Help
Difference between revisions of "SPARQL for maintenance"
SPARQL for maintenance gathers various SPARQL queries helping to monitors data inconsistencies on Lingualibre. When identified and depending on the quantity, manual or bot-lead fix can be edited onto those items. Bot request to add to Dragons_Bot.
(124 intermediate revisions by 2 users not shown) | |||
Line 1: | Line 1: | ||
− | {{#Subtitle:'''SPARQL for maintenance''' | + | {{#Subtitle:'''SPARQL for maintenance''' gathers various SPARQL queries helping to monitors data inconsistencies on Lingualibre. When identified and depending on the quantity, manual or bot-lead fix can be edited onto those items. Bot request to add to [https://lingualibre.org/wiki/User_talk:Dragons_Bot Dragons_Bot].}} |
== Speakers == | == Speakers == | ||
=== ✅ Speakers → Username containing reserved sign `<code>-</code>` === | === ✅ Speakers → Username containing reserved sign `<code>-</code>` === | ||
− | :''See also [[:phabricator:T297635|T297635]]'' | + | :''Lists declared speakers accounts, different from speakers account with 1+ recordings.'' |
+ | :''See also [[:phabricator:T297635|T297635]] : Lingualibre filename separator should be mass migrated from <code>-</code> to <code>—</code>, without breaking usernames nor words.'' | ||
{| style="width:100%" | {| style="width:100%" | ||
|- style="vertical-align:top;" | |- style="vertical-align:top;" | ||
|style="padding: 0 3em;width:60%"| | |style="padding: 0 3em;width:60%"| | ||
<syntaxhighlight lang="sparql"> | <syntaxhighlight lang="sparql"> | ||
+ | #defaultEndpoint:Lingualibre | ||
SELECT * | SELECT * | ||
WHERE { | WHERE { | ||
Line 15: | Line 17: | ||
?id rdfs:label ?name . | ?id rdfs:label ?name . | ||
} | } | ||
− | BIND (regex(STR(?name),"-") AS ? | + | BIND (regex(STR(?name),"-") AS ?has_fields_separator_in_username) |
} | } | ||
− | ORDER BY DESC (? | + | ORDER BY DESC (?has_fields_separator_in_username) |
</syntaxhighlight> | </syntaxhighlight> | ||
|| | || | ||
<query _pagination="5"> | <query _pagination="5"> | ||
+ | #defaultEndpoint:Lingualibre | ||
SELECT * | SELECT * | ||
WHERE { | WHERE { | ||
Line 28: | Line 31: | ||
?id rdfs:label ?name . | ?id rdfs:label ?name . | ||
} | } | ||
− | BIND (regex(STR(?name),"-") AS ? | + | BIND (regex(STR(?name),"-") AS ?has_fields_separator_in_username) |
} | } | ||
− | ORDER BY DESC (? | + | ORDER BY DESC (?has_fields_separator_in_username) |
</query> | </query> | ||
|} | |} | ||
Line 38: | Line 41: | ||
|style="padding: 0 3em;width:60%"| | |style="padding: 0 3em;width:60%"| | ||
<syntaxhighlight lang="sparql"> | <syntaxhighlight lang="sparql"> | ||
− | SELECT ? | + | #defaultEndpoint:Lingualibre |
+ | SELECT ?has_fields_separator_in_username (COUNT(?has_fields_separator_in_username) AS ?found) | ||
WHERE { | WHERE { | ||
?id prop:P2 entity:Q3 . | ?id prop:P2 entity:Q3 . | ||
Line 46: | Line 50: | ||
} | } | ||
− | BIND (regex(STR(?name),"-") AS ? | + | BIND (regex(STR(?name),"-") AS ?has_fields_separator_in_username) |
# filter( regex(?name, "-" )) | # filter( regex(?name, "-" )) | ||
} | } | ||
− | #ORDER BY DESC (? | + | #ORDER BY DESC (?has_fields_separator_in_username) |
− | GROUP BY (? | + | GROUP BY (?has_fields_separator_in_username) |
</syntaxhighlight> | </syntaxhighlight> | ||
|| | || | ||
<query _pagination="5"> | <query _pagination="5"> | ||
− | SELECT ? | + | #defaultEndpoint:Lingualibre |
+ | SELECT ?has_fields_separator_in_username (COUNT(?has_fields_separator_in_username) AS ?found) | ||
WHERE { | WHERE { | ||
?id prop:P2 entity:Q3 . | ?id prop:P2 entity:Q3 . | ||
Line 62: | Line 67: | ||
} | } | ||
− | BIND (regex(STR(?name),"-") AS ? | + | BIND (regex(STR(?name),"-") AS ?has_fields_separator_in_username) |
# filter( regex(?name, "-" )) | # filter( regex(?name, "-" )) | ||
} | } | ||
− | #ORDER BY DESC (? | + | #ORDER BY DESC (?has_fields_separator_in_username) |
− | GROUP BY (? | + | GROUP BY (?has_fields_separator_in_username) |
</query> | </query> | ||
|} | |} | ||
− | === ✅ | + | === ✅ Recordings → Gascon `Q930` recordings containing reserved sign `<code>-</code>` === |
+ | :''See also [[:phabricator:T297635|T297635]] : Lingualibre filename separator should be mass migrated from <code>-</code> to <code>—</code>, without breaking usernames nor words.'' | ||
+ | {| style="width:100%" | ||
+ | |- style="vertical-align:top;" | ||
+ | |style="padding: 0 3em;width:60%"| | ||
+ | <syntaxhighlight lang="sparql"> | ||
+ | #defaultEndpoint:Lingualibre | ||
+ | SELECT * | ||
+ | WHERE { | ||
+ | ?id prop:P2 entity:Q2 . | ||
+ | ?id prop:P4 entity:Q930 . | ||
+ | SERVICE wikibase:label { | ||
+ | bd:serviceParam wikibase:language "[AUTO_LANGUAGE],en" . | ||
+ | ?id rdfs:label ?name . | ||
+ | } | ||
+ | BIND (regex(STR(?name),"-") AS ?has_fields_separator_in_written_word) | ||
+ | } | ||
+ | ORDER BY DESC (?has_fields_separator_in_written_word) | ||
+ | </syntaxhighlight> | ||
+ | || | ||
+ | <query _pagination="5"> | ||
+ | #defaultEndpoint:Lingualibre | ||
+ | SELECT * | ||
+ | WHERE { | ||
+ | ?id prop:P2 entity:Q2 . | ||
+ | ?id prop:P4 entity:Q930 . | ||
+ | SERVICE wikibase:label { | ||
+ | bd:serviceParam wikibase:language "[AUTO_LANGUAGE],en" . | ||
+ | ?id rdfs:label ?name . | ||
+ | } | ||
+ | BIND (regex(STR(?name),"-") AS ?has_fields_separator_in_written_word) | ||
+ | } | ||
+ | ORDER BY DESC (?has_fields_separator_in_written_word) | ||
+ | </query> | ||
+ | |} | ||
+ | |||
+ | {| style="width:100%" | ||
+ | |- style="vertical-align:top;" | ||
+ | |style="padding: 0 3em;width:60%"| | ||
+ | <syntaxhighlight lang="sparql"> | ||
+ | #defaultEndpoint:Lingualibre | ||
+ | SELECT ?has_fields_separator_in_username (COUNT(?has_fields_separator_in_username) AS ?found) | ||
+ | WHERE { | ||
+ | ?id prop:P2 entity:Q2 . | ||
+ | ?id prop:P4 entity:Q930 . | ||
+ | SERVICE wikibase:label { | ||
+ | bd:serviceParam wikibase:language "[AUTO_LANGUAGE],en" . | ||
+ | ?id rdfs:label ?name . | ||
+ | } | ||
+ | BIND (regex(STR(?name),"-") AS ?has_fields_separator_in_written_word) | ||
+ | # filter( regex(?name, "-" )) | ||
+ | } | ||
+ | #ORDER BY DESC (?has_fields_separator_in_written_word) | ||
+ | GROUP BY (?has_fields_separator_in_written_word) | ||
+ | </syntaxhighlight> | ||
+ | || | ||
+ | <query _pagination="5"> | ||
+ | #defaultEndpoint:Lingualibre | ||
+ | SELECT ?has_fields_separator_in_username (COUNT(?has_fields_separator_in_username) AS ?found) | ||
+ | WHERE { | ||
+ | ?id prop:P2 entity:Q2 . | ||
+ | ?id prop:P4 entity:Q930 . | ||
+ | SERVICE wikibase:label { | ||
+ | bd:serviceParam wikibase:language "[AUTO_LANGUAGE],en" . | ||
+ | ?id rdfs:label ?name . | ||
+ | } | ||
+ | |||
+ | BIND (regex(STR(?name),"-") AS ?has_fields_separator_in_written_word) | ||
+ | # filter( regex(?name, "-" )) | ||
+ | } | ||
+ | #ORDER BY DESC (?has_fields_separator_in_written_word) | ||
+ | GROUP BY (?has_fields_separator_in_written_word) | ||
+ | </query> | ||
+ | |} | ||
+ | |||
+ | === ✅ Speakers → Speakers of obsolete languages === | ||
:''Should be maintained to 0.'' | :''Should be maintained to 0.'' | ||
{| style="width:100%" | {| style="width:100%" | ||
Line 76: | Line 156: | ||
|style="padding: 0 3em;width:60%"| | |style="padding: 0 3em;width:60%"| | ||
<syntaxhighlight lang="sparql"> | <syntaxhighlight lang="sparql"> | ||
− | SELECT | + | #defaultEndpoint:Lingualibre |
+ | SELECT ?speaker ?speakerLabel | ||
WHERE { | WHERE { | ||
− | ? | + | # Obsolete languages items (duplicata and redirects) |
− | ?speaker prop:P2 entity:Q3 . | + | # Chinese Q130 → Q113 |
− | ?speaker prop:P4 ? | + | # Mossi Q170137 → Q359 |
− | + | # Duala Q52071 → Q73 | |
+ | VALUES ?i18nQid { entity:Q130 entity:Q170137 entity:Q52071 } | ||
+ | ?speaker prop:P2 entity:Q3 . # Filter: audios | ||
+ | ?speaker prop:P4 ?i18nQid . # Filter: P4 language is Q130/Q170137/Q52071 ; | ||
# Add Labels | # Add Labels | ||
SERVICE wikibase:label { bd:serviceParam wikibase:language "[AUTO_LANGUAGE],en" . } | SERVICE wikibase:label { bd:serviceParam wikibase:language "[AUTO_LANGUAGE],en" . } | ||
− | } | + | } |
− | |||
</syntaxhighlight> | </syntaxhighlight> | ||
|| | || | ||
<query _pagination="5"> | <query _pagination="5"> | ||
− | SELECT | + | #defaultEndpoint:Lingualibre |
+ | SELECT ?speaker ?speakerLabel | ||
WHERE { | WHERE { | ||
− | ? | + | # Obsolete languages items (duplicata and redirects) |
− | ?speaker prop:P2 entity:Q3 . | + | # Chinese Q130 → Q113 |
− | ?speaker prop:P4 ? | + | # Mossi Q170137 → Q359 |
− | + | # Duala Q52071 → Q73 | |
+ | VALUES ?i18nQid { entity:Q130 entity:Q170137 entity:Q52071 } | ||
+ | ?speaker prop:P2 entity:Q3 . # Filter: audios | ||
+ | ?speaker prop:P4 ?i18nQid . # Filter: P4 language is Q130/Q170137/Q52071 ; | ||
# Add Labels | # Add Labels | ||
SERVICE wikibase:label { bd:serviceParam wikibase:language "[AUTO_LANGUAGE],en" . } | SERVICE wikibase:label { bd:serviceParam wikibase:language "[AUTO_LANGUAGE],en" . } | ||
− | } | + | } |
− | |||
</query> | </query> | ||
|} | |} | ||
=== ✅ Speakers → Undefined place of residence === | === ✅ Speakers → Undefined place of residence === | ||
− | :''The following may need precision.'' | + | :''The following may need precision. If stale, it mean none was found.'' |
+ | |||
+ | {| style="width:100%" | ||
+ | |- style="vertical-align:top;" | ||
+ | |style="padding: 0 3em;width:60%"| | ||
+ | <syntaxhighlight lang="sparql"> | ||
+ | #defaultEndpoint:Lingualibre | ||
+ | SELECT ?speaker ?speakerLabel ?localisationLabel ?languageLabel (COUNT(?audio) AS ?audio) | ||
+ | WHERE { | ||
+ | ?speaker prop:P2 entity:Q3 . | ||
+ | FILTER NOT EXISTS { ?speaker prop:P14 ?localisation } | ||
+ | ?audio prop:P5 ?speaker . # Filter: P5 'speaker' is Q445757 'SangeetaRH' | ||
+ | ?audio prop:P4 ?language . # Filter: P4 'language' is Q34 'Marathi' | ||
+ | # Add labels | ||
+ | SERVICE wikibase:label {bd:serviceParam wikibase:language "[AUTO_LANGUAGE],en"} | ||
+ | } | ||
+ | GROUP BY ?speaker ?speakerLabel ?localisationLabel ?languageLabel # Sorting first groups per language and speaker | ||
+ | ORDER BY DESC (?audio) | ||
+ | </syntaxhighlight> | ||
+ | | | ||
+ | <query _pagination="6"> | ||
+ | #defaultEndpoint:Lingualibre | ||
