Spaces:
Running
Running
File size: 14,524 Bytes
07273d8 |
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 |
from __future__ import annotations
import html
from typing import Any, Callable, Dict, Optional
from utils.cv_parser import parse_cv
from utils.cv_project_matcher import match_cv_to_projects
from utils.skill_extractor import extract_skills_from_cv_text
from .render_cv_html import render_cv_analysis_html
from .render_cv_matching import render_cv_matching_html
class CVInterface:
"""
Handles all CV-related functionality including upload, parsing, skill extraction,
and project matching.
"""
def __init__(self, main_interface):
"""
Initialize CV interface with reference to main interface for shared functionality.
Args:
main_interface: Reference to EastSyncInterface instance for accessing
shared methods like register_agent_action, start_processing, etc.
"""
self._main_interface = main_interface
self._cv_skills_data: Optional[Dict[str, Any]] = None
self._cv_filename: str = "Unknown"
def render_cv_upload_interface(self) -> str:
"""Render the CV upload interface instructions for the right panel."""
return """
<div style="display: flex; align-items: center; justify-content: center; min-height: 60vh; padding: 40px;">
<div style="max-width: 900px; width: 100%;">
<div style="background: var(--bg-panel); border: 2px solid var(--arc-orange); border-radius: 4px; padding: 40px;">
<div style="display: flex; align-items: center; gap: 16px; margin-bottom: 24px;">
<div style="font-size: 48px;">📄</div>
<div>
<h2 style="color: var(--arc-orange); margin: 0; font-size: 28px; font-weight: 700;">CV ANALYSIS OPTIONS</h2>
<p style="color: var(--text-dim); margin: 8px 0 0 0; font-size: 15px;">
Upload a candidate's CV (PDF or DOCX format) to extract skills and optionally match against projects.
</p>
</div>
</div>
<div style="margin-top: 32px; padding: 24px; background: rgba(0,0,0,0.4); border-radius: 4px; border: 1px solid var(--border-dim);">
<div style="color: var(--arc-cyan); font-size: 14px; margin-bottom: 20px; text-transform: uppercase; letter-spacing: 1px;">
<strong>TWO ANALYSIS MODES:</strong>
</div>
<div style="display: grid; grid-template-columns: 1fr 1fr; gap: 20px; margin-bottom: 24px;">
<div style="padding: 20px; background: rgba(255,255,255,0.05); border-radius: 4px; border-left: 4px solid var(--arc-cyan);">
<div style="color: var(--arc-cyan); font-weight: 700; margin-bottom: 10px; font-size: 15px;">📊 EXTRACT SKILLS ONLY</div>
<div style="color: var(--text-dim); font-size: 13px; line-height: 1.5;">
Parse CV to identify technical skills, experience, certifications, and education.
</div>
</div>
<div style="padding: 20px; background: rgba(255,255,255,0.05); border-radius: 4px; border-left: 4px solid var(--arc-orange);">
<div style="color: var(--arc-orange); font-weight: 700; margin-bottom: 10px; font-size: 15px;">🎯 EXTRACT + MATCH PROJECTS</div>
<div style="color: var(--text-dim); font-size: 13px; line-height: 1.5;">
Parse CV, rank matching projects by skill compatibility, and identify skill gaps.
</div>
</div>
</div>
<div style="color: var(--arc-yellow); font-size: 13px; padding: 16px; background: rgba(255,185,0,0.1); border-radius: 4px; border: 1px solid rgba(255,185,0,0.3);">
<strong>⚠️ Instructions:</strong> Use the file upload on the left panel to select a CV, then choose your desired analysis mode.
