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
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581# coding=utf-8
"""
消息分批处理模块
提供消息内容分批拆分功能，确保消息大小不超过各平台限制
"""
from datetime import datetime
from typing import Dict, List, Optional, Callable
from trendradar.report.formatter import format_title_for_platform
# 默认批次大小配置
DEFAULT_BATCH_SIZES = {
"dingtalk": 20000,
"feishu": 29000,
"ntfy": 3800,
"default": 4000,
}
def split_content_into_batches(
report_data: Dict,
format_type: str,
update_info: Optional[Dict] = None,
max_bytes: Optional[int] = None,
mode: str = "daily",
batch_sizes: Optional[Dict[str, int]] = None,
feishu_separator: str = "---",
reverse_content_order: bool = False,
get_time_func: Optional[Callable[[], datetime]] = None,
) -> List[str]:
"""分批处理消息内容，确保词组标题+至少第一条新闻的完整性
Args:
report_data: 报告数据字典，包含 stats, new_titles, failed_ids, total_new_count
format_type: 格式类型 (feishu, dingtalk, wework, telegram, ntfy, bark, slack)
update_info: 版本更新信息（可选）
max_bytes: 最大字节数（可选，如果不指定则使用默认配置）
mode: 报告模式 (daily, incremental, current)
batch_sizes: 批次大小配置字典（可选）
feishu_separator: 飞书消息分隔符
reverse_content_order: 是否反转内容顺序（新增在前）
get_time_func: 获取当前时间的函数（可选）
Returns:
分批后的消息内容列表
"""
# 合并批次大小配置
sizes = {**DEFAULT_BATCH_SIZES, **(batch_sizes or {})}
if max_bytes is None:
if format_type == "dingtalk":
max_bytes = sizes.get("dingtalk", 20000)
elif format_type == "feishu":
max_bytes = sizes.get("feishu", 29000)
elif format_type == "ntfy":
max_bytes = sizes.get("ntfy", 3800)
else:
max_bytes = sizes.get("default", 4000)
batches = []
total_titles = sum(
len(stat["titles"]) for stat in report_data["stats"] if stat["count"] > 0
)
now = get_time_func() if get_time_func else datetime.now()
base_header = ""
if format_type in ("wework", "bark"):
base_header = f"**总新闻数：** {total_titles}\n\n\n\n"
elif format_type == "telegram":
base_header = f"总新闻数： {total_titles}\n\n"
elif format_type == "ntfy":
base_header = f"**总新闻数：** {total_titles}\n\n"
elif format_type == "feishu":
base_header = ""
elif format_type == "dingtalk":
base_header = f"**总新闻数：** {total_titles}\n\n"
base_header += f"**时间：** {now.strftime('%Y-%m-%d %H:%M:%S')}\n\n"
base_header += f"**类型：** 热点分析报告\n\n"
base_header += "---\n\n"
elif format_type == "slack":
base_header = f"*总新闻数：* {total_titles}\n\n"
base_footer = ""
if format_type in ("wework", "bark"):
base_footer = f"\n\n\n> 更新时间：{now.strftime('%Y-%m-%d %H:%M:%S')}"
if update_info:
base_footer += f"\n> TrendRadar 发现新版本 **{update_info['remote_version']}**，当前 **{update_info['current_version']}**"
elif format_type == "telegram":
base_footer = f"\n\n更新时间：{now.strftime('%Y-%m-%d %H:%M:%S')}"
if update_info:
base_footer += f"\nTrendRadar 发现新版本 {update_info['remote_version']}，当前 {update_info['current_version']}"
elif format_type == "ntfy":
base_footer = f"\n\n> 更新时间：{now.strftime('%Y-%m-%d %H:%M:%S')}"
if update_info:
base_footer += f"\n> TrendRadar 发现新版本 **{update_info['remote_version']}**，当前 **{update_info['current_version']}**"
elif format_type == "feishu":
base_footer = f"\n\n<font color='grey'>更新时间：{now.strftime('%Y-%m-%d %H:%M:%S')}</font>"
if update_info:
base_footer += f"\n<font color='grey'>TrendRadar 发现新版本 {update_info['remote_version']}，当前 {update_info['current_version']}</font>"
elif format_type == "dingtalk":
base_footer = f"\n\n> 更新时间：{now.strftime('%Y-%m-%d %H:%M:%S')}"
if update_info:
base_footer += f"\n> TrendRadar 发现新版本 **{update_info['remote_version']}**，当前 **{update_info['current_version']}**"
elif format_type == "slack":
