kreuzberg 3.15.0__py3-none-any.whl → 3.17.0__py3-none-any.whl

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (99) hide show
  1. kreuzberg/__init__.py +6 -0
  2. kreuzberg/_api/main.py +0 -53
  3. kreuzberg/_config.py +17 -8
  4. kreuzberg/_document_classification.py +1 -1
  5. kreuzberg/_extractors/_base.py +0 -46
  6. kreuzberg/_extractors/_email.py +16 -10
  7. kreuzberg/_extractors/_html.py +39 -12
  8. kreuzberg/_extractors/_pandoc.py +2 -2
  9. kreuzberg/_extractors/_pdf.py +6 -7
  10. kreuzberg/_extractors/_presentation.py +4 -0
  11. kreuzberg/_extractors/_spread_sheet.py +0 -1
  12. kreuzberg/_extractors/_structured.py +83 -15
  13. kreuzberg/_gmft.py +7 -2
  14. kreuzberg/_mcp/server.py +1 -22
  15. kreuzberg/_mime_types.py +1 -1
  16. kreuzberg/_ocr/_easyocr.py +47 -20
  17. kreuzberg/_ocr/_paddleocr.py +1 -1
  18. kreuzberg/_ocr/_tesseract.py +27 -26
  19. kreuzberg/_token_reduction/__init__.py +11 -0
  20. kreuzberg/_token_reduction/_reducer.py +439 -0
  21. kreuzberg/_token_reduction/_stopwords.py +116 -0
  22. kreuzberg/_token_reduction/stopwords/af_stopwords.json +53 -0
  23. kreuzberg/_token_reduction/stopwords/ar_stopwords.json +482 -0
  24. kreuzberg/_token_reduction/stopwords/bg_stopwords.json +261 -0
  25. kreuzberg/_token_reduction/stopwords/bn_stopwords.json +400 -0
  26. kreuzberg/_token_reduction/stopwords/br_stopwords.json +1205 -0
  27. kreuzberg/_token_reduction/stopwords/ca_stopwords.json +280 -0
  28. kreuzberg/_token_reduction/stopwords/cs_stopwords.json +425 -0
  29. kreuzberg/_token_reduction/stopwords/da_stopwords.json +172 -0
  30. kreuzberg/_token_reduction/stopwords/de_stopwords.json +622 -0
  31. kreuzberg/_token_reduction/stopwords/el_stopwords.json +849 -0
  32. kreuzberg/_token_reduction/stopwords/en_stopwords.json +1300 -0
  33. kreuzberg/_token_reduction/stopwords/eo_stopwords.json +175 -0
  34. kreuzberg/_token_reduction/stopwords/es_stopwords.json +734 -0
  35. kreuzberg/_token_reduction/stopwords/et_stopwords.json +37 -0
  36. kreuzberg/_token_reduction/stopwords/eu_stopwords.json +100 -0
  37. kreuzberg/_token_reduction/stopwords/fa_stopwords.json +801 -0
  38. kreuzberg/_token_reduction/stopwords/fi_stopwords.json +849 -0
  39. kreuzberg/_token_reduction/stopwords/fr_stopwords.json +693 -0
  40. kreuzberg/_token_reduction/stopwords/ga_stopwords.json +111 -0
  41. kreuzberg/_token_reduction/stopwords/gl_stopwords.json +162 -0
  42. kreuzberg/_token_reduction/stopwords/gu_stopwords.json +226 -0
  43. kreuzberg/_token_reduction/stopwords/ha_stopwords.json +41 -0
  44. kreuzberg/_token_reduction/stopwords/he_stopwords.json +196 -0
  45. kreuzberg/_token_reduction/stopwords/hi_stopwords.json +227 -0
  46. kreuzberg/_token_reduction/stopwords/hr_stopwords.json +181 -0
