Esa Kataja
6ff956a622
Systems anchor on the vertical bracket and expand over nearby ink, per ADR 0006. Two corrections the corpus forced: - Expansion measures distance from the bracket, never from the growing extent. A chaining expansion hops between the closely-stacked lines of a title block and walks the whole way up the page — on Engel p1 it swallowed the title into system 1 and the copyright footer into system 3. - Reach is 1.5 staff heights, which takes in the lyrics below the last staff and the tempo mark and INTRO box above the first, while leaving the title block and footer out. Verified against the corpus. Ketun joululaulu: 2 systems per page except p7 (3) and p12 (1), staff 48px throughout, skew -2.7 to +1.2 per page, and p2 system 1 spans 179-1071 where its bracket is 177-994 — the difference being the bottom voice's lyric line. Engel: 2-3 systems per page, staff 70-72px. Elaman nalka: 3 systems per page, 0 skew, staff 118px at 600 DPI. The overlay dump is what made both bugs visible, and stays as the tool for diagnosing a page that comes out wrong. Closes #4, #5, #6, #7, #8, #9
83 lines
2.8 KiB
Python
83 lines
2.8 KiB
Python
"""Command line entry point."""
|
||
|
||
from __future__ import annotations
|
||
|
||
import argparse
|
||
import sys
|
||
|
||
import numpy as np
|
||
|
||
from pathlib import Path
|
||
|
||
from . import __version__, overlay
|
||
from .detect import detect_page
|
||
from .pdf import SourceType, open_source, page_raster
|
||
|
||
|
||
def _info(args: argparse.Namespace) -> int:
|
||
source = open_source(args.pdf, SourceType(args.type) if args.type else None)
|
||
note = f" (detected {source.detected.value}, overridden)" if source.overridden else ""
|
||
print(f"{source.path.name}: {source.type.value}{note}, {len(source)} pages")
|
||
for i in range(len(source)):
|
||
h, w = page_raster(source, i).shape
|
||
print(f" p{i + 1:<3} {w}x{h}")
|
||
source.close()
|
||
return 0
|
||
|
||
|
||
def _detect(args: argparse.Namespace) -> int:
|
||
source = open_source(args.pdf, SourceType(args.type) if args.type else None)
|
||
out = Path(args.out)
|
||
out.mkdir(parents=True, exist_ok=True)
|
||
pages = range(len(source)) if args.page is None else [args.page - 1]
|
||
|
||
for i in pages:
|
||
gray = page_raster(source, i)
|
||
detection = detect_page(gray)
|
||
staves = [s.staff_height for s in detection.systems if s.staff_height]
|
||
note = f", staff {np.median(staves):.0f}px" if staves else ""
|
||
print(
|
||
f"p{i + 1:<3} skew {detection.skew:+.2f}° "
|
||
f"{len(detection.systems)} systems{note}"
|
||
f"{' (no bracket)' if detection.bracketless else ''}"
|
||
)
|
||
for n, system in enumerate(detection.systems, 1):
|
||
print(f" sys{n}: {system.top}–{system.bottom} h={system.height}")
|
||
overlay.write(gray, detection, out / f"{source.path.stem}-p{i + 1:02}.png")
|
||
|
||
print(f"overlays written to {out}/")
|
||
source.close()
|
||
return 0
|
||
|
||
|
||
def main(argv: list[str] | None = None) -> int:
|
||
parser = argparse.ArgumentParser(
|
||
prog="noteman-slicer",
|
||
description="Cut score PDFs into noteman's slice images and markers.",
|
||
)
|
||
parser.add_argument("--version", action="version", version=__version__)
|
||
sub = parser.add_subparsers(dest="command", required=True)
|
||
|
||
info = sub.add_parser("info", help="classify a PDF and report its page rasters")
|
||
info.add_argument("pdf")
|
||
info.add_argument(
|
||
"--type",
|
||
choices=[t.value for t in SourceType],
|
||
help="override source-type detection",
|
||
)
|
||
info.set_defaults(func=_info)
|
||
|
||
det = sub.add_parser("detect", help="run detection and write debug overlays")
|
||
det.add_argument("pdf")
|
||
det.add_argument("--out", default="overlays", help="output directory")
|
||
det.add_argument("--page", type=int, help="single 1-based page instead of all")
|
||
det.add_argument("--type", choices=[t.value for t in SourceType])
|
||
det.set_defaults(func=_detect)
|
||
|
||
args = parser.parse_args(argv)
|
||
return args.func(args)
|
||
|
||
|
||
if __name__ == "__main__":
|
||
sys.exit(main())
|