Add code to strip markdown before readability

ghrepo.py

@@ -6,6 +6,7 @@
 from base64 import b64decode
 import textstat
 import httpx
+from unmarkdown import unmark
 
 Severity = Literal["ok", "low", "high"]
 Criteria = tuple[str, Severity]
@@ -126,8 +127,9 @@ async def get_readme(full_name: str, token: str | None = None) -> str | None:
 
 def compute_readability(readme_txt: str):
     """Compute readability from readme markdown text."""
-    # TODO: strip markdown before computing readability
-    return textstat.textstat.flesch_reading_ease(readme_txt)
+    # Strip markdown before computing readability.
+    readme_plain = unmark(readme_txt)
+    return textstat.textstat.flesch_reading_ease(readme_plain)
 
 
 async def get_org_repos(org: str, token: str | None = None) -> list[GitHubRepo]:

pyproject.toml

@@ -11,14 +11,12 @@ httpx = "^0.24.1"
 jinja2 = "^3.1.2"
 toml = "^0.10.2"
 textstat = "^0.7.3"
+markdown = "^3.5.1"
 
 [tool.ruff]
 line-length = 100
 
 [tool.ruff.lint]
-# Enable Pyflakes (`F`) and a subset of the pycodestyle (`E`)  codes by default.
-# Unlike Flake8, Ruff doesn't enable pycodestyle warnings (`W`) or
-# McCabe complexity (`C901`) by default.
 select = ["E4", "E7", "E9", "F"]
 ignore = []
 

unmarkdown.py

@@ -0,0 +1,26 @@
+"""Module to convert markdown to plain text. Code based on https://stackoverflow.com/a/54923798"""
+from io import StringIO
+from markdown import Markdown
+
+
+def unmark_element(element, stream=None):
+    """Custom plain output format for markdown."""
+    if stream is None:
+        stream = StringIO()
+    if element.text:
+        stream.write(element.text)
+    for sub in element:
+        unmark_element(sub, stream)
+    if element.tail:
+        stream.write(element.tail)
+    return stream.getvalue()
+
+
+Markdown.output_formats["plain"] = unmark_element
+
+
+def unmark(text):
+    """Convert markdown-formatted text to plain text."""
+    md = Markdown(output_format="plain")
+    md.stripTopLevelTags = False
+    return md.convert(text)