base_footer = f"\n\n_更新时间：{now.strftime('%Y-%m-%d %H:%M:%S')}_"
if update_info:
base_footer += f"\n_TrendRadar 发现新版本 *{update_info['remote_version']}*，当前 *{update_info['current_version']}_"
stats_header = ""
if report_data["stats"]:
if format_type in ("wework", "bark"):
stats_header = f"📊 **热点词汇统计**\n\n"
elif format_type == "telegram":
stats_header = f"📊 热点词汇统计\n\n"
elif format_type == "ntfy":
stats_header = f"📊 **热点词汇统计**\n\n"
elif format_type == "feishu":
stats_header = f"📊 **热点词汇统计**\n\n"
elif format_type == "dingtalk":
stats_header = f"📊 **热点词汇统计**\n\n"
elif format_type == "slack":
stats_header = f"📊 *热点词汇统计*\n\n"
current_batch = base_header
current_batch_has_content = False
if (
not report_data["stats"]
and not report_data["new_titles"]
and not report_data["failed_ids"]
):
if mode == "incremental":
mode_text = "增量模式下暂无新增匹配的热点词汇"
elif mode == "current":
mode_text = "当前榜单模式下暂无匹配的热点词汇"
else:
mode_text = "暂无匹配的热点词汇"
simple_content = f"📭 {mode_text}\n\n"
final_content = base_header + simple_content + base_footer
batches.append(final_content)
return batches
# 定义处理热点词汇统计的函数
def process_stats_section(current_batch, current_batch_has_content, batches):
"""处理热点词汇统计"""
if not report_data["stats"]:
return current_batch, current_batch_has_content, batches
total_count = len(report_data["stats"])
# 添加统计标题
test_content = current_batch + stats_header
if (
len(test_content.encode("utf-8")) + len(base_footer.encode("utf-8"))
< max_bytes
):
current_batch = test_content
current_batch_has_content = True
else:
if current_batch_has_content:
batches.append(current_batch + base_footer)
current_batch = base_header + stats_header
current_batch_has_content = True
# 逐个处理词组（确保词组标题+第一条新闻的原子性）
for i, stat in enumerate(report_data["stats"]):
word = stat["word"]
count = stat["count"]
sequence_display = f"[{i + 1}/{total_count}]"
# 构建词组标题
word_header = ""
if format_type in ("wework", "bark"):
if count >= 10:
word_header = (
f"🔥 {sequence_display} **{word}** : **{count}** 条\n\n"
)
elif count >= 5:
word_header = (
f"📈 {sequence_display} **{word}** : **{count}** 条\n\n"
)
else:
word_header = f"📌 {sequence_display} **{word}** : {count} 条\n\n"
elif format_type == "telegram":
if count >= 10:
word_header = f"🔥 {sequence_display} {word} : {count} 条\n\n"
elif count >= 5:
word_header = f"📈 {sequence_display} {word} : {count} 条\n\n"
else:
word_header = f"📌 {sequence_display} {word} : {count} 条\n\n"
elif format_type == "ntfy":
if count >= 10:
word_header = (
f"🔥 {sequence_display} **{word}** : **{count}** 条\n\n"
)
elif count >= 5:
word_header = (
f"📈 {sequence_display} **{word}** : **{count}** 条\n\n"
)
else:
word_header = f"📌 {sequence_display} **{word}** : {count} 条\n\n"
elif format_type == "feishu":
if count >= 10:
word_header = f"🔥 <font color='grey'>{sequence_display}</font> **{word}** : <font color='red'>{count}</font> 条\n\n"
elif count >= 5:
word_header = f"📈 <font color='grey'>{sequence_display}</font> **{word}** : <font color='orange'>{count}</font> 条\n\n"
else:
word_header = f"📌 <font color='grey'>{sequence_display}</font> **{word}** : {count} 条\n\n"
elif format_type == "dingtalk":
if count >= 10:
word_header = (
f"🔥 {sequence_display} **{word}** : **{count}** 条\n\n"
)
elif count >= 5:
word_header = (
f"📈 {sequence_display} **{word}** : **{count}** 条\n\n"
)
else:
word_header = f"📌 {sequence_display} **{word}** : {count} 条\n\n"
elif format_type == "slack":
if count >= 10:
word_header = (
f"🔥 {sequence_display} *{word}* : *{count}* 条\n\n"
)
elif count >= 5:
