Esa Kataja
e2f3e8fbdc
The pdf module is the whole of M1 except the debug overlay, which needs detection results to draw. Source type is detected per PDF by looking for a page-covering image, and is always reported for confirmation rather than applied silently (ADR 0004). Rasters are extracted via Pixmap(doc, xref) rather than by decoding extract_image() bytes, because MuPDF handles JBIG2 and CCITT scans that no image library will. Scanned pages are extracted at the embedded image's native resolution; only vector pages are rendered, at 600 DPI. Verified against the corpus: Elaman nalka (vector) renders 4959x7017, Ketun joululaulu (scan) loads 1653x2332, Engel (scan) 2552x3504 — and Engel's page 2 is 2480 wide where page 1 is 2552, so scan width varies within one PDF. tests/test_pdf.py builds its own PDFs so the check runs without corpus files, which are copyrighted and gitignored. Closes #1, #2, #3
83 lines
2.6 KiB
Python
83 lines
2.6 KiB
Python
"""Runnable check for source classification and raster loading.
|
|
|
|
Builds its own PDFs so it needs no corpus files (scores are copyrighted and
|
|
gitignored). Run with `python tests/test_pdf.py`.
|
|
"""
|
|
|
|
from __future__ import annotations
|
|
|
|
import sys
|
|
from pathlib import Path
|
|
|
|
import numpy as np
|
|
import pymupdf
|
|
|
|
sys.path.insert(0, str(Path(__file__).resolve().parents[1]))
|
|
|
|
from noteman_slicer.pdf import SourceType, open_source, page_raster # noqa: E402
|
|
|
|
A4 = pymupdf.paper_rect("a4")
|
|
|
|
|
|
def _vector_pdf(path: Path, pages: int = 2) -> None:
|
|
doc = pymupdf.open()
|
|
for _ in range(pages):
|
|
page = doc.new_page(width=A4.width, height=A4.height)
|
|
page.draw_line((50, 100), (A4.width - 50, 100))
|
|
page.insert_text((50, 150), "notation", fontsize=24)
|
|
doc.save(path)
|
|
|
|
|
|
def _scan_pdf(path: Path, pages: int = 2, w: int = 1653, h: int = 2332) -> None:
|
|
"""Each page is one full-page grayscale image — what a real scan looks like."""
|
|
art = np.full((h, w), 255, np.uint8)
|
|
art[500:505, 100 : w - 100] = 0 # a staff line, so it isn't uniform
|
|
pix = pymupdf.Pixmap(pymupdf.csGRAY, w, h, bytearray(art.tobytes()), False)
|
|
doc = pymupdf.open()
|
|
for _ in range(pages):
|
|
page = doc.new_page(width=A4.width, height=A4.height)
|
|
page.insert_image(page.rect, pixmap=pix)
|
|
doc.save(path)
|
|
|
|
|
|
def main() -> int:
|
|
tmp = Path(__file__).with_name("_tmp")
|
|
tmp.mkdir(exist_ok=True)
|
|
vec, scan = tmp / "vector.pdf", tmp / "scan.pdf"
|
|
_vector_pdf(vec)
|
|
_scan_pdf(scan)
|
|
|
|
src = open_source(vec)
|
|
assert src.type is SourceType.VECTOR, src.type
|
|
assert not src.overridden
|
|
page = page_raster(src, 0)
|
|
# Rendered at 600 DPI, so an A4 page is ~4960px wide.
|
|
assert page.ndim == 2 and page.dtype == np.uint8, (page.ndim, page.dtype)
|
|
assert 4900 < page.shape[1] < 5000, page.shape
|
|
src.close()
|
|
|
|
src = open_source(scan)
|
|
assert src.type is SourceType.RASTER, src.type
|
|
page = page_raster(src, 0)
|
|
# Native resolution of the embedded image, NOT a 600 DPI re-render.
|
|
assert page.shape == (2332, 1653), page.shape
|
|
assert page.min() == 0 and page.max() == 255, (page.min(), page.max())
|
|
src.close()
|
|
|
|
# An override must win over detection, and say so.
|
|
src = open_source(scan, SourceType.VECTOR)
|
|
assert src.type is SourceType.VECTOR and src.detected is SourceType.RASTER
|
|
assert src.overridden
|
|
assert page_raster(src, 0).shape[1] > 4000, "override must force a render"
|
|
src.close()
|
|
|
|
for f in (vec, scan):
|
|
f.unlink()
|
|
tmp.rmdir()
|
|
print("ok")
|
|
return 0
|
|
|
|
|
|
if __name__ == "__main__":
|
|
sys.exit(main())
|