parse-docs.js
27 KB
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
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
/**
* 文档解析脚本
*
* @description 扫描 docs/to-parse 文件夹中的文档,调用 AI 服务解析,自动更新配置
* @module scripts/parse-docs
* @author Claude Code
* @created 2026-02-13
*
* @usage
* # 解析所有待处理文档
* npm run parse:docs
*
* # 解析指定文档
* npm run parse:docs -- --file=产品说明书.pdf
*
* # 查看待处理文档
* npm run parse:docs -- --list
*/
import crypto from 'crypto'
import fs from 'fs'
import path from 'path'
import { PDFParse } from 'pdf-parse'
import mammoth from 'mammoth'
import Ajv from 'ajv'
// ========== 配置区 ==========
const DOCS_DIR = path.resolve(process.cwd(), 'docs/to-parse')
const CONFIG_FILE = path.resolve(process.cwd(), 'src/config/plan-templates.js')
const BACKUP_DIR = path.resolve(process.cwd(), 'docs/parsed-backup')
// 支持的文档格式
const SUPPORTED_EXTENSIONS = ['.pdf', '.doc', '.docx', '.txt', '.md']
// AI 解析服务选择(通过 skill 调用)
const AI_SERVICE = 'openai' // 'openai' | 'anthropic' | 'openrouter'
const ajv = new Ajv({ allErrors: true, strict: false })
const parseConfigSchema = {
type: 'object',
required: ['product_name', 'product_type', 'currency', 'form_schema', 'submit_mapping'],
properties: {
product_name: { type: 'string', minLength: 1 },
product_type: { type: 'string', enum: ['savings', 'life-insurance', 'critical-illness'] },
currency: { type: 'string', minLength: 1 },
form_schema: { type: 'object' },
submit_mapping: { type: 'object' }
},
additionalProperties: true
}
const validateParsedConfigSchema = ajv.compile(parseConfigSchema)
// ========== 工具函数 ==========
/**
* 确保目录存在
*/
function ensureDir(dirPath) {
if (!fs.existsSync(dirPath)) {
fs.mkdirSync(dirPath, { recursive: true })
console.log(`📁 创建目录: ${dirPath}`)
}
}
/**
* 读取文件内容
*/
function readFile(filePath) {
return fs.readFileSync(filePath, 'utf-8')
}
function getFileMeta(filePath, extraMeta = {}) {
const stats = fs.existsSync(filePath) ? fs.statSync(filePath) : { size: 0 }
return {
file_name: path.basename(filePath),
ext: path.extname(filePath).toLowerCase(),
size: stats.size,
ocr: {
enabled: false,
provider: null,
reason: 'not_configured'
},
...extraMeta
}
}
function buildExtractResult(filePath, text, warnings = [], extraMeta = {}) {
return {
text,
warnings,
meta: getFileMeta(filePath, extraMeta)
}
}
async function extractTextFromPdf(filePath) {
const buffer = fs.readFileSync(filePath)
const parser = new PDFParse({ data: buffer })
let result
try {
result = await parser.getText()
} finally {
await parser.destroy()
}
return buildExtractResult(filePath, result?.text || '', [], {
total_pages: result?.total || 0
})
}
async function extractTextFromDocx(filePath) {
const buffer = fs.readFileSync(filePath)
const result = await mammoth.extractRawText({ buffer })
const warnings = (result.messages || []).map(item => `${item.type || 'warning'}:${item.message}`)
return buildExtractResult(filePath, result.value || '', warnings)
}
function extractTextFromDoc(filePath) {
return buildExtractResult(filePath, '', ['暂不支持 .doc,请转换为 .docx'])
}
function extractTextFromPlainFile(filePath) {
return buildExtractResult(filePath, readFile(filePath), [])
}
export async function extractDocumentText(filePath) {
const ext = path.extname(filePath).toLowerCase()
let result
if (ext === '.pdf') {
result = await extractTextFromPdf(filePath)
} else if (ext === '.docx') {
result = await extractTextFromDocx(filePath)
} else if (ext === '.doc') {
result = extractTextFromDoc(filePath)
} else if (ext === '.txt' || ext === '.md') {
result = extractTextFromPlainFile(filePath)
} else {
result = buildExtractResult(filePath, '', [`不支持的文件类型: ${ext}`])
}
if (!result.text || !result.text.trim()) {
result.warnings.push('抽取文本为空,可能是扫描件')