word_header = (
f"📈 {sequence_display} *{word}* : *{count}* 条\n\n"
)
else:
word_header = f"📌 {sequence_display} *{word}* : {count} 条\n\n"
# 构建第一条新闻
first_news_line = ""
if stat["titles"]:
first_title_data = stat["titles"][0]
if format_type in ("wework", "bark"):
formatted_title = format_title_for_platform(
"wework", first_title_data, show_source=True
)
elif format_type == "telegram":
formatted_title = format_title_for_platform(
"telegram", first_title_data, show_source=True
)
elif format_type == "ntfy":
formatted_title = format_title_for_platform(
"ntfy", first_title_data, show_source=True
)
elif format_type == "feishu":
formatted_title = format_title_for_platform(
"feishu", first_title_data, show_source=True
)
elif format_type == "dingtalk":
formatted_title = format_title_for_platform(
"dingtalk", first_title_data, show_source=True
)
elif format_type == "slack":
formatted_title = format_title_for_platform(
"slack", first_title_data, show_source=True
)
else:
formatted_title = f"{first_title_data['title']}"
first_news_line = f" 1. {formatted_title}\n"
if len(stat["titles"]) > 1:
first_news_line += "\n"
# 原子性检查：词组标题+第一条新闻必须一起处理
word_with_first_news = word_header + first_news_line
test_content = current_batch + word_with_first_news
if (
len(test_content.encode("utf-8")) + len(base_footer.encode("utf-8"))
>= max_bytes
):
# 当前批次容纳不下，开启新批次
if current_batch_has_content:
batches.append(current_batch + base_footer)
current_batch = base_header + stats_header + word_with_first_news
current_batch_has_content = True
start_index = 1
else:
current_batch = test_content
current_batch_has_content = True
start_index = 1
# 处理剩余新闻条目
for j in range(start_index, len(stat["titles"])):
title_data = stat["titles"][j]
if format_type in ("wework", "bark"):
formatted_title = format_title_for_platform(
"wework", title_data, show_source=True
)
elif format_type == "telegram":
formatted_title = format_title_for_platform(
"telegram", title_data, show_source=True
)
elif format_type == "ntfy":
formatted_title = format_title_for_platform(
"ntfy", title_data, show_source=True
)
elif format_type == "feishu":
formatted_title = format_title_for_platform(
"feishu", title_data, show_source=True
)
elif format_type == "dingtalk":
formatted_title = format_title_for_platform(
"dingtalk", title_data, show_source=True
)
elif format_type == "slack":
formatted_title = format_title_for_platform(
"slack", title_data, show_source=True
)
else:
formatted_title = f"{title_data['title']}"
news_line = f" {j + 1}. {formatted_title}\n"
if j < len(stat["titles"]) - 1:
news_line += "\n"
test_content = current_batch + news_line
if (
len(test_content.encode("utf-8")) + len(base_footer.encode("utf-8"))
>= max_bytes
):
if current_batch_has_content:
batches.append(current_batch + base_footer)
current_batch = base_header + stats_header + word_header + news_line
current_batch_has_content = True
else:
current_batch = test_content
current_batch_has_content = True
# 词组间分隔符
if i < len(report_data["stats"]) - 1:
separator = ""
if format_type in ("wework", "bark"):
separator = f"\n\n\n\n"
elif format_type == "telegram":
separator = f"\n\n"
elif format_type == "ntfy":
separator = f"\n\n"
elif format_type == "feishu":
separator = f"\n{feishu_separator}\n\n"
elif format_type == "dingtalk":
separator = f"\n---\n\n"
elif format_type == "slack":
separator = f"\n\n"
test_content = current_batch + separator
if (
len(test_content.encode("utf-8")) + len(base_footer.encode("utf-8"))
< max_bytes
):
current_batch = test_content
