feat: initial commit
This commit is contained in:
@@ -0,0 +1,938 @@
|
||||
#!/usr/bin/env python3
|
||||
# -*- coding: utf-8 -*-
|
||||
"""
|
||||
Chapter Analyzer - 章节自动解构与模式提取
|
||||
|
||||
功能：
|
||||
1. 章节内容解析（场景分割、人物提取）
|
||||
2. 张力曲线分析（情绪压强跟踪）
|
||||
3. 爽点模式识别（打脸、降维、闭环、僭越）
|
||||
4. 套路结构提取（铺垫→压抑→爆发→反转）
|
||||
5. 学习成果输出（可复用模式）
|
||||
|
||||
用法：
|
||||
python chapter_analyzer.py --chapter-file "正文/第0003章-当众打脸.md" --project-root . --learn
|
||||
"""
|
||||
|
||||
import re
|
||||
import json
|
||||
import hashlib
|
||||
import sqlite3
|
||||
from pathlib import Path
|
||||
from dataclasses import dataclass, field, asdict
|
||||
from typing import List, Dict, Any, Optional, Tuple
|
||||
from datetime import datetime
|
||||
from enum import Enum
|
||||
import asyncio
|
||||
|
||||
try:
|
||||
from runtime_compat import enable_windows_utf8_stdio
|
||||
except ImportError:
|
||||
enable_windows_utf8_stdio = lambda: None
|
||||
|
||||
|
||||
class PatternType(Enum):
|
||||
"""模式类型"""
|
||||
HOOK = "hook" # 钩子
|
||||
PACING = "pacing" # 节奏
|
||||
DIALOGUE = "dialogue" # 对话
|
||||
PAYOFF = "payoff" # 兑现
|
||||
EMOTION = "emotion" # 情绪
|
||||
TENSION_BUILD = "tension_build" # 压强积累
|
||||
RELEASE = "release" # 释放
|
||||
TWIST = "twist" # 反转
|
||||
|
||||
|
||||
class CatharsisModel(Enum):
|
||||
"""爽感模型"""
|
||||
TABOO_TRANSGRESSION = "taboo_transgression" # 禁忌僭越
|
||||
OVERKILL_REVERSAL = "overkill_reversal" # 降维打击
|
||||
COGNITIVE_CLOSURE = "cognitive_closure" # 认知闭环
|
||||
|
||||
|
||||
@dataclass
|
||||
class TensionPoint:
|
||||
"""张力点"""
|
||||
position: int # 位置（字符偏移）
|
||||
tension: float # 张力值 0-1
|
||||
event_type: str # 事件类型
|
||||
description: str # 描述
|
||||
|
||||
|
||||
@dataclass
|
||||
class HotSpot:
|
||||
"""爽点"""
|
||||
position: int
|
||||
span: int # 持续长度
|
||||
catharsis_type: str # 爽感类型
|
||||
intensity: float # 强度 0-1
|
||||
description: str
|
||||
|
||||
|
||||
@dataclass
|
||||
class ChapterStructure:
|
||||
"""章节结构"""
|
||||
setup: int = 0 # 铺垫段落长度
|
||||
suppress: int = 0 # 压抑段落长度
|
||||
release: int = 0 # 释放段落长度
|
||||
twist: int = 0 # 反转段落长度
|
||||
|
||||
|
||||
@dataclass
|
||||
class LearnedPattern:
|
||||
"""学习到的模式"""
|
||||
pattern_id: str
|
||||
pattern_type: str
|
||||
title: str
|
||||
description: str
|
||||
tension_curve: List[List[float]] # [[position, tension], ...]
|
||||
catharsis_model: str
|
||||
structure: Dict[str, int]
|
||||
hot_spots: List[List[Any]]
|
||||
style_tags: List[str]
|
||||
source_project: str
|
||||
source_chapter: int
|
||||
learned_at: str
|
||||
usage_count: int = 0
|
||||
metadata: Dict[str, Any] = field(default_factory=dict)
|
||||
|
||||
|
||||
@dataclass
|
||||
class ChapterAnalysisResult:
|
||||
"""章节分析结果"""
|
||||
chapter: int
|
||||
title: str
|
||||
word_count: int
|
||||
scene_count: int
|
||||
character_count: int
|
||||
|
||||
# 张力分析
|
||||
tension_curve: List[List[float]] # [[position, tension], ...]