  47. kreuzberg/_token_reduction/stopwords/hu_stopwords.json +791 -0
  48. kreuzberg/_token_reduction/stopwords/hy_stopwords.json +47 -0
  49. kreuzberg/_token_reduction/stopwords/id_stopwords.json +760 -0
  50. kreuzberg/_token_reduction/stopwords/it_stopwords.json +634 -0
  51. kreuzberg/_token_reduction/stopwords/ja_stopwords.json +136 -0
  52. kreuzberg/_token_reduction/stopwords/kn_stopwords.json +84 -0
  53. kreuzberg/_token_reduction/stopwords/ko_stopwords.json +681 -0
  54. kreuzberg/_token_reduction/stopwords/ku_stopwords.json +64 -0
  55. kreuzberg/_token_reduction/stopwords/la_stopwords.json +51 -0
  56. kreuzberg/_token_reduction/stopwords/lt_stopwords.json +476 -0
  57. kreuzberg/_token_reduction/stopwords/lv_stopwords.json +163 -0
  58. kreuzberg/_token_reduction/stopwords/ml_stopwords.json +11 -0
  59. kreuzberg/_token_reduction/stopwords/mr_stopwords.json +101 -0
  60. kreuzberg/_token_reduction/stopwords/ms_stopwords.json +477 -0
  61. kreuzberg/_token_reduction/stopwords/ne_stopwords.json +490 -0
  62. kreuzberg/_token_reduction/stopwords/nl_stopwords.json +415 -0
  63. kreuzberg/_token_reduction/stopwords/no_stopwords.json +223 -0
  64. kreuzberg/_token_reduction/stopwords/pl_stopwords.json +331 -0
  65. kreuzberg/_token_reduction/stopwords/pt_stopwords.json +562 -0
  66. kreuzberg/_token_reduction/stopwords/ro_stopwords.json +436 -0
  67. kreuzberg/_token_reduction/stopwords/ru_stopwords.json +561 -0
  68. kreuzberg/_token_reduction/stopwords/si_stopwords.json +193 -0
  69. kreuzberg/_token_reduction/stopwords/sk_stopwords.json +420 -0
  70. kreuzberg/_token_reduction/stopwords/sl_stopwords.json +448 -0
  71. kreuzberg/_token_reduction/stopwords/so_stopwords.json +32 -0
  72. kreuzberg/_token_reduction/stopwords/st_stopwords.json +33 -0
  73. kreuzberg/_token_reduction/stopwords/sv_stopwords.json +420 -0
  74. kreuzberg/_token_reduction/stopwords/sw_stopwords.json +76 -0
  75. kreuzberg/_token_reduction/stopwords/ta_stopwords.json +129 -0
  76. kreuzberg/_token_reduction/stopwords/te_stopwords.json +54 -0
  77. kreuzberg/_token_reduction/stopwords/th_stopwords.json +118 -0
  78. kreuzberg/_token_reduction/stopwords/tl_stopwords.json +149 -0
  79. kreuzberg/_token_reduction/stopwords/tr_stopwords.json +506 -0
  80. kreuzberg/_token_reduction/stopwords/uk_stopwords.json +75 -0
  81. kreuzberg/_token_reduction/stopwords/ur_stopwords.json +519 -0
  82. kreuzberg/_token_reduction/stopwords/vi_stopwords.json +647 -0
  83. kreuzberg/_token_reduction/stopwords/yo_stopwords.json +62 -0
  84. kreuzberg/_token_reduction/stopwords/zh_stopwords.json +796 -0
  85. kreuzberg/_token_reduction/stopwords/zu_stopwords.json +31 -0
  86. kreuzberg/_types.py +146 -43
  87. kreuzberg/_utils/_html_streaming.py +20 -0
  88. kreuzberg/_utils/_image_preprocessing.py +1 -1
