Initial release: export 1C Help to Gitea wiki.

Convert Ext/Help/ru.html to Markdown and push to a wiki git repository.

export1c_help/naming.py

@@ -0,0 +1,106 @@
+"""Wiki page titles and Gitea filename encoding."""
+
+from __future__ import annotations
+
+import hashlib
+import re
+from urllib.parse import quote, unquote
+
+from export1c_help.discover import HelpPage
+
+_INVALID = re.compile(r'[\\/:*?"<>|#\[\]]+')
+_SPACES = re.compile(r"\s+")
+_MAX_NAME_BYTES = 180
+
+
+def sanitize_title(title: str) -> str:
+    title = _SPACES.sub(" ", title).strip()
+    title = _INVALID.sub(" ", title)
+    title = _SPACES.sub(" ", title).strip()
+    return title or "untitled"
+
+
+def _truncate_utf8(s: str, max_bytes: int) -> str:
+    raw = s.encode("utf-8")
+    if len(raw) <= max_bytes:
+        return s
+    raw = raw[:max_bytes]
+    while raw:
+        try:
+            return raw.decode("utf-8").rstrip("- ")
+        except UnicodeDecodeError:
+            raw = raw[:-1]
+    return "page"
+
+
+def _short_hash(s: str) -> str:
+    return hashlib.sha1(s.encode("utf-8")).hexdigest()[:8]
+
+
+def wiki_filename(title: str, *, meta_key: str | None = None) -> str:
+    """Unicode wiki slug (spaces → «-»)."""
+    slug = sanitize_title(title).replace(" ", "-")
+    # reserve room for optional -xxxxxxxx suffix
+    slug = _truncate_utf8(slug, _MAX_NAME_BYTES)
+    return f"{slug}.md"
+
+
+def wiki_filename_gitea_legacy(title: str) -> str:
+    slug = sanitize_title(title).replace(" ", "-")
+    slug = _truncate_utf8(slug, 80)
+    return quote(slug, safe="-_.") + ".md"
+
+
+def decode_wiki_filename(name: str) -> str:
+    base = name[:-3] if name.endswith(".md") else name
+    return unquote(base)
+
+
+def assign_titles(
+    pages: list[HelpPage],
+    h1_by_meta: dict[str, str | None],
+) -> tuple[dict[str, str], dict[str, str]]:
+    """
+    Returns (meta_key → title, meta_key → filename).
+
+    Filenames are unique even after UTF-8 truncation.
+    """
+    used_title: set[str] = set()
+    used_file: set[str] = set()
+    titles: dict[str, str] = {}
+    files: dict[str, str] = {}
+
+    for p in pages:
+        h1 = h1_by_meta.get(p.meta_key)
+        base = sanitize_title(h1 or p.synonym or p.meta_key)
+        title = base
+        n = 2
+        while title.casefold() in used_title:
+            if p.is_form and p.form_name and n == 2:
+                title = sanitize_title(f"{base} — {p.form_name}")
+            elif n == 2:
+                title = sanitize_title(f"{base} — {p.object_name}")
+            else:
+                title = sanitize_title(f"{base} ({n})")
+            n += 1
+            if n > 5000:
+                title = sanitize_title(p.meta_key)
+                break
+
+        fname = wiki_filename(title)
+        if fname.casefold() in used_file:
+            stem = fname[:-3]
+            stem = _truncate_utf8(stem, _MAX_NAME_BYTES - 9)
+            fname = f"{stem}-{_short_hash(p.meta_key)}.md"
+        # last-resort unique
+        guard = 0
+        while fname.casefold() in used_file:
+            fname = f"page-{_short_hash(p.meta_key + str(guard))}.md"
+            guard += 1
+
+        used_title.add(title.casefold())
+        used_file.add(fname.casefold())
+        titles[p.meta_key] = title
+        files[p.meta_key] = fname
+
+    return titles, files