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 +1,163 @@
1
+ [
2
+ "aiz",
3
+ "ap",
4
+ "apakš",
5
+ "apakšpus",
6
+ "ar",
7
+ "arī",
8
+ "augšpus",
9
+ "bet",
10
+ "bez",
11
+ "bija",
12
+ "biji",
13
+ "biju",
14
+ "bijām",
15
+ "bijāt",
16
+ "būs",
17
+ "būsi",
18
+ "būsiet",
19
+ "būsim",
20
+ "būt",
21
+ "būšu",
22
+ "caur",
23
+ "diemžēl",
24
+ "diezin",
25
+ "droši",
26
+ "dēļ",
27
+ "esam",
28
+ "esat",
29
+ "esi",
30
+ "esmu",
31
+ "gan",
32
+ "gar",
33
+ "iekam",
34
+ "iekams",
35
+ "iekām",
36
+ "iekāms",
37
+ "iekš",
38
+ "iekšpus",
39
+ "ik",
40
+ "ir",
41
+ "it",
42
+ "itin",
43
+ "iz",
44
+ "ja",
45
+ "jau",
46
+ "jeb",
47
+ "jebšu",
48
+ "jel",
49
+ "jo",
50
+ "jā",
51
+ "ka",
52
+ "kamēr",
53
+ "kaut",
54
+ "kolīdz",
55
+ "kopš",
56
+ "kā",
57
+ "kļuva",
58
+ "kļuvi",
59
+ "kļuvu",
60
+ "kļuvām",
61
+ "kļuvāt",
62
+ "kļūs",
63
+ "kļūsi",
64
+ "kļūsiet",
65
+ "kļūsim",
66
+ "kļūst",
67
+ "kļūstam",
68
+ "kļūstat",
69
+ "kļūsti",
70
+ "kļūstu",
71
+ "kļūt",
72
+ "kļūšu",
73
+ "labad",
74
+ "lai",
75
+ "lejpus",
76
+ "līdz",
77
+ "līdzko",
78
+ "ne",
79
+ "nebūt",
80
+ "nedz",
81
+ "nekā",
82
+ "nevis",
83
+ "nezin",
84
+ "no",
85
+ "nu",
86
+ "nē",
87
+ "otrpus",
88
+ "pa",
89
+ "par",
90
+ "pat",
91
+ "pie",
92
+ "pirms",
93
+ "pret",
94
+ "priekš",
95
+ "pār",
96
+ "pēc",
97
+ "starp",
98
+ "tad",
99
+ "tak",
100
+ "tapi",
101
+ "taps",
102
+ "tapsi",
103
+ "tapsiet",
104
+ "tapsim",
105
+ "tapt",
106
+ "tapāt",
107
+ "tapšu",
108
+ "taču",
109
+ "te",
110
+ "tiec",
111
+ "tiek",
112
+ "tiekam",
113
+ "tiekat",
114
+ "tieku",
115
+ "tik",
116
+ "tika",
117
+ "tikai",
118
+ "tiki",
119
+ "tikko",
120
+ "tiklab",
121
+ "tiklīdz",
122
+ "tiks",
123
+ "tiksiet",
124
+ "tiksim",
125
+ "tikt",
126
+ "tiku",
127
+ "tikvien",
128
+ "tikām",
129
+ "tikāt",
130
+ "tikšu",
131
+ "tomēr",
132
+ "topat",
133
+ "turpretim",
134
+ "turpretī",
135
+ "tā",
136
+ "tādēļ",
137
+ "tālab",
138
+ "tāpēc",
139
+ "un",
140
+ "uz",
141
+ "vai",
142
+ "var",
143
+ "varat",
144
+ "varēja",
145
+ "varēji",
146
+ "varēju",
147
+ "varējām",
148
+ "varējāt",
149
+ "varēs",
150
+ "varēsi",
151
+ "varēsiet",
152
+ "varēsim",
153
+ "varēt",
154
+ "varēšu",
155
+ "vien",
156
+ "virs",
157
+ "virspus",
158
+ "vis",
159
+ "viņpus",
160
+ "zem",
161
+ "ārpus",
162
+ "šaipus"
163
+ ]
@@ -0,0 +1,11 @@
1
+ [
2
+ "അത്",
3
+ "അന്നേരം",
4
+ "അന്ന്",
5
+ "ആകുന്നു",
6
+ "ആണ്",
7
+ "ആയിരുന്നു",
8
+ "ഇത്",
9
+ "ഇന്ന്",
10
+ "വരെ"
11
+ ]
@@ -0,0 +1,101 @@
1
+ [
2
+ "अधिक",
3
+ "अनेक",
4
+ "अशी",
5
+ "असलयाचे",
6
+ "असलेल्या",
7
+ "असा",
8
+ "असून",
9
+ "असे",
10
+ "आज",
11
+ "आणि",
12
+ "आता",
13
+ "आपल्या",
14
+ "आला",
15
+ "आली",
16
+ "आले",
17
+ "आहे",
18
+ "आहेत",
19
+ "एक",
20
+ "एका",
21
+ "कमी",
22
+ "करणयात",
23
+ "करून",
24
+ "का",
25
+ "काम",
26
+ "काय",
27
+ "काही",
28
+ "किवा",
29
+ "की",
30
+ "केला",
31
+ "केली",
32
+ "केले",
33
+ "कोटी",
34
+ "गेल्या",
35
+ "घेऊन",
36
+ "जात",
37
+ "झाला",
38
+ "झाली",
39
+ "झाले",
40
+ "झालेल्या",
41
+ "टा",
42
+ "डॉ",
43
+ "तर",
44
+ "तरी",
45
+ "तसेच",
46
+ "ता",
47
+ "ती",
48
+ "तीन",
49
+ "ते",
50
+ "तो",
51
+ "त्या",
52
+ "त्याचा",
53
+ "त्याची",
54
+ "त्याच्या",
55
+ "त्याना",
56
+ "त्यानी",
57
+ "त्यामुळे",
58
+ "त्री",
59
+ "दिली",
60
+ "दोन",
61
+ "न",
62
+ "नाही",
63
+ "निर्ण्य",
64
+ "पण",
65
+ "पम",
66
+ "परयतन",
67
+ "पाटील",
68
+ "म",
69
+ "मात्र",
70
+ "माहिती",
71
+ "मी",
72
+ "मुबी",
73
+ "म्हणजे",
74
+ "म्हणाले",
75
+ "म्हणून",
76
+ "या",
77
+ "याचा",
78
+ "याची",
79
+ "याच्या",
80
+ "याना",
81
+ "यानी",
82
+ "येणार",
83
+ "येत",
84
+ "येथील",
85
+ "येथे",
86
+ "लाख",
87
+ "व",
88
+ "व्यकत",
89
+ "सर्व",
90
+ "सागित्ले",
91
+ "सुरू",
92
+ "हजार",
93
+ "हा",
94
+ "ही",
95
+ "हे",
96
+ "होणार",
97
+ "होत",
98
+ "होता",
99
+ "होती",
100
+ "होते"
101
+ ]