simplify language lookup

main
Simon Aubury 2023-02-09 16:26:22 +11:00
rodzic d027287829
commit f2cbab1237
4 zmienionych plików z 405 dodań i 88 usunięć

2
.gitignore vendored
Wyświetl plik

@ -5,3 +5,5 @@ BAK
data/*
config/mastodon-sink-s3-aws.json
notebooks/demo.ipynb
duckdb/init-s3.sql
data_tmp/*

Wyświetl plik

@ -42,6 +42,8 @@ select 'epoch'::TIMESTAMP + INTERVAL 1675325510 seconds;
# AWS
```
aws s3 ls s3://2023mastodon --recursive --human-readable --summarize | tail
aws s3 cp s3://2023mastodon . --recursive --exclude "*" --include "*.parquet"
```
# OLD Notes

229
duckdb/language.csv 100644
Wyświetl plik

@ -0,0 +1,229 @@
lang_iso,language_name
af,Afrikaans
af-ZA,Afrikaans (South Africa)
ar,Arabic
ar-AE,Arabic (U.A.E.)
ar-BH,Arabic (Bahrain)
ar-DZ,Arabic (Algeria)
ar-EG,Arabic (Egypt)
ar-IQ,Arabic (Iraq)
ar-JO,Arabic (Jordan)
ar-KW,Arabic (Kuwait)
ar-LB,Arabic (Lebanon)
ar-LY,Arabic (Libya)
ar-MA,Arabic (Morocco)
ar-OM,Arabic (Oman)
ar-QA,Arabic (Qatar)
ar-SA,Arabic (Saudi Arabia)
ar-SY,Arabic (Syria)
ar-TN,Arabic (Tunisia)
ar-YE,Arabic (Yemen)
az,Azeri (Latin)
az-AZ,Azeri (Latin) (Azerbaijan)
be,Belarusian
be-BY,Belarusian (Belarus)
bg,Bulgarian
bg-BG,Bulgarian (Bulgaria)
bs-BA,Bosnian (Bosnia and Herzegovina)
ca,Catalan
ca-ES,Catalan (Spain)
cs,Czech
cs-CZ,Czech (Czech Republic)
cy,Welsh
cy-GB,Welsh (United Kingdom)
da,Danish
da-DK,Danish (Denmark)
de,German
de-AT,German (Austria)
de-CH,German (Switzerland)
de-DE,German (Germany)
de-LI,German (Liechtenstein)
de-LU,German (Luxembourg)
dv,Divehi
dv-MV,Divehi (Maldives)
el,Greek
el-GR,Greek (Greece)
en,English
en-AU,English (Australia)
en-BZ,English (Belize)
en-CA,English (Canada)
en-CB,English (Caribbean)
en-GB,English (United Kingdom)
en-IE,English (Ireland)
en-JM,English (Jamaica)
en-NZ,English (New Zealand)
en-PH,English (Republic of the Philippines)
en-TT,English (Trinidad and Tobago)
en-US,English (United States)
en-ZA,English (South Africa)
en-ZW,English (Zimbabwe)
eo,Esperanto
es,Spanish
es-AR,Spanish (Argentina)
es-BO,Spanish (Bolivia)
es-CL,Spanish (Chile)
es-CO,Spanish (Colombia)
es-CR,Spanish (Costa Rica)
es-DO,Spanish (Dominican Republic)
es-EC,Spanish (Ecuador)
es-ES,Spanish (Spain)
es-GT,Spanish (Guatemala)
es-HN,Spanish (Honduras)
es-MX,Spanish (Mexico)
es-NI,Spanish (Nicaragua)
es-PA,Spanish (Panama)
es-PE,Spanish (Peru)
es-PR,Spanish (Puerto Rico)
es-PY,Spanish (Paraguay)
es-SV,Spanish (El Salvador)
es-UY,Spanish (Uruguay)
es-VE,Spanish (Venezuela)
et,Estonian
et-EE,Estonian (Estonia)
eu,Basque
eu-ES,Basque (Spain)
fa,Farsi
fa-IR,Farsi (Iran)
fi,Finnish
fi-FI,Finnish (Finland)
fo,Faroese
fo-FO,Faroese (Faroe Islands)
fr,French
fr-BE,French (Belgium)
fr-CA,French (Canada)
fr-CH,French (Switzerland)
fr-FR,French (France)
fr-LU,French (Luxembourg)
