feat(export): PDF 内嵌函数图像矢量图

- 抽取 render.py 共享几何:新增 PlotGeometry + compute_geometry,render_svg
  改为薄序列化层,SVG 输出与重构前逐字节一致(8 组用例回归验证)
- 新增 app/plot/render_reportlab.py:消费共享几何产出 reportlab 矢量 Drawing
  (网格/坐标轴 Line、曲线 PolyLine、刻度/标签 String、ylabel Group 旋转),
  复用 STSong-Light 渲染中文,按页面内容宽 renderScale 缩放
- pdf.py _block_function_plot 改为内嵌矢量图(解析/渲染失败或超预算回退占位,
  单图失败不阻断整篇);mermaid 仍占位
- 抽取 FunctionPlotBudget + format_plot_diagnostic 到 _common.py,html/pdf 共用
- 文档同步:PDF 已内嵌函数图像,DOCX 仍占位(栅格化范围外)

Co-Authored-By: Claude Code <noreply@anthropic.com>
This commit is contained in:
yxx
2026-09-06 21:26:54 +08:00
co-authored by Claude Code
parent 4fc26a11e1
commit f1ac414866
9 changed files with 490 additions and 137 deletions
+45 -3
View File
@@ -1,6 +1,7 @@
"""导出器共享工具:URL 协议校验与占位 warning 文案。
"""导出器共享工具:URL 协议校验、函数图像预算与占位 warning 文案。
html / pdf / docx 三个导出器共用同一套安全规则,避免各写一份导致行为漂移。
html / pdf / docx 三个导出器共用同一套安全规则与函数图像资源预算,避免各写一份
导致行为漂移。
"""
from __future__ import annotations
@@ -13,9 +14,50 @@ ALLOWED_URL_SCHEMES = frozenset({"http", "https", "mailto"})
MERMAID_WARNING = "mermaid 需前端渲染,已保留为占位代码块"
RAW_HTML_WARNING = "原始 HTML 已按纯文本转义保留"
# PDF/DOCX 暂不支持静态渲染函数图像,统一回退源码占位
# DOCX 暂不支持静态渲染函数图像,统一回退源码占位
PLOT_PLACEHOLDER_WARNING = "函数图像:该格式暂不支持静态渲染,已保留为源码占位"
# 单篇文档允许的函数图像数量上限,超出部分回退占位,防止多图块并发采样耗尽内存/线程
MAX_FUNCTION_PLOTS = 16
# 单篇文档允许的函数图像累计 AST 节点预算,超出部分回退占位,防止组合复杂度(多图块
# × 多表达式 × 深表达式)在采样求值时长时间占满 CPU
MAX_TOTAL_PLOT_NODES = 8000
class FunctionPlotBudget:
"""函数图像文档级资源预算:数量上限 + 累计 AST 节点上限。
HTML 与 PDF 导出器在渲染每个 function-plot 图块前先问预算,超限即回退源码占位,
不解析不采样,避免多图块组合复杂度耗尽内存/CPU。
"""
def __init__(self, max_plots: int | None = None, max_total_nodes: int | None = None) -> None:
# 默认读模块常量(便于测试 monkeypatch 常量后重新生效)
self.max_plots = MAX_FUNCTION_PLOTS if max_plots is None else max_plots
self.max_total_nodes = MAX_TOTAL_PLOT_NODES if max_total_nodes is None else max_total_nodes
self.count = 0
self.total_nodes = 0
def check_count(self) -> str | None:
"""图块数量 +1;超限返回 warning 文案,否则返回 None。"""
self.count += 1
if self.count > self.max_plots:
return f"函数图像:文档内函数图像数量超过上限 {self.max_plots},已回退为源码占位"
return None
def check_nodes(self, node_count: int) -> str | None:
"""累计节点预算校验;超限返回 warning 文案(不累加),否则累加并返回 None。"""
if self.total_nodes + node_count > self.max_total_nodes:
return f"函数图像:文档内函数图像累计复杂度超过上限 {self.max_total_nodes} 节点,已回退为源码占位"
self.total_nodes += node_count
return None
def format_plot_diagnostic(diag) -> str:
"""把解析诊断格式化为面向用户的 warning 文案。"""
loc = f"(第 {diag.line} 行)" if diag.line else ""
return f"函数图像:{diag.message}{loc}"
def safe_url(url: str) -> str | None:
"""校验 URL 协议;安全返回原串,不安全返回 None。"""
+9 -24
View File
@@ -13,6 +13,7 @@ from urllib.parse import urlparse
from app.contracts import ExportOptions
from app.export.document import Document, DocumentNode, ExportResult
from app.export.exporters._common import FunctionPlotBudget, format_plot_diagnostic
from app.plot.renderer import FunctionPlotStaticRenderer, StaticRenderRequest
_MERMAID_WARNING = "mermaid 需前端渲染,已保留为占位代码块"
@@ -21,12 +22,6 @@ _RAW_HTML_WARNING = "原始 HTML 已按纯文本转义保留"
# 链接/图片地址允许的协议;无 scheme 的相对地址视为安全,其余协议一律降级
_ALLOWED_URL_SCHEMES = frozenset({"http", "https", "mailto"})
# 单篇文档允许的函数图像数量上限,超出部分回退占位,防止多图块并发采样耗尽内存/线程
_MAX_FUNCTION_PLOTS = 16
# 单篇文档允许的函数图像累计 AST 节点预算,超出部分回退占位,防止组合复杂度(多图块
# × 多表达式 × 深表达式)在采样求值时长时间占满 CPU
_MAX_TOTAL_PLOT_NODES = 8000
def _safe_url(url: str) -> str | None:
"""校验 URL 协议;安全返回原串,不安全返回 None。"""
@@ -74,8 +69,7 @@ class HtmlExporter:
def render(self, document: Document, options: ExportOptions) -> ExportResult:
"""同步渲染;CPU 密集,调用方应放入线程执行,避免阻塞事件循环。"""
self._options = options
self._plot_count = 0
self._plot_nodes = 0
self._plot_budget = FunctionPlotBudget()
self._plot_renderer = FunctionPlotStaticRenderer()
warnings: list[str] = []
body = self._render_children(document.children, warnings)
@@ -205,18 +199,11 @@ class HtmlExporter:
warnings.append(_MERMAID_WARNING)
return f'<pre class="mermaid">{html.escape(node.text)}</pre>'
@staticmethod
def _format_plot_diagnostic(diag) -> str:
loc = f"(第 {diag.line} 行)" if diag.line else ""
return f"函数图像:{diag.message}{loc}"
def _render_function_plot(self, node: DocumentNode, warnings: list[str]) -> str:
# 文档级数量上限:超出部分直接回退占位,不解析不采样,防止海量图像耗尽资源
self._plot_count += 1
if self._plot_count > _MAX_FUNCTION_PLOTS:
warnings.append(
f"函数图像:文档内函数图像数量超过上限 {_MAX_FUNCTION_PLOTS},已回退为源码占位"
)
over = self._plot_budget.check_count()
if over is not None:
warnings.append(over)
return f'<pre class="function-plot">{html.escape(node.text)}</pre>'
# 解析与渲染共同纳入局部异常回退:单个图像失败只回退占位 + warning,
# 绝不阻断整篇导出(含复杂表达式触发的 RecursionError 等异常)。
@@ -226,16 +213,14 @@ class HtmlExporter:
)
parsed = self._plot_renderer.parse(request)
for diag in parsed.diagnostics:
warnings.append(self._format_plot_diagnostic(diag))
warnings.append(format_plot_diagnostic(diag))
if parsed.plot is None:
return f'<pre class="function-plot">{html.escape(node.text)}</pre>'
# 文档级累计复杂度预算:超出后回退占位,不再采样求值
if self._plot_nodes + parsed.plot.node_count > _MAX_TOTAL_PLOT_NODES:
warnings.append(
f"函数图像:文档内函数图像累计复杂度超过上限 {_MAX_TOTAL_PLOT_NODES} 节点,已回退为源码占位"
)
over = self._plot_budget.check_nodes(parsed.plot.node_count)
if over is not None:
warnings.append(over)
return f'<pre class="function-plot">{html.escape(node.text)}</pre>'
self._plot_nodes += parsed.plot.node_count
rendered = self._plot_renderer.render_plot(parsed.plot)
except Exception as exc:
warnings.append(f"函数图像:解析或渲染失败,已回退占位({exc}")
+39 -3
View File
@@ -31,11 +31,14 @@ from app.contracts import ExportOptions
from app.export.document import Document, DocumentNode, ExportResult
from app.export.exporters._common import (
MERMAID_WARNING,
PLOT_PLACEHOLDER_WARNING,
RAW_HTML_WARNING,
FunctionPlotBudget,
format_meta_value,
format_plot_diagnostic,
safe_url,
)
from app.plot.render_reportlab import render_drawing
from app.plot.renderer import FunctionPlotStaticRenderer, StaticRenderRequest
_FONT = "STSong-Light"
pdfmetrics.registerFont(UnicodeCIDFont(_FONT))
@@ -118,6 +121,11 @@ class PdfExporter:
warnings: list[str] = []
page = _PAGE_SIZES.get((options.page_size or "A4").lower(), A4)
self._options = options
self._plot_budget = FunctionPlotBudget()
self._plot_renderer = FunctionPlotStaticRenderer()
# 内容区宽度(左右各 20mm 边距),供函数图像缩放适配页面
self._plot_width = page[0] - 40 * mm
buf = BytesIO()
doc = SimpleDocTemplate(
buf,
@@ -292,8 +300,36 @@ class PdfExporter:
story.append(Preformatted(node.text, self._styles["code"]))
def _block_function_plot(self, node: DocumentNode, story: list, warnings: list[str]) -> None:
warnings.append(PLOT_PLACEHOLDER_WARNING)
story.append(Preformatted(node.text, self._styles["code"]))
# 文档级数量上限:超出部分直接回退占位,不解析不采样,防止海量图像耗尽资源
over = self._plot_budget.check_count()
if over is not None:
warnings.append(over)
story.append(Preformatted(node.text, self._styles["code"]))
return
# 解析与渲染共同纳入局部异常回退:单个图像失败只回退占位 + warning,
# 绝不阻断整篇导出(含复杂表达式触发的 RecursionError 等异常)。
try:
request = StaticRenderRequest(
kind="function_plot", source=node.text, theme=self._options.theme_id
)
parsed = self._plot_renderer.parse(request)
for diag in parsed.diagnostics:
warnings.append(format_plot_diagnostic(diag))
if parsed.plot is None:
story.append(Preformatted(node.text, self._styles["code"]))
return
# 文档级累计复杂度预算:超出后回退占位,不再采样求值
over = self._plot_budget.check_nodes(parsed.plot.node_count)
if over is not None:
warnings.append(over)
story.append(Preformatted(node.text, self._styles["code"]))
return
# Drawing 本身即 Flowable,缩放后追加到 story,与 HTML 视觉一致
drawing = render_drawing(parsed.plot, width=self._plot_width)
story.append(drawing)
