import pytest
from app.ingest.extractors import extract, ExtractedPage, UnsupportedFileType


def test_extract_pdf_returns_pages(sample_pdf_bytes):
    pages = extract(sample_pdf_bytes, "pdf", filename="x.pdf")
    assert len(pages) == 2
    assert pages[0].page == 1
    assert "Seite eins" in pages[0].text
    assert pages[1].page == 2
    assert "Seite zwei" in pages[1].text


def test_extract_docx_returns_single_page(sample_docx_bytes):
    pages = extract(sample_docx_bytes, "docx", filename="x.docx")
    assert len(pages) == 1
    assert pages[0].page == 1
    assert "Erster Absatz." in pages[0].text
    assert "Zweiter Absatz" in pages[0].text


def test_extract_md_returns_single_page(sample_md_bytes):
    pages = extract(sample_md_bytes, "md", filename="x.md")
    assert len(pages) == 1
    assert pages[0].page == 1
    assert "First paragraph." in pages[0].text


def test_extract_xlsx_returns_filename_pseudo_text(sample_xlsx_bytes):
    pages = extract(sample_xlsx_bytes, "xlsx", filename="my-sheet.xlsx")
    assert len(pages) == 1
    assert pages[0].page == 1
    assert pages[0].text == "Tabelle: my-sheet.xlsx"


def test_extract_unsupported_raises():
    with pytest.raises(UnsupportedFileType):
        extract(b"data", "txt", filename="x.txt")