result.meta.ocr = {
enabled: false,
provider: null,
reason: 'text_empty'
}
}
return result
}
export function validateParsedConfig(config) {
const valid = validateParsedConfigSchema(config)
if (valid) {
return { valid: true, errors: [] }
}
const errors = (validateParsedConfigSchema.errors || []).map(error => {
if (error.keyword === 'required' && error.params?.missingProperty) {
return `${error.instancePath || '/'} 缺少字段 ${error.params.missingProperty}`
}
if (error.message) {
return `${error.instancePath || '/'} ${error.message}`.trim()
}
return `${error.instancePath || '/'} 校验失败`
})
return { valid: false, errors }
}
/**
* 写入文件内容
*/
function writeFile(filePath, content) {
fs.writeFileSync(filePath, content, 'utf-8')
}
/**
* 获取所有待处理的文档
*/
function getDocsToParse() {
if (!fs.existsSync(DOCS_DIR)) {
console.log('📂 文档夹不存在:', DOCS_DIR)
return []
}
const files = fs.readdirSync(DOCS_DIR)
return files
.filter(file => SUPPORTED_EXTENSIONS.includes(path.extname(file).toLowerCase()))
.map(file => ({
name: file,
fullPath: path.join(DOCS_DIR, file),
ext: path.extname(file).toLowerCase(),
size: fs.statSync(path.join(DOCS_DIR, file)).size
}))
}
/**
* 生成 form_sn
*/
export function generateFormSn(config) {
if (config?.form_sn) {
return config.form_sn
}
const product_type = config?.product_type || 'product'
const raw_name = (config?.product_name || '').trim()
const name_slug = raw_name
.toLowerCase()
.replace(/[^a-z0-9]+/g, '-')
.replace(/^-+|-+$/g, '')
const base_value = `${product_type}|${name_slug || 'product'}|${raw_name}`
const hash = crypto.createHash('sha1').update(base_value).digest('hex').slice(0, 8)
return `${product_type}-${name_slug || 'product'}-${hash}`
}
/**
* 生成配置代码
*/
export function generateConfigCode(config) {
const formSn = generateFormSn(config)
const isSavings = config.is_savings || config.product_type === 'savings'
const productType = config.product_type || 'life-insurance'
const componentName = isSavings
? 'SavingsTemplate'
: (productType === 'critical-illness' ? 'CriticalIllnessTemplate' : 'LifeInsuranceTemplate')
let code = " /**\n"
code += " * " + config.product_name + "\n"
code += " * @added " + new Date().toISOString() + "\n"
code += " * @source docs/to-parse/" + config.source_file + "\n"
code += " */\n"
code += " '" + formSn + "': {\n"
code += " name: '" + config.product_name + "',\n"
code += " component: '" + componentName + "',\n"
if (isSavings) {
code += " category: 'savings',\n"
}
code += " config: {\n"
if (isSavings) {
code += " currency: '" + config.currency + "',\n"
code += " payment_periods: " + JSON.stringify(config.payment_periods || []) + ",\n"
code += " age_range: { min: " + (config.age_range?.min || 0) + ", max: " + (config.age_range?.max || 75) + " },\n"
code += " insurance_period: '" + (config.insurance_period || '终身') + "',\n"
code += " withdrawal_plan: {\n"
code += " enabled: true,\n"
code += " currencies: ['HKD', 'USD', 'CNY'],\n"
code += " default_currency: '" + config.currency + "',\n"
code += " withdrawal_modes: " + JSON.stringify(config.withdrawal_modes || []) + ",\n"
code += " withdrawal_periods: " + JSON.stringify(config.withdrawal_periods || []) + "\n"
code += " },\n"
if (config.form_schema) {
const form_schema_code = JSON.stringify(config.form_schema, null, 2).replace(/\n/g, '\n ')
code += " form_schema: " + form_schema_code + ",\n"
}
if (config.submit_mapping) {
const submit_mapping_code = JSON.stringify(config.submit_mapping, null, 2).replace(/\n/g, '\n ')
code += " submit_mapping: " + submit_mapping_code + "\n"
}
} else {
code += " currency: '" + config.currency + "',\n"
code += " payment_periods: " + JSON.stringify(config.payment_periods || []) + ",\n"