  89. kreuzberg/_utils/_ref.py +14 -6
  90. kreuzberg/_utils/_serialization.py +13 -6
  91. kreuzberg/_utils/_sync.py +15 -16
  92. kreuzberg/exceptions.py +0 -1
  93. kreuzberg/extraction.py +27 -11
  94. {kreuzberg-3.15.0.dist-info → kreuzberg-3.17.0.dist-info}/METADATA +15 -13
  95. kreuzberg-3.17.0.dist-info/RECORD +128 -0
  96. kreuzberg-3.15.0.dist-info/RECORD +0 -60
  97. {kreuzberg-3.15.0.dist-info → kreuzberg-3.17.0.dist-info}/WHEEL +0 -0
  98. {kreuzberg-3.15.0.dist-info → kreuzberg-3.17.0.dist-info}/entry_points.txt +0 -0
  99. {kreuzberg-3.15.0.dist-info → kreuzberg-3.17.0.dist-info}/licenses/LICENSE +0 -0
@@ -0,0 +1,477 @@
1
+ [
2
+ "abdul",
3
+ "abdullah",
4
+ "acara",
5
+ "ada",
6
+ "adalah",
7
+ "ahmad",
8
+ "air",
9
+ "akan",
10
+ "akhbar",
11
+ "akhir",
12
+ "aktiviti",
13
+ "alam",
14
+ "amat",
15
+ "amerika",
16
+ "anak",
17
+ "anggota",
18
+ "antara",
19
+ "antarabangsa",
20
+ "apa",
21
+ "apabila",
22
+ "april",
23
+ "as",
24
+ "asas",
25
+ "asean",
26
+ "asia",
27
+ "asing",
28
+ "atas",
29
+ "atau",
30
+ "australia",
31
+ "awal",
32
+ "awam",
33
+ "bagaimanapun",
34
+ "bagi",
35
+ "bahagian",
36
+ "bahan",
37
+ "baharu",
38
+ "bahawa",
39
+ "baik",
40
+ "bandar",
41
+ "bank",
42
+ "banyak",
43
+ "barangan",
44
+ "baru",
45
+ "baru-baru",
46
+ "bawah",
47
+ "beberapa",
48
+ "bekas",
49
+ "beliau",
50
+ "belum",
51
+ "berada",
52
+ "berakhir",
53
+ "berbanding",
54
+ "berdasarkan",
55
+ "berharap",
56
+ "berikutan",
57
+ "berjaya",
58
+ "berjumlah",
59
+ "berkaitan",
60
+ "berkata",
61
+ "berkenaan",
62
+ "berlaku",
63
+ "bermula",
64
+ "bernama",
65
+ "bernilai",
66
+ "bersama",
67
+ "berubah",
68
+ "besar",
69
+ "bhd",
70
+ "bidang",
71
+ "bilion",
72
+ "bn",
73
+ "boleh",
74
+ "bukan",
75
+ "bulan",
76
+ "bursa",
77
+ "cadangan",
78
+ "china",
79
+ "dagangan",
80
+ "dalam",
81
+ "dan",
82
+ "dana",
83
+ "dapat",
84
+ "dari",
85
+ "daripada",
86
+ "dasar",
87
+ "datang",
88
+ "datuk",
89
+ "demikian",
90
+ "dengan",
91
+ "depan",
92
+ "derivatives",
93
+ "dewan",
94
+ "di",
95
+ "diadakan",
96
+ "dibuka",
97
+ "dicatatkan",
98
+ "dijangka",
99
+ "diniagakan",
100
+ "dis",
101
+ "disember",
102
+ "ditutup",
103
+ "dolar",
104
+ "dr",
105
+ "dua",
106
+ "dunia",
107
+ "ekonomi",
108
+ "eksekutif",
109
+ "eksport",
110
+ "empat",
111
+ "enam",
112
+ "faedah",
113
+ "feb",
114
+ "global",
115
+ "hadapan",
116
+ "hanya",
117
+ "harga",
118
+ "hari",
119
+ "hasil",
120
+ "hingga",
121
+ "hubungan",
122
+ "ia",
123
+ "iaitu",
124
+ "ialah",
125
+ "indeks",
126
+ "india",
127
+ "indonesia",
128
+ "industri",
129
+ "ini",
130
+ "islam",
131
+ "isnin",
132
+ "isu",
133
+ "itu",
134
+ "jabatan",
135
+ "jalan",
136
+ "jan",
137
+ "jawatan",
138
+ "jawatankuasa",
139
+ "jepun",
140
+ "jika",
141
+ "jualan",
142
+ "juga",
143
+ "julai",
144
