Esa Kataja
ff1cc6740e
Markers are stored per (page, slot), parallel to the discard flags, so adding or removing a cut keeps them aligned with their slices. On a split they stay with the upper half: a marker sits on a printed symbol and nothing can say which side that symbol landed on, so predictable beats clever. Jump targets are chosen by clicking the slice rather than from the thumbnail strip the plan called for. Less code, and it reads the score instead of a list of thumbnails - which is what you want when hunting for the Coda sign. Any page; PageUp/PageDown while picking. Export resolves (page, slot) to the bundle's array index, the only cross-reference the format has. A jump whose target was discarded or re-cut away is dropped rather than exported dangling, since noteman would have nothing to resolve it to. tests/test_markers.py covers the enum size - that is the coupling between two repos - along with cut-edit alignment, index resolution, the dangling-target drop, and round-trips through both the project file and a real bundle. Closes #28 Closes #29 Closes #30
363 lines
13 KiB
Python
363 lines
13 KiB
Python
"""Project state: everything the human decided, on disk beside the PDF.
|
||
|
||
The bundle is generated from this, so export is a pure function of the project
|
||
plus the PDF. That buys crash safety, resume across sessions, and re-export —
|
||
change the width cap or fix one cut and every song regenerates without
|
||
repeating any human work.
|
||
|
||
All geometry is stored in **normalised page coordinates** (0–1 of the deskewed
|
||
page), so the file is independent of DPI and of which renderer produced it.
|
||
"""
|
||
|
||
from __future__ import annotations
|
||
|
||
import hashlib
|
||
import json
|
||
from dataclasses import dataclass, field
|
||
from pathlib import Path
|
||
|
||
from .detect import PageDetection
|
||
|
||
FORMAT_VERSION = 1
|
||
SUFFIX = ".slicer.json"
|
||
|
||
Point = tuple[float, float]
|
||
|
||
|
||
@dataclass
|
||
class Cut:
|
||
"""A boundary splitting one slice into two, spanning the page left to right.
|
||
|
||
A polyline, not a line. Two points is the ordinary straight case; extra
|
||
vertices handle a section label printed in the left margin at the same
|
||
height as the previous system's lyrics, where no horizontal line separates
|
||
the two (see docs/spec.md).
|
||
"""
|
||
|
||
points: list[Point]
|
||
|
||
@classmethod
|
||
def straight(cls, y: float) -> Cut:
|
||
return cls([(0.0, y), (1.0, y)])
|
||
|
||
@property
|
||
def straight_y(self) -> float | None:
|
||
"""The single y of a straight cut, or None if it steps."""
|
||
ys = {y for _, y in self.points}
|
||
return self.points[0][1] if len(ys) == 1 else None
|
||
|
||
def y_at(self, x: float) -> float:
|
||
"""Height of the boundary at a horizontal position."""
|
||
pts = self.points
|
||
if x <= pts[0][0]:
|
||
return pts[0][1]
|
||
for (x0, y0), (x1, y1) in zip(pts, pts[1:]):
|
||
if x <= x1:
|
||
if x1 == x0:
|
||
return y1
|
||
return y0 + (y1 - y0) * (x - x0) / (x1 - x0)
|
||
return pts[-1][1]
|
||
|
||
@property
|
||
def lowest(self) -> float:
|
||
return max(y for _, y in self.points)
|
||
|
||
@property
|
||
def highest(self) -> float:
|
||
return min(y for _, y in self.points)
|
||
|
||
|
||
# noteman's enum, verbatim. Real coupling between two repos: adding a type
|
||
# means changing both. Order is the order they appear in the editor's picker.
|
||
MARKER_TYPES = (
|
||
"rehearsal_letter",
|
||
"section_label",
|
||
"segno",
|
||
"coda",
|
||
"fine",
|
||
"repeat_start",
|
||
"repeat_end",
|
||
"volta",
|
||
"to_coda",
|
||
"ds_al_coda",
|
||
"ds_al_fine",
|
||
"dc_al_coda",
|
||
"dc_al_fine",
|
||
"generic_jump",
|
||
)
|
||
|
||
# The types that carry free text.
|
||
LABELLED_TYPES = frozenset({"rehearsal_letter", "section_label", "volta"})
|
||
|
||
# The types that send the reader elsewhere. Every one stores its target
|
||
# explicitly rather than resolving by type at read time, so the bundle is
|
||
# self-describing and a score with two codas simply works.
|
||
JUMP_TYPES = frozenset(
|
||
{"to_coda", "ds_al_coda", "ds_al_fine", "dc_al_coda", "dc_al_fine", "generic_jump"}
|
||
)
|
||
|
||
|
||
@dataclass
|
||
class Marker:
|
||
"""A semantic tag on a slice, used by noteman's navigation."""
