job-research/tests/profile/test_cv_extractor.py

from textwrap import dedent
from pathlib import Path

from job_research.profile.cv_extractor import extract_cv_signals
from job_research.profile.cv_extractor import extract_pdf_text


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


def test_extract_cv_signals_allows_single_word_titles() -> None:
    text = dedent(
        """
        Tonio
        Location: France
        Consultant at Accenture
        """
    ).strip()

    extracted = extract_cv_signals(text)

    assert extracted["experience_entries"] == [
        {"title": "Consultant", "company": "Accenture"}
    ]


def test_extract_cv_signals_allows_lowercase_company_names() -> None:
    text = dedent(
        """
        Tonio
        Location: France
        Data Engineer at leboncoin
        """
    ).strip()

    extracted = extract_cv_signals(text)

    assert extracted["experience_entries"] == [
        {"title": "Data Engineer", "company": "leboncoin"}
    ]


def test_extract_cv_signals_ignores_prose_after_company_name() -> None:
    text = dedent(
        """
        Tonio
        Location: France
        Senior engineer at Microsoft before moving to Paris.
        """
    ).strip()

    extracted = extract_cv_signals(text)

    assert extracted["experience_entries"] == []


def test_extract_cv_signals_normalizes_bullet_prefixed_fields_and_experience() -> None:
    text = dedent(
        """
        Tonio
        - Location: France
        - Data Engineer at Company A
        """
    ).strip()

    extracted = extract_cv_signals(text)

    assert extracted["location"] == "France"
    assert extracted["experience_entries"] == [
        {"title": "Data Engineer", "company": "Company A"}
    ]


def test_extract_cv_signals_normalizes_en_dash_bullet_prefixed_fields_and_experience() -> None:
    text = dedent(
        """
        Tonio
        – Location: France
        — Data Engineer at Company A
        """
    ).strip()

    extracted = extract_cv_signals(text)

    assert extracted["location"] == "France"
    assert extracted["experience_entries"] == [
        {"title": "Data Engineer", "company": "Company A"}
    ]


def test_extract_cv_signals_parses_french_experience_connectors() -> None:
    text = dedent(
        """
        Tonio
        Location: France
        Ingénieur chez Dassault Systèmes
        Développeur au CNRS
        """
    ).strip()

    extracted = extract_cv_signals(text)

    assert extracted["experience_entries"] == [
        {"title": "Ingénieur", "company": "Dassault Systèmes"},
        {"title": "Développeur", "company": "CNRS"},
    ]


def test_extract_cv_signals_ignores_in_paris_prose_tail() -> None:
    text = dedent(
        """
        Tonio
        Location: France
        Data Engineer at Microsoft in Paris
        """
    ).strip()

    extracted = extract_cv_signals(text)

    assert extracted["experience_entries"] == []


def test_extract_cv_signals_extracts_education_entries_after_heading() -> None:
    text = dedent(
        """
        Tonio
        Location: France
        Education:
        - Master of Science in Data Science at University of Paris
        """
    ).strip()

    extracted = extract_cv_signals(text)

    assert extracted["education_entries"] == [
        {
            "credential": "Master of Science in Data Science",
            "institution": "University of Paris",
        }
    ]


def test_extract_cv_signals_extracts_common_french_education_entries() -> None:
    text = dedent(
        """
        Tonio
        Location: France
        Education:
        Diplôme d'ingénieur
        CentraleSupélec
        MSc
        University of Paris
        BSc
        University of Oxford
        Bac+5
        École Polytechnique
        """
    ).strip()

    extracted = extract_cv_signals(text)

    assert extracted["education_entries"] == [
        {
            "credential": "Diplôme d'ingénieur",
            "institution": "CentraleSupélec",
        },
        {"credential": "MSc", "institution": "University of Paris"},
        {"credential": "BSc", "institution": "University of Oxford"},
        {"credential": "Bac+5", "institution": "École Polytechnique"},
    ]


def test_extract_cv_signals_ignores_before_moving_prose_tail() -> None:
    text = dedent(
        """
        Tonio
        Location: France
        Senior Engineer at Microsoft Before moving to Paris.
        """
    ).strip()

    extracted = extract_cv_signals(text)

    assert extracted["experience_entries"] == []


def test_extract_pdf_text_skips_blank_pages(monkeypatch) -> None:
    class FakePage:
        def __init__(self, text: str | None) -> None:
            self._text = text

        def extract_text(self) -> str | None:
            return self._text

    class FakePdfReader:
        def __init__(self, path: str) -> None:
            self.path = path
            self.pages = [
                FakePage(None),
                FakePage("Tonio"),
                FakePage(""),
                FakePage("Data Engineer"),
            ]

    seen_paths: list[str] = []

    def fake_pdf_reader(path: str) -> FakePdfReader:
        seen_paths.append(path)
        return FakePdfReader(path)

    monkeypatch.setattr("job_research.profile.cv_extractor.PdfReader", fake_pdf_reader)

    extracted = extract_pdf_text(Path("cv.pdf"))

    assert extracted == "Tonio\nData Engineer"
    assert seen_paths == ["cv.pdf"]