Merge pull request #149 from googlefonts/ci-tests

Make language names unique

Author: simoncozens

Lib/gflanguages/data/languages/bdh_Latn.textproto

@@ -1,11 +1,12 @@
 id: "bdh_Latn"
 language: "bdh"
 script: "Latn"
-name: "Baka"
+name: "Baka (DRC/South Sudan)"
+autonym: "Tara Baká"
 population: 60000
 region: "CD"
 region: "SS"
 exemplar_chars {
   base: "a A b B c C d D e E f F g G h H i I ị Ị ɨ Ɨ k K l L m M n N ṇ Ṇ o O p P r R ṛ Ṛ s S t T u U ụ Ụ v V ṿ Ṿ w W y Y z Z ꞌ Ꞌ"
   marks: "◌̣ ◌́"
-}
+}

Lib/gflanguages/data/languages/beh_Latn.textproto

@@ -1,10 +1,10 @@
 id: "beh_Latn"
 language: "beh"
 script: "Latn"
-name: "Baka"
+name: "Biali"
 population: 100000
 region: "BJ"
 exemplar_chars {
   base: "a A b B c C d D e E ə Ə f F g G h H i I k K l L m M n N o O p P r R s S t T u U w W y Y"
   auxiliary: "j J q Q v V x X z Z"
-}
+}

Lib/gflanguages/data/languages/bgn_Arab.textproto

@@ -2,7 +2,7 @@ id: "bgn_Arab"
 language: "bgn"
 script: "Arab"
 name: "Western Balochi"
-preferred_name: "Balochi"
+#preferred_name: "Balochi"
 population: 2037382
 region: "AF"
 region: "IR"

Lib/gflanguages/data/languages/bkc_Latn.textproto

@@ -1,11 +1,11 @@
 id: "bkc_Latn"
 language: "bkc"
 script: "Latn"
-name: "Baka"
+name: "Baka (Cameroon/Gabon)"
 population: 71000
 region: "CM"
 region: "GA"
 exemplar_chars {
   base: "a A b B ɓ Ɓ d D ɗ Ɗ e E ɛ Ɛ f F g G h H i I j J k K l L m M n N o O ɔ Ɔ s S t T u U w W y Y"
   auxiliary: "c C p P q Q r R v V x X z Z"
-}
+}

Lib/gflanguages/data/languages/bsc_Latn_GN.textproto

@@ -1,7 +1,7 @@
 id: "bsc_Latn_GN"
 language: "bsc"
 script: "Latn"
-name: "Bassari"
+name: "Guinean Bassari"
 autonym: "oneyan"
 population: 18000
 region: "GN"

Lib/gflanguages/data/languages/bsq_Bass.textproto

@@ -1,7 +1,7 @@
 id: "bsq_Bass"
 language: "bsq"
 script: "Bass"
-name: "Bassa"
+name: "Bassa, Vah"
 population: 410000
 region: "LR"
 region: "SL"

Lib/gflanguages/data/languages/bsq_Latn.textproto

@@ -1,7 +1,7 @@
 id: "bsq_Latn"
 language: "bsq"
 script: "Latn"
-name: "Bassa"
+name: "Bassa, Latin"
 population: 410000
 region: "LR"
 region: "SL"
@@ -11,4 +11,4 @@ exemplar_chars {
   auxiliary: "l L q Q r R x X y Y z Z"
 }
 source: "“Bassa dictionary”, Christian Education Foundation in Liberia (CEFL), https://cefliberia.org/bassa/bassa-dictionary/"
-source: "Ɓǎsɔ́ɔ̀ Báɓòɔ̀, Bible Society Liberia, 2002"
+source: "Ɓǎsɔ́ɔ̀ Báɓòɔ̀, Bible Society Liberia, 2002"

Lib/gflanguages/data/languages/crh_Cyrl.textproto

@@ -1,7 +1,7 @@
 id: "crh_Cyrl"
 language: "crh"
 script: "Cyrl"
-name: "Crimean Turkish"
+name: "Crimean Turkish, Cyrillic"
 autonym: "Къырымтатар"
 population: 245968
 region: "UA"

