halorgium-actionpack 3.0.pre
Sign up to get free protection for your applications and to get access to all the features.
- data/CHANGELOG +5179 -0
- data/MIT-LICENSE +21 -0
- data/README +409 -0
- data/lib/abstract_controller.rb +16 -0
- data/lib/abstract_controller/base.rb +158 -0
- data/lib/abstract_controller/callbacks.rb +113 -0
- data/lib/abstract_controller/exceptions.rb +12 -0
- data/lib/abstract_controller/helpers.rb +151 -0
- data/lib/abstract_controller/layouts.rb +250 -0
- data/lib/abstract_controller/localized_cache.rb +49 -0
- data/lib/abstract_controller/logger.rb +61 -0
- data/lib/abstract_controller/rendering_controller.rb +188 -0
- data/lib/action_controller.rb +72 -0
- data/lib/action_controller/base.rb +168 -0
- data/lib/action_controller/caching.rb +80 -0
- data/lib/action_controller/caching/actions.rb +163 -0
- data/lib/action_controller/caching/fragments.rb +116 -0
- data/lib/action_controller/caching/pages.rb +154 -0
- data/lib/action_controller/caching/sweeping.rb +97 -0
- data/lib/action_controller/deprecated.rb +4 -0
- data/lib/action_controller/deprecated/integration_test.rb +2 -0
- data/lib/action_controller/deprecated/performance_test.rb +1 -0
- data/lib/action_controller/dispatch/dispatcher.rb +57 -0
- data/lib/action_controller/metal.rb +129 -0
- data/lib/action_controller/metal/benchmarking.rb +73 -0
- data/lib/action_controller/metal/compatibility.rb +145 -0
- data/lib/action_controller/metal/conditional_get.rb +86 -0
- data/lib/action_controller/metal/configuration.rb +28 -0
- data/lib/action_controller/metal/cookies.rb +105 -0
- data/lib/action_controller/metal/exceptions.rb +55 -0
- data/lib/action_controller/metal/filter_parameter_logging.rb +77 -0
- data/lib/action_controller/metal/flash.rb +162 -0
- data/lib/action_controller/metal/head.rb +27 -0
- data/lib/action_controller/metal/helpers.rb +115 -0
- data/lib/action_controller/metal/hide_actions.rb +47 -0
- data/lib/action_controller/metal/http_authentication.rb +312 -0
- data/lib/action_controller/metal/layouts.rb +171 -0
- data/lib/action_controller/metal/mime_responds.rb +317 -0
- data/lib/action_controller/metal/rack_convenience.rb +27 -0
- data/lib/action_controller/metal/redirector.rb +22 -0
- data/lib/action_controller/metal/render_options.rb +103 -0
- data/lib/action_controller/metal/rendering_controller.rb +57 -0
- data/lib/action_controller/metal/request_forgery_protection.rb +108 -0
- data/lib/action_controller/metal/rescuable.rb +13 -0
- data/lib/action_controller/metal/responder.rb +200 -0
- data/lib/action_controller/metal/session.rb +15 -0
- data/lib/action_controller/metal/session_management.rb +45 -0
- data/lib/action_controller/metal/streaming.rb +188 -0
- data/lib/action_controller/metal/testing.rb +39 -0
- data/lib/action_controller/metal/url_for.rb +41 -0
- data/lib/action_controller/metal/verification.rb +130 -0
- data/lib/action_controller/middleware.rb +38 -0
- data/lib/action_controller/notifications.rb +10 -0
- data/lib/action_controller/polymorphic_routes.rb +183 -0
- data/lib/action_controller/record_identifier.rb +91 -0
- data/lib/action_controller/testing/process.rb +111 -0
- data/lib/action_controller/testing/test_case.rb +345 -0
- data/lib/action_controller/translation.rb +13 -0
- data/lib/action_controller/url_rewriter.rb +204 -0
- data/lib/action_controller/vendor/html-scanner.rb +16 -0
- data/lib/action_controller/vendor/html-scanner/html/document.rb +68 -0
- data/lib/action_controller/vendor/html-scanner/html/node.rb +537 -0
- data/lib/action_controller/vendor/html-scanner/html/sanitizer.rb +176 -0
- data/lib/action_controller/vendor/html-scanner/html/selector.rb +828 -0
- data/lib/action_controller/vendor/html-scanner/html/tokenizer.rb +105 -0
- data/lib/action_controller/vendor/html-scanner/html/version.rb +11 -0
- data/lib/action_dispatch.rb +70 -0
- data/lib/action_dispatch/http/headers.rb +33 -0
- data/lib/action_dispatch/http/mime_type.rb +231 -0
- data/lib/action_dispatch/http/mime_types.rb +23 -0
- data/lib/action_dispatch/http/request.rb +539 -0
- data/lib/action_dispatch/http/response.rb +290 -0
- data/lib/action_dispatch/http/status_codes.rb +42 -0
- data/lib/action_dispatch/http/utils.rb +20 -0
- data/lib/action_dispatch/middleware/callbacks.rb +50 -0
- data/lib/action_dispatch/middleware/params_parser.rb +79 -0
- data/lib/action_dispatch/middleware/rescue.rb +26 -0
- data/lib/action_dispatch/middleware/session/abstract_store.rb +208 -0
- data/lib/action_dispatch/middleware/session/cookie_store.rb +235 -0
- data/lib/action_dispatch/middleware/session/mem_cache_store.rb +47 -0
- data/lib/action_dispatch/middleware/show_exceptions.rb +143 -0
- data/lib/action_dispatch/middleware/stack.rb +116 -0
- data/lib/action_dispatch/middleware/static.rb +44 -0
- data/lib/action_dispatch/middleware/string_coercion.rb +29 -0
- data/lib/action_dispatch/middleware/templates/rescues/_request_and_response.erb +24 -0
- data/lib/action_dispatch/middleware/templates/rescues/_trace.erb +26 -0
- data/lib/action_dispatch/middleware/templates/rescues/diagnostics.erb +10 -0
- data/lib/action_dispatch/middleware/templates/rescues/layout.erb +29 -0
- data/lib/action_dispatch/middleware/templates/rescues/missing_template.erb +2 -0
- data/lib/action_dispatch/middleware/templates/rescues/routing_error.erb +10 -0
- data/lib/action_dispatch/middleware/templates/rescues/template_error.erb +21 -0
- data/lib/action_dispatch/middleware/templates/rescues/unknown_action.erb +2 -0
- data/lib/action_dispatch/routing.rb +381 -0
- data/lib/action_dispatch/routing/deprecated_mapper.rb +878 -0
- data/lib/action_dispatch/routing/mapper.rb +327 -0
- data/lib/action_dispatch/routing/route.rb +49 -0
- data/lib/action_dispatch/routing/route_set.rb +497 -0
- data/lib/action_dispatch/testing/assertions.rb +8 -0
- data/lib/action_dispatch/testing/assertions/dom.rb +35 -0
- data/lib/action_dispatch/testing/assertions/model.rb +19 -0
- data/lib/action_dispatch/testing/assertions/response.rb +145 -0
- data/lib/action_dispatch/testing/assertions/routing.rb +144 -0
- data/lib/action_dispatch/testing/assertions/selector.rb +639 -0
- data/lib/action_dispatch/testing/assertions/tag.rb +123 -0
- data/lib/action_dispatch/testing/integration.rb +504 -0
- data/lib/action_dispatch/testing/performance_test.rb +15 -0
- data/lib/action_dispatch/testing/test_request.rb +83 -0
- data/lib/action_dispatch/testing/test_response.rb +131 -0
- data/lib/action_pack.rb +24 -0
- data/lib/action_pack/version.rb +9 -0
- data/lib/action_view.rb +58 -0
- data/lib/action_view/base.rb +308 -0
- data/lib/action_view/context.rb +44 -0
- data/lib/action_view/erb/util.rb +48 -0
- data/lib/action_view/helpers.rb +62 -0
- data/lib/action_view/helpers/active_model_helper.rb +306 -0
- data/lib/action_view/helpers/ajax_helper.rb +68 -0
- data/lib/action_view/helpers/asset_tag_helper.rb +830 -0
- data/lib/action_view/helpers/atom_feed_helper.rb +198 -0
- data/lib/action_view/helpers/cache_helper.rb +39 -0
- data/lib/action_view/helpers/capture_helper.rb +168 -0
- data/lib/action_view/helpers/date_helper.rb +988 -0
- data/lib/action_view/helpers/debug_helper.rb +38 -0
- data/lib/action_view/helpers/form_helper.rb +1102 -0
- data/lib/action_view/helpers/form_options_helper.rb +600 -0
- data/lib/action_view/helpers/form_tag_helper.rb +495 -0
- data/lib/action_view/helpers/javascript_helper.rb +208 -0
- data/lib/action_view/helpers/number_helper.rb +311 -0
- data/lib/action_view/helpers/prototype_helper.rb +1309 -0
- data/lib/action_view/helpers/raw_output_helper.rb +9 -0
- data/lib/action_view/helpers/record_identification_helper.rb +20 -0
- data/lib/action_view/helpers/record_tag_helper.rb +58 -0
- data/lib/action_view/helpers/sanitize_helper.rb +259 -0
- data/lib/action_view/helpers/scriptaculous_helper.rb +226 -0
- data/lib/action_view/helpers/tag_helper.rb +151 -0
- data/lib/action_view/helpers/text_helper.rb +594 -0
- data/lib/action_view/helpers/translation_helper.rb +39 -0
- data/lib/action_view/helpers/url_helper.rb +639 -0
- data/lib/action_view/locale/en.yml +117 -0
- data/lib/action_view/paths.rb +80 -0
- data/lib/action_view/render/partials.rb +342 -0
- data/lib/action_view/render/rendering.rb +134 -0
- data/lib/action_view/safe_buffer.rb +28 -0
- data/lib/action_view/template/error.rb +101 -0
- data/lib/action_view/template/handler.rb +36 -0
- data/lib/action_view/template/handlers.rb +52 -0
- data/lib/action_view/template/handlers/builder.rb +17 -0
- data/lib/action_view/template/handlers/erb.rb +53 -0
- data/lib/action_view/template/handlers/rjs.rb +18 -0
- data/lib/action_view/template/resolver.rb +165 -0
- data/lib/action_view/template/template.rb +131 -0
- data/lib/action_view/template/text.rb +38 -0
- data/lib/action_view/test_case.rb +163 -0
- metadata +236 -0
@@ -0,0 +1,204 @@
|
|
1
|
+
module ActionController
|
2
|
+
# In <b>routes.rb</b> one defines URL-to-controller mappings, but the reverse
|
3
|
+
# is also possible: an URL can be generated from one of your routing definitions.
|
