Spaces:
Sleeping
Sleeping
File size: 19,383 Bytes
7dfe46c |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 |
import logging
import sqlite3
from pathlib import Path
from typing import Dict, List, Any, Optional
from dataclasses import dataclass, asdict
from datetime import datetime
import json
import os
import sys
sys.path.append(os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
from src.document_processor import ProcessingStatus, DocumentType
try:
from logger.custom_logger import CustomLoggerTracker
custom_log = CustomLoggerTracker()
logger = custom_log.get_logger("meta_manager")
except ImportError:
# Fallback to standard logging if custom logger not available
logger = logging.getLogger("meta_manager")
@dataclass
class DocumentMetadata:
"""Metadata for a processed document."""
document_id: str
filename: str
file_path: str
file_type: str
upload_timestamp: datetime
processing_status: ProcessingStatus
total_chunks: int
file_size: int
checksum: str
error_message: Optional[str] = None
processing_time: Optional[float] = None
metadata_json: Optional[str] = None # Additional metadata as JSON
@dataclass
class CitationInfo:
"""Citation information for a document chunk."""
chunk_id: str
document_id: str
source_document: str
location_reference: str
extraction_method: str
confidence_level: float
page_number: Optional[int] = None
worksheet_name: Optional[str] = None
cell_range: Optional[str] = None
section_title: Optional[str] = None
class MetadataManager:
"""
SQLite-based metadata manager for document tracking and citation management.
This manager provides persistent storage for document metadata, processing status,
and citation information with efficient querying capabilities.
"""
def __init__(self, config: Dict[str, Any]):
"""
Initialize the metadata manager.
Args:
config: Configuration dictionary containing database settings
"""
self.config = config
self.db_path = config.get('metadata_db_path', './data/metadata.db')
# Ensure database directory exists
Path(self.db_path).parent.mkdir(parents=True, exist_ok=True)
# Initialize database
self._init_database()
logger.info(f"Metadata manager initialized with database: {self.db_path}")
def _init_database(self):
"""Initialize the SQLite database with required tables."""
try:
with sqlite3.connect(self.db_path) as conn:
cursor = conn.cursor()
# Create documents table
cursor.execute('''
CREATE TABLE IF NOT EXISTS documents (
document_id TEXT PRIMARY KEY,
filename TEXT NOT NULL,
file_path TEXT NOT NULL,
file_type TEXT NOT NULL,
upload_timestamp TEXT NOT NULL,
processing_status TEXT NOT NULL,
total_chunks INTEGER DEFAULT 0,
file_size INTEGER DEFAULT 0,
checksum TEXT,
error_message TEXT,
processing_time REAL,
metadata_json TEXT,
created_at TEXT DEFAULT CURRENT_TIMESTAMP,
updated_at TEXT DEFAULT CURRENT_TIMESTAMP
)
''')
# Create citations table
cursor.execute('''
CREATE TABLE IF NOT EXISTS citations (
id INTEGER PRIMARY KEY AUTOINCREMENT,
chunk_id TEXT NOT NULL,
document_id TEXT NOT NULL,
source_document TEXT NOT NULL,
location_reference TEXT NOT NULL,
extraction_method TEXT NOT NULL,
confidence_level REAL NOT NULL,
page_number INTEGER,
worksheet_name TEXT,
cell_range TEXT,
section_title TEXT,
created_at TEXT DEFAULT CURRENT_TIMESTAMP,
FOREIGN KEY (document_id) REFERENCES documents (document_id)
)
''')
# Create indexes for efficient querying
cursor.execute('CREATE INDEX IF NOT EXISTS idx_documents_status ON documents (processing_status)')
cursor.execute('CREATE INDEX IF NOT EXISTS idx_documents_type ON documents (file_type)')
cursor.execute('CREATE INDEX IF NOT EXISTS idx_citations_document ON citations (document_id)')
cursor.execute('CREATE INDEX IF NOT EXISTS idx_citations_chunk ON citations (chunk_id)')
conn.commit()
logger.debug("Database tables initialized successfully")
except Exception as e:
logger.error(f"Failed to initialize database: {e}")
raise
def store_document_metadata(self, doc_id: str, metadata: DocumentMetadata) -> bool:
"""
Store document metadata in the database.
Args:
doc_id: Document ID
metadata: DocumentMetadata object
Returns:
True if successful, False otherwise
"""
try:
with sqlite3.connect(self.db_path) as conn:
cursor = conn.cursor()
# Convert datetime to ISO string
upload_timestamp = metadata.upload_timestamp.isoformat()
cursor.execute('''
INSERT OR REPLACE INTO documents (
document_id, filename, file_path, file_type, upload_timestamp,
processing_status, total_chunks, file_size, checksum,
error_message, processing_time, metadata_json, updated_at
) VALUES (?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?)
''', (
doc_id,
metadata.filename,
metadata.file_path,
metadata.file_type,
upload_timestamp,
metadata.processing_status.value,
metadata.total_chunks,
metadata.file_size,
metadata.checksum,
metadata.error_message,
metadata.processing_time,
metadata.metadata_json,
datetime.now().isoformat()
))
conn.commit()
logger.debug(f"Stored metadata for document: {doc_id}")
return True
except Exception as e:
logger.error(f"Failed to store document metadata: {e}")
return False
def get_document_metadata(self, doc_id: str) -> Optional[DocumentMetadata]:
"""
Retrieve document metadata by ID.
Args:
doc_id: Document ID
Returns:
DocumentMetadata object or None if not found
"""
try:
with sqlite3.connect(self.db_path) as conn:
cursor = conn.cursor()
cursor.execute('''
SELECT document_id, filename, file_path, file_type, upload_timestamp,
processing_status, total_chunks, file_size, checksum,
error_message, processing_time, metadata_json
FROM documents WHERE document_id = ?
''', (doc_id,))
row = cursor.fetchone()
if row:
return DocumentMetadata(
document_id=row[0],
filename=row[1],
file_path=row[2],
file_type=row[3],
upload_timestamp=datetime.fromisoformat(row[4]),
processing_status=ProcessingStatus(row[5]),
total_chunks=row[6],
file_size=row[7],
checksum=row[8],
error_message=row[9],
processing_time=row[10],
metadata_json=row[11]
)
return None
except Exception as e:
logger.error(f"Failed to get document metadata: {e}")
return None
def update_document_status(self, doc_id: str, status: ProcessingStatus,
error_message: Optional[str] = None,
processing_time: Optional[float] = None) -> bool:
"""
Update document processing status.
Args:
doc_id: Document ID
status: New processing status
error_message: Optional error message
processing_time: Optional processing time
Returns:
True if successful, False otherwise
"""
try:
with sqlite3.connect(self.db_path) as conn:
cursor = conn.cursor()
cursor.execute('''
UPDATE documents
SET processing_status = ?, error_message = ?, processing_time = ?, updated_at = ?
WHERE document_id = ?
''', (
status.value,
error_message,
processing_time,
datetime.now().isoformat(),
doc_id
))
conn.commit()
logger.debug(f"Updated status for document {doc_id}: {status.value}")
return True
except Exception as e:
logger.error(f"Failed to update document status: {e}")
return False
def store_citation_info(self, citation: CitationInfo) -> bool:
"""
Store citation information.
Args:
citation: CitationInfo object
Returns:
True if successful, False otherwise
"""
try:
with sqlite3.connect(self.db_path) as conn:
cursor = conn.cursor()
cursor.execute('''
INSERT OR REPLACE INTO citations (
chunk_id, document_id, source_document, location_reference,
extraction_method, confidence_level, page_number,
worksheet_name, cell_range, section_title
) VALUES (?, ?, ?, ?, ?, ?, ?, ?, ?, ?)
''', (
citation.chunk_id,
citation.document_id,
citation.source_document,
citation.location_reference,
citation.extraction_method,
citation.confidence_level,
citation.page_number,
citation.worksheet_name,
citation.cell_range,
citation.section_title
))
conn.commit()
logger.debug(f"Stored citation for chunk: {citation.chunk_id}")
return True
except Exception as e:
logger.error(f"Failed to store citation info: {e}")
return False
def get_citation_info(self, chunk_id: str) -> Optional[CitationInfo]:
"""
Retrieve citation information by chunk ID.
Args:
chunk_id: Chunk ID
Returns:
CitationInfo object or None if not found
"""
try:
with sqlite3.connect(self.db_path) as conn:
cursor = conn.cursor()
cursor.execute('''
SELECT chunk_id, document_id, source_document, location_reference,
extraction_method, confidence_level, page_number,
worksheet_name, cell_range, section_title
FROM citations WHERE chunk_id = ?
