File size: 13,592 Bytes
167596f | 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 | """
Batch and Parallel Document Parsing
This module provides functionality for processing multiple documents in parallel,
with progress reporting and error handling.
"""
import asyncio
import logging
from concurrent.futures import ThreadPoolExecutor, as_completed
from pathlib import Path
from typing import Dict, List, Optional, Tuple
from dataclasses import dataclass
import time
from tqdm import tqdm
from .parser import MineruParser, DoclingParser
@dataclass
class BatchProcessingResult:
"""Result of batch processing operation"""
successful_files: List[str]
failed_files: List[str]
total_files: int
processing_time: float
errors: Dict[str, str]
output_dir: str
@property
def success_rate(self) -> float:
"""Calculate success rate as percentage"""
if self.total_files == 0:
return 0.0
return (len(self.successful_files) / self.total_files) * 100
def summary(self) -> str:
"""Generate a summary of the batch processing results"""
return (
f"Batch Processing Summary:\n"
f" Total files: {self.total_files}\n"
f" Successful: {len(self.successful_files)} ({self.success_rate:.1f}%)\n"
f" Failed: {len(self.failed_files)}\n"
f" Processing time: {self.processing_time:.2f} seconds\n"
f" Output directory: {self.output_dir}"
)
class BatchParser:
"""
Batch document parser with parallel processing capabilities
Supports processing multiple documents concurrently with progress tracking
and comprehensive error handling.
"""
def __init__(
self,
parser_type: str = "mineru",
max_workers: int = 4,
show_progress: bool = True,
timeout_per_file: int = 300,
skip_installation_check: bool = False,
):
"""
Initialize batch parser
Args:
parser_type: Type of parser to use ("mineru" or "docling")
max_workers: Maximum number of parallel workers
show_progress: Whether to show progress bars
timeout_per_file: Timeout in seconds for each file
skip_installation_check: Skip parser installation check (useful for testing)
"""
self.parser_type = parser_type
self.max_workers = max_workers
self.show_progress = show_progress
self.timeout_per_file = timeout_per_file
self.logger = logging.getLogger(__name__)
# Initialize parser
if parser_type == "mineru":
self.parser = MineruParser()
elif parser_type == "docling":
self.parser = DoclingParser()
else:
raise ValueError(f"Unsupported parser type: {parser_type}")
# Check parser installation (optional)
if not skip_installation_check:
if not self.parser.check_installation():
self.logger.warning(
f"{parser_type.title()} parser installation check failed. "
f"This may be due to package conflicts. "
f"Use skip_installation_check=True to bypass this check."
)
# Don't raise an error, just warn - the parser might still work
def get_supported_extensions(self) -> List[str]:
"""Get list of supported file extensions"""
return list(
self.parser.OFFICE_FORMATS
| self.parser.IMAGE_FORMATS
| self.parser.TEXT_FORMATS
| {".pdf"}
)
def filter_supported_files(
self, file_paths: List[str], recursive: bool = True
) -> List[str]:
"""
Filter file paths to only include supported file types
Args:
file_paths: List of file paths or directories
recursive: Whether to search directories recursively
Returns:
List of supported file paths
"""
supported_extensions = set(self.get_supported_extensions())
supported_files = []
for path_str in file_paths:
path = Path(path_str)
if path.is_file():
if path.suffix.lower() in supported_extensions:
supported_files.append(str(path))
else:
self.logger.warning(f"Unsupported file type: {path}")
elif path.is_dir():
if recursive:
# Recursively find all files
for file_path in path.rglob("*"):
if (
file_path.is_file()
and file_path.suffix.lower() in supported_extensions
):
supported_files.append(str(file_path))
else:
# Only files in the directory (not subdirectories)
for file_path in path.glob("*"):
if (
file_path.is_file()
and file_path.suffix.lower() in supported_extensions
):
supported_files.append(str(file_path))
else:
self.logger.warning(f"Path does not exist: {path}")
return supported_files
def process_single_file(
self, file_path: str, output_dir: str, parse_method: str = "auto", **kwargs
) -> Tuple[bool, str, Optional[str]]:
"""
Process a single file
Args:
file_path: Path to the file to process
output_dir: Output directory
parse_method: Parsing method
**kwargs: Additional parser arguments
Returns:
Tuple of (success, file_path, error_message)
"""
try:
start_time = time.time()
# Create file-specific output directory
file_name = Path(file_path).stem
file_output_dir = Path(output_dir) / file_name
file_output_dir.mkdir(parents=True, exist_ok=True)
# Parse the document
content_list = self.parser.parse_document(
file_path=file_path,
output_dir=str(file_output_dir),
method=parse_method,
**kwargs,
)
processing_time = time.time() - start_time
self.logger.info(
f"Successfully processed {file_path} "
f"({len(content_list)} content blocks, {processing_time:.2f}s)"
)