|
||||
tension_avg: float
|
||||
tension_peak: float
|
||||
tension_peak_position: int
|
||||
|
||||
# 爽点分析
|
||||
hot_spots: List[HotSpot]
|
||||
catharsis_model: str
|
||||
|
||||
# 结构分析
|
||||
structure: ChapterStructure
|
||||
|
||||
# 模式
|
||||
detected_patterns: List[str]
|
||||
|
||||
# 风格标签
|
||||
style_tags: List[str]
|
||||
|
||||
# 人物出场
|
||||
characters: List[str]
|
||||
|
||||
# 建议
|
||||
suggestions: List[str]
|
||||
|
||||
|
||||
class ChapterAnalyzer:
|
||||
"""
|
||||
章节分析器
|
||||
|
||||
自动解构章节，提取：
|
||||
- 张力曲线
|
||||
- 爽点位置和类型
|
||||
- 套路结构
|
||||
- 可复用模式
|
||||
"""
|
||||
|
||||
# 爽点关键词
|
||||
HOT_SPOT_KEYWORDS = {
|
||||
CatharsisModel.OVERKILL_REVERSAL: [
|
||||
"碾压", "秒杀", "不堪一击", "一招", "跪下", "颤抖", "惊恐",
|
||||
"脸色大变", "难以置信", "怎么可能", "废物", "蝼蚁", "打脸",
|
||||
"当众", "所有人", "目瞪口呆", "鸦雀无声", "死寂"
|
||||
],
|
||||
CatharsisModel.TABOO_TRANSGRESSION: [
|
||||
"禁忌", "僭越", "突破底线", "危险", "禁忌", "邪魅", "诱惑",
|
||||
"堕落", "黑化", "疯狂", "失控", "暴走", "越界", "禁忌"
|
||||
],
|
||||
CatharsisModel.COGNITIVE_CLOSURE: [
|
||||
"原来", "竟然", "真相", "伏笔", "恍然大悟", "所有一切",
|
||||
"早该", "早就在", "铺垫", "埋下", "算计", "布局"
|
||||
]
|
||||
}
|
||||
|
||||
# 情绪压强关键词
|
||||
TENSION_KEYWORDS = {
|
||||
# 压强上升
|
||||
"rise": ["紧张", "危机", "危险", "困境", "难题", "冲突", "对峙",
|
||||
"杀意", "阴谋", "威胁", "危机", "悬念", "未知"],
|
||||
# 压强高峰
|
||||
"peak": ["爆发", "突破", "反击", "反转", "真相", "高潮", "决战",
|
||||
"绝杀", "逆转", "翻盘", "打脸", "碾压"],
|
||||
# 压强下降
|
||||
"fall": ["松了口气", "终于", "安心", "胜利", "结束", "平息", "安然"]
|
||||
}
|
||||
|
||||
def __init__(self, project_root: Optional[Path] = None):
|
||||
self.project_root = Path(project_root) if project_root else Path.cwd()
|
||||
|
||||
def analyze_chapter(
|
||||
self,
|
||||
chapter_file: Path,
|
||||
chapter_num: Optional[int] = None
|
||||
) -> ChapterAnalysisResult:
|
||||
"""
|
||||
分析章节
|
||||
|
||||
Args:
|
||||
chapter_file: 章节文件路径
|
||||
chapter_num: 章节号（从文件名推断或手动指定）
|
||||
|
||||
Returns:
|
||||
章节分析结果
|
||||
"""
|
||||
content = chapter_file.read_text(encoding="utf-8")
|
||||
|
||||
# 解析章节号
|
||||
if chapter_num is None:
|
||||
chapter_num = self._extract_chapter_num(chapter_file.name)
|
||||
|
||||
# 解析标题
|
||||
title = self._extract_title(chapter_file.name, content)
|
||||
|
||||
# 统计字数
|
||||
word_count = len(content)
|
||||
|
||||
# 场景分割
|
||||
scenes = self._split_scenes(content)
|
||||
scene_count = len(scenes)
|
||||
|
||||
# 人物提取
|
||||
characters = self._extract_characters(content, scenes)
|
||||
|
||||
# 张力曲线分析
|
||||
tension_curve = self._analyze_tension_curve(content, scenes)
|
||||
tension_avg = sum(p[1] for p in tension_curve) / len(tension_curve) if tension_curve else 0
|
||||
peak = max(tension_curve, key=lambda x: x[1]) if tension_curve else (0, 0)
|
||||
tension_peak = peak[1]
|
||||
tension_peak_position = peak[0]
|
||||
|
||||
# 爽点分析
|
||||
hot_spots = self._detect_hot_spots(content, scenes)
|
||||
catharsis_model = self._detect_catharsis_model(hot_spots)
|
||||
|
||||
# 结构分析
|
||||
structure = self._analyze_structure(content, scenes, hot_spots)
|
||||
|
||||
# 模式检测
|
||||
detected_patterns = self._detect_patterns(
|
||||
content, scenes, tension_curve, hot_spots, structure
|
||||
)
|
||||
|
||||
# 风格标签
|
||||
style_tags = self._extract_style_tags(content, tension_curve, hot_spots)
|
||||
|
||||
# 建议
|
||||
suggestions = self._generate_suggestions(
|
||||
tension_curve, hot_spots, structure, detected_patterns
