claude-resume-kit/tests/test_document_scanner.py

"""Negative regression tests for the document scanner (review findings F05 and F06).

Each case below is a counter-proof from `output/Project_Review_2026-09-11/project_review.tex`
that the scanner accepted before 2026-09-11. The point of these tests is that a green
validator run means something; they are not a claim that the scanner proves truthfulness.
See `validate_resume_system.UNCHECKED` for what deliberately stays a reading task.
"""
from __future__ import annotations

import sys
import tempfile
import unittest
from pathlib import Path

ROOT = Path(__file__).resolve().parents[1]
sys.path.insert(0, str(ROOT / "resume_builder" / "helpers"))

import validate_resume_system as validator  # noqa: E402

CLAIMS = validator.load_json(validator.CLAIMS_PATH)


def scan(body: str) -> str:
    with tempfile.TemporaryDirectory() as directory:
        path = Path(directory) / "candidate.tex"
        path.write_text(
            "\\documentclass{resume}\n\\begin{document}\n"
            "\\contactline{dennis@thiessen.io $\\vert$ +41 795 955 585}\n"
            f"{body}\n\\end{{document}}\n",
            encoding="utf-8")
        return " | ".join(validator.scan_document(path, CLAIMS))


class ScannerCatchesTests(unittest.TestCase):
    """Things that must fail. Every one of these passed before the fix."""

    def test_solo_ownership_of_a_company_scale_platform(self):
        # The recorded regression wording carried an adjective the literal list missed.
        self.assertIn("SW-7", scan(r"\item Built a decentralized Data Mesh for the group."))

    def test_full_ml_lifecycle_ownership(self):
        self.assertIn("BS-1", scan(r"\item I owned the full ML lifecycle end to end."))

    def test_employer_excluded_from_all_documents(self):
        self.assertIn("Capgemini", scan(r"\item Capgemini Deutschland GmbH, Nov 2014 -- May 2015."))

    def test_certification_only_skill_without_its_context(self):
        self.assertIn("PyTorch", scan(r"\item Trained production models in PyTorch."))

    def test_forbidden_skill_split_by_markup(self):
        # \textbf{Snow}flake defeated a plain substring comparison.
        self.assertIn("Snowflake", scan(r"\item Delivered \textbf{Snow}flake pipelines."))

    def test_unregistered_but_forbidden_skill(self):
        self.assertIn("Groovy", scan(r"\item Maintained Groovy build jobs."))

    def test_unresolved_placeholder(self):
        self.assertIn("placeholder", scan(r"\item [GENERATE: Bullet]"))

    def test_wrong_contact_details(self):
        with tempfile.TemporaryDirectory() as directory:
            path = Path(directory) / "wrong.tex"
            path.write_text(
                "\\documentclass{resume}\n\\begin{document}\n"
                "\\contactline{wrong@example.com $\\vert$ +41 000 000 000}\n"
                "\\end{document}\n", encoding="utf-8")
            found = " | ".join(validator.scan_document(path, CLAIMS))
        self.assertIn("e-mail", found)
        self.assertIn("phone", found)


class ScannerAllowsTests(unittest.TestCase):
    """Things that must NOT fail. False positives taught the workflow to write around the checker."""

    def test_latex_comment_is_not_a_claim(self):
        self.assertEqual("", scan("% Never claim Terraform experience\n\\item Built pipelines."))

    def test_honestly_denying_a_skill_is_not_claiming_it(self):
        self.assertEqual("", scan(r"\item I have no Terraform experience and say so openly."))

    def test_german_denial_is_not_claiming_it(self):
        self.assertEqual("", scan(r"\item Keine Terraform-Erfahrung vorhanden."))

    def test_education_institution_is_not_the_employment_entry(self):
        # "Universitaet der Bundeswehr Muenchen" is a school, not the Bundeswehr employment
        # record, and in German packages it is written with LaTeX accent macros.
        body = r'\compactentry{M.Eng., Universit\"at der Bundeswehr M\"unchen}{Apr 2012 -- Oct 2013}'
        self.assertNotIn("BUNDESWEHR", scan(body))


class ShippedDocumentsTests(unittest.TestCase):
    """The packages built under the current rules must stay clean."""

    CURRENT = (
        "SBB_DataEngineer_AssetMgmt", "NVIDIA_SrDevOps_Zurich", "RUAG_AI_Engineer_C5I",
        "KdoCy_DevOps_Data_Platform", "CitadelSecurities_PlatformEngineer",
        "AkerBP_Data_Product_Architect",
    )

    def test_current_packages_have_no_findings(self):
        for folder in self.CURRENT:
            for document in (ROOT / "output" / folder).glob("e2e_*resume.tex"):
                with self.subTest(document=document.name):
                    self.assertEqual([], validator.scan_document(document, CLAIMS))


if __name__ == "__main__":
    unittest.main()