Spaces:
Sleeping
Sleeping
File size: 1,803 Bytes
7fced16 c198598 7fced16 c198598 7fced16 c198598 7fced16 c198598 7fced16 c198598 7fced16 |
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 |
from typing import List, Dict
import re
def _period_key(item_text: str) -> str:
m = re.search(r"(\d{4}[./年]\d{1,2})\s*[-〜~]\s*(\d{4}[./年]?\d{0,2}|現在|至今)?", item_text)
return m.group(0) if m else item_text[:50]
def merge_normalized_records(records: List[Dict]) -> Dict:
merged = {"work_experience": [], "education": [], "certifications": [], "skills": [], "raw_sections": {}}
seen_we, seen_edu, seen_cert = set(), set(), set()
skill_set = set()
for r in records:
for w in r.get("work_experience", []):
key = _period_key(w.get("text", "")) + "|" + w.get("text", "")[:80]
if key not in seen_we:
seen_we.add(key)
merged["work_experience"].append(w)
for e in r.get("education", []):
k = e.get("text", "")
if k and k not in seen_edu:
seen_edu.add(k)
merged["education"].append(e)
for c in r.get("certifications", []):
k = c.get("text", "")
if k and k not in seen_cert:
seen_cert.add(k)
merged["certifications"].append(c)
for s in r.get("skills", []):
if s:
skill_set.add(s)
for k, v in r.get("raw_sections", {}).items():
merged["raw_sections"][k] = (merged["raw_sections"].get(k, "") + "\n" + v).strip()
def _sort_key(w):
m = re.search(r"(\d{4})([./年])(\d{1,2})", w.get("period", "") or w.get("text", ""))
if m:
try:
return (-(int(m.group(1)) * 100 + int(m.group(3))), 0)
except Exception:
return (0, 1)
return (0, 1)
merged["work_experience"].sort(key=_sort_key)
merged["skills"] = sorted(skill_set)
return merged
|