Update the SPDX license list to v3.0

The SPDX team have decided to rename quite a few common tags (with the '-only'
and '-or-later') suffixes and this unfortunately breaks the world.

Convert the new-style v3 style IDs to the v2 style and thus accept both forms.

Fixes https://github.com/hughsie/appstream-glib/issues/225

3 files changed, 164 insertions, 116 deletions

diff --git a/libappstream-glib/as-license-ids.txt b/libappstream-glib/as-license-ids.txt
index 794751e..aac4b08 100644
--- a/libappstream-glib/as-license-ids.txt
+++ b/libappstream-glib/as-license-ids.txt
@@ -1,87 +1,69 @@
-# the list of licenses from http://spdx.org/licenses/ version: 2.6
-Glide
+# the list of licenses from http://spdx.org/licenses/ version: 3.0
+0BSD
+AAL
 Abstyles
+Adobe-2006
+Adobe-Glyph
+ADSL
 AFL-1.1
 AFL-1.2
 AFL-2.0
 AFL-2.1
 AFL-3.0
-AMPAS
-APL-1.0
-Adobe-Glyph
-APAFML
-Adobe-2006
-AGPL-1.0
 Afmparse
+AGPL-1.0
+AGPL-3.0-only
+AGPL-3.0-or-later
 Aladdin
-ADSL
 AMDPLPA
+AML
+AMPAS
 ANTLR-PD
 Apache-1.0
 Apache-1.1
 Apache-2.0
-AML
+APAFML
+APL-1.0
 APSL-1.0
 APSL-1.1
 APSL-1.2
 APSL-2.0
-Artistic-1.0
-Artistic-1.0-Perl
 Artistic-1.0-cl8
+Artistic-1.0-Perl
+Artistic-1.0
 Artistic-2.0
-AAL
 Bahyph
 Barr
 Beerware
 BitTorrent-1.0
 BitTorrent-1.1
-BSL-1.0
 Borceux
-BSD-2-Clause
+BSD-1-Clause
 BSD-2-Clause-FreeBSD
 BSD-2-Clause-NetBSD
-BSD-3-Clause
+BSD-2-Clause-Patent
+BSD-2-Clause
+BSD-3-Clause-Attribution
 BSD-3-Clause-Clear
-BSD-3-Clause-No-Nuclear-License
+BSD-3-Clause-LBNL
 BSD-3-Clause-No-Nuclear-License-2014
+BSD-3-Clause-No-Nuclear-License
 BSD-3-Clause-No-Nuclear-Warranty
+BSD-3-Clause
+BSD-4-Clause-UC
 BSD-4-Clause
 BSD-Protection
 BSD-Source-Code
-BSD-3-Clause-Attribution
-0BSD
-BSD-4-Clause-UC
+BSL-1.0
 bzip2-1.0.5
 bzip2-1.0.6
 Caldera
-CECILL-1.0
-CECILL-1.1
-CECILL-2.0
-CECILL-2.1
-CECILL-B
-CECILL-C
-ClArtistic
-MIT-CMU
-CNRI-Jython
-CNRI-Python
-CNRI-Python-GPL-Compatible
-CPOL-1.02
-CDDL-1.0
-CDDL-1.1
-CPAL-1.0
-CPL-1.0
 CATOSL-1.1
-Condor-1.1
 CC-BY-1.0
 CC-BY-2.0
 CC-BY-2.5
 CC-BY-3.0
 CC-BY-4.0
-CC-BY-ND-1.0
-CC-BY-ND-2.0
-CC-BY-ND-2.5
-CC-BY-ND-3.0
-CC-BY-ND-4.0
 CC-BY-NC-1.0
 CC-BY-NC-2.0
