cb3a876790
stackx category in provenance pies (color #00acc1), landing donut segment + legend explaining the contribution (practitioner Q&A from six SE communities, per-entry CC-BY-SA attribution), 6-source chip/formula/pipeline texts, stats.json stackexchange block, package integration via practitioner-qa.md, repo-wide ATTRIBUTION.md, verify suite (XML spot checks, mapping consistency, attribution links, homepage consistency). Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01PDKeXvpT6tENSvyQGLV1Uq
106 lines
3.4 KiB
Python
106 lines
3.4 KiB
Python
"""Generate stats.json — the single source of truth for every displayed count
|
|
(landing page, marketplace README, reports). Phase 2c: no number is ever
|
|
hard-coded again; whatever the UI shows comes from this file.
|
|
|
|
Writes:
|
|
data/stats.json (versioned artifact)
|
|
<gitea>/custom/public/assets/stats.json (served to the landing page)
|
|
|
|
Run after enrichment/aggregation changes: python pipeline/gen_stats.py
|
|
"""
|
|
import json
|
|
import os
|
|
import sys
|
|
from datetime import datetime
|
|
|
|
sys.path.insert(0, os.path.dirname(__file__))
|
|
|
|
BASE = os.path.join(os.path.dirname(__file__), "..")
|
|
SKILLS = os.path.join(BASE, "skills")
|
|
OUT = os.path.join(BASE, "data", "stats.json")
|
|
ASSETS_OUT = (r"C:\Program Files (x86)\TempoBill\Zeiterfassung.Cloud"
|
|
r"\Tools\gitea\custom\public\assets\stats.json")
|
|
FLAGSHIP = "artificial-intelligence-engineer"
|
|
|
|
|
|
def main():
|
|
total = white = enriched = mapped_links = 0
|
|
flagship = {}
|
|
for slug in os.listdir(SKILLS):
|
|
mp = os.path.join(SKILLS, slug, "manifest.json")
|
|
if not os.path.isfile(mp):
|
|
continue
|
|
try:
|
|
m = json.load(open(mp, encoding="utf-8"))
|
|
except ValueError:
|
|
continue
|
|
total += 1
|
|
if m.get("collar") == "white":
|
|
white += 1
|
|
enr = m.get("enrichment_ai_skills") or {}
|
|
n = enr.get("total_skills", 0)
|
|
if n:
|
|
enriched += 1
|
|
mapped_links += n
|
|
if slug == FLAGSHIP:
|
|
flagship = {
|
|
"slug": slug,
|
|
"ai_skills_total": n,
|
|
"tiers": enr.get("tiers", {}),
|
|
"provenance_items": (m.get("provenance") or {}).get("items", {}),
|
|
}
|
|
|
|
# occupation-to-skill relations + external catalog size
|
|
relations = 0
|
|
try:
|
|
from db import connect
|
|
cn = connect()
|
|
cur = cn.cursor()
|
|
cur.execute("SELECT COUNT(*) FROM esco_occ_skill")
|
|
relations = cur.fetchone()[0]
|
|
cn.close()
|
|
except Exception:
|
|
pass
|
|
ext_sources = ext_skills = 0
|
|
try:
|
|
import p5_enrich_ai_skills as p5
|
|
catalog = p5.load_catalog()
|
|
ext_sources = len(p5.ALL_SOURCES)
|
|
ext_skills = sum(len(v) for v in catalog.values())
|
|
except Exception:
|
|
pass
|
|
|
|
# Stack-Exchange-Wissensschicht (knowledge/): kompilierte Q&A-Einträge
|
|
se = {}
|
|
se_stats_p = os.path.join(BASE, "knowledge", "data", "compile-stats.json")
|
|
if os.path.exists(se_stats_p):
|
|
try:
|
|
cs = json.load(open(se_stats_p, encoding="utf-8"))
|
|
se = {"professions": len(cs),
|
|
"qa_entries": sum(v.get("entries", 0) for v in cs.values())}
|
|
except ValueError:
|
|
pass
|
|
|
|
stats = {
|
|
"generated_at": datetime.now().isoformat(timespec="seconds"),
|
|
"stackexchange": se,
|
|
"total_occupations": total,
|
|
"white_collar": white,
|
|
"occupation_skill_relations": relations,
|
|
"external_sources": ext_sources,
|
|
"external_skills": ext_skills,
|
|
"enriched_packages": enriched,
|
|
"mapped_skill_links": mapped_links,
|
|
"flagship": flagship,
|
|
}
|
|
json.dump(stats, open(OUT, "w", encoding="utf-8"), indent=2)
|
|
try:
|
|
json.dump(stats, open(ASSETS_OUT, "w", encoding="utf-8"), indent=2)
|
|
except OSError as exc:
|
|
print(f"WARN: assets copy failed: {exc}")
|
|
print(json.dumps(stats, indent=1)[:600])
|
|
|
|
|
|
if __name__ == "__main__":
|
|
main()
|