+ | SELECT ?speaker ?speakerLabel ?localisationLabel ?languageLabel (COUNT(?audio) AS ?audio) | ||
+ | WHERE { | ||
+ | ?speaker prop:P2 entity:Q3 . | ||
+ | FILTER NOT EXISTS { ?speaker prop:P14 ?localisation } | ||
+ | ?audio prop:P5 ?speaker . # Filter: P5 'speaker' is Q445757 'SangeetaRH' | ||
+ | ?audio prop:P4 ?language . # Filter: P4 'language' is Q34 'Marathi' | ||
+ | # Add labels | ||
+ | SERVICE wikibase:label {bd:serviceParam wikibase:language "[AUTO_LANGUAGE],en"} | ||
+ | } | ||
+ | GROUP BY ?speaker ?speakerLabel ?localisationLabel ?languageLabel # Sorting first groups per language and speaker | ||
+ | ORDER BY DESC (?audio) | ||
+ | </query> | ||
+ | |} | ||
+ | |||
{| style="width:100%" | {| style="width:100%" | ||
|- style="vertical-align:top;" | |- style="vertical-align:top;" | ||
|style="padding: 0 3em;width:60%"| | |style="padding: 0 3em;width:60%"| | ||
<syntaxhighlight lang="sparql"> | <syntaxhighlight lang="sparql"> | ||
− | SELECT ? | + | #defaultEndpoint:Lingualibre |
+ | SELECT ?type (COUNT(DISTINCT ?user) AS ?users) | ||
WHERE { | WHERE { | ||
?item prop:P2 entity:Q3 . # Filter: is Q3 `speaker` | ?item prop:P2 entity:Q3 . # Filter: is Q3 `speaker` | ||
− | ?item prop: | + | ?item prop:P2 ?type . |
+ | ?item prop:P11 ?user . | ||
+ | FILTER NOT EXISTS { ?item prop:P14 []. } | ||
# Add labels to each variable used. | # Add labels to each variable used. | ||
− | SERVICE wikibase:label { | + | SERVICE wikibase:label { bd:serviceParam wikibase:language "fr,en". } |
− | + | } GROUP BY ?type | |
− | |||
− | } | ||
</syntaxhighlight> | </syntaxhighlight> | ||
| | | | ||
− | <query _pagination="6 | + | <query _pagination="6"> |
− | SELECT ? | + | #defaultEndpoint:Lingualibre |
+ | SELECT ?type (COUNT(DISTINCT ?user) AS ?users) | ||
WHERE { | WHERE { | ||
?item prop:P2 entity:Q3 . # Filter: is Q3 `speaker` | ?item prop:P2 entity:Q3 . # Filter: is Q3 `speaker` | ||
− | ?item prop: | + | ?item prop:P2 ?type . |
+ | ?item prop:P11 ?user . | ||
+ | FILTER NOT EXISTS { ?item prop:P14 []. } | ||
# Add labels to each variable used. | # Add labels to each variable used. | ||
− | SERVICE wikibase:label { | + | SERVICE wikibase:label { bd:serviceParam wikibase:language "fr,en". } |
− | + | } GROUP BY ?type | |
− | |||
− | } | ||
</query> | </query> | ||
|} | |} | ||
− | |||
=== ✅ Speakers → Non-documented genders values === | === ✅ Speakers → Non-documented genders values === | ||
Line 139: | Line 261: | ||
|style="padding: 0 3em;width:60%"| | |style="padding: 0 3em;width:60%"| | ||
<syntaxhighlight lang="sparql"> | <syntaxhighlight lang="sparql"> | ||
+ | #defaultEndpoint:Lingualibre | ||
SELECT ?item ?itemLabel ?filledGenderLabel | SELECT ?item ?itemLabel ?filledGenderLabel | ||
WHERE { | WHERE { | ||
Line 152: | Line 275: | ||
| | | | ||
<query _pagination="6" item="Property" itemLabel="Values"> | <query _pagination="6" item="Property" itemLabel="Values"> | ||
+ | #defaultEndpoint:Lingualibre | ||
SELECT ?item ?itemLabel ?filledGenderLabel | SELECT ?item ?itemLabel ?filledGenderLabel | ||
WHERE { | WHERE { | ||
Line 173: | Line 297: | ||
|style="padding: 0 3em;width:60%"| | |style="padding: 0 3em;width:60%"| | ||
<syntaxhighlight lang="sparql"> | <syntaxhighlight lang="sparql"> | ||
− | SELECT ?speaker ?speakerLabel ? | + | #defaultEndpoint:Lingualibre |
+ | SELECT ?speaker ?speakerLabel ?genderLabel ?languageLabel (COUNT(?audio) AS ?audio) | ||
WHERE { | WHERE { | ||
?speaker prop:P2 entity:Q3 . | ?speaker prop:P2 entity:Q3 . | ||
Line 187: | Line 312: | ||
| | | | ||
<query _pagination="6" item="Property" itemLabel="Values"> | <query _pagination="6" item="Property" itemLabel="Values"> | ||
+ | #defaultEndpoint:Lingualibre | ||
SELECT ?speaker ?speakerLabel ?genderLabel ?languageLabel (COUNT(?audio) AS ?audio) | SELECT ?speaker ?speakerLabel ?genderLabel ?languageLabel (COUNT(?audio) AS ?audio) | ||
WHERE { | WHERE { | ||
Line 202: | Line 328: | ||
== Recordings == | == Recordings == | ||
− | === ✅ Recordings → With | + | === ✅ Recordings → With language `P4` as <code>Chinese writing</code> `Q130` to change to <code>cmn</code> `Q113` === |
+ | :''✅ Users linguistic profile has been corrected into Q359. Erroneous recordings language (P4) on Lingualibre, while Commons use correct Wikidata language Qid.'' | ||
{| style="width:100%" | {| style="width:100%" | ||
|- style="vertical-align:top;" | |- style="vertical-align:top;" | ||
|style="padding: 0 3em;width:60%"| | |style="padding: 0 3em;width:60%"| | ||
<syntaxhighlight lang="sparql"> | <syntaxhighlight lang="sparql"> | ||
− | SELECT ?langLabel ?isoLabel | + | #defaultEndpoint:Lingualibre |
+ | SELECT ?langLabel ?isoLabel ?speaker ?speakerLabel ?audio ?audioLabel | ||
WHERE { | WHERE { | ||
?audio prop:P4 entity:Q130 . # Filter: P4 language is Q130 zho ; | ?audio prop:P4 entity:Q130 . # Filter: P4 language is Q130 zho ; | ||
?audio prop:P2 entity:Q2 . # Filter: audios | ?audio prop:P2 entity:Q2 . # Filter: audios | ||
?audio prop:P4 ?lang . | ?audio prop:P4 ?lang . | ||
+ | ?audio prop:P5 ?speaker . | ||
?lang prop:P13 ?iso . | ?lang prop:P13 ?iso . | ||
# Add Labels | # Add Labels | ||
Line 220: | Line 349: | ||
|| | || | ||
<query _pagination="5"> | <query _pagination="5"> | ||
− | SELECT ?langLabel ?isoLabel | + | #defaultEndpoint:Lingualibre |
+ | SELECT ?langLabel ?isoLabel ?speaker ?speakerLabel ?audio ?audioLabel | ||
WHERE { | WHERE { | ||
?audio prop:P4 entity:Q130 . # Filter: P4 language is Q130 zho ; | ?audio prop:P4 entity:Q130 . # Filter: P4 language is Q130 zho ; | ||
?audio prop:P2 entity:Q2 . # Filter: audios | ?audio prop:P2 entity:Q2 . # Filter: audios | ||
?audio prop:P4 ?lang . | ?audio prop:P4 ?lang . | ||
+ | ?audio prop:P5 ?speaker . | ||
?lang prop:P13 ?iso . | ?lang prop:P13 ?iso . | ||
# Add Labels | # Add Labels | ||
Line 238: | Line 369: | ||
|style="padding: 0 3em;width:60%"| | |style="padding: 0 3em;width:60%"| | ||
<syntaxhighlight lang="sparql"> | <syntaxhighlight lang="sparql"> | ||
+ | #defaultEndpoint:Lingualibre | ||
SELECT ?isoLabel (COUNT(?iso) AS ?found) | SELECT ?isoLabel (COUNT(?iso) AS ?found) | ||
WHERE { | WHERE { | ||
Line 251: | Line 383: | ||
|| | || | ||
<query _pagination="5"> | <query _pagination="5"> | ||
+ | #defaultEndpoint:Lingualibre | ||
SELECT ?isoLabel (COUNT(?iso) AS ?found) | SELECT ?isoLabel (COUNT(?iso) AS ?found) | ||
WHERE { | WHERE { | ||
Line 264: | Line 397: | ||
|} | |} | ||
+ | === [?] Recordings → With with corrupted information === | ||
+ | :''✅ Users linguistic profile has been corrected.'' | ||
+ | {| style="width:100%" | ||
+ | |- style="vertical-align:top;" | ||
+ | |style="padding: 0 3em;width:60%"| | ||
+ | <syntaxhighlight lang="sparql"> | ||
+ | #defaultEndpoint:Lingualibre | ||
+ | SELECT ?lang | ||
+ | (SUBSTR(STR(?speaker),32) AS ?SpeakerQid) ?speakerLabel | ||
+ | ?audio ?audioLabel | ||
+ | ?url (SUBSTR(STR(?urlLabel),52) AS ?filename) | ||
+ | WHERE { | ||
+ | # Obsolete languages items (duplicata and redirects) | ||
+ | # Chinese Q130 → Q113 | ||
+ | # Mossi Q170137 → Q359 | ||
+ | # Duala Q52071 → Q73 | ||
+ | VALUES ?i18nQid { entity:Q130 entity:Q170137 entity:Q52071 } | ||
+ | |||
+ | { ?audio prop:P4 ?i18nQid . } # Filter: P4 language is Q130/Q170137/Q52071 ; | ||
+ | # ?audio prop:P4 entity:Q170137 . # Filter: P4 language is Q170137 (redirect) ; | ||
+ | ?audio prop:P2 entity:Q2 . # Filter: audios | ||
+ | ?audio prop:P4 ?lang . | ||
+ | ?audio prop:P5 ?speaker . | ||
+ | ?audio prop:P3 ?url . | ||
+ | # Add Labels | ||
+ | SERVICE wikibase:label { bd:serviceParam wikibase:language "[AUTO_LANGUAGE],en" . } | ||
+ | } | ||
+ | # ORDER BY ASC(?audio) | ||
+ | # GROUP BY ?lang ?SpeakerQid ?speakerLabel | ||
+ | </syntaxhighlight> | ||
+ | || | ||
+ | <query _pagination="5"> | ||
+ | #defaultEndpoint:Lingualibre | ||
+ | SELECT ?lang | ||
+ | (SUBSTR(STR(?speaker),32) AS ?SpeakerQid) ?speakerLabel | ||
+ | ?audio ?audioLabel | ||
+ | ?url (SUBSTR(STR(?urlLabel),52) AS ?filename) | ||
+ | WHERE { | ||
+ | # Obsolete languages items (duplicata and redirects) | ||
+ | # Chinese Q130 → Q113 | ||
+ | # Mossi Q170137 → Q359 | ||
+ | # Duala Q52071 → Q73 | ||
+ | VALUES ?i18nQid { entity:Q130 entity:Q170137 entity:Q52071 } | ||
+ | |||
+ | { ?audio prop:P4 ?i18nQid . } # Filter: P4 language is Q130/Q170137/Q52071 ; | ||
+ | # ?audio prop:P4 entity:Q170137 . # Filter: P4 language is Q170137 (redirect) ; | ||
+ | ?audio prop:P2 entity:Q2 . # Filter: audios | ||
+ | ?audio prop:P4 ?lang . | ||
+ | ?audio prop:P5 ?speaker . | ||
+ | ?audio prop:P3 ?url . | ||
+ | # Add Labels | ||
+ | SERVICE wikibase:label { bd:serviceParam wikibase:language "[AUTO_LANGUAGE],en" . } | ||
+ | } | ||
+ | # ORDER BY ASC(?audio) | ||
+ | # GROUP BY ?lang ?SpeakerQid ?speakerLabel | ||
+ | </query> | ||
+ | |} | ||
+ | |||
+ | ==== Counts ==== | ||
+ | {| style="width:100%" | ||
+ | |- style="vertical-align:top;" | ||
+ | |style="padding: 0 3em;width:60%"| | ||
+ | <syntaxhighlight lang="sparql"> | ||
+ | #defaultEndpoint:Lingualibre | ||
+ | SELECT ?lang ?langLabel ?iso | ||
+ | ?speaker ?speakerLabel | ||
+ | (COUNT(?audio) AS ?found) | ||
+ | WHERE { | ||
+ | # Obsolete languages items (duplicata and redirects) | ||
+ | # Chinese Q130 → Q113 | ||
+ | # Mossi Q170137 → Q359 | ||
+ | # Duala Q52071 → Q73 | ||
+ | VALUES ?i18nQid { entity:Q130 entity:Q170137 entity:Q52071 } | ||
+ | |||
+ | { ?audio prop:P4 ?i18nQid . } # Filter: P4 language is Q130/Q170137/Q52071 ; | ||
+ | ?audio prop:P2 entity:Q2 . # Filter: audios | ||
+ | ?audio prop:P4 ?lang . | ||
+ | OPTIONAL { ?lang prop:P13 ?iso . } | ||
+ | ?audio prop:P5 ?speaker . | ||
+ | ?audio prop:P3 ?url . | ||
+ | # Add Labels | ||
+ | SERVICE wikibase:label { bd:serviceParam wikibase:language "[AUTO_LANGUAGE],en" . } | ||
+ | } | ||
+ | GROUP BY ?lang ?langLabel ?iso ?speaker ?speakerLabel | ||
+ | ORDER BY ?lang | ||
+ | </syntaxhighlight> | ||
+ | || | ||
+ | <query _pagination="10"> | ||
+ | #defaultEndpoint:Lingualibre | ||
+ | SELECT ?lang ?langLabel ?iso | ||
+ | ?speaker ?speakerLabel | ||
+ | (COUNT(?audio) AS ?found) | ||
+ | WHERE { | ||
+ | # Obsolete languages items (duplicata and redirects) | ||
+ | # Chinese Q130 → Q113 | ||
+ | # Mossi Q170137 → Q359 | ||
+ | # Duala Q52071 → Q73 | ||
