Add DB indexes and extract shared query methods to Database class

Add missing indexes on ratings(false_positive), drafts(source), and
draft_authors(person_id) for faster filtering. Extract 12 shared query
methods (false_positive_drafts_raw, non_false_positive_ratings_raw,
false_positive_names, rated_count, gap_count, search_gaps, search_authors,
draft_affiliation_pairs, all_persons_info, category_counts,
draft_author_count_map, source_counts) to eliminate duplicated SQL across
cli.py, data.py, and reports.py.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

src/webui/data.py

@@ -253,12 +253,7 @@ def get_overview_stats(db: Database) -> OverviewStats:
 
 def get_category_counts(db: Database) -> dict[str, int]:
     """Return {category: draft_count} for all categories."""
-    pairs = db.drafts_with_ratings(limit=1000)
-    counts: dict[str, int] = Counter()
-    for _, rating in pairs:
-        for cat in rating.categories:
-            counts[cat] += 1
-    return dict(counts.most_common())
+    return db.category_counts()
 
 
 def get_category_summary(db: Database, category: str) -> dict | None:
@@ -1002,8 +997,7 @@ def _compute_idea_clusters(db: Database) -> dict:
         return {"clusters": [], "scatter": [], "stats": {"total": 0, "clustered": 0, "num_clusters": 0}, "empty": True}
 
     # Exclude ideas from false-positive drafts
-    fp_names = {r[0] for r in db.conn.execute(
-        "SELECT draft_name FROM ratings WHERE false_positive = 1").fetchall()}
+    fp_names = db.false_positive_names()
 
     # Fetch ideas with IDs for metadata lookup
     rows = db.conn.execute("SELECT id, title, description, idea_type, draft_name FROM ideas").fetchall()
@@ -1512,34 +1506,10 @@ def global_search(db: Database, query: str) -> SearchResults:
         })
 
     # 3. Authors via LIKE
-    rows = db.conn.execute(
-        """SELECT person_id, name, affiliation FROM authors
-        WHERE name LIKE ? OR affiliation LIKE ?
-        ORDER BY name LIMIT 50""",
-        (like, like),
-    ).fetchall()
-    for r in rows:
-        results["authors"].append({
-            "person_id": r["person_id"],
-            "name": r["name"],
-            "affiliation": r["affiliation"] or "",
-        })
+    results["authors"] = db.search_authors(q, limit=50)
 
     # 4. Gaps via LIKE
-    rows = db.conn.execute(
-        """SELECT id, topic, description, category, severity FROM gaps
-        WHERE topic LIKE ? OR description LIKE ?
-        ORDER BY id LIMIT 50""",
-        (like, like),
-    ).fetchall()
-    for r in rows:
-        results["gaps"].append({
-            "id": r["id"],
-            "topic": r["topic"],
-            "description": (r["description"] or "")[:200],
-            "category": r["category"],
-            "severity": r["severity"],
-        })
+    results["gaps"] = db.search_gaps(q, limit=50)
 
     return results
 
@@ -2258,24 +2228,12 @@ def get_source_comparison(db: Database) -> dict:
 def get_false_positive_profile(db: Database) -> dict:
     """Profile drafts flagged as false positives."""
     # Get false positives
-    fp_rows = db.conn.execute(
-        """SELECT d.*, r.novelty, r.maturity, r.overlap, r.momentum, r.relevance,
-            r.summary, r.categories as r_categories, r.false_positive
-        FROM drafts d
-        JOIN ratings r ON d.name = r.draft_name
-        WHERE r.false_positive = 1
-        ORDER BY d.name"""
-    ).fetchall()
+    fp_rows = db.false_positive_drafts_raw()
 
     # Get non-FP rated drafts for comparison
-    nonfp_rows = db.conn.execute(
-        """SELECT r.novelty, r.maturity, r.overlap, r.momentum, r.relevance,
-            r.categories as r_categories
-        FROM ratings r
-        WHERE COALESCE(r.false_positive, 0) = 0"""
-    ).fetchall()
+    nonfp_rows = db.non_false_positive_ratings_raw()
 
-    total_rated = db.conn.execute("SELECT COUNT(*) FROM ratings").fetchone()[0]
+    total_rated = db.rated_count()
     total_drafts = db.count_drafts(include_false_positives=True)
 