return current_batch, current_batch_has_content, batches
# 定义处理新增新闻的函数
def process_new_titles_section(current_batch, current_batch_has_content, batches):
"""处理新增新闻"""
if not report_data["new_titles"]:
return current_batch, current_batch_has_content, batches
new_header = ""
if format_type in ("wework", "bark"):
new_header = f"\n\n\n\n🆕 **本次新增热点新闻** (共 {report_data['total_new_count']} 条)\n\n"
elif format_type == "telegram":
new_header = (
f"\n\n🆕 本次新增热点新闻 (共 {report_data['total_new_count']} 条)\n\n"
)
elif format_type == "ntfy":
new_header = f"\n\n🆕 **本次新增热点新闻** (共 {report_data['total_new_count']} 条)\n\n"
elif format_type == "feishu":
new_header = f"\n{feishu_separator}\n\n🆕 **本次新增热点新闻** (共 {report_data['total_new_count']} 条)\n\n"
elif format_type == "dingtalk":
new_header = f"\n---\n\n🆕 **本次新增热点新闻** (共 {report_data['total_new_count']} 条)\n\n"
elif format_type == "slack":
new_header = f"\n\n🆕 *本次新增热点新闻* (共 {report_data['total_new_count']} 条)\n\n"
test_content = current_batch + new_header
if (
len(test_content.encode("utf-8")) + len(base_footer.encode("utf-8"))
>= max_bytes
):
if current_batch_has_content:
batches.append(current_batch + base_footer)
current_batch = base_header + new_header
current_batch_has_content = True
else:
current_batch = test_content
current_batch_has_content = True
# 逐个处理新增新闻来源
for source_data in report_data["new_titles"]:
source_header = ""
if format_type in ("wework", "bark"):
source_header = f"**{source_data['source_name']}** ({len(source_data['titles'])} 条):\n\n"
elif format_type == "telegram":
source_header = f"{source_data['source_name']} ({len(source_data['titles'])} 条):\n\n"
elif format_type == "ntfy":
source_header = f"**{source_data['source_name']}** ({len(source_data['titles'])} 条):\n\n"
elif format_type == "feishu":
source_header = f"**{source_data['source_name']}** ({len(source_data['titles'])} 条):\n\n"
elif format_type == "dingtalk":
source_header = f"**{source_data['source_name']}** ({len(source_data['titles'])} 条):\n\n"
elif format_type == "slack":
source_header = f"*{source_data['source_name']}* ({len(source_data['titles'])} 条):\n\n"
# 构建第一条新增新闻
first_news_line = ""
if source_data["titles"]:
first_title_data = source_data["titles"][0]
title_data_copy = first_title_data.copy()
title_data_copy["is_new"] = False
if format_type in ("wework", "bark"):
formatted_title = format_title_for_platform(
"wework", title_data_copy, show_source=False
)
elif format_type == "telegram":
formatted_title = format_title_for_platform(
"telegram", title_data_copy, show_source=False
)
elif format_type == "feishu":
formatted_title = format_title_for_platform(
"feishu", title_data_copy, show_source=False
)
elif format_type == "dingtalk":
formatted_title = format_title_for_platform(
"dingtalk", title_data_copy, show_source=False
)
elif format_type == "slack":
formatted_title = format_title_for_platform(
"slack", title_data_copy, show_source=False
)
else:
formatted_title = f"{title_data_copy['title']}"
first_news_line = f" 1. {formatted_title}\n"
# 原子性检查：来源标题+第一条新闻
source_with_first_news = source_header + first_news_line
test_content = current_batch + source_with_first_news
if (
len(test_content.encode("utf-8")) + len(base_footer.encode("utf-8"))
>= max_bytes
):
if current_batch_has_content:
batches.append(current_batch + base_footer)
current_batch = base_header + new_header + source_with_first_news
current_batch_has_content = True
start_index = 1
else:
current_batch = test_content
current_batch_has_content = True