4
|
+
# URL generation functionality is centralized in this module.
|
5
|
+
#
|
6
|
+
# See ActionController::Routing and ActionController::Resources for general
|
7
|
+
# information about routing and routes.rb.
|
8
|
+
#
|
9
|
+
# <b>Tip:</b> If you need to generate URLs from your models or some other place,
|
10
|
+
# then ActionController::UrlWriter is what you're looking for. Read on for
|
11
|
+
# an introduction.
|
12
|
+
#
|
13
|
+
# == URL generation from parameters
|
14
|
+
#
|
15
|
+
# As you may know, some functions - such as ActionController::Base#url_for
|
16
|
+
# and ActionView::Helpers::UrlHelper#link_to, can generate URLs given a set
|
17
|
+
# of parameters. For example, you've probably had the chance to write code
|
18
|
+
# like this in one of your views:
|
19
|
+
#
|
20
|
+
# <%= link_to('Click here', :controller => 'users',
|
21
|
+
# :action => 'new', :message => 'Welcome!') %>
|
22
|
+
#
|
23
|
+
# #=> Generates a link to: /users/new?message=Welcome%21
|
24
|
+
#
|
25
|
+
# link_to, and all other functions that require URL generation functionality,
|
26
|
+
# actually use ActionController::UrlWriter under the hood. And in particular,
|
27
|
+
# they use the ActionController::UrlWriter#url_for method. One can generate
|
28
|
+
# the same path as the above example by using the following code:
|
29
|
+
#
|
30
|
+
# include UrlWriter
|
31
|
+
# url_for(:controller => 'users',
|
32
|
+
# :action => 'new',
|
33
|
+
# :message => 'Welcome!',
|
34
|
+
# :only_path => true)
|
35
|
+
# # => "/users/new?message=Welcome%21"
|
36
|
+
#
|
37
|
+
# Notice the <tt>:only_path => true</tt> part. This is because UrlWriter has no
|
38
|
+
# information about the website hostname that your Rails app is serving. So if you
|
39
|
+
# want to include the hostname as well, then you must also pass the <tt>:host</tt>
|
40
|
+
# argument:
|
41
|
+
#
|
42
|
+
# include UrlWriter
|
43
|
+
# url_for(:controller => 'users',
|
44
|
+
# :action => 'new',
|
45
|
+
# :message => 'Welcome!',
|
46
|
+
# :host => 'www.example.com') # Changed this.
|
47
|
+
# # => "http://www.example.com/users/new?message=Welcome%21"
|
48
|
+
#
|
49
|
+
# By default, all controllers and views have access to a special version of url_for,
|
50
|
+
# that already knows what the current hostname is. So if you use url_for in your
|
51
|
+
# controllers or your views, then you don't need to explicitly pass the <tt>:host</tt>
|
52
|
+
# argument.
|
53
|
+
#
|
54
|
+
# For convenience reasons, mailers provide a shortcut for ActionController::UrlWriter#url_for.
|
55
|
+
# So within mailers, you only have to type 'url_for' instead of 'ActionController::UrlWriter#url_for'
|
56
|
+
# in full. However, mailers don't have hostname information, and what's why you'll still
|
57
|
+
# have to specify the <tt>:host</tt> argument when generating URLs in mailers.
|
58
|
+
#
|
59
|
+
#
|
60
|
+
# == URL generation for named routes
|
61
|
+
#
|
62
|
+
# UrlWriter also allows one to access methods that have been auto-generated from
|
63
|
+
# named routes. For example, suppose that you have a 'users' resource in your
|
64
|
+
# <b>routes.rb</b>:
|
65
|
+
#
|
66
|
+
# map.resources :users
|
67
|
+
#
|
68
|
+
# This generates, among other things, the method <tt>users_path</tt>. By default,
|
69
|
+
# this method is accessible from your controllers, views and mailers. If you need
|
70
|
+
# to access this auto-generated method from other places (such as a model), then
|
71
|
+
# you can do that by including ActionController::UrlWriter in your class:
|
