Files
Esa Kataja 38cb6ce09a Stop an edge artefact and a speck filter from destroying a song
Olukainen juomukainen came out unusable, from two separate faults.

The scanner left a dark line down the sheet edge, running the full height
of every page but the first. Being taller than any bracket it won every
overlap in anchor selection and swallowed the page into one system, so
five pages of six proposed no cuts at all. A page's brackets and barlines
are all about one system tall, so a stroke far taller than the typical
one is not notation — relative to the page's own strokes, since a page
holding one big system is legitimate.

The trim then removed each system's bottom line of lyrics. It judged ink
blobs by area, and a letter is nowhere near the threshold; a whole line
of them is dozens of blobs, none of which qualifies. Measure ink per row
and per column instead — a line of text carries plenty in total, and a
fleck's row carries almost none, which is the case the filter was for.

Detection now finds three systems on every page of that score, and every
slice keeps all four voices' words.
2026-07-29 12:22:08 +03:00

186 lines
7.1 KiB
Python

"""Runnable check for the render pipeline and bundle export."""
from __future__ import annotations
import json
import sys
import zipfile
from pathlib import Path
import cv2
import numpy as np
import pymupdf
sys.path.insert(0, str(Path(__file__).resolve().parents[1]))
from noteman_slicer import bundle # noqa: E402
from noteman_slicer.detect import detect_page # noqa: E402
from noteman_slicer.pdf import open_source, page_raster # noqa: E402
from noteman_slicer.project import Cut, Project, default_path # noqa: E402
from noteman_slicer.render import ( # noqa: E402
ALPHA_LEVELS,
_ink_bbox,
apply_levels,
encode,
pad_right,
render_slices,
scale_song,
)
W, H = 1200, 1600
GAP = 15
def _system(page: np.ndarray, top: int, right: int) -> None:
"""A bracket plus two staves, with a lyric line under each."""
page[top : top + 200, 100:104] = 0
for staff in (top, top + 140):
for i in range(5):
page[staff + i * GAP : staff + i * GAP + 2, 110:right] = 0
page[staff + 90 : staff + 105, 200 : right - 100] = 0
def _scan_pdf(path: Path) -> None:
art = np.full((H, W), 255, np.uint8)
art[40:60, 400:800] = 0 # title, far from any system
_system(art, 300, 1100)
_system(art, 800, 900) # narrower: exercises the right pad
pix = pymupdf.Pixmap(pymupdf.csGRAY, W, H, bytearray(art.tobytes()), False)
doc = pymupdf.open()
page = doc.new_page(width=595, height=842)
page.insert_image(page.rect, pixmap=pix)
doc.save(path)
def main() -> int:
tmp = Path(__file__).with_name("_tmp")
tmp.mkdir(exist_ok=True)
pdf = tmp / "scan.pdf"
_scan_pdf(pdf)
source = open_source(pdf)
gray = page_raster(source, 0)
project = Project.from_detection(pdf, [detect_page(gray)], [gray.shape[0]])
slices = render_slices(project, source)
assert len(slices) == 2, f"expected 2 kept slices, got {len(slices)}"
# The title is far from any bracket, so it is not in a kept slice: both
# slices must be shorter than the gap between the systems.
assert all(s.gray.shape[0] < 400 for s in slices), [s.gray.shape for s in slices]
# System 2 is drawn narrower, so before padding the widths differ.
assert slices[0].width != slices[1].width, "the fixture should differ in width"
scaled = scale_song(slices, cap=4000) # a cap far above the fixture
assert all(abs(a.shape[1] - b.width) <= 2 for a, b in zip(scaled, slices)), (
"never upscale: a song narrower than the cap must be left alone"
)
padded = pad_right(scale_song(slices))
assert len({p.shape[1] for p in padded}) == 1, "slices must share one width"
assert max(p.shape[1] for p in padded) <= 1920
rgba = cv2.imdecode(np.frombuffer(encode(padded[0]), np.uint8), cv2.IMREAD_UNCHANGED)
assert rgba.shape[2] == 4
assert rgba[:, :, :3].max() == 0, "ink must be pure black"
