File size: 11,504 Bytes
e63569d e8412e3 e63569d 8c50d16 e63569d e8412e3 e63569d e8412e3 e63569d f712f4b e63569d adf92db e8412e3 e63569d e8412e3 e63569d e8412e3 e63569d e8412e3 e63569d e8412e3 e63569d 8c50d16 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 | """Build a small fine-tuning set focused on repaired filename structures."""
from __future__ import annotations
import argparse
import json
import random
import re
from pathlib import Path
from typing import Iterable, List
from anifilebert.label_repairs import repair_jsonl_item
SPECIAL_FOCUS_RE = re.compile(
r"(?<![A-Za-z0-9])(?:NCOP|NCED|OP|ED|PV|CM|IV)\s*[_\-.]?\s*\d{0,4}"
r"(?:[_\-.]?\s*(?:EP?|#)?\d{1,4})?(?![A-Za-z0-9])",
re.I,
)
def parse_args() -> argparse.Namespace:
parser = argparse.ArgumentParser(description="Build repair-focused char JSONL fine-tune data")
parser.add_argument("--input", required=True, help="Repaired char JSONL dataset")
parser.add_argument("--output", required=True, help="Output focus JSONL")
parser.add_argument("--context-samples", type=int, default=50000,
help="Random non-repaired rows to include for stability")
parser.add_argument("--repeat-repaired", type=int, default=4,
help="Repeat rows that still trigger a repair pass")
parser.add_argument("--repeat-focus", type=int, default=3,
help="Repeat rows matching special-code focus patterns")
parser.add_argument("--max-focus-rows", type=int, default=80000,
help="Maximum dataset rows matching special-code focus patterns")
parser.add_argument("--repeat-manual", type=int, default=24,
help="Repeat hand-labeled hard cases")
parser.add_argument("--seed", type=int, default=42)
return parser.parse_args()
def char_item(filename: str, spans: List[tuple[str, str]]) -> dict:
tokens = list(filename)
labels = ["O"] * len(tokens)
cursor = 0
for text, entity in spans:
start = filename.find(text, cursor)
if start < 0:
start = filename.find(text)
if start < 0:
raise ValueError(f"Could not find span {text!r} in {filename!r}")
end = start + len(text)
labels[start] = f"B-{entity}"
for idx in range(start + 1, end):
labels[idx] = f"I-{entity}"
cursor = end
return {
"filename": filename,
"tokens": tokens,
"labels": labels,
"tokenizer_variant": "char",
"source": "manual_repair_focus",
}
def manual_cases() -> Iterable[dict]:
yield char_item(
"One.Piece.1110.1080p.WEB-DL.AAC2.0.H.264",
[
("One.Piece", "TITLE"),
("1110", "EPISODE"),
("1080p", "RESOLUTION"),
("WEB-DL", "SOURCE"),
],
)
yield char_item(
"One.Piece.1111.1080p.WEB-DL.AAC2.0.H.264",
[
("One.Piece", "TITLE"),
("1111", "EPISODE"),
("1080p", "RESOLUTION"),
("WEB-DL", "SOURCE"),
],
)
yield char_item(
"【喵萌奶茶屋】★04月新番★[葬送的芙莉莲][01][1080P][HEVC]",
[
("喵萌奶茶屋", "GROUP"),
("葬送的芙莉莲", "TITLE"),
("01", "EPISODE"),
("1080P", "RESOLUTION"),
("HEVC", "SOURCE"),
],
)
yield char_item(
