public inbox for openembedded-core@lists.openembedded.org
 help / color / mirror / Atom feed
From: "Khem Raj" <raj.khem@gmail.com>
To: openembedded-core@lists.openembedded.org
Cc: Khem Raj <raj.khem@gmail.com>,
	Wouter Meek <w.meek@metrological.com>,
	Richard Purdie <richard.purdie@linuxfoundation.org>
Subject: [PATCH V2] icu: Add knobs to generate a subset of ICU data
Date: Fri,  3 Apr 2020 14:31:54 -0700	[thread overview]
Message-ID: <20200403213154.197656-1-raj.khem@gmail.com> (raw)

Recent versions of ICU (64+) provides a tool for configuring ICU
locale data file with finer granularity [1]

Default generated size for libicudata.so.66.1 is ~27M, which is quite
large for embedded systems and all of them may not even need all locale
data.

This patch calls the icudata buildtool during configure on the icudata
and utilizes a filter called 'filter.json` ( empty by default) to
create the data, default behavior should remain same but someone can
add a filter.json in own layer to configure this data, e.g.

{
  "localeFilter": {
    "filterType": "language",
    "whitelist": [
      "en",
      "de",
      "it"
    ]
  }
}

would only generate the locale data for english/german/italian

This would reduce the size of libicudata.so.66.1 to 12M

Ensure that icudata is generated using host-tools so it can deal with
endianness correctly, when host and target systems have different
endianness

[1] https://github.com/unicode-org/icu/blob/master/docs/userguide/icu_data/buildtool.md

Signed-off-by: Khem Raj <raj.khem@gmail.com>
Suggested-by: Wouter Meek <w.meek@metrological.com>
Signed-off-by: Richard Purdie <richard.purdie@linuxfoundation.org>
---
v2: Fix build for BE systems

 meta/recipes-support/icu/icu.inc         |  2 +-
 meta/recipes-support/icu/icu/filter.json |  2 ++
 meta/recipes-support/icu/icu_66.1.bb     | 25 +++++++++++++++++++++---
 3 files changed, 25 insertions(+), 4 deletions(-)
 create mode 100644 meta/recipes-support/icu/icu/filter.json

diff --git a/meta/recipes-support/icu/icu.inc b/meta/recipes-support/icu/icu.inc
index 6d9728903d..d6ff82926e 100644
--- a/meta/recipes-support/icu/icu.inc
+++ b/meta/recipes-support/icu/icu.inc
@@ -59,7 +59,7 @@ do_install_append_class-target() {
     # Use icupkg to re-generate it.
     if [ "${SITEINFO_ENDIANNESS}" = "be" ] ; then
         rm -f ${D}/${datadir}/${BPN}/${PV}/icudt${ICU_MAJOR_VER}b.dat
-        icupkg -tb ${S}/data/in/icudt${ICU_MAJOR_VER}l.dat ${D}/${datadir}/${BPN}/${PV}/icudt${ICU_MAJOR_VER}b.dat
+        icupkg -tb ${S}/data/out/icudt${ICU_MAJOR_VER}l.dat ${D}/${datadir}/${BPN}/${PV}/icudt${ICU_MAJOR_VER}b.dat
     fi
 	
 	# Remove build host references...
diff --git a/meta/recipes-support/icu/icu/filter.json b/meta/recipes-support/icu/icu/filter.json
new file mode 100644
index 0000000000..2c63c08510
--- /dev/null
+++ b/meta/recipes-support/icu/icu/filter.json
@@ -0,0 +1,2 @@
+{
+}
diff --git a/meta/recipes-support/icu/icu_66.1.bb b/meta/recipes-support/icu/icu_66.1.bb
index 5018464c14..0e1304b52d 100644
--- a/meta/recipes-support/icu/icu_66.1.bb
+++ b/meta/recipes-support/icu/icu_66.1.bb
@@ -18,7 +18,10 @@ ARM_INSTRUCTION_SET_armv4 = "arm"
 ARM_INSTRUCTION_SET_armv5 = "arm"
 
 BASE_SRC_URI = "https://github.com/unicode-org/icu/releases/download/release-${ICU_FOLDER}/icu4c-${ICU_PV}-src.tgz"
-SRC_URI = "${BASE_SRC_URI} \
+DATA_SRC_URI = "https://github.com/unicode-org/icu/releases/download/release-${ICU_FOLDER}/icu4c-${ICU_PV}-data.zip"
+SRC_URI = "${BASE_SRC_URI};name=code \
+           ${DATA_SRC_URI};name=data \
+           file://filter.json \
            file://icu-pkgdata-large-cmd.patch \
            file://fix-install-manx.patch \
            file://0001-Fix-big-endian-build.patch \
@@ -28,8 +31,24 @@ SRC_URI = "${BASE_SRC_URI} \
 SRC_URI_append_class-target = "\
            file://0001-Disable-LDFLAGSICUDT-for-Linux.patch \
           "
-SRC_URI[md5sum] = "b33dc6766711517c98d318447e5110f8"
-SRC_URI[sha256sum] = "52a3f2209ab95559c1cf0a14f24338001f389615bf00e2585ef3dbc43ecf0a2e"
+SRC_URI[code.sha256sum] = "52a3f2209ab95559c1cf0a14f24338001f389615bf00e2585ef3dbc43ecf0a2e"
+SRC_URI[data.sha256sum] = "8be647f738891d2beb79d48f99077b3499948430eae6f1be112553b15ab0243e"
 
 UPSTREAM_CHECK_REGEX = "icu4c-(?P<pver>\d+(_\d+)+)-src"
 UPSTREAM_CHECK_URI = "https://github.com/unicode-org/icu/releases"
+
+do_make_icudata_class-target () {
+    rm -rf ${S}/data
+    cp -a ${WORKDIR}/data ${S}
+    cd ${S}
+    unset CC CPP CXX CFLAGS CPPFLAGS CXXFLAGS LDFLAGS
+    ICU_DATA_FILTER_FILE=${WORKDIR}/filter.json \
+    ./runConfigureICU Linux --with-data-packaging=archive
+    oe_runmake ${PARALLEL_MAKE}
+}
+
+do_make_icudata() {
+    :
+}
+
+addtask make_icudata before do_configure after do_patch
-- 
2.26.0


                 reply	other threads:[~2020-04-03 21:31 UTC|newest]

Thread overview: [no followups] expand[flat|nested]  mbox.gz  Atom feed

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20200403213154.197656-1-raj.khem@gmail.com \
    --to=raj.khem@gmail.com \
    --cc=openembedded-core@lists.openembedded.org \
    --cc=richard.purdie@linuxfoundation.org \
    --cc=w.meek@metrological.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox