data(brand): require source urls for brand records

Author: Seungpyo1007

README.md

@@ -12,20 +12,20 @@ static-dump generator live in
 
 ## Layout
 
-```
-data/brand/<slug>.json                                  # e.g. data/brand/samsung.json
-data/soc/<manufacturer>/<slug>.json                     # data/soc/qualcomm/snapdragon-8-elite.json
-data/smartphone/<brand>/<slug>.json                     # data/smartphone/samsung/galaxy-s25.json
-data/gpu/<manufacturer>/<year>/<segment>/<slug>.json    # data/gpu/nvidia/2025/consumer/geforce-rtx-5090.json
-data/cpu/<manufacturer>/<year>/<segment>/<slug>.json    # data/cpu/intel/2023/consumer/core-i9-14900k.json
+```text
+data/brand/<country>/<slug>.json                       # e.g. data/brand/kr/samsung.json
+data/soc/<manufacturer>/<year>/<slug>.json             # data/soc/qualcomm/2024/snapdragon-8-elite.json
+data/smartphone/<brand>/<year>/<slug>.json             # data/smartphone/samsung/2025/galaxy-s25.json
+data/gpu/<manufacturer>/<year>/<segment>/<slug>.json   # data/gpu/nvidia/2025/consumer/geforce-rtx-5090.json
+data/cpu/<manufacturer>/<year>/<segment>/<slug>.json   # data/cpu/intel/2023/consumer/core-i9-14900k.json
 ```
 
 All paths use singular folder names. Slugs are kebab-case and unique within each category.
 
-The Astro site lives under `site/` and is the deploy target for GitHub Pages —
-it consumes the static JSON dump produced by TechEngine's `weekly-refresh` workflow.
+The Astro site lives under `site/` and is the deploy target for GitHub Pages. It
+consumes the static JSON dump produced by TechEngine's `weekly-refresh` workflow.
 
-## Self-check
+## Self-Check
 
 A lightweight bundled validator lives at `app/validate.py`. It runs on every PR via
 [`validate-data.yml`](.github/workflows/validate-data.yml) and is also chained into
@@ -35,15 +35,16 @@ the heavier TechEngine validation workflow as a downstream job.
 python -m app.validate
 ```
 
-The validator uses only the Python standard library — no install step required.
+The validator uses only the Python standard library; no install step required.
 
 ## Contributing
 
 Open a PR with the new/updated JSON file. The PR template walks through what to
-include. The validator must pass and `source_urls` must cite at least one canonical
+include. The validator must pass. All records (`brand`, `soc`, `smartphone`,
+`gpu`, and `cpu`) must include `source_urls` with at least one canonical
 reference (vendor product page, Wikipedia infobox, datasheet).
 
 ## License
 
-Data is licensed **CC-BY-SA 4.0** — attribute "Data from TechAPI" and share alike.
+Data is licensed **CC-BY-SA 4.0**; attribute "Data from TechAPI" and share alike.
 The bundled validator code is [MIT](LICENSE).

app/validate.py

@@ -17,7 +17,7 @@
 
 SLUG_RE = re.compile(r"^[a-z0-9]+(?:-[a-z0-9]+)*$")
 
-BRAND_REQUIRED = {"slug", "name", "country", "categories"}
+BRAND_REQUIRED = {"slug", "name", "country", "categories", "source_urls"}
 BRAND_CATEGORIES = {
     "smartphone-oem",
     "soc-designer",
@@ -78,7 +78,7 @@ def _load(subdir: str) -> list[tuple[str, dict[str, Any]]]:
     if not path.exists():
         return []
     return [
-        (str(f.relative_to(DATA_DIR)), json.loads(f.read_text(encoding="utf-8")))
+        (str(f.relative_to(DATA_DIR)), json.loads(f.read_text(encoding="utf-8-sig")))
         for f in sorted(path.rglob("*.json"))  # recurse into brand subfolders
     ]
 
@@ -127,6 +127,14 @@ def _check_unique_slugs(
             seen[slug] = fname
 
 
+def _check_source_urls(name: str, record: dict[str, Any], errors: list[str]) -> None:
+    urls = record.get("source_urls")
+    if not isinstance(urls, list) or not urls or not all(
+        isinstance(url, str) and url.startswith(("http://", "https://")) for url in urls
+    ):
+        errors.append(f"{name}: source_urls must be a non-empty list of http(s) URL strings")
+
+
 def validate() -> list[str]:
     errors: list[str] = []
 