code += " age_range: { min: " + (config.age_range?.min || 0) + ", max: " + (config.age_range?.max || 75) + " },\n"
code += " insurance_period: '" + (config.insurance_period || '终身') + "',\n"
if (config.form_schema) {
const form_schema_code = JSON.stringify(config.form_schema, null, 2).replace(/\n/g, '\n ')
code += " form_schema: " + form_schema_code + ",\n"
}
if (config.submit_mapping) {
const submit_mapping_code = JSON.stringify(config.submit_mapping, null, 2).replace(/\n/g, '\n ')
code += " submit_mapping: " + submit_mapping_code + "\n"
}
}
code += " }\n"
code += " }\n\n"
return { formSn, code }
}
function formatSize(size) {
if (size < 1024) return `${size} B`
if (size < 1024 * 1024) return `${(size / 1024).toFixed(1)} KB`
if (size < 1024 * 1024 * 1024) return `${(size / (1024 * 1024)).toFixed(1)} MB`
return `${(size / (1024 * 1024 * 1024)).toFixed(1)} GB`
}
/**
* 调用 AI 服务解析文档
*
* 这里使用 skill 工具调用实际的 AI 解析服务
* 可以是:file-url-to-pdf + openai/anthropic skill
*/
async function parseDocumentWithAI(docPath) {
console.log(`\n🤖 正在解析: ${path.basename(docPath)}`)
try {
const extract_result = await extractDocumentText(docPath)
if (extract_result.warnings.length > 0) {
extract_result.warnings.forEach(message => {
console.log(`⚠️ 抽取警告: ${message}`)
})
}
if (!extract_result.text || !extract_result.text.trim()) {
console.error(`❌ 文本抽取失败 (${docPath})`)
return null
}
const content = extract_result.text
// 模拟解析:从文档内容中提取配置
// 实际使用时可以调用 AI 服务
const mockConfig = {
product_name: path.basename(docPath, path.extname(docPath)),
product_type: 'savings',
currency: 'USD',
payment_periods: ['整付', '3年', '5年'],
age_range: { min: 0, max: 75 },
insurance_period: '终身',
is_savings: true,
withdrawal_modes: ['年龄指定金额', '最高固定金额'],
withdrawal_periods: ['1年', '3年', '5年', '10年'],
form_schema: { base_fields: [], withdrawal_fields: [], reset_map: {} },
submit_mapping: {}
}
console.log('✅ 解析成功')
return mockConfig
} catch (error) {
console.error(`❌ 解析失败 (${docPath}):`, error.message)
return null
}
}
/**
* 解析单个文档
*/
async function parseSingleFile(filePath) {
const fileName = path.basename(filePath)
console.log("\n" + "=".repeat(60))
console.log("📄 处理文件: " + fileName)
console.log("=".repeat(60))
// 解析文档
const config = await parseDocumentWithAI(filePath)
if (!config) {
console.log("⏭️ 跳过文件: " + fileName + " (解析失败)")
return { success: false, file: fileName, reason: 'parse_failed' }
}
const validation = validateParsedConfig(config)
if (!validation.valid) {
console.error("❌ 校验失败: " + fileName)
validation.errors.forEach(message => {
console.error(" - " + message)
})
return { success: false, file: fileName, reason: 'validation_failed', errors: validation.errors }
}
// 添加源文件信息
config.source_file = fileName
// 生成配置代码
const { formSn, code } = generateConfigCode(config)
console.log("\n📝 生成 form_sn: " + formSn)
console.log("📋 生成配置代码:\n" + code)
return { success: true, formSn, code, file: fileName, config }
}
/**
* 更新配置文件
* @description 使用简单的字符串搜索找到正确的插入位置
*/
export function updateConfigContent(existingContent, newConfigs) {
const range = getPlanTemplatesRange(existingContent)
if (!range) {
return null
}
const insertContent = newConfigs.map((item, index) => {
const code = item.code.trimEnd()
return index === newConfigs.length - 1 ? code : code + ','
}).join('\n\n')
const before = existingContent.substring(0, range.endIndex)
const after = existingContent.substring(range.endIndex)
const beforeTrimmed = before.replace(/\s+$/, '')
const needsComma = !beforeTrimmed.endsWith(',')
const comma = needsComma ? ',' : ''
return `${beforeTrimmed}${comma}\n\n${insertContent}${after}`
}
function getPlanTemplatesRange(content) {
const startToken = 'export const PLAN_TEMPLATES = {'
