Add new LanguageTag class.

The scripts/update-language-subtags script will download the RFC 5646
registry and write it to src/language_tag_lists.cc.  This may need
to be re-run if the subtags change.

2 files changed, 180 insertions, 0 deletions

diff --git a/test/language_tag_test.cc b/test/language_tag_test.cc
new file mode 100644
index 00000000..fd90b629
--- /dev/null
+++ b/test/language_tag_test.cc
@@ -0,0 +1,179 @@
+/*
+    Copyright (C) 2020 Carl Hetherington <cth@carlh.net>
+
+    This file is part of libdcp.
+
+    libdcp is free software; you can redistribute it and/or modify
+    it under the terms of the GNU General Public License as published by
+    the Free Software Foundation; either version 2 of the License, or
+    (at your option) any later version.
+
+    libdcp is distributed in the hope that it will be useful,
+    but WITHOUT ANY WARRANTY; without even the implied warranty of
+    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+    GNU General Public License for more details.
+
+    You should have received a copy of the GNU General Public License
+    along with libdcp.  If not, see <http://www.gnu.org/licenses/>.
+
+    In addition, as a special exception, the copyright holders give
+    permission to link the code of portions of this program with the
+    OpenSSL library under certain conditions as described in each
+    individual source file, and distribute linked combinations
+    including the two.
+
+    You must obey the GNU General Public License in all respects
+    for all of the code used other than OpenSSL.  If you modify
+    file(s) with this exception, you may extend this exception to your
+    version of the file(s), but you are not obligated to do so.  If you
+    do not wish to do so, delete this exception statement from your
+    version.  If you delete this exception statement from all source
+    files in the program, then also delete it here.
+*/
+
+
+#include "exceptions.h"
+#include "language_tag.h"
+#include <boost/test/unit_test.hpp>
+
+
+using std::vector;
+using std::string;
+
+
+BOOST_AUTO_TEST_CASE (language_tag_test)
+{
+	/* Bad subtags raise errors */
+
+	{
+		dcp::LanguageTag t;
+
+		BOOST_CHECK_THROW (t.to_string(), dcp::LanguageTagError);
+
+		BOOST_CHECK_THROW (t.set_language("sheila"), dcp::LanguageTagError);
+		BOOST_CHECK_THROW (t.set_script("frobozz"), dcp::LanguageTagError);
+		BOOST_CHECK_THROW (t.set_region("ostrabaglous"), dcp::LanguageTagError);
+		BOOST_CHECK_THROW (dcp::LanguageTag::VariantSubtag("universe"), dcp::LanguageTagError);
+		BOOST_CHECK_THROW (dcp::LanguageTag::ExtlangSubtag("universe"), dcp::LanguageTagError);
+	}
+
+	/* Duplicate subtags raise errors */
+
+	{
+		dcp::LanguageTag t;
+
+		BOOST_CHECK_NO_THROW (t.add_variant("rozaj"));
+		BOOST_CHECK_THROW (t.add_variant("rozaj"), dcp::LanguageTagError);
+
+		BOOST_CHECK_NO_THROW (t.add_extlang("ltg"));
+		BOOST_CHECK_THROW (t.add_extlang("ltg"), dcp::LanguageTagError);
+	}
+
+	/* Language */
+
+	{
+		dcp::LanguageTag t;
+		BOOST_CHECK_NO_THROW (t.set_language("de"));
+		BOOST_CHECK_EQUAL (t.to_string(), "de");
+		BOOST_CHECK_EQUAL (t.description(), "German");
+	}
+
+	/* Language + script */
+
+	{
+		dcp::LanguageTag t;
+		BOOST_CHECK_NO_THROW (t.set_language("zh"));
+		BOOST_CHECK_NO_THROW (t.set_script("Hant"));
+		BOOST_CHECK_EQUAL (t.to_string(), "zh-Hant");
