Re-engraving is a rescue path for the handful of systems a scan cannot deliver, so the window is an editing surface rather than an automation project. Three full-width rows - the scanned system, the render, the form - because a system is wide and short and the job is comparing one against the other bar by bar. The render is shown scaled to the scan's staff height, which is what export does anyway, so it previews the real thing. A form rather than a text box. Key and time are slice-level, clef, notes and lyrics per voice: every staff in a system carries the same key signature, and Kaipaava proves it across five-staff and two-staff systems alike. Notes and lyrics stay raw LilyPond, so slurs, dynamics, tuplets and the laissezVibrer/repeatTie idiom for ties crossing into the next slice all work untouched. Notes are entered in \relative mode, referenced to the middle of each clef's staff, so a part needs no octave marks at all in the common case. The time signature is used for spacing and bar checks but not printed: the printed score repeats the key at every system and the time only at the first, so a re-engraved middle slice showing one would stand out. Seeded from what can be known reliably. Voice count comes from counting staves in the slice; key, time and clefs are inherited from the song, because the slices being re-engraved are the illegible ones and reading a key signature off them is exactly the measurement that fails. After the first replacement in a song only the notes need typing. Staff counting needed two corrections against the corpus: compare gaps against line spacing rather than staff height, since adjacent staves can sit closer together than one staff is tall; and require five lines in a group, since Engel's 'uh______' lyric extenders are long horizontal runs too and each counted as a staff. Kaipaava now reads 2,2,2,2,5 on page 1, Ketun 6, Engel 4. Also in this change: - Title is required for export, every other metadata field optional, enforced in bundle.write so the CLI and the editor both get it. Tempo added; noteman already has a free-form column for it. - The panel is a splitter rather than a fixed width, sections collapse under bold grey disclosure headers, and it scrolls. - A re-engraved slice is washed amber with an ENGRAVED badge, and markers get badges too. Thin coloured text was invisible against a scan. Closes #31 Closes #32 Closes #33 Closes #34
172 lines
6.3 KiB
Python
172 lines
6.3 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,
|
|
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
|
|
|
|
# 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())
|