Spaces:
Running
Running
File size: 5,758 Bytes
968e24d | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 | # """Create SQLite index for fast paragraph lookup"""
# import sqlite3
# import json
# from pathlib import Path
# from tqdm import tqdm
# def create_sqlite_index():
# print("Creating SQLite index...")
# db_path = Path("data/processed/indexed/paragraphs.db")
# db_path.parent.mkdir(parents=True, exist_ok=True)
# # Create database
# conn = sqlite3.connect(db_path)
# cursor = conn.cursor()
# # Create table
# cursor.execute("""
# CREATE TABLE IF NOT EXISTS paragraphs (
# id TEXT PRIMARY KEY,
# judgment_id TEXT,
# page_no INTEGER,
# text TEXT,
# char_count INTEGER,
# word_count INTEGER
# )
# """)
# cursor.execute("CREATE INDEX IF NOT EXISTS idx_judgment ON paragraphs(judgment_id)")
# # Load data
# index_file = Path("data/processed/indexed/paragraph_index.jsonl")
# with open(index_file, 'r', encoding='utf-8') as f:
# total = sum(1 for _ in f)
# with open(index_file, 'r', encoding='utf-8') as f:
# batch = []
# for line in tqdm(f, total=total, desc="Inserting"):
# p = json.loads(line)
# batch.append((
# p['id'], p['judgment_id'], p['page_no'],
# p['text'], p['char_count'], p['word_count']
# ))
# if len(batch) >= 1000:
# cursor.executemany(
# "INSERT OR REPLACE INTO paragraphs VALUES (?,?,?,?,?,?)",
# batch
# )
# batch = []
# if batch:
# cursor.executemany(
# "INSERT OR REPLACE INTO paragraphs VALUES (?,?,?,?,?,?)",
# batch
# )
# conn.commit()
# conn.close()
# print(f"✓ SQLite index created: {db_path}")
# if __name__ == "__main__":
# create_sqlite_index()
"""
Create SQLite index with section annotations
Source: paragraph_index_with_sections.jsonl
"""
import sqlite3
import json
from pathlib import Path
from tqdm import tqdm
INPUT_INDEX = Path("data/processed/indexed/paragraph_index_with_sections.jsonl")
DB_PATH = Path("data/processed/indexed/paragraphs.db")
def create_sqlite_index():
print("=" * 70)
print("NyayLens – Creating SQLite Index (with Sections)")
print("=" * 70)
DB_PATH.parent.mkdir(parents=True, exist_ok=True)
# Connect to SQLite
conn = sqlite3.connect(DB_PATH)
cursor = conn.cursor()
# Drop existing table (derived data → safe to rebuild)
cursor.execute("DROP TABLE IF EXISTS paragraphs")
# Create table
cursor.execute("""
CREATE TABLE paragraphs (
id TEXT PRIMARY KEY,
judgment_id TEXT,
page_no INTEGER,
text TEXT,
char_count INTEGER,
word_count INTEGER,
section TEXT,
section_conf REAL
)
""")
# Create FTS5 virtual table for fast full-text search (BM25)
cursor.execute("DROP TABLE IF EXISTS paragraphs_fts")
cursor.execute("""
CREATE VIRTUAL TABLE paragraphs_fts USING fts5(
id UNINDEXED,
text,
tokenize='porter unicode61'
)
""")
# Indexes for fast lookup
cursor.execute("CREATE INDEX idx_judgment_id ON paragraphs(judgment_id)")
cursor.execute("CREATE INDEX idx_section ON paragraphs(section)")
cursor.execute("CREATE INDEX idx_judgment_section ON paragraphs(judgment_id, section)")
conn.commit()
# Count total records
with open(INPUT_INDEX, "r", encoding="utf-8") as f:
total = sum(1 for _ in f)
print(f"✓ Inserting {total:,} paragraphs")
# Insert data in batches
batch = []
BATCH_SIZE = 1000
with open(INPUT_INDEX, "r", encoding="utf-8") as f:
for line in tqdm(f, total=total, desc="Inserting"):
p = json.loads(line)
batch.append((
p["id"],
p["judgment_id"],
p.get("page_no", -1),
p["text"],
p.get("char_count", len(p["text"])),
p.get("word_count", len(p["text"].split())),
p.get("section", "unknown"),
p.get("section_conf", 0.0),
))
if len(batch) >= BATCH_SIZE:
cursor.executemany(
"""
INSERT INTO paragraphs
(id, judgment_id, page_no, text, char_count, word_count, section, section_conf)
VALUES (?, ?, ?, ?, ?, ?, ?, ?)
""",
batch
)
# Insert into FTS5 table
fts_batch = [(b[0], b[3]) for b in batch]
cursor.executemany(
"INSERT INTO paragraphs_fts (id, text) VALUES (?, ?)",
fts_batch
)
batch.clear()
if batch:
cursor.executemany(
"""
INSERT INTO paragraphs
(id, judgment_id, page_no, text, char_count, word_count, section, section_conf)
VALUES (?, ?, ?, ?, ?, ?, ?, ?)
""",
batch
)
fts_batch = [(b[0], b[3]) for b in batch]
cursor.executemany(
"INSERT INTO paragraphs_fts (id, text) VALUES (?, ?)",
fts_batch
)
conn.commit()
conn.close()
print("\n✓ SQLite index created successfully")
print(f"✓ Database path: {DB_PATH}")
print("=" * 70)
if __name__ == "__main__":
create_sqlite_index()
|