Spaces:
Sleeping
Sleeping
File size: 12,123 Bytes
8f66a5f |
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 |
"""
File processor class for handling dataset file operations
"""
import os
import json
import time
import asyncio
from pathlib import Path
from typing import Dict, List, Optional, Tuple
from datetime import datetime
import aiohttp
from sqlalchemy.orm import Session
from models import ProcessingState, ProcessingStatusEnum
import logging
logger = logging.getLogger(__name__)
class FileProcessor:
"""Object-oriented file processor for dataset integration"""
def __init__(self, processed_files_dir: str = "processed_files"):
"""
Initialize file processor
Args:
processed_files_dir: Directory to store processed files
"""
self.processed_files_dir = Path(processed_files_dir)
self.all_raw_dir = self.processed_files_dir / "all_raw"
self.ato_raw_dir = self.processed_files_dir / "ato_raw"
# Create directories
self.processed_files_dir.mkdir(parents=True, exist_ok=True)
self.all_raw_dir.mkdir(parents=True, exist_ok=True)
self.ato_raw_dir.mkdir(parents=True, exist_ok=True)
async def download_file(
self,
repo_id: str,
filename: str,
local_dir: Path,
token: Optional[str] = None,
) -> Optional[str]:
"""
Download a single file from Hugging Face
Args:
repo_id: Repository ID (e.g., "samfred2/ALL")
filename: File to download
local_dir: Local directory to save file
token: Optional HF token for authentication
Returns:
Path to downloaded file or None if failed
"""
try:
logger.info(f"Downloading {filename} from {repo_id}...")
await asyncio.sleep(1) # Rate limiting
local_path = local_dir / filename
local_path.parent.mkdir(parents=True, exist_ok=True)
url = f"https://huggingface.co/api/datasets/{repo_id}/resolve/main/{filename}"
headers = {"Authorization": f"Bearer {token}"} if token else {}
async with aiohttp.ClientSession() as session:
async with session.get(url, headers=headers) as response:
if response.status != 200:
logger.error(
f"Failed to download {filename}: HTTP {response.status}"
)
return None
content = await response.read()
local_path.write_bytes(content)
logger.info(f"Downloaded to {local_path}")
return str(local_path)
except Exception as e:
logger.error(f"Error downloading {filename}: {e}")
return None
def load_json_file(self, file_path: str) -> Optional[Dict]:
"""
Load and parse JSON file
Args:
file_path: Path to JSON file
Returns:
Parsed JSON data or None if failed
"""
try:
with open(file_path, "r") as f:
return json.load(f)
except Exception as e:
logger.error(f"Error loading JSON from {file_path}: {e}")
return None
def find_matching_all_file(
self, ato_filename: str, all_filenames: List[str]
) -> Optional[str]:
"""
Find matching ALL file for ATO file using suffix matching
Args:
ato_filename: ATO filename to match
all_filenames: List of ALL filenames
Returns:
Matching ALL filename or None
"""
for all_name in all_filenames:
if all_name.endswith(ato_filename):
return all_name
return None
async def list_json_files(
self, repo_id: str, token: Optional[str] = None
) -> List[str]:
"""
List all JSON files in a repository
Args:
repo_id: Repository ID
token: Optional HF token
Returns:
List of JSON filenames
"""
try:
url = f"https://huggingface.co/api/datasets/{repo_id}"
headers = {"Authorization": f"Bearer {token}"} if token else {}
async with aiohttp.ClientSession() as session:
async with session.get(url, headers=headers) as response:
if response.status != 200:
logger.error(f"Failed to list files from {repo_id}")
return []
data = await response.json()
siblings = data.get("siblings", [])
return [
f["rfilename"]
for f in siblings
if f["rfilename"].endswith(".json")
]
except Exception as e:
logger.error(f"Error listing files from {repo_id}: {e}")
return []
async def process_datasets(
self,
all_repo_id: str,
ato_repo_id: str,
hf_token: Optional[str] = None,
max_files: int = 0,
db: Optional[Session] = None,
) -> Dict:
"""
Process datasets: download, match, integrate, and save
Args:
all_repo_id: Source ALL repository ID
ato_repo_id: Source ATO repository ID
hf_token: Optional HF token
max_files: Maximum files to process (0 = all)
db: Database session for state tracking
Returns:
Processing result dictionary
"""
try:
# Update state to downloading
if db:
state = db.query(ProcessingState).first()
if not state:
state = ProcessingState(status=ProcessingStatusEnum.DOWNLOADING)
db.add(state)
else:
state.status = ProcessingStatusEnum.DOWNLOADING
state.started_at = datetime.utcnow()
db.commit()
logger.info("Listing repository files...")
