xcc.es
[READ-ONLY] Mirror of https://github.com/mrgnw/ananas. learn multiple languages at once
ananas.xcc.es
1SELECT DISTINCT ?iso ?iso1 ?langLabel
2 (FLOOR(MAX(?nativeSpeakers_) / 1000) as ?nativeSpeakers_k)
3 (GROUP_CONCAT(DISTINCT ?writingSystemLabel; separator=", ") as ?writingSystems)
4 (GROUP_CONCAT(DISTINCT ?countryLabel; separator="|") as ?countries)
5 (MIN(STRAFTER(STR(?unescoStatus), "Q")) as ?unescoStatus)
6 (MIN(STRAFTER(STR(?ethnologueStatus), "Q")) as ?ethnologueStatus)
7 (GROUP_CONCAT(DISTINCT ?nativeName; separator=", ") as ?nativeNames)
8 (MAX(?isRTL) as ?rtl)
9WHERE {
10 # Core data
11 ?lang wdt:P220 ?iso ;
12 wdt:P1098 ?nativeSpeakers_ ;
13 rdfs:label ?langLabel .
14 FILTER(LANG(?langLabel) = "en")
15 FILTER(?nativeSpeakers_ >= 1000000)
16
17 # ISO 639-1 code (optional)
18 OPTIONAL { ?lang wdt:P218 ?iso1 }
19
20 # Optional data
21 OPTIONAL {
22 ?lang wdt:P282 ?writingSystem .
23 ?writingSystem rdfs:label ?writingSystemLabel .
24 FILTER(LANG(?writingSystemLabel) = "en")
25 }
26 OPTIONAL {
27 ?lang wdt:P17 ?country .
28 ?country rdfs:label ?countryLabel .
29 FILTER(LANG(?countryLabel) = "en")
30 }
31
32 # RTL detection based on writing system
33 OPTIONAL {
34 ?lang wdt:P282 ?writingSystem .
35 VALUES ?rtlSystem {
36 wd:Q8196 # Arabic script
37 wd:Q9288 # Hebrew alphabet
38 wd:Q28564 # Persian alphabet
39 wd:Q47577 # N'Ko script
40 wd:Q1137511 # Mandaic alphabet
41 wd:Q1137469 # Samaritan script
42 wd:Q1137466 # Syriac alphabet
43 }
44 BIND(IF(?writingSystem = ?rtlSystem, true, false) as ?isRTL)
45 }
46
47 # Status and names
48 OPTIONAL { ?lang wdt:P1999 ?unescoStatus }
49 OPTIONAL { ?lang wdt:P3823 ?ethnologueStatus }
50 OPTIONAL { ?lang wdt:P1705 ?nativeName }
51}
52GROUP BY ?iso ?iso1 ?langLabel
53HAVING(MAX(?nativeSpeakers_) >= 1000000)
54ORDER BY DESC(MAX(?nativeSpeakers_)) ?iso
55LIMIT 200