initial commit: codex draft

src/markdown_utils.py

@@ -0,0 +1,62 @@
+from __future__ import annotations
+
+import re
+
+import markdown as md_lib
+
+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]) -> str | None:
+    try:
+        return md_lib.markdown(markdown_text, extensions=["extra"], 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