Check (small) ICU into repo

BUILDING.md

@@ -117,29 +117,14 @@ $ make
 
 ### `Intl` (ECMA-402) support:
 
-[Intl](https://github.com/nodejs/node/wiki/Intl) support is not
-enabled by default.
+[Intl](https://github.com/nodejs/node/wiki/Intl) support is 
+enabled by default, with English data only.
 
+#### Default: `small-icu` (English only) support
 
-#### "small" (English only) support
-
-This option will build with "small" (English only) support, but
-the full `Intl` (ECMA-402) APIs.  With `--download=all` it will
-download the ICU library as needed.
-
-##### Unix / OS X:
-
-```text
-$ ./configure --with-intl=small-icu --download=all
-```
-
-##### Windows:
-
-```text
-> vcbuild small-icu download-all
-```
-
-The `small-icu` mode builds with English-only data. You can add full
+By default, only English data is included, but
+the full `Intl` (ECMA-402) APIs.  It does not need to download
+any dependencies to function. You can add full
 data at runtime.
 
 *Note:* more docs are on
@@ -148,7 +133,8 @@ data at runtime.
 #### Build with full ICU support (all locales supported by ICU):
 
 With the `--download=all`, this may download ICU if you don't have an
-ICU in `deps/icu`.
+ICU in `deps/icu`. (The embedded `small-icu` included in the default
+Node.js source does not include all locales.)
 
 ##### Unix / OS X:
 
@@ -164,19 +150,19 @@ $ ./configure --with-intl=full-icu --download=all
 
 #### Building without Intl support
 
-The `Intl` object will not be available. This is the default at
-present, so this option is not normally needed.
+The `Intl` object will not be available, nor some other APIs such as
+`String.normalize`.
 
 ##### Unix / OS X:
 
 ```text
-$ ./configure --with-intl=none
+$ ./configure --without-intl
 ```
 
 ##### Windows:
 
 ```text
-> vcbuild intl-none
+> vcbuild without-intl
 ```
 
 #### Use existing installed ICU (Unix / OS X only):

configure

@@ -303,20 +303,28 @@ parser.add_option('--with-etw',
 intl_optgroup.add_option('--with-intl',
     action='store',
     dest='with_intl',
-    default='none',
+    default='small-icu',
     choices=valid_intl_modes,
     help='Intl mode (valid choices: {0}) [default: %default]'.format(
         ', '.join(valid_intl_modes)))
 
+intl_optgroup.add_option('--without-intl',
+    action='store_const',
+    dest='with_intl',
+    const='none',
+    help='Disable Intl, same as --with-intl=none')
+
 intl_optgroup.add_option('--with-icu-path',
     action='store',
     dest='with_icu_path',
     help='Path to icu.gyp (ICU i18n, Chromium version only.)')
 
+icu_default_locales='root,en'
+
 intl_optgroup.add_option('--with-icu-locales',
     action='store',
     dest='with_icu_locales',
-    default='root,en',
+    default=icu_default_locales,
     help='Comma-separated list of locales for "small-icu". "root" is assumed. '
         '[default: %default]')
 
@@ -880,7 +888,7 @@ do_not_edit = '# Do not edit. Generated by the configure script.\n'
 
 def glob_to_var(dir_base, dir_sub, patch_dir):
   list = []
-  dir_all = os.path.join(dir_base, dir_sub)
+  dir_all = '%s/%s' % (dir_base, dir_sub)
   files = os.walk(dir_all)
   for ent in files:
     (path, dirs, files) = ent
@@ -900,8 +908,8 @@ def glob_to_var(dir_base, dir_sub, patch_dir):
 def configure_intl(o):
   icus = [
     {
-      'url': 'https://ssl.icu-project.org/files/icu4c/56.1/icu4c-56_1-src.zip',
-      'md5': '61d71888f14bf00cc3e8a6f2c087d367',
+      'url': 'https://ssl.icu-project.org/files/icu4c/57.1/icu4c-57_1-src.zip',
+      'md5': 'f797503ecaebf1d38920013dc7893066',
     },
   ]
   def icu_download(path):
@@ -968,6 +976,7 @@ def configure_intl(o):
     locs = set(options.with_icu_locales.split(','))
     locs.add('root')  # must have root
     o['variables']['icu_locales'] = string.join(locs,',')
+    # We will check a bit later if we can use the canned deps/icu-small
   elif with_intl == 'full-icu':
     # full ICU
     o['variables']['v8_enable_i18n_support'] = 1
@@ -994,15 +1003,42 @@ def configure_intl(o):
   # this is just the 'deps' dir. Used for unpacking.
   icu_parent_path = os.path.join(root_dir, 'deps')
 