except Exception as exc:
warnings.append(f"函数图像:解析或渲染失败,已回退占位({exc}")
story.append(Preformatted(node.text, self._styles["code"]))
def _block_math_block(self, node: DocumentNode, story: list, warnings: list[str]) -> None:
story.append(Paragraph(f"$${_html.escape(node.text)}$$", self._styles["math"]))
+171 -95
View File
@@ -1,7 +1,11 @@
"""Function Plot → 静态 SVG 渲染。
"""Function Plot → 静态 SVG 渲染 + 共享几何计算
只输出纯几何与 <text> 的 SVG(无 script/foreignObject/内联事件),可安全内嵌 HTML。
所有文本与颜色都经过转义/校验,不把用户输入直接拼进标记。
几何计算(范围解析、采样、刻度、非有限点分段)统一收敛到 ``compute_geometry``
返回像素坐标的 ``PlotGeometry````render_svg`` 只做 SVG 序列化,reportlab 后端
``render_reportlab.py``)消费同一份几何,保证 PDF 与 SVG 视觉一致。
"""
from __future__ import annotations
@@ -9,7 +13,7 @@ from __future__ import annotations
import html
import math
import re
from typing import Callable
from dataclasses import dataclass
from app.plot.model import FunctionPlot, StaticRenderResult
from app.plot.parser import PlotParseError, evaluate, parse_expression
@@ -102,17 +106,51 @@ def _compute_range(
return lo - pad, hi + pad
def _polyline(
def _sx(x: float, xmin: float, xmax: float) -> float:
"""数据 x → 像素 x(SVG y-down 约定,原点左上)。"""
return _MARGIN + (x - xmin) / (xmax - xmin) * (_WIDTH - 2 * _MARGIN)
def _sy(y: float, ymin: float, ymax: float) -> float:
"""数据 y → 像素 y(SVG y-down 约定,原点左上)。"""
return _HEIGHT - _MARGIN - (y - ymin) / (ymax - ymin) * (_HEIGHT - 2 * _MARGIN)
@dataclass
class PlotGeometry:
"""已解析的几何:范围、轴位置、刻度、曲线像素点段、标签与 warnings。
像素坐标统一为 SVG y-down 约定;reportlab 后端(y-up)自行翻转 y。
"""
width: int
height: int
xmin: float
xmax: float
ymin: float
ymax: float
x_axis_y: float # 数据空间里 x 轴所在 y(过原点则 0,否则贴边)
y_axis_x: float # 数据空间里 y 轴所在 x(过原点则 0,否则贴边)
xticks: list[float]
yticks: list[float]
polylines: list[list[list[tuple[float, float]]]] # 按表达式分组:段 → 像素点
colors: list[str] # 与 polylines 对齐
xlabel: str | None
ylabel: str | None
grid: bool
warnings: list[str]
def _sample_segments(
tree: object,
xmin: float,
xmax: float,
sx: Callable[[float], float],
sy: Callable[[float], float],
color: str,
) -> str:
"""采样并把非有限点处断开成多段 polyline,避免画穿渐近线。"""
segments: list[str] = []
points: list[str] = []
ymin: float,
ymax: float,
) -> list[list[tuple[float, float]]]:
"""采样并映射为像素点段;非有限点处断段,避免画穿渐近线。"""
segments: list[list[tuple[float, float]]] = []
points: list[tuple[float, float]] = []
for i in range(_SAMPLES + 1):
x = xmin + (xmax - xmin) * i / _SAMPLES
try:
@@ -121,85 +159,25 @@ def _polyline(
y = math.nan
if not isinstance(y, (int, float)) or not math.isfinite(y):
if points:
segments.append(f'<polyline points="{" ".join(points)}" fill="none" stroke="{color}"/>')
segments.append(points)
points = []
continue
px = sx(x)
py = sy(y)
px = _sx(x, xmin, xmax)
py = _sy(y, ymin, ymax)
# 映射后的坐标必须有限:显式 range 下极端 y 值可能让像素坐标溢出为 inf
if not (math.isfinite(px) and math.isfinite(py)):
if points:
segments.append(f'<polyline points="{" ".join(points)}" fill="none" stroke="{color}"/>')
segments.append(points)
points = []
continue
points.append(f"{px:.2f},{py:.2f}")
points.append((px, py))
if points:
segments.append(f'<polyline points="{" ".join(points)}" fill="none" stroke="{color}"/>')
return "".join(segments)
segments.append(points)
return segments
def _grid(
xmin: float,
xmax: float,
ymin: float,
ymax: float,
sx: Callable[[float], float],
sy: Callable[[float], float],
) -> str:
parts: list[str] = []
for x in _ticks(xmin, xmax, _nice_step(xmax - xmin)):
parts.append(f'<line x1="{sx(x):.2f}" y1="{sy(ymin):.2f}" x2="{sx(x):.2f}" y2="{sy(ymax):.2f}" stroke="#eaeef2"/>')
for y in _ticks(ymin, ymax, _nice_step(ymax - ymin)):
parts.append(f'<line x1="{sx(xmin):.2f}" y1="{sy(y):.2f}" x2="{sx(xmax):.2f}" y2="{sy(y):.2f}" stroke="#eaeef2"/>')
return "".join(parts)
def _axes(
xmin: float,
xmax: float,
ymin: float,
