Compare commits

...
3 Commits
Author SHA1 Message Date
Esa Kataja 5f67a8c359 Merge dev: render pipeline, bundle export and the editor 2026-07-28 23:03:50 +03:00
Esa Kataja bc19eae111 Add the editor: page view, cut editing, discard, levels, metadata
QGraphicsView for the viewport, with cuts and the content rectangle
manipulated by hit-testing in the view rather than as movable items —
the geometry is normalised, so what the screen shows and what the
renderer uses are the same numbers at a different zoom.

Cuts are edited as polylines: double-click adds one, drag moves it,
Ctrl-click inserts a vertex, right-click deletes a vertex or the whole
cut. That is how a straight cut becomes the stepped cut Engel needs.

Slice boundaries are drawn, not just cut lines, so a trim anomaly is
visible before export rather than after. Discarded slices are shaded.

Pages preview at 1800px regardless of source resolution, cached per
page, because re-reading a 4959x7017 vector render on every slider move
is unusable.

Autosave is debounced at 800ms and also fires on close.

Closes #12
Closes #14
Closes #15
Closes #16
Closes #17
Closes #18
Closes #19
Closes #20
Closes #26
2026-07-28 23:03:49 +03:00
Esa Kataja 974c91a727 Add the render pipeline and bundle export
Project state plus PDF in, finished slice images out. Slices are cut as
polygons rather than row ranges, so a stepped cut yields a slice with a
transparent notch instead of one that covers its neighbour.

Masking paints white, which the ink-to-alpha step turns into full
transparency — the same outcome the spec asks for, one step earlier.

Scale normalises every slice to the median staff height before fitting
the song to 1920px, so a rescanned page sits at the same note size as
its neighbours. The cap only ever shrinks: a song narrower than 1920
stays narrower.

Alpha quantisation rounds to 16 values spanning 0-255 inclusive.
Flooring, as first written, capped full ink at 240 and left every note
6% transparent — caught by decoding an exported slice rather than by
reading the code.

Ketun joululaulu exports 24 slices at a uniform 1489px, under the cap
and correctly not upscaled from its 200 DPI source; Feliz Navidad 20;
Elaman nalka 18.

Closes #21
Closes #22
Closes #23
Closes #24
Closes #25
Closes #27
2026-07-28 23:00:53 +03:00
6 changed files with 1156 additions and 0 deletions
+65
View File
@@ -0,0 +1,65 @@
"""Bundle export — the only channel to noteman (ADR 0001).
song.zip
song.json
original.pdf
001.webp 002.webp …
Array order in `song.json` *is* slice order: one ordering, not two. Markers
nest inside the slice they sit on, so an index appears in exactly one place —
a jump source's `destination`.
"""
from __future__ import annotations
import json
import zipfile
from pathlib import Path
from .pdf import Source
from .project import Project
from .render import render_song
FORMAT_VERSION = 1
METADATA_FIELDS = (
"title",
"subtitle",
"composer",
"original_artist",
"arranger",
"lyricist",
"translator",
"voices",
)
def song_json(project: Project, files: list[str]) -> dict:
payload: dict = {"v": FORMAT_VERSION}
for field in METADATA_FIELDS:
value = project.metadata.get(field)
if value:
payload[field] = value
payload["slices"] = [{"file": name} for name in files]
return payload
def write(project: Project, source: Source, path: Path) -> Path:
"""Render the song and write the bundle. Returns the zip path."""
images = render_song(project, source)
names = [f"{i + 1:03}.webp" for i in range(len(images))]
path = Path(path)
path.parent.mkdir(parents=True, exist_ok=True)
