RubyGems - aai10-mechanize - Versions diffs - 2.0.1.0 - Mend

aai10-mechanize 2.0.1.0

Files changed (176) hide show

data/.autotest +6 -0
data/.gitignore +9 -0
data/CHANGELOG.rdoc +652 -0
data/EXAMPLES.rdoc +187 -0
data/FAQ.rdoc +11 -0
data/GUIDE.rdoc +163 -0
data/LICENSE.rdoc +20 -0
data/Manifest.txt +172 -0
data/README.rdoc +63 -0
data/Rakefile +36 -0
data/aai10-mechanize.gemspec +20 -0
data/examples/flickr_upload.rb +22 -0
data/examples/mech-dump.rb +5 -0
data/examples/proxy_req.rb +7 -0
data/examples/rubyforge.rb +20 -0
data/examples/spider.rb +21 -0
data/lib/mechanize.rb +664 -0
data/lib/mechanize/content_type_error.rb +14 -0
data/lib/mechanize/cookie.rb +116 -0
data/lib/mechanize/cookie_jar.rb +202 -0
data/lib/mechanize/element_matcher.rb +35 -0
data/lib/mechanize/file.rb +80 -0
data/lib/mechanize/file_connection.rb +17 -0
data/lib/mechanize/file_request.rb +26 -0
data/lib/mechanize/file_response.rb +74 -0
data/lib/mechanize/file_saver.rb +37 -0
data/lib/mechanize/form.rb +478 -0
data/lib/mechanize/form/button.rb +9 -0
data/lib/mechanize/form/check_box.rb +11 -0
data/lib/mechanize/form/field.rb +44 -0
data/lib/mechanize/form/file_upload.rb +23 -0
data/lib/mechanize/form/image_button.rb +20 -0
data/lib/mechanize/form/multi_select_list.rb +83 -0
data/lib/mechanize/form/option.rb +49 -0
data/lib/mechanize/form/radio_button.rb +48 -0
data/lib/mechanize/form/select_list.rb +40 -0
data/lib/mechanize/headers.rb +25 -0
data/lib/mechanize/history.rb +83 -0
data/lib/mechanize/http.rb +3 -0
data/lib/mechanize/http/agent.rb +738 -0
data/lib/mechanize/inspect.rb +88 -0
data/lib/mechanize/monkey_patch.rb +37 -0
data/lib/mechanize/page.rb +408 -0
data/lib/mechanize/page/base.rb +8 -0
data/lib/mechanize/page/frame.rb +27 -0
data/lib/mechanize/page/image.rb +30 -0
data/lib/mechanize/page/label.rb +20 -0
data/lib/mechanize/page/link.rb +82 -0
data/lib/mechanize/page/meta_refresh.rb +56 -0
data/lib/mechanize/pluggable_parsers.rb +101 -0
data/lib/mechanize/redirect_limit_reached_error.rb +16 -0
data/lib/mechanize/redirect_not_get_or_head_error.rb +19 -0
data/lib/mechanize/response_code_error.rb +22 -0
data/lib/mechanize/response_read_error.rb +27 -0
data/lib/mechanize/robots_disallowed_error.rb +29 -0
data/lib/mechanize/unsupported_scheme_error.rb +8 -0
data/lib/mechanize/util.rb +113 -0
data/test/data/htpasswd +1 -0
data/test/data/server.crt +16 -0
data/test/data/server.csr +12 -0
data/test/data/server.key +15 -0
data/test/data/server.pem +15 -0
data/test/helper.rb +175 -0
data/test/htdocs/alt_text.html +10 -0
data/test/htdocs/bad_form_test.html +9 -0
data/test/htdocs/button.jpg +0 -0
data/test/htdocs/canonical_uri.html +9 -0
data/test/htdocs/dir with spaces/foo.html +1 -0
data/test/htdocs/empty_form.html +6 -0
data/test/htdocs/file_upload.html +26 -0
data/test/htdocs/find_link.html +41 -0
data/test/htdocs/form_multi_select.html +16 -0
data/test/htdocs/form_multival.html +37 -0
data/test/htdocs/form_no_action.html +18 -0
data/test/htdocs/form_no_input_name.html +16 -0
data/test/htdocs/form_select.html +16 -0
data/test/htdocs/form_select_all.html +16 -0
data/test/htdocs/form_select_none.html +17 -0
data/test/htdocs/form_select_noopts.html +10 -0
data/test/htdocs/form_set_fields.html +14 -0
data/test/htdocs/form_test.html +188 -0
data/test/htdocs/frame_referer_test.html +10 -0
data/test/htdocs/frame_test.html +30 -0
data/test/htdocs/google.html +13 -0
data/test/htdocs/iframe_test.html +16 -0
data/test/htdocs/index.html +6 -0
data/test/htdocs/link with space.html +5 -0
data/test/htdocs/meta_cookie.html +11 -0
