53d9e003af
- 回忆录：事实边界补充允许清单；传记文体示例与 JSON 叙事要求对齐 - default 职业提示 occupation_context；cadre/military 退休语境 - GET 章节读路径零写入，prepare_chapter_read_view + markdown_for_response - 文本归一抽到 core/text_normalize；移除弃用 reply 策略与 recompose_chapters_for_story - ConversationService：WS 连接/用户段落/结束对话；对外错误固定文案 - 测试：HTTP 脱敏契约、章节读视图、occupation 与 background_voice
195 lines
7.1 KiB
Python
195 lines
7.1 KiB
Python
"""回忆录序列化与图片归一化辅助（供 MemoirService 使用）。"""
|
||
|
||
from app.core.config import settings
|
||
from app.core.logging import get_logger
|
||
from app.features.memoir.asset_resolver import resolve_asset_refs_in_markdown
|
||
from app.features.memoir.cover_eligibility import (
|
||
chapter_eligible_for_cover_by_inline_body_image_count,
|
||
primary_chapter_memoir_image,
|
||
)
|
||
from app.features.memoir.memoir_images.schema import (
|
||
IMAGE_STATUS_COMPLETED,
|
||
IMAGE_STATUS_FAILED,
|
||
completed_image_assets,
|
||
normalize_image_assets,
|
||
)
|
||
from app.features.memoir.memoir_images.serializers import memoir_image_to_dict
|
||
from app.features.memoir.memoir_images.settings import MemoirImageSettings
|
||
from app.features.memoir.memoir_images.storage import (
|
||
CosDownloadUrlError,
|
||
TencentCosStorageService,
|
||
mark_image_delivery_unavailable,
|
||
normalize_cos_url,
|
||
resolve_image_storage_key,
|
||
)
|
||
from app.features.memoir.models import Chapter
|
||
from app.features.memoir.reading_segment_materialize import (
|
||
resolve_reading_segments_for_chapter_detail,
|
||
)
|
||
|
||
logger = get_logger(__name__)
|
||
|
||
|
||
def first_normalized_image_for_api(img: dict | None) -> dict | None:
|
||
"""单条图片经 schema 归一化后仍可能为空（例如非法状态且无可用字段），勿直接 [0]。"""
|
||
if not img:
|
||
return None
|
||
out = normalize_image_assets_for_api([img])
|
||
return out[0] if out else None
|
||
|
||
|
||
def normalize_image_assets_for_api(images: list[dict] | None) -> list[dict]:
|
||
bucket = settings.tencent_cos_bucket or ""
|
||
region = settings.tencent_cos_region or ""
|
||
base_url = settings.tencent_cos_base_url or ""
|
||
storage = TencentCosStorageService.from_settings(settings)
|
||
img_settings = MemoirImageSettings.from_settings(settings)
|
||
source_assets = normalize_image_assets(images)
|
||
if not img_settings.enabled:
|
||
source_assets = completed_image_assets(source_assets)
|
||
normalized_assets: list[dict] = []
|
||
for item in source_assets:
|
||
asset = dict(item)
|
||
normalized_url = normalize_cos_url(
|
||
asset.get("url"), bucket=bucket, region=region, base_url=base_url
|
||
)
|
||
storage_key = resolve_image_storage_key(asset)
|
||
if asset.get("status") == IMAGE_STATUS_COMPLETED and storage_key:
|
||
try:
|
||
asset["url"] = storage.get_download_url(storage_key)
|
||
except CosDownloadUrlError as exc:
|
||
logger.warning(
|
||
"章节图片签名失败: key={}, retryable={}, error={}",
|
||
storage_key,
|
||
exc.retryable,
|
||
exc,
|
||
)
|
||
asset = mark_image_delivery_unavailable(asset)
|
||
except Exception as exc:
|
||
logger.warning("章节图片签名失败: key={}, error={}", storage_key, exc)
|
||
asset = mark_image_delivery_unavailable(asset)
|
||
else:
|
||
asset["url"] = normalized_url
|
||
asset.pop("storage_key", None)
|
||
normalized_assets.append(asset)
|
||
return normalized_assets
|
||
|
||
|
||
def is_image_permanently_unavailable(rec) -> bool:
|
||
if not rec:
|
||
return False
|
||
status = getattr(rec, "status", None) or ""
|
||
retryable = getattr(rec, "retryable", None)
|
||
url = getattr(rec, "url", None)
|
||
storage_key = getattr(rec, "storage_key", None)
|
||
if status == IMAGE_STATUS_FAILED and retryable is False:
|
||
return True
|
||
