File size: 12,184 Bytes
b9c7f6c | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 | """μ¨λΌμΈ νκΈ° strokeλ₯Ό λͺ¨λΈ λ
립μ μΈ 2μ°¨μ μμ μ
λ‘ λ¬Άλλ€."""
from __future__ import annotations
from dataclasses import dataclass
from statistics import median
from typing import Any, Sequence
from PIL import Image, ImageDraw
@dataclass(frozen=True, slots=True)
class GridConfig:
"""νμ λ³μ: κΈ°ν μκ³κ°κ³Ό μ
λ ₯ μνμ΄λ€.
μλ μ리: κ³ μ μ΅μκ°κ³Ό λν ν λμ΄ λΉμ¨μ ν¨κ» μ¬μ©ν΄ κΈ°κΈ° μ’νκ³ λ³νμ λμνλ€.
"""
baseline_tolerance: float = 24.0
expression_gap: float = 72.0
structure_gap: float = 52.0
padding: float = 12.0
max_strokes: int = 2_000
max_points_per_stroke: int = 4_096
max_total_points: int = 200_000
coordinate_limit: float = 20_000.0
@dataclass(frozen=True, slots=True)
class StrokeBox:
"""νμ λ³μ: μ’Β·μΒ·μ°Β·ν κ²½κ³λ€.
μλ μ리: νκ³Ό μμ μ
μ μΆ μ λ ¬ κ²½κ³ λ° λ³ν© μ°μ°μ μ 곡νλ€.
"""
left: float
top: float
right: float
bottom: float
@property
def width(self) -> float:
"""νμ λ³μ: μ’μ° μ’ν. μλ μ리: μμκ° μλ νμ λ°ννλ€."""
return max(0.0, self.right - self.left)
@property
def height(self) -> float:
"""νμ λ³μ: μν μ’ν. μλ μ리: μμκ° μλ λμ΄λ₯Ό λ°ννλ€."""
return max(0.0, self.bottom - self.top)
@property
def center_y(self) -> float:
"""νμ λ³μ: μν μ’ν. μλ μ리: κ°μ κΈ°μ€μ νμ μ© μ€μ¬μ λ°ννλ€."""
return (self.top + self.bottom) / 2.0
def union(self, other: "StrokeBox") -> "StrokeBox":
"""νμ λ³μ: λ€λ₯Έ κ²½κ³. μλ μ리: λ κ²½κ³λ₯Ό ν¬ν¨νλ μ΅μ κ²½κ³λ₯Ό λ§λ λ€."""
return StrokeBox(
min(self.left, other.left),
min(self.top, other.top),
max(self.right, other.right),
max(self.bottom, other.bottom),
)
@dataclass(frozen=True, slots=True)
class Stroke:
"""νμ λ³μ: μμ μ μΈ ν IDΒ·μμ μλ μ Β·μ κ΅΅κΈ°λ€.
μλ μ리: μ λ°μ§λ¦μ ν¬ν¨ν κ²½κ³λ₯Ό κ³μ°ν΄ νκΈ° νμ 보쑴νλ€.
"""
stroke_id: int
points: tuple[tuple[float, float], ...]
width: float = 3.0
@property
def box(self) -> StrokeBox:
"""νμ λ³μ: νκΈ°μ Β·κ΅΅κΈ°. μλ μ리: μ λ°μ§λ¦κΉμ§ ν¬ν¨ν κ²½κ³λ₯Ό κ³μ°νλ€."""
radius = self.width / 2.0
return StrokeBox(
min(point[0] for point in self.points) - radius,
min(point[1] for point in self.points) - radius,
max(point[0] for point in self.points) + radius,
max(point[1] for point in self.points) + radius,
)
@dataclass(frozen=True, slots=True)
class FormulaGrid:
"""νμ λ³μ: μ
μλ²Β·κ²½κ³Β·μμ ν IDλ€.
μλ μ리: μΈμκΈ°μ 무κ΄ν κ²°μ μ μμ μ
κ³μ½μ νννλ€.