 CC-BY-NC-2.5
@@ -97,12 +79,35 @@ CC-BY-NC-SA-2.0
 CC-BY-NC-SA-2.5
 CC-BY-NC-SA-3.0
 CC-BY-NC-SA-4.0
+CC-BY-ND-1.0
+CC-BY-ND-2.0
+CC-BY-ND-2.5
+CC-BY-ND-3.0
+CC-BY-ND-4.0
 CC-BY-SA-1.0
 CC-BY-SA-2.0
 CC-BY-SA-2.5
 CC-BY-SA-3.0
 CC-BY-SA-4.0
 CC0-1.0
+CDDL-1.0
+CDDL-1.1
+CDLA-Permissive-1.0
+CDLA-Sharing-1.0
+CECILL-1.0
+CECILL-1.1
+CECILL-2.0
+CECILL-2.1
+CECILL-B
+CECILL-C
+ClArtistic
+CNRI-Jython
+CNRI-Python-GPL-Compatible
+CNRI-Python
+Condor-1.1
+CPAL-1.0
+CPL-1.0
+CPOL-1.02
 Crossword
 CrystalStacker
 CUA-OPL-1.0
@@ -110,131 +115,142 @@ Cube
 curl
 D-FSL-1.0
 diffmark
-WTFPL
 DOC
 Dotseqn
 DSDP
 dvipdfm
-EPL-1.0
 ECL-1.0
 ECL-2.0
-eGenix
 EFL-1.0
 EFL-2.0
-MIT-advertising
-MIT-enna
+eGenix
 Entessa
+EPL-1.0
+EPL-2.0
 ErlPL-1.1
 EUDatagrid
 EUPL-1.0
 EUPL-1.1
+EUPL-1.2
 Eurosym
 Fair
-MIT-feh
 Frameworx-1.0
 FreeImage
-FTL
 FSFAP
 FSFUL
 FSFULLR
+FTL
+GFDL-1.1-only
+GFDL-1.1-or-later
+GFDL-1.2-only
+GFDL-1.2-or-later
+GFDL-1.3-only
+GFDL-1.3-or-later
 Giftware
 GL2PS
+Glide
 Glulxe
-AGPL-3.0
-GFDL-1.1
-GFDL-1.2
-GFDL-1.3
-GPL-1.0
-GPL-2.0
-GPL-3.0
-LGPL-2.1
-LGPL-3.0
-LGPL-2.0
 gnuplot
+GPL-1.0-only
+GPL-1.0-or-later
+GPL-2.0-only
+GPL-2.0-or-later
+GPL-3.0-only
+GPL-3.0-or-later
 gSOAP-1.3b
 HaskellReport
 HPND
 IBM-pibs
-IPL-1.0
 ICU
+IJG
 ImageMagick
 iMatix
 Imlib2
-IJG
 Info-ZIP
 Intel-ACPI
 Intel
 Interbase-1.0
 IPA
+IPL-1.0
 ISC
 JasPer-2.0
 JSON
-LPPL-1.0
-LPPL-1.1
-LPPL-1.2
-LPPL-1.3a
-LPPL-1.3c
+LAL-1.2
+LAL-1.3
 Latex2e
-BSD-3-Clause-LBNL
 Leptonica
+LGPL-2.0-only
+LGPL-2.0-or-later
+LGPL-2.1-only
+LGPL-2.1-or-later
+LGPL-3.0-only
+LGPL-3.0-or-later
 LGPLLR
 Libpng
 libtiff
-LAL-1.2
-LAL-1.3
 LiLiQ-P-1.1
-LiLiQ-Rplus-1.1
 LiLiQ-R-1.1
-LPL-1.02
+LiLiQ-Rplus-1.1
 LPL-1.0
+LPL-1.02
+LPPL-1.0
+LPPL-1.1
+LPPL-1.2
+LPPL-1.3a
+LPPL-1.3c
 MakeIndex
-MTLL
-MS-PL
-MS-RL
 MirOS
-MITNFA
+MIT-advertising
+MIT-CMU
+MIT-enna
+MIT-feh
 MIT
+MITNFA
 Motosoto
+mpich2
 MPL-1.0
 MPL-1.1
-MPL-2.0
 MPL-2.0-no-copyleft-exception
-mpich2
+MPL-2.0
+MS-PL
+MS-RL
+MTLL
 Multics
 Mup
 NASA-1.3
 Naumen
 NBPL-1.0
+NCSA
 Net-SNMP
 NetCDF
+Newsletr
 NGPL
+NLOD-1.0
+NLPL
+Nokia
 NOSL
+Noweb
 NPL-1.0