fr-MC,French (Principality of Monaco)
gl,Galician
gl-ES,Galician (Spain)
gu,Gujarati
gu-IN,Gujarati (India)
he,Hebrew
he-IL,Hebrew (Israel)
hi,Hindi
hi-IN,Hindi (India)
hr,Croatian
hr-BA,Croatian (Bosnia and Herzegovina)
hr-HR,Croatian (Croatia)
hu,Hungarian
hu-HU,Hungarian (Hungary)
hy,Armenian
hy-AM,Armenian (Armenia)
id,Indonesian
id-ID,Indonesian (Indonesia)
is,Icelandic
is-IS,Icelandic (Iceland)
it,Italian
it-CH,Italian (Switzerland)
it-IT,Italian (Italy)
ja,Japanese
ja-JP,Japanese (Japan)
ka,Georgian
ka-GE,Georgian (Georgia)
kk,Kazakh
kk-KZ,Kazakh (Kazakhstan)
kn,Kannada
kn-IN,Kannada (India)
ko,Korean
ko-KR,Korean (Korea)
kok,Konkani
kok-IN,Konkani (India)
ky,Kyrgyz
ky-KG,Kyrgyz (Kyrgyzstan)
lt,Lithuanian
lt-LT,Lithuanian (Lithuania)
lv,Latvian
lv-LV,Latvian (Latvia)
mi,Maori
mi-NZ,Maori (New Zealand)
mk,FYRO Macedonian
mk-MK,FYRO Macedonian (Former Yugoslav Republic of Macedonia)
mn,Mongolian
mn-MN,Mongolian (Mongolia)
mr,Marathi
mr-IN,Marathi (India)
ms,Malay
ms-BN,Malay (Brunei Darussalam)
ms-MY,Malay (Malaysia)
mt,Maltese
mt-MT,Maltese (Malta)
nb,Norwegian (Bokm?l)
nb-NO,Norwegian (Bokm?l) (Norway)
nl,Dutch
nl-BE,Dutch (Belgium)
nl-NL,Dutch (Netherlands)
nn-NO,Norwegian (Nynorsk) (Norway)
ns,Northern Sotho
ns-ZA,Northern Sotho (South Africa)
pa,Punjabi
pa-IN,Punjabi (India)
pl,Polish
pl-PL,Polish (Poland)
ps,Pashto
ps-AR,Pashto (Afghanistan)
pt,Portuguese
pt-BR,Portuguese (Brazil)
pt-PT,Portuguese (Portugal)
qu,Quechua
qu-BO,Quechua (Bolivia)
qu-EC,Quechua (Ecuador)
qu-PE,Quechua (Peru)
ro,Romanian
ro-RO,Romanian (Romania)
ru,Russian
ru-RU,Russian (Russia)
sa,Sanskrit
sa-IN,Sanskrit (India)
se,Sami (Northern)
se-FI,Sami (Skolt) (Finland)
se-NO,Sami (Southern) (Norway)
se-SE,Sami (Southern) (Sweden)
sk,Slovak
sk-SK,Slovak (Slovakia)
sl,Slovenian
sl-SI,Slovenian (Slovenia)
sq,Albanian
sq-AL,Albanian (Albania)
sr-BA,Serbian (Latin) (Bosnia and Herzegovina)
sr-SP,Serbian (Latin) (Serbia and Montenegro)
sv,Swedish
sv-FI,Swedish (Finland)
sv-SE,Swedish (Sweden)
sw,Swahili
sw-KE,Swahili (Kenya)
syr,Syriac
syr-SY,Syriac (Syria)
ta,Tamil
ta-IN,Tamil (India)
te,Telugu
te-IN,Telugu (India)
th,Thai
th-TH,Thai (Thailand)
tl,Tagalog
tl-PH,Tagalog (Philippines)
tn,Tswana
tn-ZA,Tswana (South Africa)
tr,Turkish
tr-TR,Turkish (Turkey)
ts,Tsonga
tt,Tatar
tt-RU,Tatar (Russia)
uk,Ukrainian
uk-UA,Ukrainian (Ukraine)
ur,Urdu
ur-PK,Urdu (Islamic Republic of Pakistan)
uz,Uzbek (Latin)
uz-UZ,Uzbek (Latin) (Uzbekistan)
vi,Vietnamese
vi-VN,Vietnamese (Viet Nam)
xh,Xhosa
xh-ZA,Xhosa (South Africa)
zh,Chinese
zh-CN,Chinese (S)
zh-HK,Chinese (Hong Kong)
zh-MO,Chinese (Macau)
zh-SG,Chinese (Singapore)
zh-TW,Chinese (T)
zu,Zulu
zu-ZA,Zulu (South Africa)
1 lang_iso language_name
2 af Afrikaans
3 af-ZA Afrikaans (South Africa)
4 ar Arabic
5 ar-AE Arabic (U.A.E.)