+ | VALUES ?i18nQid { entity:Q130 entity:Q170137 entity:Q52071 } | ||
+ | |||
+ | { ?audio prop:P4 ?i18nQid . } # Filter: P4 language is Q130/Q170137/Q52071 ; | ||
+ | ?audio prop:P2 entity:Q2 . # Filter: audios | ||
+ | ?audio prop:P4 ?lang . | ||
+ | OPTIONAL { ?lang prop:P13 ?iso . } | ||
+ | ?audio prop:P5 ?speaker . | ||
+ | ?audio prop:P3 ?url . | ||
+ | # Add Labels | ||
+ | SERVICE wikibase:label { bd:serviceParam wikibase:language "[AUTO_LANGUAGE],en" . } | ||
+ | } | ||
+ | GROUP BY ?lang ?langLabel ?iso ?speaker ?speakerLabel | ||
+ | ORDER BY ?lang | ||
+ | </query> | ||
+ | |} | ||
== Languages == | == Languages == | ||
− | === ✅ Languages → duplicata by Wikidata ID === | + | === ✅ LL Languages → duplicata by Wikidata ID === |
− | :''Duplicated languages can be merged.'' | + | :''Duplicated languages can be merged. If stale, it mean none was found.'' |
{| style="width:100%" | {| style="width:100%" | ||
|- style="vertical-align:top;" | |- style="vertical-align:top;" | ||
|style="padding: 0 3em;width:60%"| | |style="padding: 0 3em;width:60%"| | ||
<syntaxhighlight lang="sparql"> | <syntaxhighlight lang="sparql"> | ||
+ | #defaultEndpoint:Lingualibre | ||
SELECT ?idWD (COUNT(?item) AS ?count) (GROUP_CONCAT(?item) AS ?items) | SELECT ?idWD (COUNT(?item) AS ?count) (GROUP_CONCAT(?item) AS ?items) | ||
WHERE { | WHERE { | ||
Line 283: | Line 529: | ||
|| | || | ||
<query _pagination="5"> | <query _pagination="5"> | ||
+ | #defaultEndpoint:Lingualibre | ||
SELECT ?idWD (COUNT(?item) AS ?count) (GROUP_CONCAT(?item) AS ?items) | SELECT ?idWD (COUNT(?item) AS ?count) (GROUP_CONCAT(?item) AS ?items) | ||
WHERE { | WHERE { | ||
Line 293: | Line 540: | ||
|} | |} | ||
− | === ✅ Languages → languages by type (if it exists) === | + | === ✅ LL Languages → LL Qid, records, speakers === |
+ | :''Note: If some languageLabels display full uri, those are remains of duplicate language items now merged, one being a redirect. Erroneous data should be corrected or deleted on both Commons and Lingualibre's recordings. [[User:Yug]] has [[User:Dragons Bot|Dragons Bot]] for that.'' | ||
+ | {| style="width:100%" | ||
+ | |- style="vertical-align:top;" | ||
+ | |style="padding: 0 3em;width:60%"| | ||
+ | <syntaxhighlight lang="sparql"> | ||
+ | #defaultEndpoint:Lingualibre | ||
+ | SELECT | ||
+ | ?language | ||
+ | ?languageLabel | ||
+ | (COUNT(DISTINCT ?record) AS ?records) | ||
+ | (COUNT(DISTINCT ?speaker) AS ?speakers) | ||
+ | WHERE { | ||
+ | ?record prop:P2 entity:Q2 . | ||
+ | # If all speakers P5 corrected, recordings still accounted for | ||
+ | OPTIONAL { ?record prop:P5 ?speaker . } | ||
+ | ?record prop:P4 ?language . | ||
+ | SERVICE wikibase:label { bd:serviceParam wikibase:language "[AUTO_LANGUAGE],en". } | ||
+ | |||
+ | } | ||
+ | GROUP BY ?language ?languageLabel | ||
+ | ORDER BY ?languageLabel | ||
+ | </syntaxhighlight> | ||
+ | || | ||
+ | <query _pagination="5"> | ||
+ | #defaultEndpoint:Lingualibre | ||
+ | SELECT | ||
+ | ?language | ||
+ | ?languageLabel | ||
+ | (COUNT(DISTINCT ?record) AS ?records) | ||
+ | (COUNT(DISTINCT ?speaker) AS ?speakers) | ||
+ | WHERE { | ||
+ | ?record prop:P2 entity:Q2 . | ||
+ | # If all speakers P5 corrected, recordings still accounted for | ||
+ | OPTIONAL { ?record prop:P5 ?speaker . } | ||
+ | ?record prop:P4 ?language . | ||
+ | SERVICE wikibase:label { bd:serviceParam wikibase:language "[AUTO_LANGUAGE],en". } | ||
+ | |||
+ | } | ||
+ | GROUP BY ?language ?languageLabel | ||
+ | ORDER BY ?languageLabel | ||
+ | </query> | ||
+ | |} | ||
+ | |||
+ | ==== See also ==== | ||
+ | Sections above : [[#Recordings]] for corrupt data to fix. | ||
+ | |||
+ | === ✅ LL Languages → languages by type (if it exists) === | ||
:''Note: query to improve.'' | :''Note: query to improve.'' | ||
{| style="width:100%" | {| style="width:100%" | ||
Line 299: | Line 593: | ||
|style="padding: 0 3em;width:60%"| | |style="padding: 0 3em;width:60%"| | ||
<syntaxhighlight lang="sparql"> | <syntaxhighlight lang="sparql"> | ||
− | SELECT ?language ?languageLabel ?code ?typeLabel | + | #defaultEndpoint:Lingualibre |
+ | SELECT ?language ?languageLabel ?code ?type ?typeLabel | ||
WHERE { | WHERE { | ||
?language prop:P2 entity:Q4 . | ?language prop:P2 entity:Q4 . | ||
Line 311: | Line 606: | ||
} | } | ||
} | } | ||
+ | ORDER BY DESC (?typeLabel) | ||
</syntaxhighlight> | </syntaxhighlight> | ||
|| | || | ||
<query _pagination="5"> | <query _pagination="5"> | ||
− | SELECT ?language ?languageLabel ?code ?typeLabel | + | #defaultEndpoint:Lingualibre |
+ | SELECT ?language ?languageLabel ?code ?type ?typeLabel | ||
WHERE { | WHERE { | ||
?language prop:P2 entity:Q4 . | ?language prop:P2 entity:Q4 . | ||
Line 327: | Line 624: | ||
} | } | ||
} | } | ||
+ | ORDER BY DESC (?typeLabel) | ||
</query> | </query> | ||
|} | |} | ||
− | === ✅ Languages → | + | === ✅ LL Languages → média types === |
{| style="width:100%" | {| style="width:100%" | ||
|- style="vertical-align:top;" | |- style="vertical-align:top;" | ||
|style="padding: 0 3em;width:60%"| | |style="padding: 0 3em;width:60%"| | ||
<syntaxhighlight lang="sparql"> | <syntaxhighlight lang="sparql"> | ||
+ | #defaultEndpoint:Lingualibre | ||
+ | SELECT ?id ?idLabel | ||
+ | WHERE { | ||
+ | ?id prop:P2 entity:Q88888 . | ||
+ | SERVICE wikibase:label { bd:serviceParam wikibase:language "fr,en". } | ||
+ | } | ||
+ | </syntaxhighlight> | ||
+ | || | ||
+ | <query _pagination="10"> | ||
+ | #defaultEndpoint:Lingualibre | ||
+ | SELECT ?id ?idLabel | ||
+ | WHERE { | ||
+ | ?id prop:P2 entity:Q88888 . | ||
+ | SERVICE wikibase:label { bd:serviceParam wikibase:language "fr,en". } | ||
+ | } | ||
+ | </query> | ||
+ | |} | ||
+ | |||
+ | === ✅ LL Languages → language with media type (P24) is video (Q88890) === | ||
+ | {| style="width:100%" | ||
+ | |- style="vertical-align:top;" | ||
+ | |style="padding: 0 3em;width:60%"| | ||
+ | <syntaxhighlight lang="sparql"> | ||
+ | #defaultEndpoint:Lingualibre | ||
SELECT ?id ?idLabel WHERE { | SELECT ?id ?idLabel WHERE { | ||
?id prop:P2 entity:Q4 . | ?id prop:P2 entity:Q4 . | ||
Line 342: | Line 664: | ||
</syntaxhighlight> | </syntaxhighlight> | ||
|| | || | ||
− | <query _pagination=" | + | <query _pagination="10"> |
+ | #defaultEndpoint:Lingualibre | ||
SELECT ?id ?idLabel WHERE { | SELECT ?id ?idLabel WHERE { | ||
?id prop:P2 entity:Q4 . | ?id prop:P2 entity:Q4 . | ||
Line 348: | Line 671: | ||
SERVICE wikibase:label { bd:serviceParam wikibase:language "fr,en". } | SERVICE wikibase:label { bd:serviceParam wikibase:language "fr,en". } | ||
} | } | ||
+ | </query> | ||
+ | |} | ||
+ | |||
+ | === ✅ LL Languages → language with media type (P24) is missing === | ||
+ | :''Empty if displaying rotating animation too long.'' | ||
+ | {| style="width:100%" | ||
+ | |- style="vertical-align:top;" | ||
+ | |style="padding: 0 3em;width:60%"| | ||
+ | <syntaxhighlight lang="sparql"> | ||
+ | #defaultEndpoint:Lingualibre | ||
+ | SELECT ?id ?idLabel ?type ?typeLabel | ||
+ | WHERE { | ||
+ | ?id prop:P2 entity:Q4 . | ||
+ | FILTER NOT EXISTS { | ||
+ | ?id prop:P24 []. | ||
+ | } | ||
+ | SERVICE wikibase:label { bd:serviceParam wikibase:language "fr,en". } | ||
+ | } | ||
+ | </syntaxhighlight> | ||
+ | || | ||
+ | <query _pagination="5"> | ||
+ | #defaultEndpoint:Lingualibre | ||
+ | SELECT ?id ?idLabel ?type ?typeLabel | ||
+ | WHERE { | ||
+ | ?id prop:P2 entity:Q4 . | ||
+ | FILTER NOT EXISTS { | ||
+ | ?id prop:P24 []. | ||
+ | } | ||
+ | SERVICE wikibase:label { bd:serviceParam wikibase:language "fr,en". } | ||
+ | } | ||
+ | </query> | ||
+ | <query _pagination="10"> | ||
+ | #defaultEndpoint:Lingualibre | ||
+ | SELECT (COUNT(?id) AS ?found) | ||
+ | WHERE { | ||
+ | ?id prop:P2 entity:Q4 . | ||
+ | FILTER NOT EXISTS { | ||
+ | ?id prop:P24 []. | ||
+ | } | ||
+ | SERVICE wikibase:label { bd:serviceParam wikibase:language "fr,en". } | ||
+ | } GROUP BY ?type | ||
+ | </query> | ||
+ | |} | ||
+ | |||
+ | === ✅ LL Languages → language with commons category (P26) is missing === | ||
+ | :''Empty if displaying rotating animation too long.'' | ||
+ | {| style="width:100%" | ||
+ | |- style="vertical-align:top;" | ||
+ | |style="padding: 0 3em;width:60%"| | ||
+ | <syntaxhighlight lang="sparql"> | ||
+ | #defaultEndpoint:Lingualibre | ||
+ | SELECT ?language ?languageLabel ?iso | ||
+ | (URL(CONCAT('<a href=https://commons.wikimedia.org/wiki/Category:Lingua_Libre_pronunciation-',?iso,'>',?iso,'</a>')) AS ?cat) | ||
+ | WHERE { | ||
+ | ?record prop:P2 entity:Q2 . | ||
+ | ?record prop:P4 ?language . | ||
+ | FILTER NOT EXISTS { | ||
+ | ?language prop:P26 []. | ||
+ | } | ||
+ | ?language prop:P13 ?iso . | ||
+ | SERVICE wikibase:label { bd:serviceParam wikibase:language "fr,en". } | ||
+ | } GROUP BY ?language ?languageLabel ?iso ?cat | ||
+ | </syntaxhighlight> | ||
+ | || | ||
+ | <query _pagination="10"> | ||
+ | #defaultEndpoint:Lingualibre | ||
+ | SELECT ?language ?languageLabel ?iso | ||
+ | (CONCAT('<a href=https://commons.wikimedia.org/wiki/Category:Lingua_Libre_pronunciation-',?iso,'>',?iso,'</a>') AS ?cat) | ||
+ | WHERE { | ||
+ | ?record prop:P2 entity:Q2 . | ||
+ | ?record prop:P4 ?language . | ||
+ | FILTER NOT EXISTS { | ||
+ | ?language prop:P26 []. | ||
+ | } | ||
+ | ?language prop:P13 ?iso . | ||
+ | SERVICE wikibase:label { bd:serviceParam wikibase:language "fr,en". } | ||
+ | } GROUP BY ?language ?languageLabel ?iso ?cat | ||
+ | </query> | ||
+ | <query _pagination="10"> | ||
+ | #defaultEndpoint:Lingualibre | ||
+ | SELECT (COUNT(DISTINCT ?iso) AS ?found_DOES_NOT_WORK) | ||
+ | WHERE { | ||
+ | ?record prop:P2 entity:Q2 ; | ||
+ | prop:P4 ?language . | ||
+ | FILTER NOT EXISTS { # doesnt have | ||
+ | ?language prop:P26 []. # commons category P26 declared | ||
+ | } | ||
+ | }GROUP BY ?language | ||
</query> | </query> | ||
|} | |} | ||
Line 356: | Line 767: | ||
|style="padding: 0 3em;width:60%"| | |style="padding: 0 3em;width:60%"| | ||
<syntaxhighlight lang="sparql"> | <syntaxhighlight lang="sparql"> | ||
+ | #defaultEndpoint:Lingualibre | ||
SELECT ?word ?filename ?speaker WHERE { | SELECT ?word ?filename ?speaker WHERE { | ||
?record prop:P4 entity:Q99628 . | ?record prop:P4 entity:Q99628 . | ||
Line 368: | Line 780: | ||
|| | || | ||
