feat: add Gitea action to update language usage stats in profile README.md

Co-authored-by: aider (o3) <aider@aider.chat>
2025-08-13 11:15:41 -04:00
commit b64c743108
2 changed files with 130 additions and 0 deletions
@@ -0,0 +1,37 @@
+name: Update Language Stats
+
+on:
+  schedule:
+    - cron: "0 6 * * *"          # run every day at 06:00 UTC
+  workflow_dispatch:             # allow manual runs
+  push:
+    paths:
+      - "scripts/language_stats.py"
+
+jobs:
+  lang-stats:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+
+      - name: Install Python deps
+        run: sudo apt-get update && sudo apt-get install -y python3 python3-pip
+
+      - name: Run language stats script
+        env:
+          GITEA_BASE_URL: ${{ secrets.GITEA_BASE_URL }}
+          GITEA_TOKEN:    ${{ secrets.GITEA_TOKEN }}
+          GITEA_USERNAME: ${{ secrets.GITEA_USERNAME }}
+        run: python3 scripts/language_stats.py
+
+      - name: Commit and push changes
+        run: |
+          git config --global user.name  "lang-stats-bot"
+          git config --global user.email "bot@example.com"
+          git add .profile/README.md
+          if git diff --cached --quiet; then
+            echo "No changes to commit"
+          else
+            git commit -m "chore(profile): update language stats"
+            git push
+          fi
@@ -0,0 +1,93 @@
+#!/usr/bin/env python3
+"""
+Gitea Language Stats Action
+Calculates the percentage of every programming language used
+in all repositories of a given account and writes / updates
+a markdown table inside `.profile/README.md` delimited by the
+markers  <!--LANG_STATS_START--> … <!--LANG_STATS_END-->.
+
+Required environment variables
+--------------------------------
+GITEA_BASE_URL   e.g. https://gitea.example.com
+GITEA_TOKEN      personal access-token with `repo` scope
+GITEA_USERNAME   the account to analyse
+"""
+import os
+import sys
+import requests
+from collections import defaultdict
+
+BASE_URL   = os.getenv("GITEA_BASE_URL", "").rstrip("/")
+TOKEN      = os.getenv("GITEA_TOKEN")
+USERNAME   = os.getenv("GITEA_USERNAME")
+
+if not BASE_URL or not TOKEN or not USERNAME:
+    sys.exit("GITEA_BASE_URL, GITEA_TOKEN and GITEA_USERNAME must be set")
+
+session = requests.Session()
+session.headers["Authorization"] = f"token {TOKEN}"
+
+# ---------- collect repositories ----------
+page = 1
+repos = []
+while True:
+    resp = session.get(
+        f"{BASE_URL}/api/v1/users/{USERNAME}/repos",
+        params={"page": page, "limit": 50},
+        timeout=30,
+    )
+    resp.raise_for_status()
+    batch = resp.json()
+    if not batch:
+        break
+    repos.extend(batch)
+    page += 1
+
+# ---------- aggregate language bytes ----------
+totals: dict[str, int] = defaultdict(int)
+
+for repo in repos:
+    langs = session.get(
+        f"{BASE_URL}/api/v1/repos/{USERNAME}/{repo['name']}/languages",
+        timeout=30,
+    ).json()
+    for lang, bytes_ in langs.items():
+        totals[lang] += bytes_
+
+total_bytes = sum(totals.values())
+if total_bytes == 0:
+    sys.exit("No language data returned from API.")
+
+# ---------- build markdown table ----------
+pairs = sorted(totals.items(), key=lambda x: x[1], reverse=True)
+
+lines = [
+    "## 📊 Language Usage\n",
+    "| Language | Percent |\n",
+    "|----------|---------|\n",
+]
+for lang, nbytes in pairs:
+    pct = nbytes * 100 / total_bytes
+    bar = "█" * int(pct / 2)  # up to 50 chars
+    lines.append(f"| {lang} | {pct:5.1f}% {bar} |\n")
+
+block = "<!--LANG_STATS_START-->\n" + "".join(lines) + "<!--LANG_STATS_END-->\n"
+
+# ---------- patch .profile/README.md ----------
+readme_path = ".profile/README.md"
+os.makedirs(".profile", exist_ok=True)
+if not os.path.exists(readme_path):
+    with open(readme_path, "w", encoding="utf-8") as fh:
+        fh.write(block)
+else:
+    with open(readme_path, "r+", encoding="utf-8") as fh:
+        content = fh.read()
+        if "<!--LANG_STATS_START-->" in content and "<!--LANG_STATS_END-->" in content:
+            pre  = content.split("<!--LANG_STATS_START-->")[0]
+            post = content.split("<!--LANG_STATS_END-->")[-1]
+            content = pre + block + post
+        else:
+            content = content.rstrip() + "\n\n" + block
+        fh.seek(0)
+        fh.write(content)
+        fh.truncate()