Rhythm Selection & Cleanup
ci / checks (push) Successful in 1h16m10s

This commit is contained in:
khodowany
2026-09-26 02:50:22 -05:00
parent 4d6348d354
commit 9fd5abd075
91 changed files with 4692 additions and 2484 deletions
+261
View File
@@ -0,0 +1,261 @@
from __future__ import annotations
import collections
import concurrent.futures
import dataclasses
import hashlib
import json
import multiprocessing
import pathlib
import shutil
import tempfile
import time
import PIL.Image
import generator.engraving.audit
import generator.engraving.cache
import generator.engraving.fonts
import generator.engraving.layout
import generator.engraving.raster
import generator.engraving.types
import generator.engraving.validation
import generator.model
@dataclasses.dataclass
class GroupResult:
scores: list = dataclasses.field(default_factory=list)
fullscore: int = 0
bodyhits: int = 0
bodies: int = 0
renderedpages: int = 0
rejected: int = 0
timings: dict = dataclasses.field(default_factory=lambda: dict.fromkeys(('layout', 'pagination', 'raster', 'cache'), 0.0))
class BodyBands:
def __init__(self, root, persistent, result, limit=16 * 1024 * 1024):
self.root, self.persistent, self.result, self.limit = root, persistent, result, limit
self.images = collections.OrderedDict()
self.size = 0
self.known = {}
self.root.mkdir(parents=True, exist_ok=True)
def get(self, notation, page, band, fonts):
key = generator.engraving.cache.band_fingerprint(notation, page, band)
if key in self.images:
self.images.move_to_end(key)
self.result.bodyhits += 1
return self.images[key]
started = time.monotonic()
entry = self.root / (key + '.rgb')
image = None
if key in self.known:
if entry.is_symlink() or entry.stat().st_size != page.width * (band.bottom - band.top) * 3:
raise generator.engraving.types.EngravingError('temporary notation band was corrupted')
data = entry.read_bytes()
if hashlib.sha256(data).hexdigest() != self.known[key]:
raise generator.engraving.types.EngravingError('temporary notation band was corrupted')
image = PIL.Image.frombytes('RGB', (page.width, band.bottom - band.top), data)
elif self.persistent:
cached = self.persistent / 'notation' / key
image = generator.engraving.cache.restore_band(cached, key, page.width, band.bottom - band.top)
self.result.rejected += int(image is None and (cached.exists() or cached.is_symlink()))
self.result.timings['cache'] += time.monotonic() - started
if image is None:
started = time.monotonic()
image = generator.engraving.raster.rasterize_band(page, band.primitives, band.top, band.bottom, fonts)
self.result.timings['raster'] += time.monotonic() - started
self.result.bodies += 1
if self.persistent:
started = time.monotonic()
generator.engraving.cache.store_band(self.persistent / 'notation' / key, key, image)
self.result.timings['cache'] += time.monotonic() - started
else:
self.result.bodyhits += 1
if key not in self.known:
started = time.monotonic()