72
|
+
#
|
73
|
+
# class User < ActiveRecord::Base
|
74
|
+
# include ActionController::UrlWriter
|
75
|
+
#
|
76
|
+
# def base_uri
|
77
|
+
# user_path(self)
|
78
|
+
# end
|
79
|
+
# end
|
80
|
+
#
|
81
|
+
# User.find(1).base_uri # => "/users/1"
|
82
|
+
module UrlWriter
|
83
|
+
def self.included(base) #:nodoc:
|
84
|
+
ActionController::Routing::Routes.install_helpers(base)
|
85
|
+
base.mattr_accessor :default_url_options
|
86
|
+
|
87
|
+
# The default options for urls written by this writer. Typically a <tt>:host</tt> pair is provided.
|
88
|
+
base.default_url_options ||= {}
|
89
|
+
end
|
90
|
+
|
91
|
+
# Generate a url based on the options provided, default_url_options and the
|
92
|
+
# routes defined in routes.rb. The following options are supported:
|
93
|
+
#
|
94
|
+
# * <tt>:only_path</tt> - If true, the relative url is returned. Defaults to +false+.
|
95
|
+
# * <tt>:protocol</tt> - The protocol to connect to. Defaults to 'http'.
|
96
|
+
# * <tt>:host</tt> - Specifies the host the link should be targeted at.
|
97
|
+
# If <tt>:only_path</tt> is false, this option must be
|
98
|
+
# provided either explicitly, or via +default_url_options+.
|
99
|
+
# * <tt>:port</tt> - Optionally specify the port to connect to.
|
100
|
+
# * <tt>:anchor</tt> - An anchor name to be appended to the path.
|
101
|
+
# * <tt>:skip_relative_url_root</tt> - If true, the url is not constructed using the
|
102
|
+
# +relative_url_root+ set in ActionController::Base.relative_url_root.
|
103
|
+
# * <tt>:trailing_slash</tt> - If true, adds a trailing slash, as in "/archive/2009/"
|
104
|
+
#
|
105
|
+
# Any other key (<tt>:controller</tt>, <tt>:action</tt>, etc.) given to
|
106
|
+
# +url_for+ is forwarded to the Routes module.
|
107
|
+
#
|
108
|
+
# Examples:
|
109
|
+
#
|
110
|
+
# url_for :controller => 'tasks', :action => 'testing', :host=>'somehost.org', :port=>'8080' # => 'http://somehost.org:8080/tasks/testing'
|
111
|
+
# url_for :controller => 'tasks', :action => 'testing', :host=>'somehost.org', :anchor => 'ok', :only_path => true # => '/tasks/testing#ok'
|
112
|
+
# url_for :controller => 'tasks', :action => 'testing', :trailing_slash=>true # => 'http://somehost.org/tasks/testing/'
|
113
|
+
# url_for :controller => 'tasks', :action => 'testing', :host=>'somehost.org', :number => '33' # => 'http://somehost.org/tasks/testing?number=33'
|
114
|
+
def url_for(options)
|
115
|
+
options = self.class.default_url_options.merge(options)
|
116
|
+
|
117
|
+
url = ''
|
118
|
+
|
119
|
+
unless options.delete(:only_path)
|
120
|
+
url << (options.delete(:protocol) || 'http')
|
121
|
+
url << '://' unless url.match("://")
|
122
|
+
|
123
|
+
raise "Missing host to link to! Please provide :host parameter or set default_url_options[:host]" unless options[:host]
|
124
|
+
|
125
|
+
url << options.delete(:host)
|
126
|
+
url << ":#{options.delete(:port)}" if options.key?(:port)
|
127
|
+
else
|
128
|
+
# Delete the unused options to prevent their appearance in the query string.
|
129
|
+
[:protocol, :host, :port, :skip_relative_url_root].each { |k| options.delete(k) }
|
130
|
+
end
|
131
|
+
trailing_slash = options.delete(:trailing_slash) if options.key?(:trailing_slash)
|
132
|
+
url << ActionController::Base.relative_url_root.to_s unless options[:skip_relative_url_root]
|
133
|
+
anchor = "##{CGI.escape options.delete(:anchor).to_param.to_s}" if options[:anchor]
|
134
|
+
generated = Routing::Routes.generate(options, {})
|
135
|
+
url << (trailing_slash ? generated.sub(/\?|\z/) { "/" + $& } : generated)
