140 lines
5.8 KiB
Python
140 lines
5.8 KiB
Python
# -*- coding: utf-8 -*-
|
||
"""铁律组装与校验:tags / 前奏注入 / 密度闸门。"""
|
||
import re
|
||
|
||
from ..core.errors import RuleViolation
|
||
from ..lyrics import meter
|
||
from ..rules import ironlaw
|
||
from .common import chill_intro_bars, resolve_profile
|
||
|
||
|
||
def split_sections(lyrics_raw):
|
||
"""把裸歌词切成 [(tag, text)],识别不出标记时整段当 [verse]。"""
|
||
secs = []
|
||
cur_tag, buf = None, []
|
||
for ln in lyrics_raw.split("\n"):
|
||
s = ln.strip()
|
||
if s.startswith("[") and s.endswith("]"):
|
||
if cur_tag and buf:
|
||
secs.append((cur_tag, "\n".join(buf).strip()))
|
||
cur_tag, buf = s, []
|
||
elif s:
|
||
buf.append(s)
|
||
if cur_tag and buf:
|
||
secs.append((cur_tag, "\n".join(buf).strip()))
|
||
if not secs:
|
||
secs = [("[verse]", lyrics_raw.strip())]
|
||
return secs
|
||
|
||
|
||
def vocal_sections(lyrics_raw):
|
||
"""只取真正有人唱的段:丢掉所有只挂 [inst] 的纯器乐占位。
|
||
|
||
chill 重排时器乐占位要全部重新生成,先从原始歌词剥掉,
|
||
否则同一段器乐会被写两遍,第二遍反而把人声提前拉回来。
|
||
"""
|
||
out = []
|
||
for tag, text in split_sections(lyrics_raw):
|
||
t = text.strip()
|
||
if not t or re.fullmatch(r"\[?inst\]?|\[Instrumental[^\]]*\]", t, re.I):
|
||
continue
|
||
out.append((tag, text))
|
||
return out or [("[verse]", "")]
|
||
|
||
|
||
def duration_allowed(cfg, dur):
|
||
"""时长闸门:主区间 + 显式白名单区间。
|
||
|
||
主区间 150~200s 来自 35 首已验证实歌,不能为短时长题材放宽。
|
||
短视频/口水歌这类确实需要 100~130s,但没有实歌背书,
|
||
所以走 config.song.duration_extra_ranges 显式列出。
|
||
"""
|
||
lo, hi = cfg["song"]["duration_range"]
|
||
if lo <= dur <= hi:
|
||
return True
|
||
for a, b in cfg["song"].get("duration_extra_ranges") or []:
|
||
if a <= dur <= b:
|
||
return True
|
||
return False
|
||
|
||
|
||
def _extra_hint(cfg, dur):
|
||
"""报错时列出当前生效的额外区间,省一次查配置。"""
|
||
ex = cfg["song"].get("duration_extra_ranges") or []
|
||
if not ex:
|
||
return ""
|
||
return "(额外放行区间:%s)" % ", ".join("%d~%ds" % (a, b) for a, b in ex)
|
||
|
||
|
||
def assemble(args, cfg, st, lyrics_raw, title):
|
||
"""套用铁律:生成 tags、补器乐前奏、清洗中文标记。"""
|
||
chill = bool(getattr(args, "chill_vocal", False))
|
||
inst = bool(getattr(args, "instrumental", False))
|
||
lean = bool(getattr(args, "lean_tags", False))
|
||
tags = ironlaw.build_tags(
|
||
style=st.get("style", ""), instruments=st.get("instruments", ""),
|
||
mood=st.get("mood", ""), extra=st.get("extra", ""),
|
||
chill_vocal=chill, instrumental=inst, lean=lean)
|
||
ibars = chill_intro_bars(cfg, chill)
|
||
# 纯器乐:没有可唱正文,歌词体直接由结构标记铺出来,
|
||
# 密度闸门对纯器乐不适用(见 do_validate)。
|
||
if inst and not lyrics_raw.lstrip().lower().startswith("[intro]"):
|
||
lyrics = ironlaw.build_inst_lyrics(
|
||
st.get("intro_detail") or st.get("instruments"),
|
||
bars=ibars)
|
||
return tags, lyrics
|
||
if chill:
|
||
# chill 走独立结构体:器乐段整体排在人声段之前。
|
||
# 实测这只降低人声密度,并不推迟起点(chill 3 第一句仍在 0 秒),
|
||
# 标签侧的时间/时机约束同样无效。详见 ironlaw 顶部实测结论。
|
||
cfg_lyrics = meter.pick(cfg["lyrics"], resolve_profile(args))
|
||
cap = meter.capacity(st["duration"], st["bpm"], cfg_lyrics)
|
||
lyrics = ironlaw.build_chill_lyrics(
|
||
vocal_sections(lyrics_raw),
|
||
st.get("intro_detail") or st.get("instruments"),
|
||
bars=ibars, total_bars=cap["total_bars"])
|
||
return tags, lyrics
|
||
lyrics = lyrics_raw
|
||
if not lyrics.lstrip().lower().startswith("[intro]"):
|
||
lyrics = ironlaw.build_lyrics(
|
||
split_sections(lyrics_raw),
|
||
st.get("intro_detail") or st.get("instruments"),
|
||
bars=ibars)
|
||
else:
|
||
# 已有 [intro] 头的歌词文件:强制把前奏小节数对齐到标签写的值。
|
||
# 标签写 16 小节而歌词头写 8 小节时,check_rules 会判两处不一致
|
||
# ——这是故意留的闸门,不是 bug。
|
||
lyrics = ironlaw.force_intro_bars(lyrics, ibars)
|
||
# 前奏括号里的配器也要过 rhythm 过滤(2026-10-05 补)。
|
||
# 之前这条分支只改小节数,作者手写的 [Instrumental: ...] 直接
|
||
# 原样送进模型。ckfunk 批次的 8 首歌词前奏括号里就带着
|
||
# "half time feel" 这类非节奏组描述,而作者也可能写 pad、
|
||
# riser、sweep——intro_rhythm_only() 存在的全部理由就是把这些
|
||
# 空场信号从前奏里剔掉,只留节奏组。手写歌词不等于免检。
|
||
lyrics = ironlaw.filter_intro_bracket(lyrics)
|
||
lyrics = "\n".join(ironlaw.strip_cn_instrumental(lyrics.splitlines())) + "\n"
|
||
return tags, lyrics
|
||
|
||
|
||
def do_validate(lyrics, tags, cfg, st, lexicon, strict=True,
|
||
instrumental=False, profile=None, lean=False):
|
||
errs = []
|
||
errs += ironlaw.check_rules(lyrics, tags, lean=lean)
|
||
errs += ironlaw.check_lexicon(lyrics, lexicon)
|
||
cfg_lyrics = meter.pick(cfg["lyrics"], profile)
|
||
if instrumental:
|
||
# 纯器乐没有可唱正文,"歌词过少/过多/每句音节"三条全部不适用。
|
||
# 只保留结构与词典校验,密度统计仅作诊断记录。
|
||
derr = []
|
||
stats = meter.analyse(lyrics, st["duration"], st["bpm"], cfg_lyrics)
|
||
else:
|
||
derr, stats = meter.check(lyrics, st["duration"], st["bpm"], cfg_lyrics)
|
||
errs += derr
|
||
if strict and errs:
|
||
raise RuleViolation("校验未通过:\n - " + "\n - ".join(errs))
|
||
return errs, stats
|
||
|
||
|
||
# ---------------------------------------------------------------- commands
|
||
|