add logic to handle Unicode beta period file names

In downloader.rb, add logic to handle file names of the form
UnicodeData-12.0.0d6.txt. To find the right file, we download
the index of the directory. Then we download the files by finding
the file names from the index. Files are always checked for changes,
because changes might be frequent during the beta period.
We also check whether any index.html files are left when we are not
in the beta period. This would indicate that we might have stale
data from the beta period rather than the actual release data.

git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@66737 b2dd03c8-39d4-4d8f-98ff-823fe69b080e

1 files changed, 29 insertions, 12 deletions

diff --git a/tool/downloader.rb b/tool/downloader.rb
index 3cf98e9655..1d1df2244c 100644
--- a/tool/downloader.rb
+++ b/tool/downloader.rb
@@ -70,8 +70,34 @@ class Downloader
   Gems = RubyGems
 
   class Unicode < self
-    def self.download(name, *rest)
-      super("http://www.unicode.org/Public/#{name}", name, *rest)
+    INDEX = {}  # cache index file information across files in the same directory
+    UNICODE_PUBLIC = "http://www.unicode.org/Public/"
+
+    def self.download(name, dir = nil, since = true, options = {})
+      options = options.dup
+      unicode_beta = options.delete(:unicode_beta)
+      name_dir_part = name.sub(/[^\/]+$/, '')
+      if unicode_beta == 'YES'
+        if INDEX.size == 0
+          index_options = options.dup
+          index_options[:cache_save] = false # TODO: make sure caching really doesn't work for index file
+          index_file = super(UNICODE_PUBLIC+name_dir_part, "#{name_dir_part}index.html", dir, true, index_options)
+          INDEX[:index] = IO.read index_file
+        end
+        file_base = name.sub(/^.*\//, '').sub(/\.txt$/, '')
+        beta_name = INDEX[:index].match(/#{file_base}(-[0-9.]+d\d+)?\.txt/)[0]
+        # make sure we always check for new versions of files,
+        # because they can easily change in the beta period
+        super(UNICODE_PUBLIC+name_dir_part+beta_name, name, dir, true, options)
+      else
+        index_file = Pathname.new(under(dir, name_dir_part+'index.html'))
+        if index_file.exist?
+          raise "Although Unicode is not in beta, file #{index_file} exists. " +
+                "Remove all files in this directory and in .downloaded-cache/ " +
+                "because they may be leftovers from the beta period."
+        end
+        super(UNICODE_PUBLIC+name, name, dir, since, options)
+      end
     end
   end
 
@@ -124,10 +150,7 @@ class Downloader
     options = options.dup
     url = URI(url)
     dryrun = options.delete(:dryrun)
-
-    # remove from options (future use, see r66448), see L166
-    unicode_beta = options.delete(:unicode_beta)
-    puts "never" if unicode_beta == 'assigned but unused variable...'
+    options.delete(:unicode_beta) # just to be on the safe side for gems and gcc
 
     if name
       file = Pathname.new(under(dir, name))
@@ -318,12 +341,6 @@ if $0 == __FILE__
     when '--unicode-beta'
       options[:unicode_beta] = ARGV[1]
       ARGV.shift
-      # TODO: Move this code further down
-      if options[:unicode_beta]=='YES'
-        raise "Not yet able to deal with Unicode Data beta versions."
-      else
-        # TODO: deal with the case that we just switched from beta to 'regular'
-      end
     when /\A--cache-dir=(.*)/m
       options[:cache_dir] = $1
     when /\A-/