feat: add deterministic CV extraction

src/job_research/profile/cv_extractor.py

@@ -0,0 +1,55 @@
+from __future__ import annotations
+
+from pathlib import Path
+
+from pypdf import PdfReader
+
+
+def extract_pdf_text(path: Path) -> str:
+    reader = PdfReader(str(path))
+    return "\n".join(page.extract_text() or "" for page in reader.pages)
+
+
+def extract_cv_signals(text: str) -> dict[str, object]:
+    lines = [line.strip() for line in text.splitlines()]
+    non_empty_lines = [line for line in lines if line]
+
+    name = non_empty_lines[0] if non_empty_lines else None
+    location = None
+    languages: list[str] = []
+    skills: list[str] = []
+    experience_entries: list[dict[str, str]] = []
+
+    for line in non_empty_lines[1:]:
+        lowered = line.lower()
+        if lowered.startswith("location:"):
+            location = line.split(":", 1)[1].strip() or None
+            continue
+        if lowered.startswith("languages:"):
+            languages = _parse_csv_field(line)
+            continue
+        if lowered.startswith("skills:"):
+            skills = _parse_csv_field(line)
+            continue
+        if " at " in line:
+            title, company = line.split(" at ", 1)
+            experience_entries.append(
+                {
+                    "title": title.strip(),
+                    "company": company.strip(),
+                }
+            )
+
+    return {
+        "name": name,
+        "location": location,
+        "languages": languages,
+        "skills": skills,
+        "experience_entries": experience_entries,
+        "education_entries": [],
+    }
+
+
+def _parse_csv_field(line: str) -> list[str]:
+    _, value = line.split(":", 1)
+    return [item.strip() for item in value.split(",") if item.strip()]

tests/profile/test_cv_extractor.py

@@ -0,0 +1,25 @@
+from textwrap import dedent
+
+from job_research.profile.cv_extractor import extract_cv_signals
+
+
+def test_extract_cv_signals_reads_basic_fields_from_text() -> None:
+    text = dedent(
+        """
+        Tonio
+        Location: France
+        Languages: French, English
+        Skills: Python, SQL, Terraform, GCP, BigQuery
+        Data Engineer at Company A
+        Analytics Engineer at Company B
+        """
+    ).strip()
+
+    extracted = extract_cv_signals(text)
+
+    assert extracted["name"] == "Tonio"
+    assert extracted["location"] == "France"
+    assert extracted["languages"] == ["French", "English"]
+    assert extracted["skills"] == ["Python", "SQL", "Terraform", "GCP", "BigQuery"]
+    assert extracted["experience_entries"][0]["title"] == "Data Engineer"
+    assert len(extracted["experience_entries"]) == 2