''', (chunk_id,))
row = cursor.fetchone()
if row:
return CitationInfo(
chunk_id=row[0],
document_id=row[1],
source_document=row[2],
location_reference=row[3],
extraction_method=row[4],
confidence_level=row[5],
page_number=row[6],
worksheet_name=row[7],
cell_range=row[8],
section_title=row[9]
)
return None
except Exception as e:
logger.error(f"Failed to get citation info: {e}")
return None
def list_documents(self, status: Optional[ProcessingStatus] = None,
file_type: Optional[str] = None,
limit: int = 100) -> List[DocumentMetadata]:
try:
with sqlite3.connect(self.db_path) as conn:
cursor = conn.cursor()
query = '''
SELECT document_id, filename, file_path, file_type, upload_timestamp,
processing_status, total_chunks, file_size, checksum,
error_message, processing_time, metadata_json
FROM documents
'''
conditions = []
params = []
if status:
conditions.append('processing_status = ?')
params.append(status.value)
if file_type:
conditions.append('file_type = ?')
params.append(file_type)
if conditions:
query += ' WHERE ' + ' AND '.join(conditions)
query += ' ORDER BY upload_timestamp DESC LIMIT ?'
params.append(limit)
cursor.execute(query, params)
rows = cursor.fetchall()
documents = []
for row in rows:
documents.append(DocumentMetadata(
document_id=row[0],
filename=row[1],
file_path=row[2],
file_type=row[3],
upload_timestamp=datetime.fromisoformat(row[4]),
processing_status=ProcessingStatus(row[5]),
total_chunks=row[6],
file_size=row[7],
checksum=row[8],
error_message=row[9],
processing_time=row[10],
metadata_json=row[11]
))
return documents
except Exception as e:
logger.error(f"Failed to list documents: {e}")
return []
def delete_document(self, doc_id: str) -> bool:
try:
with sqlite3.connect(self.db_path) as conn:
cursor = conn.cursor()
# Delete citations first (foreign key constraint)
cursor.execute('DELETE FROM citations WHERE document_id = ?', (doc_id,))
# Delete document
cursor.execute('DELETE FROM documents WHERE document_id = ?', (doc_id,))
conn.commit()
logger.info(f"Deleted document and citations: {doc_id}")
return True
except Exception as e:
logger.error(f"Failed to delete document: {e}")
return False
def get_statistics(self) -> Dict[str, Any]:
"""
Get database statistics.
Returns:
Dictionary with database statistics
"""
try:
with sqlite3.connect(self.db_path) as conn:
cursor = conn.cursor()
# Count documents by status
cursor.execute('''
SELECT processing_status, COUNT(*)
FROM documents
GROUP BY processing_status
''')
status_counts = dict(cursor.fetchall())
# Count documents by type
cursor.execute('''
SELECT file_type, COUNT(*)
FROM documents
GROUP BY file_type
''')
type_counts = dict(cursor.fetchall())
# Total statistics
cursor.execute('SELECT COUNT(*) FROM documents')
total_documents = cursor.fetchone()[0]
cursor.execute('SELECT COUNT(*) FROM citations')
total_citations = cursor.fetchone()[0]
cursor.execute('SELECT SUM(total_chunks) FROM documents')
total_chunks = cursor.fetchone()[0] or 0
cursor.execute('SELECT SUM(file_size) FROM documents')
total_file_size = cursor.fetchone()[0] or 0
return {
'total_documents': total_documents,
'total_citations': total_citations,
'total_chunks': total_chunks,
'total_file_size': total_file_size,
'documents_by_status': status_counts,
'documents_by_type': type_counts,
'database_path': self.db_path
}
except Exception as e:
logger.error(f"Failed to get statistics: {e}")
return {'error': str(e)}
def cleanup_orphaned_citations(self) -> int:
"""
Clean up citations that reference non-existent documents.
Returns:
Number of orphaned citations removed
"""
try:
with sqlite3.connect(self.db_path) as conn:
cursor = conn.cursor()
cursor.execute('''
DELETE FROM citations
WHERE document_id NOT IN (SELECT document_id FROM documents)
''')
removed_count = cursor.rowcount
conn.commit()
logger.info(f"Cleaned up {removed_count} orphaned citations")
return removed_count
except Exception as e:
logger.error(f"Failed to cleanup orphaned citations: {e}")
return 0
if __name__=="__main__":
logger.info(f"metadata init ..") |