Create skills.py

pipelines/skills.py

@@ -0,0 +1,31 @@
+import re
+from typing import Dict, List
+
+SKILL_LEXICON = [
+    "Python","C++","Java","Go","Rust","JavaScript","TypeScript","SQL","R",
+    "PyTorch","TensorFlow","Keras","scikit-learn","Hugging Face","Transformers",
+    "FastAPI","Django","Flask","React","Vue","Next.js","Node.js",
+    "Spark","Hadoop","Airflow","dbt","Kafka",
+    "AWS","GCP","Azure","Docker","Kubernetes",
+    "Tableau","Power BI","Looker",
+    "Git","Linux","Terraform","OpenAPI",
+]
+
+NAME_HINTS = ["氏名", "Name"]
+
+def _regex_ner_contacts(text: str) -> Dict[str, List[str]]:
+    emails = re.findall(r"[A-Za-z0-9._%+-]+@[A-Za-z0-9.-]+\.[A-Za-z]{2,}", text)
+    phones = re.findall(r"(?:\+?\d{1,3}[ -]?)?(?:\(\d{2,4}\)[ -]?)?\d{2,4}[ -]?\d{2,4}[ -]?\d{3,4}", text)
+    return {"EMAIL": list(set(emails)), "PHONE": list(set(phones))}
+
+def extract_skills(text: str, sections: Dict[str, str]) -> Dict:
+    contacts = _regex_ner_contacts(text)
+    name_lines = []
+    for hint in NAME_HINTS:
+        name_lines += [l.strip() for l in text.splitlines() if hint in l][:3]
+    found = []
+    text_lower = text.lower()
+    for s in SKILL_LEXICON:
+        if s.lower() in text_lower:
+            found.append(s)
+    return {"skills": sorted(list(set(found))), "contacts": contacts, "name_candidates": name_lines}