|
||
|
||
type: str
|
||
label: str | None = None
|
||
# (page, slot) of the target slice, for jump sources. Positional like the
|
||
# slices themselves; resolved to a bundle index at export.
|
||
destination: tuple[int, int] | None = None
|
||
|
||
@property
|
||
def is_jump(self) -> bool:
|
||
return self.type in JUMP_TYPES
|
||
|
||
def describe(self) -> str:
|
||
text = self.type
|
||
if self.label:
|
||
text += f" “{self.label}”"
|
||
if self.destination:
|
||
text += f" → p{self.destination[0] + 1}s{self.destination[1] + 1}"
|
||
return text
|
||
|
||
|
||
@dataclass
|
||
class Page:
|
||
"""One page's decisions. `cuts` are ordered top to bottom."""
|
||
|
||
skew: float = 0.0
|
||
cuts: list[Cut] = field(default_factory=list)
|
||
discards: list[bool] = field(default_factory=lambda: [False])
|
||
# One list per slice, parallel to `discards`.
|
||
markers: list[list[Marker]] = field(default_factory=lambda: [[]])
|
||
content_rect: tuple[float, float, float, float] | None = None
|
||
levels: tuple[int, int] | None = None
|
||
|
||
@property
|
||
def slice_count(self) -> int:
|
||
return len(self.cuts) + 1
|
||
|
||
def bounds(self, index: int) -> tuple[Cut | None, Cut | None]:
|
||
"""The cuts above and below a slice; None means the page edge."""
|
||
above = self.cuts[index - 1] if index > 0 else None
|
||
below = self.cuts[index] if index < len(self.cuts) else None
|
||
return above, below
|
||
|
||
def add_cut(self, cut: Cut) -> int:
|
||
"""Insert a cut, splitting the slice it lands in. Returns its index."""
|
||
y = cut.points[0][1]
|
||
index = sum(1 for c in self.cuts if c.points[0][1] < y)
|
||
self.cuts.insert(index, cut)
|
||
# The split slice keeps its flag on both halves. Its markers stay with
|
||
# the upper half: a marker sits on a printed symbol, and splitting a
|
||
# slice cannot say which side that symbol landed on — leaving them put
|
||
# is at least predictable, and moving one is a click.
|
||
self.discards.insert(index, self.discards[index])
|
||
self.markers.insert(index + 1, [])
|
||
return index
|
||
|
||
def remove_cut(self, index: int) -> None:
|
||
"""Drop a cut, merging the two slices it separated."""
|
||
self.cuts.pop(index)
|
||
merged = self.discards[index] and self.discards[index + 1]
|
||
self.discards.pop(index + 1)
|
||
self.discards[index] = merged
|
||
self.markers[index].extend(self.markers.pop(index + 1))
|
||
|
||
|
||
@dataclass
|
||
class Project:
|
||
source: Path
|
||
source_hash: str
|
||
pages: list[Page]
|
||
content_rect: tuple[float, float, float, float] = (0.0, 0.0, 1.0, 1.0)
|
||
levels: tuple[int, int] = (0, 255)
|
||
metadata: dict[str, str] = field(default_factory=dict)
|
||
path: Path | None = None
|
||
# Set once the song has been exported. A project is spent at that point:
|
||
# opening the PDF again starts a fresh session from detection rather than
|
||
# resuming, so a re-cut never begins from stale decisions. `--resume`
|
||
# overrides it when the old state really is wanted.
|
||
exported: bool = False
|
||
|
||
# -- geometry helpers -------------------------------------------------
|
||
|
||
def page_content_rect(self, index: int) -> tuple[float, float, float, float]:
|
||
return self.pages[index].content_rect or self.content_rect
|
||
|
||
def page_levels(self, index: int) -> tuple[int, int]:
|
||
return self.pages[index].levels or self.levels
|
||
|
||
def kept_slices(self) -> list[tuple[int, int]]:
|
||
"""(page, slice) of every slice that will be exported, in song order."""
|
||
return [
|
||
(p, s)
|
||
for p, page in enumerate(self.pages)
|
||
for s in range(page.slice_count)
|
||
if not page.discards[s]
|
||
]
|
||
|
||
# -- persistence ------------------------------------------------------
|
||
|
||
@classmethod
|
||
def from_detection(
|
||
cls, source: Path, detections: list[PageDetection], heights: list[int]
|
||
) -> Project:
|
||
"""Seed a project from detection. Every value here is a suggestion.
|
||
|
||
Detection emits cuts only *between* systems, so a page would otherwise
|
||
have exactly as many slices as it has systems, with the header and
|
||
footer inside the first and last. The boundary cuts that isolate them —
|
||
and the discard flags that drop them — are a slicing decision, not a
|
||
detection result, so they are added here.
