build: i18n: add icu config options

Make "--with-intl=none" the default and add "intl-none" option to
vcbuild.bat.

If icu data is missing print a warning unless either --download=all or
--download=icu is set. If set then automatically download, verify (MD5)
and unpack the ICU data if not already available.

There's a "list" of URLs being used, but right now only the first is
picked up. The logic works something like this:

* If there is no directory deps/icu,
  * If no zip file (currently icu4c-54_1-src.zip),
    * Download zip file (icu-project.org -> sf.net)
  * Verify the MD5 sum of the zipfile
    * If bad, print error and exit
  * Unpack the zipfile into deps/icu
* If deps/icu now exists, use it, else fail with help text

Add the configuration option "--with-icu-source=..."

Usage:
  * --with-icu-source=/path/to/my/other/icu
  * --with-icu-source=/path/to/icu54.zip
  * --with-icu-source=/path/to/icu54.tgz
  * --with-icu-source=http://example.com/icu54.tar.bz2

Add the configuration option "--with-icu-locals=...".  Allows choosing
which locales are used in the "small-icu" case.

Example:
    configure --with-intl=small-icu --with-icu-locales=tlh,grc,nl

(Also note that as of this writing, neither Klingon nor Ancient Greek
are in upstream CLDR data. Serving suggestion only.)

Don't use hard coded ../../out paths on windows. This was suggested by
@misterdjules as it causes test failures.  With this fix, "out" is no
longer created on windows and the following can run properly:

    python tools/test.py simple

Reduce space by about 1MB with ICU 54 (over without this patch). Also
trims a few other source files, but only conditional on the exact ICU
version used. This is to future-proof - a file that is unneeded now may
be needed in future ICUs.

Also:
  * Update distclean to remove icu related files
  * Refactor some code into tools/configure.d/nodedownload.py
  * Update docs
  * Add test

PR-URL: https://github.com/joyent/node/pull/8719
Fixes: https://github.com/joyent/node/issues/7676#issuecomment-64704230
[trev.norris@gmail.com small change to test's whitespace and logic]
Signed-off-by: Trevor Norris <trev.norris@gmail.com>

1 files changed, 130 insertions, 7 deletions

diff --git a/configure b/configure
index c558f7f8dd..51475f0357 100755
--- a/configure
+++ b/configure
@@ -6,6 +6,8 @@ import re
 import shlex
 import subprocess
 import sys
+import shutil
+import string
 
 CC = os.environ.get('CC', 'cc')
 
@@ -13,6 +15,10 @@ root_dir = os.path.dirname(__file__)
 sys.path.insert(0, os.path.join(root_dir, 'tools', 'gyp', 'pylib'))
 from gyp.common import GetFlavor
 
+# imports in tools/configure.d
+sys.path.insert(0, os.path.join(root_dir, 'tools', 'configure.d'))
+import nodedownload
+
 # parse our options
 parser = optparse.OptionParser()
 
@@ -236,16 +242,31 @@ parser.add_option('--with-etw',
     dest='with_etw',
     help='build with ETW (default is true on Windows)')
 
+parser.add_option('--download',
+    action='store',
+    dest='download_list',
+    help=nodedownload.help())
+
 parser.add_option('--with-icu-path',
     action='store',
     dest='with_icu_path',
     help='Path to icu.gyp (ICU i18n, Chromium version only.)')
 
+parser.add_option('--with-icu-locales',
+    action='store',
+    dest='with_icu_locales',
+    help='Comma-separated list of locales for "small-icu". Default: "root,en". "root" is assumed.')
+
 parser.add_option('--with-intl',
     action='store',
     dest='with_intl',
     help='Intl mode: none, full-icu, small-icu (default is none)')
 
+parser.add_option('--with-icu-source',
+    action='store',
+    dest='with_icu_source',
+    help='Intl mode: optional local path to icu/ dir, or path/URL of icu source archive.')
+
 parser.add_option('--with-perfctr',
     action='store_true',
     dest='with_perfctr',
@@ -294,6 +315,8 @@ parser.add_option('--xcode',
 
 (options, args) = parser.parse_args()
 