<query _pagination="5"> | <query _pagination="5"> | ||
+ | #defaultEndpoint:Lingualibre | ||
SELECT ?word ?filename ?speaker WHERE { | SELECT ?word ?filename ?speaker WHERE { | ||
?record prop:P4 entity:Q99628 . | ?record prop:P4 entity:Q99628 . | ||
Line 382: | Line 795: | ||
=== ✅ Languages iso from SignIt → relevant data === | === ✅ Languages iso from SignIt → relevant data === | ||
− | :'' | + | :''This is based on [https://translatewiki.net/wiki/Translating:Lingua_Libre_SignIt#sortable:3=desc Translatewiki:Translating:Lingua_Libre_SignIt] and helps https://github.com/lingua-libre/Signit ''. |
{| style="width:100%" | {| style="width:100%" | ||
|- style="vertical-align:top;" | |- style="vertical-align:top;" | ||
|style="padding: 0 3em;width:60%"| | |style="padding: 0 3em;width:60%"| | ||
<syntaxhighlight lang="sparql"> | <syntaxhighlight lang="sparql"> | ||
− | SELECT ?wdQid ?wikimediaCode ? | + | # List from https://translatewiki.net/wiki/Translating:Lingua_Libre_SignIt#sortable:3=desc |
+ | # 2023.07.26 | ||
+ | #defaultEndpoint:Wikidata | ||
+ | SELECT ?wdQid ?wikimediaCode ?i18nCode ?labelEN | ||
+ | (SAMPLE(?nativeLabel) as ?labelNative) | ||
WHERE { | WHERE { | ||
− | VALUES ? | + | # languages & scripts |
+ | VALUES ?i18nCode { | ||
+ | "anp" "ar" "bn" "br" "de" "en" "es" "fa" "fi" "fr" | ||
+ | "he" "hi" "ia" "id" "it" "ja" "kk-cyrl" "ko" "krc" "lmo" | ||
+ | "mk" "ms" "nb" "pnb" "pt" "pt-br" "qqq" "ru" "scn" "sl" | ||
+ | "sv" "sw" "tl" "tr" "uk" "zh-hans" "zh-hant" "mnw" "hu" | ||
+ | "kk" "zh" | ||
} | } | ||
− | ?langId wdt:P31 wd: | + | # Scripts, not languages |
− | + | VALUES ?i18nScript { "kk-cyrl" "zh-hans" "zh-hant" } | |
− | + | ||
− | + | { ?langId wdt:P218 ?i18nCode. } # has for iso 639-1 code | |
+ | UNION {?langId wdt:P219 ?i18nCode. } # has for iso 639-2 code | ||
+ | UNION {?langId wdt:P220 ?i18nCode. } # has for iso 639-3 code | ||
+ | UNION {?langId wdt:P305 ?i18nCode. } # has for isoIETF code | ||
+ | |||
+ | # UNION {?langId wdt:P31 wd:Q1149626 ; # has for instance written language | ||
+ | # wdt:P424 ?i18nScript ; # has for wikimedia code | ||
+ | # rdfs:label ?labelEN . } | ||
+ | |||
+ | # UNION { ?langId wdt:P424 ?i18nCode. } # has for wikimedia code | ||
+ | |||
+ | OPTIONAL { ?langId wdt:P424 ?wikimediaCode. } | ||
+ | OPTIONAL { ?langId wdt:P1705 ?native. } | ||
# wdt:P10369 ?lingualibreQid ; | # wdt:P10369 ?lingualibreQid ; | ||
− | + | ?langId rdfs:label ?labelEN . | |
− | FILTER ( lang(? | + | FILTER ( lang(?labelEN) = "en" ) |
BIND(REPLACE(STR(?langId), ".*/Q", "Q") AS ?wdQid) | BIND(REPLACE(STR(?langId), ".*/Q", "Q") AS ?wdQid) | ||
BIND(CONCAT(UCASE(SUBSTR(?native, 1 , 1 )), SUBSTR(?native, 2 )) AS ?nativeLabel) | BIND(CONCAT(UCASE(SUBSTR(?native, 1 , 1 )), SUBSTR(?native, 2 )) AS ?nativeLabel) | ||
} | } | ||
− | GROUP BY ?wdQid ?wikimediaCode ? | + | GROUP BY ?wdQid ?wikimediaCode ?i18nCode ?labelEN |
+ | ORDER BY ASC(?i18nCode) | ||
</syntaxhighlight> | </syntaxhighlight> | ||
|| | || | ||
− | <query _pagination=" | + | <query _pagination="10"> |
− | SELECT ?wdQid ?wikimediaCode ? | + | #defaultEndpoint:Wikidata |
+ | # List from https://translatewiki.net/wiki/Translating:Lingua_Libre_SignIt#sortable:3=desc | ||
+ | SELECT ?wdQid ?wikimediaCode ?i18nCode ?labelEN | ||
+ | (SAMPLE(?nativeLabel) as ?labelNative) | ||
WHERE { | WHERE { | ||
− | VALUES ? | + | # languages & scripts |
+ | VALUES ?i18nCode { | ||
+ | "anp" "ar" "bn" "br" "de" "en" "es" "fa" "fi" "fr" | ||
+ | "he" "hi" "ia" "id" "it" "ja" "kk-cyrl" "ko" "krc" "lmo" | ||
+ | "mk" "ms" "nb" "pnb" "pt" "pt-br" "qqq" "ru" "scn" "sl" | ||
+ | "sv" "sw" "tl" "tr" "uk" "zh-hans" "zh-hant" "mnw" "hu" | ||
+ | "kk" "zh" | ||
} | } | ||
− | ?langId wdt:P31 wd: | + | # Scripts, not languages |
− | + | VALUES ?i18nScript { "kk-cyrl" "zh-hans" "zh-hant" } | |
− | + | ||
− | + | { ?langId wdt:P218 ?i18nCode. } # has for iso 639-1 code | |
+ | UNION {?langId wdt:P219 ?i18nCode. } # has for iso 639-2 code | ||
+ | UNION {?langId wdt:P220 ?i18nCode. } # has for iso 639-3 code | ||
+ | UNION {?langId wdt:P305 ?i18nCode. } # has for isoIETF code | ||
+ | |||
+ | # UNION {?langId wdt:P31 wd:Q1149626 ; # has for instance written language | ||
+ | # wdt:P424 ?i18nScript ; # has for wikimedia code | ||
+ | # rdfs:label ?labelEN . } | ||
+ | |||
+ | # UNION { ?langId wdt:P424 ?i18nCode. } # has for wikimedia code | ||
+ | |||
+ | OPTIONAL { ?langId wdt:P424 ?wikimediaCode. } | ||
+ | OPTIONAL { ?langId wdt:P1705 ?native. } | ||
# wdt:P10369 ?lingualibreQid ; | # wdt:P10369 ?lingualibreQid ; | ||
− | + | ?langId rdfs:label ?labelEN . | |
− | FILTER ( lang(? | + | FILTER ( lang(?labelEN) = "en" ) |
BIND(REPLACE(STR(?langId), ".*/Q", "Q") AS ?wdQid) | BIND(REPLACE(STR(?langId), ".*/Q", "Q") AS ?wdQid) | ||
BIND(CONCAT(UCASE(SUBSTR(?native, 1 , 1 )), SUBSTR(?native, 2 )) AS ?nativeLabel) | BIND(CONCAT(UCASE(SUBSTR(?native, 1 , 1 )), SUBSTR(?native, 2 )) AS ?nativeLabel) | ||
} | } | ||
− | GROUP BY ?wdQid ?wikimediaCode ? | + | GROUP BY ?wdQid ?wikimediaCode ?i18nCode ?labelEN |
+ | ORDER BY ASC(?i18nCode) | ||
+ | </query> | ||
+ | |} | ||
+ | |||
+ | === ✅ LL's Languages → WD: with Lingua Libre ID ([[:d:P:P10369|P10369]])=== | ||
+ | :''To create.'' | ||
+ | {| style="width:100%" | ||
+ | |- style="vertical-align:top;" | ||
+ | |style="padding: 0 3em;width:60%"| | ||
+ | <syntaxhighlight lang="sparql"> | ||
+ | #defaultEndpoint:Wikidata | ||
+ | # MediaWiki:LanguagesPopulationData.js | ||
+ | # defaultView:Table | ||
+ | # Run on WDQS <--------------------------------------------------- | ||
+ | # Same can apply to languages : | ||
+ | # Q3→Q4 : items speaker and language | ||
+ | # P14→P12 : items WD location and WD language | ||
+ | # P5→P4 : properties speaker and languages | ||
+ | # P625→P1098 : properties location and population | ||
+ | # | ||
+ | PREFIX ll: <https://lingualibre.org/entity/> | ||
+ | PREFIX llt: <https://lingualibre.org/prop/direct/> | ||
+ | # | ||
+ | SELECT | ||
+ | (SAMPLE(STR(?languageLabelNative_)) AS ?languageLabelNative) | ||
+ | (SAMPLE(STR(?isoLabel_)) AS ?isoLabel) | ||
+ | ?itemLabel ?item | ||
+ | ?wikidataURL | ||
+ | ?LinguaLibreID | ||
+ | |||
+ | # On Lingualibre, get item's info | ||
+ | WITH { | ||
+ | SELECT * | ||
+ | WHERE { | ||
+ | SERVICE <https://lingualibre.org/sparql> { # Commented on LLQS only | ||
+ | SELECT ?item ?itemLabel ?wikidata # (COUNT(?record) AS ?records) | ||
+ | { | ||
+ | ?item llt:P2 ll:Q4 ; | ||
+ | rdfs:label ?itemLabel; | ||
+ | llt:P12 ?wikidata . | ||
+ | FILTER EXISTS { ?record llt:P4 ?item } | ||
+ | FILTER (LANG(?itemLabel)='en') | ||
+ | FILTER (regex(?wikidata, '^Q')) | ||
+ | } GROUP BY ?item ?itemLabel ?wikidata | ||
+ | } # Commented on LLQS only | ||
+ | } | ||
+ | } AS %infoWikidataId | ||
+ | |||
+ | # On Wikidata, get the target info | ||
+ | WHERE { | ||
+ | INCLUDE %infoWikidataId | ||
+ | BIND (URI(CONCAT("http://www.wikidata.org/entity/", ?wikidata)) AS ?wikidataURL) | ||
+ | SERVICE <https://query.wikidata.org/sparql> { | ||
+ | SELECT ?wikidataURL ?LinguaLibreID ?languageLabelNative_ ?isoLabel_ { | ||
+ | OPTIONAL { ?wikidataURL wdt:P10369 ?LinguaLibreID . } | ||
+ | OPTIONAL { ?wikidataURL wdt:P1705 ?languageLabelNative_ . } | ||
+ | OPTIONAL { ?wikidataURL wdt:P218 ?iso639_1 ; rdfs:label ?isoLabel_ . FILTER(LANG(?isoLabel_)=?iso639_1) . } | ||
+ | } | ||
+ | } | ||
+ | } | ||
+ | |||
+ | GROUP BY ?itemLabel ?item ?wikidataURL ?LinguaLibreID | ||
+ | ORDER BY (?LinguaLibreID) | ||
+ | </syntaxhighlight> | ||
+ | || | ||
+ | <query _pagination="10"> | ||
+ | #defaultEndpoint:Wikidata | ||
+ | # MediaWiki:LanguagesPopulationData.js | ||
+ | # defaultView:Table | ||
+ | # Run on WDQS <--------------------------------------------------- | ||
+ | # Same can apply to languages : | ||
+ | # Q3→Q4 : items speaker and language | ||
+ | # P14→P12 : items WD location and WD language | ||
+ | # P5→P4 : properties speaker and languages | ||
+ | # P625→P1098 : properties location and population | ||
+ | # | ||
+ | PREFIX ll: <https://lingualibre.org/entity/> | ||
+ | PREFIX llt: <https://lingualibre.org/prop/direct/> | ||
+ | # | ||
+ | SELECT | ||
+ | (SAMPLE(STR(?languageLabelNative_)) AS ?languageLabelNative) | ||
+ | (SAMPLE(STR(?isoLabel_)) AS ?isoLabel) | ||
+ | ?itemLabel ?item | ||
+ | ?wikidataURL | ||
+ | ?LinguaLibreID | ||
+ | |||
+ | # On Lingualibre, get item's info | ||
+ | WITH { | ||
+ | SELECT * | ||
+ | WHERE { | ||
+ | SERVICE <https://lingualibre.org/sparql> { # Commented on LLQS only | ||
+ | SELECT ?item ?itemLabel ?wikidata # (COUNT(?record) AS ?records) | ||
+ | { | ||
+ | ?item llt:P2 ll:Q4 ; | ||
+ | rdfs:label ?itemLabel; | ||
+ | llt:P12 ?wikidata . | ||
+ | FILTER EXISTS { ?record llt:P4 ?item } | ||
+ | FILTER (LANG(?itemLabel)='en') | ||
+ | FILTER (regex(?wikidata, '^Q')) | ||
+ | } GROUP BY ?item ?itemLabel ?wikidata | ||
+ | } # Commented on LLQS only | ||
+ | } | ||
+ | } AS %infoWikidataId | ||
+ | |||
+ | # On Wikidata, get the target info | ||
+ | WHERE { | ||
+ | INCLUDE %infoWikidataId | ||
+ | BIND (URI(CONCAT("http://www.wikidata.org/entity/", ?wikidata)) AS ?wikidataURL) | ||
+ | SERVICE <https://query.wikidata.org/sparql> { | ||
+ | SELECT ?wikidataURL ?LinguaLibreID ?languageLabelNative_ ?isoLabel_ { | ||
+ | OPTIONAL { ?wikidataURL wdt:P10369 ?LinguaLibreID . } | ||
+ | OPTIONAL { ?wikidataURL wdt:P1705 ?languageLabelNative_ . } | ||
+ | OPTIONAL { ?wikidataURL wdt:P218 ?iso639_1 ; rdfs:label ?isoLabel_ . FILTER(LANG(?isoLabel_)=?iso639_1) . } | ||
+ | } | ||
+ | } | ||
+ | } | ||
+ | |||
+ | GROUP BY ?itemLabel ?item ?wikidataURL ?LinguaLibreID | ||
+ | ORDER BY (?LinguaLibreID) | ||
+ | </query> | ||
+ | |} | ||
+ | |||
+ | === ❌ LL's Languages → WD: without Lingua Libre ID ([[:d:P:P10369|P10369]])=== | ||
+ | :''To create.'' | ||
+ | {| style="width:100%" | ||
+ | |- style="vertical-align:top;" | ||
+ | |style="padding: 0 3em;width:60%"| | ||
+ | <syntaxhighlight lang="sparql"> | ||
+ | #defaultEndpoint:Wikidata | ||
+ | |||
+ | </syntaxhighlight> | ||
+ | || | ||
+ | <query _pagination="10"> | ||
+ | #defaultEndpoint:Wikidata | ||
+ | </query> | ||
+ | |} | ||
+ | |||
+ | === ❌ LL's Languages → WD → en.wikipedia.org : article pagename === | ||
