add pdftomd

tests/test_pdf_splitter.py

@@ -0,0 +1,62 @@
+from __future__ import annotations
+
+from pathlib import Path
+
+import pytest
+from pypdf import PdfReader, PdfWriter
+
+from pdf2md.pdf_splitter import PdfChunkError, count_pdf_pages, plan_pdf_chunks, write_pdf_chunk
+
+
+def make_blank_pdf(path: Path, page_count: int) -> Path:
+    path.parent.mkdir(parents=True, exist_ok=True)
+    writer = PdfWriter()
+    for _ in range(page_count):
+        writer.add_blank_page(width=72, height=72)
+    with path.open("wb") as file:
+        writer.write(file)
+    return path
+
+
+@pytest.mark.parametrize(
+    ("page_count", "expected_ranges"),
+    [
+        (1, [(1, 1)]),
+        (20, [(1, 20)]),
+        (21, [(1, 20), (21, 21)]),
+        (40, [(1, 20), (21, 40)]),
+        (41, [(1, 20), (21, 40), (41, 41)]),
+    ],
+)
+def test_plan_pdf_chunks_uses_one_based_ranges_and_names(
+    tmp_path: Path,
+    page_count: int,
+    expected_ranges: list[tuple[int, int]],
+) -> None:
+    pdf = make_blank_pdf(tmp_path / "paper.pdf", page_count)
+
+    chunks = plan_pdf_chunks(pdf, chunk_pages=20)
+
+    assert count_pdf_pages(pdf) == page_count
+    assert [(chunk.source_page_start, chunk.source_page_end) for chunk in chunks] == expected_ranges
+    assert [chunk.output_filename for chunk in chunks] == [
+        f"paper.part-{index:03d}.pages-{start:03d}-{end:03d}.pdf"
+        for index, (start, end) in enumerate(expected_ranges, start=1)
+    ]
+
+
+def test_write_pdf_chunk_writes_expected_page_count(tmp_path: Path) -> None:
+    pdf = make_blank_pdf(tmp_path / "paper.pdf", 41)
+    chunk = plan_pdf_chunks(pdf, chunk_pages=20)[1]
+
+    output = write_pdf_chunk(chunk, tmp_path / "chunks" / chunk.output_filename)
+
+    assert output.exists()
+    assert len(PdfReader(output).pages) == 20
+
+
+def test_plan_pdf_chunks_rejects_non_positive_chunk_size(tmp_path: Path) -> None:
+    pdf = make_blank_pdf(tmp_path / "paper.pdf", 1)
+
+    with pytest.raises(PdfChunkError, match="positive integer"):
+        plan_pdf_chunks(pdf, chunk_pages=0)