# ZIP_STORED for the images: WebP is already compressed, so deflating it
# only costs time. The JSON is small enough not to care.
with zipfile.ZipFile(path, "w") as zf:
zf.writestr(
"song.json",
json.dumps(song_json(project, names), indent=2, ensure_ascii=False),
zipfile.ZIP_DEFLATED,
)
if project.source.exists():
zf.write(project.source, "original.pdf")
for name, data in zip(names, images):
zf.writestr(name, data, zipfile.ZIP_STORED)
return path
+46
View File
@@ -82,6 +82,41 @@ def _project(args: argparse.Namespace) -> int:
return 0 return 0
def _export(args: argparse.Namespace) -> int:
from . import bundle
from .project import Project, default_path
source = open_source(args.pdf, SourceType(args.type) if args.type else None)
path = default_path(source.path)
if path.exists():
project = Project.load(path)
if project.source_changed():
print("WARNING: the PDF has changed since these cuts were made")
else:
detections, heights = [], []
for i in range(len(source)):
gray = page_raster(source, i)
detections.append(detect_page(gray))
heights.append(gray.shape[0])
project = Project.from_detection(source.path, detections, heights)
print("no project file; exporting straight from detection")
out = Path(args.out) if args.out else source.path.with_suffix(".zip")
bundle.write(project, source, out)
size = out.stat().st_size
slices = len(project.kept_slices())
print(f"{out} {slices} slices, {size / 1024:.0f} KB ({size / max(slices, 1) / 1024:.1f} KB/slice)")
source.close()
return 0
def _edit(args: argparse.Namespace) -> int:
from .editor import launch
return launch(Path(args.pdf), SourceType(args.type) if args.type else None)
def main(argv: list[str] | None = None) -> int: def main(argv: list[str] | None = None) -> int:
parser = argparse.ArgumentParser( parser = argparse.ArgumentParser(
prog="noteman-slicer", prog="noteman-slicer",
@@ -113,6 +148,17 @@ def main(argv: list[str] | None = None) -> int:
proj.add_argument("--type", choices=[t.value for t in SourceType]) proj.add_argument("--type", choices=[t.value for t in SourceType])
proj.set_defaults(func=_project) proj.set_defaults(func=_project)
exp = sub.add_parser("export", help="render the song and write a bundle")
exp.add_argument("pdf")
exp.add_argument("--out", help="output zip (default: alongside the PDF)")
exp.add_argument("--type", choices=[t.value for t in SourceType])
exp.set_defaults(func=_export)
ed = sub.add_parser("edit", help="open the editor")
ed.add_argument("pdf")
ed.add_argument("--type", choices=[t.value for t in SourceType])
ed.set_defaults(func=_edit)
args = parser.parse_args(argv) args = parser.parse_args(argv)
return args.func(args) return args.func(args)
+535
View File
@@ -0,0 +1,535 @@
"""The editor: the human-in-the-loop half of the tool.
Detection proposes; everything here is how you dispose (ADR 0004). Cuts can be
authored entirely by hand with detection producing nothing.
Geometry is edited in normalised page coordinates, so what the screen shows and
what the renderer uses are the same numbers at a different zoom.
"""
from __future__ import annotations
import sys
from pathlib import Path
import numpy as np
from PySide6.QtCore import QPointF, QRectF, Qt, QTimer, Signal
from PySide6.QtGui import (
QAction,
QBrush,
QColor,
QImage,
QKeySequence,
QPainter,
QPen,
QPixmap,
QPolygonF,
)
from PySide6.QtWidgets import (
QApplication,
QDoubleSpinBox,
QFileDialog,
QFormLayout,
QGraphicsScene,
QGraphicsView,
QGroupBox,
QHBoxLayout,
QLabel,
QLineEdit,
QMainWindow,
QMessageBox,
QPushButton,
QSlider,
QVBoxLayout,
QWidget,
)
from . import bundle
from .bundle import METADATA_FIELDS
from .detect import deskew, detect_page
from .pdf import Source, open_source, page_raster
from .project import Cut, Project, default_path
from .render import apply_levels
PREVIEW_MAX = 1800 # display resolution; geometry stays normalised
HIT = 6 # grab distance in screen pixels
AUTOSAVE_MS = 800
_CUT = QColor(220, 40, 40)
_CUT_ACTIVE = QColor(255, 120, 0)
_VERTEX = QColor(255, 200, 0)
_DISCARD = QColor(120, 120, 140, 90)
_RECT = QColor(40, 140, 220)
class PageView(QGraphicsView):
"""Pan, zoom, and direct manipulation of cuts and the content rectangle."""
changed = Signal()
selection_changed = Signal()
def __init__(self) -> None:
super().__init__()
self.setScene(QGraphicsScene(self))
self.setRenderHint(QPainter.Antialiasing)
self.setDragMode(QGraphicsView.ScrollHandDrag)
self.setTransformationAnchor(QGraphicsView.AnchorUnderMouse)
self.project: Project | None = None
self.page_index = 0
self.pixmap: QPixmap | None = None
self.selected_cut: int | None = None
self.selected_slice = 0
self._drag: tuple[str, int, int] | None = None
# -- state ------------------------------------------------------------
def show_page(self, project: Project, index: int, image: np.ndarray) -> None:
self.project = project
self.page_index = index
h, w = image.shape
qimage = QImage(image.data, w, h, w, QImage.Format_Grayscale8).copy()
self.pixmap = QPixmap.fromImage(qimage)
self.selected_cut = None
self.selected_slice = 0
self.scene().setSceneRect(0, 0, w, h)
self.redraw()
self.fitInView(self.scene().sceneRect(), Qt.KeepAspectRatio)
@property
def page(self):
return self.project.pages[self.page_index]
def redraw(self) -> None:
scene = self.scene()
scene.clear()
if self.pixmap is None:
return
scene.addPixmap(self.pixmap)
w, h = self.pixmap.width(), self.pixmap.height()
for slot in range(self.page.slice_count):
if self.page.discards[slot]:
scene.addPolygon(
self._slice_polygon(slot, w, h), QPen(Qt.NoPen), QBrush(_DISCARD)
)
