105 lines
3.3 KiB
Python
105 lines
3.3 KiB
Python
"""
|
||
StoryImageIntentExtractor — 从 story markdown 提取唯一主图意图。
|
||
|
||
每个 story 必须且仅有一张主插图。提取策略：
|
||
1. 最具画面感的场景段落
|
||
2. 具有人物 + 动作 + 场景 + 时代细节的段落
|
||
3. 故事转折点或记忆锚点段落
|
||
4. 若 story 过于抽象，则退化为 story title/stage/time_refs/place_refs/people_refs/summary
|
||
"""
|
||
|
||
from __future__ import annotations
|
||
|
||
import re
|
||
from dataclasses import dataclass
|
||
|
||
|
||
@dataclass
|
||
class StoryImageIntentResult:
|
||
"""提取出的主图意图。"""
|
||
|
||
caption: str
|
||
prompt_brief: str
|
||
style_profile: str | None
|
||
|
||
|
||
# 画面感相关词汇（用于简单启发式评分）
|
||
_SCENE_WORDS = frozenset(
|
||
"坐 站 走 跑 看 望 笑 哭 说 听 拿 放 穿 戴 吃 喝 院子 路 巷 房 屋 树 花 山 水 河 桥 街 镇 村 城 夏天 冬天 春天 秋天 早晨 傍晚 夜晚 童年 少年 青年 中年 老人 奶奶 爷爷 父亲 母亲 孩子 朋友 老师 同学".split()
|
||
)
|
||
|
||
|
||
def _score_paragraph(text: str) -> float:
|
||
"""对段落做简单画面感评分。"""
|
||
if not text or len(text.strip()) < 20:
|
||
return 0.0
|
||
t = text.strip()
|
||
score = min(len(t) / 100.0, 2.0) # 长度 0~2 分
|
||
overlap = sum(1 for w in _SCENE_WORDS if w in t)
|
||
score += min(overlap * 0.3, 2.0) # 场景词 0~2 分
|
||
return score
|
||
|
||
|
||
def extract_primary_image_intent(
|
||
markdown: str,
|
||
*,
|
||
title: str = "",
|
||
stage: str | None = None,
|
||
summary: str | None = None,
|
||
people_refs: list[str] | None = None,
|
||
place_refs: list[str] | None = None,
|
||
time_start: str | None = None,
|
||
time_end: str | None = None,
|
||
style_profile: str | None = None,
|
||
) -> StoryImageIntentResult:
|
||
"""
|
||
从 story markdown 提取唯一主图意图。
|
||
|
||
优先从正文中选取最具画面感的段落；若正文过短或过于抽象，则使用 fallback。
|
||
"""
|
||
paragraphs: list[str] = []
|
||
if markdown and markdown.strip():
|
||
for p in re.split(r"\n\n+", markdown.strip()):
|
||
t = p.strip()
|
||
if t:
|
||
paragraphs.append(t)
|
||
|
||
best_caption = ""
|
||
best_prompt_brief = ""
|
||
best_score = 0.0
|
||
|
||
for text in paragraphs:
|
||
score = _score_paragraph(text)
|
||
if score > best_score:
|
||
best_score = score
|
||
best_caption = (text[:80] + "…") if len(text) > 80 else text
|
||
best_prompt_brief = text[:500].strip()
|
||
|
||
if best_score >= 0.5:
|
||
return StoryImageIntentResult(
|
||
caption=best_caption,
|
||
prompt_brief=best_prompt_brief,
|
||
style_profile=style_profile,
|
||
)
|
||
|
||
# Fallback: story title, stage, time, place, people, summary
|
||
fallback_parts = []
|
||
if title:
|
||
fallback_parts.append(title)
|
||
if stage:
|
||
fallback_parts.append(stage)
|
||
if time_start or time_end:
|
||
fallback_parts.append(f"{time_start or ''}-{time_end or ''}".strip("-"))
|
||
if place_refs:
|
||
fallback_parts.extend(place_refs[:3])
|
||
if people_refs:
|
||
fallback_parts.extend(people_refs[:3])
|
||
if summary:
|
||
fallback_parts.append(summary[:200])
|
||
fallback_text = "，".join(p for p in fallback_parts if p) or "人生故事"
|
||
return StoryImageIntentResult(
|
||
caption=fallback_text[:80],
|
||
prompt_brief=fallback_text,
|
||
style_profile=style_profile,
|
||
)
|