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 +1,118 @@
1
+ [
2
+ "กล่าว",
3
+ "กว่า",
4
+ "กัน",
5
+ "กับ",
6
+ "การ",
7
+ "ก็",
8
+ "ก่อน",
9
+ "ขณะ",
10
+ "ขอ",
11
+ "ของ",
12
+ "ขึ้น",
13
+ "คง",
14
+ "ครั้ง",
15
+ "ความ",
16
+ "คือ",
17
+ "จะ",
18
+ "จัด",
19
+ "จาก",
20
+ "จึง",
21
+ "ช่วง",
22
+ "ซึ่ง",
23
+ "ดัง",
24
+ "ด้วย",
25
+ "ด้าน",
26
+ "ตั้ง",
27
+ "ตั้งแต่",
28
+ "ตาม",
29
+ "ต่อ",
30
+ "ต่าง",
31
+ "ต่างๆ",
32
+ "ต้อง",
33
+ "ถึง",
34
+ "ถูก",
35
+ "ถ้า",
36
+ "ทั้ง",
37
+ "ทั้งนี้",
38
+ "ทาง",
39
+ "ที่",
40
+ "ที่สุด",
41
+ "ทุก",
42
+ "ทํา",
43
+ "ทําให้",
44
+ "นอกจาก",
45
+ "นัก",
46
+ "นั้น",
47
+ "นี้",
48
+ "น่า",
49
+ "นํา",
50
+ "บาง",
51
+ "ผล",
52
+ "ผ่าน",
53
+ "พบ",
54
+ "พร้อม",
55
+ "มา",
56
+ "มาก",
57
+ "มี",
58
+ "ยัง",
59
+ "รวม",
60
+ "ระหว่าง",
61
+ "รับ",
62
+ "ราย",
63
+ "ร่วม",
64
+ "ลง",
65
+ "วัน",
66
+ "ว่า",
67
+ "สุด",
68
+ "ส่ง",
69
+ "ส่วน",
70
+ "สําหรับ",
71
+ "หนึ่ง",
72
+ "หรือ",
73
+ "หลัง",
74
+ "หลังจาก",
75
+ "หลาย",
76
+ "หาก",
77
+ "อยาก",
78
+ "อยู่",
79
+ "อย่าง",
80
+ "ออก",
81
+ "อะไร",
82
+ "อาจ",
83
+ "อีก",
84
+ "เขา",
85
+ "เข้า",
86
+ "เคย",
87
+ "เฉพาะ",
88
+ "เช่น",
89
+ "เดียว",
90
+ "เดียวกัน",
91
+ "เนื่องจาก",
92
+ "เปิด",
93
+ "เปิดเผย",
94
+ "เป็น",
95
+ "เป็นการ",
96
+ "เพราะ",
97
+ "เพื่อ",
98
+ "เมื่อ",
99
+ "เรา",
100
+ "เริ่ม",
101
+ "เลย",
102
+ "เห็น",
103
+ "เอง",
104
+ "แต่",
105
+ "แบบ",
106
+ "แรก",
107
+ "และ",
108
+ "แล้ว",
109
+ "แห่ง",
110
+ "โดย",
111
+ "ใน",
112
+ "ให้",
113
+ "ได้",
114
+ "ไป",
115
+ "ไม่",
116
+ "ไว้",
117
+ "้ง"
118
+ ]
@@ -0,0 +1,149 @@
1
+ [
2
+ "akin",
3
+ "aking",
4
+ "ako",
5
+ "alin",
6
+ "am",
7
+ "amin",
8
+ "aming",
9
+ "ang",
10
+ "ano",
11
+ "anumang",
12
+ "apat",
13
+ "at",
14
+ "atin",
15
+ "ating",
16
+ "ay",
17
+ "bababa",
18
+ "bago",
19
+ "bakit",
20
+ "bawat",
21
+ "bilang",
22
+ "dahil",
23
+ "dalawa",
24
+ "dapat",
25
+ "din",
26
+ "dito",
27
+ "doon",
28
+ "gagawin",
29
+ "gayunman",
30
+ "ginagawa",
31
+ "ginawa",
32
+ "ginawang",
33
+ "gumawa",
34
+ "gusto",
35
+ "habang",
36
+ "hanggang",
37
+ "hindi",
38
+ "huwag",
39
+ "iba",
40
+ "ibaba",
41
+ "ibabaw",
42
+ "ibig",
43
+ "ikaw",
44
+ "ilagay",
45
+ "ilalim",
46
+ "ilan",
47
+ "inyong",
48
+ "isa",
49
+ "isang",
50
+ "itaas",
51
+ "ito",
52
+ "iyo",
53
+ "iyon",
54
+ "iyong",
55
+ "ka",
56
+ "kahit",
57
+ "kailangan",
58
+ "kailanman",
59
+ "kami",
60
+ "kanila",
61
+ "kanilang",
62
+ "kanino",
63
+ "kanya",
64
+ "kanyang",
65
+ "kapag",
66
+ "kapwa",
67
+ "karamihan",
68
+ "katiyakan",
69
+ "katulad",
70
+ "kaya",
71
+ "kaysa",
72
+ "ko",
73
+ "kong",
74
+ "kulang",
75
+ "kumuha",
76
+ "kung",
77
+ "laban",
78
+ "lahat",
79
+ "lamang",
80
+ "likod",
81
+ "lima",
82
+ "maaari",
83
+ "maaaring",
84
+ "maging",
85
+ "mahusay",
86
+ "makita",
87
+ "marami",
88
+ "marapat",
89
+ "masyado",
90
+ "may",
91
+ "mayroon",
92
+ "mga",
93
+ "minsan",
94
+ "mismo",
95
+ "mula",
96
+ "muli",
97
+ "na",
98
+ "nabanggit",
99
+ "naging",
100
+ "nagkaroon",
101
+ "nais",
102
+ "nakita",
103
+ "namin",
104
+ "napaka",
105
+ "narito",
106
+ "nasaan",
107
+ "ng",
108
+ "ngayon",
109
+ "ni",
110
+ "nila",
111
+ "nilang",
112
+ "nito",
113
+ "niya",
114
+ "niyang",
115
+ "noon",
116
+ "o",
117
+ "pa",
118
+ "paano",
119
+ "pababa",
120
+ "paggawa",
121
+ "pagitan",
122
+ "pagkakaroon",
123
+ "pagkatapos",
124
+ "palabas",
125
+ "pamamagitan",
126
+ "panahon",
127
+ "pangalawa",
128
+ "para",
129
+ "paraan",
130
+ "pareho",
131
+ "pataas",
132
+ "pero",
133
+ "pumunta",
134
+ "pumupunta",
135
+ "sa",
136
+ "saan",
137
+ "sabi",
138
+ "sabihin",
139
+ "sarili",
140
+ "sila",
141
+ "sino",
142
+ "siya",
143
+ "tatlo",
144
+ "tayo",
145
+ "tulad",
146
+ "tungkol",
147
+ "una",
148
+ "walang"
149
+ ]