data/test/htdocs/no_title_test.html +6 -0
data/test/htdocs/nofollow.html +9 -0
data/test/htdocs/noindex.html +9 -0
data/test/htdocs/norobots.html +8 -0
data/test/htdocs/rails_3_encoding_hack_form_test.html +27 -0
data/test/htdocs/rel_nofollow.html +8 -0
data/test/htdocs/relative/tc_relative_links.html +21 -0
data/test/htdocs/robots.html +8 -0
data/test/htdocs/robots.txt +2 -0
data/test/htdocs/tc_bad_charset.html +9 -0
data/test/htdocs/tc_bad_links.html +5 -0
data/test/htdocs/tc_base_images.html +10 -0
data/test/htdocs/tc_base_link.html +8 -0
data/test/htdocs/tc_blank_form.html +11 -0
data/test/htdocs/tc_charset.html +6 -0
data/test/htdocs/tc_checkboxes.html +19 -0
data/test/htdocs/tc_encoded_links.html +5 -0
data/test/htdocs/tc_field_precedence.html +11 -0
data/test/htdocs/tc_follow_meta.html +8 -0
data/test/htdocs/tc_form_action.html +48 -0
data/test/htdocs/tc_images.html +8 -0
data/test/htdocs/tc_links.html +18 -0
data/test/htdocs/tc_meta_in_body.html +9 -0
data/test/htdocs/tc_no_attributes.html +16 -0
data/test/htdocs/tc_pretty_print.html +17 -0
data/test/htdocs/tc_radiobuttons.html +17 -0
data/test/htdocs/tc_referer.html +16 -0
data/test/htdocs/tc_relative_links.html +19 -0
data/test/htdocs/tc_textarea.html +23 -0
data/test/htdocs/test_bad_encoding.html +52 -0
data/test/htdocs/test_click.html +11 -0
data/test/htdocs/unusual______.html +5 -0
data/test/servlets.rb +402 -0
data/test/ssl_server.rb +48 -0
data/test/test_cookies.rb +129 -0
data/test/test_form_action.rb +52 -0
data/test/test_form_as_hash.rb +59 -0
data/test/test_form_button.rb +46 -0
data/test/test_frames.rb +34 -0
data/test/test_headers.rb +33 -0
data/test/test_history.rb +118 -0
data/test/test_history_added.rb +16 -0
data/test/test_html_unscape_forms.rb +46 -0
data/test/test_if_modified_since.rb +20 -0
data/test/test_images.rb +19 -0
data/test/test_mechanize.rb +852 -0
data/test/test_mechanize_cookie.rb +345 -0
data/test/test_mechanize_cookie_jar.rb +433 -0
data/test/test_mechanize_file.rb +53 -0
data/test/test_mechanize_file_request.rb +19 -0
data/test/test_mechanize_file_response.rb +21 -0
data/test/test_mechanize_form.rb +576 -0
data/test/test_mechanize_form_check_box.rb +37 -0
data/test/test_mechanize_form_encoding.rb +120 -0
data/test/test_mechanize_form_field.rb +21 -0
data/test/test_mechanize_form_image_button.rb +12 -0
data/test/test_mechanize_form_textarea.rb +51 -0
data/test/test_mechanize_http_agent.rb +697 -0
data/test/test_mechanize_link.rb +84 -0
data/test/test_mechanize_page_encoding.rb +147 -0
data/test/test_mechanize_page_link.rb +382 -0
data/test/test_mechanize_page_meta_refresh.rb +115 -0
data/test/test_mechanize_redirect_not_get_or_head_error.rb +18 -0
data/test/test_mechanize_subclass.rb +22 -0
data/test/test_mechanize_util.rb +92 -0
data/test/test_multi_select.rb +118 -0
data/test/test_no_attributes.rb +13 -0
data/test/test_option.rb +18 -0
data/test/test_pluggable_parser.rb +136 -0
data/test/test_post_form.rb +37 -0
data/test/test_pretty_print.rb +22 -0
data/test/test_radiobutton.rb +75 -0
data/test/test_redirect_limit_reached.rb +39 -0
data/test/test_redirect_ok.rb +25 -0
data/test/test_referer.rb +81 -0
data/test/test_relative_links.rb +40 -0
data/test/test_request.rb +13 -0
data/test/test_response_code.rb +53 -0
data/test/test_robots.rb +72 -0
data/test/test_save_file.rb +48 -0
data/test/test_scheme.rb +48 -0
data/test/test_select.rb +119 -0
data/test/test_select_all.rb +15 -0
data/test/test_select_none.rb +15 -0
data/test/test_select_noopts.rb +18 -0
data/test/test_set_fields.rb +44 -0
data/test/test_ssl_server.rb +20 -0
metadata +360 -0