|
||||
)
|
||||
|
||||
return ChapterAnalysisResult(
|
||||
chapter=chapter_num,
|
||||
title=title,
|
||||
word_count=word_count,
|
||||
scene_count=scene_count,
|
||||
character_count=len(characters),
|
||||
tension_curve=tension_curve,
|
||||
tension_avg=tension_avg,
|
||||
tension_peak=tension_peak,
|
||||
tension_peak_position=tension_peak_position,
|
||||
hot_spots=hot_spots,
|
||||
catharsis_model=catharsis_model,
|
||||
structure=structure,
|
||||
detected_patterns=detected_patterns,
|
||||
style_tags=style_tags,
|
||||
characters=characters,
|
||||
suggestions=suggestions
|
||||
)
|
||||
|
||||
def _extract_chapter_num(self, filename: str) -> int:
|
||||
"""从文件名提取章节号"""
|
||||
match = re.search(r'第(\d+)[章节]', filename)
|
||||
if match:
|
||||
return int(match.group(1))
|
||||
return 0
|
||||
|
||||
def _extract_title(self, filename: str, content: str) -> str:
|
||||
"""提取标题"""
|
||||
# 尝试从文件名提取
|
||||
match = re.search(r'第\d+章[章节]-?(.+)', filename)
|
||||
if match:
|
||||
return match.group(1).replace('.md', '').strip()
|
||||
|
||||
# 尝试从内容第一行提取
|
||||
lines = content.split('\n')
|
||||
for line in lines[:5]:
|
||||
line = line.strip()
|
||||
if line.startswith('#'):
|
||||
return line.lstrip('#').strip()
|
||||
|
||||
return filename.replace('.md', '')
|
||||
|
||||
def _split_scenes(self, content: str) -> List[Dict[str, Any]]:
|
||||
"""
|
||||
分割场景
|
||||
|
||||
Returns:
|
||||
List[{"start": int, "end": int, "location": str, "characters": []}]
|
||||
"""
|
||||
scenes = []
|
||||
lines = content.split('\n')
|
||||
|
||||
current_scene = {
|
||||
"start": 0,
|
||||
"end": 0,
|
||||
"location": "未知",
|
||||
"characters": [],
|
||||
"lines": []
|
||||
}
|
||||
|
||||
location_patterns = [
|
||||
r'^---+$', # 分割线
|
||||
r'^【(.+?)】', # 【场景名】
|
||||
r'^（(.+?)）', # （场景名）
|
||||
]
|
||||
|
||||
for i, line in enumerate(lines):
|
||||
# 检测场景分隔
|
||||
is_divider = any(re.match(p, line.strip()) for p in location_patterns)
|
||||
|
||||
if is_divider and current_scene["lines"]:
|
||||
# 保存当前场景
|
||||
current_scene["end"] = sum(len(l) + 1 for l in current_scene["lines"][:-1])
|
||||
scenes.append(current_scene)
|
||||
|
||||
# 新场景
|
||||
location_match = re.search(r'【(.+?)】|（(.+?)）', line)
|
||||
current_scene = {
|
||||
"start": sum(len(l) + 1 for l in lines[:i]) + 1,
|
||||
"end": 0,
|
||||
"location": location_match.group(1) if location_match else "未知",
|
||||
"characters": [],
|
||||
"lines": []
|
||||
}
|
||||
|
||||
current_scene["lines"].append(line)
|
||||
|
||||
# 保存最后一个场景
|
||||
if current_scene["lines"]:
|
||||
current_scene["end"] = len(content)
|
||||
scenes.append(current_scene)
|
||||
|
||||
return scenes if scenes else [{"start": 0, "end": len(content), "location": "未知", "characters": [], "lines": content.split('\n')}]
|
||||
|
||||
def _extract_characters(
|
||||
self,
|
||||
content: str,
|
||||
scenes: List[Dict[str, Any]]
|
||||
) -> List[str]:
|
||||
"""提取人物列表"""
|
||||
# 简单实现：提取引号内的对话人
|
||||
characters = set()
|
||||
|
||||
# 匹配 "XXX说" 格式
|
||||
dialogue_pattern = re.compile(r'^"?([^"说]{2,5})"?[说问道喊叫笑骂冷哼]')
|
||||
for scene in scenes:
|
||||
for line in scene["lines"]:
|
||||
match = dialogue_pattern.match(line.strip())
|
||||
if match:
|
||||
name = match.group(1).strip()
|
||||
if name and len(name) <= 5:
|
||||
characters.add(name)
|
||||
|
||||
return list(characters)
|
||||
|
