Azure Language add scriptCode, and enums for script Language Detectio…

…n Results (#26777)

* add scriptCode, and enums for script

* update name for sciptcode

* fixed policheck and spelling issue

* Add new words to custom-words.txt and update Bengala enum

custom-words.txt

@@ -194,6 +194,7 @@ arima
 arimax
 arin
 arjun
+armn
 armtemplates
 arp
 arpa
@@ -940,6 +941,7 @@ etags
 etcd
 ethereum
 ethertype
+ethi
 eucloud
 eucloudprototype
 eugps
@@ -1097,6 +1099,7 @@ geofences
 geofencing
 geojson
 geopair
+geor
 georegions
 georeplication
 geospatial
@@ -1170,6 +1173,7 @@ granularities
 graphrbac
 graphservice
 greenplum
+grek
 groundstation
 groupby
 groupedby
@@ -1186,6 +1190,7 @@ guami
 guestconfiguration
 guid
 guids
+gujr
 gurung
 guti
 gxlarge
@@ -1221,6 +1226,7 @@ healthmodels
 healthstatus
 heatbeat
 heatmap
+hebr
 hecto
 helmchart
 helpdesk
@@ -1433,6 +1439,7 @@ jobschedules
 johnc
 johndeere
 johnsmith
+jpan
 json
 jsonl
 jsonld
@@ -1473,6 +1480,7 @@ keyvaultproperties
 keyvaulturi
 keyversion
 khaling
+khmr
 khtml
 kibana
 kiswahili
@@ -1481,6 +1489,7 @@ kmgtpe
 kmph
 Kmskeyaccessdenied
 Kmskeynotfound
+knda
 knowledgebase
 knowledgebases
 koelner
@@ -1523,6 +1532,7 @@ labservices
 lajolla
 lakehouse
 languagedata
+laoo
 largefacelists
 largepersongroups
 largerc
@@ -1753,6 +1763,7 @@ mlapi
 mlflow
 mlflowtrackinguri
 mltable
+mlym
 mmtc
 mnist
 mobo
@@ -1834,6 +1845,7 @@ myimage
 mylocation
 mylog
 mymodel
+mymr
 mypath
 mypicture
 mypictures
@@ -1992,6 +2004,7 @@ octokit
 odata
 odatatype
 odbc
+odia
 oeverify
 offboard
 offboarding
@@ -2053,6 +2066,7 @@ optout
 organisation
 orgs
 originpath
+orya
 oscp
 osdisk
 osdiskforlinuxsimple
@@ -2854,6 +2868,7 @@ taginheritance
 tagname
 tagsandregions
 tagvalue
+taml
 targetduration
 taskcompletion
 taskcounts
@@ -2868,6 +2883,7 @@ teamsinterop
 telangana
 telemetryconfig
 teleportal
+telu
 tempdb
 templated
 templatelink
@@ -2896,10 +2912,12 @@ textanalytics
 tfidf
 tful
 tfvc
+thaa
 thangmi
 thirdparty
 threatintelligence
 threatintelligenceindicators
+tibt
 tilejson
 tileset
 tilesetconfiguration

specification/cognitiveservices/data-plane/Language/preview/2023-11-15-preview/analyzetext.json

@@ -4193,14 +4193,81 @@
         },
         "script": {
           "type": "string",
-          "description": "Identifies the script of the input document.",
+          "description": "Identifies the script of the input document. Maps to the ISO 15924 standard formal name.",
           "enum": [
-            "Latin"
+            "Arabic",
+            "Armenian",
+            "Bangla",
+            "UnifiedCanadianAboriginalSyllabics",
+            "Cyrillic",
+            "Devanagari",
+            "Ethiopic",
+            "Georgian",
+            "Greek",
+            "Gujarati",
+            "Gurmukhi",
+            "Hangul",
+            "HanSimplified",
+            "HanTraditional",
+            "Hebrew",
+            "Japanese",
+            "Khmer",
+            "Kannada",
+            "Lao",
+            "Latin",
+            "Malayalam",
+            "Myanmar",
+            "Odia",
+            "Sinhala",
+            "Tamil",
+            "Telugu",
+            "Thaana",
+            "Thai",
+            "Tibetan"
           ],
           "x-ms-enum": {
             "name": "ScriptKind",
             "modelAsString": true
           }
+        },
+        "scriptCode": {
+          "type": "string",
+          "description": "Identifies the script of the input document. Maps to the ISO 15924 standard script code.",
+          "enum": [
+            "Arab",
+            "Armn",
+            "Beng",
+            "Cans",
+            "Cyrl",
+            "Deva",
+            "Ethi",
+            "Geor",
+            "Grek",
+            "Gujr",
+            "Guru",
+            "Hang",
+            "Hans",
+            "Hant",
+            "Hebr",
+            "Jpan",
+            "Khmr",
+            "Knda",
+            "Laoo",
+            "Latn",
+            "Mlym",
+            "Mymr",
+            "Orya",
+            "Sinh",
+            "Taml",
+            "Telu",
+            "Thaa",
+            "Thai",
+            "Tibt"
+          ],
+          "x-ms-enum": {
+            "name": "ScriptCode",
+            "modelAsString": true
+          }
         }
       }
     },