|
136
|
+
url << anchor if anchor
|
137
|
+
|
138
|
+
url
|
139
|
+
end
|
140
|
+
end
|
141
|
+
|
142
|
+
# Rewrites URLs for Base.redirect_to and Base.url_for in the controller.
|
143
|
+
class UrlRewriter #:nodoc:
|
144
|
+
RESERVED_OPTIONS = [:anchor, :params, :only_path, :host, :protocol, :port, :trailing_slash, :skip_relative_url_root]
|
145
|
+
def initialize(request, parameters)
|
146
|
+
@request, @parameters = request, parameters
|
147
|
+
end
|
148
|
+
|
149
|
+
def rewrite(options = {})
|
150
|
+
rewrite_url(options)
|
151
|
+
end
|
152
|
+
|
153
|
+
def to_str
|
154
|
+
"#{@request.protocol}, #{@request.host_with_port}, #{@request.path}, #{@parameters[:controller]}, #{@parameters[:action]}, #{@request.parameters.inspect}"
|
155
|
+
end
|
156
|
+
|
157
|
+
alias_method :to_s, :to_str
|
158
|
+
|
159
|
+
private
|
160
|
+
# Given a path and options, returns a rewritten URL string
|
161
|
+
def rewrite_url(options)
|
162
|
+
rewritten_url = ""
|
163
|
+
|
164
|
+
unless options[:only_path]
|
165
|
+
rewritten_url << (options[:protocol] || @request.protocol)
|
166
|
+
rewritten_url << "://" unless rewritten_url.match("://")
|
167
|
+
rewritten_url << rewrite_authentication(options)
|
168
|
+
rewritten_url << (options[:host] || @request.host_with_port)
|
169
|
+
rewritten_url << ":#{options.delete(:port)}" if options.key?(:port)
|
170
|
+
end
|
171
|
+
|
172
|
+
path = rewrite_path(options)
|
173
|
+
rewritten_url << ActionController::Base.relative_url_root.to_s unless options[:skip_relative_url_root]
|
174
|
+
rewritten_url << (options[:trailing_slash] ? path.sub(/\?|\z/) { "/" + $& } : path)
|
175
|
+
rewritten_url << "##{CGI.escape(options[:anchor].to_param.to_s)}" if options[:anchor]
|
176
|
+
|
177
|
+
rewritten_url
|
178
|
+
end
|
179
|
+
|
180
|
+
# Given a Hash of options, generates a route
|
181
|
+
def rewrite_path(options)
|
182
|
+
options = options.symbolize_keys
|
183
|
+
options.update(options[:params].symbolize_keys) if options[:params]
|
184
|
+
|
185
|
+
if (overwrite = options.delete(:overwrite_params))
|
186
|
+
options.update(@parameters.symbolize_keys)
|
187
|
+
options.update(overwrite.symbolize_keys)
|
188
|
+
end
|
189
|
+
|
190
|
+
RESERVED_OPTIONS.each { |k| options.delete(k) }
|
191
|
+
|
192
|
+
# Generates the query string, too
|
193
|
+
Routing::Routes.generate(options, @request.symbolized_path_parameters)
|
194
|
+
end
|
195
|
+
|
196
|
+
def rewrite_authentication(options)
|
197
|
+
if options[:user] && options[:password]
|
198
|
+
"#{CGI.escape(options.delete(:user))}:#{CGI.escape(options.delete(:password))}@"
|
199
|
+
else
|
200
|
+
""
|
201
|
+
end
|
202
|
+
end
|
203
|
+
end
|
204
|
+
end
|
@@ -0,0 +1,16 @@
|
|
1
|
+
$LOAD_PATH << "#{File.dirname(__FILE__)}/html-scanner"
|
2
|
+
|
3
|
+
module HTML
|
4
|
+
autoload :CDATA, 'html/node'
|
5
|
+
autoload :Document, 'html/document'
|
6
|
+
autoload :FullSanitizer, 'html/sanitizer'
|
7
|
+
autoload :LinkSanitizer, 'html/sanitizer'
|
8
|
+
autoload :Node, 'html/node'
|
9
|
+
autoload :Sanitizer, 'html/sanitizer'
|
10
|
+
autoload :Selector, 'html/selector'
|
11
|
+
autoload :Tag, 'html/node'
|
12
|
+
autoload :Text, 'html/node'
|
13
|
+
autoload :Tokenizer, 'html/tokenizer'
|
14
|
+
autoload :Version, 'html/version'
|
15
|
+
autoload :WhiteListSanitizer, 'html/sanitizer'
|
16
|
+
end
|
@@ -0,0 +1,68 @@
|
|
1
|
+
require 'html/tokenizer'
|
2
|
+
require 'html/node'
|
3
|
+
require 'html/selector'
|
4
|
+
require 'html/sanitizer'
|
5
|
+
|
6
|
+
module HTML #:nodoc:
|
7
|
+
# A top-level HTMl document. You give it a body of text, and it will parse that
|
8
|
+
# text into a tree of nodes.
|
9
|
+
class Document #:nodoc:
|
10
|
+
|
11
|
+
# The root of the parsed document.
|
12
|
+
attr_reader :root
|
13
|
+
|
14
|
+
# Create a new Document from the given text.
|
15
|
+
def initialize(text, strict=false, xml=false)
|
16
|
+
tokenizer = Tokenizer.new(text)
|
17
|
+
@root = Node.new(nil)
|
18
|
+
node_stack = [ @root ]
|
19
|
+
while token = tokenizer.next
|
20
|
+
node = Node.parse(node_stack.last, tokenizer.line, tokenizer.position, token, strict)
|
21
|
+
|
22
|
+
node_stack.last.children << node unless node.tag? && node.closing == :close
|
23
|
+
if node.tag?