"""
index: int
box: StrokeBox
stroke_ids: tuple[int, ...]
class _DisjointSet:
"""νμ λ³μ: ν κ°μ. μλ μ리: κ²½λ‘ μμΆκ³Ό ν¬κΈ° κΈ°μ€ λ³ν©μΌλ‘ μ°κ²° μ±λΆμ κ΄λ¦¬νλ€."""
def __init__(self, size: int) -> None:
"""νμ λ³μ: μμ μ. μλ μ리: κ° νμ λ
립 μ§ν©μΌλ‘ μ΄κΈ°ννλ€."""
self.parent = list(range(size))
self.size = [1] * size
def find(self, value: int) -> int:
"""νμ λ³μ: ν μΈλ±μ€. μλ μ리: λνλ₯Ό μ°Ύλ λμ κ²½λ‘λ₯Ό μμΆνλ€."""
while self.parent[value] != value:
self.parent[value] = self.parent[self.parent[value]]
value = self.parent[value]
return value
def union(self, first: int, second: int) -> None:
"""νμ λ³μ: λ ν μΈλ±μ€. μλ μ리: μμ νΈλ¦¬λ₯Ό ν° νΈλ¦¬ μλμ κ²°ν©νλ€."""
root_first = self.find(first)
root_second = self.find(second)
if root_first == root_second:
return
if self.size[root_first] < self.size[root_second]:
root_first, root_second = root_second, root_first
self.parent[root_second] = root_first
self.size[root_first] += self.size[root_second]
def parse_writing_events(value: Any, config: GridConfig | None = None) -> list[Stroke]:
"""νμ λ³μ: JSON μ μ¬ writing eventsμ μ ν μ€μ μ΄λ€.
μλ μ리: μ νν μ’νΒ·μ Β·νλ§ μν μμμ λ°μ μμ ν λΆλ³ Strokeλ‘ μ κ·ννλ€.
"""
settings = config or GridConfig()
if not isinstance(value, list):
return []
total_points = 0
strokes: list[Stroke] = []
for fallback_id, item in enumerate(value[: settings.max_strokes]):
if not isinstance(item, dict) or not isinstance(item.get("points"), list):
continue
points: list[tuple[float, float]] = []
for point in item["points"][: settings.max_points_per_stroke]:
if not isinstance(point, dict):
continue
try:
x = float(point["x"])
y = float(point["y"])
except (KeyError, TypeError, ValueError):
continue
if abs(x) <= settings.coordinate_limit and abs(y) <= settings.coordinate_limit:
points.append((x, y))
if len(points) < 2:
continue
if total_points + len(points) > settings.max_total_points:
break
try:
stroke_id = int(item.get("stroke_id", fallback_id))
width = min(32.0, max(0.5, float(item.get("width", 3.0))))
except (TypeError, ValueError):
continue
strokes.append(Stroke(stroke_id, tuple(points), width))
total_points += len(points)
return strokes
def build_formula_grids(
strokes: Sequence[Stroke],
config: GridConfig | None = None,
) -> list[FormulaGrid]:
"""νμ λ³μ: μ κ·νλ νκ³Ό μ ν μ€μ μ΄λ€.
μλ μ리: κΈ°μ€μ Β·κ·Όμ λΆμ°©Β·κ΅¬μ‘°μ κ΄κ³ κ·Έλνμ μ°κ²° μ±λΆμ 2μ°¨μ μμ μ
λ‘ λ§λ λ€.
"""
if not strokes:
return []
settings = config or GridConfig()
boxes = [stroke.box for stroke in strokes]
typical_height = median(box.height for box in boxes)
baseline = max(settings.baseline_tolerance, typical_height * 0.50)
expression_gap = max(settings.expression_gap, typical_height * 1.25)
structure_gap = max(settings.structure_gap, typical_height * 0.80)
attachment_gap = max(18.0, typical_height * 0.18)
groups = _DisjointSet(len(strokes))
for first in range(len(strokes)):
for second in range(first + 1, len(strokes)):
horizontal_gap = _axis_gap(
boxes[first].left,
boxes[first].right,
boxes[second].left,
boxes[second].right,
)
vertical_gap = _axis_gap(
boxes[first].top,
boxes[first].bottom,
boxes[second].top,
boxes[second].bottom,
)
center_gap = abs(boxes[first].center_y - boxes[second].center_y)
same_line = center_gap <= baseline and horizontal_gap <= expression_gap
attachment = (
horizontal_gap <= attachment_gap
and vertical_gap <= attachment_gap
and center_gap
<= max(boxes[first].height, boxes[second].height) * 1.35 + attachment_gap
)
if same_line or attachment:
groups.union(first, second)
_join_structural_bridges(boxes, groups, structure_gap)
members: dict[int, list[int]] = {}
for index in range(len(strokes)):
members.setdefault(groups.find(index), []).append(index)
raw: list[tuple[StrokeBox, tuple[int, ...]]] = []
for indices in members.values():
box = boxes[indices[0]]
for index in indices[1:]:
box = box.union(boxes[index])
padded = StrokeBox(
box.left - settings.padding,
box.top - settings.padding,
box.right + settings.padding,
box.bottom + settings.padding,
)
raw.append((padded, tuple(sorted(strokes[index].stroke_id for index in indices))))
raw.sort(key=lambda item: (round(item[0].top / max(1.0, baseline)), item[0].left))
return [
FormulaGrid(index=index, box=box, stroke_ids=stroke_ids)
for index, (box, stroke_ids) in enumerate(raw)
]
def render_grid_images(
image: Image.Image,
strokes: Sequence[Stroke],
grids: Sequence[FormulaGrid],
) -> list[Image.Image]:
"""νμ λ³μ: κΈ°μ€ μΊλ²μ€Β·μλ³Έ νΒ·μμ μ
μ΄λ€.