if status == IMAGE_STATUS_COMPLETED and not url and not storage_key:
|
||
return True
|
||
return False
|
||
|
||
|
||
def chapter_cover_to_dict(
|
||
ch: Chapter, asset_url_map: dict[str, str] | None = None
|
||
) -> dict | None:
|
||
if not chapter_eligible_for_cover_by_inline_body_image_count(ch):
|
||
return None
|
||
m = primary_chapter_memoir_image(ch)
|
||
if m and is_image_permanently_unavailable(m):
|
||
m = None
|
||
if m:
|
||
return memoir_image_to_dict(m)
|
||
asset_url_map = asset_url_map or {}
|
||
aid = getattr(ch, "cover_asset_id", None)
|
||
if aid and asset_url_map.get(str(aid)):
|
||
url = asset_url_map[str(aid)]
|
||
return {
|
||
"placeholder": "",
|
||
"description": "章节封面",
|
||
"index": 0,
|
||
"status": IMAGE_STATUS_COMPLETED,
|
||
"prompt": None,
|
||
"url": url,
|
||
"storage_key": None,
|
||
"provider": None,
|
||
"style": None,
|
||
"size": None,
|
||
"error": None,
|
||
"retryable": None,
|
||
"created_at": None,
|
||
"updated_at": None,
|
||
}
|
||
return None
|
||
|
||
|
||
def _chapter_markdown(ch: Chapter, *, override: str | None = None) -> str:
|
||
"""正文：优先读路径临时物化串，否则 canonical_markdown。"""
|
||
if override is not None and str(override).strip():
|
||
return str(override).strip()
|
||
md = getattr(ch, "canonical_markdown", None)
|
||
if md and str(md).strip():
|
||
return str(md).strip()
|
||
return ""
|
||
|
||
|
||
def chapter_to_list_dict(
|
||
ch: Chapter,
|
||
asset_url_map: dict[str, str] | None = None,
|
||
*,
|
||
markdown_for_response: str | None = None,
|
||
) -> dict:
|
||
"""列表视图：与详情字段对齐的最小子集。"""
|
||
cover = chapter_cover_to_dict(ch, asset_url_map=asset_url_map)
|
||
cover_normalized = first_normalized_image_for_api(cover)
|
||
canonical_raw = _chapter_markdown(ch, override=markdown_for_response)
|
||
wcount = len(canonical_raw.strip()) if canonical_raw else 0
|
||
return {
|
||
"id": ch.id,
|
||
"title": ch.title,
|
||
"category": ch.category,
|
||
"order_index": ch.order_index,
|
||
"status": getattr(ch, "status", None) or "draft",
|
||
"summary": getattr(ch, "summary", None) or "",
|
||
"canonical_markdown": canonical_raw,
|
||
"cover_asset": cover_normalized,
|
||
"images": [],
|
||
"word_count": wcount,
|
||
"updated_at": ch.updated_at.isoformat() if ch.updated_at else None,
|
||
"is_new": getattr(ch, "is_new", False),
|
||
"source_segments": getattr(ch, "source_segments", None) or [],
|
||
}
|
||
|
||
|
||
def chapter_to_dict(
|
||
ch: Chapter,
|
||
asset_url_map: dict[str, str] | None = None,
|
||
*,
|
||
markdown_for_response: str | None = None,
|
||
) -> dict:
|
||
"""详情视图：stories-first 契约。asset_url_map 用于解析 asset:// 与 cover_asset_id。"""
|
||
asset_url_map = asset_url_map or {}
|
||
resolve = lambda aid: asset_url_map.get(aid) # noqa: E731
|
||
|
||
cover = chapter_cover_to_dict(ch, asset_url_map=asset_url_map)
|
||
cover_normalized = first_normalized_image_for_api(cover)
|
||
# 正文真源：优先 canonical_markdown
|
||
canonical_md = _chapter_markdown(ch, override=markdown_for_response)
|
||
canonical_md = resolve_asset_refs_in_markdown(canonical_md, resolve)
|
||
reading_segments = resolve_reading_segments_for_chapter_detail(
|
||
ch, asset_url_map=asset_url_map
|
||
)
|
||
return {
|
||
"id": ch.id,
|
||
"title": ch.title,
|
||
"canonical_markdown": canonical_md,
|
||
"order_index": ch.order_index,
|
||
"status": ch.status,
|
||
"category": ch.category,
|
||
"images": [],
|
||
"cover_asset": cover_normalized,
|
||
"reading_segments": reading_segments,
|
||
"updated_at": ch.updated_at.isoformat() if ch.updated_at else None,
|
||
"is_new": ch.is_new,
|
||
"source_segments": ch.source_segments or [],
|
||
}
|