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>
66 lines
1.8 KiB
Python
66 lines
1.8 KiB
Python
#!/usr/bin/env python3
|
|
"""Download full text for the 9 classifier-relevant unrated drafts."""
|
|
|
|
import sqlite3
|
|
import time
|
|
import sys
|
|
sys.path.insert(0, "src")
|
|
|
|
import httpx
|
|
from ietf_analyzer.config import Config
|
|
|
|
cfg = Config.load()
|
|
conn = sqlite3.connect(cfg.db_path)
|
|
conn.row_factory = sqlite3.Row
|
|
|
|
# The 9 relevant drafts from classifier
|
|
relevant_names = [
|
|
"draft-bondar-wca",
|
|
"draft-latour-pre-registration",
|
|
"draft-li-trustworthy-routing-discovery",
|
|
"draft-scrm-aiproto-usecases",
|
|
"draft-song-dmsc-problem-statement",
|
|
"draft-wiethuechter-drip-det-moc",
|
|
"draft-wiethuechter-drip-det-tada",
|
|
"draft-zzn-dvs",
|
|
"w3c-cuap",
|
|
]
|
|
|
|
client = httpx.Client(timeout=30, follow_redirects=True)
|
|
|
|
for name in relevant_names:
|
|
row = conn.execute("SELECT name, rev, source, source_url, full_text FROM drafts WHERE name=?", (name,)).fetchone()
|
|
if not row:
|
|
print(f" SKIP {name}: not in DB")
|
|
continue
|
|
if row["full_text"]:
|
|
print(f" SKIP {name}: already has text")
|
|
continue
|
|
|
|
if row["source"] == "w3c":
|
|
url = row["source_url"] or ""
|
|
if not url:
|
|
print(f" SKIP {name}: no source_url for W3C doc")
|
|
continue
|
|
else:
|
|
rev = row["rev"] or "00"
|
|
url = f"https://www.ietf.org/archive/id/{name}-{rev}.txt"
|
|
|
|
print(f" Fetching {name} from {url}...")
|
|
try:
|
|
resp = client.get(url)
|
|
if resp.status_code == 200:
|
|
text = resp.text[:500000] # cap at 500K
|
|
conn.execute("UPDATE drafts SET full_text=? WHERE name=?", (text, name))
|
|
conn.commit()
|
|
print(f" OK ({len(text)} chars)")
|
|
else:
|
|
print(f" FAIL: HTTP {resp.status_code}")
|
|
except Exception as e:
|
|
print(f" ERROR: {e}")
|
|
time.sleep(0.5)
|
|
|
|
client.close()
|
|
conn.close()
|
|
print("\nDone.")
|