ymax: float,
sx: Callable[[float], float],
sy: Callable[[float], float],
) -> str:
parts: list[str] = []
# 坐标轴:过原点则画在原点,否则贴边,保证始终有参照系
x_axis_y = 0.0 if ymin <= 0 <= ymax else ymin
y_axis_x = 0.0 if xmin <= 0 <= xmax else xmin
parts.append(
f'<line x1="{sx(xmin):.2f}" y1="{sy(x_axis_y):.2f}" x2="{sx(xmax):.2f}" y2="{sy(x_axis_y):.2f}" stroke="#57606a"/>'
)
parts.append(
f'<line x1="{sx(y_axis_x):.2f}" y1="{sy(ymin):.2f}" x2="{sx(y_axis_x):.2f}" y2="{sy(ymax):.2f}" stroke="#57606a"/>'
)
# x 轴刻度数字(画在轴下方)
for x in _ticks(xmin, xmax, _nice_step(xmax - xmin)):
parts.append(
f'<text x="{sx(x):.2f}" y="{sy(x_axis_y) + 14:.2f}" text-anchor="middle" font-size="10" fill="#57606a">{html.escape(_fmt_num(x))}</text>'
)
# y 轴刻度数字(画在轴左侧)
for y in _ticks(ymin, ymax, _nice_step(ymax - ymin)):
parts.append(
f'<text x="{sx(y_axis_x) - 6:.2f}" y="{sy(y) + 3:.2f}" text-anchor="end" font-size="10" fill="#57606a">{html.escape(_fmt_num(y))}</text>'
)
return "".join(parts)
def _labels(plot: FunctionPlot, sx: Callable[[float], float], sy: Callable[[float], float]) -> str:
parts: list[str] = []
if plot.axes.xlabel:
parts.append(
f'<text x="{(_WIDTH / 2):.2f}" y="{_HEIGHT - 10:.2f}" text-anchor="middle" font-size="12" fill="#1f2328">{html.escape(plot.axes.xlabel)}</text>'
)
if plot.axes.ylabel:
parts.append(
f'<text x="16" y="{(_HEIGHT / 2):.2f}" text-anchor="middle" font-size="12" fill="#1f2328" transform="rotate(-90 16 {_HEIGHT / 2:.2f})">{html.escape(plot.axes.ylabel)}</text>'
)
return "".join(parts)
def render_svg(plot: FunctionPlot) -> StaticRenderResult:
"""把已解析的 FunctionPlot 渲染为内嵌 SVG。"""
def compute_geometry(plot: FunctionPlot) -> PlotGeometry:
"""解析并计算几何,供 SVG 与 reportlab 后端复用。"""
warnings: list[str] = []
xmin, xmax = plot.domain
if not _valid_span(xmin, xmax):
@@ -232,27 +210,125 @@ def render_svg(plot: FunctionPlot) -> StaticRenderResult:
warnings.append("y 范围跨度无法表示,回退到 [-10, 10]")
ymin, ymax = -10.0, 10.0
def sx(x: float) -> float:
return _MARGIN + (x - xmin) / (xmax - xmin) * (_WIDTH - 2 * _MARGIN)
x_axis_y = 0.0 if ymin <= 0 <= ymax else ymin
y_axis_x = 0.0 if xmin <= 0 <= xmax else xmin
xticks = _ticks(xmin, xmax, _nice_step(xmax - xmin))
yticks = _ticks(ymin, ymax, _nice_step(ymax - ymin))
def sy(y: float) -> float:
return _HEIGHT - _MARGIN - (y - ymin) / (ymax - ymin) * (_HEIGHT - 2 * _MARGIN)
parts: list[str] = [
f'<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 {_WIDTH} {_HEIGHT}" role="img">'
]
if plot.axes.grid:
parts.append(_grid(xmin, xmax, ymin, ymax, sx, sy))
parts.append(_axes(xmin, xmax, ymin, ymax, sx, sy))
polylines: list[list[list[tuple[float, float]]]] = []
colors: list[str] = []
for i, (expr, tree) in enumerate(fns):
color = _safe_color(expr.color, _PALETTE[i % len(_PALETTE)])
parts.append(_polyline(tree, xmin, xmax, sx, sy, color))
parts.append(_labels(plot, sx, sy))
colors.append(color)
polylines.append(_sample_segments(tree, xmin, xmax, ymin, ymax))
return PlotGeometry(
width=_WIDTH,
height=_HEIGHT,
xmin=xmin,
xmax=xmax,
ymin=ymin,
ymax=ymax,
x_axis_y=x_axis_y,
y_axis_x=y_axis_x,
xticks=xticks,
yticks=yticks,
polylines=polylines,
colors=colors,
xlabel=plot.axes.xlabel,
ylabel=plot.axes.ylabel,
grid=plot.axes.grid,
warnings=warnings,
)
# --- SVG 序列化(与 compute_geometry 共用,保证字节级稳定) ---
def _grid_svg(geo: PlotGeometry) -> str:
sx = lambda x: _sx(x, geo.xmin, geo.xmax)
sy = lambda y: _sy(y, geo.ymin, geo.ymax)
parts: list[str] = []
for x in geo.xticks:
parts.append(
f'<line x1="{sx(x):.2f}" y1="{sy(geo.ymin):.2f}" x2="{sx(x):.2f}" '
f'y2="{sy(geo.ymax):.2f}" stroke="#eaeef2"/>'
)
for y in geo.yticks:
parts.append(
f'<line x1="{sx(geo.xmin):.2f}" y1="{sy(y):.2f}" x2="{sx(geo.xmax):.2f}" '
f'y2="{sy(y):.2f}" stroke="#eaeef2"/>'
)
return "".join(parts)