+# set up auto-download list
+auto_downloads = nodedownload.parse(options.download_list)
 
 def b(value):
   """Returns the string 'true' if value is truthy, 'false' otherwise."""
@@ -712,6 +735,35 @@ def glob_to_var(dir_base, dir_sub):
   return list
 
 def configure_intl(o):
+  icus = [
+    {
+      'url': 'http://download.icu-project.org/files/icu4c/54.1/icu4c-54_1-src.zip',
+      # from https://ssl.icu-project.org/files/icu4c/54.1/icu4c-src-54_1.md5:
+      'md5': '6b89d60e2f0e140898ae4d7f72323bca',
+    },
+  ]
+  def icu_download(path):
+    # download ICU, if needed
+    for icu in icus:
+      url = icu['url']
+      md5 = icu['md5']
+      local = url.split('/')[-1]
+      targetfile = os.path.join(root_dir, 'deps', local)
+      if not os.path.isfile(targetfile):
+        if nodedownload.candownload(auto_downloads, "icu"):
+          nodedownload.retrievefile(url, targetfile)
+      else:
+        print ' Re-using existing %s' % targetfile
+      if os.path.isfile(targetfile):
+        sys.stdout.write(' Checking file integrity with MD5:\r')
+        gotmd5 = nodedownload.md5sum(targetfile)
+        print ' MD5:      %s  %s' % (gotmd5, targetfile)
+        if (md5 == gotmd5):
+          return targetfile
+        else:
+          print ' Expected: %s      *MISMATCH*' % md5
+          print '\n ** Corrupted ZIP? Delete %s to retry download.\n' % targetfile
+    return None
   icu_config = {
     'variables': {}
   }
@@ -723,11 +775,11 @@ def configure_intl(o):
   write(icu_config_name, do_not_edit +
         pprint.pformat(icu_config, indent=2) + '\n')
 
-  # small ICU is off by default.
   # always set icu_small, node.gyp depends on it being defined.
   o['variables']['icu_small'] = b(False)
 
   with_intl = options.with_intl
+  with_icu_source = options.with_icu_source
   have_icu_path = bool(options.with_icu_path)
   if have_icu_path and with_intl:
     print 'Error: Cannot specify both --with-icu-path and --with-intl'
@@ -739,6 +791,13 @@ def configure_intl(o):
     o['variables']['icu_gyp_path'] = options.with_icu_path
     return
   # --with-intl=<with_intl>
+  # set the default
+  if with_intl is None:
+    with_intl = 'none'  # The default mode of Intl
+  # sanity check localelist
+  if options.with_icu_locales and (with_intl != 'small-icu'):
+    print 'Error: --with-icu-locales only makes sense with --with-intl=small-icu'
+    sys.exit(1)
   if with_intl == 'none' or with_intl is None:
     o['variables']['v8_enable_i18n_support'] = 0
     return  # no Intl
@@ -746,6 +805,12 @@ def configure_intl(o):
     # small ICU (English only)
     o['variables']['v8_enable_i18n_support'] = 1
     o['variables']['icu_small'] = b(True)
+    with_icu_locales = options.with_icu_locales
+    if not with_icu_locales:
+      with_icu_locales = 'root,en'
+    locs = set(with_icu_locales.split(','))
+    locs.add('root')  # must have root
+    o['variables']['icu_locales'] = string.join(locs,',')
   elif with_intl == 'full-icu':
     # full ICU
     o['variables']['v8_enable_i18n_support'] = 1
@@ -769,20 +834,78 @@ def configure_intl(o):
   # Note: non-ICU implementations could use other 'with_intl'
   # values.
 