assert rgba[:, :, 3].max() == 255, "full ink must be fully opaque"
assert rgba[:, :, 3].min() == 0, "paper must be fully transparent"
assert len(np.unique(rgba[:, :, 3])) <= ALPHA_LEVELS
# Trim keeps a line of lyrics and drops a fleck. Each letter is its own
# small blob, so judging blobs by area threw the whole line away and the
# bottom voice lost its words; a fleck's row carries almost no ink at all.
art = np.full((300, 800), 255, np.uint8)
art[100:150, 50:750] = 0 # a staff
for x in range(60, 700, 30): # lyrics: many small glyphs, one row
art[200:220, x : x + 14] = 0
art[5:9, 10:14] = 0 # a fleck in the far corner
x0, y0, x1, y1 = _ink_bbox(art)
assert (y0, y1) == (100, 220), f"lyrics kept, fleck dropped: {(y0, y1)}"
assert (x0, x1) == (50, 750), (x0, x1)
assert _ink_bbox(np.full((50, 50), 255, np.uint8)) is None, "blank slice has no box"
# Levels: a white point below the paper value wipes the paper out entirely.
faint = np.full((10, 10), 200, np.uint8)
assert apply_levels(faint, 0, 180).max() == 255
# The Engel case: a section label printed in the left margin at a height
# that belongs to the *next* system. A straight cut cannot separate it from
# the previous system's lyrics; a stepped one can.
label_top, label_bottom = 620, 680
labelled = tmp / "labelled.pdf"
art = np.full((H, W), 255, np.uint8)
_system(art, 300, 1100)
_system(art, 800, 900)
art[label_top:label_bottom, 120:300] = 0 # the label
art[label_top:label_bottom, 500:1000] = 0 # system 1's trailing lyrics, same rows
pix = pymupdf.Pixmap(pymupdf.csGRAY, W, H, bytearray(art.tobytes()), False)
doc = pymupdf.open()
doc.new_page(width=595, height=842).insert_image(pymupdf.Rect(0, 0, 595, 842), pixmap=pix)
doc.save(labelled)
src2 = open_source(labelled)
g2 = page_raster(src2, 0)
proj2 = Project.from_detection(labelled, [detect_page(g2)], [g2.shape[0]])
page = proj2.pages[0]
scale = g2.shape[0] / H
def ink(images: list) -> list[int]:
"""Ink in the left margin of each slice — where the label sits."""
return [int((i.gray[:, : int(i.width * 0.3)] < 128).sum()) for i in images]
# Straight cut through the middle of that band: the label goes with
# whichever side the line falls on, and cannot be separated.
band_mid = (label_top + label_bottom) / 2 * scale / g2.shape[0]
page.cuts[1] = Cut.straight(band_mid)
straight_ink = ink(render_slices(proj2, src2))
# Stepped: above the label on the left, below the lyrics on the right.
above = (label_top - 10) * scale / g2.shape[0]
below = (label_bottom + 10) * scale / g2.shape[0]
page.cuts[1] = Cut([(0.0, above), (0.35, above), (0.35, below), (1.0, below)])
stepped_ink = ink(render_slices(proj2, src2))
# The straight cut splits the label down the middle; the stepped cut gives
# all of it to the lower slice and none to the upper.
assert stepped_ink[1] > straight_ink[1], (
f"the label must move into the lower slice: {straight_ink}{stepped_ink}"
)
assert stepped_ink[0] < straight_ink[0], (
f"and out of the upper one: {straight_ink}{stepped_ink}"
)
src2.close()
labelled.unlink()
# Bundle. A title is required; everything else is optional.
try:
bundle.write(project, source, tmp / "untitled.zip")
except ValueError as error:
assert "title" in str(error)
else:
raise AssertionError("export without a title should be refused")
project.metadata["title"] = "Test song"
out = bundle.write(project, source, tmp / "song.zip")
with zipfile.ZipFile(out) as zf:
names = zf.namelist()
assert "song.json" in names and "original.pdf" in names, names
meta = json.loads(zf.read("song.json"))
assert meta["v"] == 1
files = [s["file"] for s in meta["slices"]]
assert files == ["001.webp", "002.webp"], files
assert all(f in names for f in files)
source.close()
# Exporting marks the project spent, which writes the project file.
for f in (pdf, out, default_path(pdf)):
f.unlink(missing_ok=True)
tmp.rmdir()
print("ok")
return 0
if __name__ == "__main__":
sys.exit(main())