fix: fix various issues before merging

api/services/pdf_service.py

@@ -2,23 +2,23 @@
 PDF 生成服务
 """
 import logging
-import re
+from io import BytesIO
 from typing import List
 
 import httpx
+from PIL import Image
 from reportlab.lib.pagesizes import A4
 from reportlab.lib.styles import getSampleStyleSheet, ParagraphStyle
 from reportlab.lib.units import inch
 from reportlab.platypus import SimpleDocTemplate, Paragraph, Spacer, PageBreak, Image as ReportLabImage
 from reportlab.pdfbase import pdfmetrics
 from reportlab.pdfbase.cidfonts import UnicodeCIDFont
-from io import BytesIO
+from services.memoir_images.parser import PLACEHOLDER_RE
+from services.memoir_images.schema import IMAGE_STATUS_COMPLETED, normalize_image_assets
 from services.memoir_images.storage import TencentCosStorageService, resolve_image_storage_key
 
 logger = logging.getLogger(__name__)
 
-PLACEHOLDER_RE = re.compile(r"\{\{\{\{IMAGE:.*?\}\}\}\}|\{\{IMAGE:.*?\}\}", re.DOTALL)
-
 
 def strip_image_placeholders(text: str) -> str:
     return PLACEHOLDER_RE.sub("", text or "").strip()
@@ -35,7 +35,7 @@ def split_content_blocks(content: str, images: list[dict]) -> list[dict]:
         cleaned_before = strip_image_placeholders(before)
         if cleaned_before:
             blocks.append({"type": "text", "value": cleaned_before})
-        if image.get("status") == "completed" and image.get("url"):
+        if image.get("status") == IMAGE_STATUS_COMPLETED and image.get("url"):
             blocks.append({"type": "image", "url": image["url"]})
     cleaned_remaining = strip_image_placeholders(remaining)
     if cleaned_remaining:
@@ -47,10 +47,10 @@ def _prepare_pdf_image_assets(images: list[dict]) -> list[dict]:
     storage = TencentCosStorageService.from_env()
     prepared_assets: list[dict] = []
 
-    for item in images or []:
+    for item in normalize_image_assets(images):
         asset = dict(item)
         storage_key = resolve_image_storage_key(asset)
-        if asset.get("status") == "completed" and storage_key:
+        if asset.get("status") == IMAGE_STATUS_COMPLETED and storage_key:
             try:
                 asset["url"] = storage.get_download_url(storage_key)
             except Exception as exc:
@@ -60,6 +60,16 @@ def _prepare_pdf_image_assets(images: list[dict]) -> list[dict]:
     return prepared_assets
 
 
+def _fit_image_size(image_bytes: bytes, max_width: float, max_height: float) -> tuple[float, float]:
+    with Image.open(BytesIO(image_bytes)) as image:
+        width, height = image.size
+    if width <= 0 or height <= 0:
+        return max_width, max_height
+
+    scale = min(max_width / width, max_height / height)
+    return width * scale, height * scale
+
+
 class PDFService:
     """PDF 生成服务"""
 
@@ -140,7 +150,12 @@ class PDFService:
                     image_bytes = await self._fetch_image_bytes(block["url"])
                     if image_bytes:
                         try:
-                            img = ReportLabImage(BytesIO(image_bytes), width=5 * inch, height=3.75 * inch)
+                            width, height = _fit_image_size(
+                                image_bytes,
+                                max_width=5 * inch,
+                                max_height=3.75 * inch,
+                            )
+                            img = ReportLabImage(BytesIO(image_bytes), width=width, height=height)
                             story.append(img)
                             story.append(Spacer(1, 0.2 * inch))
                         except Exception as exc: