Function _remove_doc_from_pages

openkb/agent/compiler.py:1298–1378

Update or delete pages in ``page_dir`` affected by removing a document. For each ``{page_dir}/*.md`` whose frontmatter ``sources:`` lists ``summaries/{doc_name}``: - Remove that source from the frontmatter list. - Remove any ``- [[summaries/{doc_name}]]`` entries from the ``#

(
    wiki_dir: Path,
    doc_name: str,
    *,
    page_dir: str,
    keep_empty: bool = False,
)

def _remove_doc_from_pages(
    wiki_dir: Path,
    doc_name: str,
    *,
    page_dir: str,
    keep_empty: bool = False,
) -> dict[str, list[str]]:
    """Update or delete pages in ``page_dir`` affected by removing a document.

    For each ``{page_dir}/*.md`` whose frontmatter ``sources:`` lists
    ``summaries/{doc_name}``:

    - Remove that source from the frontmatter list.
    - Remove any ``- [[summaries/{doc_name}]]`` entries from the
      ``## Related Documents`` section.
    - Remove any standalone ``See also: [[summaries/{doc_name}]]`` lines
      (left by ``_add_related_link``).
    - If the ``sources:`` list becomes empty AND ``keep_empty`` is False,
      delete the page entirely.

    Shared by the concept and entity removal wrappers so the cleanup (in
    particular the standalone ``See also:`` strip) can never drift between
    the two page types.

    Returns ``{"modified": [slugs...], "deleted": [slugs...]}``.
    """
    pages_dir = wiki_dir / page_dir
    if not pages_dir.is_dir():
        return {"modified": [], "deleted": []}

    source_file = f"summaries/{doc_name}.md"
    bare_source = f"summaries/{doc_name}"
    link = f"[[{bare_source}]]"

    modified: list[str] = []
    deleted: list[str] = []

    for path in sorted(pages_dir.glob("*.md")):
        text = path.read_text(encoding="utf-8")
        # Cheap filter: skip pages that don't reference the doc at all.
        if source_file not in text and bare_source not in text:
            continue

        new_text, sources_empty = _remove_source_from_frontmatter(text, source_file)

        # Drop the doc's entry from the "## Related Documents" section.
        if link in new_text:
            lines = new_text.split("\n")
            while _remove_section_entry(lines, "## Related Documents", link):
                pass
            new_text = "\n".join(lines)

        # Drop standalone "See also: [[summaries/{doc_name}]]" lines.
        # The dominant form (written by ``_add_related_link``) is a
        # paragraph: preceded by a blank line and trailed by either a
        # newline or end-of-string. The first regex matches that shape
        # exactly, preserving one trailing newline so paragraph spacing
        # in surrounding content survives.