fix(export): outline SVG text for AI export

backend/service/app.py

@@ -18,6 +18,7 @@ from pathlib import Path
 from typing import Optional
 from urllib.error import HTTPError, URLError
 from urllib.request import Request as UrlRequest, urlopen
+from xml.etree import ElementTree as ET
 
 from fastapi import FastAPI, File, Form, HTTPException, Query, Request, UploadFile
 from fastapi.middleware.cors import CORSMiddleware
@@ -90,6 +91,8 @@ PRODUCT_ARCHIVES_DIR.mkdir(parents=True, exist_ok=True)
 # only generated SVG documents to this private service.
 AI_CONVERTER_URL = os.environ.get("AI_CONVERTER_URL", "").rstrip("/")
 AI_EXPORT_MAX_BYTES = 25 * 1024 * 1024
+SVG_NAMESPACE = "http://www.w3.org/2000/svg"
+_AI_TEXT_FONT_CACHE: tuple[object, object, dict[int, str], int] | None = None
 
 metadata_store = MetadataStore(METADATA_DIR / "app.db")
 manager = JobManager(metadata_store)
@@ -1035,6 +1038,109 @@ class AiExportRequest(BaseModel):
     filename: str = "wordcloud.ai"
 
 
+def _ai_text_font() -> tuple[object, object, dict[int, str], int]:
+    """Load the bundled CJK font once for SVG text-to-outline conversion."""
+    global _AI_TEXT_FONT_CACHE
+    if _AI_TEXT_FONT_CACHE is not None:
+        return _AI_TEXT_FONT_CACHE
+
+    from fontTools.ttLib import TTFont
+
+    font_path = PROJECT_ROOT / "assets" / "fonts" / "STHeiti Medium.ttc"
+    font = TTFont(font_path, fontNumber=0)
+    _AI_TEXT_FONT_CACHE = (
+        font,
+        font.getGlyphSet(),
+        font.getBestCmap() or {},
+        int(font["head"].unitsPerEm),
+    )
+    return _AI_TEXT_FONT_CACHE
+
+
+def _svg_number(value: str | None, default: float = 0) -> float:
+    if value is None:
+        return default
+    match = re.match(r"\s*([-+]?(?:\d*\.\d+|\d+\.?)(?:[eE][-+]?\d+)?)", value)
+    if not match:
+        raise ValueError(f"无效数值: {value}")
+    number = float(match.group(1))
+    if not number == number or number in {float("inf"), float("-inf")}:
+        raise ValueError(f"无效数值: {value}")
+    return number
+
+
+def _svg_tag_name(element: ET.Element) -> str:
+    return element.tag.rsplit("}", 1)[-1]
+
+
+def _outline_svg_text(svg_bytes: bytes) -> bytes:
+    """Replace application SVG ``text`` nodes with CJK-safe glyph outlines.
+
+    AI5/PostScript has no portable Unicode text encoding.  Outlining here keeps
+    Chinese canvas text visually stable and leaves the private converter to
+    process only paths and basic geometry.
+    """
+    try:
+        root = ET.fromstring(svg_bytes)
+    except ET.ParseError as exc:
+        raise ValueError(f"SVG 解析失败: {exc}") from exc
+
+    font, glyph_set, cmap, units_per_em = _ai_text_font()
+    from fontTools.pens.svgPathPen import SVGPathPen
+
+    text_only_attributes = {
+        "x", "y", "dx", "dy", "rotate", "textLength", "lengthAdjust",
+        "font-family", "font-size", "font-weight", "font-style", "text-anchor",
+        "dominant-baseline", "alignment-baseline",
+    }
+
+    def outline_children(parent: ET.Element) -> None:
+        for index, element in enumerate(list(parent)):
+            if _svg_tag_name(element) != "text":
+                outline_children(element)
+                continue
+            if list(element):
+                raise ValueError("AI 导出暂不支持包含 tspan 等子节点的文字")
+
+            try:
+                font_size = _svg_number(element.get("font-size"), 16)
+                x = _svg_number(element.get("x"), 0)
+                y = _svg_number(element.get("y"), 0)
+            except ValueError as exc:
+                raise ValueError(f"AI 文字轮廓转换失败: {exc}") from exc
+            if font_size <= 0:
+                raise ValueError("AI 文字轮廓转换失败: font-size 必须大于 0")
+
+            outer = ET.Element(
+                f"{{{SVG_NAMESPACE}}}g",
+                {key: value for key, value in element.attrib.items() if key not in text_only_attributes},
+            )
+            scale = font_size / units_per_em
+            glyph_group = ET.SubElement(
+                outer,
+                f"{{{SVG_NAMESPACE}}}g",
+                {"transform": f"translate({x:g} {y:g}) scale({scale:.12g} {-scale:.12g})"},
+            )
+            cursor = 0.0
+            for character in element.text or "":
+                glyph_name = cmap.get(ord(character), ".notdef")
+                glyph = glyph_set.get(glyph_name) or glyph_set[".notdef"]
+                pen = SVGPathPen(glyph_set)
+                glyph.draw(pen)
+                path_data = pen.getCommands()
+                if path_data:
+                    ET.SubElement(
+                        glyph_group,
+                        f"{{{SVG_NAMESPACE}}}path",
+                        {"d": path_data, "transform": f"translate({cursor:g} 0)"},
+                    )
+                cursor += float(glyph.width)
+            parent[index] = outer
+
+    outline_children(root)
+    return ET.tostring(root, encoding="utf-8")
+
+
 def _ai_download_name(value: str) -> str:
     stem = Path(value).stem
     stem = re.sub(r"[^A-Za-z0-9._-]+", "-", stem).strip(".-")[:80]
@@ -1052,11 +1158,17 @@ def export_ai(payload: AiExportRequest):
     if not AI_CONVERTER_URL:
         raise HTTPException(status_code=503, detail="AI 转换服务尚未配置")
 
-    svg_bytes = payload.svg.encode("utf-8")
-    if not svg_bytes:
+    raw_svg_bytes = payload.svg.encode("utf-8")
+    if not raw_svg_bytes:
         raise HTTPException(status_code=400, detail="SVG 内容不能为空")
-    if len(svg_bytes) > AI_EXPORT_MAX_BYTES:
+    if len(raw_svg_bytes) > AI_EXPORT_MAX_BYTES:
         raise HTTPException(status_code=413, detail="SVG 文件超过 25 MB 限制")
+    try:
+        svg_bytes = _outline_svg_text(raw_svg_bytes)
+    except ValueError as exc:
+        raise HTTPException(status_code=422, detail=str(exc)) from exc
+    if len(svg_bytes) > AI_EXPORT_MAX_BYTES:
+        raise HTTPException(status_code=413, detail="文字转轮廓后的 SVG 超过 25 MB 限制")
 
     request = UrlRequest(
         f"{AI_CONVERTER_URL}/convert",