No public description

PiperOrigin-RevId: 705401605
google-research · Dec 12, 2024 · 2bb5257 · 2bb5257
1 parent b27afc4
commit 2bb5257
Show file tree

Hide file tree

Showing 32 changed files with 172 additions and 94 deletions.
diff --git a/linguameta/data/ahr.json b/linguameta/data/ahr.json
@@ -513,6 +513,11 @@
       "name": "アヒラーニー語",
       "bcp_47_code": "ja",
       "source": "WIKIDATA"
+    },
+    {
+      "name": "Khandeshi",
+      "bcp_47_code": "en",
+      "source": "WIKIPEDIA"
     }
   ],
   "language_script_locale": [

diff --git a/linguameta/data/alq.json b/linguameta/data/alq.json
@@ -226,11 +226,6 @@
       "bcp_47_code": "en",
       "source": "WIKIDATA"
     },
-    {
-      "name": "Article Name",
-      "bcp_47_code": "en",
-      "source": "WIKIDATA"
-    },
     {
       "name": "algonkin",
       "bcp_47_code": "fr",

diff --git a/linguameta/data/alz.json b/linguameta/data/alz.json
@@ -3,6 +3,7 @@
   "iso_639_3_code": "alz",
   "glottocode": "alur1250",
   "wikidata_id": "Q56507",
+  "total_population": 1700000,
   "language_scope": {
     "scope": "LANGUAGE",
     "source": "ISO_639"
@@ -586,6 +587,10 @@
         "iso_3166_code": "cd",
         "source": "GOOGLE_RESEARCH"
       },
+      "speaker_data": {
+        "number_of_speakers": 1700000,
+        "source": "WIKIPEDIA"
+      },
       "geolocation": {
         "latitude": 2.36213,
         "longitude": 31.0016,

diff --git a/linguameta/data/ba.json b/linguameta/data/ba.json
@@ -19,11 +19,6 @@
       "is_canonical": true,
       "source": "ISO_639"
     },
-    {
-      "name": "Balochi",
-      "bcp_47_code": "en",
-      "source": "GOOGLE_RESEARCH"
-    },
     {
       "name": "абашкир",
       "bcp_47_code": "ab",

diff --git a/linguameta/data/bfc.json b/linguameta/data/bfc.json
@@ -53,7 +53,6 @@
     {
       "script": {
         "iso_15924_code": "hani",
-        "is_canonical": true,
         "source": "WIKTIONARY"
       },
       "locale": {
@@ -69,6 +68,7 @@
     {
       "script": {
         "iso_15924_code": "latn",
+        "is_canonical": true,
         "is_for_transliteration": true,
         "source": "WIKTIONARY"
       },

diff --git a/linguameta/data/bfs.json b/linguameta/data/bfs.json
@@ -55,7 +55,6 @@
     {
       "script": {
         "iso_15924_code": "hani",
-        "is_canonical": false,
         "is_historical": true,
         "source": "GOOGLE_RESEARCH"
       },

diff --git a/linguameta/data/bho.json b/linguameta/data/bho.json
@@ -1307,11 +1307,6 @@
       "bcp_47_code": "pl",
       "source": "WIKIDATA"
     },
-    {
-      "name": "bh",
-      "bcp_47_code": "fr",
-      "source": "WIKIDATA"
-    },
     {
       "name": "idioma bopuri",
       "bcp_47_code": "es",
@@ -1413,11 +1408,6 @@
       "bcp_47_code": "ne",
       "source": "WIKIDATA"
     },
-    {
-      "name": "Bh",
-      "bcp_47_code": "en",
-      "source": "WIKIDATA"
-    },
     {
       "name": "bhodjpuri",
       "bcp_47_code": "nb",

diff --git a/linguameta/data/br.json b/linguameta/data/br.json
@@ -1572,11 +1572,6 @@
       "bcp_47_code": "en",
       "source": "WIKIDATA"
     },
-    {
-      "name": "Bre",
-      "bcp_47_code": "en",
-      "source": "WIKIDATA"
-    },
     {
       "name": "lingua brètuna",
       "bcp_47_code": "scn",
@@ -1612,11 +1607,6 @@
       "bcp_47_code": "br",
       "source": "WIKIDATA"
     },
-    {
-      "name": "kltg",
-      "bcp_47_code": "br",
-      "source": "WIKIDATA"
-    },
     {
       "name": "idioma bretão",
       "bcp_47_code": "pt",