|
24
|
+
if node_stack.length > 1 && node.closing == :close
|
25
|
+
if node_stack.last.name == node.name
|
26
|
+
if node_stack.last.children.empty?
|
27
|
+
node_stack.last.children << Text.new(node_stack.last, node.line, node.position, "")
|
28
|
+
end
|
29
|
+
node_stack.pop
|
30
|
+
else
|
31
|
+
open_start = node_stack.last.position - 20
|
32
|
+
open_start = 0 if open_start < 0
|
33
|
+
close_start = node.position - 20
|
34
|
+
close_start = 0 if close_start < 0
|
35
|
+
msg = <<EOF.strip
|
36
|
+
ignoring attempt to close #{node_stack.last.name} with #{node.name}
|
37
|
+
opened at byte #{node_stack.last.position}, line #{node_stack.last.line}
|
38
|
+
closed at byte #{node.position}, line #{node.line}
|
39
|
+
attributes at open: #{node_stack.last.attributes.inspect}
|
40
|
+
text around open: #{text[open_start,40].inspect}
|
41
|
+
text around close: #{text[close_start,40].inspect}
|
42
|
+
EOF
|
43
|
+
strict ? raise(msg) : warn(msg)
|
44
|
+
end
|
45
|
+
elsif !node.childless?(xml) && node.closing != :close
|
46
|
+
node_stack.push node
|
47
|
+
end
|
48
|
+
end
|
49
|
+
end
|
50
|
+
end
|
51
|
+
|
52
|
+
# Search the tree for (and return) the first node that matches the given
|
53
|
+
# conditions. The conditions are interpreted differently for different node
|
54
|
+
# types, see HTML::Text#find and HTML::Tag#find.
|
55
|
+
def find(conditions)
|
56
|
+
@root.find(conditions)
|
57
|
+
end
|
58
|
+
|
59
|
+
# Search the tree for (and return) all nodes that match the given
|
60
|
+
# conditions. The conditions are interpreted differently for different node
|
61
|
+
# types, see HTML::Text#find and HTML::Tag#find.
|
62
|
+
def find_all(conditions)
|
63
|
+
@root.find_all(conditions)
|
64
|
+
end
|
65
|
+
|
66
|
+
end
|
67
|
+
|
68
|
+
end
|
@@ -0,0 +1,537 @@
|
|
1
|
+
require 'strscan'
|
2
|
+
|
3
|
+
module HTML #:nodoc:
|
4
|
+
|
5
|
+
class Conditions < Hash #:nodoc:
|
6
|
+
def initialize(hash)
|
7
|
+
super()
|
8
|
+
hash = { :content => hash } unless Hash === hash
|
9
|
+
hash = keys_to_symbols(hash)
|
10
|
+
hash.each do |k,v|
|
11
|
+
case k
|
12
|
+
when :tag, :content then
|
13
|
+
# keys are valid, and require no further processing
|
14
|
+
when :attributes then
|
15
|
+
hash[k] = keys_to_strings(v)
|
16
|
+
when :parent, :child, :ancestor, :descendant, :sibling, :before,
|
17
|
+
:after
|
18
|
+
hash[k] = Conditions.new(v)
|
19
|
+
when :children
|
20
|
+
hash[k] = v = keys_to_symbols(v)
|
21
|
+
v.each do |k,v2|
|
22
|
+
case k
|
23
|
+
when :count, :greater_than, :less_than
|
24
|
+
# keys are valid, and require no further processing
|
25
|
+
when :only
|
26
|
+
v[k] = Conditions.new(v2)
|
27
|
+
else
|
28
|
+
raise "illegal key #{k.inspect} => #{v2.inspect}"
|
29
|
+
end
|
30
|
+
end
|
31
|
+
else
|
32
|
+
raise "illegal key #{k.inspect} => #{v.inspect}"
|
33
|
+
end
|
34
|
+
end
|
35
|
+
update hash
|
36
|
+
end
|
37
|
+
|
38
|
+
private
|
39
|
+
|
40
|
+
def keys_to_strings(hash)
|
41
|
+
hash.keys.inject({}) do |h,k|
|
42
|
+
h[k.to_s] = hash[k]
|
43
|
+
h
|
44
|
+
end
|
45
|
+
end
|
46
|
+
|
47
|
+
def keys_to_symbols(hash)
|
48
|
+
hash.keys.inject({}) do |h,k|
|
49
|
+
raise "illegal key #{k.inspect}" unless k.respond_to?(:to_sym)
|
50
|
+
h[k.to_sym] = hash[k]
