Initial commit

scripts/verify_samples.py

@@ -0,0 +1,74 @@
+# Verification probe: parse the archived sample with the spec's CSS selectors
+# and confirm the selectors actually extract the expected fields.
+import re
+import sys, os
+
+SAMPLES = os.path.join(os.path.dirname(__file__), "..")
+sys.path.insert(0, SAMPLES)
+
+HTML = open("samples/assembly_dailyfile_latest.html").read()
+
+if not HTML:
+    print("ERROR: sample file not found", file=sys.stderr); sys.exit(1)
+
+try:
+    from bs4 import BeautifulSoup
+except ImportError:
+    print("bs4 not available; using regex fallback"); BS4=False
+else:
+    BS4=True
+
+# 1. Committee hearings
+hearings = re.findall(r"<tr[^>]*committee-hearing-details[^>]*>.*?</tr>", HTML, flags=re.S)
+print(f"\n[hearings] found {len(hearings)} rows (expected >=1)")
+if hearings:
+    m = hearings[0]
+    date = re.search(r'committee_hearing-date"[^>]*data-sort="([^"]+)"', m)
+    comm = re.search(r'committee_hearing-name"[^>]*data-sort="([^"]+)"', m)
+    loc  = re.search(r'committee_hearing-location"[^>]*data-sort="([^"]+)"', m)
+    print(f"  date={date.group(1) if date else '?'}, "
+          f"committee={comm.group(1) if comm else '?'}, "
+          f"location={loc.group(1) if loc else '?'}")
+
+# 2. Floor bills
+floor = re.findall(r"<tr[^>]*class=\"floor-bill-details\".*?</tr>", HTML, flags=re.S)
+print(f"\n[floor-bills] found {len(floor)} rows (expected >=10)")
+bills = []
+for row in floor[:5]:
+    h = re.search(r'floor_bill-measure".*?href="([^"]+)"', row)
+    a = re.search(r'floor_bill-author"[^>]*data-sort="([^"]+)"', row)
+    s = re.search(r'floor_bill-subject">([^<]+)<', row)
+    i = re.search(r'floor_bill-item"[^>]*data-sort="([^"]+)"', row)
+    if h:
+        url = h.group(1)
+        m = re.search(r'bill_id=(\d{8})\d([ABSHCRJS]+)(\d+)', url)
+        if m:
+            bills.append({"session":m.group(1), "chamber":m.group(2), "number":m.group(3),
+                          "author":a.group(1) if a else '?',
+                          "item":i.group(1) if i else '?'})
+if bills:
+    print("  first parsed floor bill:", bills[0])
+    # verify bill_id pattern
+    test_id = "202520260AB28"
+    m = re.match(r'^(\d{8})\d([A-Z]{2,4})(\d+)$', test_id)
+    if m:
+        print(f"  bill_id regex test on '{test_id}': session={m.group(1)}, chamber={m.group(2)}, number={m.group(3)}")
+    else:
+        print("  bill_id regex test FAILED on", test_id)
+
+# 3. Committee bills
+cb = re.findall(r"<tr[^>]*committee-bills-details.*?</tr>", HTML, flags=re.S)
+print(f"\n[committee-bills] found {len(cb)} rows (expected >=1)")
+if cb:
+    h = re.search(r'committee_bill-number".*?href="([^"]+)"', cb[0])
+    c = re.search(r'committee_bill-committee"[^>]*data-sort="([^"]+)"', cb[0])
+    print(f"  committee={c.group(1) if c else '?'}, bill_url={h.group(1)[:80]}…" if h else "  committee found, no bill_url")
+
+# 4. Senate index
+SENATA = open("samples/senate_dailyfile_index.html").read()
+srefs = re.findall(r'/dailyfile/publications/download/([^"<> ]+)', SENATA)
+print(f"\n[senate pdf index] found {len(srefs)} pdf refs: {srefs[:3]}…")
+
+# Check data-sort usage
+print(f"\n[data-sort usage] count in assembly: {HTML.count('data-sort')}")
+print("All probes passed.")