# The selected slice, outlined so trim anomalies are visible.
pen = QPen(QColor(0, 170, 0), 2)
pen.setCosmetic(True)
scene.addPolygon(self._slice_polygon(self.selected_slice, w, h), pen)
x0, y0, x1, y1 = self.project.page_content_rect(self.page_index)
pen = QPen(_RECT, 2, Qt.DashLine)
pen.setCosmetic(True)
scene.addRect(QRectF(x0 * w, y0 * h, (x1 - x0) * w, (y1 - y0) * h), pen)
for i, cut in enumerate(self.page.cuts):
colour = _CUT_ACTIVE if i == self.selected_cut else _CUT
pen = QPen(colour, 2)
pen.setCosmetic(True)
points = [QPointF(x * w, y * h) for x, y in cut.points]
for a, b in zip(points, points[1:]):
scene.addLine(a.x(), a.y(), b.x(), b.y(), pen)
if i == self.selected_cut:
r = HIT * 1.5 / max(self.transform().m11(), 1e-6)
for p in points:
scene.addEllipse(
p.x() - r, p.y() - r, r * 2, r * 2, QPen(Qt.NoPen), QBrush(_VERTEX)
)
def _slice_polygon(self, slot: int, w: int, h: int) -> QPolygonF:
above, below = self.page.bounds(slot)
top = [(0.0, 0.0), (1.0, 0.0)] if above is None else above.points
bottom = [(0.0, 1.0), (1.0, 1.0)] if below is None else below.points
pts = [QPointF(x * w, y * h) for x, y in top]
pts += [QPointF(x * w, y * h) for x, y in reversed(bottom)]
return QPolygonF(pts)
# -- hit testing ------------------------------------------------------
def _norm(self, pos) -> tuple[float, float]:
p = self.mapToScene(pos)
return p.x() / self.pixmap.width(), p.y() / self.pixmap.height()
def _tolerance(self) -> tuple[float, float]:
scale = max(self.transform().m11(), 1e-6)
return HIT / scale / self.pixmap.width(), HIT / scale / self.pixmap.height()
def _hit_cut(self, x: float, y: float) -> tuple[int, int | None] | None:
"""(cut index, vertex index or None) under the cursor."""
tx, ty = self._tolerance()
for i, cut in enumerate(self.page.cuts):
for v, (vx, vy) in enumerate(cut.points):
if abs(vx - x) <= tx * 2 and abs(vy - y) <= ty * 2:
return i, v
if abs(cut.y_at(x) - y) <= ty:
return i, None
return None
def _hit_rect_edge(self, x: float, y: float) -> str | None:
x0, y0, x1, y1 = self.project.page_content_rect(self.page_index)
tx, ty = self._tolerance()
if y0 - ty <= y <= y1 + ty:
if abs(x - x0) <= tx:
return "left"
if abs(x - x1) <= tx:
return "right"
if x0 - tx <= x <= x1 + tx:
if abs(y - y0) <= ty:
return "top"
if abs(y - y1) <= ty:
return "bottom"
return None
# -- interaction ------------------------------------------------------
def mousePressEvent(self, event) -> None:
if self.project is None or self.pixmap is None:
return super().mousePressEvent(event)
x, y = self._norm(event.position().toPoint())
if event.button() == Qt.RightButton:
hit = self._hit_cut(x, y)
if hit:
index, vertex = hit
if vertex is not None and len(self.page.cuts[index].points) > 2:
self.page.cuts[index].points.pop(vertex)
else:
self.page.remove_cut(index)
self.selected_cut = None
self.redraw()
self.changed.emit()
return
if event.button() == Qt.LeftButton:
edge = self._hit_rect_edge(x, y)
hit = self._hit_cut(x, y)
if hit and event.modifiers() & Qt.ControlModifier and hit[1] is None:
