Files
wp-materialize/src/markdown_utils.py

111 lines
4.0 KiB
Python

from __future__ import annotations
import re
import markdown as md_lib
import subprocess
from .errors import ValidationIssue
_HEADING_RE = re.compile(r"^(#{1,6})(\s+.*)$")
def extract_title(markdown_text: str, level: int, strict: bool, context: str, issues: list[ValidationIssue]) -> tuple[str, str] | None:
pattern = re.compile(rf"^{'#' * level}\s+(.*)$", re.MULTILINE)
matches = list(pattern.finditer(markdown_text))
if strict and len(matches) != 1:
issues.append(
ValidationIssue(
f"Expected exactly one level-{level} heading, found {len(matches)}",
context=context,
)
)
return None
if not matches:
issues.append(ValidationIssue(f"Missing level-{level} heading", context=context))
return None
match = matches[0]
title = match.group(1).strip()
if not title:
issues.append(ValidationIssue("Heading title cannot be empty", context=context))
return None
lines = markdown_text.splitlines()
line_index = markdown_text[: match.start()].count("\n")
lines.pop(line_index)
body = "\n".join(lines)
body = _promote_headings(body)
return title, body
def _promote_headings(text: str) -> str:
promoted_lines = []
for line in text.splitlines():
match = _HEADING_RE.match(line)
if not match:
promoted_lines.append(line)
continue
hashes, rest = match.groups()
level = len(hashes)
if level > 1:
level -= 1
promoted_lines.append("#" * level + rest)
return "\n".join(promoted_lines)
def convert_markdown(
markdown_text: str,
context: str,
issues: list[ValidationIssue],
renderer: str = "default",
hard_line_breaks: bool = False,
) -> str | None:
if renderer == "default":
try:
extensions = ["extra"]
if hard_line_breaks:
extensions.append("nl2br")
return md_lib.markdown(markdown_text, extensions=extensions, output_format="html5")
except Exception as exc: # pragma: no cover - depends on markdown internals
issues.append(ValidationIssue(f"Markdown conversion failed: {exc}", context=context))
return None
if renderer == "py-gfm":
try:
import mdx_gfm
except Exception as exc: # pragma: no cover - dependency missing
issues.append(ValidationIssue(f"py-gfm is not available: {exc}", context=context))
return None
extension_class = getattr(mdx_gfm, "GithubFlavoredMarkdownExtension", None)
if extension_class is None:
issues.append(ValidationIssue("py-gfm extension not found: GithubFlavoredMarkdownExtension", context=context))
return None
try:
extensions = [extension_class()]
if hard_line_breaks:
extensions.append("nl2br")
return md_lib.markdown(markdown_text, extensions=extensions, output_format="html5")
except Exception as exc: # pragma: no cover - depends on markdown internals
issues.append(ValidationIssue(f"Markdown conversion failed: {exc}", context=context))
return None
if renderer == "pandoc":
try:
result = subprocess.run(
["pandoc", f"--from={'markdown+hard_line_breaks' if hard_line_breaks else 'markdown'}", "--to=html5"],
input=markdown_text,
text=True,
capture_output=True,
check=True,
)
return result.stdout
except FileNotFoundError as exc:
issues.append(ValidationIssue(f"pandoc is not available: {exc}", context=context))
return None
except subprocess.CalledProcessError as exc:
stderr = exc.stderr.strip() if exc.stderr else ""
issues.append(ValidationIssue(f"Pandoc conversion failed: {stderr}", context=context))
return None
issues.append(ValidationIssue(f"Unknown renderer: {renderer}", context=context))
return None