def _axes_svg(geo: PlotGeometry) -> str:
sx = lambda x: _sx(x, geo.xmin, geo.xmax)
sy = lambda y: _sy(y, geo.ymin, geo.ymax)
parts: list[str] = []
# 坐标轴:过原点则画在原点,否则贴边,保证始终有参照系
parts.append(
f'<line x1="{sx(geo.xmin):.2f}" y1="{sy(geo.x_axis_y):.2f}" x2="{sx(geo.xmax):.2f}" '
f'y2="{sy(geo.x_axis_y):.2f}" stroke="#57606a"/>'
)
parts.append(
f'<line x1="{sx(geo.y_axis_x):.2f}" y1="{sy(geo.ymin):.2f}" x2="{sx(geo.y_axis_x):.2f}" '
f'y2="{sy(geo.ymax):.2f}" stroke="#57606a"/>'
)
# x 轴刻度数字(画在轴下方)
for x in geo.xticks:
parts.append(
f'<text x="{sx(x):.2f}" y="{sy(geo.x_axis_y) + 14:.2f}" text-anchor="middle" '
f'font-size="10" fill="#57606a">{html.escape(_fmt_num(x))}</text>'
)
# y 轴刻度数字(画在轴左侧)
for y in geo.yticks:
parts.append(
f'<text x="{sx(geo.y_axis_x) - 6:.2f}" y="{sy(y) + 3:.2f}" text-anchor="end" '
f'font-size="10" fill="#57606a">{html.escape(_fmt_num(y))}</text>'
)
return "".join(parts)
def _polylines_svg(geo: PlotGeometry) -> str:
parts: list[str] = []
for segments, color in zip(geo.polylines, geo.colors):
for seg in segments:
points = " ".join(f"{px:.2f},{py:.2f}" for px, py in seg)
parts.append(f'<polyline points="{points}" fill="none" stroke="{color}"/>')
return "".join(parts)
def _labels_svg(geo: PlotGeometry) -> str:
parts: list[str] = []
if geo.xlabel:
parts.append(
f'<text x="{geo.width / 2:.2f}" y="{geo.height - 10:.2f}" text-anchor="middle" '
f'font-size="12" fill="#1f2328">{html.escape(geo.xlabel)}</text>'
)
if geo.ylabel:
parts.append(
f'<text x="16" y="{geo.height / 2:.2f}" text-anchor="middle" font-size="12" '
f'fill="#1f2328" transform="rotate(-90 16 {geo.height / 2:.2f})">'
f'{html.escape(geo.ylabel)}</text>'
)
return "".join(parts)
def render_svg(plot: FunctionPlot) -> StaticRenderResult:
"""把已解析的 FunctionPlot 渲染为内嵌 SVG。"""
geo = compute_geometry(plot)
parts: list[str] = [
f'<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 {geo.width} {geo.height}" role="img">'
]
if geo.grid:
parts.append(_grid_svg(geo))
parts.append(_axes_svg(geo))
parts.append(_polylines_svg(geo))
parts.append(_labels_svg(geo))
parts.append("</svg>")
return StaticRenderResult(
content="".join(parts),
width=_WIDTH,
height=_HEIGHT,
warnings=warnings,
width=geo.width,
height=geo.height,
warnings=geo.warnings,
)
+116
View File
@@ -0,0 +1,116 @@
"""Function Plot → reportlab 矢量 Drawing(供 PDF 内嵌)。
消费 ``render.compute_geometry`` 的共享几何,产出 ``reportlab.graphics.shapes.Drawing``
网格/坐标轴用 ``Line``、曲线用 ``PolyLine``、刻度数字与轴标签用 ``String``。
reportlab 原点在左下(y-up),与 SVG 的 y-down 相反,故对几何里的像素 y 统一翻转;
轴标签(ylabel)用 ``Group.rotate`` 旋转为竖向文本。中文字体复用内置 STSong-Light
guarded 注册避免与 pdf.py 重复注册。
"""
from __future__ import annotations
from reportlab.graphics.shapes import Drawing, Group, Line, PolyLine, String
from reportlab.lib.colors import HexColor
from reportlab.pdfbase import pdfmetrics
from reportlab.pdfbase.cidfonts import UnicodeCIDFont
from app.plot.model import FunctionPlot
from app.plot.render import PlotGeometry, _fmt_num, _sx, _sy, compute_geometry
_FONT = "STSong-Light"
if _FONT not in pdfmetrics.getRegisteredFontNames():
pdfmetrics.registerFont(UnicodeCIDFont(_FONT))
_GRID_COLOR = HexColor("#eaeef2")
_AXIS_COLOR = HexColor("#57606a")
_LABEL_COLOR = HexColor("#1f2328")
_TICK_FONT_SIZE = 10
_LABEL_FONT_SIZE = 12
def _build_drawing(geo: PlotGeometry) -> Drawing:
"""由共享几何构建矢量 Drawing(坐标翻转后仍沿用 SVG 的像素布局)。"""
drawing = Drawing(geo.width, geo.height)
# SVG y-down → reportlab y-up:翻转像素 y
def sx(x: float) -> float:
return _sx(x, geo.xmin, geo.xmax)
def sy(y: float) -> float:
return geo.height - _sy(y, geo.ymin, geo.ymax)
# 网格
if geo.grid:
for x in geo.xticks:
drawing.add(
Line(sx(x), sy(geo.ymin), sx(x), sy(geo.ymax), strokeColor=_GRID_COLOR, strokeWidth=0.5)
)
for y in geo.yticks:
drawing.add(
