File size: 7,315 Bytes
ff7b177
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
"""
Parse uploaded files:
  - XLSX β†’ list of CandidateData (same column schema as Sample_Candidate_Data.xlsx)
  - PDF  β†’ raw text for JD parsing
"""
import ast
import re
import uuid
import logging
from io import BytesIO
from typing import Optional

import pandas as pd
import fitz  # PyMuPDF

from app.models.domain import CandidateData, WorkExperience

logger = logging.getLogger(__name__)

# ─── Constants ────────────────────────────────────────────────────────────────

REQUIRED_COLUMNS = {
    "name", "parsed_skills", "parsed_summary",
    "parsed_work_experience", "parsed_metadata_calculated_years_experience",
    "engineer_type", "current_position",
}

ENGINEER_TYPE_MAP = {
    "ai engineer": "AI Engineer",
    "ai": "AI Engineer",
    "ml engineer": "AI Engineer",
    "machine learning engineer": "AI Engineer",
    "backend engineer": "Backend Engineer",
    "backend": "Backend Engineer",
    "be": "Backend Engineer",
    "frontend engineer": "Frontend Engineer",
    "frontend": "Frontend Engineer",
    "fe": "Frontend Engineer",
    "full stack engineer": "Full Stack Engineer",
    "fullstack": "Full Stack Engineer",
    "full stack": "Full Stack Engineer",
    "software engineer": "Software Engineer",
    "sde": "Software Engineer",
    "data engineer": "Data Engineer",
    "devops engineer": "DevOps Engineer",
    "devops": "DevOps Engineer",
}

RECENT_EXP_MAP = {
    "companytype.product": "Product Company",
    "companytype.service": "Service Company",
    "a company that build its own technology products": "Product Company",
    "product": "Product Company",
    "service": "Service Company",
    "both": "Both",
}

GEN_AI_POSITIVE = {
    "6 months - 1 year", "1 to 1.5 years", "1.5 years - 2 years",
    "2+ years", "only internship/project experience",
}

GEN_AI_NEGATIVE = {"i do not have gen ai experience"}


# ─── XLSX Parsing ─────────────────────────────────────────────────────────────

def parse_xlsx(file_bytes: bytes) -> tuple[list[CandidateData], dict[str, int]]:
    """Return (candidates, engineer_type_distribution)."""
    df = pd.read_excel(BytesIO(file_bytes))
    df.columns = [c.strip().lower().replace(" ", "_") for c in df.columns]

    missing = REQUIRED_COLUMNS - set(df.columns)
    if missing:
        raise ValueError(f"XLSX missing required columns: {missing}")

    candidates: list[CandidateData] = []
    for idx, row in df.iterrows():
        try:
            candidate = _parse_row(row, idx)
            if candidate:
                candidates.append(candidate)
        except Exception as e:
            logger.warning(f"Skipping row {idx}: {e}")

    dist: dict[str, int] = {}
    for c in candidates:
        dist[c.engineer_type] = dist.get(c.engineer_type, 0) + 1

    return candidates, dist


def _parse_row(row: pd.Series, idx: int) -> Optional[CandidateData]:
    def get(col: str, default=None):
        v = row.get(col, default)
        if v is None or (isinstance(v, float) and pd.isna(v)):
            return default
        return v

    # ID
    candidate_id = str(get("id") or get("submission_id") or f"cand_{idx}")

    # Years
    yoe = _parse_float(get("parsed_metadata_calculated_years_experience"))
    if yoe is None:
        yoe = _parse_float(get("years_of_experience"))
    if yoe is None:
        yoe = -1.0

    # Engineer type
    raw_type = str(get("engineer_type", "")).strip()
    engineer_type = ENGINEER_TYPE_MAP.get(raw_type.lower(), raw_type or "Unknown")

    # Work experience
    raw_we = str(get("parsed_work_experience", "") or "")
    work_experiences, we_text = _parse_work_experience(raw_we, candidate_id)

    # Gen AI
    gen_ai_raw = get("gen_ai_experience")
    gen_ai = str(gen_ai_raw).strip() if gen_ai_raw else None

    # Active looking
    active_raw = get("is_actively_or_passively_looking")
    if active_raw is not None:
        active = str(active_raw).strip().lower() not in ("false", "no", "0", "nan", "none")
    else:
        active = None

    flags: list[str] = []
    if yoe == -1.0:
        flags.append("years_unknown")
    if not raw_we or raw_we == "nan":
        flags.append("work_exp_unavailable")
    if engineer_type == "Unknown":
        flags.append("engineer_type_unknown")

    return CandidateData(
        id=candidate_id,
        name=str(get("name", f"Candidate_{idx}")),
        current_position=str(get("current_position", "")),
        current_title=get("current_title"),
        years_of_experience=yoe,
        engineer_type=engineer_type,
        gen_ai_experience=gen_ai,
        parsed_skills=str(get("parsed_skills", "") or ""),
        parsed_summary=str(get("parsed_summary", "") or ""),
        parsed_work_experience_raw=raw_we,
        parsed_work_experience_text=we_text,
        work_experiences=work_experiences,
        extracted_skills=[],   # filled by skill_parser
        most_recent_company=get("parsed_metadata_most_recent_company"),
        notice_period=get("notice_period"),
        is_actively_looking=active,
        flags=flags,
        penalties=[],
    )


def _parse_work_experience(raw: str, cand_id: str) -> tuple[list[WorkExperience], str]:
    if not raw or raw.strip() in ("", "nan", "None"):
        return [], ""

    entries: list[WorkExperience] = []
    try:
        parsed = ast.literal_eval("[" + raw + "]")
        for item in parsed:
            if isinstance(item, dict):
                entries.append(WorkExperience(
                    company=str(item.get("company", "")),
                    role=str(item.get("role", "")),
                    duration=str(item.get("duration", "")),
                    description=str(item.get("description", "")),
                ))
    except Exception:
        logger.debug(f"ast.literal_eval failed for {cand_id}, using raw text")
        entries.append(WorkExperience(
            company="", role="", duration="",
            description=raw[:1000],
        ))

    text_parts = []
    for e in entries:
        text_parts.append(
            f"{e.role} at {e.company} ({e.duration}): {e.description}"
        )
    return entries, " | ".join(text_parts)


def _parse_float(val) -> Optional[float]:
    if val is None:
        return None
    try:
        f = float(str(val).strip())
        return f if f >= 0 else None
    except (ValueError, TypeError):
        return None


# ─── PDF Parsing ──────────────────────────────────────────────────────────────

def parse_pdf(file_bytes: bytes) -> str:
    """Extract full text from PDF, preserving newlines."""
    text_parts: list[str] = []
    try:
        doc = fitz.open(stream=file_bytes, filetype="pdf")
        for page in doc:
            text_parts.append(page.get_text("text"))
        doc.close()
    except Exception as e:
        raise ValueError(f"Failed to read PDF: {e}")

    text = "\n".join(text_parts)
    # Collapse 3+ blank lines to 2
    text = re.sub(r"\n{3,}", "\n\n", text)
    return text.strip()