+		BOOST_CHECK_EQUAL (t.description(), "Chinese written using the Han (Traditional variant) script");
+	}
+
+	/* Language + region */
+
+	{
+		dcp::LanguageTag t;
+		BOOST_CHECK_NO_THROW (t.set_language("de"));
+		BOOST_CHECK_NO_THROW (t.set_region("DE"));
+		BOOST_CHECK_EQUAL (t.to_string(), "de-DE");
+		BOOST_CHECK_EQUAL (t.description(), "German for Germany");
+	}
+
+	/* Language + variant */
+
+	{
+		dcp::LanguageTag t;
+		BOOST_CHECK_NO_THROW (t.set_language("sl"));
+		BOOST_CHECK_NO_THROW (t.add_variant("rozaj"));
+		BOOST_CHECK_EQUAL (t.to_string(), "sl-rozaj");
+		BOOST_CHECK_EQUAL (t.description(), "Rezijan dialect of Slovenian");
+	}
+
+	/* Language + 2 variants */
+
+	{
+		dcp::LanguageTag t;
+		BOOST_CHECK_NO_THROW (t.set_language("sl"));
+		BOOST_CHECK_NO_THROW (t.add_variant("biske"));
+		BOOST_CHECK_NO_THROW (t.add_variant("rozaj"));
+		BOOST_CHECK_EQUAL (t.to_string(), "sl-biske-rozaj");
+		BOOST_CHECK_EQUAL (t.description(), "The Bila dialect of Resian dialect of Rezijan dialect of Slovenian");
+	}
+
+	/* Language + extlang */
+
+	{
+		dcp::LanguageTag t;
+		BOOST_CHECK_NO_THROW (t.set_language("sl"));
+		BOOST_CHECK_NO_THROW (t.add_extlang("afb"));
+		BOOST_CHECK_EQUAL (t.to_string(), "sl-afb");
+		BOOST_CHECK_EQUAL (t.description(), "Slovenian, Gulf Arabic");
+	}
+
+	/* Language + 2 extlangs */
+
+	{
+		dcp::LanguageTag t;
+		BOOST_CHECK_NO_THROW (t.set_language("sl"));
+		BOOST_CHECK_NO_THROW (t.add_extlang("afb"));
+		BOOST_CHECK_NO_THROW (t.add_extlang("ltg"));
+		BOOST_CHECK_EQUAL (t.to_string(), "sl-afb-ltg");
+		BOOST_CHECK_EQUAL (t.description(), "Slovenian, Gulf Arabic, Latgalian");
+	}
+
+	/* Language + script + region */
+
+	{
+		dcp::LanguageTag t;
+		BOOST_CHECK_NO_THROW (t.set_language("zh"));
+		BOOST_CHECK_NO_THROW (t.set_script("Hant"));
+		BOOST_CHECK_NO_THROW (t.set_region("DE"));
+		BOOST_CHECK_EQUAL (t.to_string(), "zh-Hant-DE");
+		BOOST_CHECK_EQUAL (t.description(), "Chinese written using the Han (Traditional variant) script for Germany");
+	}
+
+	/* Language + script + region + variant */
+
+	{
+		dcp::LanguageTag t;
+		BOOST_CHECK_NO_THROW (t.set_language("hy"));
+		BOOST_CHECK_NO_THROW (t.set_script("Latn"));
+		BOOST_CHECK_NO_THROW (t.set_region("IT"));
+		BOOST_CHECK_NO_THROW (t.add_variant("arevela"));
+		BOOST_CHECK_EQUAL (t.to_string(), "hy-Latn-IT-arevela");
+		BOOST_CHECK_EQUAL (t.description(), "Eastern Armenian dialect of Armenian written using the Latin script for Italy");
+	}
+
+	/* Langauge + script + region + variant + extlang */
+
+	{
+		dcp::LanguageTag t;
+		BOOST_CHECK_NO_THROW (t.set_language("hy"));
+		BOOST_CHECK_NO_THROW (t.set_script("Latn"));
+		BOOST_CHECK_NO_THROW (t.set_region("IT"));
+		BOOST_CHECK_NO_THROW (t.add_variant("arevela"));
+		BOOST_CHECK_NO_THROW (t.add_extlang("ltg"));
+		BOOST_CHECK_EQUAL (t.to_string(), "hy-Latn-IT-arevela-ltg");
+		BOOST_CHECK_EQUAL (t.description(), "Eastern Armenian dialect of Armenian written using the Latin script for Italy, Latgalian");
+	}
+
+}
diff --git a/test/wscript b/test/wscript
index d6eb078b..9958a677 100644
--- a/test/wscript
+++ b/test/wscript
@@ -85,6 +85,7 @@ def build(bld):
                  markers_test.cc
                  kdm_test.cc
                  key_test.cc
+                 language_tag_test.cc
                  raw_convert_test.cc
                  read_dcp_test.cc
                  read_interop_subtitle_test.cc