applepy/tests/test_reporters.py

from pathlib import Path

from applepy.findings import Finding, Severity
from applepy.reporters.markdown import write_markdown_report
from applepy.reporters.xlsx import (
    _evidence_chunks_for_excel,
    _xlsx_cell_text,
    write_xlsx_report,
)


def test_markdown_and_xlsx(tmp_path: Path) -> None:
    f = Finding(
        id="t-1",
        title="Test finding",
        category="Test",
        severity=Severity.INFORMATIONAL,
        description="Desc",
        evidence="Ev",
        worksheet="Test checks",
        mitre_techniques=("T1082",),
    )
    cis = Finding(
        id="cis-099",
        title="CIS tab sample",
        category="Compliance",
        severity=Severity.INFORMATIONAL,
        description="d",
        evidence="e",
        worksheet="CIS",
    )
    md = tmp_path / "r.md"
    xl = tmp_path / "f.xlsx"
    write_markdown_report(md, [f, cis], ["warn1"])
    write_xlsx_report(xl, [f, cis])
    md_text = md.read_text(encoding="utf-8")
    assert md_text.startswith("# ApplePY")
    assert "## Contents" in md_text
    assert "[Executive summary](#executive-summary)" in md_text
    assert "overarching themes" in md_text.lower()
    assert "## Other findings" in md_text or "## Core platform and controls" in md_text
    assert "Detail category:" in md_text
    assert "Granular categories covered here:" in md_text
    assert "#### Evidence" in md_text
    assert "```" in md_text
    assert "CIS macOS worksheet index" in md_text
    assert "cis-099" in md_text
    assert xl.is_file() and xl.stat().st_size > 200
    from openpyxl import load_workbook

    wb = load_workbook(xl)
    assert wb.sheetnames[0] == "Summary"
    assert wb.sheetnames[1] == "Findings list"
    assert "CIS" in wb.sheetnames
    assert wb["CIS"]["A2"].value == "cis-099"
    fl = wb["Findings list"]
    assert fl["A1"].value == "ID"
    assert fl["E1"].value == "Detail worksheet"
    assert fl.max_row == 1
    # Summary sheet must contain the worksheet index section
    summary_ws = wb["Summary"]
    col_a_vals = [summary_ws.cell(row=r, column=1).value for r in range(1, summary_ws.max_row + 1)]
    assert "Findings list (non-informational)" in col_a_vals
    assert "CIS" in col_a_vals


def test_xlsx_cell_text_strips_control_chars() -> None:
    raw = "a\x00b\x08c"
    assert _xlsx_cell_text(raw) == "a b c"


def test_evidence_chunks_split_for_excel_limit() -> None:
    long_ev = "X" * 40000
    chunks = _evidence_chunks_for_excel(long_ev)
    assert len(chunks) >= 2
    assert all(len(c) <= 32767 for c in chunks)
    assert "".join(chunks) == _xlsx_cell_text(long_ev)


def test_xlsx_sorts_by_severity_descending(tmp_path: Path) -> None:
    from openpyxl import load_workbook

    lo = Finding(
        id="a-low",
        title="Later",
        category="Test",
        severity=Severity.INFORMATIONAL,
        description="d",
        evidence="e",
        worksheet="Zebra",
    )
    hi = Finding(
        id="z-high",
        title="First",
        category="Test",
        severity=Severity.HIGH,
        description="d",
        evidence="e",
        worksheet="Zebra",
    )
    xl = tmp_path / "sort.xlsx"
    write_xlsx_report(xl, [lo, hi])
    wb = load_workbook(xl)
    assert wb.sheetnames[:2] == ["Summary", "Findings list"]
    fl = wb["Findings list"]
    assert fl.max_row == 2
    assert fl["A2"].value == "z-high"
    assert fl["C2"].value == "high"
    ws = wb["Zebra"]
    assert ws["A2"].value == "z-high"
    assert ws["A3"].value == "a-low"


def test_xlsx_findings_list_includes_non_informational_only(tmp_path: Path) -> None:
    from openpyxl import load_workbook

    info = Finding(
        id="i-1",
        title="Noise",
        category="Test",
        severity=Severity.INFORMATIONAL,
        description="d",
        evidence="e",
        worksheet="Alpha",
    )
    med = Finding(
        id="m-1",
        title="Material",
        category="Test",
        severity=Severity.MEDIUM,
        description="d",
        evidence="e",
        worksheet="Alpha",
    )
    xl = tmp_path / "fl.xlsx"
    write_xlsx_report(xl, [info, med])
    wb = load_workbook(xl)
    fl = wb["Findings list"]
    assert fl.max_row == 2
    assert fl["A2"].value == "m-1"
    assert fl["E2"].value == "Alpha"


def test_xlsx_severity_row_has_distinct_fill(tmp_path: Path) -> None:
    from openpyxl import load_workbook

    high_f = Finding(
        id="h-sev",
        title="High item",
        category="Test",
        severity=Severity.HIGH,
        description="d",
        evidence="e",
        worksheet="Alpha",
    )
    low_f = Finding(
        id="l-sev",
        title="Low item",
        category="Test",
        severity=Severity.LOW,
        description="d",
        evidence="e",
        worksheet="Alpha",
    )
    xl = tmp_path / "sevfill.xlsx"
    write_xlsx_report(xl, [high_f, low_f])
    wb = load_workbook(xl)
    ws = wb["Alpha"]
    hi_fill = ws["A2"].fill
    lo_fill = ws["A3"].fill
    assert hi_fill.fill_type == "solid"
    assert lo_fill.fill_type == "solid"
    assert hi_fill.start_color.rgb != lo_fill.start_color.rgb
    fl = wb["Findings list"]
    assert fl["A2"].fill.start_color.rgb == hi_fill.start_color.rgb


def test_xlsx_long_evidence_writes_continuation_rows(tmp_path: Path) -> None:
    from openpyxl import load_workbook

    long_ev = "Y" * 35000
    f = Finding(
        id="long-1",
        title="Long evidence",
        category="Test",
        severity=Severity.INFORMATIONAL,
        description="d",
        evidence=long_ev,
        worksheet="Evidence sheet",
    )
    xl = tmp_path / "big.xlsx"
    write_xlsx_report(xl, [f])
    wb = load_workbook(xl)
    assert wb.sheetnames[1] == "Findings list"
    assert wb["Findings list"].max_row == 1
    ws = wb["Evidence sheet"]
    assert ws.max_row >= 3