From: nathan-williams <nathan.le.williams@gmail.com>
Date: Mon, 22 Jul 2024 04:43:01 +0000 (-0400)
Subject: Expand character class for language names
X-Git-Url: http://git.ipfire.org/cgi-bin/gitweb.cgi?a=commitdiff_plain;h=640c050f19b10245ef27ebea400f4bf445843c02;p=thirdparty%2Fgoogle%2Ffonts.git

Expand character class for language names
---

diff --git a/Lib/gflanguages/data/languages/bdh_Latn.textproto b/Lib/gflanguages/data/languages/bdh_Latn.textproto
index 7e7ccf6dda..ecbbb850b3 100644
--- a/Lib/gflanguages/data/languages/bdh_Latn.textproto
+++ b/Lib/gflanguages/data/languages/bdh_Latn.textproto
@@ -1,7 +1,7 @@
 id: "bdh_Latn"
 language: "bdh"
 script: "Latn"
-name: "Baka (DRC/South Sudan)"
+name: "Baka, DRC/South Sudan"
 autonym: "Tara Baká"
 population: 60000
 region: "CD"
diff --git a/Lib/gflanguages/data/languages/bkc_Latn.textproto b/Lib/gflanguages/data/languages/bkc_Latn.textproto
index 02b8bca30d..08da4d26da 100644
--- a/Lib/gflanguages/data/languages/bkc_Latn.textproto
+++ b/Lib/gflanguages/data/languages/bkc_Latn.textproto
@@ -1,7 +1,7 @@
 id: "bkc_Latn"
 language: "bkc"
 script: "Latn"
-name: "Baka (Cameroon/Gabon)"
+name: "Baka, Cameroon/Gabon"
 population: 71000
 region: "CM"
 region: "GA"
diff --git a/Lib/gflanguages/data/languages/bm_Nkoo.textproto b/Lib/gflanguages/data/languages/bm_Nkoo.textproto
index 2734cdca76..1136be516c 100644
--- a/Lib/gflanguages/data/languages/bm_Nkoo.textproto
+++ b/Lib/gflanguages/data/languages/bm_Nkoo.textproto
@@ -1,6 +1,6 @@
 id: "bm_Nkoo"
 language: "bm"
 script: "Nkoo"
-name: "Bambara (Nko)"
+name: "Bambara (N’Ko)"
 population: 16000000
 region: "ML"
diff --git a/Lib/gflanguages/data/languages/bsq_Bass.textproto b/Lib/gflanguages/data/languages/bsq_Bass.textproto
index 3d76b53b1d..e2984fefbb 100644
--- a/Lib/gflanguages/data/languages/bsq_Bass.textproto
+++ b/Lib/gflanguages/data/languages/bsq_Bass.textproto
@@ -1,7 +1,7 @@
 id: "bsq_Bass"
 language: "bsq"
 script: "Bass"
-name: "Bassa (Vah)"
+name: "Bassa (Bassa Vah)"
 population: 410000
 region: "LR"
 region: "SL"
diff --git a/Lib/gflanguages/data/languages/cbk_Latn.textproto b/Lib/gflanguages/data/languages/cbk_Latn.textproto
index 7053e530f9..748d555e18 100644
--- a/Lib/gflanguages/data/languages/cbk_Latn.textproto
+++ b/Lib/gflanguages/data/languages/cbk_Latn.textproto
@@ -1,7 +1,7 @@
 id: "cbk_Latn"
 language: "cbk"
 script: "Latn"
-name: "Chavacano, Latin, Philippines"
+name: "Chavacano, Philippines (Latin)"
 region: "PH"
 sample_text {
   masthead_full: "TtOo"
diff --git a/Lib/gflanguages/data/languages/chn_Dupl.textproto b/Lib/gflanguages/data/languages/chn_Dupl.textproto
index d402556fcb..2e8e8213cb 100644
--- a/Lib/gflanguages/data/languages/chn_Dupl.textproto
+++ b/Lib/gflanguages/data/languages/chn_Dupl.textproto
@@ -1,6 +1,6 @@
 id: "chn_Dupl"
 language: "chn"
 script: "Dupl"
-name: "Chinook Jargon (Duployan shorthand)"
+name: "Chinook Jargon (Duployan)"
 region: "US"
 region: "CA"
diff --git a/Lib/gflanguages/data/languages/de_Dupl.textproto b/Lib/gflanguages/data/languages/de_Dupl.textproto
index 7910e1de42..718b6fd747 100644
--- a/Lib/gflanguages/data/languages/de_Dupl.textproto
+++ b/Lib/gflanguages/data/languages/de_Dupl.textproto
@@ -1,5 +1,5 @@
 id: "de_Dupl"
 language: "de"
 script: "Dupl"
-name: "German (Duployan shorthand)"
+name: "German (Duployan)"
 region: "DE"
diff --git a/Lib/gflanguages/data/languages/dyu_Nkoo.textproto b/Lib/gflanguages/data/languages/dyu_Nkoo.textproto
index 7edc157ecd..eb891abd2d 100644
--- a/Lib/gflanguages/data/languages/dyu_Nkoo.textproto
+++ b/Lib/gflanguages/data/languages/dyu_Nkoo.textproto
@@ -1,5 +1,5 @@
 id: "dyu_Nkoo"
 language: "dyu"
 script: "Nkoo"
-name: "Dyula (Nko)"
+name: "Dyula (N’Ko)"
 region: "CI"
diff --git a/Lib/gflanguages/data/languages/eto_Latn.textproto b/Lib/gflanguages/data/languages/eto_Latn.textproto
index d016fd39f9..2da83f6b07 100644
--- a/Lib/gflanguages/data/languages/eto_Latn.textproto
+++ b/Lib/gflanguages/data/languages/eto_Latn.textproto
@@ -1,7 +1,7 @@
 id: "eto_Latn"
 language: "eto"
 script: "Latn"
-name: "Eton (Cameroon)"
+name: "Eton, Cameroon"
 population: 400000
 region: "CM"
 exemplar_chars {
diff --git a/Lib/gflanguages/data/languages/fr_Dupl.textproto b/Lib/gflanguages/data/languages/fr_Dupl.textproto
index 584d4cbda7..0093d282a8 100644
--- a/Lib/gflanguages/data/languages/fr_Dupl.textproto
+++ b/Lib/gflanguages/data/languages/fr_Dupl.textproto
@@ -1,5 +1,5 @@
 id: "fr_Dupl"
 language: "fr"
 script: "Dupl"
-name: "French (Duployan shorthand)"
+name: "French (Duployan)"
 historical: true
diff --git a/Lib/gflanguages/data/languages/gcf_Latn.textproto b/Lib/gflanguages/data/languages/gcf_Latn.textproto
index 56401d24d8..b36c6e6044 100644
--- a/Lib/gflanguages/data/languages/gcf_Latn.textproto
+++ b/Lib/gflanguages/data/languages/gcf_Latn.textproto
@@ -1,7 +1,7 @@
 id: "gcf_Latn"
 language: "gcf"
 script: "Latn"
-name: "Guadeloupean Creole French, Latin, Martinique"
+name: "Guadeloupean Creole French, Martinique (Latin)"
 region: "GP"
 region: "MQ"
 sample_text {
diff --git a/Lib/gflanguages/data/languages/man_Nkoo.textproto b/Lib/gflanguages/data/languages/man_Nkoo.textproto
index 2ba2349b18..4e9166d020 100644
--- a/Lib/gflanguages/data/languages/man_Nkoo.textproto
+++ b/Lib/gflanguages/data/languages/man_Nkoo.textproto
@@ -1,5 +1,5 @@
 id: "man_Nkoo"
 language: "man"
 script: "Nkoo"
-name: "Mandingo (Nko)"
+name: "Mandingo (N’Ko)"
 region: "GN"
diff --git a/Lib/gflanguages/data/scripts/Beng.textproto b/Lib/gflanguages/data/scripts/Beng.textproto
index d583c7ead8..d68be9e4d7 100644
--- a/Lib/gflanguages/data/scripts/Beng.textproto
+++ b/Lib/gflanguages/data/scripts/Beng.textproto
@@ -1,3 +1,2 @@
 id: "Beng"
-name: "Bangla"
-
+name: "Bengali"
diff --git a/tests/test_data_languages.py b/tests/test_data_languages.py
index c05b7d8a57..a859cf78fe 100644
--- a/tests/test_data_languages.py
+++ b/tests/test_data_languages.py
@@ -84,7 +84,15 @@ SKIP_REGION = {
 }
 
