Initial commit

2026-03-11 15:27:10 +03:00
commit 8b4b8d54d1
34 changed files with 7407 additions and 0 deletions
--- a/extract/sections.py
+++ b/extract/sections.py
@@ -0,0 +1,70 @@
+from __future__ import annotations
+
+import re
+from typing import Dict, List, Optional, Tuple
+
+
+_SECTION_PATTERNS: dict[str, List[re.Pattern]] = {
+    "contacts": [
+        re.compile(r"^\s*(contacts?|contact info|контакты)\s*$", re.I),
+    ],
+    "about": [
+        re.compile(r"^\s*(summary|about|profile|objective|о\s+себе|обо\s+мне|профиль|цель)\s*$", re.I),
+    ],
+    "skills": [
+        re.compile(r"^\s*(skills?|key skills|stack|tech( stack)?|навыки|технологии|компетенции)\s*$", re.I),
+    ],
+    "experience": [
+        re.compile(r"^\s*(experience|work experience|employment|опыт\s+работы|опыт)\s*$", re.I),
+    ],
+    "education": [
+        re.compile(r"^\s*(education|образование|курсы|certifications?|сертификаты)\s*$", re.I),
+    ],
+    "projects": [
+        re.compile(r"^\s*(projects?|проекты)\s*$", re.I),
+    ],
+    "languages": [
+        re.compile(r"^\s*(languages?|языки)\s*$", re.I),
+    ],
+    "certifications": [
+        re.compile(r"^\s*(certifications?|сертификаты|курсы)\s*$", re.I),
+    ],
+    "publications": [
+        re.compile(r"^\s*(publications?|публикации)\s*$", re.I),
+    ],
+}
+
+
+def _match_header(line: str) -> Optional[str]:
+    for key, patterns in _SECTION_PATTERNS.items():
+        for rx in patterns:
+            if rx.match(line):
+                return key
+    return None
+
+
+def split_sections(clean_text: str, doc_type: str | None = None) -> Dict[str, str]:
+    lines = [ln.strip() for ln in (clean_text or "").splitlines()]
+    sections: Dict[str, List[str]] = {"header": []}
+    current = "header"
+
+    for ln in lines:
+        if not ln:
+            continue
+        key = _match_header(ln)
+        if key:
+            current = key
+            sections.setdefault(current, [])
+            continue
+        sections.setdefault(current, []).append(ln)
+
+    out: Dict[str, str] = {}
+    for k, vals in sections.items():
+        text = "\n".join(vals).strip()
+        if text:
+            out[k] = text
+    return out
+
+
+def sections_present(sections: Dict[str, str]) -> List[str]:
+    return sorted([k for k, v in (sections or {}).items() if v and k != "header"])