+  # 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')
+
+  # icu-tmp is used to download and unpack the ICU tarball.
+  icu_tmp_path = os.path.join(icu_parent_path, 'icu-tmp')
+
+  # --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):
+    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.
+  if with_icu_source:
+    if os.path.isdir(icu_full_path):
+      print 'Deleting old ICU source: %s' % (icu_full_path)
+      shutil.rmtree(icu_full_path)
+    # now, what path was given?
+    if os.path.isdir(with_icu_source):
+      # it's a path. Copy it.
+      print '%s -> %s' % (with_icu_source, icu_full_path)
+      shutil.copytree(with_icu_source, icu_full_path)
+    else:
+      # could be file or URL.
+      # Set up temporary area
+      if os.path.isdir(icu_tmp_path):
+        shutil.rmtree(icu_tmp_path)
+      os.mkdir(icu_tmp_path)
+      icu_tarball = None
+      if os.path.isfile(with_icu_source):
+        # it's a file. Try to unpack it.
+        icu_tarball = with_icu_source
+      else:
+        # Can we download it?
+        local = os.path.join(icu_tmp_path, with_icu_source.split('/')[-1])  # local part
+        icu_tarball = nodedownload.retrievefile(with_icu_source, local)
+      # continue with "icu_tarball"
+      nodedownload.unpack(icu_tarball, icu_tmp_path)
+      # Did it unpack correctly? Should contain 'icu'
+      tmp_icu = os.path.join(icu_tmp_path, 'icu')
+      if os.path.isdir(tmp_icu):
+        os.rename(tmp_icu, icu_full_path)
+        shutil.rmtree(icu_tmp_path)
+      else:
+        print ' Error: --with-icu-source=%s did not result in an "icu" dir.' % with_icu_source
+        shutil.rmtree(icu_tmp_path)
+        sys.exit(1)
+
   # ICU mode. (icu-generic.gyp)
   byteorder = sys.byteorder
   o['variables']['icu_gyp_path'] = 'tools/icu/icu-generic.gyp'
   # ICU source dir relative to root
-  icu_full_path = os.path.join(root_dir, 'deps/icu')
   o['variables']['icu_path'] = icu_full_path
   if not os.path.isdir(icu_full_path):
-    print 'Error: ICU path is not a directory: %s' % (icu_full_path)
+    print '* ECMA-402 (Intl) support didn\'t find ICU in %s..' % (icu_full_path)
+    # can we download (or find) a zipfile?
+    localzip = icu_download(icu_full_path)
+    if localzip:
+      nodedownload.unpack(localzip, icu_parent_path)
+  if not os.path.isdir(icu_full_path):
+    print ' Cannot build Intl without ICU in %s.' % (icu_full_path)
+    print ' (Fix, or disable with "--with-intl=none" )'
     sys.exit(1)
+  else:
+    print '* Using ICU in %s' % (icu_full_path)
   # Now, what version of ICU is it? We just need the "major", such as 54.
   # uvernum.h contains it as a #define.
   uvernum_h = os.path.join(icu_full_path, 'source/common/unicode/uvernum.h')
   if not os.path.isfile(uvernum_h):
-    print 'Error: could not load %s - is ICU installed?' % uvernum_h
+    print ' Error: could not load %s - is ICU installed?' % uvernum_h
     sys.exit(1)
   icu_ver_major = None
   matchVerExp = r'^\s*#define\s+U_ICU_VERSION_SHORT\s+"([^"]*)".*'
@@ -792,7 +915,7 @@ def configure_intl(o):
     if m:
       icu_ver_major = m.group(1)
   if not icu_ver_major:
-    print 'Could not read U_ICU_VERSION_SHORT version from %s' % uvernum_h
+    print ' Could not read U_ICU_VERSION_SHORT version from %s' % uvernum_h
     sys.exit(1)
   icu_endianness = sys.byteorder[0];  # TODO(srl295): EBCDIC should be 'e'
   o['variables']['icu_ver_major'] = icu_ver_major
@@ -819,8 +942,8 @@ def configure_intl(o):
   # this is the icudt*.dat file which node will be using (platform endianness)
   o['variables']['icu_data_file'] = icu_data_file
   if not os.path.isfile(icu_data_path):
-    print 'Error: ICU prebuilt data file %s does not exist.' % icu_data_path
-    print 'See the README.md.'
+    print ' Error: ICU prebuilt data file %s does not exist.' % icu_data_path
+    print ' See the README.md.'
     # .. and we're not about to build it from .gyp!
     sys.exit(1)
   # map from variable name to subdirs