||||
def _analyze_tension_curve(
|
||||
self,
|
||||
content: str,
|
||||
scenes: List[Dict[str, Any]]
|
||||
) -> List[List[float]]:
|
||||
"""
|
||||
分析张力曲线
|
||||
|
||||
Returns:
|
||||
[[position, tension], ...] - 位置（字数）和张力值（0-1）
|
||||
"""
|
||||
curve = []
|
||||
total_len = len(content)
|
||||
segment_size = 200 # 每200字一个采样点
|
||||
|
||||
content_lower = content # 网文不区分大小写
|
||||
|
||||
for pos in range(0, total_len, segment_size):
|
||||
segment = content_lower[pos:pos + segment_size]
|
||||
tension = 0.0
|
||||
|
||||
# 检查压强上升关键词
|
||||
for kw in self.TENSION_KEYWORDS["rise"]:
|
||||
if kw in segment:
|
||||
tension += 0.2
|
||||
|
||||
# 检查压强高峰关键词
|
||||
for kw in self.TENSION_KEYWORDS["peak"]:
|
||||
if kw in segment:
|
||||
tension += 0.4
|
||||
|
||||
# 检查压强下降关键词
|
||||
for kw in self.TENSION_KEYWORDS["fall"]:
|
||||
if kw in segment:
|
||||
tension -= 0.15
|
||||
|
||||
# 限制范围
|
||||
tension = max(0.0, min(1.0, tension))
|
||||
|
||||
curve.append([pos, tension])
|
||||
|
||||
# 平滑曲线
|
||||
curve = self._smooth_curve(curve)
|
||||
|
||||
return curve
|
||||
|
||||
def _smooth_curve(self, curve: List[List[float]]) -> List[List[float]]:
|
||||
"""平滑张力曲线"""
|
||||
if len(curve) < 3:
|
||||
return curve
|
||||
|
||||
smoothed = []
|
||||
for i, point in enumerate(curve):
|
||||
if i == 0 or i == len(curve) - 1:
|
||||
smoothed.append(point)
|
||||
else:
|
||||
# 移动平均
|
||||
avg_pos = (curve[i-1][0] + point[0] + curve[i+1][0]) / 3
|
||||
avg_tension = (curve[i-1][1] + point[1] + curve[i+1][1]) / 3
|
||||
smoothed.append([avg_pos, avg_tension])
|
||||
|
||||
return smoothed
|
||||
|
||||
def _detect_hot_spots(
|
||||
self,
|
||||
content: str,
|
||||
scenes: List[Dict[str, Any]]
|
||||
) -> List[HotSpot]:
|
||||
"""检测爽点"""
|
||||
hot_spots = []
|
||||
|
||||
for model_type, keywords in self.HOT_SPOT_KEYWORDS.items():
|
||||
for keyword in keywords:
|
||||
# 查找所有出现位置
|
||||
start = 0
|
||||
while True:
|
||||
pos = content.find(keyword, start)
|
||||
if pos == -1:
|
||||
break
|
||||
|
||||
# 计算附近区域的强度
|
||||
context_start = max(0, pos - 100)
|
||||
context_end = min(len(content), pos + 100)
|
||||
context = content[context_start:context_end]
|
||||
|
||||
# 统计上下文中的情绪词数量
|
||||
intensity = 0.5 # 基础强度
|
||||
for kw_set in self.HOT_SPOT_KEYWORDS.values():
|
||||
for kw in kw_set:
|
||||
if kw in context:
|
||||
intensity += 0.1
|
||||
|
||||
intensity = min(1.0, intensity)
|
||||
|
||||
# 避免重叠
|
||||
span = len(keyword)
|
||||
is_overlap = any(
|
||||
abs(pos - hs.position) < span
|
||||
for hs in hot_spots
|
||||
)
|
||||
|
||||
if not is_overlap:
|
||||
hot_spots.append(HotSpot(
|
||||
position=pos,
|
||||
span=span,
|
||||
catharsis_type=model_type.value,
|
||||
intensity=intensity,
|
||||
description=f"发现「{keyword}」"
|
||||
))
|
||||
|
||||
start = pos + 1
|
||||
|
||||
# 按位置排序
|
||||
hot_spots.sort(key=lambda x: x.position)
|
||||
|
||||
return hot_spots
|
||||
|
||||
def _detect_catharsis_model(
|
||||
self,
|
||||
hot_spots: List[HotSpot]
|
||||
) -> str:
|
||||
"""检测主导爽感模型"""
|
||||
if not hot_spots:
|
||||
return "unknown"
|
||||
|
||||
model_counts = {}
|
||||
model_intensity = {}
|
||||
|
||||
for hs in hot_spots:
|
||||
model = hs.catharsis_type
|
||||
model_counts[model] = model_counts.get(model, 0) + 1
|
||||
model_intensity[model] = model_intensity.get(model, 0) + hs.intensity
|
||||
|
||||