 NPL-1.1
-Newsletr
-NLPL
-Nokia
 NPOSL-3.0
-NLOD-1.0
-Noweb
 NRL
 NTP
-Nunit
+OCCT-PL
 OCLC-2.0
 ODbL-1.0
-PDDL-1.0
-OCCT-PL
+OFL-1.0
+OFL-1.1
 OGTSL
-OLDAP-2.2.2
 OLDAP-1.1
 OLDAP-1.2
 OLDAP-1.3
 OLDAP-1.4
-OLDAP-2.0
 OLDAP-2.0.1
+OLDAP-2.0
 OLDAP-2.1
-OLDAP-2.2
 OLDAP-2.2.1
+OLDAP-2.2.2
+OLDAP-2.2
 OLDAP-2.3
 OLDAP-2.4
 OLDAP-2.5
@@ -242,14 +258,15 @@ OLDAP-2.6
 OLDAP-2.7
 OLDAP-2.8
 OML
+OpenSSL
 OPL-1.0
+OSET-PL-2.1
 OSL-1.0
 OSL-1.1
 OSL-2.0
 OSL-2.1
 OSL-3.0
-OpenSSL
-OSET-PL-2.1
+PDDL-1.0
 PHP-3.0
 PHP-3.01
 Plexus
@@ -257,62 +274,60 @@ PostgreSQL
 psfrag
 psutils
 Python-2.0
-QPL-1.0
 Qhull
+QPL-1.0
 Rdisc
-RPSL-1.0
+RHeCos-1.1
 RPL-1.1
 RPL-1.5
-RHeCos-1.1
-RSCPL
+RPSL-1.0
 RSA-MD
+RSCPL
 Ruby
 SAX-PD
 Saxpath
 SCEA
-SWL
-SMPPL
 Sendmail
 SGI-B-1.0
 SGI-B-1.1
 SGI-B-2.0
-OFL-1.0
-OFL-1.1
 SimPL-2.0
+SISSL-1.2
+SISSL
 Sleepycat
+SMLNJ
+SMPPL
 SNIA
 Spencer-86
 Spencer-94
 Spencer-99
-SMLNJ
-SugarCRM-1.1.3
-SISSL
-SISSL-1.2
 SPL-1.0
-Watcom-1.0
+SugarCRM-1.1.3
+SWL
 TCL
 TCP-wrappers
-Unlicense
 TMate
 TORQUE-1.1
 TOSL
 Unicode-DFS-2015
 Unicode-DFS-2016
 Unicode-TOU
+Unlicense
 UPL-1.0
-NCSA
 Vim
 VOSTROM
 VSL-1.0
-W3C-20150513
 W3C-19980720
+W3C-20150513
 W3C
+Watcom-1.0
 Wsuipa
-Xnet
+WTFPL
 X11
 Xerox
 XFree86-1.1
 xinetd
+Xnet
 xpp
 XSkat
 YPL-1.0
@@ -321,24 +336,35 @@ Zed
 Zend-2.0
 Zimbra-1.3
 Zimbra-1.4
-Zlib
 zlib-acknowledgement
+Zlib
 ZPL-1.1
 ZPL-2.0
 ZPL-2.1
+AGPL-3.0
 eCos-2.0
+GFDL-1.1
+GFDL-1.2
+GFDL-1.3
 GPL-1.0+
+GPL-1.0
 GPL-2.0+
 GPL-2.0-with-autoconf-exception
 GPL-2.0-with-bison-exception
 GPL-2.0-with-classpath-exception
 GPL-2.0-with-font-exception
 GPL-2.0-with-GCC-exception
+GPL-2.0
 GPL-3.0+
 GPL-3.0-with-autoconf-exception
 GPL-3.0-with-GCC-exception
+GPL-3.0
+LGPL-2.0+
+LGPL-2.0
 LGPL-2.1+
+LGPL-2.1
 LGPL-3.0+
-LGPL-2.0+
+LGPL-3.0
+Nunit
 StandardML-NJ
-WXwindows
+wxWindows
diff --git a/libappstream-glib/as-self-test.c b/libappstream-glib/as-self-test.c
index d5fa597..a6edd49 100644
--- a/libappstream-glib/as-self-test.c
+++ b/libappstream-glib/as-self-test.c
@@ -4386,6 +4386,13 @@ as_test_utils_spdx_token_func (void)
 	g_strfreev (tok);
 	g_free (tmp);
 
