Feature #4142: multipart/form-data for net/http
http://redmine.ruby-lang.org/issues/show/4142

ɼ???: Yui NARUSE
?????????: Open, ?????: Normal
????????: lib

multipart/form-data 対????? net/http ??????????????????
追??????????? API ??? Net::HTTPRequest#set_form ????????????

akr ??????????????? multipart/form-data ???????????????????? API ????示??????????????????????
chunked encoding ????????????????????????????????????????????????????????

diff --git a/lib/net/http.rb b/lib/net/http.rb
index 4d475b1..2751f77 100644
--- a/lib/net/http.rb
+++ b/lib/net/http.rb
@@ -22,6 +22,7 @@
 require 'net/protocol'
 autoload :OpenSSL, 'openssl'
 require 'uri'
+autoload :SecureRandom, 'securerandom'
 
 module Net   #:nodoc:
 
@@ -1772,7 +1773,8 @@ module Net   #:nodoc:
     alias content_type= set_content_type
 
     # Set header fields and a body from HTML form data.
-    # +params+ should be a Hash containing HTML form data.
+    # +params+ should be an Array of Arrays or
+    # a Hash containing HTML form data.
     # Optional argument +sep+ means data record separator.
     #
     # Values are URL encoded as necessary and the content-type is set to
@@ -1792,6 +1794,48 @@ module Net   #:nodoc:
 
     alias form_data= set_form_data
 
+    # Set a HTML form data set.
+    # +params+ is the form data set; it is an Array of Arrays or a Hash
+    # +enctype is the type to encode the form data set.
+    # It is application/x-www-form-urlencoded or multipart/form-data.
+    # +formpot+ is an optional hash to specify the detail.
+    #
+    # boundary:: the boundary of the multipart message
+    # charset::  the charset of the message. All names and the values of
+    #            non-file fields are encoded as the charset.
+    #
+    # Each item of params is an array and contains following items:
+    # +name+::  the name of the field
+    # +value+:: the value of the field, it should be a String or a File
+    # +opt+::   an optional hash to specify additional information
+    #
+    # Each item is a file field or a normal field.
+    # If +value+ is a File object or the +opt+ have a filename key,
+    # the item is treated as a file field.
+    #
+    # If Transfer-Encoding is set as chunked, this send the request in
+    # chunked encoding. Because chunked encoding is HTTP/1.1 feature,
+    # you must confirm the server to support HTTP/1.1 before sending it.
+    #
+    # Example:
+    #    http.set_form([["q", "ruby"], ["lang", "en"]])
+    #
+    # See also RFC 2388, RFC 2616, HTML 4.01, and HTML5
+    #
+    def set_form(params, enctype='application/x-www-form-urlencoded', formopt={})
+      @body_data = params
+      @body = nil
+      @body_stream = nil
+      @form_option = formopt
+      case enctype
+      when /\Aapplication\/x-www-form-urlencoded\z/i,
+        /\Amultipart\/form-data\z/i
+        self.content_type = enctype
+      else
+        raise ArgumentError, "invalid enctype: #{enctype}"
+      end
+    end
+
     # Set the Authorization: header for "Basic" authorization.
     def basic_auth(account, password)
       @header['authorization'] = [basic_encode(account, password)]
@@ -1849,6 +1893,7 @@ module Net   #:nodoc:
       self['User-Agent'] ||= 'Ruby'
       @body = nil
       @body_stream = nil
+      @body_data = nil
     end
 
     attr_reader :method
@@ -1876,6 +1921,7 @@ module Net   #:nodoc:
     def body=(str)
       @body = str
       @body_stream = nil
+      @body_data = nil
       str
     end
 
@@ -1884,6 +1930,7 @@ module Net   #:nodoc:
     def body_stream=(input)
       @body = nil
       @body_stream = input
+      @body_data = nil
       input
     end
 
@@ -1901,6 +1948,8 @@ module Net   #:nodoc:
         send_request_with_body sock, ver, path, @body
       elsif @body_stream
         send_request_with_body_stream sock, ver, path, @body_stream
+      elsif @body_data
+        send_request_with_body_data sock, ver, path, @body_data
       else
         write_header sock, ver, path
       end
@@ -1935,6 +1984,92 @@ module Net   #:nodoc:
       end
     end
 