Lib/gflanguages/data/languages/dnj_Latn_LR.textproto

@@ -1,7 +1,7 @@
 id: "dnj_Latn_LR"
 language: "dnj"
 script: "Latn"
-name: "Dan"
+name: "Liberian Dan"
 autonym: "Gio"
 population: 1099244
 region: "LR"

Lib/gflanguages/data/languages/evn_Latn.textproto

@@ -1,7 +1,7 @@
 id: "evn_Latn"
 language: "evn"
 script: "Latn"
-name: "Evenki"
+name: "Evenki, Latin"
 population: 16000
 region: "RU"
 region: "CN"

Lib/gflanguages/data/languages/kr_Arab.textproto

@@ -1,4 +1,4 @@
 id: "kr_Arab"
 language: "kr"
 script: "Arab"
-name: "Kanuri"
+name: "Kanuri, Arabic"

Lib/gflanguages/data/languages/mlt_Latn.textproto

@@ -2,7 +2,7 @@
 id: "sa_Nand"
 language: "sa"
 script: "Nand"
-name: "Sanskrit"
+name: "Sanskrit, Nandinagari"
 autonym: "𑧍𑧞𑧍𑧠𑦮𑧖𑦽𑧆𑧠"
 region: "IN"
 exemplar_chars {

Lib/gflanguages/data/languages/sa_Nand.textproto

@@ -1,4 +1,5 @@
 id: "uma_Latn"
+language: "uma"
 script: "Latn"
 name: "Umatilla"
 population: 25

Lib/gflanguages/data/languages/uma_Latn.textproto

@@ -1,6 +1,6 @@
 id: "wal_Ethi"
 language: "wal"
 script: "Ethi"
-name: "Wolaytta"
+name: "Wolaytta, Ethiopic"
 population: 1946034
 region: "ET"

Lib/gflanguages/data/languages/wal_Ethi.textproto

@@ -1,9 +1,9 @@
 id: "wal_Latn"
 language: "wal"
 script: "Latn"
-name: "Wolaytta"
+name: "Wolaytta, Latin"
 population: 7000000
 region: "ET"
 exemplar_chars {
   base: "a A b B c C d D e E f F g G h H i I j J k K l L m M n N o O p P q Q r R s S t T u U v V w W x X y Y z Z"
-}
+}

Lib/gflanguages/data/languages/wal_Latn.textproto

@@ -1,7 +1,7 @@
 id: "xsm_Latn_BF"
 language: "xsm"
 script: "Latn"
-name: "Kasem"
+name: "Burkinabè Kasem"
 population: 250000
 region: "BF"
 exemplar_chars {

Lib/gflanguages/data/languages/xsm_Latn_BF.textproto

@@ -265,3 +265,18 @@ def test_exemplar_parser():
         "l",
         "̍",
     }
+
+
+def test_language_uniqueness():
+    names = Counter([])
+    for lang in LANGUAGES.values():
+        # We check that names are unique *within a script* since
+        # when we display them in a menu we segment that menu by
+        # script and then by language
+        if lang.preferred_name:
+            names[lang.script + "/" + lang.preferred_name] += 1
+        else:
+            names[lang.name + "/" + lang.preferred_name] += 1
+    if any(count > 1 for count in names.values()):
+        duplicates = {name: count for name, count in names.items() if count > 1}
+        pytest.fail(f"Duplicate language names: {duplicates}")

tests/test_data_languages.py

@@ -7,9 +7,16 @@
 
 
 languages_dir = os.path.join(DATA_DIR, "languages")
-textproto_files = [os.path.basename(x) for x in glob.iglob(os.path.join(languages_dir, "*.textproto"))]
+textproto_files = [
+    os.path.basename(x) for x in glob.iglob(os.path.join(languages_dir, "*.textproto"))
+]
+
 
 @pytest.mark.parametrize("lang_code", textproto_files)
 def test_parsable(lang_code):
     with open(os.path.join(languages_dir, lang_code), "r", encoding="utf-8") as f:
-        text_format.Parse(f.read(), languages_public_pb2.LanguageProto())
+        msg = text_format.Parse(f.read(), languages_public_pb2.LanguageProto())
+        assert msg.id
+        assert msg.language
+        assert msg.script
+        assert msg.population is not None