# Spill finalized pixels, so eviction never repeats rasterization or PNG decoding.
data = image.tobytes()
entry.write_bytes(data)
self.result.timings['cache'] += time.monotonic() - started
self.known[key] = hashlib.sha256(data).hexdigest()
size = image.width * image.height * 3
while self.images and self.size + size > self.limit:
_, old = self.images.popitem(last=False)
self.size -= old.width * old.height * 3
old.close()
self.images[key] = image
self.size += size
return image
def close(self):
for image in self.images.values():
image.close()
self.images.clear()
self.size = 0
def clear_pages(destination):
if destination.is_symlink() or destination.is_file():
destination.unlink()
elif destination.exists():
shutil.rmtree(destination)
def write_bundle(path, document, pages, fingerprint):
entries = [{**page, 'path': path.with_suffix('.pages').name + '/' + page['path']} for page in pages]
music = {key: value for key, value in document.items() if key != 'playback'}
bundle = {'music': music, 'presentation': {'engine': generator.engraving.validation.ENGINE_NAME, 'style_sha256': fingerprint,
'width': generator.engraving.validation.PAGE_WIDTH, 'height': generator.engraving.validation.PAGE_HEIGHT, 'pages': entries}}
if 'playback' in document:
bundle['playback'] = document['playback']
path.write_text(json.dumps(bundle, indent=2, ensure_ascii=False) + '\n', encoding='utf-8')
def engrave_group(notation, paths, root, font_path, cache_dir, fingerprint, progress=False):
family = generator.engraving.fonts.Fonts(font_path)
style = generator.engraving.types.Style()
systems = None
scores = {}
audited = set()
result = GroupResult()
with tempfile.TemporaryDirectory(prefix='vamp-notation-') as temporary:
bodies = BodyBands(pathlib.Path(temporary), cache_dir, result)
try:
for path, score_key in paths:
try:
document = json.loads(path.read_text(encoding='utf-8'))
destination = path.with_suffix('.pages')
clear_pages(destination)
destination.mkdir()
if score_key in scores:
source, pages = scores[score_key]
for page in pages:
shutil.copyfile(source / page['path'], destination / page['path'])
result.fullscore += 1
else:
if systems is None:
started = time.monotonic()
systems = generator.engraving.layout.layout_systems(document, style, family)
result.timings['layout'] += time.monotonic() - started
started = time.monotonic()
pages_layout = generator.engraving.layout.paginate(systems, document, family, style)
placement = tuple((page.width, page.height, tuple((system.start, system.end, system.box) for system in page.systems)) for page in pages_layout)
if placement not in audited:
layout = generator.engraving.types.LayoutDocument(pages_layout, style, fingerprint)
generator.engraving.audit.audit_layout(document, layout, family)
audited.add(placement)
else:
for page in pages_layout:
decoration = tuple(p for p in page.primitives if p.role in ('title', 'subtitle', 'page-number'))
generator.engraving.audit.audit_primitives(decoration, page.width, page.height, family)
result.timings['pagination'] += time.monotonic() - started
pages = []
for page in pages_layout:
bands = generator.engraving.raster.page_bands(page)
if bands is None:
started = time.monotonic()
image = generator.engraving.raster.rasterize_page(page, family)
else:
body = bodies.get(notation, page, bands[1], family)
started = time.monotonic()
image = generator.engraving.raster.compose_page(page, family, bands, body)
target = destination / f'{page.number:04}.png'
with image:
image.save(target, format='PNG')
result.timings['raster'] += time.monotonic() - started
result.renderedpages += 1
pages.append({'path': target.name, 'sha256': hashlib.sha256(target.read_bytes()).hexdigest()})
scores[score_key] = (destination, pages)
write_bundle(path, document, pages, fingerprint)
result.scores.append((path, score_key, pages))
if progress and len(result.scores) % 50 == 0:
print(f'Engraving body {notation[:12]}: {len(result.scores)}/{len(paths)} scores, fullscore {result.fullscore}, bodyhits {result.bodyhits}, bodies {result.bodies}, renderedpages {result.renderedpages}', flush=True)
except ValueError as error:
raise generator.engraving.types.EngravingError(f'{path.relative_to(root)}: {error}') from error
finally:
bodies.close()
return result
def engrave_tree(root: pathlib.Path, fonts: pathlib.Path, *, cache_dir: pathlib.Path | None = None, jobs: int = 1, progress: bool = False) -> set[str]:
if type(jobs) is not int or not 1 <= jobs <= 16:
