File size: 8,449 Bytes
08615f0 6cf3d0d 08615f0 6cf3d0d 08615f0 23fc6bf 08615f0 23fc6bf 6cf3d0d 08615f0 23fc6bf 6cf3d0d 08615f0 8740e76 08615f0 8740e76 08615f0 |
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 |
"""
Utility functions for the IITM LLM Quiz Solver.
"""
import re
import json
import logging
from typing import Optional, Dict, Any
from urllib.parse import urlparse, urljoin
# Configure logging
logging.basicConfig(
level=logging.INFO,
format='%(asctime)s - %(name)s - %(levelname)s - %(message)s'
)
logger = logging.getLogger(__name__)
def extract_submit_url(text: str, base_url: str) -> Optional[str]:
"""
Extract submit URL from page text.
Looks for patterns like:
- "Submit your answer to: https://example.com/submit"
- "Submit to: https://example.com/submit"
- "URL: https://example.com/submit"
Args:
text: The page text content
base_url: Base URL for relative URL resolution
Returns:
Extracted submit URL or None
"""
# Common patterns for submit URLs
patterns = [
r'[Ss]ubmit\s+(?:your\s+)?(?:answer\s+)?(?:to|at|via):\s*(https?://[^\s<>"\'\)]+)',
r'[Ss]ubmit\s+[Tt]o:\s*(https?://[^\s<>"\'\)]+)',
r'[Pp]ost\s+(?:to|at|JSON\s+to):\s*(https?://[^\s<>"\'\)]+)', # "POST to JSON to https://..."
r'[Pp]ost\s+to\s+JSON\s+to\s*(https?://[^\s<>"\'\)]+)', # "POST to JSON to https://..."
r'[Uu][Rr][Ll]:\s*(https?://[^\s<>"\'\)]+)',
r'[Pp]ost\s+(?:to|at):\s*(https?://[^\s<>"\'\)]+)',
r'[Ss]end\s+(?:to|at):\s*(https?://[^\s<>"\'\)]+)',
r'(https?://[^\s<>"\'\)]*submit[^\s<>"\'\)]*)',
r'(https?://[^\s<>"\'\)]*answer[^\s<>"\'\)]*)',
r'POST\s+to\s+JSON\s+to\s*(https?://[^\s<>"\'\)]+)', # "POST to JSON to https://..."
]
for pattern in patterns:
matches = re.findall(pattern, text, re.IGNORECASE)
if matches:
url = matches[0].strip().rstrip('.,;:!?)}]{["\'')
# Validate URL
try:
parsed = urlparse(url)
if parsed.scheme and parsed.netloc:
logger.info(f"Found submit URL: {url}")
return url
except Exception as e:
logger.warning(f"Invalid URL pattern found: {url}, error: {e}")
continue
# Try to find any URL that might be a submit endpoint
url_pattern = r'https?://[^\s<>"\'\)]+'
all_urls = re.findall(url_pattern, text)
for url in all_urls:
url_lower = url.lower()
if 'submit' in url_lower or 'answer' in url_lower:
try:
parsed = urlparse(url)
if parsed.scheme and parsed.netloc:
logger.info(f"Found potential submit URL: {url}")
return url
except:
continue
# Try to find relative submit links (e.g. href="/submit")
# Be more strict - only match actual submit endpoints, not paths that happen to contain "submit" in text
rel_patterns = [
r'href=["\\\'](/[^"\\\']*submit[^"\\\']*)["\\\']', # href="/submit" or href="/api/submit"
r'POST\s+to\s+JSON\s+to\s+(/[^\s<>"\'\)]+)', # "POST to JSON to /submit"
r'[Pp]ost\s+(?:to|at):\s+(/[^\s<>"\'\)]+)', # "POST to: /submit"
]
for pattern in rel_patterns:
matches = re.findall(pattern, text, re.IGNORECASE)
if matches:
candidate = matches[0].strip()
# Clean up - stop at first space, parenthesis, or other non-URL character
# This prevents matching text like "/path (description).Submit"
candidate = re.sub(r'[\s\(\)].*$', '', candidate) # Remove everything after space or paren
candidate = candidate.rstrip('.,;:!?)}]{["\'')
# Validate it's actually a submit endpoint (contains "submit" in the path)
# AND it doesn't contain file extensions that indicate it's a document path
if 'submit' in candidate.lower() and not any(ext in candidate.lower() for ext in ['.md', '.txt', '.pdf', '.html']):