# 综合评分：出现次数 * 0.4 + 强度 * 0.6
|
||||
scores = {
|
||||
m: model_counts[m] * 0.4 + model_intensity[m] * 0.6
|
||||
for m in model_counts
|
||||
}
|
||||
|
||||
return max(scores, key=scores.get) if scores else "unknown"
|
||||
|
||||
def _analyze_structure(
|
||||
self,
|
||||
content: str,
|
||||
scenes: List[Dict[str, Any]],
|
||||
hot_spots: List[HotSpot]
|
||||
) -> ChapterStructure:
|
||||
"""分析章节结构"""
|
||||
total_len = len(content)
|
||||
|
||||
if not hot_spots:
|
||||
# 无爽点：均匀分布
|
||||
segment = total_len // 4
|
||||
return ChapterStructure(
|
||||
setup=segment,
|
||||
suppress=segment,
|
||||
release=segment,
|
||||
twist=segment
|
||||
)
|
||||
|
||||
# 找第一个爽点位置作为分界
|
||||
first_hot = hot_spots[0].position
|
||||
last_hot = hot_spots[-1].position
|
||||
|
||||
# 铺垫：第一个爽点之前
|
||||
setup = first_hot
|
||||
|
||||
# 压抑+释放：根据爽点密集程度判断
|
||||
# 简化：中间区域前40%压抑，后40%释放
|
||||
middle_start = first_hot
|
||||
middle_end = last_hot + 100
|
||||
middle_len = middle_end - middle_start
|
||||
|
||||
suppress = int(middle_len * 0.4)
|
||||
release = int(middle_len * 0.4)
|
||||
twist = total_len - middle_end
|
||||
|
||||
return ChapterStructure(
|
||||
setup=max(0, setup),
|
||||
suppress=max(0, suppress),
|
||||
release=max(0, release),
|
||||
twist=max(0, twist)
|
||||
)
|
||||
|
||||
def _detect_patterns(
|
||||
self,
|
||||
content: str,
|
||||
scenes: List[Dict[str, Any]],
|
||||
tension_curve: List[List[float]],
|
||||
hot_spots: List[HotSpot],
|
||||
structure: ChapterStructure
|
||||
) -> List[str]:
|
||||
"""检测章节中的模式"""
|
||||
patterns = []
|
||||
|
||||
# 检测钩子模式
|
||||
if tension_curve and tension_curve[0][1] > 0.3:
|
||||
patterns.append("开篇高能钩")
|
||||
elif "？" in content[:200] or "！" in content[:200]:
|
||||
patterns.append("悬念钩子")
|
||||
|
||||
# 检测打脸模式
|
||||
if any(hs.catharsis_type == "overkill_reversal" for hs in hot_spots):
|
||||
patterns.append("打脸反转")
|
||||
|
||||
# 检测升级模式
|
||||
if any(kw in content for kw in ["突破", "晋升", "升级", "进阶"]):
|
||||
patterns.append("境界突破")
|
||||
|
||||
# 检测装逼模式
|
||||
if any(kw in content for kw in ["冷笑", "不屑", "蝼蚁", "可笑"]):
|
||||
patterns.append("装逼打脸")
|
||||
|
||||
# 张力曲线形状检测
|
||||
if tension_curve:
|
||||
# 持续上升 = 压抑型
|
||||
tensions = [p[1] for p in tension_curve]
|
||||
if tensions == sorted(tensions) and tensions[-1] - tensions[0] > 0.5:
|
||||
patterns.append("单线压抑")
|
||||
# 波动大 = 节奏快
|
||||
elif max(tensions) - min(tensions) > 0.6:
|
||||
patterns.append("爽点密集")
|
||||
|
||||
return patterns
|
||||
|
||||
def _extract_style_tags(
|
||||
self,
|
||||
content: str,
|
||||
tension_curve: List[List[float]],
|
||||
hot_spots: List[HotSpot]
|
||||
) -> List[str]:
|
||||
"""提取风格标签"""
|
||||
tags = []
|
||||
|
||||
# 基于字数
|
||||
word_count = len(content)
|
||||
if word_count < 2000:
|
||||
tags.append("短小精悍")
|
||||
elif word_count > 5000:
|
||||
tags.append("长篇巨制")
|
||||
|
||||
# 基于爽点密度
|
||||
if tension_curve:
|
||||
avg_tension = sum(p[1] for p in tension_curve) / len(tension_curve)
|
||||
if avg_tension > 0.5:
|
||||
tags.append("情绪压强高")
|
||||
elif avg_tension < 0.2:
|
||||
tags.append("节奏舒缓")
|
||||
|
||||
# 基于爽点类型
|
||||
if hot_spots:
|
||||
model = self._detect_catharsis_model(hot_spots)
|
||||
if model == "overkill_reversal":
|
||||
tags.append("爽点密集")
|
||||
elif model == "taboo_transgression":
|
||||
tags.append("边缘拉扯")
|
||||
elif model == "cognitive_closure":
|
||||