+ | :''To create.'' | ||
+ | {| style="width:100%" | ||
+ | |- style="vertical-align:top;" | ||
+ | |style="padding: 0 3em;width:60%"| | ||
+ | <syntaxhighlight lang="sparql"> | ||
+ | #defaultEndpoint:Wikidata | ||
+ | |||
+ | </syntaxhighlight> | ||
+ | || | ||
+ | <query _pagination="10"> | ||
+ | #defaultEndpoint:Wikidata | ||
+ | </query> | ||
+ | |} | ||
+ | |||
+ | === ✅ LL Languages → by date of first recording === | ||
+ | ==== Basic-slow query ==== | ||
+ | {| style="width:100%" | ||
+ | |- style="vertical-align:top;" | ||
+ | |style="padding: 0 3em;width:60%"| | ||
+ | <syntaxhighlight lang="sparql"> | ||
+ | #defaultEndpoint:Lingualibre | ||
+ | SELECT ?lang ?langLabel (SUBSTR(MIN(?date), 1, 10) AS ?first ) | ||
+ | WHERE { | ||
+ | ?audio prop:P4 ?lang ; | ||
+ | prop:P6 ?date . | ||
+ | SERVICE wikibase:label { bd:serviceParam wikibase:language "en". } | ||
+ | } | ||
+ | GROUP BY ?lang ?langLabel | ||
+ | ORDER BY (?first) | ||
+ | </syntaxhighlight> | ||
+ | || | ||
+ | <query _pagination="10"> | ||
+ | #defaultEndpoint:Lingualibre | ||
+ | SELECT ?lang ?langLabel (SUBSTR(MIN(?date), 1, 10) AS ?first ) | ||
+ | WHERE { | ||
+ | ?audio prop:P4 ?lang ; | ||
+ | prop:P6 ?date . | ||
+ | SERVICE wikibase:label { bd:serviceParam wikibase:language "en". } | ||
+ | } | ||
+ | GROUP BY ?lang ?langLabel | ||
+ | ORDER BY (?first) | ||
+ | </query> | ||
+ | |} | ||
+ | |||
+ | ==== Faster query ==== | ||
+ | {| style="width:100%" | ||
+ | |- style="vertical-align:top;" | ||
+ | |style="padding: 0 3em;width:60%"| | ||
+ | <syntaxhighlight lang="sparql"> | ||
+ | #defaultEndpoint:Lingualibre | ||
+ | SELECT ?lang ?langLabel (SUBSTR(STR(?first),1,10) AS ?First) | ||
+ | (CONCAT('<a href=https://commons.wikimedia.org/wiki/Category:Lingua_Libre_pronunciation-',?iso,'>',?iso,'</a>') AS ?cat) | ||
+ | WHERE { | ||
+ | SERVICE wikibase:label { bd:serviceParam wikibase:language "en". } | ||
+ | { SELECT ?lang ?iso (MIN(?date) AS ?first) | ||
+ | WHERE { | ||
+ | ?audio prop:P4 ?lang ; | ||
+ | prop:P6 ?date . | ||
+ | ?lang prop:P13 ?iso . | ||
+ | } GROUP BY ?lang ?iso | ||
+ | } | ||
+ | } ORDER BY DESC (?First) | ||
+ | </syntaxhighlight> | ||
+ | || | ||
+ | <query _pagination="10"> | ||
+ | #defaultEndpoint:Lingualibre | ||
+ | SELECT ?lang ?langLabel (SUBSTR(STR(?first),1,10) AS ?First) | ||
+ | (CONCAT('<a href=https://commons.wikimedia.org/wiki/Category:Lingua_Libre_pronunciation-',?iso,'>',?iso,'</a>') AS ?cat) | ||
+ | WHERE { | ||
+ | SERVICE wikibase:label { bd:serviceParam wikibase:language "en". } | ||
+ | { SELECT ?lang ?iso (MIN(?date) AS ?first) | ||
+ | WHERE { | ||
+ | ?audio prop:P4 ?lang ; | ||
+ | prop:P6 ?date . | ||
+ | ?lang prop:P13 ?iso . | ||
+ | } GROUP BY ?lang ?iso | ||
+ | } | ||
+ | } ORDER BY DESC (?First) | ||
+ | </query> | ||
+ | |} | ||
+ | |||
+ | === ✅ WD Languages → language status ([[:d:P3823|P3823]],[[:d:P1999|P1999]]) === | ||
+ | {| style="width:100%" | ||
+ | |- style="vertical-align:top;" | ||
+ | |style="padding: 0 3em;width:60%"| | ||
+ | <syntaxhighlight lang="sparql"> | ||
+ | #defaultEndpoint:Wikidata | ||
+ | SELECT ?item ?itemLabel ?statusUNLabel ?statusEthnoLabel | ||
+ | WHERE { | ||
+ | SERVICE wikibase:label { bd:serviceParam wikibase:language "[AUTO_LANGUAGE],en". } | ||
+ | ?item wdt:P31 wd:Q34770. | ||
+ | OPTIONAL { ?item wdt:P1999 ?statusUN. } | ||
+ | OPTIONAL { ?item wdt:P3823 ?statusEthno. } | ||
+ | } | ||
+ | ORDER BY DESC (?itemLabel) | ||
+ | </syntaxhighlight> | ||
+ | || | ||
+ | <query _pagination="10"> | ||
+ | #defaultEndpoint:Wikidata | ||
+ | SELECT ?item ?itemLabel ?statusUNLabel ?statusEthnoLabel | ||
+ | WHERE { | ||
+ | SERVICE wikibase:label { bd:serviceParam wikibase:language "[AUTO_LANGUAGE],en". } | ||
+ | ?item wdt:P31 wd:Q34770. | ||
+ | OPTIONAL { ?item wdt:P1999 ?statusUN. } | ||
+ | OPTIONAL { ?item wdt:P3823 ?statusEthno. } | ||
+ | } | ||
+ | ORDER BY DESC (?itemLabel) | ||
+ | </query> | ||
+ | |} | ||
+ | |||
+ | === ✅ Is corpora ([[d:Q461183]]) → Languages ([[d:P:P407]]) === | ||
+ | {| style="width:100%" | ||
+ | |- style="vertical-align:top;" | ||
+ | |style="padding: 0 3em;width:60%"| | ||
+ | <syntaxhighlight lang="sparql"> | ||
+ | #defaultEndpoint:Wikidata | ||
+ | SELECT ?text_corpus ?languageLabel ?website ?date ?size | ||
+ | WHERE { | ||
+ | ?text_corpus wdt:P31 wd:Q461183. | ||
+ | OPTIONAL { ?text_corpus wdt:P407 ?language. } | ||
+ | OPTIONAL { ?text_corpus wdt:P856 ?website. } | ||
+ | OPTIONAL { ?text_corpus wdt:P577 ?date. } | ||
+ | OPTIONAL { ?text_corpus wdt:P2043 ?size. } | ||
+ | SERVICE wikibase:label { bd:serviceParam wikibase:language "[AUTO_LANGUAGE],en". } | ||
+ | } | ||
+ | ORDER BY DESC (?languageLabel) | ||
+ | </syntaxhighlight> | ||
+ | || | ||
+ | <query _pagination="10"> | ||
+ | #defaultEndpoint:Wikidata | ||
+ | SELECT ?text_corpus ?languageLabel ?website ?date ?size | ||
+ | WHERE { | ||
+ | ?text_corpus wdt:P31 wd:Q461183. | ||
+ | OPTIONAL { ?text_corpus wdt:P407 ?language. } | ||
+ | OPTIONAL { ?text_corpus wdt:P856 ?website. } | ||
+ | OPTIONAL { ?text_corpus wdt:P577 ?date. } | ||
+ | OPTIONAL { ?text_corpus wdt:P2043 ?size. } | ||
+ | SERVICE wikibase:label { bd:serviceParam wikibase:language "[AUTO_LANGUAGE],en". } | ||
+ | } | ||
+ | ORDER BY DESC (?languageLabel) | ||
+ | </query> | ||
+ | |} | ||
+ | |||
+ | |||
+ | === ✅ Wikidata item with coordinates ([[d:P:P625]]) and pronunciation ([[d:P:P443]]) === | ||
+ | {| style="width:100%" | ||
+ | |- style="vertical-align:top;" | ||
+ | |style="padding: 0 3em;width:60%"| | ||
+ | <syntaxhighlight lang="sparql"> | ||
+ | #defaultEndpoint:Wikidata | ||
+ | #defaultView:Map | ||
+ | SELECT ?id ?idLabel ?audio ?audio_ocwLabel ?coord ?image | ||
+ | WHERE { | ||
+ | SERVICE wikibase:label { bd:serviceParam wikibase:language "[AUTO_LANGUAGE],oc,fr,en". } | ||
+ | ?id wdt:P443 ?audio. | ||
+ | ?id wdt:P625 ?coord . #coordonnées géo | ||
+ | OPTIONAL { ?id wdt:P18 ?image } | ||
+ | } | ||
+ | </syntaxhighlight> | ||
+ | || | ||
+ | <query _pagination="10">#defaultEndpoint:Wikidata | ||
+ | #defaultView:Map | ||
+ | SELECT ?id ?idLabel ?audio ?audio_ocwLabel ?coord ?image | ||
+ | WHERE { | ||
+ | SERVICE wikibase:label { bd:serviceParam wikibase:language "[AUTO_LANGUAGE],oc,fr,en". } | ||
+ | ?id wdt:P443 ?audio. | ||
+ | ?id wdt:P625 ?coord . # geocoordinates | ||
+ | OPTIONAL { ?id wdt:P18 ?image } | ||
+ | } | ||
+ | </query> | ||
+ | |||
+ | <query _pagination="10"> | ||
+ | #defaultEndpoint:Wikidata | ||
+ | #defaultView:Map | ||
+ | SELECT (COUNT(DISTINCT ?id) as ?found) | ||
+ | WHERE { | ||
+ | SERVICE wikibase:label { bd:serviceParam wikibase:language "[AUTO_LANGUAGE],oc,fr,en". } | ||
+ | ?id wdt:P443 ?audio. | ||
+ | ?id wdt:P625 ?coord . # geocoordinates | ||
+ | } | ||
+ | </query> | ||
+ | |} | ||
+ | |||
+ | === ✅ Wikidata item with coordinates ([[d:P:P625]]) and pronunciation ([[d:P:P443]]) from Lingualibre === | ||
+ | {| style="width:100%" | ||
+ | |- style="vertical-align:top;" | ||
+ | |style="padding: 0 3em;width:60%"| | ||
+ | <syntaxhighlight lang="sparql"> | ||
+ | #defaultEndpoint:Wikidata | ||
+ | #defaultView:Map | ||
+ | SELECT ?id ?idLabel ?audio ?audioLabel ?coord ?image | ||
+ | WHERE { | ||
+ | SERVICE wikibase:label { bd:serviceParam wikibase:language "[AUTO_LANGUAGE],oc,fr,en". } | ||
+ | ?id wdt:P443 ?audio. | ||
+ | FILTER(CONTAINS(STR(?audio), "LL-")) | ||
+ | ?id wdt:P625 ?coord . #coordonnées géo | ||
+ | OPTIONAL { ?id wdt:P18 ?image } | ||
+ | } | ||
+ | </syntaxhighlight> | ||
+ | || | ||
+ | <query _pagination="10"> | ||
+ | #defaultEndpoint:Wikidata | ||
+ | #defaultView:Map | ||
+ | SELECT ?id ?idLabel ?audio ?audioLabel ?coord ?image | ||
+ | WHERE { | ||
+ | SERVICE wikibase:label { bd:serviceParam wikibase:language "[AUTO_LANGUAGE],oc,fr,en". } | ||
+ | ?id wdt:P443 ?audio. | ||
+ | FILTER(CONTAINS(STR(?audio), "LL-")) | ||
+ | ?id wdt:P625 ?coord . #coordonnées géo | ||
+ | OPTIONAL { ?id wdt:P18 ?image } | ||
+ | } | ||
+ | </query> | ||
+ | |||
+ | |||
+ | <query _pagination="10"> | ||
+ | #defaultEndpoint:Wikidata | ||
+ | #defaultView:Map | ||
+ | SELECT (COUNT(DISTINCT ?id) as ?found) | ||
+ | WHERE { | ||
+ | SERVICE wikibase:label { bd:serviceParam wikibase:language "[AUTO_LANGUAGE],oc,fr,en". } | ||
+ | ?id wdt:P443 ?audio. | ||
+ | FILTER(CONTAINS(STR(?audio), "LL-")) | ||
+ | ?id wdt:P625 ?coord . #coordonnées géo | ||
+ | OPTIONAL { ?id wdt:P18 ?image } | ||
+ | } | ||
+ | </query> | ||
+ | |} | ||
+ | |||
+ | === ✅ Wikidata item with coordinates ([[d:P:P625]]) and pronunciation ([[d:P:P443]]) from Lingualibre, with qualifiers === | ||
+ | |||
+ | {| style="width:100%" | ||
+ | |- style="vertical-align:top;" | ||
+ | |style="padding: 0 3em;width:60%"| | ||
+ | <syntaxhighlight lang="sparql"> | ||
+ | #defaultEndpoint:Wikidata | ||
+ | SELECT ?id ?idLabel ?audio ?audioLabel ?audioFile ?audioLangLabel ?speakerLabel | ||
+ | WHERE { | ||
+ | SERVICE wikibase:label { bd:serviceParam wikibase:language "en". } | ||
+ | ?id wdt:P443 ?audio. | ||
+ | FILTER(CONTAINS(STR(?audio), "LL-Q117707514")) # occitan whistled -Q117707514 | ||
+ | ?id wdt:P625 ?coord . # geocoordinates | ||
+ | OPTIONAL { | ||
+ | ?id p:P443 ?audioStatement . | ||
+ | ?audioStatement ps:P443 ?audioFile. | ||
+ | ?audioStatement pq:P407 ?audioLang. | ||
+ | ?audioStatement pq:P10894 ?speaker. | ||
+ | } | ||
+ | } | ||
+ | </syntaxhighlight> | ||
+ | |||
+ | <syntaxhighlight lang="sparql"> | ||
+ | #defaultEndpoint:Wikidata | ||
+ | SELECT ?id ?idLabel ?audioFile ?audioLangLabel ?speakerLabel | ||
+ | WHERE { | ||
+ | SERVICE wikibase:label { bd:serviceParam wikibase:language "en". } | ||
+ | ?id p:P443 ?audioStatement . | ||
+ | ?audioStatement ps:P443 ?audioFile. | ||
+ | FILTER(CONTAINS(STR(?audioFile), "LL-Q117707514")) # occitan whistled -Q117707514 | ||
+ | # ?id wdt:P625 ?coord . # geocoordinates | ||
+ | ?audioStatement pq:P407 ?audioLang. | ||
+ | ?audioStatement pq:P10894 ?speaker. | ||
+ | } | ||
+ | </syntaxhighlight> | ||
+ | || | ||
+ | <query _pagination="10"> | ||
+ | #defaultEndpoint:Wikidata | ||
+ | SELECT ?id ?idLabel ?audio ?audioLabel ?audioFile ?audioLangLabel ?speakerLabel | ||
+ | WHERE { | ||
