pdf-accessibility/tests/test_remediation_extended.py

"""
Extended tests for pdf_remediation.py — covers PDFRemediator analysis and fix methods.
"""

import pytest
from pathlib import Path
from unittest.mock import patch, MagicMock


class TestPDFRemediatorAnalysis:
    def test_analyze_and_suggest_fixes(self, sample_poor_pdf):
        from pdf_remediation import PDFRemediator

        remediator = PDFRemediator(str(sample_poor_pdf))
        suggestions = remediator.analyze_and_suggest_fixes()

        assert isinstance(suggestions, dict)
        # Should have at least one category
        assert len(suggestions) >= 0

    def test_analyze_good_pdf(self, sample_good_pdf):
        from pdf_remediation import PDFRemediator

        remediator = PDFRemediator(str(sample_good_pdf))
        suggestions = remediator.analyze_and_suggest_fixes()

        assert isinstance(suggestions, dict)


class TestPDFRemediatorApplyFixes:
    def test_apply_fixes_produces_output(self, sample_poor_pdf, tmp_path):
        from pdf_remediation import PDFRemediator

        output_path = str(tmp_path / "fixed.pdf")
        remediator = PDFRemediator(str(sample_poor_pdf))

        result = remediator.apply_fixes([], output_path=output_path)
        assert isinstance(result, dict)

    def test_apply_fixes_with_title(self, sample_poor_pdf, tmp_path):
        from pdf_remediation import PDFRemediator

        output_path = str(tmp_path / "titled.pdf")
        remediator = PDFRemediator(str(sample_poor_pdf))

        result = remediator.apply_fixes(
            ["add_title"], output_path=output_path,
            custom_values={"title": "Test Title"}
        )
        assert isinstance(result, dict)

    def test_apply_fixes_default_output_path(self, sample_poor_pdf):
        from pdf_remediation import PDFRemediator

        remediator = PDFRemediator(str(sample_poor_pdf))
        result = remediator.apply_fixes([])
        assert isinstance(result, dict)


class TestPDFRemediatorFixMethods:
    def test_fix_add_title(self, sample_poor_pdf):
        from pdf_remediation import PDFRemediator

        remediator = PDFRemediator(str(sample_poor_pdf))
        # Clone pages first (required before fix methods)
        for page in remediator.reader.pages:
            remediator.writer.add_page(page)

        if hasattr(remediator, '_fix_add_title'):
            remediator._fix_add_title("Test Title")
        else:
            pytest.skip("_fix_add_title not available")

    def test_fix_set_language(self, sample_poor_pdf):
        from pdf_remediation import PDFRemediator

        remediator = PDFRemediator(str(sample_poor_pdf))
        for page in remediator.reader.pages:
            remediator.writer.add_page(page)

        if hasattr(remediator, '_fix_set_language'):
            remediator._fix_set_language("en-US")
        else:
            pytest.skip("_fix_set_language not available")

    def test_fix_mark_tagged(self, sample_poor_pdf):
        from pdf_remediation import PDFRemediator

        remediator = PDFRemediator(str(sample_poor_pdf))
        for page in remediator.reader.pages:
            remediator.writer.add_page(page)

        if hasattr(remediator, '_fix_mark_tagged'):
            remediator._fix_mark_tagged()
        else:
            pytest.skip("_fix_mark_tagged not available")


class TestVeraPDFValidatorExtended:
    @patch("subprocess.run")
    def test_validate_compliant(self, mock_run, sample_good_pdf):
        from pdf_remediation import VeraPDFValidator

        mock_run.return_value = MagicMock(
            returncode=0,
            stdout='{"report":{"jobs":[{"validationResult":[{"details":{"passedRules":50,"failedRules":0,"passedChecks":200,"failedChecks":0,"ruleSummaries":[]}}]}]}}',
            stderr=""
        )

        validator = VeraPDFValidator()
        result = validator.validate(str(sample_good_pdf))

        assert result["compliant"] is True
        assert result["passed_rules"] == 50
        assert result["failed_rules"] == 0

    @patch("subprocess.run")
    def test_validate_non_compliant(self, mock_run, sample_poor_pdf):
        from pdf_remediation import VeraPDFValidator

        mock_run.return_value = MagicMock(
            returncode=0,
            stdout='{"report":{"jobs":[{"validationResult":[{"details":{"passedRules":30,"failedRules":5,"passedChecks":150,"failedChecks":10,"ruleSummaries":[{"ruleStatus":"FAILED","clause":"7.1","description":"Missing tag","testNumber":1,"failedChecks":2}]}}]}]}}',
            stderr=""
        )

        validator = VeraPDFValidator()
        result = validator.validate(str(sample_poor_pdf))

        assert result["compliant"] is False
        assert result["failed_rules"] == 5
        assert len(result["errors"]) == 1

    @patch("subprocess.run")
    def test_validate_timeout(self, mock_run, sample_good_pdf):
        import subprocess as sp
        from pdf_remediation import VeraPDFValidator

        mock_run.side_effect = sp.TimeoutExpired(cmd="verapdf", timeout=30)

        validator = VeraPDFValidator()
        result = validator.validate(str(sample_good_pdf), timeout=30)

        assert "error" in result
        assert "timeout" in result["error"].lower()

    @patch("subprocess.run")
    def test_validate_process_error(self, mock_run, sample_good_pdf):
        from pdf_remediation import VeraPDFValidator

        mock_run.return_value = MagicMock(
            returncode=1,
            stdout="",
            stderr="veraPDF not found"
        )

        validator = VeraPDFValidator()
        result = validator.validate(str(sample_good_pdf))

        assert "error" in result

    @patch("subprocess.run")
    def test_validate_no_jobs(self, mock_run, sample_good_pdf):
        from pdf_remediation import VeraPDFValidator

        mock_run.return_value = MagicMock(
            returncode=0,
            stdout='{"report":{"jobs":[]}}',
            stderr=""
        )

        validator = VeraPDFValidator()
        result = validator.validate(str(sample_good_pdf))

        assert "error" in result


class TestPDFRemediatorInit:
    def test_reader_and_writer_types(self, sample_good_pdf):
        from pdf_remediation import PDFRemediator
        from pypdf import PdfReader, PdfWriter

        remediator = PDFRemediator(str(sample_good_pdf))
        assert isinstance(remediator.reader, PdfReader)
        assert isinstance(remediator.writer, PdfWriter)
        assert remediator.fixes_applied == []

    def test_pdf_path_stored(self, sample_good_pdf):
        from pdf_remediation import PDFRemediator

        remediator = PDFRemediator(str(sample_good_pdf))
        assert remediator.pdf_path == Path(sample_good_pdf)


if __name__ == "__main__":
    pytest.main([__file__, "-v"])