Christian Nennemann
e247bfef8f
Pipeline: - Extract ideas for 38 new drafts → 462 ideas total - Convergence analysis: 132 cross-org convergent ideas (33% rate) - Fetch authors for 102 drafts → 709 authors (up from 403) - Refresh gap analysis: 12 gaps across full 474-draft corpus - Update verified counts with new totals Post 08: - Complete rewrite of "Agents Building the Agent Analysis" (2,953 words) - Covers 3 phases: writing team → review cycle → fix cycle - Meta-irony table mapping team coordination to IETF gap names - Specific examples from dev journal (SQL injection, consent conflation, ideas mismatch) Untracked files committed: - scripts/: backfill-wg-names, classify-unrated, compare-classifiers, download-relevant-text, run-webui - src/ietf_analyzer/classifier.py: two-stage Ollama classifier - src/webui/: analytics (GDPR-compliant), auth, obsidian_export - tests/test_obsidian_export.py (10 tests) - data/reports/: wg-analysis, generated draft for gap #37 Housekeeping: - .gitignore: exclude LaTeX artifacts, stale DBs, analytics.db Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
67 lines
1.9 KiB
Python
67 lines
1.9 KiB
Python
#!/usr/bin/env python3
|
|
"""Backfill working group names by resolving group_uri from Datatracker API."""
|
|
|
|
import sqlite3
|
|
import time
|
|
import httpx
|
|
|
|
DB_PATH = "data/drafts.db"
|
|
|
|
conn = sqlite3.connect(DB_PATH)
|
|
conn.row_factory = sqlite3.Row
|
|
|
|
# Get distinct group_uris that don't have a group name yet
|
|
rows = conn.execute("""
|
|
SELECT DISTINCT group_uri FROM drafts
|
|
WHERE group_uri IS NOT NULL AND group_uri != ''
|
|
AND ("group" IS NULL OR "group" = '')
|
|
""").fetchall()
|
|
|
|
uris = [r["group_uri"] for r in rows]
|
|
print(f"Resolving {len(uris)} unique group URIs...")
|
|
|
|
client = httpx.Client(timeout=30, follow_redirects=True)
|
|
resolved = {}
|
|
|
|
for uri in uris:
|
|
try:
|
|
resp = client.get(f"https://datatracker.ietf.org{uri}", params={"format": "json"})
|
|
resp.raise_for_status()
|
|
data = resp.json()
|
|
acronym = data.get("acronym", "")
|
|
name = data.get("name", "")
|
|
resolved[uri] = acronym or name or ""
|
|
print(f" {uri} -> {resolved[uri]} ({name})")
|
|
time.sleep(0.3)
|
|
except Exception as e:
|
|
print(f" {uri} -> ERROR: {e}")
|
|
resolved[uri] = ""
|
|
|
|
client.close()
|
|
|
|
# Update the database
|
|
for uri, group_name in resolved.items():
|
|
if group_name:
|
|
conn.execute(
|
|
'UPDATE drafts SET "group" = ? WHERE group_uri = ?',
|
|
(group_name, uri),
|
|
)
|
|
|
|
conn.commit()
|
|
|
|
# Show summary
|
|
rows = conn.execute("""
|
|
SELECT "group", COUNT(*) as cnt FROM drafts
|
|
WHERE "group" IS NOT NULL AND "group" != ''
|
|
GROUP BY "group" ORDER BY cnt DESC
|
|
""").fetchall()
|
|
|
|
print(f"\nWorking groups resolved ({len(rows)} groups):")
|
|
for r in rows:
|
|
print(f" {r[0]:30s} {r[1]} drafts")
|
|
|
|
total = conn.execute('SELECT COUNT(*) FROM drafts WHERE "group" IS NOT NULL AND "group" != ""').fetchone()[0]
|
|
none_count = conn.execute('SELECT COUNT(*) FROM drafts WHERE "group" IS NULL OR "group" = ""').fetchone()[0]
|
|
print(f"\nTotal with WG: {total}, individual/unresolved: {none_count}")
|
|
conn.close()
|