+ | SERVICE wikibase:label { bd:serviceParam wikibase:language "en". } | ||
+ | ?id wdt:P443 ?audio. | ||
+ | FILTER(CONTAINS(STR(?audio), "LL-Q117707514")) # occitan whistled -Q117707514 | ||
+ | # ?id wdt:P625 ?coord . # geocoordinates | ||
+ | OPTIONAL { | ||
+ | ?id p:P443 ?audioStatement . | ||
+ | ?audioStatement ps:P443 ?audioFile. | ||
+ | ?audioStatement pq:P407 ?audioLang. | ||
+ | ?audioStatement pq:P10894 ?speaker. | ||
+ | } | ||
+ | } | ||
+ | </query> | ||
+ | |} | ||
+ | |||
+ | === ✅ Wikidata toponyms from administrative entity ([[d:Q12703]]) with Occitan and French labels === | ||
+ | :''This query can be used in Recording Studio, Step 3 : « External tool » to provide list of Wikidata toponyms. Doing so, [[User:Lingua Libre Bot]] will update their Wikidata pages with the recorded pronunciations. This will occurs the next day about 6:00 UTC.'' | ||
+ | {| style="width:100%" | ||
+ | |- style="vertical-align:top;" | ||
+ | |style="padding: 0 3em;width:60%"| | ||
+ | <syntaxhighlight lang="sparql"> | ||
+ | #defaultEndpoint:Wikidata | ||
+ | #defaultView:Map | ||
+ | SELECT DISTINCT ?id ?label ?label_fr ?coord ?population ?OSM_relation_ID | ||
+ | WHERE { | ||
+ | SERVICE wikibase:label { bd:serviceParam wikibase:language "[AUTO_LANGUAGE],oc,fr,en". } | ||
+ | VALUES ?humanSettlementTypes { | ||
+ | wd:Q515 # city | ||
+ | wd:Q3957 # town | ||
+ | # wd:Q484170 # French communes | ||
+ | wd:Q486972 # human settlement | ||
+ | wd:Q618123 # geographic feature | ||
+ | wd:Q3257686 # locality | ||
+ | wd:Q123964505 # populated item | ||
+ | } | ||
+ | VALUES ?administrativeArea { | ||
+ | wd:Q12703 # Pyrennees-Atlantic | ||
+ | # wd:Q213763 # Béarn | ||
+ | # wd:Q12538 # Haute-Garonne | ||
+ | } | ||
+ | ?id (wdt:P31/(wdt:P279*)) ?humanSettlementTypes ; | ||
+ | wdt:P131 ?administrativeArea . | ||
+ | ?id rdfs:label ?label . FILTER(LANG(?label) = "oc") | ||
+ | ?id rdfs:label ?label_fr . FILTER(LANG(?label_fr) = "fr") | ||
+ | ?id wdt:P625 ?coord . # geo coordinates | ||
+ | OPTIONAL { ?id wdt:P1082 ?population . } | ||
+ | OPTIONAL { ?id wdt:P402 ?OSM_relation_ID } | ||
+ | } | ||
+ | </syntaxhighlight> | ||
+ | || | ||
+ | <query _pagination="10"> | ||
+ | #defaultEndpoint:Wikidata | ||
+ | #defaultView:Map | ||
+ | SELECT DISTINCT ?id ?label ?label_fr ?coord ?population ?OSM_relation_ID | ||
+ | WHERE { | ||
+ | SERVICE wikibase:label { bd:serviceParam wikibase:language "[AUTO_LANGUAGE],oc,fr,en". } | ||
+ | VALUES ?humanSettlementTypes { | ||
+ | wd:Q515 # city | ||
+ | wd:Q3957 # town | ||
+ | # wd:Q484170 # French communes | ||
+ | wd:Q486972 # human settlement | ||
+ | wd:Q618123 # geographic feature | ||
+ | wd:Q3257686 # locality | ||
+ | wd:Q123964505 # populated item | ||
+ | } | ||
+ | VALUES ?administrativeArea { | ||
+ | wd:Q12703 # Pyrennees-Atlantic | ||
+ | # wd:Q213763 # Béarn | ||
+ | # wd:Q12538 # Haute-Garonne | ||
+ | } | ||
+ | ?id (wdt:P31/(wdt:P279*)) ?humanSettlementTypes ; | ||
+ | wdt:P131 ?administrativeArea . | ||
+ | ?id rdfs:label ?label . FILTER(LANG(?label) = "oc") | ||
+ | ?id rdfs:label ?label_fr . FILTER(LANG(?label_fr) = "fr") | ||
+ | ?id wdt:P625 ?coord . # geo coordinates | ||
+ | OPTIONAL { ?id wdt:P1082 ?population . } | ||
+ | OPTIONAL { ?id wdt:P402 ?OSM_relation_ID } | ||
+ | } | ||
+ | </query> | ||
+ | |||
+ | |||
+ | <query _pagination="10"> | ||
+ | #defaultEndpoint:Wikidata | ||
+ | #defaultView:Map | ||
+ | SELECT (COUNT(DISTINCT ?id) as ?found) | ||
+ | WHERE { | ||
+ | SERVICE wikibase:label { bd:serviceParam wikibase:language "[AUTO_LANGUAGE],oc,fr,en". } | ||
+ | VALUES ?humanSettlementTypes { | ||
+ | wd:Q515 # city | ||
+ | wd:Q3957 # town | ||
+ | # wd:Q484170 # French communes | ||
+ | wd:Q486972 # human settlement | ||
+ | wd:Q618123 # geographic feature | ||
+ | wd:Q3257686 # locality | ||
+ | wd:Q123964505 # populated item | ||
+ | } | ||
+ | VALUES ?administrativeArea { | ||
+ | wd:Q12703 # Pyrennees-Atlantic | ||
+ | } | ||
+ | ?id (wdt:P31/(wdt:P279*)) ?humanSettlementTypes ; | ||
+ | wdt:P131 ?administrativeArea . | ||
+ | ?id rdfs:label ?label . FILTER(LANG(?label) = "oc") | ||
+ | ?id rdfs:label ?label_fr . FILTER(LANG(?label_fr) = "fr") | ||
+ | ?id wdt:P625 ?coord . # geo coordinates | ||
+ | } | ||
+ | </query> | ||
+ | |} | ||
+ | |||
+ | === ✅ Wikidata toponyms from administrative district ([[d:484170]]) in French labels === | ||
+ | :''This query can be used in Recording Studio, Step 3 : « External tool » to provide list of Wikidata toponyms. Doing so, [[User:Lingua Libre Bot]] will update their Wikidata pages with the recorded pronunciations. This will occurs the next day about 6:00 UTC.'' | ||
+ | {| style="width:100%" | ||
+ | |- style="vertical-align:top;" | ||
+ | |style="padding: 0 3em;width:60%"| | ||
+ | <syntaxhighlight lang="sparql"> | ||
+ | #defaultEndpoint:Wikidata | ||
+ | #defaultView:Map | ||
+ | SELECT DISTINCT ?id ?label WHERE { | ||
+ | # SERVICE wikibase:label { bd:serviceParam wikibase:language "[AUTO_LANGUAGE]". } | ||
+ | ?id (wdt:P31/(wdt:P279*)) wd:Q484170 ; # Commune de France | ||
+ | wdt:P131 wd:Q3342. # Cote d'or | ||
+ | ?id rdfs:label ?label . FILTER(LANG(?label) = "fr") | ||
+ | } LIMIT 1000 | ||
+ | </syntaxhighlight> | ||
+ | || | ||
+ | <query _pagination="10"> | ||
+ | #defaultEndpoint:Wikidata | ||
+ | SELECT DISTINCT ?id ?label WHERE { | ||
+ | # SERVICE wikibase:label { bd:serviceParam wikibase:language "[AUTO_LANGUAGE]". } | ||
+ | ?id (wdt:P31/(wdt:P279*)) wd:Q484170 ; # Commune de France | ||
+ | wdt:P131 wd:Q3342. # Cote d'or | ||
+ | ?id rdfs:label ?label . FILTER(LANG(?label) = "fr") | ||
+ | } LIMIT 1000 | ||
+ | </query> | ||
+ | |} | ||
+ | |||
+ | === ✅ Wikidata toponyms from administrative district ([[d:Q12700]]) with French labels but NO Occitan labels === | ||
+ | :''This query can be used in Recording Studio, Step 3 : « External tool » to provide list of Wikidata toponyms. Doing so, [[User:Lingua Libre Bot]] will update their Wikidata pages with the recorded pronunciations. This will occurs the next day about 6:00 UTC.'' | ||
+ | {| style="width:100%" | ||
+ | |- style="vertical-align:top;" | ||
+ | |style="padding: 0 3em;width:60%"| | ||
+ | <syntaxhighlight lang="sparql"> | ||
+ | #defaultEndpoint:Wikidata | ||
+ | SELECT DISTINCT ?id ?label ?frwikiArticle ?instanceEndTime | ||
+ | WHERE { | ||
+ | ?id (wdt:P31/(wdt:P279*)) wd:Q484170; | ||
+ | wdt:P131 wd:Q12703. | ||
+ | # If occitan label, filter item out | ||
+ | MINUS { | ||
+ | ?id rdfs:label ?labels. | ||
+ | FILTER((LANG(?labels)) = "oc") | ||
+ | } | ||
+ | ?id rdfs:label ?label. | ||
+ | FILTER((LANG(?label)) = "fr") | ||
+ | |||
+ | # BELOW IS OPTIONAL, TO TEST SPARQL FEATURES | ||
+ | # Title fr.wikipedia.org page | ||
+ | OPTIONAL { | ||
+ | ?frwikiArticle schema:about ?id; | ||
+ | schema:isPartOf <https://fr.wikipedia.org/>. | ||
+ | } | ||
+ | # End time | ||
+ | OPTIONAL { | ||
+ | ?id p:P31 ?instanceStatement. | ||
+ | ?instanceStatement ps:P31 ?instanceOf; | ||
+ | pq:P582 ?instanceEndTime. | ||
+ | } | ||
+ | } | ||
+ | </syntaxhighlight> | ||
+ | || | ||
+ | <query _pagination="10"> | ||
+ | #defaultEndpoint:Wikidata | ||
+ | SELECT DISTINCT ?id ?label ?frwikiArticle ?instanceEndTime | ||
+ | WHERE { | ||
+ | ?id (wdt:P31/(wdt:P279*)) wd:Q484170; | ||
+ | wdt:P131 wd:Q12703. | ||
+ | # If occitan label, filter item out | ||
+ | MINUS { | ||
+ | ?id rdfs:label ?labels. | ||
+ | FILTER((LANG(?labels)) = "oc") | ||
+ | } | ||
+ | ?id rdfs:label ?label. | ||
+ | FILTER((LANG(?label)) = "fr") | ||
+ | # Title fr.wikipedia.org page | ||
+ | OPTIONAL { | ||
+ | ?frwikiArticle schema:about ?id; | ||
+ | schema:isPartOf <https://fr.wikipedia.org/>. | ||
+ | } | ||
+ | # End time | ||
+ | OPTIONAL { | ||
+ | ?id p:P31 ?instanceStatement. | ||
+ | ?instanceStatement ps:P31 ?instanceOf; | ||
+ | pq:P582 ?instanceEndTime. | ||
+ | } | ||
+ | } | ||
</query> | </query> | ||
|} | |} | ||
Line 426: | Line 1,482: | ||
== All properties with their Wikidata equivalent (if it exists) == | == All properties with their Wikidata equivalent (if it exists) == | ||
+ | :''See also [[Special:ListProperties]].'' | ||
{| style="width:100%" | {| style="width:100%" | ||
|- style="vertical-align:top;" | |- style="vertical-align:top;" | ||
|style="padding: 0 3em;width:60%"| | |style="padding: 0 3em;width:60%"| | ||
<syntaxhighlight lang="sparql"> | <syntaxhighlight lang="sparql"> | ||
− | SELECT | + | #defaultEndpoint:Lingualibre |
− | { ?propLili rdf:type owl:ObjectProperty } | + | SELECT |
− | UNION | + | (SUBSTR(STR(?propLili),38) AS ?QidNum) |
− | { ?propLili rdf:type owl:DatatypeProperty } | + | ?propLiliClaimLabel ?propLili ?propWD |
− | OPTIONAL { | + | WHERE { |
− | + | # { ?propLili rdf:type owl:ObjectProperty } | |
− | + | # UNION | |
− | } | + | # { ?propLili rdf:type owl:DatatypeProperty } |
+ | OPTIONAL { ?propLiliClaim <http://wikiba.se/ontology#directClaim> ?propLili ; prop:P12 ?propWD } | ||
+ | SERVICE wikibase:label { bd:serviceParam wikibase:language "[AUTO_LANGUAGE],en". } | ||
} | } | ||
+ | ORDER BY xsd:integer(?QidNum) | ||
</syntaxhighlight> | </syntaxhighlight> | ||
|| | || | ||
− | <query _pagination=" | + | <query _pagination="15"> |
− | SELECT | + | #defaultEndpoint:Lingualibre |
− | { ?propLili rdf:type owl:ObjectProperty } UNION { ?propLili rdf:type owl:DatatypeProperty } | + | SELECT |
+ | (SUBSTR(STR(?propLili),38) AS ?QidNum) | ||
+ | ?propLiliClaimLabel ?propLili ?propWD | ||
+ | WHERE { | ||
+ | # { ?propLili rdf:type owl:ObjectProperty } | ||
+ | # UNION | ||
+ | # { ?propLili rdf:type owl:DatatypeProperty } | ||
OPTIONAL { ?propLiliClaim <http://wikiba.se/ontology#directClaim> ?propLili ; prop:P12 ?propWD } | OPTIONAL { ?propLiliClaim <http://wikiba.se/ontology#directClaim> ?propLili ; prop:P12 ?propWD } | ||
+ | SERVICE wikibase:label { bd:serviceParam wikibase:language "[AUTO_LANGUAGE],en". } | ||
} | } | ||
+ | ORDER BY xsd:integer(?QidNum) | ||
</query> | </query> | ||
|} | |} | ||
== See also == | == See also == | ||
− | {{ | + | {{Technicals}} |
Latest revision as of 17:40, 6 June 2024
Speakers
✅ Speakers → Username containing reserved sign `-
`
- Lists declared speakers accounts, different from speakers account with 1+ recordings.
