Spaces:
Sleeping
Sleeping
Update app.py
Browse files
app.py
CHANGED
@@ -8,13 +8,16 @@ from nltk.tokenize import word_tokenize
|
|
8 |
import torch
|
9 |
from transformers import pipeline, AutoModelForCausalLM, AutoTokenizer
|
10 |
import time
|
|
|
|
|
|
|
|
|
11 |
|
12 |
# Set page title and configuration
|
13 |
st.set_page_config(
|
14 |
page_title="Resume-Job Fit Analyzer",
|
15 |
page_icon="π",
|
16 |
-
layout="wide"
|
17 |
-
initial_sidebar_state="expanded"
|
18 |
)
|
19 |
|
20 |
# Download NLTK resources if needed
|
@@ -49,6 +52,61 @@ def load_models():
|
|
49 |
|
50 |
return models
|
51 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
52 |
# Extract skills from text
|
53 |
def extract_skills(text, skill_keywords):
|
54 |
"""Extract skills from text based on a predefined list of skills"""
|
@@ -353,28 +411,30 @@ def generate_fallback_assessment(resume_data, job_data, match_scores, fit_status
|
|
353 |
st.title("Resume-Job Fit Analyzer")
|
354 |
st.markdown("### Evaluate how well a resume matches a job description")
|
355 |
|
356 |
-
#
|
357 |
-
|
|
|
358 |
|
359 |
-
|
360 |
-
|
361 |
-
|
362 |
-
|
363 |
-
placeholder="Paste the candidate's resume text here...")
|
364 |
|
365 |
-
|
366 |
-
|
367 |
-
|
368 |
-
|
369 |
-
|
|
|
|
|
370 |
|
371 |
# Analysis button
|
372 |
-
analyze_button = st.button("Analyze Match", type="primary"
|
373 |
|
374 |
# Main analysis logic
|
375 |
if analyze_button:
|
376 |
if not resume_text or not job_description:
|
377 |
-
st.error("Please
|
378 |
else:
|
379 |
with st.spinner("Analyzing resume and job match..."):
|
380 |
# Record start time
|
|
|
8 |
import torch
|
9 |
from transformers import pipeline, AutoModelForCausalLM, AutoTokenizer
|
10 |
import time
|
11 |
+
import os
|
12 |
+
import docx2txt
|
13 |
+
import io
|
14 |
+
import docx
|
15 |
|
16 |
# Set page title and configuration
|
17 |
st.set_page_config(
|
18 |
page_title="Resume-Job Fit Analyzer",
|
19 |
page_icon="π",
|
20 |
+
layout="wide"
|
|
|
21 |
)
|
22 |
|
23 |
# Download NLTK resources if needed
|
|
|
52 |
|
53 |
return models
|
54 |
|
55 |
+
# Read resume file
|
56 |
+
def read_resume_file(uploaded_file):
|
57 |
+
"""Extract text from uploaded resume file"""
|
58 |
+
file_extension = os.path.splitext(uploaded_file.name)[1].lower()
|
59 |
+
|
60 |
+
if file_extension == ".txt":
|
61 |
+
# Text file
|
62 |
+
text = uploaded_file.read().decode('utf-8')
|
63 |
+
return text
|
64 |
+
|
65 |
+
elif file_extension == ".docx":
|
66 |
+
# Modern Word document
|
67 |
+
try:
|
68 |
+
text = docx2txt.process(uploaded_file)
|
69 |
+
return text
|
70 |
+
except Exception as e:
|
71 |
+
st.error(f"Error reading DOCX file: {str(e)}")
|
72 |
+
return None
|
73 |
+
|
74 |
+
elif file_extension == ".doc":
|
75 |
+
# Legacy Word document - this is more complex
|
76 |
+
try:
|
77 |
+
# For .doc files, we'll return a warning that the conversion might not be perfect
|
78 |
+
st.warning("Note: .doc files might not convert perfectly. For best results, upload .docx or .txt files.")
|
79 |
+
|
80 |
+
# Save the uploaded file temporarily
|
81 |
+
with open("temp_file.doc", "wb") as f:
|
82 |
+
f.write(uploaded_file.getbuffer())
|
83 |
+
|
84 |
+
# Use an external converter - this is a placeholder
|
85 |
+
# In a real implementation, you might want to use antiword, textract or similar
|
86 |
+
# Here we'll try using docx2txt as a fallback but it might not work well
|
87 |
+
try:
|
88 |
+
text = docx2txt.process("temp_file.doc")
|
89 |
+
except:
|
90 |
+
# If that fails, try a very basic approach
|
91 |
+
with open("temp_file.doc", "rb") as f:
|
92 |
+
content = f.read()
|
93 |
+
text = content.decode('utf-8', errors='ignore')
|
94 |
+
# Try to extract readable text by removing binary parts
|
95 |
+
text = re.sub(r'[^\x20-\x7E\n\r\t]', '', text)
|
96 |
+
|
97 |
+
# Clean up
|
98 |
+
if os.path.exists("temp_file.doc"):
|
99 |
+
os.remove("temp_file.doc")
|
100 |
+
|
101 |
+
return text
|
102 |
+
except Exception as e:
|
103 |
+
st.error(f"Error reading DOC file: {str(e)}")
|
104 |
+
return None
|
105 |
+
|
106 |
+
else:
|
107 |
+
st.error(f"Unsupported file format: {file_extension}")
|
108 |
+
return None
|
109 |
+
|
110 |
# Extract skills from text
|
111 |
def extract_skills(text, skill_keywords):
|
112 |
"""Extract skills from text based on a predefined list of skills"""
|
|
|
411 |
st.title("Resume-Job Fit Analyzer")
|
412 |
st.markdown("### Evaluate how well a resume matches a job description")
|
413 |
|
414 |
+
# Resume upload
|
415 |
+
st.subheader("Resume")
|
416 |
+
uploaded_file = st.file_uploader("Upload Resume (.doc, .docx, .txt)", type=["doc", "docx", "txt"])
|
417 |
|
418 |
+
# Job description input
|
419 |
+
st.subheader("Job Description")
|
420 |
+
job_description = st.text_area("Paste job description here", height=200,
|
421 |
+
placeholder="Paste the job description here...")
|
|
|
422 |
|
423 |
+
# Display resume text if file is uploaded
|
424 |
+
resume_text = None
|
425 |
+
if uploaded_file is not None:
|
426 |
+
resume_text = read_resume_file(uploaded_file)
|
427 |
+
if resume_text:
|
428 |
+
with st.expander("View Resume Text"):
|
429 |
+
st.text(resume_text[:1000] + ("..." if len(resume_text) > 1000 else ""))
|
430 |
|
431 |
# Analysis button
|
432 |
+
analyze_button = st.button("Analyze Match", type="primary")
|
433 |
|
434 |
# Main analysis logic
|
435 |
if analyze_button:
|
436 |
if not resume_text or not job_description:
|
437 |
+
st.error("Please upload a resume file and provide a job description.")
|
438 |
else:
|
439 |
with st.spinner("Analyzing resume and job match..."):
|
440 |
# Record start time
|