Fix race condition on GitHub authors (#177)

Co-authored-by: UltralyticsAssistant <web@ultralytics.com>

Author: glenn-jocher

plugin/__init__.py

@@ -1,6 +1,6 @@
 # Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
 
-__version__ = "0.2.3"
+__version__ = "0.2.4"
 
 from .main import MetaPlugin
 from .postprocess import postprocess_site

plugin/postprocess.py

@@ -16,6 +16,7 @@
 
 import plugin.processor as processor
 from plugin.processor import process_html
+from plugin.utils import resolve_all_authors
 
 # Shared worker state for process pools (avoids re-pickling large read-only data per task)
 _WORKER_STATE: dict[str, Any] | None = None
@@ -37,7 +38,6 @@ def _process_file(html_file: Path) -> bool:
         _WORKER_STATE["repo_url"],
         site_url=_WORKER_STATE["site_url"],
         default_image=_WORKER_STATE["default_image"],
-        default_author=_WORKER_STATE["default_author"],
         add_desc=_WORKER_STATE["add_desc"],
         add_image=_WORKER_STATE["add_image"],
         add_keywords=_WORKER_STATE["add_keywords"],
@@ -59,7 +59,6 @@ def process_html_file(
     repo_url: str | None,
     site_url: str = "",
     default_image: str | None = None,
-    default_author: str | None = None,
     add_desc: bool = True,
     add_image: bool = True,
     add_keywords: bool = True,
@@ -114,7 +113,6 @@ def process_html_file(
         git_data=git_data,
         repo_url=repo_url,
         default_image=default_image,
-        default_author=default_author,
         keywords=keywords,
         add_desc=add_desc,
         add_image=add_image,
@@ -184,6 +182,9 @@ def postprocess_site(
     git_data = None
     if (add_authors or add_json_ld) and md_index:
         repo_url, git_data = processor.build_git_map(list(md_index.values()))
+        # Resolve all authors ONCE in main process before spawning workers
+        # This prevents race conditions when workers try to write to the cache file
+        git_data = resolve_all_authors(git_data, default_author=default_author, repo_url=repo_url, verbose=verbose)
 
     progress = TQDM(total=len(html_files), desc="Postprocessing", unit="file", disable=not verbose) if TQDM else None
     # Enable logging only for the synchronous path; pools run without per-task log_fn to remain pickle-safe.
@@ -196,7 +197,6 @@ def postprocess_site(
         repo_url=repo_url,
         site_url=site_url,
         default_image=default_image,
-        default_author=default_author,
         add_desc=add_desc,
         add_image=add_image,
         add_keywords=add_keywords,

plugin/processor.py

@@ -13,11 +13,7 @@
 
 from bs4 import BeautifulSoup
 
-from plugin.utils import (
-    calculate_time_difference,
-    get_github_usernames_from_file,
-    get_youtube_video_ids,
-)
+from plugin.utils import calculate_time_difference, get_youtube_video_ids
 
 today = datetime.now()
 DEFAULT_CREATION_DATE = (today - timedelta(days=365)).strftime("%Y-%m-%d %H:%M:%S +0000")
@@ -30,11 +26,9 @@
 def get_git_info(
     file_path: str,
     add_authors: bool = True,
-    default_author: str | None = None,
     git_data: dict[str, dict[str, Any]] | None = None,
-    repo_url: str | None = None,
 ) -> dict[str, Any]:
-    """Retrieve git information (dates + optional authors) from precomputed git data."""
+    """Retrieve git information (dates + pre-resolved authors) from precomputed git data."""
     file_path = str(Path(file_path).resolve())
     git_info = {
         "creation_date": DEFAULT_CREATION_DATE,
@@ -45,29 +39,12 @@ def get_git_info(
         return git_info
 
     cached = git_data[file_path]
-    git_info.update(
-        {
-            "creation_date": cached.get("creation_date", DEFAULT_CREATION_DATE),
-            "last_modified_date": cached.get("last_modified_date", DEFAULT_MODIFIED_DATE),
-        }
-    )
-
-    if add_authors and cached.get("emails"):
-        git_info["authors"] = sorted(
-            [
-                (
-                    author,
-                    info["url"],
-                    info["changes"],
-                    info["avatar"],
-                )
-                for author, info in get_github_usernames_from_file(
-                    file_path, default_user=default_author, emails=cached["emails"], repo_url=repo_url
-                ).items()
-            ],
-            key=lambda x: x[2],
-            reverse=True,
-        )
+    git_info["creation_date"] = cached.get("creation_date", DEFAULT_CREATION_DATE)
+    git_info["last_modified_date"] = cached.get("last_modified_date", DEFAULT_MODIFIED_DATE)
+
+    # Authors are pre-resolved by resolve_all_authors() in the main process
+    if add_authors and "authors" in cached:
+        git_info["authors"] = cached["authors"]
 
     return git_info
 
@@ -309,7 +286,6 @@ def process_html(
     git_data: dict[str, dict[str, Any]] | None = None,
     repo_url: str | None = None,
     default_image: str | None = None,
-    default_author: str | None = None,
     keywords: str | None = None,
     add_desc: bool = True,
     add_image: bool = True,
@@ -493,9 +469,7 @@ def process_html(
     needs_git = (add_authors or add_json_ld) and src_path
 
     if needs_git:
-        git_info = get_git_info(
-            src_path, add_authors=add_authors, default_author=default_author, git_data=git_data, repo_url=repo_url
-        )
+        git_info = get_git_info(src_path, add_authors=add_authors, git_data=git_data)
 
         # Only render git footer if we have real git history (not placeholder defaults)
         has_real_git_data = (