</div>
</div>
</div>
</div>
</div>
"""
def process_cv_upload(self, file_obj) -> str:
"""Process uploaded CV file and extract skills. Returns main output HTML."""
if file_obj is None:
return '<div style="color: var(--arc-red); padding: 40px; text-align: center;">⚠️ No file uploaded. Please select a CV file (PDF or DOCX).</div>'
try:
import os
file_name = os.path.basename(file_obj.name) if hasattr(file_obj, 'name') else "unknown"
self._cv_filename = file_name
# Terminal logging
print("\n" + "="*80)
print(f"[CV UPLOAD] Processing CV: {file_name}")
print("="*80)
self._main_interface.register_agent_action("📤 CV Upload Started", {"file": file_name})
# Read file content
if hasattr(file_obj, 'name'):
# Gradio file object
file_path = file_obj.name
with open(file_path, 'rb') as f:
file_content = f.read()
else:
# Direct file path
file_path = str(file_obj)
with open(file_path, 'rb') as f:
file_content = f.read()
file_size_kb = len(file_content) / 1024
self._main_interface.register_agent_action("📄 Parsing Document", {
"size": f"{file_size_kb:.1f}KB",
"format": os.path.splitext(file_name)[1].upper()
})
# Extract text from CV
cv_text = parse_cv(file_path=file_path, file_content=file_content, log_callback=self._main_interface.register_agent_action)
if not cv_text or len(cv_text.strip()) < 50:
self._main_interface.register_agent_action("⚠️ Text Extraction Failed", {"extracted_chars": len(cv_text) if cv_text else 0})
print(f"[CV UPLOAD] ❌ ERROR: Text extraction failed - only {len(cv_text) if cv_text else 0} chars extracted")
return '<div style="color: var(--arc-red); padding: 40px; text-align: center;">⚠️ Could not extract meaningful text from the CV. Please ensure the file is not corrupted.</div>'
word_count = len(cv_text.split())
char_count = len(cv_text)
self._main_interface.register_agent_action("✅ Text Extracted", {
"words": word_count,
"characters": char_count,
"pages_est": max(1, word_count // 300) # Rough estimate
})
self._main_interface.register_agent_action("🤖 AI Analysis Starting", {"status": "Initializing AI-powered skill extraction..."})
# Extract skills using LLM with logging callback
skills_data = extract_skills_from_cv_text(cv_text, log_callback=self._main_interface.register_agent_action)
self._cv_skills_data = skills_data
if "error" not in skills_data:
total_skills = len(skills_data.get("technical_skills", [])) + len(skills_data.get("soft_skills", []))
self._main_interface.register_agent_action("🎯 Skills Extracted", {
"technical_skills": len(skills_data.get("technical_skills", [])),
"soft_skills": len(skills_data.get("soft_skills", [])),
"total": total_skills
})
print(f"[CV UPLOAD] ✅ SUCCESS: Extracted {total_skills} total skills")
else:
print(f"[CV UPLOAD] ⚠️ WARNING: Skills extraction completed with errors")
print("="*80 + "\n")
# Render CV analysis HTML for main display
main_output = render_cv_analysis_html(skills_data, file_name)
return main_output
except Exception as e:
error_msg = str(e)
self._main_interface.register_agent_action("CV Processing Error", {"error": error_msg})
print(f"[CV UPLOAD] ❌ EXCEPTION: {type(e).__name__} - {error_msg}")
print("="*80 + "\n")
return f'<div style="color: var(--arc-red); padding: 40px; text-align: center;">⚠️ Error processing CV: {html.escape(error_msg)}</div>'
def get_extracted_skills(self) -> Optional[Dict[str, Any]]:
"""Get the most recently extracted skills data."""
return self._cv_skills_data
def process_cv_with_matching(self, file_obj) -> str:
"""Process CV and match against projects. Returns main output HTML."""