data/lib/mechanize/unsupported_scheme_error.rb ADDED

@@ -0,0 +1,8 @@
+class Mechanize
+  class UnsupportedSchemeError < Mechanize::Error
+    attr_accessor :scheme
+    def initialize(scheme)
+      @scheme = scheme
+    end
+  end
+end

data/lib/mechanize/util.rb ADDED

@@ -0,0 +1,113 @@
+require 'cgi'
+class Mechanize::Util
+  CODE_DIC = {
+    :JIS => "ISO-2022-JP",
+    :EUC => "EUC-JP",
+    :SJIS => "SHIFT_JIS",
+    :UTF8 => "UTF-8", :UTF16 => "UTF-16", :UTF32 => "UTF-32"}
+  # true if RUBY_VERSION is 1.9.0 or later
+  NEW_RUBY_ENCODING = RUBY_VERSION >= '1.9.0'
+  # contains encoding error classes to raise
+  ENCODING_ERRORS = if NEW_RUBY_ENCODING
+                      [EncodingError]
+                    else
+                      [Iconv::InvalidEncoding, Iconv::IllegalSequence]
+                    end
+  def self.build_query_string(parameters, enc=nil)
+    parameters.map { |k,v|
+      # WEBrick::HTTP.escape* has some problems about m17n on ruby-1.9.*.
+      [CGI.escape(k.to_s), CGI.escape(v.to_s)].join("=") if k
+    }.compact.join('&')
+  end
+  def self.to_native_charset(s, code=nil)
+    location = Gem.location_of_caller.join ':'
+    warn "#{location}: Mechanize::Util::to_native_charset is deprecated and will be removed October 2011"
+    if Mechanize.html_parser == Nokogiri::HTML
+      return unless s
+      code ||= detect_charset(s)
+      Iconv.iconv("UTF-8", code, s).join("")
+    else
+      s
+    end
+  end
+  # Converts string +s+ from +code+ to UTF-8.
+  def self.from_native_charset(s, code, ignore_encoding_error=false, log=nil)
+    return s unless s && code
+    return s unless Mechanize.html_parser == Nokogiri::HTML
+    begin
+      encode_to(code, s)
+    rescue *ENCODING_ERRORS => ex
+      log.debug("from_native_charset: #{ex.class}: form encoding: #{code.inspect} string: #{s}") if log
+      if ignore_encoding_error
+        s
+      else
+        raise
+      end
+    end
+  end
+  # inner convert method of Util.from_native_charset
+  def self.encode_to(encoding, str)
+    if NEW_RUBY_ENCODING
+      str.encode(encoding)
+    else
+      Iconv.conv(encoding.to_s, "UTF-8", str)
+    end
+  end
+  private_class_method :encode_to
+  def self.html_unescape(s)
+    return s unless s
+    s.gsub(/&(\w+|#[0-9]+);/) { |match|
+      number = case match
+               when /&(\w+);/
+                 Mechanize.html_parser::NamedCharacters[$1]
+               when /&#([0-9]+);/
+                 $1.to_i
+               end
+      number ? ([number].pack('U') rescue match) : match
+    }
+  end
+  def self.detect_charset(src)
+    tmp = NKF.guess(src || "<html></html>")
+    if RUBY_VERSION >= "1.9.0"
+      enc = tmp.to_s.upcase
+    else
+      enc = NKF.constants.find{|c|
+        NKF.const_get(c) == tmp
+      }
+      enc = CODE_DIC[enc.intern]
+    end
+    enc || "ISO-8859-1"
+  end
+  def self.uri_escape str
+    @parser ||= begin
+                  URI::Parser.new
+                rescue NameError
+                  URI
+                end
+    @parser.escape str
+  end
+  def self.uri_unescape str
+    @parser ||= begin
+                  URI::Parser.new
+                rescue NameError
+                  URI
+                end
+    @parser.unescape str
+  end
+end

