toolchain: add option to copy the gconv libraries

The gconv libraries are used to translate between different character sets
('charsets', even 'csets' sometimes). Some packages need them to present
text to the user (eg. XBMC Gotham).

In (e)glibc they are implemented by the internal implemenation of iconv,
called gconv, and are provided as dlopen-able libraries.

Note that some gconv modules need extra libraries (shared by more than
one gconv module), so we must, when adding a subset of modules, scan the
installed modules in search of the missing libraries.

[Thomas: add general explanation in expunge-gconv-modules and fix
coding style.]

Signed-off-by: "Yann E. MORIN" <yann.morin.1998@free.fr>
Cc: Maxime Hadjinlian <maxime.hadjinlian@gmail.com>
Cc: Bernd Kuhls <bernd.kuhls@t-online.de>
Signed-off-by: Bernd Kuhls <bernd.kuhls@t-online.de>
Cc: Eric Limpens <limpens@gmail.com>
Signed-off-by: Thomas Petazzoni <thomas.petazzoni@free-electrons.com>

4 files changed, 118 insertions, 1 deletions

diff --git a/Makefile b/Makefile
index 6bd18e323..d4ef081f5 100644
--- a/Makefile
+++ b/Makefile
@@ -369,7 +369,7 @@ include support/dependencies/dependencies.mk
 # We also need the various per-package makefiles, which also add
 # each selected package to TARGETS if that package was selected
 # in the .config file.
-include toolchain/helpers.mk
+include toolchain/*.mk
 include toolchain/*/*.mk
 
 # Include the package override file if one has been provided in the
diff --git a/support/scripts/expunge-gconv-modules b/support/scripts/expunge-gconv-modules
new file mode 100755
index 000000000..a77b063ca
--- /dev/null
+++ b/support/scripts/expunge-gconv-modules
@@ -0,0 +1,59 @@
+#!/bin/bash
+
+# This script is used to generate a gconv-modules file that takes into
+# account only the gconv modules installed by Buildroot. It receives
+# on its standard input the original complete gconv-modules file from
+# the toolchain, and as arguments the list of gconv modules that were
+# actually installed, and writes on its standard output the new
+# gconv-modules file.
+
+# The format of gconv-modules is precisely documented in the
+# file itself. It consists of two different directives:
+#   module  FROMSET  TOSET  FILENAME  COST
+#   alias   ALIAS  REALNAME
+# and that's what this script parses and generates.
+#
+# There are two kinds of 'module' directives:
+#   - the first defines conversion of a charset to/from INTERNAL representation
+#   - the second defines conversion of a charset to/from another charset
+# we handle each with slightly different code, since the second never has
+# associated aliases.
+
+gawk -v files="${1}" '
+$1 == "alias" {
+    aliases[$3] = aliases[$3] " " $2;
+}
+$1 == "module" && $2 != "INTERNAL" && $3 == "INTERNAL" {
+    file2internals[$4] = file2internals[$4] " " $2;
+    mod2cost[$2] = $5;
+}
+$1 == "module" && $2 != "INTERNAL" && $3 != "INTERNAL" {
+    file2cset[$4] = file2cset[$4] " " $2 ":" $3;
+    mod2cost[$2] = $5;
+}
+
+END {
+    nb_files = split(files, all_files);
+    for(f = 1; f <= nb_files; f++) {
+        file = all_files[f];
+        printf("# Modules and aliases for: %s\n", file);
+        nb_mods = split(file2internals[file], mods);
+        for(i = 1; i <= nb_mods; i++) {
+            nb_aliases = split(aliases[mods[i]], mod_aliases);
+            for(j = 1; j <= nb_aliases; j++) {
+                printf("alias\t%s\t%s\n", mod_aliases[j], mods[i]);
+            }
+            printf("module\t%s\t%s\t%s\t%d\n", mods[i], "INTERNAL", file, mod2cost[mods[i]]);
+            printf("module\t%s\t%s\t%s\t%d\n", "INTERNAL", mods[i], file, mod2cost[mods[i]]);
+            printf("\n" );
+        }
+        printf("%s", nb_mods != 0 ? "\n" : "");
+        nb_csets = split(file2cset[file], csets);
+        for(i = 1; i <= nb_csets; i++) {
+            split(csets[i], cs, ":");
+            printf("module\t%s\t%s\t%s\t%d\n", cs[1], cs[2], file, mod2cost[cs[1]]);
+        }
+        printf("%s", nb_csets != 0 ? "\n\n" : "");
+    }
+}
+'
diff --git a/toolchain/toolchain-common.in b/toolchain/toolchain-common.in
index a91d24707..13de9e5c5 100644
--- a/toolchain/toolchain-common.in
+++ b/toolchain/toolchain-common.in
@@ -77,6 +77,28 @@ config BR2_GENERATE_LOCALE
 	  specified, UTF-8 is assumed. Examples of locales: en_US,
 	  fr_FR.UTF-8.
 
