kreuzberg 3.16.0__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.
- kreuzberg/__init__.py +2 -0
- kreuzberg/_config.py +8 -9
- kreuzberg/_extractors/_base.py +0 -46
- kreuzberg/_extractors/_html.py +1 -1
- kreuzberg/_extractors/_pandoc.py +2 -2
- kreuzberg/_extractors/_pdf.py +4 -4
- kreuzberg/_gmft.py +2 -2
- kreuzberg/_mcp/server.py +1 -1
- kreuzberg/_mime_types.py +1 -1
- kreuzberg/_ocr/_easyocr.py +4 -9
- kreuzberg/_ocr/_paddleocr.py +1 -1
- kreuzberg/_ocr/_tesseract.py +15 -25
- kreuzberg/_token_reduction/__init__.py +11 -0
- kreuzberg/_token_reduction/_reducer.py +439 -0
- kreuzberg/_token_reduction/_stopwords.py +116 -0
- kreuzberg/_token_reduction/stopwords/af_stopwords.json +53 -0
- kreuzberg/_token_reduction/stopwords/ar_stopwords.json +482 -0
- kreuzberg/_token_reduction/stopwords/bg_stopwords.json +261 -0
- kreuzberg/_token_reduction/stopwords/bn_stopwords.json +400 -0
- kreuzberg/_token_reduction/stopwords/br_stopwords.json +1205 -0
- kreuzberg/_token_reduction/stopwords/ca_stopwords.json +280 -0
- kreuzberg/_token_reduction/stopwords/cs_stopwords.json +425 -0
- kreuzberg/_token_reduction/stopwords/da_stopwords.json +172 -0
- kreuzberg/_token_reduction/stopwords/de_stopwords.json +622 -0
- kreuzberg/_token_reduction/stopwords/el_stopwords.json +849 -0
- kreuzberg/_token_reduction/stopwords/en_stopwords.json +1300 -0
- kreuzberg/_token_reduction/stopwords/eo_stopwords.json +175 -0
- kreuzberg/_token_reduction/stopwords/es_stopwords.json +734 -0
- kreuzberg/_token_reduction/stopwords/et_stopwords.json +37 -0
- kreuzberg/_token_reduction/stopwords/eu_stopwords.json +100 -0
- kreuzberg/_token_reduction/stopwords/fa_stopwords.json +801 -0
- kreuzberg/_token_reduction/stopwords/fi_stopwords.json +849 -0
- kreuzberg/_token_reduction/stopwords/fr_stopwords.json +693 -0
- kreuzberg/_token_reduction/stopwords/ga_stopwords.json +111 -0
- kreuzberg/_token_reduction/stopwords/gl_stopwords.json +162 -0
- kreuzberg/_token_reduction/stopwords/gu_stopwords.json +226 -0
- kreuzberg/_token_reduction/stopwords/ha_stopwords.json +41 -0
- kreuzberg/_token_reduction/stopwords/he_stopwords.json +196 -0
- kreuzberg/_token_reduction/stopwords/hi_stopwords.json +227 -0
- kreuzberg/_token_reduction/stopwords/hr_stopwords.json +181 -0
- kreuzberg/_token_reduction/stopwords/hu_stopwords.json +791 -0
- kreuzberg/_token_reduction/stopwords/hy_stopwords.json +47 -0
- kreuzberg/_token_reduction/stopwords/id_stopwords.json +760 -0
- kreuzberg/_token_reduction/stopwords/it_stopwords.json +634 -0
- kreuzberg/_token_reduction/stopwords/ja_stopwords.json +136 -0
- kreuzberg/_token_reduction/stopwords/kn_stopwords.json +84 -0
- kreuzberg/_token_reduction/stopwords/ko_stopwords.json +681 -0
- kreuzberg/_token_reduction/stopwords/ku_stopwords.json +64 -0