start_index = 1
# 处理剩余新增新闻
for j in range(start_index, len(source_data["titles"])):
title_data = source_data["titles"][j]
title_data_copy = title_data.copy()
title_data_copy["is_new"] = False
if format_type == "wework":
formatted_title = format_title_for_platform(
"wework", title_data_copy, show_source=False
)
elif format_type == "telegram":
formatted_title = format_title_for_platform(
"telegram", title_data_copy, show_source=False
)
elif format_type == "feishu":
formatted_title = format_title_for_platform(
"feishu", title_data_copy, show_source=False
)
elif format_type == "dingtalk":
formatted_title = format_title_for_platform(
"dingtalk", title_data_copy, show_source=False
)
elif format_type == "slack":
formatted_title = format_title_for_platform(
"slack", title_data_copy, show_source=False
)
else:
formatted_title = f"{title_data_copy['title']}"
news_line = f" {j + 1}. {formatted_title}\n"
test_content = current_batch + news_line
if (
len(test_content.encode("utf-8")) + len(base_footer.encode("utf-8"))
>= max_bytes
):
if current_batch_has_content:
batches.append(current_batch + base_footer)
current_batch = base_header + new_header + source_header + news_line
current_batch_has_content = True
else:
current_batch = test_content
current_batch_has_content = True
current_batch += "\n"
return current_batch, current_batch_has_content, batches
# 根据配置决定处理顺序
if reverse_content_order:
# 新增热点在前，热点词汇统计在后
current_batch, current_batch_has_content, batches = process_new_titles_section(
current_batch, current_batch_has_content, batches
)
current_batch, current_batch_has_content, batches = process_stats_section(
current_batch, current_batch_has_content, batches
)
else:
# 默认：热点词汇统计在前，新增热点在后
current_batch, current_batch_has_content, batches = process_stats_section(
current_batch, current_batch_has_content, batches
)
current_batch, current_batch_has_content, batches = process_new_titles_section(
current_batch, current_batch_has_content, batches
)
if report_data["failed_ids"]:
failed_header = ""
if format_type == "wework":
failed_header = f"\n\n\n\n⚠️ **数据获取失败的平台：**\n\n"
elif format_type == "telegram":
failed_header = f"\n\n⚠️ 数据获取失败的平台：\n\n"
elif format_type == "ntfy":
failed_header = f"\n\n⚠️ **数据获取失败的平台：**\n\n"
elif format_type == "feishu":
failed_header = f"\n{feishu_separator}\n\n⚠️ **数据获取失败的平台：**\n\n"
elif format_type == "dingtalk":
failed_header = f"\n---\n\n⚠️ **数据获取失败的平台：**\n\n"
test_content = current_batch + failed_header
if (
len(test_content.encode("utf-8")) + len(base_footer.encode("utf-8"))
>= max_bytes
):
if current_batch_has_content:
batches.append(current_batch + base_footer)
current_batch = base_header + failed_header
current_batch_has_content = True
else:
current_batch = test_content
current_batch_has_content = True
for i, id_value in enumerate(report_data["failed_ids"], 1):
if format_type == "feishu":
failed_line = f" • <font color='red'>{id_value}</font>\n"
elif format_type == "dingtalk":
failed_line = f" • **{id_value}**\n"
else:
failed_line = f" • {id_value}\n"
test_content = current_batch + failed_line
if (
len(test_content.encode("utf-8")) + len(base_footer.encode("utf-8"))
>= max_bytes
):
if current_batch_has_content:
batches.append(current_batch + base_footer)
current_batch = base_header + failed_header + failed_line
current_batch_has_content = True
else:
current_batch = test_content
current_batch_has_content = True
# 完成最后批次
if current_batch_has_content:
batches.append(current_batch + base_footer)
return batches