return True, file_path, None
except Exception as e:
error_msg = f"Failed to process {file_path}: {str(e)}"
self.logger.error(error_msg)
return False, file_path, error_msg
def process_batch(
self,
file_paths: List[str],
output_dir: str,
parse_method: str = "auto",
recursive: bool = True,
**kwargs,
) -> BatchProcessingResult:
"""
Process multiple files in parallel
Args:
file_paths: List of file paths or directories to process
output_dir: Base output directory
parse_method: Parsing method for all files
recursive: Whether to search directories recursively
**kwargs: Additional parser arguments
Returns:
BatchProcessingResult with processing statistics
"""
start_time = time.time()
# Filter to supported files
supported_files = self.filter_supported_files(file_paths, recursive)
if not supported_files:
self.logger.warning("No supported files found to process")
return BatchProcessingResult(
successful_files=[],
failed_files=[],
total_files=0,
processing_time=0.0,
errors={},
output_dir=output_dir,
)
self.logger.info(f"Found {len(supported_files)} files to process")
# Create output directory
output_path = Path(output_dir)
output_path.mkdir(parents=True, exist_ok=True)
# Process files in parallel
successful_files = []
failed_files = []
errors = {}
# Create progress bar if requested
pbar = None
if self.show_progress:
pbar = tqdm(
total=len(supported_files),
desc=f"Processing files ({self.parser_type})",
unit="file",
)
try:
with ThreadPoolExecutor(max_workers=self.max_workers) as executor:
# Submit all tasks
future_to_file = {
executor.submit(
self.process_single_file,
file_path,
output_dir,
parse_method,
**kwargs,
): file_path
for file_path in supported_files
}
# Process completed tasks
for future in as_completed(
future_to_file, timeout=self.timeout_per_file
):
success, file_path, error_msg = future.result()
if success:
successful_files.append(file_path)
else:
failed_files.append(file_path)
errors[file_path] = error_msg
if pbar:
pbar.update(1)
except Exception as e:
self.logger.error(f"Batch processing failed: {str(e)}")
# Mark remaining files as failed
for future in future_to_file:
if not future.done():
file_path = future_to_file[future]
failed_files.append(file_path)
errors[file_path] = f"Processing interrupted: {str(e)}"
if pbar:
pbar.update(1)
finally:
if pbar:
pbar.close()
processing_time = time.time() - start_time
# Create result
result = BatchProcessingResult(
successful_files=successful_files,
failed_files=failed_files,
total_files=len(supported_files),
processing_time=processing_time,
errors=errors,
output_dir=output_dir,
)
# Log summary
self.logger.info(result.summary())
return result
async def process_batch_async(
self,
file_paths: List[str],
output_dir: str,
parse_method: str = "auto",
recursive: bool = True,
**kwargs,
) -> BatchProcessingResult:
"""
Async version of batch processing
Args:
file_paths: List of file paths or directories to process
output_dir: Base output directory
parse_method: Parsing method for all files
recursive: Whether to search directories recursively
**kwargs: Additional parser arguments
Returns:
BatchProcessingResult with processing statistics
"""
# Run the sync version in a thread pool
loop = asyncio.get_event_loop()
return await loop.run_in_executor(
None,
self.process_batch,
file_paths,
output_dir,
parse_method,
recursive,
**kwargs,
)
def main():
"""Command-line interface for batch parsing"""
import argparse
parser = argparse.ArgumentParser(description="Batch document parsing")
parser.add_argument("paths", nargs="+", help="File paths or directories to process")
parser.add_argument("--output", "-o", required=True, help="Output directory")
parser.add_argument(
"--parser",
choices=["mineru", "docling"],
default="mineru",
help="Parser to use",
)
parser.add_argument(
"--method",
choices=["auto", "txt", "ocr"],
default="auto",
help="Parsing method",
)
parser.add_argument(
"--workers", type=int, default=4, help="Number of parallel workers"
)
parser.add_argument(
"--no-progress", action="store_true", help="Disable progress bar"
)
parser.add_argument(
"--recursive",
action="store_true",
default=True,
help="Search directories recursively",
)
parser.add_argument(
"--timeout", type=int, default=300, help="Timeout per file (seconds)"
)
args = parser.parse_args()
# Configure logging
logging.basicConfig(
level=logging.INFO,
format="%(asctime)s - %(name)s - %(levelname)s - %(message)s",
)
try:
# Create batch parser
batch_parser = BatchParser(
parser_type=args.parser,
max_workers=args.workers,
show_progress=not args.no_progress,
timeout_per_file=args.timeout,
)
# Process files
result = batch_parser.process_batch(
file_paths=args.paths,
output_dir=args.output,
parse_method=args.method,
recursive=args.recursive,
)
# Print summary
print("\n" + result.summary())
# Exit with error code if any files failed
if result.failed_files:
return 1
return 0
except Exception as e:
print(f"Error: {str(e)}")
return 1
if __name__ == "__main__":
exit(main())
|