 # "ʼ" allowed as last character in language name for Metaʼ
-LANGUAGE_NAME_REGEX = "^[-A-Za-zÀ-ÿ ]+(ʼ)?(, [-A-Za-zÀ-ÿ ]+)?( [(][-A-Za-zÀ-ÿ ]+[)])?$"
+LANGUAGE_NAME_REGEX = "^[-’A-Za-zÀ-ÿ ]+(ʼ)?(, [-’A-Za-zÀ-ÿ/ ]+)?( [(][-’A-Za-zÀ-ÿ ]+[)])?$"
+# Some scripts have abbreviated names for reference in language names that are
+# sufficient in context. If an alternate is listed here, it should be used
+# universally and consistently across all language names.
+ALTERNATE_SCRIPT_NAMES = {
+    "Dupl": "Duployan",
+    "Hans": "Simplified",
+    "Hant": "Traditional",
+}
 
 
 @pytest.mark.parametrize("lang_code", LANGUAGES)
@@ -291,7 +299,7 @@ def test_language_uniqueness():
 def test_language_name_structure():
     languages_with_bad_name_structure = {}
     for lang in LANGUAGES.values():
-        script_name = SCRIPTS[lang.script].name
+        script_name = SCRIPTS[lang.script].name if lang.script not in ALTERNATE_SCRIPT_NAMES else ALTERNATE_SCRIPT_NAMES[lang.script]
         names = [["name", lang.name]]
         if lang.preferred_name:
             names += [["preferred_name", lang.preferred_name]]