- kreuzberg/_token_reduction/stopwords/la_stopwords.json +51 -0
- kreuzberg/_token_reduction/stopwords/lt_stopwords.json +476 -0
- kreuzberg/_token_reduction/stopwords/lv_stopwords.json +163 -0
- kreuzberg/_token_reduction/stopwords/ml_stopwords.json +11 -0
- kreuzberg/_token_reduction/stopwords/mr_stopwords.json +101 -0
- kreuzberg/_token_reduction/stopwords/ms_stopwords.json +477 -0
- kreuzberg/_token_reduction/stopwords/ne_stopwords.json +490 -0
- kreuzberg/_token_reduction/stopwords/nl_stopwords.json +415 -0
- kreuzberg/_token_reduction/stopwords/no_stopwords.json +223 -0
- kreuzberg/_token_reduction/stopwords/pl_stopwords.json +331 -0
- kreuzberg/_token_reduction/stopwords/pt_stopwords.json +562 -0
- kreuzberg/_token_reduction/stopwords/ro_stopwords.json +436 -0
- kreuzberg/_token_reduction/stopwords/ru_stopwords.json +561 -0
- kreuzberg/_token_reduction/stopwords/si_stopwords.json +193 -0
- kreuzberg/_token_reduction/stopwords/sk_stopwords.json +420 -0
- kreuzberg/_token_reduction/stopwords/sl_stopwords.json +448 -0
- kreuzberg/_token_reduction/stopwords/so_stopwords.json +32 -0
- kreuzberg/_token_reduction/stopwords/st_stopwords.json +33 -0
- kreuzberg/_token_reduction/stopwords/sv_stopwords.json +420 -0
- kreuzberg/_token_reduction/stopwords/sw_stopwords.json +76 -0
- kreuzberg/_token_reduction/stopwords/ta_stopwords.json +129 -0
- kreuzberg/_token_reduction/stopwords/te_stopwords.json +54 -0
- kreuzberg/_token_reduction/stopwords/th_stopwords.json +118 -0
- kreuzberg/_token_reduction/stopwords/tl_stopwords.json +149 -0
- kreuzberg/_token_reduction/stopwords/tr_stopwords.json +506 -0
- kreuzberg/_token_reduction/stopwords/uk_stopwords.json +75 -0
- kreuzberg/_token_reduction/stopwords/ur_stopwords.json +519 -0
- kreuzberg/_token_reduction/stopwords/vi_stopwords.json +647 -0
- kreuzberg/_token_reduction/stopwords/yo_stopwords.json +62 -0
- kreuzberg/_token_reduction/stopwords/zh_stopwords.json +796 -0
- kreuzberg/_token_reduction/stopwords/zu_stopwords.json +31 -0
- kreuzberg/_types.py +35 -3
- kreuzberg/_utils/_image_preprocessing.py +1 -1
- kreuzberg/_utils/_ref.py +14 -6
- kreuzberg/exceptions.py +0 -1
- kreuzberg/extraction.py +25 -9
- {kreuzberg-3.16.0.dist-info → kreuzberg-3.17.0.dist-info}/METADATA +4 -3
- kreuzberg-3.17.0.dist-info/RECORD +128 -0
- kreuzberg-3.16.0.dist-info/RECORD +0 -61
- {kreuzberg-3.16.0.dist-info → kreuzberg-3.17.0.dist-info}/WHEEL +0 -0
- {kreuzberg-3.16.0.dist-info → kreuzberg-3.17.0.dist-info}/entry_points.txt +0 -0
- {kreuzberg-3.16.0.dist-info → kreuzberg-3.17.0.dist-info}/licenses/LICENSE +0 -0
@@ -0,0 +1,175 @@
|
|
1
|
+
[
|
2
|
+
"adiaŭ",
|
3
|
+
"ajn",
|
4
|
+
"al",
|
5
|
+
"ankoraŭ",
|
6
|
+
"antaŭ",
|
7
|
+
"aŭ",
|
8
|
+
"bonan",
|
9
|
+
"bonvole",
|
10
|
+
"bonvolu",
|
11
|
+
"bv",
|
12
|
+
"ci",
|
13
