From 02965a7f10e6155e266e0a30e67b5e11c785155e Mon Sep 17 00:00:00 2001
From: Seungpyo1007 <rush94434@gmail.com>
Date: Tue, 15 Sep 2026 11:29:46 +0900
Subject: [PATCH] feat(site): publish history.json with the record count per
 data commit

The build replays every commit that touched data/cpu and writes its date
and record count, so TechAPI's dataset-growth chart can plot this repo
over time. Pages checkout now fetches full history for it.
---
 .github/workflows/deploy-pages.yml |  2 ++
 .gitignore                         |  1 +
 site/build.py                      | 19 +++++++++++++++++++
 3 files changed, 22 insertions(+)

diff --git a/.github/workflows/deploy-pages.yml b/.github/workflows/deploy-pages.yml
index fd75840..d56af16 100644
--- a/.github/workflows/deploy-pages.yml
+++ b/.github/workflows/deploy-pages.yml
@@ -19,6 +19,8 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - uses: actions/checkout@v4
+        with:
+          fetch-depth: 0  # history.json replays every data commit
       - uses: actions/setup-python@v5
         with:
           python-version: "3.12"
diff --git a/.gitignore b/.gitignore
index 3396d45..da2305e 100644
--- a/.gitignore
+++ b/.gitignore
@@ -30,6 +30,7 @@ coverage.xml
 
 # Generated site catalog (rebuilt in CI)
 site/catalog.json
+site/history.json
 
 # Local GitHub setup helpers (not part of the catalog)
 .github-setup/
diff --git a/site/build.py b/site/build.py
index 407097d..a3a05e4 100644
--- a/site/build.py
+++ b/site/build.py
@@ -3,12 +3,28 @@
 from __future__ import annotations
 
 import json
+import subprocess
 import sys
 from pathlib import Path
 
 ROOT = Path(__file__).resolve().parent.parent
 DATA = ROOT / "data" / "cpu"
 OUT = Path(__file__).resolve().parent / "catalog.json"
+HISTORY = Path(__file__).resolve().parent / "history.json"
+
+
+def git(*args: str) -> str:
+    return subprocess.run(["git", *args], cwd=ROOT, check=True, capture_output=True, text=True).stdout
+
+
+def build_history() -> list[dict]:
+    """Record count after every commit that touched data/cpu (needs full clone)."""
+    points = []
+    for line in git("log", "--reverse", "--format=%H %cI", "--", "data/cpu").splitlines():
+        sha, date = line.split(" ", 1)
+        names = git("ls-tree", "-r", "--name-only", sha, "--", "data/cpu").splitlines()
+        points.append({"sha": sha, "date": date, "count": sum(n.endswith(".json") for n in names)})
+    return points
 
 
 def main() -> int:
@@ -34,6 +50,9 @@ def main() -> int:
         )
     OUT.write_text(json.dumps(records, indent=2) + "\n", encoding="utf-8")
     print(f"wrote {OUT} ({len(records)} ES records)")
+    history = build_history()
+    HISTORY.write_text(json.dumps({"points": history}, indent=2) + "\n", encoding="utf-8")
+    print(f"wrote {HISTORY} ({len(history)} points)")
     return 0