feat: add light markdown candidate profile parser

docs/profile-template.md

@@ -0,0 +1,22 @@
+# Candidate Profile
+
+## Summary
+One short paragraph describing your target profile.
+
+## Target Roles
+- Data Engineer
+
+## Strengths
+- Python
+- SQL
+
+## Skills To Emphasize
+- GCP
+- BigQuery
+
+## Constraints
+- CDI only
+- France only
+
+## Notes
+- Anything the CV parser might miss but future ranking should understand.

src/job_research/profile/__init__.py

@@ -0,0 +1 @@
+__all__ = ["profile_parser"]

src/job_research/profile/profile_parser.py

@@ -0,0 +1,68 @@
+from __future__ import annotations
+
+from collections import defaultdict
+from dataclasses import dataclass, field
+
+
+@dataclass
+class AuthoredProfile:
+    summary: str | None = None
+    target_roles: list[str] = field(default_factory=list)
+    strengths: list[str] = field(default_factory=list)
+    skills_to_emphasize: list[str] = field(default_factory=list)
+    constraints: list[str] = field(default_factory=list)
+    notes: list[str] = field(default_factory=list)
+
+
+REQUIRED_SECTIONS = {
+    "summary",
+    "target roles",
+    "strengths",
+    "skills to emphasize",
+    "constraints",
+    "notes",
+}
+
+
+def parse_profile_markdown(markdown: str) -> AuthoredProfile:
+    sections: dict[str, list[str]] = defaultdict(list)
+    current_section: str | None = None
+
+    for raw_line in markdown.splitlines():
+        line = raw_line.strip()
+        if line.startswith("## "):
+            current_section = line[3:].strip().lower()
+            continue
+        if not line or current_section is None:
+            continue
+        sections[current_section].append(line)
+
+    missing = REQUIRED_SECTIONS - set(sections)
+    if missing:
+        missing_text = ", ".join(sorted(missing))
+        raise ValueError(f"Missing required markdown sections: {missing_text}")
+
+    return AuthoredProfile(
+        summary=" ".join(sections["summary"]),
+        target_roles=[
+            line[2:].strip()
+            for line in sections["target roles"]
+            if line.startswith("- ")
+        ],
+        strengths=[
+            line[2:].strip()
+            for line in sections["strengths"]
+            if line.startswith("- ")
+        ],
+        skills_to_emphasize=[
+            line[2:].strip()
+            for line in sections["skills to emphasize"]
+            if line.startswith("- ")
+        ],
+        constraints=[
+            line[2:].strip()
+            for line in sections["constraints"]
+            if line.startswith("- ")
+        ],
+        notes=[line[2:].strip() if line.startswith("- ") else line for line in sections["notes"]],
+    )

tests/profile/test_profile_parser.py

@@ -0,0 +1,42 @@
+from textwrap import dedent
+
+from job_research.profile.profile_parser import parse_profile_markdown
+
+
+def test_parse_profile_markdown_reads_light_required_template() -> None:
+    markdown = dedent(
+        """
+        # Candidate Profile
+
+        ## Summary
+        Junior data engineer focused on Python and GCP.
+
+        ## Target Roles
+        - Data Engineer
+        - Analytics Engineer
+
+        ## Strengths
+        - Python
+        - SQL
+
+        ## Skills To Emphasize
+        - BigQuery
+        - Terraform
+
+        ## Constraints
+        - CDI only
+        - France only
+
+        ## Notes
+        - Slight preference for French listings.
+        """
+    ).strip()
+
+    profile = parse_profile_markdown(markdown)
+
+    assert profile.summary == "Junior data engineer focused on Python and GCP."
+    assert profile.target_roles == ["Data Engineer", "Analytics Engineer"]
+    assert profile.strengths == ["Python", "SQL"]
+    assert profile.skills_to_emphasize == ["BigQuery", "Terraform"]
+    assert profile.constraints == ["CDI only", "France only"]
+    assert profile.notes == ["Slight preference for French listings."]