6 ar-BH Arabic (Bahrain)
7 ar-DZ Arabic (Algeria)
8 ar-EG Arabic (Egypt)
9 ar-IQ Arabic (Iraq)
10 ar-JO Arabic (Jordan)
11 ar-KW Arabic (Kuwait)
12 ar-LB Arabic (Lebanon)
13 ar-LY Arabic (Libya)
14 ar-MA Arabic (Morocco)
15 ar-OM Arabic (Oman)
16 ar-QA Arabic (Qatar)
17 ar-SA Arabic (Saudi Arabia)
18 ar-SY Arabic (Syria)
19 ar-TN Arabic (Tunisia)
20 ar-YE Arabic (Yemen)
21 az Azeri (Latin)
22 az-AZ Azeri (Latin) (Azerbaijan)
23 be Belarusian
24 be-BY Belarusian (Belarus)
25 bg Bulgarian
26 bg-BG Bulgarian (Bulgaria)
27 bs-BA Bosnian (Bosnia and Herzegovina)
28 ca Catalan
29 ca-ES Catalan (Spain)
30 cs Czech
31 cs-CZ Czech (Czech Republic)
32 cy Welsh
33 cy-GB Welsh (United Kingdom)
34 da Danish
35 da-DK Danish (Denmark)
36 de German
37 de-AT German (Austria)
38 de-CH German (Switzerland)
39 de-DE German (Germany)
40 de-LI German (Liechtenstein)
41 de-LU German (Luxembourg)
42 dv Divehi
43 dv-MV Divehi (Maldives)
44 el Greek
45 el-GR Greek (Greece)
46 en English
47 en-AU English (Australia)
48 en-BZ English (Belize)
49 en-CA English (Canada)
50 en-CB English (Caribbean)
51 en-GB English (United Kingdom)
52 en-IE English (Ireland)
53 en-JM English (Jamaica)
54 en-NZ English (New Zealand)
55 en-PH English (Republic of the Philippines)
56 en-TT English (Trinidad and Tobago)
57 en-US English (United States)
58 en-ZA English (South Africa)
59 en-ZW English (Zimbabwe)
60 eo Esperanto
61 es Spanish
62 es-AR Spanish (Argentina)
63 es-BO Spanish (Bolivia)
64 es-CL Spanish (Chile)
65 es-CO Spanish (Colombia)
66 es-CR Spanish (Costa Rica)
67 es-DO Spanish (Dominican Republic)
68 es-EC Spanish (Ecuador)
69 es-ES Spanish (Spain)
70 es-GT Spanish (Guatemala)
71 es-HN Spanish (Honduras)
72 es-MX Spanish (Mexico)
73 es-NI Spanish (Nicaragua)
74 es-PA Spanish (Panama)
75 es-PE Spanish (Peru)
76 es-PR Spanish (Puerto Rico)
77 es-PY Spanish (Paraguay)
78 es-SV Spanish (El Salvador)
79 es-UY Spanish (Uruguay)
80 es-VE Spanish (Venezuela)
81 et Estonian
82 et-EE Estonian (Estonia)
83 eu Basque
84 eu-ES Basque (Spain)
85 fa Farsi
86 fa-IR Farsi (Iran)
87 fi Finnish
88 fi-FI Finnish (Finland)
89 fo Faroese
90 fo-FO Faroese (Faroe Islands)
91 fr French
92 fr-BE French (Belgium)
93 fr-CA French (Canada)
94 fr-CH French (Switzerland)
95 fr-FR French (France)
96 fr-LU French (Luxembourg)
97 fr-MC French (Principality of Monaco)
98 gl Galician
99 gl-ES Galician (Spain)
100 gu Gujarati
101 gu-IN Gujarati (India)
102 he Hebrew
103 he-IL Hebrew (Israel)
104 hi Hindi
105 hi-IN Hindi (India)
106 hr Croatian
107 hr-BA Croatian (Bosnia and Herzegovina)
108 hr-HR Croatian (Croatia)
109 hu Hungarian
110 hu-HU Hungarian (Hungary)
111 hy Armenian
112 hy-AM Armenian (Armenia)
113 id Indonesian
114 id-ID Indonesian (Indonesia)
115 is Icelandic
116 is-IS Icelandic (Iceland)