- See also T297635 : Lingualibre filename separator should be mass migrated from
-
to—
, without breaking usernames nor words.
#defaultEndpoint:Lingualibre
SELECT *
WHERE {
?id prop:P2 entity:Q3 .
SERVICE wikibase:label {
bd:serviceParam wikibase:language "[AUTO_LANGUAGE],en" .
?id rdfs:label ?name .
}
BIND (regex(STR(?name),"-") AS ?has_fields_separator_in_username)
}
ORDER BY DESC (?has_fields_separator_in_username)
|
|
#defaultEndpoint:Lingualibre
SELECT ?has_fields_separator_in_username (COUNT(?has_fields_separator_in_username) AS ?found)
WHERE {
?id prop:P2 entity:Q3 .
SERVICE wikibase:label {
bd:serviceParam wikibase:language "[AUTO_LANGUAGE],en" .
?id rdfs:label ?name .
}
BIND (regex(STR(?name),"-") AS ?has_fields_separator_in_username)
# filter( regex(?name, "-" ))
}
#ORDER BY DESC (?has_fields_separator_in_username)
GROUP BY (?has_fields_separator_in_username)
|
|
✅ Recordings → Gascon `Q930` recordings containing reserved sign `-
`
- See also T297635 : Lingualibre filename separator should be mass migrated from
-
to—
, without breaking usernames nor words.
#defaultEndpoint:Lingualibre
SELECT *
WHERE {
?id prop:P2 entity:Q2 .
?id prop:P4 entity:Q930 .
SERVICE wikibase:label {
bd:serviceParam wikibase:language "[AUTO_LANGUAGE],en" .
?id rdfs:label ?name .
}
BIND (regex(STR(?name),"-") AS ?has_fields_separator_in_written_word)
}
ORDER BY DESC (?has_fields_separator_in_written_word)
|
|
#defaultEndpoint:Lingualibre
SELECT ?has_fields_separator_in_username (COUNT(?has_fields_separator_in_username) AS ?found)
WHERE {
?id prop:P2 entity:Q2 .
?id prop:P4 entity:Q930 .
SERVICE wikibase:label {
bd:serviceParam wikibase:language "[AUTO_LANGUAGE],en" .
?id rdfs:label ?name .
}
BIND (regex(STR(?name),"-") AS ?has_fields_separator_in_written_word)
# filter( regex(?name, "-" ))
}
#ORDER BY DESC (?has_fields_separator_in_written_word)
GROUP BY (?has_fields_separator_in_written_word)
|
|
✅ Speakers → Speakers of obsolete languages
- Should be maintained to 0.
#defaultEndpoint:Lingualibre
SELECT ?speaker ?speakerLabel
WHERE {
# Obsolete languages items (duplicata and redirects)
# Chinese Q130 → Q113
# Mossi Q170137 → Q359
# Duala Q52071 → Q73
VALUES ?i18nQid { entity:Q130 entity:Q170137 entity:Q52071 }
?speaker prop:P2 entity:Q3 . # Filter: audios
?speaker prop:P4 ?i18nQid . # Filter: P4 language is Q130/Q170137/Q52071 ;
# Add Labels
SERVICE wikibase:label { bd:serviceParam wikibase:language "[AUTO_LANGUAGE],en" . }
}
|
|
✅ Speakers → Undefined place of residence
- The following may need precision. If stale, it mean none was found.
#defaultEndpoint:Lingualibre
SELECT ?speaker ?speakerLabel ?localisationLabel ?languageLabel (COUNT(?audio) AS ?audio)
WHERE {
?speaker prop:P2 entity:Q3 .
FILTER NOT EXISTS { ?speaker prop:P14 ?localisation }
?audio prop:P5 ?speaker . # Filter: P5 'speaker' is Q445757 'SangeetaRH'
?audio prop:P4 ?language . # Filter: P4 'language' is Q34 'Marathi'
# Add labels
SERVICE wikibase:label {bd:serviceParam wikibase:language "[AUTO_LANGUAGE],en"}
}
GROUP BY ?speaker ?speakerLabel ?localisationLabel ?languageLabel # Sorting first groups per language and speaker
ORDER BY DESC (?audio)
|
|
#defaultEndpoint:Lingualibre
SELECT ?type (COUNT(DISTINCT ?user) AS ?users)
WHERE {
?item prop:P2 entity:Q3 . # Filter: is Q3 `speaker`
?item prop:P2 ?type .
?item prop:P11 ?user .
FILTER NOT EXISTS { ?item prop:P14 []. }
# Add labels to each variable used.
SERVICE wikibase:label { bd:serviceParam wikibase:language "fr,en". }
} GROUP BY ?type
|
|
✅ Speakers → Non-documented genders values
- This query returns speakers who may have willfully declined to document a gender. See also list of genders.
#defaultEndpoint:Lingualibre
SELECT ?item ?itemLabel ?filledGenderLabel
WHERE {
?item prop:P2 entity:Q3 .
{ ?item prop:P8 entity:Q710460 . } # Filter: 'gender' is 'not documented'
?item prop:P8 ?filledGender .
# Add labels to each variable used.
SERVICE wikibase:label {
bd:serviceParam wikibase:language "[AUTO_LANGUAGE],en" .
}
}
|
|
✅ Speakers → missing gender value
- This query returns speakers who have missing gender value. See also list of genders.
#defaultEndpoint:Lingualibre
SELECT ?speaker ?speakerLabel ?genderLabel ?languageLabel (COUNT(?audio) AS ?audio)
WHERE {
?speaker prop:P2 entity:Q3 .
FILTER NOT EXISTS { ?speaker prop:P8 ?gender }
?audio prop:P5 ?speaker . # Filter: P5 'speaker' is Q445757 'SangeetaRH'
?audio prop:P4 ?language . # Filter: P4 'language' is Q34 'Marathi'
# Add labels
SERVICE wikibase:label {bd:serviceParam wikibase:language "[AUTO_LANGUAGE],en"}
}
GROUP BY ?speaker ?speakerLabel ?genderLabel ?languageLabel # Sorting first groups per language and speaker
ORDER BY DESC (?audio)
|
|
Recordings
✅ Recordings → With language `P4` as Chinese writing
`Q130` to change to cmn
`Q113`
- ✅ Users linguistic profile has been corrected into Q359. Erroneous recordings language (P4) on Lingualibre, while Commons use correct Wikidata language Qid.
#defaultEndpoint:Lingualibre
SELECT ?langLabel ?isoLabel ?speaker ?speakerLabel ?audio ?audioLabel
WHERE {
?audio prop:P4 entity:Q130 . # Filter: P4 language is Q130 zho ;
?audio prop:P2 entity:Q2 . # Filter: audios
?audio prop:P4 ?lang .
?audio prop:P5 ?speaker .
?lang prop:P13 ?iso .
# Add Labels
SERVICE wikibase:label { bd:serviceParam wikibase:language "[AUTO_LANGUAGE],en" . }
} ORDER BY ASC(?isoLabel)
# Helper: Chinese writing zho:Q130/wd:Q7850 ; Chinese mandarin cmn:Q113/wd:Q9192 .
|
|
#defaultEndpoint:Lingualibre
SELECT ?isoLabel (COUNT(?iso) AS ?found)
WHERE {
?audio prop:P4 entity:Q130 . # Filter: P4 language is Q130 zho ;
?audio prop:P2 entity:Q2 . # Filter: audios
?audio prop:P4 ?lang .
?lang prop:P13 ?iso .
# Add Labels
SERVICE wikibase:label { bd:serviceParam wikibase:language "[AUTO_LANGUAGE],en" . }
} GROUP BY ?isoLabel
# Helper: Chinese writing zho:Q130/wd:Q7850 ; Chinese mandarin cmn:Q113/wd:Q9192
|
|
[?] Recordings → With with corrupted information
- ✅ Users linguistic profile has been corrected.
#defaultEndpoint:Lingualibre
SELECT ?lang
(SUBSTR(STR(?speaker),32) AS ?SpeakerQid) ?speakerLabel
?audio ?audioLabel
?url (SUBSTR(STR(?urlLabel),52) AS ?filename)
WHERE {
# Obsolete languages items (duplicata and redirects)
# Chinese Q130 → Q113
# Mossi Q170137 → Q359
# Duala Q52071 → Q73
VALUES ?i18nQid { entity:Q130 entity:Q170137 entity:Q52071 }
{ ?audio prop:P4 ?i18nQid . } # Filter: P4 language is Q130/Q170137/Q52071 ;
# ?audio prop:P4 entity:Q170137 . # Filter: P4 language is Q170137 (redirect) ;
?audio prop:P2 entity:Q2 . # Filter: audios
?audio prop:P4 ?lang .
?audio prop:P5 ?speaker .
?audio prop:P3 ?url .
# Add Labels
SERVICE wikibase:label { bd:serviceParam wikibase:language "[AUTO_LANGUAGE],en" . }
}
# ORDER BY ASC(?audio)
# GROUP BY ?lang ?SpeakerQid ?speakerLabel
|
|
Counts
#defaultEndpoint:Lingualibre
SELECT ?lang ?langLabel ?iso
?speaker ?speakerLabel
(COUNT(?audio) AS ?found)
WHERE {
# Obsolete languages items (duplicata and redirects)
# Chinese Q130 → Q113
# Mossi Q170137 → Q359
# Duala Q52071 → Q73
VALUES ?i18nQid { entity:Q130 entity:Q170137 entity:Q52071 }
{ ?audio prop:P4 ?i18nQid . } # Filter: P4 language is Q130/Q170137/Q52071 ;
?audio prop:P2 entity:Q2 . # Filter: audios
?audio prop:P4 ?lang .
OPTIONAL { ?lang prop:P13 ?iso . }
?audio prop:P5 ?speaker .
?audio prop:P3 ?url .
# Add Labels
SERVICE wikibase:label { bd:serviceParam wikibase:language "[AUTO_LANGUAGE],en" . }
}
GROUP BY ?lang ?langLabel ?iso ?speaker ?speakerLabel
ORDER BY ?lang
|
|
Languages
✅ LL Languages → duplicata by Wikidata ID
- Duplicated languages can be merged. If stale, it mean none was found.
#defaultEndpoint:Lingualibre
SELECT ?idWD (COUNT(?item) AS ?count) (GROUP_CONCAT(?item) AS ?items)
WHERE {
?item prop:P2 entity:Q4 ;
prop:P12 ?idWD .
}
GROUP BY ?idWD
HAVING ( ?count > 1 )
|
|
✅ LL Languages → LL Qid, records, speakers
- Note: If some languageLabels display full uri, those are remains of duplicate language items now merged, one being a redirect. Erroneous data should be corrected or deleted on both Commons and Lingualibre's recordings. User:Yug has Dragons Bot for that.
#defaultEndpoint:Lingualibre
SELECT
?language
?languageLabel
(COUNT(DISTINCT ?record) AS ?records)
(COUNT(DISTINCT ?speaker) AS ?speakers)
WHERE {
?record prop:P2 entity:Q2 .
# If all speakers P5 corrected, recordings still accounted for
OPTIONAL { ?record prop:P5 ?speaker . }
?record prop:P4 ?language .
SERVICE wikibase:label { bd:serviceParam wikibase:language "[AUTO_LANGUAGE],en". }
}
GROUP BY ?language ?languageLabel
ORDER BY ?languageLabel
|
|
See also
Sections above : #Recordings for corrupt data to fix.
✅ LL Languages → languages by type (if it exists)
- Note: query to improve.
#defaultEndpoint:Lingualibre
SELECT ?language ?languageLabel ?code ?type ?typeLabel
WHERE {
?language prop:P2 entity:Q4 .
OPTIONAL { ?language prop:P13 ?code } .
OPTIONAL {
?language rdfs:label ?languageLabel .
FILTER( lang(?languageLabel) = "en" ) } .
OPTIONAL { ?language prop:P24 ?type } .
SERVICE wikibase:label {
bd:serviceParam wikibase:language "[AUTO_LANGUAGE],en" .
}
}
ORDER BY DESC (?typeLabel)
|
|
✅ LL Languages → média types
#defaultEndpoint:Lingualibre
SELECT ?id ?idLabel
WHERE {
?id prop:P2 entity:Q88888 .
SERVICE wikibase:label { bd:serviceParam wikibase:language "fr,en". }
}
|
|
✅ LL Languages → language with media type (P24) is video (Q88890)
#defaultEndpoint:Lingualibre
SELECT ?id ?idLabel WHERE {
?id prop:P2 entity:Q4 .
?id prop:P24 entity:Q88890 .
SERVICE wikibase:label { bd:serviceParam wikibase:language "fr,en". }
}
|
|
✅ LL Languages → language with media type (P24) is missing
- Empty if displaying rotating animation too long.
#defaultEndpoint:Lingualibre
SELECT ?id ?idLabel ?type ?typeLabel
WHERE {
?id prop:P2 entity:Q4 .
FILTER NOT EXISTS {
?id prop:P24 [].
}
SERVICE wikibase:label { bd:serviceParam wikibase:language "fr,en". }
}
|
|
✅ LL Languages → language with commons category (P26) is missing
- Empty if displaying rotating animation too long.
#defaultEndpoint:Lingualibre
SELECT ?language ?languageLabel ?iso
(URL(CONCAT('<a href=https://commons.wikimedia.org/wiki/Category:Lingua_Libre_pronunciation-',?iso,'>',?iso,'</a>')) AS ?cat)
WHERE {
?record prop:P2 entity:Q2 .
?record prop:P4 ?language .
FILTER NOT EXISTS {
?language prop:P26 [].
}
?language prop:P13 ?iso .
SERVICE wikibase:label { bd:serviceParam wikibase:language "fr,en". }
} GROUP BY ?language ?languageLabel ?iso ?cat
|
|
✅ Languages with media type video → written word (P7), url (P3) speakers (P5)
#defaultEndpoint:Lingualibre
SELECT ?word ?filename ?speaker WHERE {
?record prop:P4 entity:Q99628 .
?record prop:P2 entity:Q2 .
?record prop:P7 ?word .
?record prop:P3 ?filename .