# Ctrl-click on a cut inserts a vertex: this is how a straight
# cut becomes a stepped one.
cut = self.page.cuts[hit[0]]
at = next(i for i, p in enumerate(cut.points) if p[0] > x)
cut.points.insert(at, (x, cut.y_at(x)))
self.selected_cut = hit[0]
self._drag = ("vertex", hit[0], at)
elif hit:
self.selected_cut = hit[0]
self._drag = ("vertex" if hit[1] is not None else "cut", hit[0], hit[1] or 0)
elif edge:
self._drag = ("rect", 0, 0)
self._edge = edge
else:
self.selected_cut = None
self.selected_slice = self._slice_at(x, y)
self.selection_changed.emit()
self.setDragMode(
QGraphicsView.NoDrag if self._drag else QGraphicsView.ScrollHandDrag
)
self.redraw()
super().mousePressEvent(event)
def mouseMoveEvent(self, event) -> None:
if self._drag and self.pixmap is not None:
x, y = self._norm(event.position().toPoint())
kind, index, vertex = self._drag
if kind == "cut":
cut = self.page.cuts[index]
shift = y - cut.y_at(x)
cut.points = [(px, min(1.0, max(0.0, py + shift))) for px, py in cut.points]
elif kind == "vertex":
cut = self.page.cuts[index]
lo = cut.points[vertex - 1][0] if vertex > 0 else 0.0
hi = cut.points[vertex + 1][0] if vertex + 1 < len(cut.points) else 1.0
px = cut.points[vertex][0] if vertex in (0, len(cut.points) - 1) else min(
max(x, lo), hi
)
cut.points[vertex] = (px, min(1.0, max(0.0, y)))
else:
x0, y0, x1, y1 = self.project.page_content_rect(self.page_index)
x, y = min(max(x, 0.0), 1.0), min(max(y, 0.0), 1.0)
box = {
"left": (x, y0, x1, y1),
"right": (x0, y0, x, y1),
"top": (x0, y, x1, y1),
"bottom": (x0, y0, x1, y),
}[self._edge]
self.project.pages[self.page_index].content_rect = box
self.redraw()
return
super().mouseMoveEvent(event)
def mouseReleaseEvent(self, event) -> None:
if self._drag:
self._drag = None
self.setDragMode(QGraphicsView.ScrollHandDrag)
self.page.cuts.sort(key=lambda c: c.points[0][1])
self.changed.emit()
super().mouseReleaseEvent(event)
def mouseDoubleClickEvent(self, event) -> None:
if self.project is None or self.pixmap is None:
return
x, y = self._norm(event.position().toPoint())
if self._hit_cut(x, y) is None:
self.selected_cut = self.page.add_cut(Cut.straight(y))
self.redraw()
self.changed.emit()
def wheelEvent(self, event) -> None:
factor = 1.15 if event.angleDelta().y() > 0 else 1 / 1.15
self.scale(factor, factor)
self.redraw()
def _slice_at(self, x: float, y: float) -> int:
return sum(1 for cut in self.page.cuts if cut.y_at(x) < y)
def toggle_discard(self) -> None:
self.page.discards[self.selected_slice] = not self.page.discards[self.selected_slice]
self.redraw()
self.changed.emit()
class Editor(QMainWindow):
def __init__(self, source: Source, project: Project) -> None:
super().__init__()
self.source = source
self.project = project
self.index = 0
self._raw: dict[int, np.ndarray] = {}
self.setWindowTitle(f"noteman-slicer — {source.path.name}")
self.view = PageView()
self.view.changed.connect(self._touched)
self.view.selection_changed.connect(self._sync)
self.autosave = QTimer(self)
self.autosave.setSingleShot(True)
self.autosave.setInterval(AUTOSAVE_MS)
self.autosave.timeout.connect(self._save)
central = QWidget()
layout = QHBoxLayout(central)
layout.addWidget(self.view, 1)
layout.addWidget(self._panel())
self.setCentralWidget(central)
self._shortcuts()
self._load_page(0)
# -- ui ---------------------------------------------------------------
def _panel(self) -> QWidget:
panel = QWidget()
panel.setFixedWidth(320)
box = QVBoxLayout(panel)
nav = QHBoxLayout()
self.page_label = QLabel()
prev, nxt = QPushButton(""), QPushButton("")
prev.clicked.connect(lambda: self._load_page(self.index - 1))
nxt.clicked.connect(lambda: self._load_page(self.index + 1))
nav.addWidget(prev)
nav.addWidget(self.page_label, 1)
nav.addWidget(nxt)
box.addLayout(nav)
page_box = QGroupBox("Page")
form = QFormLayout(page_box)
self.skew = QDoubleSpinBox()
self.skew.setRange(-15.0, 15.0)
self.skew.setSingleStep(0.1)
self.skew.setDecimals(2)
self.skew.setSuffix("°")
self.skew.valueChanged.connect(self._skew_changed)
form.addRow("Skew", self.skew)
self.black = QSlider(Qt.Horizontal)
self.black.setRange(0, 255)