|
51
|
+
h
|
52
|
+
end
|
53
|
+
end
|
54
|
+
end
|
55
|
+
|
56
|
+
# The base class of all nodes, textual and otherwise, in an HTML document.
|
57
|
+
class Node #:nodoc:
|
58
|
+
# The array of children of this node. Not all nodes have children.
|
59
|
+
attr_reader :children
|
60
|
+
|
61
|
+
# The parent node of this node. All nodes have a parent, except for the
|
62
|
+
# root node.
|
63
|
+
attr_reader :parent
|
64
|
+
|
65
|
+
# The line number of the input where this node was begun
|
66
|
+
attr_reader :line
|
67
|
+
|
68
|
+
# The byte position in the input where this node was begun
|
69
|
+
attr_reader :position
|
70
|
+
|
71
|
+
# Create a new node as a child of the given parent.
|
72
|
+
def initialize(parent, line=0, pos=0)
|
73
|
+
@parent = parent
|
74
|
+
@children = []
|
75
|
+
@line, @position = line, pos
|
76
|
+
end
|
77
|
+
|
78
|
+
# Return a textual representation of the node.
|
79
|
+
def to_s
|
80
|
+
s = ""
|
81
|
+
@children.each { |child| s << child.to_s }
|
82
|
+
s
|
83
|
+
end
|
84
|
+
|
85
|
+
# Return false (subclasses must override this to provide specific matching
|
86
|
+
# behavior.) +conditions+ may be of any type.
|
87
|
+
def match(conditions)
|
88
|
+
false
|
89
|
+
end
|
90
|
+
|
91
|
+
# Search the children of this node for the first node for which #find
|
92
|
+
# returns non +nil+. Returns the result of the #find call that succeeded.
|
93
|
+
def find(conditions)
|
94
|
+
conditions = validate_conditions(conditions)
|
95
|
+
@children.each do |child|
|
96
|
+
node = child.find(conditions)
|
97
|
+
return node if node
|
98
|
+
end
|
99
|
+
nil
|
100
|
+
end
|
101
|
+
|
102
|
+
# Search for all nodes that match the given conditions, and return them
|
103
|
+
# as an array.
|
104
|
+
def find_all(conditions)
|
105
|
+
conditions = validate_conditions(conditions)
|
106
|
+
|
107
|
+
matches = []
|
108
|
+
matches << self if match(conditions)
|
109
|
+
@children.each do |child|
|
110
|
+
matches.concat child.find_all(conditions)
|
111
|
+
end
|
112
|
+
matches
|
113
|
+
end
|
114
|
+
|
115
|
+
# Returns +false+. Subclasses may override this if they define a kind of
|
116
|
+
# tag.
|
117
|
+
def tag?
|
118
|
+
false
|
119
|
+
end
|
120
|
+
|
121
|
+
def validate_conditions(conditions)
|
122
|
+
Conditions === conditions ? conditions : Conditions.new(conditions)
|
123
|
+
end
|
124
|
+
|
125
|
+
def ==(node)
|
126
|
+
return false unless self.class == node.class && children.size == node.children.size
|
127
|
+
|
128
|
+
equivalent = true
|
129
|
+
|
130
|
+
children.size.times do |i|
|
131
|
+
equivalent &&= children[i] == node.children[i]
|
132
|
+
end
|
133
|
+
|
134
|
+
equivalent
|
135
|
+
end
|
136
|
+
|
137
|
+
class <<self
|
138
|
+
def parse(parent, line, pos, content, strict=true)
|
139
|
+
if content !~ /^<\S/
|
140
|
+
Text.new(parent, line, pos, content)
|
141
|
+
else
|
142
|
+
scanner = StringScanner.new(content)
|
143
|
+
|
144
|
+
unless scanner.skip(/</)
|
145
|
+
if strict
|
146
|
+
raise "expected <"
|
147
|
+
else
|
148
|
+
return Text.new(parent, line, pos, content)
|
149
|
+
end
|
150
|
+
end
|
151
|
+
|
152
|
+
if scanner.skip(/!\[CDATA\[/)
|
153
|
+
unless scanner.skip_until(/\]\]>/)
|
154
|
+
if strict
|
155
|
+
raise "expected ]]> (got #{scanner.rest.inspect} for #{content})"
|
156
|
+
else
|
157
|
+
scanner.skip_until(/\Z/)
|
158
|
+
end
|
159
|
+
end
|
160
|
+
|
161
|
+
return CDATA.new(parent, line, pos, scanner.pre_match.gsub(/<!\[CDATA\[/, ''))
|
162
|
+
end
|
163
|
+
|
164
|
+
closing = ( scanner.scan(/\//) ? :close : nil )
|
165
|
+
return Text.new(parent, line, pos, content) unless name = scanner.scan(/[\w:-]+/)
|
166
|
+
name.downcase!