?record prop:P5 ?speakerItem .
?speakerItem rdfs:label
?speaker filter ( lang( ?speaker ) = "en" ) .
}
|
|
✅ Languages iso from SignIt → relevant data
- This is based on Translatewiki:Translating:Lingua_Libre_SignIt and helps https://github.com/lingua-libre/Signit .
# List from https://translatewiki.net/wiki/Translating:Lingua_Libre_SignIt#sortable:3=desc
# 2023.07.26
#defaultEndpoint:Wikidata
SELECT ?wdQid ?wikimediaCode ?i18nCode ?labelEN
(SAMPLE(?nativeLabel) as ?labelNative)
WHERE {
# languages & scripts
VALUES ?i18nCode {
"anp" "ar" "bn" "br" "de" "en" "es" "fa" "fi" "fr"
"he" "hi" "ia" "id" "it" "ja" "kk-cyrl" "ko" "krc" "lmo"
"mk" "ms" "nb" "pnb" "pt" "pt-br" "qqq" "ru" "scn" "sl"
"sv" "sw" "tl" "tr" "uk" "zh-hans" "zh-hant" "mnw" "hu"
"kk" "zh"
}
# Scripts, not languages
VALUES ?i18nScript { "kk-cyrl" "zh-hans" "zh-hant" }
{ ?langId wdt:P218 ?i18nCode. } # has for iso 639-1 code
UNION {?langId wdt:P219 ?i18nCode. } # has for iso 639-2 code
UNION {?langId wdt:P220 ?i18nCode. } # has for iso 639-3 code
UNION {?langId wdt:P305 ?i18nCode. } # has for isoIETF code
# UNION {?langId wdt:P31 wd:Q1149626 ; # has for instance written language
# wdt:P424 ?i18nScript ; # has for wikimedia code
# rdfs:label ?labelEN . }
# UNION { ?langId wdt:P424 ?i18nCode. } # has for wikimedia code
OPTIONAL { ?langId wdt:P424 ?wikimediaCode. }
OPTIONAL { ?langId wdt:P1705 ?native. }
# wdt:P10369 ?lingualibreQid ;
?langId rdfs:label ?labelEN .
FILTER ( lang(?labelEN) = "en" )
BIND(REPLACE(STR(?langId), ".*/Q", "Q") AS ?wdQid)
BIND(CONCAT(UCASE(SUBSTR(?native, 1 , 1 )), SUBSTR(?native, 2 )) AS ?nativeLabel)
}
GROUP BY ?wdQid ?wikimediaCode ?i18nCode ?labelEN
ORDER BY ASC(?i18nCode)
|
|
✅ LL's Languages → WD: with Lingua Libre ID (P10369)
- To create.
#defaultEndpoint:Wikidata
# MediaWiki:LanguagesPopulationData.js
# defaultView:Table
# Run on WDQS <---------------------------------------------------
# Same can apply to languages :
# Q3→Q4 : items speaker and language
# P14→P12 : items WD location and WD language
# P5→P4 : properties speaker and languages
# P625→P1098 : properties location and population
#
PREFIX ll: <https://lingualibre.org/entity/>
PREFIX llt: <https://lingualibre.org/prop/direct/>
#
SELECT
(SAMPLE(STR(?languageLabelNative_)) AS ?languageLabelNative)
(SAMPLE(STR(?isoLabel_)) AS ?isoLabel)
?itemLabel ?item
?wikidataURL
?LinguaLibreID
# On Lingualibre, get item's info
WITH {
SELECT *
WHERE {
SERVICE <https://lingualibre.org/sparql> { # Commented on LLQS only
SELECT ?item ?itemLabel ?wikidata # (COUNT(?record) AS ?records)
{
?item llt:P2 ll:Q4 ;
rdfs:label ?itemLabel;
llt:P12 ?wikidata .
FILTER EXISTS { ?record llt:P4 ?item }
FILTER (LANG(?itemLabel)='en')
FILTER (regex(?wikidata, '^Q'))
} GROUP BY ?item ?itemLabel ?wikidata
} # Commented on LLQS only
}
} AS %infoWikidataId
# On Wikidata, get the target info
WHERE {
INCLUDE %infoWikidataId
BIND (URI(CONCAT("http://www.wikidata.org/entity/", ?wikidata)) AS ?wikidataURL)
SERVICE <https://query.wikidata.org/sparql> {
SELECT ?wikidataURL ?LinguaLibreID ?languageLabelNative_ ?isoLabel_ {
OPTIONAL { ?wikidataURL wdt:P10369 ?LinguaLibreID . }
OPTIONAL { ?wikidataURL wdt:P1705 ?languageLabelNative_ . }
OPTIONAL { ?wikidataURL wdt:P218 ?iso639_1 ; rdfs:label ?isoLabel_ . FILTER(LANG(?isoLabel_)=?iso639_1) . }
}
}
}
GROUP BY ?itemLabel ?item ?wikidataURL ?LinguaLibreID
ORDER BY (?LinguaLibreID)
|
|
❌ LL's Languages → WD: without Lingua Libre ID (P10369)
- To create.
#defaultEndpoint:Wikidata
|
|
❌ LL's Languages → WD → en.wikipedia.org : article pagename
- To create.
#defaultEndpoint:Wikidata
|
|
✅ LL Languages → by date of first recording
Basic-slow query
#defaultEndpoint:Lingualibre
SELECT ?lang ?langLabel (SUBSTR(MIN(?date), 1, 10) AS ?first )
WHERE {
?audio prop:P4 ?lang ;
prop:P6 ?date .
SERVICE wikibase:label { bd:serviceParam wikibase:language "en". }
}
GROUP BY ?lang ?langLabel
ORDER BY (?first)
|
|
Faster query
#defaultEndpoint:Lingualibre
SELECT ?lang ?langLabel (SUBSTR(STR(?first),1,10) AS ?First)
(CONCAT('<a href=https://commons.wikimedia.org/wiki/Category:Lingua_Libre_pronunciation-',?iso,'>',?iso,'</a>') AS ?cat)
WHERE {
SERVICE wikibase:label { bd:serviceParam wikibase:language "en". }
{ SELECT ?lang ?iso (MIN(?date) AS ?first)
WHERE {
?audio prop:P4 ?lang ;
prop:P6 ?date .
?lang prop:P13 ?iso .
} GROUP BY ?lang ?iso
}
} ORDER BY DESC (?First)
|
|
✅ WD Languages → language status (P3823,P1999)
#defaultEndpoint:Wikidata
SELECT ?item ?itemLabel ?statusUNLabel ?statusEthnoLabel
WHERE {
SERVICE wikibase:label { bd:serviceParam wikibase:language "[AUTO_LANGUAGE],en". }
?item wdt:P31 wd:Q34770.
OPTIONAL { ?item wdt:P1999 ?statusUN. }
OPTIONAL { ?item wdt:P3823 ?statusEthno. }
}
ORDER BY DESC (?itemLabel)
|
|
✅ Is corpora (d:Q461183) → Languages (d:P:P407)
#defaultEndpoint:Wikidata
SELECT ?text_corpus ?languageLabel ?website ?date ?size
WHERE {
?text_corpus wdt:P31 wd:Q461183.
OPTIONAL { ?text_corpus wdt:P407 ?language. }
OPTIONAL { ?text_corpus wdt:P856 ?website. }
OPTIONAL { ?text_corpus wdt:P577 ?date. }
OPTIONAL { ?text_corpus wdt:P2043 ?size. }
SERVICE wikibase:label { bd:serviceParam wikibase:language "[AUTO_LANGUAGE],en". }
}
ORDER BY DESC (?languageLabel)
|
|
✅ Wikidata item with coordinates (d:P:P625) and pronunciation (d:P:P443)
#defaultEndpoint:Wikidata
#defaultView:Map
SELECT ?id ?idLabel ?audio ?audio_ocwLabel ?coord ?image
WHERE {
SERVICE wikibase:label { bd:serviceParam wikibase:language "[AUTO_LANGUAGE],oc,fr,en". }
?id wdt:P443 ?audio.
?id wdt:P625 ?coord . #coordonnées géo
OPTIONAL { ?id wdt:P18 ?image }
}
|
|
✅ Wikidata item with coordinates (d:P:P625) and pronunciation (d:P:P443) from Lingualibre
#defaultEndpoint:Wikidata
#defaultView:Map
SELECT ?id ?idLabel ?audio ?audioLabel ?coord ?image
WHERE {
SERVICE wikibase:label { bd:serviceParam wikibase:language "[AUTO_LANGUAGE],oc,fr,en". }
?id wdt:P443 ?audio.
FILTER(CONTAINS(STR(?audio), "LL-"))
?id wdt:P625 ?coord . #coordonnées géo
OPTIONAL { ?id wdt:P18 ?image }
}
|
|
✅ Wikidata item with coordinates (d:P:P625) and pronunciation (d:P:P443) from Lingualibre, with qualifiers
#defaultEndpoint:Wikidata
SELECT ?id ?idLabel ?audio ?audioLabel ?audioFile ?audioLangLabel ?speakerLabel
WHERE {
SERVICE wikibase:label { bd:serviceParam wikibase:language "en". }
?id wdt:P443 ?audio.
FILTER(CONTAINS(STR(?audio), "LL-Q117707514")) # occitan whistled -Q117707514
?id wdt:P625 ?coord . # geocoordinates
OPTIONAL {
?id p:P443 ?audioStatement .
?audioStatement ps:P443 ?audioFile.
?audioStatement pq:P407 ?audioLang.
?audioStatement pq:P10894 ?speaker.
}
}
#defaultEndpoint:Wikidata
SELECT ?id ?idLabel ?audioFile ?audioLangLabel ?speakerLabel
WHERE {
SERVICE wikibase:label { bd:serviceParam wikibase:language "en". }
?id p:P443 ?audioStatement .
?audioStatement ps:P443 ?audioFile.
FILTER(CONTAINS(STR(?audioFile), "LL-Q117707514")) # occitan whistled -Q117707514
# ?id wdt:P625 ?coord . # geocoordinates
?audioStatement pq:P407 ?audioLang.
?audioStatement pq:P10894 ?speaker.
}
|
|
✅ Wikidata toponyms from administrative entity (d:Q12703) with Occitan and French labels
- This query can be used in Recording Studio, Step 3 : « External tool » to provide list of Wikidata toponyms. Doing so, User:Lingua Libre Bot will update their Wikidata pages with the recorded pronunciations. This will occurs the next day about 6:00 UTC.
#defaultEndpoint:Wikidata
#defaultView:Map
SELECT DISTINCT ?id ?label ?label_fr ?coord ?population ?OSM_relation_ID
WHERE {
SERVICE wikibase:label { bd:serviceParam wikibase:language "[AUTO_LANGUAGE],oc,fr,en". }
VALUES ?humanSettlementTypes {
wd:Q515 # city
wd:Q3957 # town
# wd:Q484170 # French communes
wd:Q486972 # human settlement
wd:Q618123 # geographic feature
wd:Q3257686 # locality
wd:Q123964505 # populated item
}
VALUES ?administrativeArea {
wd:Q12703 # Pyrennees-Atlantic
# wd:Q213763 # Béarn
# wd:Q12538 # Haute-Garonne
}
?id (wdt:P31/(wdt:P279*)) ?humanSettlementTypes ;
wdt:P131 ?administrativeArea .
?id rdfs:label ?label . FILTER(LANG(?label) = "oc")
?id rdfs:label ?label_fr . FILTER(LANG(?label_fr) = "fr")
?id wdt:P625 ?coord . # geo coordinates
OPTIONAL { ?id wdt:P1082 ?population . }
OPTIONAL { ?id wdt:P402 ?OSM_relation_ID }
}
|
|
✅ Wikidata toponyms from administrative district (d:484170) in French labels
- This query can be used in Recording Studio, Step 3 : « External tool » to provide list of Wikidata toponyms. Doing so, User:Lingua Libre Bot will update their Wikidata pages with the recorded pronunciations. This will occurs the next day about 6:00 UTC.
#defaultEndpoint:Wikidata
#defaultView:Map
SELECT DISTINCT ?id ?label WHERE {
# SERVICE wikibase:label { bd:serviceParam wikibase:language "[AUTO_LANGUAGE]". }
?id (wdt:P31/(wdt:P279*)) wd:Q484170 ; # Commune de France
wdt:P131 wd:Q3342. # Cote d'or
?id rdfs:label ?label . FILTER(LANG(?label) = "fr")
} LIMIT 1000
|
|
✅ Wikidata toponyms from administrative district (d:Q12700) with French labels but NO Occitan labels
- This query can be used in Recording Studio, Step 3 : « External tool » to provide list of Wikidata toponyms. Doing so, User:Lingua Libre Bot will update their Wikidata pages with the recorded pronunciations. This will occurs the next day about 6:00 UTC.
#defaultEndpoint:Wikidata
SELECT DISTINCT ?id ?label ?frwikiArticle ?instanceEndTime
WHERE {
?id (wdt:P31/(wdt:P279*)) wd:Q484170;
wdt:P131 wd:Q12703.
# If occitan label, filter item out
MINUS {
?id rdfs:label ?labels.
FILTER((LANG(?labels)) = "oc")
}
?id rdfs:label ?label.
FILTER((LANG(?label)) = "fr")
# BELOW IS OPTIONAL, TO TEST SPARQL FEATURES
# Title fr.wikipedia.org page
OPTIONAL {
?frwikiArticle schema:about ?id;
schema:isPartOf <https://fr.wikipedia.org/>.
}
# End time
OPTIONAL {
?id p:P31 ?instanceStatement.
?instanceStatement ps:P31 ?instanceOf;
pq:P582 ?instanceEndTime.
}
}
|
|
Other
All properties with their Wikidata equivalent (if it exists)
- See also Special:ListProperties.
#defaultEndpoint:Lingualibre
SELECT
(SUBSTR(STR(?propLili),38) AS ?QidNum)
?propLiliClaimLabel ?propLili ?propWD
WHERE {
# { ?propLili rdf:type owl:ObjectProperty }
# UNION
# { ?propLili rdf:type owl:DatatypeProperty }
OPTIONAL { ?propLiliClaim <http://wikiba.se/ontology#directClaim> ?propLili ; prop:P12 ?propWD }
SERVICE wikibase:label { bd:serviceParam wikibase:language "[AUTO_LANGUAGE],en". }
}
ORDER BY xsd:integer(?QidNum)
|
|