all_files = await self.list_json_files(all_repo_id, hf_token)
ato_files = await self.list_json_files(ato_repo_id, hf_token)
logger.info(f"Found {len(all_files)} files in {all_repo_id}")
logger.info(f"Found {len(ato_files)} files in {ato_repo_id}")
# Match files
logger.info("Matching ATO to ALL files...")
match_map: Dict[str, str] = {}
for ato_file in ato_files:
matching_all = self.find_matching_all_file(ato_file, all_files)
if matching_all:
match_map[ato_file] = matching_all
matched_count = len(match_map)
logger.info(f"Found {matched_count} matching pairs")
if db:
state = db.query(ProcessingState).first()
if state:
state.status = ProcessingStatusEnum.MATCHING
state.total_files = len(ato_files)
state.matched_pairs = matched_count
db.commit()
# Process matched files
logger.info("Processing matched files...")
processed_count = 0
for ato_filename, all_filename in match_map.items():
if max_files > 0 and processed_count >= max_files:
logger.info(f"Reached limit of {max_files} files")
break
logger.info(f"Processing: {ato_filename} <-> {all_filename}")
# Download ATO file
ato_path = await self.download_file(
ato_repo_id, ato_filename, self.ato_raw_dir, hf_token
)
if not ato_path:
continue
ato_data = self.load_json_file(ato_path)
if not ato_data:
continue
# Download ALL file
all_path = await self.download_file(
all_repo_id, all_filename, self.all_raw_dir, hf_token
)
if not all_path:
continue
all_data = self.load_json_file(all_path)
if not all_data:
continue
# Integrate transcription
logger.info("Integrating transcription...")
all_data["transcription_content"] = ato_data
all_data["transcription_content"]["full_course_name"] = all_filename
# Save integrated file
output_path = self.processed_files_dir / all_filename
output_path.parent.mkdir(parents=True, exist_ok=True)
with open(output_path, "w") as f:
json.dump(all_data, f, indent=4)
logger.info(f"Saved integrated file to {output_path}")
processed_count += 1
if db:
state = db.query(ProcessingState).first()
if state:
state.status = ProcessingStatusEnum.INTEGRATING
state.processed_files = processed_count
db.commit()
logger.info("Processing complete")
if db:
state = db.query(ProcessingState).first()
if state:
state.status = ProcessingStatusEnum.COMPLETED
state.completed_at = datetime.utcnow()
db.commit()
return {
"success": True,
"total_files": len(ato_files),
"matched_pairs": matched_count,
"processed_files": processed_count,
}
except Exception as e:
logger.error(f"Processing error: {e}")
if db:
state = db.query(ProcessingState).first()
if state:
state.status = ProcessingStatusEnum.ERROR
state.error_message = str(e)
state.completed_at = datetime.utcnow()
db.commit()
return {
"success": False,
"total_files": 0,
"matched_pairs": 0,
"processed_files": 0,
"error": str(e),
}
def get_processed_files(self) -> List[str]:
"""
Get list of processed files ready for upload
Returns:
List of relative file paths
"""
files = []
def walk_dir(directory: Path, prefix: str = ""):
for item in directory.iterdir():
relative_path = f"{prefix}/{item.name}" if prefix else item.name
if item.is_dir():
walk_dir(item, relative_path)
elif item.suffix == ".json":
files.append(relative_path)
walk_dir(self.processed_files_dir)
return files
def get_file_content(self, filename: str) -> Optional[Dict]:
"""
Get file content for preview
Args:
filename: Relative filename
Returns:
File content or None
"""
file_path = self.processed_files_dir / filename
# Security: prevent directory traversal
try:
file_path.resolve().relative_to(self.processed_files_dir.resolve())
except ValueError:
logger.warning(f"Directory traversal attempt: {filename}")
return None
if not file_path.exists():
return None
return self.load_json_file(str(file_path))
def get_file_size(self, filename: str) -> Optional[int]:
"""
Get file size in bytes
Args:
filename: Relative filename
Returns:
File size or None
"""
file_path = self.processed_files_dir / filename
try:
file_path.resolve().relative_to(self.processed_files_dir.resolve())
except ValueError:
return None
if not file_path.exists():
return None
return file_path.stat().st_size
|