tags.append("多线收束")
|
||||
|
||||
# 基于对话比例
|
||||
dialogue_count = content.count('"') + content.count('"')
|
||||
dialogue_ratio = dialogue_count / max(word_count, 1)
|
||||
if dialogue_ratio > 0.3:
|
||||
tags.append("对话驱动")
|
||||
elif dialogue_ratio < 0.1:
|
||||
tags.append("叙事为主")
|
||||
|
||||
return tags
|
||||
|
||||
def _generate_suggestions(
|
||||
self,
|
||||
tension_curve: List[List[float]],
|
||||
hot_spots: List[HotSpot],
|
||||
structure: ChapterStructure,
|
||||
patterns: List[str]
|
||||
) -> List[str]:
|
||||
"""生成改进建议"""
|
||||
suggestions = []
|
||||
|
||||
# 张力曲线建议
|
||||
if tension_curve:
|
||||
avg = sum(p[1] for p in tension_curve) / len(tension_curve)
|
||||
if avg < 0.2:
|
||||
suggestions.append("张力整体偏低，建议增加危机感或悬念")
|
||||
elif avg > 0.7:
|
||||
suggestions.append("张力持续偏高，建议适当释放避免读者疲劳")
|
||||
|
||||
# 爽点建议
|
||||
if not hot_spots:
|
||||
suggestions.append("未检测到明显爽点，建议增加打脸/反转情节")
|
||||
|
||||
# 结构建议
|
||||
if structure.setup < 500:
|
||||
suggestions.append("铺垫不足，建议增加背景/动机描写")
|
||||
|
||||
# 节奏建议
|
||||
if "单线压抑" in patterns:
|
||||
suggestions.append("压抑较长，建议穿插小高潮保持节奏")
|
||||
|
||||
return suggestions
|
||||
|
||||
def learn_pattern(
|
||||
self,
|
||||
analysis: ChapterAnalysisResult,
|
||||
layer: str = "project"
|
||||
) -> LearnedPattern:
|
||||
"""
|
||||
从分析结果提取可学习模式
|
||||
|
||||
Args:
|
||||
analysis: 章节分析结果
|
||||
layer: 存储层级 ("project" 或 "system")
|
||||
|
||||
Returns:
|
||||
学习到的模式
|
||||
"""
|
||||
pattern_id = hashlib.md5(
|
||||
f"{self.project_root.name}_{analysis.chapter}_{datetime.now().isoformat()}".encode()
|
||||
).hexdigest()[:16]
|
||||
|
||||
return LearnedPattern(
|
||||
pattern_id=pattern_id,
|
||||
pattern_type=self._infer_pattern_type(analysis),
|
||||
title=f"第{analysis.chapter}章模式: {analysis.title}",
|
||||
description=self._generate_description(analysis),
|
||||
tension_curve=analysis.tension_curve,
|
||||
catharsis_model=analysis.catharsis_model,
|
||||
structure=asdict(analysis.structure),
|
||||
hot_spots=[[hs.position, hs.description] for hs in analysis.hot_spots],
|
||||
style_tags=analysis.style_tags,
|
||||
source_project=self.project_root.name,
|
||||
source_chapter=analysis.chapter,
|
||||
learned_at=datetime.now().isoformat(),
|
||||
metadata={
|
||||
"word_count": analysis.word_count,
|
||||
"scene_count": analysis.scene_count,
|
||||
"character_count": analysis.character_count,
|
||||
"detected_patterns": analysis.detected_patterns,
|
||||
"suggestions": analysis.suggestions
|
||||
}
|
||||
)
|
||||
|
||||
def _infer_pattern_type(self, analysis: ChapterAnalysisResult) -> str:
|
||||
"""推断模式类型"""
|
||||
if "打脸反转" in analysis.detected_patterns:
|
||||
return PatternType.HOOK.value
|
||||
elif "境界突破" in analysis.detected_patterns:
|
||||
return PatternType.PAYOFF.value
|
||||
elif analysis.tension_avg > 0.5:
|
||||
return PatternType.TENSION_BUILD.value
|
||||
else:
|
||||
return PatternType.PACING.value
|
||||
|
||||
def _generate_description(self, analysis: ChapterAnalysisResult) -> str:
|
||||
"""生成模式描述"""
|
||||
parts = []
|
||||
|
||||
if analysis.detected_patterns:
|
||||
parts.append(f"包含模式: {', '.join(analysis.detected_patterns[:3])}")
|
||||
|
||||
if analysis.style_tags:
|
||||
parts.append(f"风格标签: {', '.join(analysis.style_tags[:3])}")
|
||||
|
||||
parts.append(f"字数: {analysis.word_count}，场景: {analysis.scene_count}")
|
||||
|
||||
if analysis.hot_spots:
|
||||
parts.append(f"检测到 {len(analysis.hot_spots)} 个爽点")
|
||||
|
||||
return "; ".join(parts)
|
||||
|
||||
def save_learned_pattern(
|
||||
self,
|
||||
pattern: LearnedPattern,
|
||||
layer: str = "project"
|
||||
) -> bool:
|
||||
"""保存学习到的模式"""
|
||||
try:
|
||||
if layer == "project":
|
||||
return self._save_to_project_db(pattern)
|
||||
else:
|
||||
return self._save_to_system(pattern)
|
||||
except Exception as e:
|
||||
print(f"Error saving pattern: {e}")
|
||||
return False
|
||||
|
||||
def _init_project_learned_db(self) -> Path:
|
||||
"""初始化项目学习库"""
|
||||
db_dir = self.project_root / ".noma" / "rag"
|
||||
db_dir.mkdir(parents=True, exist_ok=True)
|
||||
db_path = db_dir / "learned.db"
|
||||
|
||||
conn = sqlite3.connect(str(db_path))
|
||||
cursor = conn.cursor()
|
||||
|
||||
cursor.execute("""
|
||||
CREATE TABLE IF NOT EXISTS learned_patterns (
|
||||
pattern_id TEXT PRIMARY KEY,
|
||||
pattern_type TEXT NOT NULL,
|
||||
title TEXT NOT NULL,
|
||||
description TEXT,
|
||||
tension_curve TEXT,
|
||||
catharsis_model TEXT,
|
||||
structure TEXT,
|
||||
hot_spots TEXT,
|
||||
style_tags TEXT,
|
||||
source_project TEXT,
|
||||
source_chapter INTEGER,
|
||||
learned_at TEXT,
|
||||
usage_count INTEGER DEFAULT 0,
|
||||
metadata TEXT
|
||||
)
|
||||
""")
|
||||
|
||||
conn.commit()
|
||||
conn.close()
|
||||
|
||||
return db_path
|
||||
|
||||
def _save_to_project_db(self, pattern: LearnedPattern) -> bool:
|
||||
"""保存到项目数据库"""
|
||||
db_path = self._init_project_learned_db()
|
||||
|
||||
conn = sqlite3.connect(str(db_path))
|
||||
cursor = conn.cursor()
|
||||
|
||||
cursor.execute("""
|
||||
INSERT OR REPLACE INTO learned_patterns
|
||||
(pattern_id, pattern_type, title, description, tension_curve,
|
||||
catharsis_model, structure, hot_spots, style_tags,
|
||||
source_project, source_chapter, learned_at, usage_count, metadata)
|
||||
VALUES (?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?)
|
||||
""", (
|
||||
pattern.pattern_id,
|
||||
pattern.pattern_type,
|
||||
pattern.title,
|
||||
pattern.description,
|
||||
json.dumps(pattern.tension_curve),
|
||||
pattern.catharsis_model,
|
||||
json.dumps(pattern.structure),
|
||||
json.dumps(pattern.hot_spots),
|
||||
json.dumps(pattern.style_tags),
|
||||
pattern.source_project,
|
||||
pattern.source_chapter,
|
||||
pattern.learned_at,
|
||||
pattern.usage_count,
|
||||
json.dumps(pattern.metadata)
|
||||
))
|
||||
|
||||
conn.commit()
|
||||
conn.close()
|
||||
|
||||
return True
|
||||
|
||||
def _save_to_system(self, pattern: LearnedPattern) -> bool:
|
||||
"""保存到系统共享库"""
|
||||
# 需要系统根目录
|
||||
system_root = self._resolve_system_root()
|
||||
learned_dir = system_root / "rag" / "learned"
|
||||
learned_dir.mkdir(parents=True, exist_ok=True)
|
||||
|
||||
pattern_file = learned_dir / f"{pattern.pattern_id}.json"
|
||||
|
||||
pattern_data = asdict(pattern)
|
||||
pattern_file.write_text(
|
||||
json.dumps(pattern_data, ensure_ascii=False, indent=2),
|
||||
encoding="utf-8"
|
||||
)
|
||||
|
||||
return True
|
||||
|
||||
def _resolve_system_root(self) -> Path:
|
||||
"""解析系统根目录"""
|
||||
# 与 project_root 同级的 .noma
|
||||
sibling = self.project_root.parent / ".noma"
|
||||
if sibling.exists():
|
||||
return sibling
|
||||
|
||||
return self.project_root / ".noma"
|
||||
|
||||
|
||||
# ==================== CLI 接口 ====================
|
||||
|
||||
