Spaces:
Build error
Build error
File size: 9,449 Bytes
aa8e38b | 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 | """
PDF processing service that orchestrates extraction, mapping, and filling.
"""
import uuid
import shutil
from pathlib import Path
from typing import Optional
from datetime import datetime
from app.config import settings
from app.extractor import PDFExtractor
from app.ocr import OCRProcessor
from app.mapper import FieldMapper
from app.filler import PDFFiller
from app.utils.logging import get_logger
from app.utils.exceptions import (
PDFProcessorError,
PDFExtractionError,
OCRError,
MappingError,
PDFFillingError,
FileValidationError
)
logger = get_logger(__name__)
class ProcessingSession:
"""Represents a single PDF processing session."""
def __init__(self, session_id: str):
self.session_id = session_id
self.created_at = datetime.utcnow()
self.source_pdf: Optional[Path] = None
self.template_pdf: Optional[Path] = None
self.output_pdf: Optional[Path] = None
self.extracted_data: Optional[dict] = None
self.mapped_fields: Optional[dict] = None
self.status: str = "initialized"
self.errors: list[str] = []
self.warnings: list[str] = []
@property
def session_dir(self) -> Path:
return settings.upload_dir / self.session_id
class PDFProcessorService:
"""
Main service class that coordinates PDF processing.
"""
def __init__(self, mapping_config_path: Optional[Path] = None):
self.extractor = PDFExtractor()
self.filler = PDFFiller()
self.mapper = FieldMapper(config_path=mapping_config_path)
# Initialize OCR (may not be available)
try:
self.ocr = OCRProcessor()
self.ocr_available = self.ocr.is_available()
except Exception as e:
logger.warning(f"OCR not available: {e}")
self.ocr = None
self.ocr_available = False
# Track active sessions
self.sessions: dict[str, ProcessingSession] = {}
def create_session(self) -> ProcessingSession:
"""Create a new processing session."""
session_id = str(uuid.uuid4())
session = ProcessingSession(session_id)
session.session_dir.mkdir(parents=True, exist_ok=True)
self.sessions[session_id] = session
logger.info(f"Created new session: {session_id}")
return session
def get_session(self, session_id: str) -> ProcessingSession:
"""Get an existing session."""
if session_id not in self.sessions:
# Try to restore from disk
session_dir = settings.upload_dir / session_id
if session_dir.exists():
session = ProcessingSession(session_id)
self.sessions[session_id] = session
return session
raise FileValidationError(f"Session not found: {session_id}")
return self.sessions[session_id]
def save_uploaded_file(
self,
session: ProcessingSession,
file_content: bytes,
filename: str,
file_type: str
) -> Path:
"""
Save an uploaded file to the session directory.
Args:
session: Processing session.
file_content: File content as bytes.
filename: Original filename.
file_type: 'source' or 'template'.
Returns:
Path to saved file.
"""
# Validate extension
ext = Path(filename).suffix.lower()
if ext not in settings.allowed_extensions:
raise FileValidationError(
f"Invalid file extension: {ext}. Allowed: {settings.allowed_extensions}"
)
# Validate file size
size_mb = len(file_content) / (1024 * 1024)
if size_mb > settings.max_file_size_mb:
raise FileValidationError(
f"File too large: {size_mb:.2f}MB. Max: {settings.max_file_size_mb}MB"
)
# Save file
safe_filename = f"{file_type}_{filename}"
file_path = session.session_dir / safe_filename
file_path.write_bytes(file_content)
if file_type == "source":
session.source_pdf = file_path
elif file_type == "template":
session.template_pdf = file_path
logger.info(f"Saved {file_type} file: {file_path}")
return file_path
def process(
self,
session: ProcessingSession,
line_numbers: Optional[list[str]] = None,
use_ocr: Optional[bool] = None,
flatten: bool = False
) -> dict:
"""
Process the uploaded PDFs.
Args:
session: Processing session.
line_numbers: Specific line numbers to extract.
use_ocr: Force OCR processing.
flatten: Flatten output PDF form.
Returns:
Processing result dictionary.
"""
if not session.source_pdf:
raise FileValidationError("No source PDF uploaded")
if not session.template_pdf:
raise FileValidationError("No template PDF uploaded")
session.status = "processing"
try:
# Step 1: Extract data from source PDF
extracted = self._extract_data(session, line_numbers, use_ocr)
session.extracted_data = extracted
# Step 2: Map extracted values to form fields
mapped = self.mapper.map_values(extracted["line_values"])
session.mapped_fields = mapped
# Step 3: Fill the template PDF
output_filename = f"filled_{session.session_id}.pdf"
output_path = settings.output_dir / output_filename
self.filler.fill_form(
template_path=session.template_pdf,
output_path=output_path,
field_values=mapped,
flatten=flatten
)
session.output_pdf = output_path
session.status = "completed"
logger.info(f"Processing completed for session {session.session_id}")
return {
"status": "success",
"extracted_data": extracted,
"mapped_fields": mapped,
"output_filename": output_filename
}
except Exception as e:
session.status = "failed"
session.errors.append(str(e))
logger.error(f"Processing failed for session {session.session_id}: {e}")
raise
def _extract_data(
self,
session: ProcessingSession,
line_numbers: Optional[list[str]] = None,
use_ocr: Optional[bool] = None
) -> dict:
"""Extract data from source PDF."""
# First try text extraction
has_text = self.extractor.has_text_content(session.source_pdf)
if has_text and not use_ocr:
# Use text extraction
result = self.extractor.extract_all_data(session.source_pdf, line_numbers)
result["extraction_method"] = "text"
elif self.ocr_available:
# Use OCR
logger.info("Using OCR for extraction")
text = self.ocr.process_pdf(session.source_pdf)
line_values = self.extractor.extract_line_values(text, line_numbers)
result = {
"text": text,
"line_values": line_values,
"has_text": False,
"extraction_method": "ocr"
}
else:
# No text and no OCR available
session.warnings.append("PDF appears to be scanned but OCR is not available")
result = self.extractor.extract_all_data(session.source_pdf, line_numbers)
result["extraction_method"] = "text_fallback"
# Add text preview (first 500 chars)
if result.get("text"):
result["text_preview"] = result["text"][:500]
return result
def get_output_path(self, session: ProcessingSession) -> Optional[Path]:
"""Get the output PDF path for a session."""
if session.output_pdf and session.output_pdf.exists():
return session.output_pdf
return None
def get_template_fields(self, session: ProcessingSession) -> dict:
"""Get form fields from the template PDF."""
if not session.template_pdf:
raise FileValidationError("No template PDF uploaded")
return self.filler.get_form_fields(session.template_pdf)
def update_mapping(self, line_number: str, field_name: str, description: str = "") -> None:
"""Update field mapping."""
self.mapper.add_mapping(line_number, field_name, description)
def get_all_mappings(self) -> dict:
"""Get all current mappings."""
return self.mapper.get_all_mappings()
def save_mapping_config(self, path: Optional[Path] = None) -> None:
"""Save current mappings to config file."""
if path is None:
path = settings.config_dir / settings.default_mapping_file
self.mapper.save_config(path)
def cleanup_session(self, session_id: str) -> None:
"""Clean up session files."""
if session_id in self.sessions:
session = self.sessions[session_id]
if session.session_dir.exists():
shutil.rmtree(session.session_dir)
del self.sessions[session_id]
logger.info(f"Cleaned up session: {session_id}")
# Global service instance
processor_service = PDFProcessorService()
|