+    def send_request_with_body_data(sock, ver, path, params)
+      if /\Amultipart\/form-data\z/i !~ self.content_type
+        self.content_type = 'application/x-www-form-urlencoded'
+        return send_request_with_body(sock, ver, path, URI.encode_www_form(params))
+      end
+
+      opt = @form_option.dup
+      opt[:boundary] ||= SecureRandom.urlsafe_base64(40)
+      self.set_content_type(self.content_type, boundary: opt[:boundary])
+      if chunked?
+        write_header sock, ver, path
+        encode_multipart_form_data(sock, params, opt)
+      else
+        require 'tempfile'
+        file = Tempfile.new('multipart')
+        encode_multipart_form_data(file, params, opt)
+        file.rewind
+        self.content_length = file.size
+        write_header sock, ver, path
+        IO.copy_stream(file, sock)
+      end
+    end
+
+    def encode_multipart_form_data(out, params, opt)
+      charset = opt[:charset]
+      boundary = opt[:boundary]
+      boundary ||= SecureRandom.urlsafe_base64(40)
+      chunked_p = chunked?
+
+      buf = ''
+      params.each do |key, value, h={}|
+        key = quote_string(key, charset)
+        filename =
+          h.key?(:filename) ? h[:filename] :
+          value.respond_to?(:to_path) ? File.basename(value.to_path) :
+          nil
+
+        buf << "--#{boundary}\r\n"
+        if filename
+          filename = quote_string(filename, charset)
+          type = h[:content_type] || 'application/octet-stream'
+          buf << "Content-Disposition: form-data; " \
+            "name=\"#{key}\"; filename=\"#{filename}\"\r\n" \
+            "Content-Type: #{type}\r\n\r\n"
+          if !out.respond_to?(:write) || !value.respond_to?(:read)
+            # if +out+ is not an IO or +value+ is not an IO
+            buf << (value.respond_to?(:read) ? value.read : value)
+          elsif value.respond_to?(:size) && chunked_p
+            # if +out+ is an IO and +value+ is a File, use IO.copy_stream
+            flush_buffer(out, buf, chunked_p)
+            out << "%x\r\n" % value.size if chunked_p
+            IO.copy_stream(value, out)
+            out << "\r\n" if chunked_p
+          else
+            # +out+ is an IO, and +value+ is not a File but an IO
+            flush_buffer(out, buf, chunked_p)
+            1 while flush_buffer(out, value.read(4096), chunked_p)
+          end
+        else
+          # non-file field:
+          #   HTML5 says, "The parts of the generated multipart/form-data
+          #   resource that correspond to non-file fields must not have a
+          #   Content-Type header specified."
+          buf << "Content-Disposition: form-data; name=\"#{key}\"\r\n\r\n"
+          buf << (value.respond_to?(:read) ? value.read : value)
+        end
+        buf << "\r\n"
+      end
+      buf << "--#{boundary}--\r\n"
+      flush_buffer(out, buf, chunked_p)
+      out << "0\r\n\r\n" if chunked_p
+    end
+
+    def quote_string(str, charset)
+      str = str.encode(charset, fallback:->(c){'&#%d;'%c.encode("UTF-8").ord}) if charset
+      str = str.gsub(/[\\"]/, '\\\\\&')
+    end
+
+    def flush_buffer(out, buf, chunked_p)
+      return unless buf
+      out << "%x\r\n"%buf.bytesize if chunked_p
+      out << buf
+      out << "\r\n" if chunked_p
+      buf.clear
+    end
+
     def supply_default_content_type
       return if content_type()
       warn 'net/http: warning: Content-Type did not set; using application/x-www-form-urlencoded' if $VERBOSE
diff --git a/lib/net/protocol.rb b/lib/net/protocol.rb
index 2a6cfb4..a3ffa71 100644
--- a/lib/net/protocol.rb
+++ b/lib/net/protocol.rb
@@ -168,6 +168,8 @@ module Net # :nodoc:
       }
     end
 
