Serbian language code update "rs" -> "sr" (#4159)

* Serbian stopwords added. (cyrillic alphabet)

* spaCy Contribution agreement included.

* Test initialize updated

* Serbian language code update. --bugfix

spacy/lang/sr/__init__.py

@@ -12,7 +12,7 @@ from ...util import update_exc, add_lookups
 
 class SerbianDefaults(Language.Defaults):
     lex_attr_getters = dict(Language.Defaults.lex_attr_getters)
-    lex_attr_getters[LANG] = lambda text: "rs"
+    lex_attr_getters[LANG] = lambda text: "sr"
     lex_attr_getters[NORM] = add_lookups(
         Language.Defaults.lex_attr_getters[NORM], BASE_NORMS
     )
@@ -21,7 +21,7 @@ class SerbianDefaults(Language.Defaults):
 
 
 class Serbian(Language):
-    lang = "rs"
+    lang = "sr"
     Defaults = SerbianDefaults
 
 

spacy/tests/lang/test_initialize.py

@@ -10,8 +10,8 @@ from spacy.util import get_lang_class
 # excluded: ja, ru, th, uk, vi, zh
 LANGUAGES = ["af", "ar", "bg", "bn", "ca", "cs", "da", "de", "el", "en", "es",
              "et", "fa", "fi", "fr", "ga", "he", "hi", "hr", "hu", "id", "is",
-             "it", "kn", "lt", "lv", "nb", "nl", "pl", "pt", "ro", "rs", "si",
-             "sk", "sl", "sq", "sv", "ta", "te", "tl", "tr", "tt", "ur"]
+             "it", "kn", "lt", "lv", "nb", "nl", "pl", "pt", "ro", "si", "sk",
+             "sl", "sq", "sr", "sv", "ta", "te", "tl", "tr", "tt", "ur"]
 # fmt: on
 
 

website/meta/languages.json

@@ -127,7 +127,7 @@
         { "code": "is", "name": "Icelandic" },
         { "code": "lt", "name": "Lithuanian" },
         { "code": "lv", "name": "Latvian" },
-        { "code": "rs", "name": "Serbian" },
+        { "code": "sr", "name": "Serbian" },
         { "code": "sk", "name": "Slovak" },
         { "code": "sl", "name": "Slovenian" },
         {