const startIndex = content.indexOf(startToken)
if (startIndex === -1) {
return null
}
const openIndex = startIndex + startToken.length - 1
let depth = 1
let inSingle = false
let inDouble = false
let inTemplate = false
let escape = false
for (let i = openIndex + 1; i < content.length; i += 1) {
const ch = content[i]
if (escape) {
escape = false
continue
}
if (ch === '\\') {
if (inSingle || inDouble || inTemplate) {
escape = true
}
continue
}
if (inSingle) {
if (ch === "'") {
inSingle = false
}
continue
}
if (inDouble) {
if (ch === '"') {
inDouble = false
}
continue
}
if (inTemplate) {
if (ch === '`') {
inTemplate = false
}
continue
}
if (ch === "'") {
inSingle = true
continue
}
if (ch === '"') {
inDouble = true
continue
}
if (ch === '`') {
inTemplate = true
continue
}
if (ch === '{') {
depth += 1
continue
}
if (ch === '}') {
depth -= 1
if (depth === 0) {
return { startIndex, endIndex: i }
}
}
}
return null
}
function readQuotedKey(content, startIndex) {
const quote = content[startIndex]
let value = ''
let escape = false
for (let i = startIndex + 1; i < content.length; i += 1) {
const ch = content[i]
if (escape) {
value += ch
escape = false
continue
}
if (ch === '\\') {
escape = true
continue
}
if (ch === quote) {
return { value, endIndex: i }
}
value += ch
}
return null
}
function extractPlanTemplateKeys(content) {
const range = getPlanTemplatesRange(content)
if (!range) {
return []
}
const block = content.slice(range.startIndex, range.endIndex + 1)
const blockStart = block.indexOf('{') + 1
const blockContent = block.slice(blockStart, block.length - 1)
const keys = []
let depth = 0
let inSingle = false
let inDouble = false
let inTemplate = false
let escape = false
for (let i = 0; i < blockContent.length; i += 1) {
const ch = blockContent[i]
if (escape) {
escape = false
continue
}
if (ch === '\\') {
if (inSingle || inDouble || inTemplate) {
escape = true
}
continue
}
if (inSingle) {
if (ch === "'") {
inSingle = false
}
continue
}
if (inDouble) {
if (ch === '"') {
inDouble = false
}
continue
}
if (inTemplate) {
if (ch === '`') {
inTemplate = false
}
continue
}
if (ch === "'") {
inSingle = true
if (depth === 0) {
const keyResult = readQuotedKey(blockContent, i)
if (keyResult) {
const nextIndex = keyResult.endIndex + 1
const rest = blockContent.slice(nextIndex)
const match = rest.match(/^\s*:/)
if (match) {
keys.push(keyResult.value)
}
i = keyResult.endIndex
inSingle = false
}
}
continue
}
if (ch === '"') {
inDouble = true
if (depth === 0) {
const keyResult = readQuotedKey(blockContent, i)
if (keyResult) {
const nextIndex = keyResult.endIndex + 1
const rest = blockContent.slice(nextIndex)
const match = rest.match(/^\s*:/)
if (match) {
keys.push(keyResult.value)
}
i = keyResult.endIndex
inDouble = false
}
}
continue
}
if (ch === '`') {
inTemplate = true
continue
}
if (ch === '{') {
depth += 1
continue
}
if (ch === '}') {
depth -= 1
}
}
return keys
}
export function detectFormSnConflicts(existingContent, newConfigs) {
const existingKeys = extractPlanTemplateKeys(existingContent)
const existingSet = new Set(existingKeys)
const conflicts = []
newConfigs.forEach(item => {
if (existingSet.has(item.formSn)) {
conflicts.push(item.formSn)
}
})
return conflicts
}
export function buildDryRunDiff(newConfigs) {
const insertContent = newConfigs.map((item, index) => {
const code = item.code.trimEnd()
return index === newConfigs.length - 1 ? code : code + ','
}).join('\n\n')
const lines = insertContent.split('\n').map(line => `+ ${line}`)
return ['--- plan-templates.js', '+++ plan-templates.js', ...lines].join('\n')
}
export function buildConfigUpdateResult(existingContent, newConfigs, options = {}) {
const conflicts = detectFormSnConflicts(existingContent, newConfigs)