|
+
"cia",
|
14
|
+
"cian",
|
15
|
+
"cin",
|
16
|
+
"d-ro",
|
17
|
+
"da",
|
18
|
+
"de",
|
19
|
+
"dek",
|
20
|
+
"deka",
|
21
|
+
"do",
|
22
|
+
"doktor'",
|
23
|
+
"doktoro",
|
24
|
+
"du",
|
25
|
+
"dua",
|
26
|
+
"dum",
|
27
|
+
"eble",
|
28
|
+
"ekz",
|
29
|
+
"ekzemple",
|
30
|
+
"en",
|
31
|
+
"estas",
|
32
|
+
"estis",
|
33
|
+
"estos",
|
34
|
+
"estu",
|
35
|
+
"estus",
|
36
|
+
"eĉ",
|
37
|
+
"f-no",
|
38
|
+
"feliĉan",
|
39
|
+
"for",
|
40
|
+
"fraŭlino",
|
41
|
+
"ha",
|
42
|
+
"havas",
|
43
|
+
"havis",
|
44
|
+
"havos",
|
45
|
+
"havu",
|
46
|
+
"havus",
|
47
|
+
"he",
|
48
|
+
"ho",
|
49
|
+
"hu",
|
50
|
+
"ili",
|
51
|
+
"ilia",
|
52
|
+
"ilian",
|
53
|
+
"ilin",
|
54
|
+
"inter",
|
55
|
+
"io",
|
56
|
+
"ion",
|
57
|
+
"iu",
|
58
|
+
"iujn",
|
59
|
+
"iun",
|
60
|
+
"ja",
|
61
|
+
"jam",
|
62
|
+
"je",
|
63
|
+
"jes",
|
64
|
+
"k",
|
65
|
+
"kaj",
|
66
|
+
"ke",
|
67
|
+
"kio",
|
68
|
+
"kion",
|
69
|
+
"kiu",
|
70
|
+
"kiujn",
|
71
|
+
"kiun",
|
72
|
+
"kvankam",
|
73
|
+
"kvar",
|
74
|
+
"kvara",
|
75
|
+
"kvazaŭ",
|
76
|
+
"kvin",
|
77
|
+
"kvina",
|
78
|
+
"la",
|
79
|
+
"li",
|
80
|
+
"lia",
|
81
|
+
"lian",
|
82
|
+
"lin",
|
83
|
+
"malantaŭ",
|
84
|
+
"male",
|
85
|
+
"malgraŭ",
|
86
|
+
"mem",
|
87
|
+
"mi",
|
88
|
+
"mia",
|
89
|
+
"mian",
|
90
|
+
"min",
|
91
|
+
"minus",
|
92
|
+
"naŭ",
|
93
|
+
"naŭa",
|
94
|
+
"ne",
|
95
|
+
"nek",
|
96
|
+
"nenio",
|
97
|
+
"nenion",
|
98
|
+
"neniu",
|
99
|
+
"neniun",
|
100
|
+
"nepre",
|
101
|
+
"ni",
|
102
|
+
"nia",
|
103
|
+
"nian",
|
104
|
+
"nin",
|
105
|
+
"nu",
|
106
|
+
"nun",
|
107
|
+
"nur",
|
108
|
+
"ok",
|
109
|
+
"oka",
|
110
|
+
"oni",
|
111
|
+
"onia",
|
112
|
+
"onian",
|
113
|
+
"onin",
|
114
|
+
"plej",
|
115
|
+
"pli",
|
116
|
+
"plu",
|
117
|
+
"plus",
|
118
|
+
"por",
|
119
|
+
"post",
|
120
|
+
"preter",
|
121
|
+
"s-no",
|
122
|
+
"s-ro",
|
123
|
+
"se",
|
124
|
+
"sed",
|
125
|
+
"sep",
|
126
|
+
"sepa",
|
127
|
+
"ses",
|
128
|
+
"sesa",
|
129
|
+
"si",
|
130
|
+
"sia",
|
131
|
+
"sian",
|
132
|
+
"sin",
|
133
|
+
"sinjor'",
|
134
|
+
"sinjorino",
|
135
|
+
"sinjoro",
|
136
|
+
"sub",
|
137
|
+
"super",
|
138
|
+
"supren",
|
139
|
+
"sur",
|
140
|
+
"tamen",
|
141
|
+
"tio",
|
142
|
+
"tion",
|
143
|
+
"tiu",
|
144
|
+
"tiujn",
|
145
|
+
"tiun",
|
146
|
+
"tra",
|
147
|
+
"tri",
|
148
|
+
"tria",
|
149
|
+
"tuj",
|
150
|
+
"tute",
|
151
|
+
"unu",
|
152
|
+
"unua",
|
153
|
+
"ve",
|
154
|
+
"verŝajne",
|
155
|
+
"vi",
|
156
|
+
"via",
|
157
|
+
"vian",
|
158
|
+
"vin",
|
159
|
+
"ĉi",
|
160
|
+
"ĉio",
|
161
|
+
"ĉion",
|
162
|
+
"ĉiu",
|
163
|
+
"ĉiujn",
|
164
|
+
"ĉiun",
|
165
|
+
"ĉu",
|
166
|
+
"ĝi",
|
167
|
+
"ĝia",
|
168
|
+
"ĝian",
|
169
|
+
"ĝin",
|
170
|
+
"ĝis",
|
171
|
+
"ĵus",
|
172
|
+
"ŝi",
|
173
|
+
"ŝia",
|
174
|
+
"ŝin"
|
175
|
+
]
|