload-time = "2025-08-11T12:57:51.923Z" },
]
[[package]]
name = "markupsafe"
version = "3.0.3"
@ -189,6 +203,15 @@ wheels = [
{ url = "https://files.pythonhosted.org/packages/70/bc/6f1c2f612465f5fa89b95bead1f44dcb607670fd42891d8fdcd5d039f4f4/markupsafe-3.0.3-cp314-cp314t-win_arm64.whl", hash = "sha256:32001d6a8fc98c8cb5c947787c5d08b0a50663d139f1305bac5885d98d9b40fa", size = 14146, upload-time = "2025-09-27T18:37:28.327Z" },
]
[[package]]
name = "mdurl"
version = "0.1.2"
source = { registry = "https://pypi.org/simple" }
sdist = { url = "https://files.pythonhosted.org/packages/d6/54/cfe61301667036ec958cb99bd3efefba235e65cdeb9c84d24a8293ba1d90/mdurl-0.1.2.tar.gz", hash = "sha256:bb413d29f5eea38f31dd4754dd7377d4465116fb207585f97bf925588687c1ba", size = 8729, upload-time = "2022-08-14T12:40:10.846Z" }
wheels = [
{ url = "https://files.pythonhosted.org/packages/b3/38/89ba8ad64ae25be8de66a6d463314cf1eb366222074cfda9ee839c56a4b4/mdurl-0.1.2-py3-none-any.whl", hash = "sha256:84008a41e51615a49fc9966191ff91509e3c40b939176e643fd50a5c2196b8f8", size = 9979, upload-time = "2022-08-14T12:40:09.779Z" },
]
[[package]]
name = "packaging"
version = "26.0"