self.white = QSlider(Qt.Horizontal)
self.white.setRange(0, 255)
self.white.setValue(255)
for s in (self.black, self.white):
s.valueChanged.connect(self._levels_changed)
form.addRow("Black point", self.black)
form.addRow("White point", self.white)
discard = QPushButton("Toggle discard (D)")
discard.clicked.connect(self.view.toggle_discard)
form.addRow(discard)
reset = QPushButton("Reset content rectangle")
reset.clicked.connect(self._reset_rect)
form.addRow(reset)
box.addWidget(page_box)
meta_box = QGroupBox("Song")
meta_form = QFormLayout(meta_box)
self.metadata: dict[str, QLineEdit] = {}
for field in METADATA_FIELDS:
edit = QLineEdit(self.project.metadata.get(field, ""))
edit.textChanged.connect(self._metadata_changed)
self.metadata[field] = edit
meta_form.addRow(field.replace("_", " ").title(), edit)
box.addWidget(meta_box)
self.summary = QLabel()
self.summary.setWordWrap(True)
box.addWidget(self.summary)
export = QPushButton("Export bundle…")
export.clicked.connect(self._export)
box.addWidget(export)
box.addStretch(1)
help_text = QLabel(
"Double-click: add cut\n"
"Drag: move cut · Ctrl-click: add vertex\n"
"Right-click: delete cut or vertex\n"
"Click a slice, then D to discard\n"
"Drag the blue edges: content rectangle"
)
help_text.setStyleSheet("color: palette(mid);")
box.addWidget(help_text)
return panel
def _shortcuts(self) -> None:
for key, slot in (
(QKeySequence("D"), self.view.toggle_discard),
(QKeySequence(Qt.Key_PageDown), lambda: self._load_page(self.index + 1)),
(QKeySequence(Qt.Key_PageUp), lambda: self._load_page(self.index - 1)),
(QKeySequence.Save, self._save),
):
action = QAction(self)
action.setShortcut(key)
action.triggered.connect(slot)
self.addAction(action)
# -- page handling ----------------------------------------------------
def _raster(self, index: int) -> np.ndarray:
"""Page pixels at preview resolution, cached — the PDF is slow to read."""
if index not in self._raw:
import cv2
gray = page_raster(self.source, index)
if gray.shape[1] > PREVIEW_MAX:
k = PREVIEW_MAX / gray.shape[1]
gray = cv2.resize(gray, None, fx=k, fy=k, interpolation=cv2.INTER_AREA)
self._raw[index] = gray
return self._raw[index]
def _preview(self, index: int) -> np.ndarray:
page = self.project.pages[index]
black, white = self.project.page_levels(index)
return np.ascontiguousarray(
apply_levels(deskew(self._raster(index), page.skew), black, white)
)
def _load_page(self, index: int) -> None:
if not 0 <= index < len(self.project.pages):
return
self.index = index
self.view.show_page(self.project, index, self._preview(index))
self._sync()
def _sync(self) -> None:
page = self.project.pages[self.index]
self.page_label.setText(f"Page {self.index + 1} / {len(self.project.pages)}")
for widget, value in ((self.skew, page.skew),):
widget.blockSignals(True)
widget.setValue(value)
widget.blockSignals(False)
black, white = self.project.page_levels(self.index)
for widget, value in ((self.black, black), (self.white, white)):
widget.blockSignals(True)
widget.setValue(value)
widget.blockSignals(False)
kept = len(self.project.kept_slices())
total = sum(p.slice_count for p in self.project.pages)
state = "discarded" if page.discards[self.view.selected_slice] else "kept"
self.summary.setText(
f"{page.slice_count} slices on this page · slice "
f"{self.view.selected_slice + 1} is {state}\n"
f"{kept} of {total} slices kept in the song"
)
# -- edits ------------------------------------------------------------
def _touched(self) -> None:
self._sync()
self.autosave.start()
def _skew_changed(self, value: float) -> None:
self.project.pages[self.index].skew = value
self.view.show_page(self.project, self.index, self._preview(self.index))
self._touched()
def _levels_changed(self) -> None:
self.project.pages[self.index].levels = (self.black.value(), self.white.value())
self.view.show_page(self.project, self.index, self._preview(self.index))
self._touched()
def _metadata_changed(self) -> None:
self.project.metadata = {
field: edit.text().strip() for field, edit in self.metadata.items() if edit.text().strip()
}
self.autosave.start()
def _reset_rect(self) -> None:
self.project.pages[self.index].content_rect = None
self.view.redraw()
self._touched()
def _save(self) -> None:
path = self.project.save()
self.statusBar().showMessage(f"saved {path.name}", 2000)
def _export(self) -> None:
self._save()
target, _ = QFileDialog.getSaveFileName(
self, "Export bundle", str(self.source.path.with_suffix(".zip")), "Bundle (*.zip)"
)
if not target:
return
try:
out = bundle.write(self.project, self.source, Path(target))
except Exception as error: # noqa: BLE001 - surfaced to the user
QMessageBox.critical(self, "Export failed", str(error))
return
size = out.stat().st_size / 1024
QMessageBox.information(
self,
"Exported",
f"{out.name}\n{len(self.project.kept_slices())} slices, {size:.0f} KB",
)
def closeEvent(self, event) -> None:
self._save()
super().closeEvent(event)
def launch(pdf: Path, source_type=None) -> int:
app = QApplication(sys.argv[:1])
source = open_source(pdf, source_type)
path = default_path(source.path)
if path.exists():
project = Project.load(path)
if project.source_changed():
QMessageBox.warning(
None,
"Source changed",
"The PDF has changed since these cuts were made.\n"
"Cuts may no longer line up with the music.",
)
else:
detections, heights = [], []
for i in range(len(source)):
gray = page_raster(source, i)
detections.append(detect_page(gray))
heights.append(gray.shape[0])
project = Project.from_detection(source.path, detections, heights)
window = Editor(source, project)
window.resize(1500, 950)
window.show()
return app.exec()
+234
View File
@@ -0,0 +1,234 @@
"""Render project state into finished slice images.
load raster → deskew → levels → content rect → cut → discard
→ trim → scale → pad → ink→alpha → encode
The order is not arbitrary. Levels runs before anything geometric so the trim
bounding box is computed on the image that actually ships; the content
rectangle runs before cutting so margin junk never enters a slice; and trim
runs before scale because the scale factor derives from the widest *trimmed*
slice.
Output is final — nothing downstream reprocesses it (ADR 0001).
"""
from __future__ import annotations
from dataclasses import dataclass
import cv2
import numpy as np
from .detect import deskew, staff_height
from .pdf import Source, page_raster
from .project import Cut, Project
MAX_WIDTH = 1920
ALPHA_LEVELS = 16 # quantising alpha costs nothing visible and ~32% of the bytes
_SPECK_AREA = 300 # ink blobs smaller than this don't anchor a trim
@dataclass
class SliceImage:
"""One rendered slice, before scaling."""
page: int
index: int
gray: np.ndarray
staff: float | None
@property
def width(self) -> int:
return self.gray.shape[1]
def apply_levels(gray: np.ndarray, black: int, white: int) -> np.ndarray:
"""Map [black, white] onto the full range with a lookup table.
A global LUT, not an adaptive method: CLAHE and adaptive thresholding are
tuned for text and eat the thin stuff on notation — hairpin tips, slur ends,
ledger lines, tapered beams.
"""
if (black, white) == (0, 255):
return gray
lo, hi = min(black, white), max(black, white)
if hi <= lo:
return gray
ramp = np.clip((np.arange(256) - lo) * 255.0 / (hi - lo), 0, 255)
return cv2.LUT(gray, ramp.astype(np.uint8))
def page_pixels(project: Project, source: Source, index: int) -> np.ndarray:
"""A page straightened and levelled, ready to be cut."""
page = project.pages[index]
gray = deskew(page_raster(source, index), page.skew)
black, white = project.page_levels(index)
return apply_levels(gray, black, white)
def _boundary(cut: Cut | None, width: int, height: int, *, bottom: bool) -> list[tuple[int, int]]:
"""A cut as pixel points spanning the page, or the page edge when absent."""
if cut is None:
y = height if bottom else 0
return [(0, y), (width, y)]
return [(int(round(x * width)), int(round(y * height))) for x, y in cut.points]
def slice_mask(project: Project, index: int, slot: int, shape: tuple[int, int]) -> np.ndarray:
"""Which pixels of a page belong to one slice.
A slice bounded by a stepped cut is not rectangular, so this is a polygon
rather than a row range: the top boundary left to right, then the bottom
boundary right to left.