Line(sx(geo.xmin), sy(y), sx(geo.xmax), sy(y), strokeColor=_GRID_COLOR, strokeWidth=0.5)
)
# 坐标轴(过原点画在原点,否则贴边,与 SVG 一致)
drawing.add(
Line(sx(geo.xmin), sy(geo.x_axis_y), sx(geo.xmax), sy(geo.x_axis_y), strokeColor=_AXIS_COLOR, strokeWidth=0.7)
)
drawing.add(
Line(sx(geo.y_axis_x), sy(geo.ymin), sx(geo.y_axis_x), sy(geo.ymax), strokeColor=_AXIS_COLOR, strokeWidth=0.7)
)
# 刻度数字(x 轴下方、y 轴左侧)
for x in geo.xticks:
drawing.add(
String(
sx(x), sy(geo.x_axis_y) - 14, _fmt_num(x),
fontName=_FONT, fontSize=_TICK_FONT_SIZE, fillColor=_AXIS_COLOR, textAnchor="middle",
)
)
for y in geo.yticks:
drawing.add(
String(
sx(geo.y_axis_x) - 6, sy(y) - 3, _fmt_num(y),
fontName=_FONT, fontSize=_TICK_FONT_SIZE, fillColor=_AXIS_COLOR, textAnchor="end",
)
)
# 曲线(非有限点处已由几何断成多段)
for segments, color in zip(geo.polylines, geo.colors):
for seg in segments:
flipped = [(px, geo.height - py) for px, py in seg]
drawing.add(PolyLine(flipped, strokeColor=HexColor(color), strokeWidth=1.4))
# 轴标签
if geo.xlabel:
drawing.add(
String(
geo.width / 2, 10, geo.xlabel,
fontName=_FONT, fontSize=_LABEL_FONT_SIZE, fillColor=_LABEL_COLOR, textAnchor="middle",
)
)
if geo.ylabel:
# 竖向标签:rotate(90) 在 y-up 坐标下等价于 SVG 的 rotate(-90)
label = Group()
label.add(
String(
16, geo.height / 2, geo.ylabel,
fontName=_FONT, fontSize=_LABEL_FONT_SIZE, fillColor=_LABEL_COLOR, textAnchor="middle",
)
)
label.rotate(90, 16, geo.height / 2)
drawing.add(label)
return drawing
def render_drawing(plot: FunctionPlot, width: float | None = None) -> Drawing:
"""把已解析的 FunctionPlot 渲染为 reportlab Drawing(可直接追加到 platypus story)。
``width`` 为目标输出宽度(点),用于把 640px 的几何缩放到页面内容宽;省略则按
原始尺寸输出。缩放只影响 PDF 渲染,不改动共享几何。
"""
geo = compute_geometry(plot)
drawing = _build_drawing(geo)
if width is not None and width > 0:
drawing.renderScale = min(1.0, width / geo.width)
return drawing
+35 -1
View File
@@ -311,16 +311,50 @@ def test_export_docx_completes_with_zip_magic_bytes() -> None:
assert path.read_bytes()[:2] == b"PK"
def test_pdf_exporter_marks_plot_and_mermaid_as_placeholders() -> None:
def test_pdf_exporter_embeds_function_plot_and_marks_mermaid() -> None:
from app.export.exporters.pdf import PdfExporter
md = "```mermaid\ngraph LR\n```\n\n```function_plot\ny = x\n```"
result = asyncio.run(PdfExporter().export(parse_document(md), ExportOptions()))
assert result.content[:4] == b"%PDF"
assert any("mermaid" in w for w in result.warnings)
# function_plot 已内嵌为矢量图,不再产生「函数图像占位」warning
assert not any("函数图像" in w for w in result.warnings)
# 绘图用 STSong-Light 渲染刻度/标签,字体应嵌入 PDF
assert b"STSong-Light" in result.content
def test_pdf_exporter_function_plot_fallback_on_error() -> None:
from app.export.exporters.pdf import PdfExporter
# 解析失败(不安全表达式)应回退源码占位并记 warning,不阻断整篇导出
md = "```function_plot\ny = os.system('x')\n```"
result = asyncio.run(PdfExporter().export(parse_document(md), ExportOptions()))
assert result.content[:4] == b"%PDF"
assert any("函数图像" in w for w in result.warnings)
def test_pdf_exporter_limits_function_plot_count() -> None:
from app.export.exporters.pdf import PdfExporter
blocks = "\n\n".join("```function-plot\ny = x\n```" for _ in range(20))
result = asyncio.run(PdfExporter().export(parse_document(blocks), ExportOptions()))
assert result.content[:4] == b"%PDF"
# 超出数量上限的图块回退占位并记 warning
assert any("数量超过上限" in w for w in result.warnings)
def test_pdf_exporter_limits_total_plot_nodes(monkeypatch) -> None:
import app.export.exporters._common as common_mod
from app.export.exporters.pdf import PdfExporter
monkeypatch.setattr(common_mod, "MAX_TOTAL_PLOT_NODES", 5)
md = "```function-plot\ny = x\n```\n\n```function-plot\ny = x + x + x + x\n```"
result = asyncio.run(PdfExporter().export(parse_document(md), ExportOptions()))
assert result.content[:4] == b"%PDF"
assert any("累计复杂度" in w for w in result.warnings)