+ "jumaat",
145
+ "jumlah",
146
+ "jun",
147
+ "juta",
148
+ "kadar",
149
+ "kalangan",
150
+ "kali",
151
+ "kami",
152
+ "kata",
153
+ "katanya",
154
+ "kaunter",
155
+ "kawasan",
156
+ "ke",
157
+ "keadaan",
158
+ "kecil",
159
+ "kedua",
160
+ "kedua-dua",
161
+ "kedudukan",
162
+ "kekal",
163
+ "kementerian",
164
+ "kemudahan",
165
+ "kenaikan",
166
+ "kenyataan",
167
+ "kepada",
168
+ "kepentingan",
169
+ "keputusan",
170
+ "kerajaan",
171
+ "kerana",
172
+ "kereta",
173
+ "kerja",
174
+ "kerjasama",
175
+ "kes",
176
+ "keselamatan",
177
+ "keseluruhan",
178
+ "kesihatan",
179
+ "ketika",
180
+ "ketua",
181
+ "keuntungan",
182
+ "kewangan",
183
+ "khamis",
184
+ "kini",
185
+ "kira-kira",
186
+ "kita",
187
+ "klci",
188
+ "klibor",
189
+ "komposit",
190
+ "kontrak",
191
+ "kos",
192
+ "kuala",
193
+ "kuasa",
194
+ "kukuh",
195
+ "kumpulan",
196
+ "lagi",
197
+ "lain",
198
+ "langkah",
199
+ "laporan",
200
+ "lebih",
201
+ "lepas",
202
+ "lima",
203
+ "lot",
204
+ "luar",
205
+ "lumpur",
206
+ "mac",
207
+ "mahkamah",
208
+ "mahu",
209
+ "majlis",
210
+ "makanan",
211
+ "maklumat",
212
+ "malam",
213
+ "malaysia",
214
+ "mana",
215
+ "manakala",
216
+ "masa",
217
+ "masalah",
218
+ "masih",
219
+ "masing-masing",
220
+ "masyarakat",
221
+ "mata",
222
+ "media",
223
+ "mei",
224
+ "melalui",
225
+ "melihat",
226
+ "memandangkan",
227
+ "memastikan",
228
+ "membantu",
229
+ "membawa",
230
+ "memberi",
231
+ "memberikan",
232
+ "membolehkan",
233
+ "membuat",
234
+ "mempunyai",
235
+ "menambah",
236
+ "menarik",
237
+ "menawarkan",
238
+ "mencapai",
239
+ "mencatatkan",
240
+ "mendapat",
241
+ "mendapatkan",
242
+ "menerima",
243
+ "menerusi",
244
+ "mengadakan",
245
+ "mengambil",
246
+ "mengenai",
247
+ "menggalakkan",
248
+ "menggunakan",
249
+ "mengikut",
250
+ "mengumumkan",
251
+ "mengurangkan",
252
+ "meningkat",
253
+ "meningkatkan",
254
+ "menjadi",
255
+ "menjelang",
256
+ "menokok",
257
+ "menteri",
258
+ "menunjukkan",
259
+ "menurut",
260
+ "menyaksikan",
261
+ "menyediakan",
262
+ "mereka",
263
+ "merosot",
264
+ "merupakan",
265
+ "mesyuarat",
266
+ "minat",
267
+ "minggu",
268
+ "minyak",
269
+ "modal",
270
+ "mohd",
271
+ "mudah",
272
+ "mungkin",
273
+ "naik",
274
+ "najib",
275
+ "nasional",
276
+ "negara",
277
+ "negara-negara",
278
+ "negeri",
279
+ "niaga",
280
+ "nilai",
281
+ "nov",
282
+ "ogos",
283
+ "okt",
284
+ "oleh",
285
+ "operasi",
286
+ "orang",
287
+ "pada",
288
+ "pagi",
289
+ "paling",
290
+ "pameran",
291
+ "papan",
292
+ "para",
293
+ "paras",
294
+ "parlimen",
295
+ "parti",
296
+ "pasaran",
297
+ "pasukan",
298
+ "pegawai",
299
+ "pejabat",
300
+ "pekerja",
301
+ "pelabur",
302
+ "pelaburan",
303
+ "pelancongan",
304
+ "pelanggan",
305
+ "pelbagai",
306
+ "peluang",
307
+ "pembangunan",
308
+ "pemberita",
309