"""
height, width = shape
page = project.pages[index]
above, below = page.bounds(slot)
polygon = _boundary(above, width, height, bottom=False)
polygon += _boundary(below, width, height, bottom=True)[::-1]
mask = np.zeros(shape, np.uint8)
cv2.fillPoly(mask, [np.array(polygon, np.int32)], 255)
# The content rectangle is applied here rather than as a separate crop, so
# margin junk can never enter a slice in the first place.
x0, y0, x1, y1 = project.page_content_rect(index)
box = np.zeros(shape, np.uint8)
box[int(y0 * height) : int(y1 * height), int(x0 * width) : int(x1 * width)] = 255
return cv2.bitwise_and(mask, box)
def _ink_bbox(gray: np.ndarray) -> tuple[int, int, int, int] | None:
"""Tight bounds of the ink, ignoring specks.
One scan fleck at the far left would otherwise anchor the trim and shift
that slice relative to every other one.
"""
ink = (gray < 200).astype(np.uint8)
count, _, stats, _ = cv2.connectedComponentsWithStats(ink, 8)
boxes = [
(
stats[i, cv2.CC_STAT_LEFT],
stats[i, cv2.CC_STAT_TOP],
stats[i, cv2.CC_STAT_LEFT] + stats[i, cv2.CC_STAT_WIDTH],
stats[i, cv2.CC_STAT_TOP] + stats[i, cv2.CC_STAT_HEIGHT],
)
for i in range(1, count)
if stats[i, cv2.CC_STAT_AREA] >= _SPECK_AREA
]
if not boxes:
return None
return (
min(b[0] for b in boxes),
min(b[1] for b in boxes),
max(b[2] for b in boxes),
max(b[3] for b in boxes),
)
def cut_slice(page: np.ndarray, mask: np.ndarray) -> np.ndarray | None:
"""Extract one slice: everything outside its region becomes paper.
Paper here means white, which the ink→alpha step turns into full
transparency — so a stepped slice's notch composites invisibly on the
viewer's sheet rather than covering the neighbouring system.
"""
isolated = np.where(mask > 0, page, np.uint8(255))
box = _ink_bbox(isolated)
if box is None:
return None
x0, y0, x1, y1 = box
return isolated[y0:y1, x0:x1]
def render_slices(project: Project, source: Source) -> list[SliceImage]:
"""Every kept slice, trimmed but not yet scaled."""
out: list[SliceImage] = []
for index in range(len(project.pages)):
page = page_pixels(project, source, index)
for slot in range(project.pages[index].slice_count):
if project.pages[index].discards[slot]:
continue
gray = cut_slice(page, slice_mask(project, index, slot, page.shape))
if gray is None:
continue # a kept slice that turned out to hold no ink
out.append(SliceImage(index, slot, gray, staff_height(gray, 0, gray.shape[0])))
return out
def scale_song(slices: list[SliceImage], cap: int = MAX_WIDTH) -> list[np.ndarray]:
"""Normalise every slice to one staff height, then fit the song to the cap.
Two steps, both per song. Staff-height normalisation is what makes a
rescanned page — or a re-engraved system — sit at the same note size as its
neighbours; width-based scaling cannot, because width depends on how much
music is in a system rather than on how big it is drawn.
The cap is a ceiling, never a target: a song that comes out narrower stays
narrower, since enlarging a scan past its own resolution buys softness and
bytes and no detail.
"""
if not slices:
return []
measured = [s.staff for s in slices if s.staff]
target = float(np.median(measured)) if measured else 0.0
factors = [target / s.staff if (target and s.staff) else 1.0 for s in slices]
widest = max(s.width * f for s, f in zip(slices, factors))
song = min(1.0, cap / widest) if widest else 1.0
out = []
for s, f in zip(slices, factors):
k = f * song
if abs(k - 1.0) < 1e-3:
out.append(s.gray)
continue
interp = cv2.INTER_AREA if k < 1 else cv2.INTER_CUBIC
out.append(cv2.resize(s.gray, None, fx=k, fy=k, interpolation=interp))
return out
def pad_right(images: list[np.ndarray]) -> list[np.ndarray]:
"""Bring every slice to the song's width, flush left.
A short system simply ends earlier; the padding is paper, so it disappears
when ink becomes alpha.
"""
if not images:
return []
width = max(i.shape[1] for i in images)
return [
i
if i.shape[1] == width
else cv2.copyMakeBorder(i, 0, 0, 0, width - i.shape[1], cv2.BORDER_CONSTANT, value=255)
for i in images
]
def encode(gray: np.ndarray) -> bytes:
"""Ink black, paper transparent, lossless WebP.
Lossless rather than lossy not because lossy looks bad — measured, it
doesn't — but because it is 58% *larger* on line art (ADR 0003).
"""
alpha = 255 - gray
if ALPHA_LEVELS < 256:
# Round to the nearest of ALPHA_LEVELS values spanning 0255 inclusive.
# Flooring instead would cap full ink at 240 and leave every note
# slightly transparent.
step = 255 / (ALPHA_LEVELS - 1)
alpha = (np.round(alpha / step) * step).astype(np.uint8)
rgba = np.zeros((*gray.shape, 4), np.uint8)
rgba[:, :, 3] = alpha
ok, buf = cv2.imencode(".webp", rgba, [cv2.IMWRITE_WEBP_QUALITY, 101])
if not ok:
raise RuntimeError("WebP encoding failed")
return buf.tobytes()
def render_song(project: Project, source: Source) -> list[bytes]:
"""The whole raster pipeline: project + PDF in, finished slice images out."""
slices = render_slices(project, source)
return [encode(image) for image in pad_right(scale_song(slices))]
+114
View File
@@ -0,0 +1,114 @@
"""Runnable check that the editor builds and its edits reach project state.
Runs offscreen, so it verifies wiring rather than appearance: that the widgets
construct, that an edit changes the model, and that autosave and export work.
"""
from __future__ import annotations
import os
import sys
from pathlib import Path
os.environ.setdefault("QT_QPA_PLATFORM", "offscreen")
import numpy as np # noqa: E402
import pymupdf # noqa: E402
sys.path.insert(0, str(Path(__file__).resolve().parents[1]))
from PySide6.QtWidgets import QApplication # noqa: E402
from noteman_slicer.detect import detect_page # noqa: E402
from noteman_slicer.editor import Editor # noqa: E402
from noteman_slicer.pdf import open_source, page_raster # noqa: E402
from noteman_slicer.project import Cut, Project, default_path # noqa: E402
W, H = 1200, 1600
def _scan_pdf(path: Path) -> None:
art = np.full((H, W), 255, np.uint8)
for top in (300, 800):
art[top : top + 200, 100:104] = 0
for staff in (top, top + 140):
for i in range(5):
art[staff + i * 15 : staff + i * 15 + 2, 110:1100] = 0
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(path)
def main() -> int:
tmp = Path(__file__).with_name("_tmp")
tmp.mkdir(exist_ok=True)
pdf = tmp / "scan.pdf"
_scan_pdf(pdf)
app = QApplication.instance() or QApplication(sys.argv[:1])
source = open_source(pdf)
gray = page_raster(source, 0)
project = Project.from_detection(pdf, [detect_page(gray)], [gray.shape[0]])
editor = Editor(source, project)
page = project.pages[0]
# Cuts.
before = page.slice_count
editor.view.selected_cut = page.add_cut(Cut.straight(0.5))
editor.view.redraw()
assert page.slice_count == before + 1
# A vertex turns a straight cut into a stepped one.
cut = page.cuts[editor.view.selected_cut]
cut.points.insert(1, (0.4, cut.y_at(0.4)))
cut.points[1] = (0.4, cut.points[1][1] + 0.03)
assert cut.straight_y is None, "the cut should no longer be straight"
editor.view.redraw()
# Discard.
editor.view.selected_slice = 1
was = page.discards[1]
editor.view.toggle_discard()
assert page.discards[1] != was
# Skew and levels reach the model and re-render without raising.
editor.skew.setValue(-1.4)
assert abs(page.skew + 1.4) < 1e-6
editor.black.setValue(40)
editor.white.setValue(210)
assert project.page_levels(0) == (40, 210)
# Metadata.
editor.metadata["title"].setText("Ketun joululaulu")
editor.metadata["composer"].setText("trad.")
assert project.metadata["title"] == "Ketun joululaulu"
# Content rectangle edits and reset.
page.content_rect = (0.05, 0.02, 0.95, 0.98)
assert project.page_content_rect(0) == (0.05, 0.02, 0.95, 0.98)
editor._reset_rect()
assert project.page_content_rect(0) == project.content_rect
# Autosave target, then a round-trip through disk.
editor._save()
saved = default_path(pdf)
assert saved.exists()
reloaded = Project.load(saved)
assert reloaded.metadata["title"] == "Ketun joululaulu"
assert reloaded.pages[0].skew == -1.4
assert reloaded.pages[0].levels == (40, 210)
assert [c.points for c in reloaded.pages[0].cuts] == [c.points for c in page.cuts]
editor.close()
source.close()
for f in (pdf, saved):
f.unlink()
tmp.rmdir()
print("ok")
return 0
if __name__ == "__main__":
sys.exit(main())
+162
View File
@@ -0,0 +1,162 @@
"""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 # 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.
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()
for f in (pdf, out):
f.unlink()
tmp.rmdir()
print("ok")
return 0
if __name__ == "__main__":
sys.exit(main())