def test_docx_exporter_marks_plot_and_mermaid_as_placeholders() -> None:
from app.export.exporters.docx import DocxExporter
+63 -2
View File
@@ -278,9 +278,9 @@ def test_html_exporter_limits_function_plot_count() -> None:
def test_html_exporter_limits_total_plot_nodes(monkeypatch) -> None:
# P1:文档级累计 AST 节点预算超限后,后续图像回退占位,防止组合复杂度耗尽 CPU
import app.export.exporters.html as html_mod
import app.export.exporters._common as common_mod
monkeypatch.setattr(html_mod, "_MAX_TOTAL_PLOT_NODES", 5)
monkeypatch.setattr(common_mod, "MAX_TOTAL_PLOT_NODES", 5)
# 第一个图块 y=x(1 节点)在预算内;第二个图块 y=x+x+x+x(7 节点)累计超限
md = "```function-plot\ny = x\n```\n\n```function-plot\ny = x + x + x + x\n```"
result = asyncio.run(HtmlExporter().export(parse_document(md), ExportOptions()))
@@ -322,3 +322,64 @@ def test_mermaid_static_renderer_returns_placeholder() -> None:
result = renderer.render(StaticRenderRequest(kind="mermaid", source="graph LR"))
assert result.content == ""
assert any("mermaid" in w for w in result.warnings)
# --------------------------------------------------------------------------- #
# 共享几何与 reportlab 后端(PDF 内嵌函数图像)
# --------------------------------------------------------------------------- #
def test_compute_geometry_shares_pixel_segments() -> None:
from app.plot.render import compute_geometry
plot = parse_source("y = x^2\ny = sin(x)").plot
geo = compute_geometry(plot)
assert geo.width == 640
assert geo.height == 480
assert len(geo.polylines) == 2
assert geo.colors == ["#0969da", "#d1242f"]
assert geo.xticks and geo.yticks
for segments in geo.polylines:
assert segments
for seg in segments:
assert seg
for px, py in seg:
assert math.isfinite(px) and math.isfinite(py)
assert 0 <= px <= geo.width
assert 0 <= py <= geo.height
def test_render_reportlab_builds_drawing() -> None:
from reportlab.graphics.shapes import Drawing, Group, Line, PolyLine, String
from app.plot.render_reportlab import render_drawing
plot = parse_source("xlabel: 时间\nylabel: 数值\ny = x^2").plot
drawing = render_drawing(plot, width=480)
assert isinstance(drawing, Drawing)
assert drawing.renderScale == 0.75 # 480 / 640
kinds = {type(c).__name__ for c in drawing.contents}
assert {"Line", "PolyLine", "String", "Group"} <= kinds
strings = [c for c in drawing.contents if isinstance(c, String)]
assert any(s.fontName == "STSong-Light" for s in strings)
assert any(s.text == "时间" for s in strings)
# ylabel 在旋转 Group 内
groups = [c for c in drawing.contents if isinstance(c, Group)]
assert groups
group_texts = [s.text for g in groups for s in g.contents if isinstance(s, String)]
assert "数值" in group_texts
def test_render_reportlab_curves_are_finite_and_bounded() -> None:
from reportlab.graphics.shapes import PolyLine
from app.plot.render_reportlab import render_drawing
plot = parse_source("y = x").plot
drawing = render_drawing(plot)
polylines = [c for c in drawing.contents if isinstance(c, PolyLine)]
assert polylines
for pl in polylines:
pts = pl.points # 扁平 [x0,y0,x1,y1,...]
for x, y in zip(pts[0::2], pts[1::2]):
assert math.isfinite(x) and math.isfinite(y)
assert 0 <= x <= 640
assert 0 <= y <= 480
@@ -74,7 +74,7 @@
| Export | GET | `/api/exports/{job_id}/file` | 已实现 | 下载已完成产物 |
| Export | POST | `/api/exports/{job_id}/cancel` | 已实现 | 取消导出任务 |
| Theme | Host Contract | `ThemePackageService` | 计划新增 | 导入、预览、启停和卸载主题包 |
| Renderer | 内部 Contract | `StaticRenderer` | 已实现 | Function Plot 后端静态 SVG 渲染;Mermaid 返回占位;PDF/DOCX 中两者保留源码占位 |
| Renderer | 内部 Contract | `StaticRenderer` | 已实现 | Function Plot 后端静态 SVG 渲染 + PDF 矢量内嵌(共享几何)Mermaid 返回占位;DOCX 保留源码占位 |
---
@@ -1080,7 +1080,7 @@ VECTOR_INDEX_REBUILD_REQUIRED
