nodejs/0003-build-auto-load-ICU-data-from-with-icu-default-data-.patch

From 30e8730b88afc2c3ac46503a8cc668b367c70e3e Mon Sep 17 00:00:00 2001
From: Stephen Gallagher <sgallagh@redhat.com>
Date: Fri, 6 Dec 2019 16:40:25 -0500
Subject: [PATCH 3/3] build: auto-load ICU data from
 --with-icu-default-data-dir

When compiled with `--with-intl=small` and
`--with-icu-default-data-dir=PATH`, Node.js will use PATH as a
fallback location for the ICU data.

We will first perform an access check using fopen(PATH, 'r') to
ensure that the file is readable. If it is, we'll set the
icu_data_directory and proceed. There's a slight overhead for the
fopen() check, but it should be barely measurable.

This will be useful for Linux distribution packagers who want to
be able to ship a minimal node binary in a container image but
also be able to add on the full i18n support where needed. With
this patch, it becomes possible to ship the interpreter as
/usr/bin/node in one package for the distribution and to ship the
data files in another package (without a strict dependency
between the two). This means that users of the distribution will
not need to explicitly direct Node.js to locate the ICU data. It
also means that in environments where full internationalization is
not required, they do not need to carry the extra content (with
the associated storage costs).

Refs: https://github.com/nodejs/node/issues/3460

Signed-off-by: Stephen Gallagher <sgallagh@redhat.com>

PR-URL: https://github.com/nodejs/node/pull/30825
Reviewed-By: Steven R Loomis <srloomis@us.ibm.com>
Reviewed-By: Ben Noordhuis <info@bnoordhuis.nl>
Reviewed-By: Richard Lau <riclau@uk.ibm.com>
Reviewed-By: Rich Trott <rtrott@gmail.com>
---
 configure.py |  9 +++++++++
 node.gypi    |  7 +++++++
 src/node.cc  | 20 ++++++++++++++++++++
 3 files changed, 36 insertions(+)

diff --git a/configure.py b/configure.py
index e2d78a2a51ef81621618cb20fa76f4a1421bf9e0..cbf0d3ad567ea7beea86f56844d950e50c98c35c 100755
--- a/configure.py
+++ b/configure.py
@@ -444,6 +444,14 @@ intl_optgroup.add_option('--with-icu-source',
         'the icu4c source archive. '
         'v%d.x or later recommended.' % icu_versions['minimum_icu'])
 
+intl_optgroup.add_option('--with-icu-default-data-dir',
+    action='store',
+    dest='with_icu_default_data_dir',
+    help='Path to the icuXXdt{lb}.dat file. If unspecified, ICU data will '
+         'only be read if the NODE_ICU_DATA environment variable or the '
+         '--icu-data-dir runtime argument is used. This option has effect '
+         'only when Node.js is built with --with-intl=small-icu.')
+
 parser.add_option('--with-ltcg',
     action='store_true',
     dest='with_ltcg',
@@ -1380,6 +1388,7 @@ def configure_intl(o):
     locs.add('root')  # must have root
     o['variables']['icu_locales'] = ','.join(str(loc) for loc in locs)
     # We will check a bit later if we can use the canned deps/icu-small
+    o['variables']['icu_default_data'] = options.with_icu_default_data_dir or ''
   elif with_intl == 'full-icu':
     # full ICU
     o['variables']['v8_enable_i18n_support'] = 1
diff --git a/node.gypi b/node.gypi
index 05d80e846cffd31a0a61943e5ab391ad79cddab0..144544214316a3a5ce256e8772d57d14817c5185 100644
--- a/node.gypi
+++ b/node.gypi
@@ -103,6 +103,13 @@
       'conditions': [
         [ 'icu_small=="true"', {
           'defines': [ 'NODE_HAVE_SMALL_ICU=1' ],
+          'conditions': [
+            [ 'icu_default_data!=""', {
+              'defines': [
+                'NODE_ICU_DEFAULT_DATA_DIR="<(icu_default_data)"',
+              ],
+            }],
+          ],
       }]],
     }],
     [ 'node_no_browser_globals=="true"', {
diff --git a/src/node.cc b/src/node.cc
index ae53d0c31c3568d04387da89ab6e9d049e41c919..cbd1c632008f89f2c4aedccb00db19f686693c75 100644
--- a/src/node.cc
+++ b/src/node.cc
@@ -79,6 +79,7 @@
 
 #if defined(NODE_HAVE_I18N_SUPPORT)
 #include <unicode/uvernum.h>
+#include <unicode/utypes.h>
 #endif
 
 
@@ -848,6 +849,25 @@ int InitializeNodeWithArgs(std::vector<std::string>* argv,
   if (per_process::cli_options->icu_data_dir.empty())
     credentials::SafeGetenv("NODE_ICU_DATA",
                             &per_process::cli_options->icu_data_dir);
+
+#ifdef NODE_ICU_DEFAULT_DATA_DIR
+  // If neither the CLI option nor the environment variable was specified,
+  // fall back to the configured default
+  if (per_process::cli_options->icu_data_dir.empty()) {
+    // Check whether the NODE_ICU_DEFAULT_DATA_DIR contains the right data
+    // file and can be read.
+    static const char full_path[] =
+        NODE_ICU_DEFAULT_DATA_DIR "/" U_ICUDATA_NAME ".dat";
+
+    FILE* f = fopen(full_path, "rb");
+
+    if (f != nullptr) {
+      fclose(f);
+      per_process::cli_options->icu_data_dir = NODE_ICU_DEFAULT_DATA_DIR;
+    }
+  }
+#endif  // NODE_ICU_DEFAULT_DATA_DIR
+
   // Initialize ICU.
   // If icu_data_dir is empty here, it will load the 'minimal' data.
   if (!i18n::InitializeICUDirectory(per_process::cli_options->icu_data_dir)) {
-- 
2.23.0