"【喵萌奶茶屋】★10月新番★[药屋少女的呢喃][02][1080P][HEVC]",
[
("喵萌奶茶屋", "GROUP"),
("药屋少女的呢喃", "TITLE"),
("02", "EPISODE"),
("1080P", "RESOLUTION"),
("HEVC", "SOURCE"),
],
)
yield char_item(
"[Billion Meta Lab] 魔法姊妹露露莉莉 Mahou no Shimai Rurutto Riryi [07][1080P][CHT&JPN][檢索：魔法姊妹露露特莉莉].mp4",
[
("Billion Meta Lab", "GROUP"),
("魔法姊妹露露莉莉 Mahou no Shimai Rurutto Riryi", "TITLE"),
("07", "EPISODE"),
("1080P", "RESOLUTION"),
("CHT&JPN", "SOURCE"),
("檢索：魔法姊妹露露特莉莉", "SPECIAL"),
],
)
yield char_item(
"[Billion Meta Lab] 魔法姊妹露露莉莉 Mahou no Shimai Rurutto Riryi [08][1080P][CHT&JPN][检索：魔法姊妹露露特莉莉].mp4",
[
("Billion Meta Lab", "GROUP"),
("魔法姊妹露露莉莉 Mahou no Shimai Rurutto Riryi", "TITLE"),
("08", "EPISODE"),
("1080P", "RESOLUTION"),
("CHT&JPN", "SOURCE"),
("检索：魔法姊妹露露特莉莉", "SPECIAL"),
],
)
yield char_item(
"[LoliHouse] Kakuriyo no Yadomeshi Ni - 12 [WebRip 1080p HEVC-10bit AAC SRTx2].mkv",
[
("LoliHouse", "GROUP"),
("Kakuriyo no Yadomeshi", "TITLE"),
("Ni", "SEASON"),
("12", "EPISODE"),
("WebRip", "SOURCE"),
("1080p", "RESOLUTION"),
("HEVC", "SOURCE"),
("AAC", "SOURCE"),
("SRTx2", "SOURCE"),
],
)
yield char_item(
"[LoliHouse] Kakuriyo no Yadomeshi Ni - 13 [WebRip 1080p HEVC-10bit AAC SRTx2].mkv",
[
("LoliHouse", "GROUP"),
("Kakuriyo no Yadomeshi", "TITLE"),
("Ni", "SEASON"),
("13", "EPISODE"),
("WebRip", "SOURCE"),
("1080p", "RESOLUTION"),
("HEVC", "SOURCE"),
("AAC", "SOURCE"),
("SRTx2", "SOURCE"),
],
)
yield char_item(
"[AI-Raws] 炎炎の消防隊 弐ノ章 #13 (BD HEVC 1920x1080 yuv444p10le FLAC)[FC74A2D5].mkv",
[
("AI-Raws", "GROUP"),
("炎炎の消防隊", "TITLE"),
("弐ノ章", "SEASON"),
("13", "EPISODE"),
("BD", "SOURCE"),
("HEVC", "SOURCE"),
("1920x1080", "RESOLUTION"),
("FLAC", "SOURCE"),
],
)
yield char_item(
"[AI-Raws] 炎炎の消防隊 弐ノ章 #01 (BD HEVC 1920x1080 FLAC).mkv",
[
("AI-Raws", "GROUP"),
("炎炎の消防隊", "TITLE"),
("弐ノ章", "SEASON"),
("01", "EPISODE"),
("BD", "SOURCE"),
("HEVC", "SOURCE"),
("1920x1080", "RESOLUTION"),
("FLAC", "SOURCE"),
],
)
yield char_item(
"[DBD-Raws][炎炎消防队 貳之章][01][1080P][BDRip][HEVC-10bit][FLAC]",
[
("DBD-Raws", "GROUP"),
("炎炎消防队", "TITLE"),
("貳之章", "SEASON"),
("01", "EPISODE"),
("1080P", "RESOLUTION"),
("BDRip", "SOURCE"),
("FLAC", "SOURCE"),
],
)
yield char_item(
"[GM-Team][国漫][逆天邪神 第2季][Against the Gods Ⅱ][2026][04][HEVC][GB][4K].mp4",
[
("GM-Team", "GROUP"),
("逆天邪神", "TITLE"),
("第2季", "SEASON"),
("04", "EPISODE"),
("HEVC", "SOURCE"),
("GB", "SOURCE"),
("4K", "RESOLUTION"),
],
)
yield char_item(
"[GM-Team][国漫][剑来 第2季][Sword of Coming Ⅱ][2025][04][HEVC][GB][4K]",
[
("GM-Team", "GROUP"),
("剑来", "TITLE"),
("第2季", "SEASON"),
("04", "EPISODE"),
("HEVC", "SOURCE"),
("GB", "SOURCE"),
("4K", "RESOLUTION"),
],
)
yield char_item(
"[GM-Team][国漫][大主宰 第2季][The Great Ruler Ⅱ][2026][04][HEVC][GB][4K]",
[
("GM-Team", "GROUP"),
("大主宰", "TITLE"),
("第2季", "SEASON"),
("04", "EPISODE"),
("HEVC", "SOURCE"),
("GB", "SOURCE"),
("4K", "RESOLUTION"),
],
)
yield char_item(
"[YYDM&VCB-Studio] Shinsekai Yori [IV05][Ma10p_1080p][x265_aac].mkv",
[
("YYDM&VCB-Studio", "GROUP"),
("Shinsekai Yori", "TITLE"),
("IV05", "SPECIAL"),
("1080p", "RESOLUTION"),
("x265_aac", "SOURCE"),
],
)
yield char_item(
"[YYDM&VCB-Studio] Shinsekai Yori [NCED02][Ma10p_1080p][x265_flac].mkv",
[
("YYDM&VCB-Studio", "GROUP"),
("Shinsekai Yori", "TITLE"),
("NCED02", "SPECIAL"),
("1080p", "RESOLUTION"),
("x265_flac", "SOURCE"),
],
)
yield char_item(
"InuYasha.2000.NCED02.BDrip.AV1.10Bit.DTS.1080p-CalChi",
[
("InuYasha", "TITLE"),
("NCED02", "SPECIAL"),
("BDrip", "SOURCE"),
("AV1", "SOURCE"),
("DTS", "SOURCE"),
("1080p", "RESOLUTION"),
],
)
yield char_item(
"[VCB-Studio] Yamada-kun to 7-nin no Majo [NCED][Ma10p_1080p][x265_flac]",
[
("VCB-Studio", "GROUP"),
("Yamada-kun to 7-nin no Majo", "TITLE"),
("NCED", "SPECIAL"),
("1080p", "RESOLUTION"),
("x265_flac", "SOURCE"),
],
)
def main() -> None:
args = parse_args()
rng = random.Random(args.seed)
input_path = Path(args.input)
output_path = Path(args.output)
repaired_rows: List[dict] = []
focus_rows: List[dict] = []
reservoir: List[dict] = []
seen_filenames = set()
total_rows = 0
with input_path.open("r", encoding="utf-8") as handle:
for line in handle:
if not line.strip():
continue
total_rows += 1
item = json.loads(line)
_repaired_item, repairs = repair_jsonl_item(item)
filename = item.get("filename")
if repairs:
repaired_rows.append(item)
if filename:
seen_filenames.add(filename)
continue
if filename and SPECIAL_FOCUS_RE.search(filename):
if len(focus_rows) < args.max_focus_rows:
focus_rows.append(item)
seen_filenames.add(filename)
else:
index = rng.randrange(total_rows)
if index < args.max_focus_rows:
focus_rows[index] = item
continue
if filename in seen_filenames:
continue
if len(reservoir) < args.context_samples:
reservoir.append(item)
else:
index = rng.randrange(total_rows)
if index < args.context_samples:
reservoir[index] = item
rows: List[dict] = []
for item in repaired_rows:
rows.extend([item] * max(1, args.repeat_repaired))
for item in focus_rows:
rows.extend([item] * max(1, args.repeat_focus))
rows.extend(reservoir)
for item in manual_cases():
rows.extend([item] * max(1, args.repeat_manual))
rng.shuffle(rows)
output_path.parent.mkdir(parents=True, exist_ok=True)
with output_path.open("w", encoding="utf-8") as handle:
for item in rows:
handle.write(json.dumps(item, ensure_ascii=False, separators=(",", ":")) + "\n")
print(json.dumps({
"input": str(input_path),
"output": str(output_path),
"total_rows": total_rows,
"repaired_rows": len(repaired_rows),
"focus_rows": len(focus_rows),
"context_rows": len(reservoir),
"manual_rows": len(list(manual_cases())),
"written_rows": len(rows),
}, ensure_ascii=False, indent=2))
if __name__ == "__main__":
main()
|