office_translator/tests/services/quality/test_file_extractor.py

"""
Tests for services/quality/file_extractor.py
Uses real files generated via temporary paths.

On Windows, tempfile.NamedTemporaryFile holds the file open and blocks
overwrite, so we use a plain temp directory + manual filename instead.
"""
import tempfile
import os
from pathlib import Path

import pytest

from services.quality.file_extractor import (
    extract_sample,
    DEFAULT_MAX_SAMPLES,
)


class TestExtractSample:
    def test_returns_empty_for_missing_file(self):
        result = extract_sample(Path("/nonexistent/path/file.docx"), ".docx")
        assert result == []

    def test_returns_empty_for_none_path(self):
        result = extract_sample(None, ".docx")
        assert result == []

    def test_returns_empty_for_unsupported_extension(self):
        # .txt isn't supported — should return [] silently
        with tempfile.TemporaryDirectory() as d:
            p = Path(d) / "test.txt"
            p.write_text("some text")
            result = extract_sample(p, ".txt")
            assert result == []


def _make_tmp_path(suffix: str) -> Path:
    """Create a unique temp file path. File does not exist yet."""
    fd, name = tempfile.mkstemp(suffix=suffix)
    os.close(fd)
    return Path(name)


class TestDocxExtraction:
    def test_extracts_paragraphs(self):
        from docx import Document
        doc = Document()
        doc.add_paragraph("Bonjour le monde")
        doc.add_paragraph("Comment allez-vous?")
        doc.add_paragraph("Merci beaucoup")
        p = _make_tmp_path(".docx")
        try:
            doc.save(str(p))
            result = extract_sample(p, ".docx", max_samples=10)
            assert len(result) >= 1
            texts = [s["translated"] for s in result]
            assert "Bonjour le monde" in texts
        finally:
            try:
                p.unlink()
            except (OSError, PermissionError):
                pass

    def test_respects_max_samples(self):
        from docx import Document
        doc = Document()
        for i in range(50):
            doc.add_paragraph(f"Paragraphe numero {i} avec du texte")
        p = _make_tmp_path(".docx")
        try:
            doc.save(str(p))
            result = extract_sample(p, ".docx", max_samples=5)
            assert len(result) == 5
        finally:
            try:
                p.unlink()
            except (OSError, PermissionError):
                pass

    def test_handles_empty_doc(self):
        from docx import Document
        doc = Document()
        p = _make_tmp_path(".docx")
        try:
            doc.save(str(p))
            result = extract_sample(p, ".docx")
            assert result == []
        finally:
            try:
                p.unlink()
            except (OSError, PermissionError):
                pass


class TestXlsxExtraction:
    def test_extracts_cells(self):
        from openpyxl import Workbook
        wb = Workbook()
        ws = wb.active
        ws["A1"] = "Bonjour"
        ws["A2"] = "Monde"
        ws["A3"] = "Comment"
        p = _make_tmp_path(".xlsx")
        try:
            wb.save(str(p))
            wb.close()
            result = extract_sample(p, ".xlsx", max_samples=10)
            assert len(result) >= 1
            texts = [s["translated"] for s in result]
            assert "Bonjour" in texts
        finally:
            try:
                p.unlink()
            except (OSError, PermissionError):
                pass

    def test_skips_numeric_cells(self):
        from openpyxl import Workbook
        wb = Workbook()
        ws = wb.active
        ws["A1"] = 100
        ws["A2"] = 200
        ws["A3"] = "Hello"
        p = _make_tmp_path(".xlsx")
        try:
            wb.save(str(p))
            wb.close()
            result = extract_sample(p, ".xlsx")
            texts = [s["translated"] for s in result]
            assert "Hello" in texts
            assert 100 not in texts  # numeric only cells skipped
        finally:
            try:
                p.unlink()
            except (OSError, PermissionError):
                pass


class TestPptxExtraction:
    def test_extracts_slide_text(self):
        from pptx import Presentation
        pres = Presentation()
        slide = pres.slides.add_slide(pres.slide_layouts[0])
        slide.shapes.title.text = "Bonjour le monde"
        p = _make_tmp_path(".pptx")
        try:
            pres.save(str(p))
            result = extract_sample(p, ".pptx")
            assert len(result) >= 1
            assert result[0]["translated"] == "Bonjour le monde"
        finally:
            try:
                p.unlink()
            except (OSError, PermissionError):
                pass


class TestPdfExtraction:
    def test_extracts_pdf_text(self):
        # Create a minimal PDF using reportlab if available, else skip
        pytest.importorskip("fitz")
        try:
            from reportlab.pdfgen import canvas
        except ImportError:
            pytest.skip("reportlab not available")
        p = _make_tmp_path(".pdf")
        try:
            c = canvas.Canvas(str(p))
            c.drawString(100, 750, "Bonjour le monde")
            c.drawString(100, 700, "Comment allez vous")
            c.save()
            result = extract_sample(p, ".pdf")
            assert len(result) >= 1
            texts = [s["translated"] for s in result]
            assert any("Bonjour" in t for t in texts)
        finally:
            try:
                p.unlink()
            except (OSError, PermissionError):
                pass