117 it Italian
118 it-CH Italian (Switzerland)
119 it-IT Italian (Italy)
120 ja Japanese
121 ja-JP Japanese (Japan)
122 ka Georgian
123 ka-GE Georgian (Georgia)
124 kk Kazakh
125 kk-KZ Kazakh (Kazakhstan)
126 kn Kannada
127 kn-IN Kannada (India)
128 ko Korean
129 ko-KR Korean (Korea)
130 kok Konkani
131 kok-IN Konkani (India)
132 ky Kyrgyz
133 ky-KG Kyrgyz (Kyrgyzstan)
134 lt Lithuanian
135 lt-LT Lithuanian (Lithuania)
136 lv Latvian
137 lv-LV Latvian (Latvia)
138 mi Maori
139 mi-NZ Maori (New Zealand)
140 mk FYRO Macedonian
141 mk-MK FYRO Macedonian (Former Yugoslav Republic of Macedonia)
142 mn Mongolian
143 mn-MN Mongolian (Mongolia)
144 mr Marathi
145 mr-IN Marathi (India)
146 ms Malay
147 ms-BN Malay (Brunei Darussalam)
148 ms-MY Malay (Malaysia)
149 mt Maltese
150 mt-MT Maltese (Malta)
151 nb Norwegian (Bokm?l)
152 nb-NO Norwegian (Bokm?l) (Norway)
153 nl Dutch
154 nl-BE Dutch (Belgium)
155 nl-NL Dutch (Netherlands)
156 nn-NO Norwegian (Nynorsk) (Norway)
157 ns Northern Sotho
158 ns-ZA Northern Sotho (South Africa)
159 pa Punjabi
160 pa-IN Punjabi (India)
161 pl Polish
162 pl-PL Polish (Poland)
163 ps Pashto
164 ps-AR Pashto (Afghanistan)
165 pt Portuguese
166 pt-BR Portuguese (Brazil)
167 pt-PT Portuguese (Portugal)
168 qu Quechua
169 qu-BO Quechua (Bolivia)
170 qu-EC Quechua (Ecuador)
171 qu-PE Quechua (Peru)
172 ro Romanian
173 ro-RO Romanian (Romania)
174 ru Russian
175 ru-RU Russian (Russia)
176 sa Sanskrit
177 sa-IN Sanskrit (India)
178 se Sami (Northern)
179 se-FI Sami (Skolt) (Finland)
180 se-NO Sami (Southern) (Norway)
181 se-SE Sami (Southern) (Sweden)
182 sk Slovak
183 sk-SK Slovak (Slovakia)
184 sl Slovenian
185 sl-SI Slovenian (Slovenia)
186 sq Albanian
187 sq-AL Albanian (Albania)
188 sr-BA Serbian (Latin) (Bosnia and Herzegovina)
189 sr-SP Serbian (Latin) (Serbia and Montenegro)
190 sv Swedish
191 sv-FI Swedish (Finland)
192 sv-SE Swedish (Sweden)
193 sw Swahili
194 sw-KE Swahili (Kenya)
195 syr Syriac
196 syr-SY Syriac (Syria)
197 ta Tamil
198 ta-IN Tamil (India)
199 te Telugu
200 te-IN Telugu (India)
201 th Thai
202 th-TH Thai (Thailand)
203 tl Tagalog
204 tl-PH Tagalog (Philippines)
205 tn Tswana
206 tn-ZA Tswana (South Africa)
207 tr Turkish
208 tr-TR Turkish (Turkey)
209 ts Tsonga
210 tt Tatar
211 tt-RU Tatar (Russia)
212 uk Ukrainian
213 uk-UA Ukrainian (Ukraine)
214 ur Urdu
215 ur-PK Urdu (Islamic Republic of Pakistan)
216 uz Uzbek (Latin)
217 uz-UZ Uzbek (Latin) (Uzbekistan)
218 vi Vietnamese
219 vi-VN Vietnamese (Viet Nam)
220 xh Xhosa
221 xh-ZA Xhosa (South Africa)
222 zh Chinese
223 zh-CN Chinese (S)
224 zh-HK Chinese (Hong Kong)
225 zh-MO Chinese (Macau)
226 zh-SG Chinese (Singapore)
227 zh-TW Chinese (T)
228 zu Zulu
229 zu-ZA Zulu (South Africa)

File diff suppressed because one or more lines are too long