+config BR2_TOOLCHAIN_GLIBC_GCONV_LIBS_COPY
+	bool "Copy gconv libraries"
+	depends on BR2_TOOLCHAIN_USES_GLIBC
+	help
+	  The gconv libraries are used to convert between different
+	  character sets (charsets).
+
+	  Say 'y' if you need to store and/or display different charsets.
+
+config BR2_TOOLCHAIN_GLIBC_GCONV_LIBS_LIST
+	string "Gconv libraries to copy"
+	depends on BR2_TOOLCHAIN_GLIBC_GCONV_LIBS_COPY
+	help
+	  Set to the list of gconv libraries to copy.
+	  Leave empty to copy all gconv libraries.
+
+	  Specify only the basename of the libraries, leave
+	  out the .so extension. Eg.:
+	    IBM850 ISO8859-15 UNICODE
+
+	  Note: the full set of gconv libs are ~8MiB (on ARM).
+
 # glibc and eglibc directly include gettext, so a separatly compiled
 # gettext isn't needed and shouldn't be built to avoid conflicts. Some
 # packages always need gettext, other packages only need gettext when
diff --git a/toolchain/toolchain.mk b/toolchain/toolchain.mk
new file mode 100644
index 000000000..8fe06ffa5
--- /dev/null
+++ b/toolchain/toolchain.mk
@@ -0,0 +1,36 @@
+# This file contains toolchain-related customisation of the content
+# of the target/ directory. Those customisations are added to the
+# TARGET_FINALIZE_HOOKS, to be applied just after all packages
+# have been built.
+
+# Install the gconv modules
+ifeq ($(BR2_TOOLCHAIN_GLIBC_GCONV_LIBS_COPY),y)
+GCONV_LIBS = $(call qstrip,$(BR2_TOOLCHAIN_GLIBC_GCONV_LIBS_LIST))
+define COPY_GCONV_LIBS
+	$(Q)if [ -z "$(GCONV_LIBS)" ]; then \
+		$(INSTALL) -m 0644 -D $(STAGING_DIR)/usr/lib/gconv/gconv-modules \
+				      $(TARGET_DIR)/usr/lib/gconv/gconv-modules; \
+		$(INSTALL) -m 0644 $(STAGING_DIR)/usr/lib/gconv/*.so \
+				   $(TARGET_DIR)/usr/lib/gconv \
+		|| exit 1; \
+	else \
+		for l in $(GCONV_LIBS); do \
+			$(INSTALL) -m 0644 -D $(STAGING_DIR)/usr/lib/gconv/$${l}.so \
+					      $(TARGET_DIR)/usr/lib/gconv/$${l}.so \
+			|| exit 1; \
+			$(TARGET_READELF) -d $(STAGING_DIR)/usr/lib/gconv/$${l}.so |\
+			sort -u |\
+			sed -e '/.*(NEEDED).*\[\(.*\.so\)\]$$/!d; s//\1/;' |\
+			while read lib; do \
+				 $(INSTALL) -m 0644 -D $(STAGING_DIR)/usr/lib/gconv/$${lib} \
+						       $(TARGET_DIR)/usr/lib/gconv/$${lib} \
+				 || exit 1; \
+			done; \
+		done; \
+		./support/scripts/expunge-gconv-modules "$(GCONV_LIBS)" \
+			<$(STAGING_DIR)/usr/lib/gconv/gconv-modules \
+			>$(TARGET_DIR)/usr/lib/gconv/gconv-modules; \
+	fi
+endef
+TARGET_FINALIZE_HOOKS += COPY_GCONV_LIBS
+endif