raise ValueError('engraving jobs must be between 1 and 16')
if cache_dir and (cache_dir.resolve().is_relative_to(root.resolve()) or root.resolve().is_relative_to(cache_dir.resolve())):
raise ValueError('engraving cache and generated assets must not overlap')
started = time.monotonic()
paths = sorted(root.rglob('*.json'))
validated_pages = set()
if not paths:
return validated_pages
family, style = generator.engraving.fonts.Fonts(fonts), generator.engraving.types.Style()
fingerprint = family.fingerprint(style)
renderer = generator.engraving.cache.renderer_fingerprint(family, style)
if cache_dir:
cache_dir = generator.engraving.cache.renderer_namespace(cache_dir, renderer)
if progress:
state = 'warm namespace' if cache_dir.is_dir() else 'cold namespace'
print(f'Engraving cache enabled: {cache_dir} ({state}; renderer {renderer})', flush=True)
elif progress:
print('Engraving cache disabled', flush=True)
totals = GroupResult()
missing, rejected, completed = 0, 0, 0
groups = {}
for path in paths:
try:
document = json.loads(path.read_text(encoding='utf-8'))
generator.model.validate_document(document)
score_key = generator.engraving.cache.score_fingerprint(document, renderer)
destination = path.with_suffix('.pages')
clear_pages(destination)
entry = cache_dir / 'fullscore' / score_key if cache_dir else None
present = entry is not None and (entry.exists() or entry.is_symlink())
pages = generator.engraving.cache.restore_pages(entry, destination, validated_pages) if entry else None
if pages is None:
rejected += int(present)
missing += int(entry is not None and not present)
notation = generator.engraving.cache.notation_fingerprint(document, renderer)
groups.setdefault(notation, []).append((path, score_key))
else:
write_bundle(path, document, pages, fingerprint)
totals.fullscore += 1
completed += 1
except ValueError as error:
raise generator.engraving.types.EngravingError(f'{path.relative_to(root)}: {error}') from error
prepare_time = time.monotonic() - started
if progress:
print(f'Engraving grouped: {len(paths)} scores, {len(groups)} notation bodies, {totals.fullscore} fullscore hits', flush=True)
validation_time = 0.0
def finish(result):
nonlocal completed, validation_time
started = time.monotonic()
for path, score_key, pages in result.scores:
destination = path.with_suffix('.pages')
for page in pages:
generator.engraving.validation.check_page(destination / page['path'], validated_pages, expected_sha256=page['sha256'])
validation_time += time.monotonic() - started
if cache_dir:
started = time.monotonic()
stored = set()
for path, score_key, pages in result.scores:
if score_key not in stored:
generator.engraving.cache.store_pages(cache_dir / 'fullscore' / score_key, path.with_suffix('.pages'), pages)
stored.add(score_key)
result.timings['cache'] += time.monotonic() - started
for field in ('fullscore', 'bodyhits', 'bodies', 'renderedpages', 'rejected'):
setattr(totals, field, getattr(totals, field) + getattr(result, field))
for phase, elapsed in result.timings.items():
totals.timings[phase] += elapsed
completed += len(result.scores)
if progress:
print(f'Engraving: {completed}/{len(paths)} scores, fullscore {totals.fullscore}, bodyhits {totals.bodyhits}, bodies {totals.bodies}, renderedpages {totals.renderedpages}', flush=True)
jobs = min(jobs, len(groups))
if jobs <= 1:
for notation, group in groups.items():
finish(engrave_group(notation, group, root, fonts, cache_dir, fingerprint, progress))
else:
with concurrent.futures.ProcessPoolExecutor(max_workers=jobs, mp_context=multiprocessing.get_context('spawn')) as pool:
futures = [pool.submit(engrave_group, notation, group, root, fonts, cache_dir, fingerprint, progress) for notation, group in groups.items()]
for future in concurrent.futures.as_completed(futures):
finish(future.result())
if progress:
print(f'Engraving complete: {len(paths)} scores, {totals.fullscore} reused, {missing} missing, {rejected} rejected; fullscore {totals.fullscore}, bodyhits {totals.bodyhits}, bodies {totals.bodies}, renderedpages {totals.renderedpages}, rejected bodies {totals.rejected}', flush=True)
phases = {'prepare': prepare_time, **totals.timings, 'validation': validation_time}
print('Engraving timings: ' + ', '.join(f'{phase} {elapsed:.3f}s' for phase, elapsed in phases.items()) + f'; wall {time.monotonic() - started:.3f}s (worker phases summed)', flush=True)
return validated_pages