-  # The full path to the ICU source directory.
-  icu_full_path = os.path.join(icu_parent_path, 'icu')
+  # The full path to the ICU source directory. Should not include './'.
+  icu_full_path = 'deps/icu'
 
   # icu-tmp is used to download and unpack the ICU tarball.
   icu_tmp_path = os.path.join(icu_parent_path, 'icu-tmp')
 
+  # canned ICU. see tools/icu/README.md to update.
+  canned_icu_dir = 'deps/icu-small'
+
+  # We can use 'deps/icu-small' - pre-canned ICU *iff*
+  # - with_intl == small-icu (the default!)
+  # - with_icu_locales == 'root,en' (the default!)
+  # - deps/icu-small exists!
+  # - with_icu_source is unset (i.e. no other ICU was specified)
+  # (Note that this is the *DEFAULT CASE*.)
+  #
+  # This is *roughly* equivalent to
+  # $ configure --with-intl=small-icu --with-icu-source=deps/icu-small
+  # .. Except that we avoid copying icu-small over to deps/icu.
+  # In this default case, deps/icu is ignored, although make clean will
+  # still harmlessly remove deps/icu.
+
+  # are we using default locales? 
+  using_default_locales = ( options.with_icu_locales == icu_default_locales )   
+
+  # make sure the canned ICU really exists
+  canned_icu_available = os.path.isdir(canned_icu_dir)
+
+  if (o['variables']['icu_small'] == b(True)) and using_default_locales and (not with_icu_source) and canned_icu_available:
+    # OK- we can use the canned ICU.
+    icu_config['variables']['icu_small_canned'] = 1
+    icu_full_path = canned_icu_dir
+
   # --with-icu-source processing
-  # first, check that they didn't pass --with-icu-source=deps/icu
-  if with_icu_source and os.path.abspath(icu_full_path) == os.path.abspath(with_icu_source):
+  # now, check that they didn't pass --with-icu-source=deps/icu
+  elif with_icu_source and os.path.abspath(icu_full_path) == os.path.abspath(with_icu_source):
     print 'Ignoring redundant --with-icu-source=%s' % (with_icu_source)
     with_icu_source = None
   # if with_icu_source is still set, try to use it.
@@ -1043,7 +1079,7 @@ def configure_intl(o):
 
   # ICU mode. (icu-generic.gyp)
   o['variables']['icu_gyp_path'] = 'tools/icu/icu-generic.gyp'
-  # ICU source dir relative to root
+  # ICU source dir relative to tools/icu (for .gyp file)
   o['variables']['icu_path'] = icu_full_path
   if not os.path.isdir(icu_full_path):
     print '* ECMA-402 (Intl) support didn\'t find ICU in %s..' % (icu_full_path)
@@ -1083,14 +1119,14 @@ def configure_intl(o):
                                'source/data/in',
                                icu_data_file_l)
   # relative to dep..
-  icu_data_in = os.path.join('../../deps/icu/source/data/in', icu_data_file_l)
+  icu_data_in = os.path.join('..','..', icu_full_path, 'source/data/in', icu_data_file_l)
   if not os.path.isfile(icu_data_path) and icu_endianness != 'l':
     # use host endianness
     icu_data_path = os.path.join(icu_full_path,
                                  'source/data/in',
                                  icu_data_file)
     # relative to dep..
-    icu_data_in = os.path.join('icu/source/data/in',
+    icu_data_in = os.path.join('..', icu_full_path, 'source/data/in',
                                icu_data_file)
   # this is the input '.dat' file to use .. icudt*.dat
   # may be little-endian if from a icu-project.org tarball
@@ -1117,7 +1153,7 @@ def configure_intl(o):
   # with a list of the src files to use
   for i in icu_src:
     var  = 'icu_src_%s' % i
-    path = '../../deps/icu/source/%s' % icu_src[i]
+    path = '../../%s/source/%s' % (icu_full_path, icu_src[i])
     icu_config['variables'][var] = glob_to_var('tools/icu', path, 'patches/%s/source/%s' % (icu_ver_major, icu_src[i]) )
   # write updated icu_config.gypi with a bunch of paths
   write(icu_config_name, do_not_edit +