μλ μ리: κ° μ
μ μμ νλ§ ν° λ°°κ²½μ μ¬λ λλ§νκ³ μ
κ²½κ³λ‘ μλΌ RGB μ΄λ―Έμ§λ‘ λ°ννλ€.
"""
stroke_by_id = {stroke.stroke_id: stroke for stroke in strokes}
results: list[Image.Image] = []
for grid in grids:
canvas = Image.new("RGB", image.size, "white")
draw = ImageDraw.Draw(canvas)
for stroke_id in grid.stroke_ids:
stroke = stroke_by_id.get(stroke_id)
if stroke is not None:
draw.line(
stroke.points,
fill="black",
width=max(1, round(stroke.width)),
joint="curve",
)
results.append(_crop(canvas, grid.box))
return results
def _join_structural_bridges(
boxes: Sequence[StrokeBox],
groups: _DisjointSet,
structure_gap: float,
) -> None:
"""νμ λ³μ: ν κ²½κ³Β·μ§ν© ꡬ쑰·ꡬ쑰 거리λ€.
μλ μ리: κΈ΄ κ°λ‘μ μ λΆμμ , κΈ΄ μΈλ‘μ μ κ΄νΈΒ·νλ ¬ κ²½κ³ νλ³΄λ‘ λ³΄κ³ μΈμ νμ μ°κ²°νλ€.
"""
for bridge_index, bridge in enumerate(boxes):
horizontal_bridge = bridge.width >= 30 and bridge.width >= bridge.height * 4
vertical_bridge = bridge.height >= 45 and bridge.height >= bridge.width * 2.5
if not horizontal_bridge and not vertical_bridge:
continue
for other_index, other in enumerate(boxes):
if other_index == bridge_index:
continue
if horizontal_bridge:
overlap = _overlap(bridge.left, bridge.right, other.left, other.right)
denominator = max(1.0, min(bridge.width, other.width))
if (
overlap / denominator >= 0.20
and _axis_gap(bridge.top, bridge.bottom, other.top, other.bottom)
<= structure_gap
):
groups.union(bridge_index, other_index)
elif (
bridge.top - 18 <= other.center_y <= bridge.bottom + 18
and _axis_gap(bridge.left, bridge.right, other.left, other.right)
<= structure_gap
):
groups.union(bridge_index, other_index)
def _crop(image: Image.Image, box: StrokeBox) -> Image.Image:
"""νμ λ³μ: μ΄λ―Έμ§μ μ
κ²½κ³. μλ μ리: κ²½κ³λ₯Ό μ΄λ―Έμ§ μ μ μ μ’νλ‘ μ νν΄ μμ νκ² μλ₯Έλ€."""
left = max(0, min(image.width - 1, int(box.left)))
top = max(0, min(image.height - 1, int(box.top)))
right = max(left + 1, min(image.width, int(box.right + 0.999)))
bottom = max(top + 1, min(image.height, int(box.bottom + 0.999)))
return image.crop((left, top, right, bottom))
def _axis_gap(
first_start: float,
first_end: float,
second_start: float,
second_end: float,
) -> float:
"""νμ λ³μ: ν μΆμ λ ꡬκ°. μλ μ리: κ²ΉμΉλ©΄ 0, μλλ©΄ μ΅κ·Όμ λμ 거리λ₯Ό λ°ννλ€."""
return max(0.0, max(first_start, second_start) - min(first_end, second_end))
def _overlap(
first_start: float,
first_end: float,
second_start: float,
second_end: float,
) -> float:
"""νμ λ³μ: ν μΆμ λ ꡬκ°. μλ μ리: λ ꡬκ°μ κ΅μ§ν© κΈΈμ΄λ₯Ό λ°ννλ€."""
return max(0.0, min(first_end, second_end) - max(first_start, second_start))
|