data/test/data/htpasswd ADDED

	@@ -0,0 +1 @@
1	+ mech:44E/qORekFV0E

data/test/data/server.crt ADDED

@@ -0,0 +1,16 @@
+-----BEGIN CERTIFICATE-----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=
+-----END CERTIFICATE-----

data/test/data/server.csr ADDED

@@ -0,0 +1,12 @@
+-----BEGIN CERTIFICATE REQUEST-----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+-----END CERTIFICATE REQUEST-----

data/test/data/server.key ADDED

@@ -0,0 +1,15 @@
+-----BEGIN RSA PRIVATE KEY-----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+-----END RSA PRIVATE KEY-----

data/test/data/server.pem ADDED

@@ -0,0 +1,15 @@
+-----BEGIN RSA PRIVATE KEY-----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+-----END RSA PRIVATE KEY-----

data/test/helper.rb ADDED

@@ -0,0 +1,175 @@
+require 'rubygems'
+require 'minitest/autorun'
+require 'mechanize'
+require 'webrick/httputils'
+require 'servlets'
+require 'tmpdir'
+require 'tempfile'
+BASE_DIR = File.dirname(__FILE__)
+# Move this to a test base class
+module MechTestHelper
+  def self.fake_page(agent)
+    html = <<-END
+    <html><body>
+    <form><input type="submit" value="submit" /></form>
+    </body></html>
+    END
+    html_response = { 'content-type' => 'text/html' }
+    Mechanize::Page.new(  nil, html_response, html, 200, agent )
+  end
+end
+class Net::HTTP
+  alias :old_do_start :do_start
+  def do_start
+    @started = true
+  end
+  SERVLETS = {
+    '/gzip'                   => GzipServlet,
+    '/form_post'              => FormTest,
+    '/basic_auth'             => BasicAuthServlet,
+    '/form post'              => FormTest,
+    '/response_code'          => ResponseCodeTest,
+    '/http_refresh'           => HttpRefreshTest,
+    '/bad_content_type'       => BadContentTypeTest,
+    '/content_type_test'      => ContentTypeTest,
+    '/referer'                => RefererServlet,
+    '/file_upload'            => FileUploadTest,
+    '/one_cookie'             => OneCookieTest,
+    '/one_cookie_no_space'    => OneCookieNoSpacesTest,
+    '/many_cookies'           => ManyCookiesTest,
+    '/many_cookies_as_string' => ManyCookiesAsStringTest,
+    '/send_cookies'           => SendCookiesTest,
+    '/quoted_value_cookie'    => QuotedValueCookieTest,
+    '/if_modified_since'      => ModifiedSinceServlet,
+    '/http_headers'           => HeaderServlet,
+    '/infinite_redirect'      => InfiniteRedirectTest,
+    '/infinite_refresh'       => InfiniteRefreshTest,
+    '/redirect_ok'            => RedirectOkTest,
+    '/redirect'               => RedirectTest,
+    '/refresh_without_url'    => RefreshWithoutUrl,
+    '/refresh_with_empty_url' => RefreshWithEmptyUrl,
+    '/digest_auth'            => DigestAuthServlet,
+    '/verb'                   => VerbServlet,
+  }
+  PAGE_CACHE = {}
+  alias :old_request :request
+  def request(request, *data, &block)
+    url = URI.parse(request.path)
+    path = WEBrick::HTTPUtils.unescape(url.path)
+    path = '/index.html' if path == '/'
+    res = ::Response.new
+    res.query_params = url.query
+    request.query = if 'POST' != request.method && url.query then
+                      WEBrick::HTTPUtils.parse_query url.query
+                    elsif request['content-type'] =~ /www-form-urlencoded/ then
+                      WEBrick::HTTPUtils.parse_query request.body