|
||
"""
|
||
pages = []
|
||
for detection, height in zip(detections, heights):
|
||
ys = list(detection.cuts)
|
||
leading = trailing = False
|
||
|
||
if detection.systems:
|
||
first, last = detection.systems[0], detection.systems[-1]
|
||
if first.top > 0:
|
||
ys.insert(0, first.top // 2)
|
||
leading = True
|
||
if last.bottom < height:
|
||
ys.append((last.bottom + height) // 2)
|
||
trailing = True
|
||
|
||
discards = [False] * (len(ys) + 1)
|
||
if leading:
|
||
discards[0] = True
|
||
if trailing:
|
||
discards[-1] = True
|
||
|
||
pages.append(
|
||
Page(
|
||
skew=detection.skew,
|
||
cuts=[Cut.straight(y / height) for y in ys],
|
||
discards=discards,
|
||
markers=[[] for _ in discards],
|
||
# Per page, not per song: scans drift, so the margin junk
|
||
# sits in a different place on each one.
|
||
content_rect=detection.content,
|
||
)
|
||
)
|
||
return cls(source=source, source_hash=hash_file(source), pages=pages)
|
||
|
||
def save(self, path: Path | None = None) -> Path:
|
||
"""Atomic write, so a crash mid-save cannot destroy the previous state."""
|
||
target = Path(path or self.path or default_path(self.source))
|
||
payload = {
|
||
"v": FORMAT_VERSION,
|
||
"source": self.source.name,
|
||
"source_hash": self.source_hash,
|
||
"exported": self.exported,
|
||
"content_rect": list(self.content_rect),
|
||
"levels": list(self.levels),
|
||
"metadata": self.metadata,
|
||
"pages": [
|
||
{
|
||
"skew": page.skew,
|
||
"cuts": [[list(p) for p in cut.points] for cut in page.cuts],
|
||
"discards": page.discards,
|
||
"markers": [
|
||
[
|
||
{
|
||
"type": m.type,
|
||
**({"label": m.label} if m.label else {}),
|
||
**(
|
||
{"destination": list(m.destination)}
|
||
if m.destination
|
||
else {}
|
||
),
|
||
}
|
||
for m in slot
|
||
]
|
||
for slot in page.markers
|
||
],
|
||
"content_rect": list(page.content_rect) if page.content_rect else None,
|
||
"levels": list(page.levels) if page.levels else None,
|
||
}
|
||
for page in self.pages
|
||
],
|
||
}
|
||
tmp = target.with_suffix(target.suffix + ".tmp")
|
||
tmp.write_text(json.dumps(payload, indent=2, ensure_ascii=False))
|
||
tmp.replace(target)
|
||
self.path = target
|
||
return target
|
||
|
||
@classmethod
|
||
def load(cls, path: Path, source: Path | None = None) -> Project:
|
||
path = Path(path)
|
||
data = json.loads(path.read_text())
|
||
if data.get("v") != FORMAT_VERSION:
|
||
raise ValueError(f"unsupported project version {data.get('v')!r}")
|
||
pdf = Path(source) if source else path.parent / data["source"]
|
||
pages = [
|
||
Page(
|
||
skew=page["skew"],
|
||
cuts=[Cut([tuple(p) for p in cut]) for cut in page["cuts"]],
|
||
discards=page["discards"],
|
||
markers=[
|
||
[
|
||
Marker(
|
||
type=m["type"],
|
||
label=m.get("label"),
|
||
destination=tuple(m["destination"]) if m.get("destination") else None,
|
||
)
|
||
for m in slot
|
||
]
|
||
for slot in page.get("markers", [[] for _ in page["discards"]])
|
||
],
|
||
content_rect=tuple(page["content_rect"]) if page["content_rect"] else None,
|
||
levels=tuple(page["levels"]) if page["levels"] else None,
|
||
)
|
||
for page in data["pages"]
|
||
]
|
||
return cls(
|
||
source=pdf,
|
||
source_hash=data["source_hash"],
|
||
pages=pages,
|
||
content_rect=tuple(data["content_rect"]),
|
||
levels=tuple(data["levels"]),
|
||
metadata=data.get("metadata", {}),
|
||
path=path,
|
||
exported=data.get("exported", False),
|
||
)
|
||
|
||
def source_changed(self) -> bool:
|
||
"""True when the PDF no longer matches what these decisions were made on."""
|
||
return self.source.exists() and hash_file(self.source) != self.source_hash
|
||
|
||
|
||
def open_project(source, *, resume: bool = False) -> Project:
|
||
"""The project for a PDF: resumed, or a fresh session from detection.
|
||
|
||
A project that has been exported is spent. Opening the PDF again starts
|
||
over from detection rather than resuming, so a re-cut never inherits stale
|
||
decisions. `resume` overrides that when the old state really is wanted.
|
||
"""
|
||
from .detect import detect_page
|
||
from .pdf import page_raster
|
||
|
||
path = default_path(source.path)
|
||
if path.exists():
|
||
existing = Project.load(path)
|
||
if resume or not existing.exported:
|
||
return existing
|
||
|
||
detections, heights = [], []
|
||
for i in range(len(source)):
|
||
gray = page_raster(source, i)
|
||
detections.append(detect_page(gray))
|
||
heights.append(gray.shape[0])
|
||
return Project.from_detection(source.path, detections, heights)
|
||
|
||
|
||
def default_path(source: Path) -> Path:
|
||
return Path(source).with_suffix(SUFFIX)
|
||
|
||
|
||
def hash_file(path: Path) -> str:
|
||
return hashlib.sha256(Path(path).read_bytes()).hexdigest()
|