+ "pembinaan",
310
+ "pemimpin",
311
+ "pendapatan",
312
+ "pendidikan",
313
+ "penduduk",
314
+ "penerbangan",
315
+ "pengarah",
316
+ "pengeluaran",
317
+ "pengerusi",
318
+ "pengguna",
319
+ "pengurusan",
320
+ "peniaga",
321
+ "peningkatan",
322
+ "penting",
323
+ "peratus",
324
+ "perdagangan",
325
+ "perdana",
326
+ "peringkat",
327
+ "perjanjian",
328
+ "perkara",
329
+ "perkhidmatan",
330
+ "perladangan",
331
+ "perlu",
332
+ "permintaan",
333
+ "perniagaan",
334
+ "persekutuan",
335
+ "persidangan",
336
+ "pertama",
337
+ "pertubuhan",
338
+ "pertumbuhan",
339
+ "perusahaan",
340
+ "peserta",
341
+ "petang",
342
+ "pihak",
343
+ "pilihan",
344
+ "pinjaman",
345
+ "polis",
346
+ "politik",
347
+ "presiden",
348
+ "prestasi",
349
+ "produk",
350
+ "program",
351
+ "projek",
352
+ "proses",
353
+ "proton",
354
+ "pukul",
355
+ "pula",
356
+ "pusat",
357
+ "rabu",
358
+ "rakan",
359
+ "rakyat",
360
+ "ramai",
361
+ "rantau",
362
+ "raya",
363
+ "rendah",
364
+ "ringgit",
365
+ "rumah",
366
+ "sabah",
367
+ "sahaja",
368
+ "saham",
369
+ "sama",
370
+ "sarawak",
371
+ "satu",
372
+ "sawit",
373
+ "saya",
374
+ "sdn",
375
+ "sebagai",
376
+ "sebahagian",
377
+ "sebanyak",
378
+ "sebarang",
379
+ "sebelum",
380
+ "sebelumnya",
381
+ "sebuah",
382
+ "secara",
383
+ "sedang",
384
+ "segi",
385
+ "sehingga",
386
+ "sejak",
387
+ "sekarang",
388
+ "sektor",
389
+ "sekuriti",
390
+ "selain",
391
+ "selama",
392
+ "selasa",
393
+ "selatan",
394
+ "selepas",
395
+ "seluruh",
396
+ "semakin",
397
+ "semalam",
398
+ "semasa",
399
+ "sementara",
400
+ "semua",
401
+ "semula",
402
+ "sen",
403
+ "sendiri",
404
+ "seorang",
405
+ "sepanjang",
406
+ "seperti",
407
+ "sept",
408
+ "september",
409
+ "serantau",
410
+ "seri",
411
+ "serta",
412
+ "sesi",
413
+ "setiap",
414
+ "setiausaha",
415
+ "sidang",
416
+ "singapura",
417
+ "sini",
418
+ "sistem",
419
+ "sokongan",
420
+ "sri",
421
+ "sudah",
422
+ "sukan",
423
+ "suku",
424
+ "sumber",
425
+ "supaya",
426
+ "susut",
427
+ "syarikat",
428
+ "syed",
429
+ "tahap",
430
+ "tahun",
431
+ "tan",
432
+ "tanah",
433
+ "tanpa",
434
+ "tawaran",
435
+ "teknologi",
436
+ "telah",
437
+ "tempat",
438
+ "tempatan",
439
+ "tempoh",
440
+ "tenaga",
441
+ "tengah",
442
+ "tentang",
443
+ "terbaik",
444
+ "terbang",
445
+ "terbesar",
446
+ "terbuka",
447
+ "terdapat",
448
+ "terhadap",
449
+ "termasuk",
450
+ "tersebut",
451
+ "terus",
452
+ "tetapi",
453
+ "thailand",
454
+ "tiada",
455
+ "tidak",
456
+ "tiga",
457
+ "timbalan",
458
+ "timur",
459
+ "tindakan",
460
+ "tinggi",
461
+ "tun",
462
+ "tunai",
463
+ "turun",
464
+ "turut",
465
+ "umno",
466
+ "unit",
467
+ "untuk",
468
+ "untung",
469
+ "urus",
470
+ "usaha",
471
+ "utama",
472
+ "walaupun",
473
+ "wang",
474
+ "wanita",
475
+ "wilayah",
476
+ "yang"
477
+ ]