+                    elsif request['content-type'] =~ /boundary=(.+)/ then
+                      boundary = WEBrick::HTTPUtils.dequote $1
+                      WEBrick::HTTPUtils.parse_form_data request.body, boundary
+                    else
+                      {}
+                    end
+    request.cookies = WEBrick::Cookie.parse(request['Cookie'])
+    if SERVLETS[path]
+      SERVLETS[path].new({}).send("do_#{request.method}", request, res)
+    else
+      filename = "htdocs#{path.gsub(/[^\/\\.\w\s]/, '_')}"
+      unless PAGE_CACHE[filename]
+        File.open("#{BASE_DIR}/#{filename}", 'rb') { |file|
+          PAGE_CACHE[filename] = file.read
+        }
+      end
+      res.body = PAGE_CACHE[filename]
+      case filename
+      when /\.txt$/
+        res['Content-Type'] = 'text/plain'
+      when /\.jpg$/
+        res['Content-Type'] = 'image/jpeg'
+      end
+    end
+    res['Content-Type'] ||= 'text/html'
+    res.code ||= "200"
+    response_klass = Net::HTTPResponse::CODE_TO_OBJ[res.code.to_s]
+    response = response_klass.new res.http_version, res.code, res.message
+    res.header.each do |k,v|
+      v = v.first if v.length == 1
+      response[k] = v
+    end
+    res.cookies.each do |cookie|
+      response.add_field 'Set-Cookie', cookie.to_s
+    end
+    response['Content-Type'] ||= 'text/html'
+    response['Content-Length'] = res['Content-Length'] || res.body.length.to_s
+    io = StringIO.new(res.body)
+    response.instance_variable_set :@socket, io
+    def io.read clen, dest, _
+      dest << string[0, clen]
+    end
+    body_exist = request.response_body_permitted? &&
+                 response_klass.body_permitted?
+    response.instance_variable_set :@body_exist, body_exist
+    yield response if block_given?
+    response
+  end
+end
+class Net::HTTPRequest
+  attr_accessor :query, :body, :cookies, :user
+end
+class Response
+  include Net::HTTPHeader
+  attr_reader :code
+  attr_accessor :body, :query, :cookies
+  attr_accessor :query_params, :http_version
+  attr_accessor :header
+  def code=(c)
+    @code = c.to_s
+  end
+  alias :status :code
+  alias :status= :code=
+  def initialize
+    @header = {}
+    @body = ''
+    @code = nil
+    @query = nil
+    @cookies = []
+    @http_version = '1.1'
+  end
+  def read_body
+    yield body
+  end
+  def message
+    ''
+  end
+end

data/test/htdocs/alt_text.html ADDED

@@ -0,0 +1,10 @@
+<html>
+  <meta http-equiv="Refresh" content="0; url=http://www.drphil.com/">
+  <body>
+    <a href="alt_text.html"><img alt="alt text" src="hello"></a>
+    <a href="no_alt_text.html"><img src="hello"></a>
+    <a href="nil_alt_text.html"><img alt src="hello"></a>
+    <a href="no_image.html">no image</a>
+    <a href="no_text.html"></a>
+  </body>
+</html>

data/test/htdocs/bad_form_test.html ADDED

@@ -0,0 +1,9 @@
+<html>
+  <head><title>Page Title</title></head>
+  <body>
+    <form name="form" method="duh" action="/form_post">
+      <input name="first" type="text" />
+      <input type="submit" value="Submit" />
+    </form>
+  </body>
+</html>

data/test/htdocs/button.jpg ADDED

Binary file

data/test/htdocs/canonical_uri.html ADDED

@@ -0,0 +1,9 @@
+<html>
+  <head>
+    <link rel="start" title="site top" href="/" />
+    <link rel="canonical" href="http://localhost/canonical_uri" />
+  </head>
+  <body>
+    test
+  </body>
+</html>

