Spaces:
Sleeping
Sleeping
File size: 6,327 Bytes
0b6ad4c |
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 |
"""
Utility Functions
Helper functions for the Resume Analyzer system.
"""
import os
import json
import hashlib
from datetime import datetime
from typing import Any, Dict, List
import logging
from pathlib import Path
logger = logging.getLogger(__name__)
def setup_logging(log_file: str = "logs/app.log", level: str = "INFO"):
"""
Setup logging configuration.
Args:
log_file: Path to log file
level: Logging level
"""
# Create logs directory if it doesn't exist
log_dir = os.path.dirname(log_file)
if log_dir and not os.path.exists(log_dir):
os.makedirs(log_dir)
logging.basicConfig(
level=getattr(logging, level),
format='%(asctime)s - %(name)s - %(levelname)s - %(message)s',
handlers=[
logging.FileHandler(log_file),
logging.StreamHandler()
]
)
logger.info("Logging initialized")
def save_json(data: Dict, filepath: str):
"""
Save data to JSON file.
Args:
data: Dictionary to save
filepath: Output file path
"""
try:
os.makedirs(os.path.dirname(filepath), exist_ok=True)
with open(filepath, 'w', encoding='utf-8') as f:
json.dump(data, f, indent=2, ensure_ascii=False)
logger.info(f"Saved data to {filepath}")
except Exception as e:
logger.error(f"Failed to save JSON: {e}")
raise
def load_json(filepath: str) -> Dict:
"""
Load data from JSON file.
Args:
filepath: Input file path
Returns:
Loaded dictionary
"""
try:
with open(filepath, 'r', encoding='utf-8') as f:
data = json.load(f)
logger.info(f"Loaded data from {filepath}")
return data
except Exception as e:
logger.error(f"Failed to load JSON: {e}")
raise
def generate_file_hash(filepath: str) -> str:
"""
Generate MD5 hash of file.
Args:
filepath: Path to file
Returns:
MD5 hash string
"""
hash_md5 = hashlib.md5()
with open(filepath, "rb") as f:
for chunk in iter(lambda: f.read(4096), b""):
hash_md5.update(chunk)
return hash_md5.hexdigest()
def log_analysis(
resume_name: str,
ats_score: float,
match_score: float = None,
log_file: str = "logs/analysis_log.jsonl"
):
"""
Log analysis results for monitoring.
Args:
resume_name: Name of resume file
ats_score: ATS compatibility score
match_score: Job match score (optional)
log_file: Path to log file
"""
log_entry = {
'timestamp': datetime.now().isoformat(),
'resume_name': resume_name,
'ats_score': ats_score,
'match_score': match_score,
}
try:
os.makedirs(os.path.dirname(log_file), exist_ok=True)
with open(log_file, 'a', encoding='utf-8') as f:
f.write(json.dumps(log_entry) + '\n')
except Exception as e:
logger.error(f"Failed to log analysis: {e}")
def format_skills_list(skills_dict: Dict[str, List[str]]) -> str:
"""
Format skills dictionary into readable string.
Args:
skills_dict: Dictionary of categorized skills
Returns:
Formatted string
"""
formatted = []
for category, skills in skills_dict.items():
category_name = category.replace('_', ' ').title()
skills_str = ', '.join(skills)
formatted.append(f"**{category_name}**: {skills_str}")
return '\n'.join(formatted)
def truncate_text(text: str, max_length: int = 100) -> str:
"""
Truncate text to maximum length.
Args:
text: Input text
max_length: Maximum length
Returns:
Truncated text
"""
if len(text) <= max_length:
return text
return text[:max_length-3] + '...'
def validate_file_upload(file_path: str, max_size_mb: int = 10) -> bool:
"""
Validate uploaded file.
Args:
file_path: Path to file
max_size_mb: Maximum file size in MB
Returns:
True if valid, raises exception otherwise
"""
if not os.path.exists(file_path):
raise FileNotFoundError(f"File not found: {file_path}")
# Check file size
file_size_mb = os.path.getsize(file_path) / (1024 * 1024)
if file_size_mb > max_size_mb:
raise ValueError(f"File too large: {file_size_mb:.1f}MB (max: {max_size_mb}MB)")
# Check file extension
valid_extensions = ['.pdf', '.docx', '.txt']
file_ext = os.path.splitext(file_path)[1].lower()
if file_ext not in valid_extensions:
raise ValueError(f"Invalid file type: {file_ext}")
return True
def create_result_summary(analysis_results: Dict) -> str:
"""
Create a summary of analysis results.
Args:
analysis_results: Complete analysis dictionary
Returns:
Formatted summary string
"""
summary_parts = []
# ATS Score
if 'ats_score' in analysis_results:
ats = analysis_results['ats_score']
summary_parts.append(
f"📊 **ATS Score**: {ats.get('overall_score', 0)}/100 "
f"(Grade: {ats.get('grade', 'N/A')})"
)
# Skills
if 'skills' in analysis_results:
total_skills = sum(
len(skills) for skills in analysis_results['skills'].values()
)
summary_parts.append(f"🎯 **Skills Found**: {total_skills}")
# Experience
if 'experience_years' in analysis_results:
summary_parts.append(
f"💼 **Experience**: ~{analysis_results['experience_years']} years"
)
# Job Matches
if 'job_matches' in analysis_results and analysis_results['job_matches']:
top_match = analysis_results['job_matches'][0]
summary_parts.append(
f"🎯 **Top Match**: {top_match['job']['title']} "
f"({top_match['match_percentage']:.0f}% match)"
)
return '\n'.join(summary_parts)
def get_timestamp() -> str:
"""Get current timestamp string."""
return datetime.now().strftime('%Y-%m-%d %H:%M:%S')
def ensure_dir(directory: str):
"""Ensure directory exists."""
Path(directory).mkdir(parents=True, exist_ok=True)
|