diff --git a/linguameta/data/cbk.json b/linguameta/data/cbk.json
@@ -3,6 +3,7 @@
   "iso_639_3_code": "cbk",
   "glottocode": "chav1241",
   "wikidata_id": "Q33281",
+  "total_population": 700000,
   "language_scope": {
     "scope": "LANGUAGE",
     "source": "ISO_639"
@@ -972,6 +973,10 @@
         "iso_3166_code": "ph",
         "source": "GOOGLE_RESEARCH"
       },
+      "speaker_data": {
+        "number_of_speakers": 700000,
+        "source": "WIKIPEDIA"
+      },
       "geolocation": {
         "latitude": 7.435034,
         "longitude": 122.18849,

diff --git a/linguameta/data/chw.json b/linguameta/data/chw.json
@@ -3,6 +3,7 @@
   "iso_639_3_code": "chw",
   "glottocode": "chuw1238",
   "wikidata_id": "Q5118412",
+  "total_population": 1000000,
   "language_scope": {
     "scope": "LANGUAGE",
     "source": "ISO_639"
@@ -108,6 +109,10 @@
         "iso_3166_code": "mz",
         "source": "GOOGLE_RESEARCH"
       },
+      "speaker_data": {
+        "number_of_speakers": 1000000,
+        "source": "WIKIPEDIA"
+      },
       "geolocation": {
         "latitude": -17.3428,
         "longitude": 37.1231,

diff --git a/linguameta/data/cnp.json b/linguameta/data/cnp.json
@@ -2,7 +2,6 @@
   "bcp_47_code": "cnp",
   "iso_639_3_code": "cnp",
   "macrolanguage_bcp_47_code": "zh",
-  "total_population": 7000000,
   "language_scope": {
     "scope": "LANGUAGE",
     "source": "ISO_639"
@@ -23,8 +22,7 @@
   "language_script_locale": [
     {
       "script": {
-        "iso_15924_code": "hani",
-        "is_canonical": true,
+        "iso_15924_code": "hans",
         "source": "WIKIDATA"
       },
       "locale": {

diff --git a/linguameta/data/csp.json b/linguameta/data/csp.json
@@ -2,7 +2,6 @@
   "bcp_47_code": "csp",
   "iso_639_3_code": "csp",
   "macrolanguage_bcp_47_code": "zh",
-  "total_population": 7000000,
   "language_scope": {
     "scope": "LANGUAGE",
     "source": "ISO_639"
@@ -23,8 +22,7 @@
   "language_script_locale": [
     {
       "script": {
-        "iso_15924_code": "hani",
-        "is_canonical": true,
+        "iso_15924_code": "hans",
         "source": "WIKIDATA"
       },
       "locale": {

diff --git a/linguameta/data/cv.json b/linguameta/data/cv.json
@@ -1762,11 +1762,6 @@
       "bcp_47_code": "nb",
       "source": "WIKIDATA"
     },
-    {
-      "name": "Chv",
-      "bcp_47_code": "en",
-      "source": "WIKIDATA"
-    },
     {
       "name": "Çăvaşla",
       "bcp_47_code": "en",

diff --git a/linguameta/data/dyu.json b/linguameta/data/dyu.json
@@ -3,7 +3,7 @@
   "iso_639_3_code": "dyu",
   "glottocode": "dyul1238",
   "wikidata_id": "Q32706",
-  "total_population": 2600000,
+  "total_population": 2500000,
   "language_scope": {
     "scope": "LANGUAGE",
     "source": "ISO_639"
@@ -1031,13 +1031,17 @@
       "name": "ߖߎ߬ߟߊ߬ߞߊ߲",
       "bcp_47_code": "dyu",
       "source": "GOOGLE_RESEARCH"
+    },
+    {
+      "name": "Dioula",
+      "bcp_47_code": "en",
+      "source": "WIKIPEDIA"
     }
   ],
   "language_script_locale": [
     {
       "script": {
         "iso_15924_code": "latn",
-        "is_canonical": true,
         "is_in_widespread_use": true,
         "has_official_status": true,
         "source": "GOOGLE_RESEARCH"
@@ -1059,6 +1063,7 @@
     {
       "script": {
         "iso_15924_code": "nkoo",
+        "is_canonical": true,
         "has_symbolic_value": true,
         "source": "GOOGLE_RESEARCH"
       },