+	/* multiple licences, using the new style */
+	tok = as_utils_spdx_license_tokenize ("LGPL-2.0-or-later AND GPL-2.0-only");
+	tmp = g_strjoinv ("  ", tok);
+	g_assert_cmpstr (tmp, ==, "@LGPL-2.0+  &  @GPL-2.0");
+	g_strfreev (tok);
+	g_free (tmp);
+
 	/* multiple licences, deprectated 'and' & 'or' */
 	tok = as_utils_spdx_license_tokenize ("LGPL-2.0+ and GPL-2.0 or LGPL-3.0");
 	tmp = g_strjoinv ("  ", tok);
diff --git a/libappstream-glib/as-utils.c b/libappstream-glib/as-utils.c
index 5526a2d..5516eca 100644
--- a/libappstream-glib/as-utils.c
+++ b/libappstream-glib/as-utils.c
@@ -394,6 +394,17 @@ as_utils_spdx_license_tokenize_drop (AsUtilsSpdxHelper *helper)
 	g_string_truncate (helper->collect, 0);
 }
 
+/* SPDX decided to rename some of the really common license IDs in v3
+ * which broke a lot of tools that we cannot really fix now */
+static gchar *
+as_utils_spdx_license_3to2 (const gchar *license3)
+{
+	GString *license2 = g_string_new (license3);
+	as_utils_string_replace (license2, "-only", "");
+	as_utils_string_replace (license2, "-or-later", "+");
+	return license2;
+}
+
 /**
  * as_utils_spdx_license_tokenize:
  * @license: a license string, e.g. "LGPLv2+ and (QPL or GPLv2) and MIT"
@@ -411,32 +422,36 @@ as_utils_spdx_license_tokenize_drop (AsUtilsSpdxHelper *helper)
 gchar **
 as_utils_spdx_license_tokenize (const gchar *license)
 {
-	guint i;
 	AsUtilsSpdxHelper helper;
+	g_autoptr(GString) license2 = NULL;
 
 	/* handle invalid */
 	if (license == NULL)
 		return NULL;
 
+	/* SPDX broke the world with v3 */
+	license2 = as_utils_spdx_license_3to2 (license);
+
 	helper.last_token_literal = FALSE;
 	helper.collect = g_string_new ("");
 	helper.array = g_ptr_array_new_with_free_func (g_free);
-	for (i = 0; license[i] != '\0'; i++) {
+	for (guint i = 0; i < license2->len; i++) {
 
 		/* handle brackets */
-		if (license[i] == '(' || license[i] == ')') {
+		const gchar tmp = license2->str[i];
+		if (tmp == '(' || tmp == ')') {
 			as_utils_spdx_license_tokenize_drop (&helper);
-			g_ptr_array_add (helper.array, g_strdup_printf ("%c", license[i]));
+			g_ptr_array_add (helper.array, g_strdup_printf ("%c", tmp));
 			helper.last_token_literal = FALSE;
 			continue;
 		}
 
 		/* space, so dump queue */
-		if (license[i] == ' ') {
+		if (tmp == ' ') {
 			as_utils_spdx_license_tokenize_drop (&helper);
 			continue;
 		}
-		g_string_append_c (helper.collect, license[i]);
+		g_string_append_c (helper.collect, tmp);
 	}
 
 	/* dump anything remaining */