File size: 2,457 Bytes
efffc2e
6d286f1
b336194
6d286f1
 
 
 
864c2ae
 
6d286f1
a511250
6d286f1
 
 
af02e64
6d286f1
 
 
 
 
 
 
 
 
 
 
 
 
 
864c2ae
 
 
 
 
6d286f1
864c2ae
 
6d286f1
 
 
a511250
6d286f1
864c2ae
6d286f1
efffc2e
d4b2339
864c2ae
efffc2e
 
6d286f1
864c2ae
 
 
 
 
 
 
 
efffc2e
 
a511250
 
 
 
efffc2e
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
from transformers import AutoTokenizer, AutoModelForTokenClassification, pipeline
import zipfile, re, os

# ===============================
# Load Model & Tokenizer
# ===============================
MODEL_NAME = "sravya-abburi/ResumeParserBERT"  # Change to Kiet/autotrain-resume_parser-1159242747 if needed
tokenizer = AutoTokenizer.from_pretrained(MODEL_NAME)
model = AutoModelForTokenClassification.from_pretrained(MODEL_NAME)
ner_pipeline = pipeline("ner", model=model, tokenizer=tokenizer, aggregation_strategy="simple")

# ===============================
# Extract Text (PDF & DOCX)
# ===============================
def extract_text(file_path: str) -> str:
    """Extract text from PDF or DOCX without external dependencies."""
    file_path_lower = file_path.lower()

    # PDF reading using PyMuPDF (built into Spaces environment)
    if file_path_lower.endswith(".pdf"):
        import fitz  # PyMuPDF
        text = ""
        with fitz.open(file_path) as pdf_doc:
            for page in pdf_doc:
                text += page.get_text()
        return text

    # DOCX reading by extracting XML content
    elif file_path_lower.endswith(".docx"):
        with zipfile.ZipFile(file_path) as zf:
            with zf.open("word/document.xml") as docx_xml:
                xml_text = docx_xml.read().decode("utf-8", errors="ignore")
                xml_text = re.sub(r"<w:p[^>]*>", "\n", xml_text, flags=re.I)
                return re.sub(r"<[^>]+>", " ", xml_text)

    return ""

# ===============================
# Parse Resume
# ===============================
def parse_resume(file_path: str, filename: str = None) -> dict:
    """Parse resume and extract structured information."""
    text = extract_text(file_path)

    entities = ner_pipeline(text)

    name, skills, education, experience = [], [], [], []
    for ent in entities:
        label = ent["entity_group"].upper()
        word = ent["word"].strip()
        if label == "NAME":
            name.append(word)
        elif label == "SKILL":
            skills.append(word)
        elif label in ["EDUCATION", "DEGREE"]:
            education.append(word)
        elif label in ["EXPERIENCE", "JOB", "ROLE"]:
            experience.append(word)

    return {
        "name": " ".join(dict.fromkeys(name)),
        "skills": ", ".join(dict.fromkeys(skills)),
        "education": ", ".join(dict.fromkeys(education)),
        "experience": ", ".join(dict.fromkeys(experience))
    }