data/test/htdocs/dir with spaces/foo.html ADDED

	@@ -0,0 +1 @@
1	+ HELLO

data/test/htdocs/empty_form.html ADDED

@@ -0,0 +1,6 @@
+<html>
+  <body>
+    <form>
+    </form>
+  </body>
+</html>

data/test/htdocs/file_upload.html ADDED

@@ -0,0 +1,26 @@
+<html>
+  <head>
+    <title>File Upload Form</title>
+  </head>
+  <body>
+    <h1>File Upload Test</h1>
+    <form enctype="multipart/form-data" action="/file_upload" method="post">
+      Your name: <input type="text" name="name" /><br />
+      File to process: <input name="userfile1" type="file" /><br />
+      <input type="text" name="foo[aaron]" value="test" />
+      <select name="foo">
+      </select>
+      <input type="submit" value="Send File" />
+    </form>
+    <form enctype="multipart/form-data" action="/file_upload" method="post">
+      Your name: <input type="text" name="name" /><br />
+      File to process: <input name="green[eggs]" type="file" /><br />
+      <input type="submit" value="Send File" />
+    </form>
+    <form enctype="multipart/form-data" action="/file_upload" name="value_test" method="post">
+      Your name: <input type="text" name="name" /><br />
+      File to process: <input name="green[eggs]" value="/etc/hosts" type="file" /><br />
+      <input type="submit" value="Send File" />
+    </form>
+  </body>
+</html>

data/test/htdocs/find_link.html ADDED

@@ -0,0 +1,41 @@
+<html>
+    <head>
+        <meta http_equiv="Refresh" content="0; url=http://www.incorrect.com">
+        <meta http-equiv="Rfresh" content="0; url=http://www.also-wrong.com">
+        <meta http-equiv="Refresh" content="0; url=http://www.drphil.com/">
+        <meta http-equiv="Refresh" content="0; url='http://tenderlovemaking.com/'">
+        <META HTTP-EQUIV="REFRESH" CONTENT="0; URL=HTTP://WWW.UPCASE.COM/">
+        <TITLE>Testing the links</TITLE>
+    </head>
+    <body>
+        <A HREF="http://blargle.com/">blargle</A>
+        <A HREF="http://a.cpan.org/">CPAN A</A>
+        <A HREF="http://b.cpan.org/">CPAN B</A>
+        <FRAME SRC="foo.html">
+        <FRAME SRC="bar.html">
+        <A HREF="http://c.cpan.org/" NAME="bongo">CPAN C</A>
+        <A HREF="http://d.cpan.org/">CPAN D</A>
+        <A HREF="http://www.msnbc.com/">MSNBC</A>
+        <FRAME SRC="http://www.oreilly.com/" NAME="wongo">
+        <A HREF="http://www.cnn.com/">CNN</A>
+        <A HREF="http://www.bbc.co.uk/" NAME="Wilma">BBC</A>
+        <A HREF="http://www.msnbc.com/">News</A>
+        <A HREF="http://www.cnn.com/" NAME="Fred">News</A>
+        <A HREF="http://www.bbc.co.uk/">News</A>
+        <A onmouseover="window.status='Rebuild Files'; return true" href="#" onClick="window.open(  '/cgi-bin/MT/mt.cgi', 'rebuild', 'width=400,height=200,resizable=yes')">Rebuild Index</A>
+        <MAP NAME="SOME_MAP">
+            <AREA HREF="http://www.msnbc.com/area" COORDS="1,2,3,4"></AREA>
+            <AREA HREF="http://www.cnn.com/area" COORDS="5,6,7,8" NAME="Marty">
+            <AREA HREF="http://www.cpan.org/area" COORDS="10,11,12,13" />
+        </MAP>
+        <IMG SRC="SOME_IMAGE" USEMAP="#SOME_MAP">
+        <!-- new stuff -->
+        <A HREF="http://nowhere.org/" Name="Here">NoWhere</A>
+        <A HREF="http://nowhere.org/padded" Name=" Here "> NoWhere </A>
+        <A HREF="blongo.html">Blongo!</A>
+    </body>
+</html>