if (conflicts.length > 0) {
return { ok: false, conflicts, updatedContent: null, diff: null }
}
const updatedContent = updateConfigContent(existingContent, newConfigs)
if (!updatedContent) {
return { ok: false, conflicts: [], updatedContent: null, diff: null }
}
const diff = options.dry_run ? buildDryRunDiff(newConfigs) : null
return { ok: true, conflicts: [], updatedContent, diff }
}
export function buildParseSummary(results, duration_ms) {
const summary = {
total: results.length,
success: 0,
failed: 0,
duration_ms,
success_list: [],
failed_list: []
}
results.forEach(result => {
if (result.success) {
summary.success += 1
summary.success_list.push({
form_sn: result.formSn,
product_name: result.config?.product_name,
file: result.file
})
} else {
summary.failed += 1
summary.failed_list.push({
file: result.file,
reason: result.reason || 'unknown',
errors: result.errors || []
})
}
})
return summary
}
function buildChangeSummary(update_result) {
if (!update_result) {
return null
}
const summary = {
ok: update_result.ok,
dry_run: update_result.dry_run || false,
updated_count: update_result.updated_count || 0,
form_sn_list: update_result.form_sn_list || [],
conflicts: update_result.conflicts || [],
reason: update_result.reason || null
}
if (update_result.diff) {
summary.diff_preview = update_result.diff.split('\n').slice(0, 60).join('\n')
}
return summary
}
function buildAuditRecord(summary, options = {}, update_result = null, mode = 'batch') {
return {
at: new Date().toISOString(),
mode,
options: {
dry_run: !!options.dry_run
},
summary,
change_summary: buildChangeSummary(update_result)
}
}
function writeBackupLog(record) {
ensureDir(BACKUP_DIR)
const logFile = path.join(BACKUP_DIR, 'backup-log.jsonl')
const line = JSON.stringify(record)
fs.appendFileSync(logFile, `${line}\n`, 'utf-8')
}
function writeAuditLog(record) {
ensureDir(BACKUP_DIR)
const logFile = path.join(BACKUP_DIR, 'parse-audit.jsonl')
const line = JSON.stringify(record)
fs.appendFileSync(logFile, `${line}\n`, 'utf-8')
}
function rollbackConfigFile(backupFile) {
if (!backupFile || !fs.existsSync(backupFile)) {
console.error("❌ 找不到备份文件: " + backupFile)
return false
}
fs.copyFileSync(backupFile, CONFIG_FILE)
writeBackupLog({
action: 'rollback',
backup_file: backupFile,
target_file: CONFIG_FILE,
at: new Date().toISOString()
})
console.log("✅ 已回滚配置文件: " + backupFile)
return true
}
function updateConfigFile(newConfigs, options = {}) {
console.log("\n" + "=".repeat(60))
console.log("📝 更新配置文件: " + CONFIG_FILE)
console.log("=".repeat(60))
const existingContent = fs.readFileSync(CONFIG_FILE, 'utf-8')
const updateResult = buildConfigUpdateResult(existingContent, newConfigs, options)
if (!updateResult.ok && updateResult.conflicts.length > 0) {
console.error("❌ 检测到重复 form_sn: " + updateResult.conflicts.join(', '))
return { ok: false, reason: 'conflict', conflicts: updateResult.conflicts }
}
if (!updateResult.ok) {
console.error('❌ 无法定位 PLAN_TEMPLATES 插入位置')
return { ok: false, reason: 'insert_not_found', conflicts: [] }
}
if (options.dry_run) {
console.log("\n🧪 dry-run 变更预览:\n" + updateResult.diff)
return {
ok: true,
dry_run: true,
diff: updateResult.diff,
form_sn_list: newConfigs.map(item => item.formSn),
updated_count: newConfigs.length
}
}
let backupFile = null
if (fs.existsSync(CONFIG_FILE)) {
ensureDir(BACKUP_DIR)
backupFile = path.join(BACKUP_DIR, `plan-templates.backup.${Date.now()}.js`)
fs.copyFileSync(CONFIG_FILE, backupFile)
console.log("💾 已备份到: " + backupFile)
}
writeFile(CONFIG_FILE, updateResult.updatedContent)
writeBackupLog({
action: 'update',
backup_file: backupFile,
target_file: CONFIG_FILE,
form_sn_list: newConfigs.map(item => item.formSn),