if file_obj is None:
return '<div style="color: var(--arc-red); padding: 40px; text-align: center;">⚠️ No file uploaded. Please select a CV file (PDF or DOCX).</div>'
try:
import os
file_name = os.path.basename(file_obj.name) if hasattr(file_obj, 'name') else "unknown"
self._cv_filename = file_name
# Terminal logging
print("\n" + "="*80)
print(f"[CV MATCHING] Processing CV with Project Matching: {file_name}")
print("="*80)
self._main_interface.register_agent_action("📤 CV Upload + Matching Started", {"file": file_name})
# Read file content
if hasattr(file_obj, 'name'):
file_path = file_obj.name
with open(file_path, 'rb') as f:
file_content = f.read()
else:
file_path = str(file_obj)
with open(file_path, 'rb') as f:
file_content = f.read()
file_size_kb = len(file_content) / 1024
self._main_interface.register_agent_action("📄 Parsing Document", {
"size": f"{file_size_kb:.1f}KB",
"format": os.path.splitext(file_name)[1].upper()
})
# Extract text from CV
cv_text = parse_cv(file_path=file_path, file_content=file_content, log_callback=self._main_interface.register_agent_action)
if not cv_text or len(cv_text.strip()) < 50:
self._main_interface.register_agent_action("⚠️ Text Extraction Failed", {"extracted_chars": len(cv_text) if cv_text else 0})
print(f"[CV MATCHING] ❌ ERROR: Text extraction failed")
return '<div style="color: var(--arc-red); padding: 40px; text-align: center;">⚠️ Could not extract meaningful text from the CV.</div>'
word_count = len(cv_text.split())
char_count = len(cv_text)
self._main_interface.register_agent_action("✅ Text Extracted", {
"words": word_count,
"characters": char_count,
"pages_est": max(1, word_count // 300)
})
self._main_interface.register_agent_action("🤖 AI Analysis Starting", {"status": "Extracting skills from CV..."})
# Extract skills using LLM
skills_data = extract_skills_from_cv_text(cv_text, log_callback=self._main_interface.register_agent_action)
self._cv_skills_data = skills_data
if "error" in skills_data:
print(f"[CV MATCHING] ⚠️ WARNING: Skills extraction completed with errors")
return '<div style="color: var(--arc-red); padding: 40px; text-align: center;">⚠️ Error extracting skills from CV.</div>'
total_skills = len(skills_data.get("technical_skills", [])) + len(skills_data.get("soft_skills", []))
self._main_interface.register_agent_action("🎯 Skills Extracted", {
"technical_skills": len(skills_data.get("technical_skills", [])),
"soft_skills": len(skills_data.get("soft_skills", [])),
"total": total_skills
})
print(f"[CV MATCHING] ✅ Skills extracted: {total_skills} total skills")
# Match against projects
self._main_interface.register_agent_action("🔍 Starting Project Matching", {"status": "Comparing skills with project requirements..."})
matched_projects = match_cv_to_projects(skills_data, log_callback=self._main_interface.register_agent_action)
if not matched_projects:
print(f"[CV MATCHING] ⚠️ No projects found for matching")
self._main_interface.register_agent_action("⚠️ No Projects Found", {"status": "No projects available in database"})
# Still show CV analysis
main_output = render_cv_analysis_html(skills_data, file_name)
return main_output
# Skip training costs - just show matching results
# Set empty training plans for all projects
for project in matched_projects:
project['training_plans'] = []
print(f"[CV MATCHING] ✅ SUCCESS: Matched {len(matched_projects)} projects")
self._main_interface.register_agent_action("✅ Matching Complete", {
"total_matches": len(matched_projects),
"best_match": f"{matched_projects[0]['project_name']} ({matched_projects[0]['match_percentage']}%)"
})
print("="*80 + "\n")
# Render CV matching results for main display
main_output = render_cv_matching_html(skills_data, matched_projects, file_name)
return main_output
except Exception as e:
error_msg = str(e)
self._main_interface.register_agent_action("CV Matching Error", {"error": error_msg})
print(f"[CV MATCHING] ❌ EXCEPTION: {type(e).__name__} - {error_msg}")
print("="*80 + "\n")
return f'<div style="color: var(--arc-red); padding: 40px; text-align: center;">⚠️ Error processing CV: {html.escape(error_msg)}</div>'
|