Initial SQL-only 1C adapter baseline

2026-07-22 03:03:47 +03:00
commit e2503b77e7
545 changed files with 184711 additions and 0 deletions
@@ -0,0 +1,115 @@
+from __future__ import annotations
+
+import re
+import urllib.parse
+from typing import Any
+
+
+PLATFORM_DOC_RE = re.compile(r"/db/(v(?:8|83|85)\d*doc)(?:/|$)", flags=re.IGNORECASE)
+BOOKMARK_PATH_RE = re.compile(r"/bookmark/([^/]+)/([^/?#]+)", flags=re.IGNORECASE)
+CONTENT_PATH_RE = re.compile(r"/content/(-?\d+)/(?:hdoc|\d+)", flags=re.IGNORECASE)
+HASH_BOOKMARK_RE = re.compile(r"^#?bookmark:([^:]+):([^:]+)$", flags=re.IGNORECASE)
+HASH_CONTENT_RE = re.compile(r"^#?content:([^:]+):([^:]+)$", flags=re.IGNORECASE)
+
+
+def platform_doc_id_from_url(url: str) -> str | None:
+    match = PLATFORM_DOC_RE.search(urllib.parse.urlparse(url).path)
+    return match.group(1).lower() if match else None
+
+
+def platform_version_from_doc_id(doc_id: str | None) -> str | None:
+    if not doc_id:
+        return None
+    doc_id = doc_id.lower()
+    if doc_id == "v8doc":
+        return "8.x"
+    match = re.fullmatch(r"v83(\d+)doc", doc_id)
+    if match:
+        patch = int(match.group(1))
+        return f"8.3.{patch}"
+    match = re.fullmatch(r"v85(\d+)doc", doc_id)
+    if match:
+        patch = int(match.group(1))
+        return f"8.5.{patch}"
+    match = re.fullmatch(r"v8(\d+)doc", doc_id)
+    if match:
+        patch = int(match.group(1))
+        return f"8.{patch}"
+    return None
+
+
+def platform_version_from_url(url: str) -> str | None:
+    return platform_version_from_doc_id(platform_doc_id_from_url(url))
+
+
+def parse_doc_coordinate(url: str) -> dict[str, str | None]:
+    parsed = urllib.parse.urlparse(url)
+    path = parsed.path
+    fragment = urllib.parse.unquote(parsed.fragment or "")
+    coordinate: dict[str, str | None] = {
+        "platform_doc_id": platform_doc_id_from_url(url),
+        "platform_version": platform_version_from_url(url),
+        "doc_book": None,
+        "doc_bookmark": None,
+        "doc_content_id": None,
+        "doc_coordinate": None,
+    }
+
+    bookmark = BOOKMARK_PATH_RE.search(path)
+    if bookmark:
+        coordinate["doc_book"] = bookmark.group(1)
+        coordinate["doc_bookmark"] = bookmark.group(2)
+    else:
+        hash_bookmark = HASH_BOOKMARK_RE.match(fragment)
+        if hash_bookmark:
+            coordinate["doc_book"] = hash_bookmark.group(1)
+            coordinate["doc_bookmark"] = hash_bookmark.group(2)
+
+    content = CONTENT_PATH_RE.search(path)
+    if content:
+        coordinate["doc_content_id"] = content.group(1)
+    else:
+        hash_content = HASH_CONTENT_RE.match(fragment)
+        if hash_content:
+            coordinate["doc_book"] = coordinate["doc_book"] or hash_content.group(1)
+            coordinate["doc_content_id"] = hash_content.group(2)
+
+    parts = [
+        coordinate.get("platform_doc_id"),
+        coordinate.get("doc_book"),
+        coordinate.get("doc_bookmark") or coordinate.get("doc_content_id"),
+    ]
+    if any(parts):
+        coordinate["doc_coordinate"] = ":".join(part or "_" for part in parts)
+    return coordinate
+
+
+def materialize_doc_url(url: str) -> str:
+    parsed = urllib.parse.urlparse(url)
+    fragment = urllib.parse.unquote(parsed.fragment or "")
+    if not fragment:
+        return url
+
+    hash_bookmark = HASH_BOOKMARK_RE.match(fragment)
+    if hash_bookmark:
+        path = parsed.path.rstrip("/") + f"/bookmark/{hash_bookmark.group(1)}/{hash_bookmark.group(2)}"
+        return urllib.parse.urlunparse(parsed._replace(path=path, fragment=""))
+
+    hash_content = HASH_CONTENT_RE.match(fragment)
+    if hash_content:
+        content_id = hash_content.group(2)
+        path = parsed.path.rstrip("/") + f"/content/{content_id}/hdoc"
+        return urllib.parse.urlunparse(parsed._replace(path=path, fragment=""))
+
+    return urllib.parse.urlunparse(parsed._replace(fragment=""))
+
+
+def merge_platform_metadata(record: dict[str, Any], url: str) -> dict[str, Any]:
+    coordinate = parse_doc_coordinate(url)
+    merged = dict(record)
+    for key, value in coordinate.items():
+        if value and not merged.get(key):
+            merged[key] = value
+    if not merged.get("platform_family") and merged.get("platform_doc_id"):
+        merged["platform_family"] = "1C:Enterprise 8"
+    return merged