## 10. Export Service
> 实现状态:HTML / PDF / DOCX 导出均已实现(`backend/app/export/`),`format` 支持 `html`/`pdf`/`docx` 三格式。`function-plot` 已支持静态 SVG 内嵌(`backend/app/plot/`),解析或渲染失败时回退为源码占位并记录 warning;Mermaid 目前仍以占位代码块保留并记 warning。PDF/DOCX 为文本优先 v1`function-plot` 与 Mermaid 保留源码占位并记 warning。
> 实现状态:HTML / PDF / DOCX 导出均已实现(`backend/app/export/`),`format` 支持 `html`/`pdf`/`docx` 三格式。`function-plot` 已支持静态 SVG 内嵌(HTML)与矢量图内嵌(PDF,经 `backend/app/plot/render_reportlab.py` 复用共享几何),解析或渲染失败时回退为源码占位并记录 warning;Mermaid 目前仍以占位代码块保留并记 warning。DOCX 为文本优先 v1`function-plot` 与 Mermaid 保留源码占位并记 warning。
### 10.1 创建导出任务
+10 -7
View File
@@ -15,16 +15,17 @@ backend/app/export/
├── markdown.py mistune 'ast' renderer → Document AST
├── exporters/
│ ├── __init__.py
│ ├── _common.py 共享工具(URL 协议校验 + 占位 warning 文案 + 元数据格式化)
│ ├── _common.py 共享工具(URL 协议校验 + 函数图像预算 + 占位 warning 文案 + 元数据格式化)
│ ├── html.py HtmlExporterDocument AST → 完整 HTML5
│ ├── pdf.py PdfExporterDocument AST → PDFreportlab
│ └── docx.py DocxExporterDocument AST → DOCXpython-docx
└── service.py ExportService(注册表 + 后台渲染 + 取消 + 产物生命周期)
backend/app/plot/
├── parser.py 函数图像表达式解析(白名单 AST)
├── render.py FunctionPlot → 静态 SVG
── renderer.py StaticRenderer 内部契约(§10.4
├── parser.py 函数图像表达式解析(白名单 AST
├── render.py FunctionPlot → 共享几何(compute_geometry+ 静态 SVG
── render_reportlab.py FunctionPlot → reportlab 矢量 DrawingPDF 内嵌
└── renderer.py StaticRenderer 内部契约(§10.4
```
HTTP DTO`ExportStatus` / `ExportFormat` / `ExportSource` / `ExportOptions` / `ExportJob` 等)放在 [app/contracts.py](../../backend/app/contracts.py),与 Benchmark DTO 同层;`DocumentNode` / `ExportResult` 属导出器内部协议,放在 `export/document.py`,不进入 HTTP 契约。
@@ -62,9 +63,10 @@ fenced code 按语言分流:`mermaid` → `mermaid` 节点、`function_plot`/`
## PDF / DOCX 导出器(v1 文本优先)
`PdfExporter`reportlab platypus)与 `DocxExporter`python-docx)实现与 HtmlExporter 一致的同步 `render(document, options) -> ExportResult` + 异步 `export`。v1 为文本优先,覆盖标题/段落/行内强调与链接/列表/引用/表格/代码块/数学文本;`function_plot``mermaid` 保留源码占位并记 warning(与现有 Mermaid 处理一致)。
`PdfExporter`reportlab platypus)与 `DocxExporter`python-docx)实现与 HtmlExporter 一致的同步 `render(document, options) -> ExportResult` + 异步 `export`。v1 为文本优先,覆盖标题/段落/行内强调与链接/列表/引用/表格/代码块/数学文本;`mermaid` 保留源码占位并记 warning。`function_plot` 在 PDF 中已内嵌为矢量图,在 DOCX 中仍保留源码占位并记 warning(DOCX 内嵌需栅格化,本轮范围外)。
- PDF 中文字体用 reportlab 内置 `STSong-Light` CID 字体,无外部字体依赖;CID 字体无独立 bold/italic 字重,行内强调退化为普通文本(内容不丢、样式简化),标题靠字号区分层级。
- PDF 的 `function_plot``render_reportlab` 消费 `compute_geometry` 的共享几何,产出矢量 `Drawing`(网格/坐标轴 `Line`、曲线 `PolyLine`、刻度/标签 `String`ylabel 用 `Group` 旋转),再按页面内容宽缩放追加到 story,与 HTML 的 SVG 视觉一致;解析/渲染失败或超预算时回退源码占位并记 warning,单图失败不阻断整篇。
- DOCX 通过 Normal 样式挂载 `w:eastAsia=宋体` 保证中文显示,bold/italic 由 Word 原生渲染;链接写入可点击的 `w:hyperlink` run。
- 扩展名/MIMEhtml→`.html`/`text/html`pdf→`.pdf`/`application/pdf`docx→`.docx`/`application/vnd.openxmlformats-officedocument.wordprocessingml.document`;路由 `FileResponse``mime_type` + `file_name` 通用化,无需改路由。
@@ -121,10 +123,11 @@ cd backend
uv run pytest -q
```
`tests/test_export.py` 覆盖 Markdown 解析(标题/行内/列表/代码分流/表格/数学)、HTML 渲染(标签 + 转义 + warning)、Service 端到端(note 源与 markdown 源、PDF/DOCX 魔法字节与 CJK 字体、引用块正文与嵌套列表顺序等结构内容回归、排队任务取消、未知 note、取消、list/get、过期 410)与 `ExportSource` 契约校验。`tests/test_plot.py` 覆盖表达式解析/求值、SVG 渲染与 `StaticRenderer` 契约(函数图像渲染、Mermaid 占位)。
`tests/test_export.py` 覆盖 Markdown 解析(标题/行内/列表/代码分流/表格/数学)、HTML 渲染(标签 + 转义 + warning)、Service 端到端(note 源与 markdown 源、PDF/DOCX 魔法字节与 CJK 字体、引用块正文与嵌套列表顺序等结构内容回归、排队任务取消、未知 note、取消、list/get、过期 410)与 `ExportSource` 契约校验。`tests/test_plot.py` 覆盖表达式解析/求值、SVG 渲染、共享几何 `compute_geometry``render_reportlab` 矢量 DrawingLine/PolyLine/String/Group、CJK 字体、y 翻转、缩放)`StaticRenderer` 契约(函数图像渲染、Mermaid 占位)。
## 范围外(后续 PR
- PDF 内嵌函数图像与 Mermaid 渲染(v1 仅源码占位)。
- Mermaid 静态渲染(后端无渲染能力,HTML/PDF/DOCX 均保留源码占位)。
- DOCX 内嵌函数图像(需栅格化为 PNG,本轮范围外,仅 PDF 内嵌矢量图)。
- 函数图像交互预览与缩放(前端 JS Renderer 负责,后端仅提供静态 SVG)。
- 代码语法高亮(当前仅 CSS class 占位)。