diff --git a/linguameta/data/fuv.json b/linguameta/data/fuv.json
@@ -4,6 +4,7 @@
   "macrolanguage_bcp_47_code": "ff",
   "glottocode": "nige1253",
   "wikidata_id": "Q36129",
+  "total_population": 14000000,
   "language_scope": {
     "scope": "LANGUAGE",
     "source": "ISO_639"
@@ -82,6 +83,10 @@
         "iso_3166_code": "ng",
         "source": "GOOGLE_RESEARCH"
       },
+      "speaker_data": {
+        "number_of_speakers": 14000000,
+        "source": "CLDR"
+      },
       "geolocation": {
         "latitude": 10.9972,
         "longitude": 11.1188,

diff --git a/linguameta/data/gno.json b/linguameta/data/gno.json
@@ -521,7 +521,6 @@
     {
       "script": {
         "iso_15924_code": "deva",
-        "is_canonical": true,
         "is_in_widespread_use": true,
         "source": "GOOGLE_RESEARCH"
       },
@@ -557,7 +556,7 @@
     {
       "script": {
         "iso_15924_code": "telu",
-        "is_canonical": false,
+        "is_canonical": true,
         "is_in_widespread_use": true,
         "source": "GOOGLE_RESEARCH"
       },

diff --git a/linguameta/data/gog.json b/linguameta/data/gog.json
@@ -3,6 +3,7 @@
   "iso_639_3_code": "gog",
   "glottocode": "gogo1263",
   "wikidata_id": "Q3272630",
+  "total_population": 1400000,
   "language_scope": {
     "scope": "LANGUAGE",
     "source": "ISO_639"
@@ -600,6 +601,10 @@
         "iso_3166_code": "tz",
         "source": "GOOGLE_RESEARCH"
       },
+      "speaker_data": {
+        "number_of_speakers": 1400000,
+        "source": "WIKIPEDIA"
+      },
       "geolocation": {
         "latitude": -6.35951,
         "longitude": 35.4807,

diff --git a/linguameta/data/hmn.json b/linguameta/data/hmn.json
@@ -997,6 +997,24 @@
       "bcp_47_code": "en",
       "is_canonical": true,
       "source": "GOOGLE_RESEARCH"
+    },
+    {
+      "name": "Hmoob",
+      "bcp_47_code": "hmn",
+      "is_canonical": true,
+      "source": "WIKIPEDIA"
+    },
+    {
+      "name": "𞄀𞄩𞄰",
+      "bcp_47_code": "hmn",
+      "is_canonical": true,
+      "source": "WIKIPEDIA"
+    },
+    {
+      "name": "𖬌𖬣𖬵",
+      "bcp_47_code": "hmn",
+      "is_canonical": true,
+      "source": "WIKIPEDIA"
     }
   ],
   "language_script_locale": [

diff --git a/linguameta/data/how.json b/linguameta/data/how.json
@@ -73,6 +73,25 @@
     {
       "script": {
         "iso_15924_code": "hani",
+        "source": "GOOGLE_RESEARCH"
+      },
+      "locale": {
+        "iso_3166_code": "cn",
+        "source": "GOOGLE_RESEARCH"
+      },
+      "speaker_data": {
+        "number_of_speakers": 140000,
+        "source": "GOOGLE_RESEARCH"
+      },
+      "geolocation": {
+        "latitude": 23.2074,
+        "longitude": 101.886,
+        "source": "GLOTTOLOG"
+      }
+    },
+    {
+      "script": {
+        "iso_15924_code": "latn",
         "is_canonical": true,
         "source": "GOOGLE_RESEARCH"
       },

diff --git a/linguameta/data/ig.json b/linguameta/data/ig.json
@@ -1705,11 +1705,6 @@
       "bcp_47_code": "lt",
       "source": "WIKIDATA"
     },
-    {
-      "name": "Ig",
-      "bcp_47_code": "en",
-      "source": "WIKIDATA"
-    },
     {
       "name": "इबो भाषा",
       "bcp_47_code": "hi",

diff --git a/linguameta/data/mni.json b/linguameta/data/mni.json
@@ -1683,7 +1683,6 @@
     {
       "script": {
         "iso_15924_code": "beng",
-        "is_canonical": true,
         "source": "GOOGLE_RESEARCH"
       },
       "locale": {
@@ -1723,6 +1722,7 @@
     {
       "script": {
         "iso_15924_code": "mtei",
+        "is_canonical": true,
         "has_official_status": true,
         "source": "GOOGLE_RESEARCH"
       },