try:
joined = urljoin(base_url, candidate)
# Final validation - ensure it's a valid URL
parsed = urlparse(joined)
if parsed.scheme and parsed.netloc:
logger.info(f"Found relative submit URL: {joined}")
return joined
except Exception as e:
logger.warning(f"Invalid relative URL candidate: {candidate}, error: {e}")
continue
# Don't match generic paths that happen to contain "submit" in surrounding text
# This was causing issues where paths like "/project2/data-preparation.md (local copy provided).Submit that exact"
# were being matched incorrectly
# Try to find submit URL in the base domain with /submit path
if base_url:
try:
parsed = urlparse(base_url)
submit_url = f"{parsed.scheme}://{parsed.netloc}/submit"
logger.info(f"Trying default submit URL: {submit_url}")
return submit_url
except:
pass
logger.warning("No submit URL found in page text")
return None
def validate_secret(secret: str, expected_secret: str) -> bool:
"""
Validate the secret key.
Args:
secret: Provided secret
expected_secret: Expected secret from environment
Returns:
True if valid, False otherwise
"""
return secret == expected_secret
def clean_text(text: str) -> str:
"""
Clean and normalize text content.
Args:
text: Raw text content
Returns:
Cleaned text
"""
if not text:
return ""
# Remove excessive whitespace
text = re.sub(r'\s+', ' ', text)
# Remove leading/trailing whitespace
text = text.strip()
return text
def extract_json_from_text(text: str) -> Optional[Dict[str, Any]]:
"""
Try to extract JSON objects from text.
Args:
text: Text that may contain JSON
Returns:
Parsed JSON dict or None
"""
# Try to find JSON blocks
json_pattern = r'\{[^{}]*(?:\{[^{}]*\}[^{}]*)*\}'
matches = re.findall(json_pattern, text, re.DOTALL)
for match in matches:
try:
return json.loads(match)
except json.JSONDecodeError:
continue
# Try to fix common JSON issues
try:
# Remove markdown code blocks
text = re.sub(r'```json\s*', '', text)
text = re.sub(r'```\s*', '', text)
# Try parsing the cleaned text
return json.loads(text.strip())
except json.JSONDecodeError:
pass
return None
def safe_extract_json(text: str, max_retries: int = 1) -> Optional[Dict[str, Any]]:
"""
Safely extract JSON with better error handling.
Args:
text: Text that may contain JSON
max_retries: Maximum retry attempts
Returns:
Parsed JSON dict or None
"""
result = extract_json_from_text(text)
if result:
return result
# Try to fix common issues
fixed_text = text
# Remove leading/trailing whitespace and newlines
fixed_text = fixed_text.strip()
# Remove markdown formatting
fixed_text = re.sub(r'^```(?:json)?\s*', '', fixed_text, flags=re.MULTILINE)
fixed_text = re.sub(r'\s*```$', '', fixed_text, flags=re.MULTILINE)
# Try again with fixed text
result = extract_json_from_text(fixed_text)
return result
def is_valid_url(url: str) -> bool:
"""
Validate if a string is a valid URL.
Args:
url: URL string to validate
Returns:
True if valid URL, False otherwise
"""
try:
result = urlparse(url)
return all([result.scheme, result.netloc])
except Exception:
return False
def sanitize_filename(filename: str) -> str:
"""
Sanitize a filename by removing invalid characters.
Args:
filename: Original filename
Returns:
Sanitized filename
"""
# Remove invalid characters
filename = re.sub(r'[<>:"/\\|?*]', '_', filename)
# Remove leading/trailing dots and spaces
filename = filename.strip('. ')
return filename
|