@@ -150,6 +158,7 @@ def validate() -> list[str]:
 
     for fname, rec in brands:
         _check_required(fname, rec, BRAND_REQUIRED, errors)
+        _check_source_urls(fname, rec, errors)
         _check_slug(fname, rec.get("slug"), errors)
         if "founded_year" in rec:
             _check_range(fname, "founded_year", rec["founded_year"], 1800, 2100, errors)
@@ -182,6 +191,7 @@ def validate() -> list[str]:
 
     for fname, rec in socs:
         _check_required(fname, rec, SOC_REQUIRED, errors)
+        _check_source_urls(fname, rec, errors)
         _check_slug(fname, rec.get("slug"), errors)
         if "release_date" in rec:
             _check_date(fname, rec["release_date"], errors)
@@ -191,6 +201,7 @@ def validate() -> list[str]:
 
     for fname, rec in phones:
         _check_required(fname, rec, PHONE_REQUIRED, errors)
+        _check_source_urls(fname, rec, errors)
         _check_slug(fname, rec.get("slug"), errors)
         if "release_date" in rec:
             _check_date(fname, rec["release_date"], errors)
@@ -206,6 +217,7 @@ def validate() -> list[str]:
 
     for fname, rec in gpus:
         _check_required(fname, rec, GPU_REQUIRED, errors)
+        _check_source_urls(fname, rec, errors)
         _check_slug(fname, rec.get("slug"), errors)
         if "release_date" in rec:
             _check_date(fname, rec["release_date"], errors)
@@ -219,6 +231,7 @@ def validate() -> list[str]:
     valid_segments = {"desktop", "laptop", "hedt", "server"}
     for fname, rec in cpus:
         _check_required(fname, rec, CPU_REQUIRED, errors)
+        _check_source_urls(fname, rec, errors)
         _check_slug(fname, rec.get("slug"), errors)
         if "release_date" in rec:
             _check_date(fname, rec["release_date"], errors)
@@ -236,6 +249,10 @@ def validate() -> list[str]:
 
 
 def run() -> int:
+    try:
+        sys.stdout.reconfigure(encoding="utf-8")  # type: ignore[union-attr]
+    except Exception:
+        pass
     errors = validate()
     if errors:
         print(f"❌ Data validation failed ({len(errors)} issue(s)):")

data/brand/at/emporia.json

@@ -3,8 +3,11 @@
   "name": "Emporia Telecom",
   "country": "AT",
   "founded_year": 1991,
-  "logo_url": null,
+  "logo_url": "https://commons.wikimedia.org/wiki/Special:FilePath/Emporia.jpg",
   "website": "https://www.emporia.eu",
+  "source_urls": [
+    "https://commons.wikimedia.org/wiki/Special:FilePath/Emporia.jpg"
+  ],
   "categories": [
     "smartphone-oem"
   ],

data/brand/ca/ati.json

@@ -5,6 +5,9 @@
   "founded_year": 1985,
   "logo_url": "https://commons.wikimedia.org/wiki/Special:FilePath/ATI_Technologies_%28logo%29.svg",
   "website": null,
+  "source_urls": [
+    "https://commons.wikimedia.org/wiki/Special:FilePath/ATI_Technologies_%28logo%29.svg"
+  ],
   "categories": [
     "gpu-designer",
     "defunct"

data/brand/ca/blackberry.json

@@ -5,6 +5,9 @@
   "founded_year": 1984,
   "logo_url": "https://commons.wikimedia.org/wiki/Special:FilePath/Blackberry_Logo.svg",
   "website": "https://www.blackberry.com",
+  "source_urls": [
+    "https://www.blackberry.com"
+  ],
   "categories": [
     "smartphone-oem",
     "defunct"

data/brand/ca/matrox.json

@@ -5,6 +5,9 @@
   "founded_year": 1976,
   "logo_url": "https://commons.wikimedia.org/wiki/Special:FilePath/Matrox_Electronic_Systems_logo.svg",
   "website": "https://www.matrox.com",
+  "source_urls": [
+    "https://www.matrox.com"
+  ],
   "categories": [
     "gpu-designer"
   ],

data/brand/ch/stmicroelectronics.json

@@ -5,6 +5,9 @@
   "founded_year": 1987,
   "logo_url": "https://commons.wikimedia.org/wiki/Special:FilePath/ST_logo_2020_blue_V.svg",
   "website": "https://www.st.com",
+  "source_urls": [
+    "https://www.st.com"
+  ],
   "categories": [
     "chipset-maker",
     "soc-designer"

data/brand/cn/alcatel.json

@@ -5,6 +5,9 @@
   "founded_year": 2004,
   "logo_url": "https://commons.wikimedia.org/wiki/Special:FilePath/Alcatel_logo_2016.svg",
   "website": "https://www.alcatelmobile.com",
+  "source_urls": [
+    "https://www.alcatelmobile.com"
+  ],
   "categories": [
     "smartphone-oem",
     "sub-brand"

data/brand/cn/allwinner.json

@@ -5,6 +5,9 @@
   "founded_year": 2007,
   "logo_url": "https://commons.wikimedia.org/wiki/Special:FilePath/Allwinner_logo.png",
   "website": "https://www.allwinnertech.com",
+  "source_urls": [
+    "https://www.allwinnertech.com"
+  ],
   "categories": [
     "soc-designer"
   ],

data/brand/cn/amlogic.json

@@ -5,6 +5,9 @@
   "founded_year": 1995,
   "logo_url": "https://commons.wikimedia.org/wiki/Special:FilePath/Amlogic_logo.svg",
   "website": "https://www.amlogic.com",
+  "source_urls": [
+    "https://www.amlogic.com"
+  ],
   "categories": [
     "soc-designer"
   ],