def main():
|
||||
import argparse
|
||||
import sys
|
||||
|
||||
if sys.platform == "win32":
|
||||
enable_windows_utf8_stdio()
|
||||
|
||||
parser = argparse.ArgumentParser(
|
||||
description="Chapter Analyzer - 章节自动解构与模式提取"
|
||||
)
|
||||
parser.add_argument("--project-root", type=str, default=".",
|
||||
help="项目根目录")
|
||||
parser.add_argument("--chapter-file", type=str, required=True,
|
||||
help="章节文件路径")
|
||||
parser.add_argument("--chapter-num", type=int,
|
||||
help="章节号（可选，从文件名推断）")
|
||||
parser.add_argument("--learn", action="store_true",
|
||||
help="学习并存储模式")
|
||||
parser.add_argument("--learn-layer", choices=["project", "system"],
|
||||
default="project",
|
||||
help="学习成果存储层级")
|
||||
parser.add_argument("--output", type=str,
|
||||
help="输出文件（JSON格式）")
|
||||
|
||||
args = parser.parse_args()
|
||||
|
||||
project_root = Path(args.project_root).resolve()
|
||||
chapter_file = project_root / args.chapter_file
|
||||
|
||||
if not chapter_file.exists():
|
||||
print(f"Error: Chapter file not found: {chapter_file}")
|
||||
sys.exit(1)
|
||||
|
||||
# 分析章节
|
||||
analyzer = ChapterAnalyzer(project_root)
|
||||
result = analyzer.analyze_chapter(chapter_file, args.chapter_num)
|
||||
|
||||
# 输出结果
|
||||
if args.output:
|
||||
output_path = Path(args.output)
|
||||
output_path.parent.mkdir(parents=True, exist_ok=True)
|
||||
output_path.write_text(
|
||||
json.dumps(asdict(result), ensure_ascii=False, indent=2),
|
||||
encoding="utf-8"
|
||||
)
|
||||
print(f"Analysis saved to: {output_path}")
|
||||
else:
|
||||
# 打印摘要
|
||||
print(f"\n{'='*60}")
|
||||
print(f"章节分析报告: 第{result.chapter}章 - {result.title}")
|
||||
print(f"{'='*60}")
|
||||
print(f"\n基本信息:")
|
||||
print(f" 字数: {result.word_count}")
|
||||
print(f" 场景数: {result.scene_count}")
|
||||
print(f" 人物数: {result.character_count}")
|
||||
print(f" 人物列表: {', '.join(result.characters[:5]) or '无'}")
|
||||
|
||||
print(f"\n张力分析:")
|
||||
print(f" 平均张力: {result.tension_avg:.2f}")
|
||||
print(f" 峰值张力: {result.tension_peak:.2f} (位置: {result.tension_peak_position})")
|
||||
|
||||
print(f"\n爽点分析:")
|
||||
print(f" 爽点数量: {len(result.hot_spots)}")
|
||||
print(f" 主导模型: {result.catharsis_model}")
|
||||
if result.hot_spots:
|
||||
print(f" 主要爽点:")
|
||||
for hs in result.hot_spots[:3]:
|
||||
print(f" - [{hs.position}] {hs.description} ({hs.intensity:.2f})")
|
||||
|
||||
print(f"\n结构分析:")
|
||||
print(f" 铺垫: {result.structure.setup}字")
|
||||
print(f" 压抑: {result.structure.suppress}字")
|
||||
print(f" 释放: {result.structure.release}字")
|
||||
print(f" 反转: {result.structure.twist}字")
|
||||
|
||||
print(f"\n检测到的模式:")
|
||||
for p in result.detected_patterns:
|
||||
print(f" - {p}")
|
||||
|
||||
print(f"\n风格标签:")
|
||||
for t in result.style_tags:
|
||||
print(f" - {t}")
|
||||
|
||||
if result.suggestions:
|
||||
print(f"\n改进建议:")
|
||||
for s in result.suggestions:
|
||||
print(f" - {s}")
|
||||
|
||||
# 学习模式
|
||||
if args.learn:
|
||||
pattern = analyzer.learn_pattern(result, args.learn_layer)
|
||||
success = analyzer.save_learned_pattern(pattern, args.learn_layer)
|
||||
|
||||
if success:
|
||||
print(f"\n✓ 模式已学习并存储到 {args.learn_layer} 层")
|
||||
print(f" Pattern ID: {pattern.pattern_id}")
|
||||
else:
|
||||
print(f"\n✗ 模式存储失败")
|
||||
sys.exit(1)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
main()
|
||||
Reference in New Issue
Block a user