86 lines
2.9 KiB
Python
86 lines
2.9 KiB
Python
from __future__ import annotations
|
||
|
||
import re
|
||
from typing import Any, Dict, Optional
|
||
|
||
from tg_resume_db.extract.parse import (
|
||
extract_contacts,
|
||
extract_name_guess,
|
||
extract_remote,
|
||
extract_english,
|
||
extract_roles_skills,
|
||
extract_salary,
|
||
extract_location_best_effort,
|
||
extract_experience_years,
|
||
)
|
||
|
||
|
||
_DESIRED_RE = re.compile(r"(?i)жел[а-я]*\s+должност[ьи]\s*[:\-]?\s*(.+)")
|
||
_SPEC_RE = re.compile(r"(?i)специализаци[яи]\s*[:\-]?\s*(.+)")
|
||
_SCHEDULE_RE = re.compile(r"(?i)график\s+работы\s*[:\-]?\s*(.+)")
|
||
_EMPLOYMENT_RE = re.compile(r"(?i)занятость\s*[:\-]?\s*(.+)")
|
||
|
||
|
||
def _pick(sections: Dict[str, str] | None, key: str, fallback: str) -> str:
|
||
if not sections:
|
||
return fallback
|
||
return sections.get(key) or fallback
|
||
|
||
|
||
def _find_first(regex: re.Pattern, text: str) -> Optional[str]:
|
||
for ln in text.splitlines():
|
||
m = regex.search(ln)
|
||
if m:
|
||
val = m.group(1).strip()
|
||
val = re.split(r"[|;/]", val)[0].strip()
|
||
if 2 <= len(val) <= 80:
|
||
return val
|
||
return None
|
||
|
||
|
||
def parse_resume(clean_text: str, sections: Dict[str, str] | None = None) -> Dict[str, Any]:
|
||
header_text = _pick(sections, "header", clean_text)
|
||
contacts_text = _pick(sections, "contacts", clean_text)
|
||
about_text = _pick(sections, "about", clean_text)
|
||
skills_text = _pick(sections, "skills", clean_text)
|
||
exp_text = _pick(sections, "experience", clean_text)
|
||
exp_scope = "\n".join([about_text, exp_text]).strip() or exp_text
|
||
|
||
name = extract_name_guess(header_text)
|
||
contacts_raw = extract_contacts(contacts_text)
|
||
roles, skills = extract_roles_skills("\n".join([about_text, skills_text, exp_text]))
|
||
|
||
remote = extract_remote(clean_text)
|
||
english = extract_english(clean_text)
|
||
location = extract_location_best_effort(clean_text)
|
||
exp_years, exp_years_eng, exp_conf, exp_dbg = extract_experience_years(exp_scope)
|
||
sal_min, sal_max, sal_conf, sal_dbg = extract_salary(clean_text)
|
||
|
||
desired_title = _find_first(_DESIRED_RE, clean_text)
|
||
specializations = _find_first(_SPEC_RE, clean_text)
|
||
schedule = _find_first(_SCHEDULE_RE, clean_text)
|
||
employment = _find_first(_EMPLOYMENT_RE, clean_text)
|
||
|
||
return {
|
||
"name": name,
|
||
"contacts_raw": contacts_raw,
|
||
"remote": remote,
|
||
"english": english,
|
||
"roles": roles,
|
||
"skills": skills,
|
||
"location": location,
|
||
"exp_years": exp_years,
|
||
"exp_years_eng": exp_years_eng,
|
||
"exp_conf": exp_conf,
|
||
"exp_dbg": exp_dbg,
|
||
"salary_min": sal_min,
|
||
"salary_max": sal_max,
|
||
"salary_conf": sal_conf,
|
||
"salary_dbg": sal_dbg,
|
||
"desired_title": desired_title,
|
||
"specializations": specializations,
|
||
"employment_type": employment,
|
||
"schedule": schedule,
|
||
"parse_method": "hh_template",
|
||
}
|