+    alias << write
+
     def writeline(str)
       writing {
         write0 str + "\r\n"
diff --git a/test/net/http/test_http.rb b/test/net/http/test_http.rb
index 76280ad..12c03a4 100644
--- a/test/net/http/test_http.rb
+++ b/test/net/http/test_http.rb
@@ -303,6 +303,102 @@ module TestNetHTTP_version_1_2_methods
     assert_equal data.size, res.body.size
     assert_equal data, res.body
   end
+
+  def test_set_form
+    require 'tempfile'
+    file = Tempfile.new('ruby-test')
+    file << "\u{30c7}\u{30fc}\u{30bf}"
+    data = [
+      ['name', 'Gonbei Nanashi'],
+      ['name', "\u{540d}\u{7121}\u{3057}\u{306e}\u{6a29}\u{5175}\u{885b}"],
+      ['s"i\o', StringIO.new("\u{3042 3044 4e9c 925b}")],
+      ["file", file, filename: "ruby-test"]
+    ]
+    expected = <<"__EOM__".gsub(/\n/, "\r\n")
+--<boundary>
+Content-Disposition: form-data; name="name"
+
+Gonbei Nanashi
+--<boundary>
+Content-Disposition: form-data; name="name"
+
+\xE5\x90\x8D\xE7\x84\xA1\xE3\x81\x97\xE3\x81\xAE\xE6\xA8\xA9\xE5\x85\xB5\xE8\xA1\x9B
+--<boundary>
+Content-Disposition: form-data; name="s\\"i\\\\o"
+
+\xE3\x81\x82\xE3\x81\x84\xE4\xBA\x9C\xE9\x89\x9B
+--<boundary>
+Content-Disposition: form-data; name="file"; filename="ruby-test"
+Content-Type: application/octet-stream
+
+\xE3\x83\x87\xE3\x83\xBC\xE3\x82\xBF
+--<boundary>--
+__EOM__
+    start {|http|
+      _test_set_form_urlencoded(http, data.reject{|k,v|!v.is_a?(String)})
+      _test_set_form_multipart(http, false, data, expected)
+      _test_set_form_multipart(http, true, data, expected)
+    }
+  end
+
+  def _test_set_form_urlencoded(http, data)
+    req = Net::HTTP::Post.new('/')
+    req.set_form(data)
+    res = http.request req
+    assert_equal "name=Gonbei+Nanashi&name=%E5%90%8D%E7%84%A1%E3%81%97%E3%81%AE%E6%A8%A9%E5%85%B5%E8%A1%9B", res.body
+  end
+
+  def _test_set_form_multipart(http, chunked_p, data, expected)
+    data.each{|k,v|v.rewind rescue nil}
+    req = Net::HTTP::Post.new('/')
+    req.set_form(data, 'multipart/form-data')
+    req['Transfer-Encoding'] = 'chunked' if chunked_p
+    res = http.request req
+    body = res.body
+    assert_match(/\A--(?<boundary>\S+)/, body)
+    /\A--(?<boundary>\S+)/ =~ body
+    expected = expected.gsub(/<boundary>/, boundary)
+    assert_equal(expected, body)
+  end
+
+  def test_set_form_with_file
+    require 'tempfile'
+    file = Tempfile.new('ruby-test')
+    file << $test_net_http_data
+    filename = File.basename(file.to_path)
+    data = [['file', file]]
+    expected = <<"__EOM__".gsub(/\n/, "\r\n")
+--<boundary>
+Content-Disposition: form-data; name="file"; filename="<filename>"
+Content-Type: application/octet-stream
+
+<data>
+--<boundary>--
+__EOM__
+    expected.sub!(/<filename>/, filename)
+    expected.sub!(/<data>/, $test_net_http_data)
+    start {|http|
+      data.each{|k,v|v.rewind rescue nil}
+      req = Net::HTTP::Post.new('/')
+      req.set_form(data, 'multipart/form-data')
+      res = http.request req
+      body = res.body
+      header, _ = body.split(/\r\n\r\n/, 2)
+      assert_match(/\A--(?<boundary>\S+)/, body)
+      /\A--(?<boundary>\S+)/ =~ body
+      expected = expected.gsub(/<boundary>/, boundary)
+      assert_match(/^--(?<boundary>\S+)\r\n/, header)
+      assert_match(
+        /^Content-Disposition: form-data; name="file"; filename="#{filename}"\r\n/,
+        header)
+      assert_equal(expected, body)
+
+      data.each{|k,v|v.rewind rescue nil}
+      req['Transfer-Encoding'] = 'chunked'
+      res = http.request req
+      #assert_equal(expected, res.body)
+    }
+  end
 end
 
 class TestNetHTTP_version_1_1 < Test::Unit::TestCase


----------------------------------------
http://redmine.ruby-lang.org