at: new Date().toISOString()
})
console.log("✅ 已更新配置文件,新增 " + newConfigs.length + " 个产品")
return {
ok: true,
dry_run: false,
backup_file: backupFile,
form_sn_list: newConfigs.map(item => item.formSn),
updated_count: newConfigs.length
}
}
/**
* 处理所有文档
*/
async function parseAllDocs(docs, options = {}) {
if (docs.length === 0) {
console.log('📭 没有待处理的文档')
return
}
const start_time = Date.now()
console.log("\n" + "=".repeat(60))
console.log("📚 发现 " + docs.length + " 个待处理文档")
console.log("=".repeat(60))
const results = []
const successResults = []
for (const doc of docs) {
const result = await parseSingleFile(doc.fullPath)
results.push(result)
if (result.success) {
successResults.push(result)
}
}
// 汇总
console.log("\n" + "=".repeat(60))
console.log("📊 解析结果汇总")
console.log("=".repeat(60))
console.log("总计: " + docs.length + " 个文档")
console.log("成功: " + successResults.length + " 个")
console.log("失败: " + (results.length - successResults.length) + " 个")
const summary = buildParseSummary(results, Date.now() - start_time)
console.log("耗时: " + summary.duration_ms + "ms")
// 显示成功的产品
if (successResults.length > 0) {
console.log("\n✅ 成功解析的产品:")
successResults.forEach(r => {
console.log(" - " + r.formSn + ": " + r.config.product_name)
})
}
if (summary.failed_list.length > 0) {
console.log("\n⚠️ 失败明细:")
summary.failed_list.forEach(item => {
console.log(" - " + item.file + " (" + item.reason + ")")
})
}
// 更新配置文件
let update_result = null
if (successResults.length > 0) {
update_result = updateConfigFile(successResults, options)
} else {
console.log("\n❌ 没有成功解析的文档,配置文件未更新")
}
const audit_record = buildAuditRecord(summary, options, update_result, 'batch')
writeAuditLog(audit_record)
}
/**
* CLI 入口
*/
async function main() {
const args = process.argv.slice(2)
const docs = getDocsToParse()
// 检查模式
const listMode = args.includes('--list')
const fileMode = args.find(arg => arg.startsWith('--file='))
const dryRunMode = args.includes('--dry-run')
const rollbackMode = args.find(arg => arg.startsWith('--rollback='))
console.log('\n🚀 文档解析工具')
console.log(" 文档目录: " + DOCS_DIR)
console.log(" 配置文件: " + CONFIG_FILE)
if (rollbackMode) {
const backupFile = rollbackMode.split('=')[1]
rollbackConfigFile(backupFile)
} else if (listMode) {
// 列出模式
const docs = getDocsToParse()
console.log("\n📋 待处理文档列表:")
if (docs.length === 0) {
console.log(' (无文档)')
} else {
docs.forEach((doc, index) => {
console.log(" " + (index + 1) + ". " + doc.name + " (" + formatSize(doc.size) + ")")
})
}
} else if (fileMode) {
// 单文件模式
const fileName = fileMode.split('=')[1]
const targetDoc = docs.find(d => d.name === fileName || d.name.includes(fileName))
if (targetDoc) {
const start_time = Date.now()
const result = await parseSingleFile(targetDoc.fullPath)
const summary = buildParseSummary([result], Date.now() - start_time)
console.log("\n📊 解析结果汇总")
console.log("总计: " + summary.total + " 个文档")
console.log("成功: " + summary.success + " 个")
console.log("失败: " + summary.failed + " 个")
console.log("耗时: " + summary.duration_ms + "ms")
if (result.success) {
const update_result = updateConfigFile([result], { dry_run: dryRunMode })
const audit_record = buildAuditRecord(summary, { dry_run: dryRunMode }, update_result, 'single')
writeAuditLog(audit_record)
} else {
const audit_record = buildAuditRecord(summary, { dry_run: dryRunMode }, null, 'single')
writeAuditLog(audit_record)
}
} else {
console.log("❌ 找不到文件: " + fileName)
}
} else {
// 批量处理模式
await parseAllDocs(docs, { dry_run: dryRunMode })
}
console.log('\n✨ 处理完成!')
}
const isDirectRun = import.meta.url === `file://${process.argv[1]}`
if (isDirectRun) {
main().catch(error => {
console.error('❌ 执行失败:', error)
process.exit(1)
})
}