     # Build FP list
@@ -2720,34 +2678,10 @@ def global_search(db: Database, query: str) -> SearchResults:
         })
 
     # 3. Authors via LIKE
-    rows = db.conn.execute(
-        """SELECT person_id, name, affiliation FROM authors
-        WHERE name LIKE ? OR affiliation LIKE ?
-        ORDER BY name LIMIT 50""",
-        (like, like),
-    ).fetchall()
-    for r in rows:
-        results["authors"].append({
-            "person_id": r["person_id"],
-            "name": r["name"],
-            "affiliation": r["affiliation"] or "",
-        })
+    results["authors"] = db.search_authors(q, limit=50)
 
     # 4. Gaps via LIKE
-    rows = db.conn.execute(
-        """SELECT id, topic, description, category, severity FROM gaps
-        WHERE topic LIKE ? OR description LIKE ?
-        ORDER BY id LIMIT 50""",
-        (like, like),
-    ).fetchall()
-    for r in rows:
-        results["gaps"].append({
-            "id": r["id"],
-            "topic": r["topic"],
-            "description": (r["description"] or "")[:200],
-            "category": r["category"],
-            "severity": r["severity"],
-        })
+    results["gaps"] = db.search_gaps(q, limit=50)
 
     return results
 
@@ -3148,11 +3082,7 @@ def get_complexity_data(db: Database) -> dict:
     """).fetchall()
 
     # Author counts
-    author_counts = {}
-    for row in conn.execute("""
-        SELECT draft_name, COUNT(*) AS cnt FROM draft_authors GROUP BY draft_name
-    """).fetchall():
-        author_counts[row["draft_name"]] = row["cnt"]
+    author_counts = db.draft_author_count_map()
 
     # Citation counts (outgoing refs)
     citation_counts = {}
@@ -3681,24 +3611,12 @@ def get_source_comparison(db: Database) -> dict:
 def get_false_positive_profile(db: Database) -> dict:
     """Profile drafts flagged as false positives."""
     # Get false positives
-    fp_rows = db.conn.execute(
-        """SELECT d.*, r.novelty, r.maturity, r.overlap, r.momentum, r.relevance,
-            r.summary, r.categories as r_categories, r.false_positive
-        FROM drafts d
-        JOIN ratings r ON d.name = r.draft_name
-        WHERE r.false_positive = 1
-        ORDER BY d.name"""
-    ).fetchall()
+    fp_rows = db.false_positive_drafts_raw()
 
     # Get non-FP rated drafts for comparison
-    nonfp_rows = db.conn.execute(
-        """SELECT r.novelty, r.maturity, r.overlap, r.momentum, r.relevance,
-            r.categories as r_categories
-        FROM ratings r
-        WHERE COALESCE(r.false_positive, 0) = 0"""
-    ).fetchall()
+    nonfp_rows = db.non_false_positive_ratings_raw()
 
-    total_rated = db.conn.execute("SELECT COUNT(*) FROM ratings").fetchone()[0]
+    total_rated = db.rated_count()
     total_drafts = db.count_drafts(include_false_positives=True)
 
     # Build FP list
@@ -4142,34 +4060,10 @@ def global_search(db: Database, query: str) -> SearchResults:
         })
 
     # 3. Authors via LIKE
-    rows = db.conn.execute(
-        """SELECT person_id, name, affiliation FROM authors
-        WHERE name LIKE ? OR affiliation LIKE ?
-        ORDER BY name LIMIT 50""",
-        (like, like),
-    ).fetchall()
-    for r in rows:
-        results["authors"].append({
-            "person_id": r["person_id"],
-            "name": r["name"],
-            "affiliation": r["affiliation"] or "",
-        })
+    results["authors"] = db.search_authors(q, limit=50)
 
     # 4. Gaps via LIKE
-    rows = db.conn.execute(
-        """SELECT id, topic, description, category, severity FROM gaps
-        WHERE topic LIKE ? OR description LIKE ?
-        ORDER BY id LIMIT 50""",
-        (like, like),
-    ).fetchall()
-    for r in rows:
-        results["gaps"].append({
-            "id": r["id"],
-            "topic": r["topic"],
-            "description": (r["description"] or "")[:200],
-            "category": r["category"],
-            "severity": r["severity"],
-        })
+    results["gaps"] = db.search_gaps(q, limit=50)
 
     return results