|
167
|
+
|
168
|
+
unless closing
|
169
|
+
scanner.skip(/\s*/)
|
170
|
+
attributes = {}
|
171
|
+
while attr = scanner.scan(/[-\w:]+/)
|
172
|
+
value = true
|
173
|
+
if scanner.scan(/\s*=\s*/)
|
174
|
+
if delim = scanner.scan(/['"]/)
|
175
|
+
value = ""
|
176
|
+
while text = scanner.scan(/[^#{delim}\\]+|./)
|
177
|
+
case text
|
178
|
+
when "\\" then
|
179
|
+
value << text
|
180
|
+
value << scanner.getch
|
181
|
+
when delim
|
182
|
+
break
|
183
|
+
else value << text
|
184
|
+
end
|
185
|
+
end
|
186
|
+
else
|
187
|
+
value = scanner.scan(/[^\s>\/]+/)
|
188
|
+
end
|
189
|
+
end
|
190
|
+
attributes[attr.downcase] = value
|
191
|
+
scanner.skip(/\s*/)
|
192
|
+
end
|
193
|
+
|
194
|
+
closing = ( scanner.scan(/\//) ? :self : nil )
|
195
|
+
end
|
196
|
+
|
197
|
+
unless scanner.scan(/\s*>/)
|
198
|
+
if strict
|
199
|
+
raise "expected > (got #{scanner.rest.inspect} for #{content}, #{attributes.inspect})"
|
200
|
+
else
|
201
|
+
# throw away all text until we find what we're looking for
|
202
|
+
scanner.skip_until(/>/) or scanner.terminate
|
203
|
+
end
|
204
|
+
end
|
205
|
+
|
206
|
+
Tag.new(parent, line, pos, name, attributes, closing)
|
207
|
+
end
|
208
|
+
end
|
209
|
+
end
|
210
|
+
end
|
211
|
+
|
212
|
+
# A node that represents text, rather than markup.
|
213
|
+
class Text < Node #:nodoc:
|
214
|
+
|
215
|
+
attr_reader :content
|
216
|
+
|
217
|
+
# Creates a new text node as a child of the given parent, with the given
|
218
|
+
# content.
|
219
|
+
def initialize(parent, line, pos, content)
|
220
|
+
super(parent, line, pos)
|
221
|
+
@content = content
|
222
|
+
end
|
223
|
+
|
224
|
+
# Returns the content of this node.
|
225
|
+
def to_s
|
226
|
+
@content
|
227
|
+
end
|
228
|
+
|
229
|
+
# Returns +self+ if this node meets the given conditions. Text nodes support
|
230
|
+
# conditions of the following kinds:
|
231
|
+
#
|
232
|
+
# * if +conditions+ is a string, it must be a substring of the node's
|
233
|
+
# content
|
234
|
+
# * if +conditions+ is a regular expression, it must match the node's
|
235
|
+
# content
|
236
|
+
# * if +conditions+ is a hash, it must contain a <tt>:content</tt> key that
|
237
|
+
# is either a string or a regexp, and which is interpreted as described
|
238
|
+
# above.
|
239
|
+
def find(conditions)
|
240
|
+
match(conditions) && self
|
241
|
+
end
|
242
|
+
|
243
|
+
# Returns non-+nil+ if this node meets the given conditions, or +nil+
|
244
|
+
# otherwise. See the discussion of #find for the valid conditions.
|
245
|
+
def match(conditions)
|
246
|
+
case conditions
|
247
|
+
when String
|
248
|
+
@content == conditions
|
249
|
+
when Regexp
|
250
|
+
@content =~ conditions
|
251
|
+
when Hash
|
252
|
+
conditions = validate_conditions(conditions)
|
253
|
+
|
254
|
+
# Text nodes only have :content, :parent, :ancestor
|
255
|
+
unless (conditions.keys - [:content, :parent, :ancestor]).empty?
|
256
|
+
return false
|
257
|
+
end
|
258
|
+
|
259
|
+
match(conditions[:content])
|
260
|
+
else
|
261
|
+
nil
|
262
|
+
end
|
263
|
+
end
|
264
|
+
|
265
|
+
def ==(node)
|
266
|
+
return false unless super
|
267
|
+
content == node.content
|
268
|
+
end
|
269
|
+
end
|
270
|
+
|
271
|
+
# A CDATA node is simply a text node with a specialized way of displaying
|
272
|
+
# itself.
|
273
|
+
class CDATA < Text #:nodoc:
|
274
|
+
def to_s
|
275
|
+
"<![CDATA[#{super}]]>"
|
276
|
+
end
|
277
|
+
end
|
278
|
+
|
279
|
+
# A Tag is any node that represents markup. It may be an opening tag, a
|
280
|
+
# closing tag, or a self-closing tag. It has a name, and may have a hash of
|
281
|
+
# attributes.
|
282
|
+
class Tag < Node #:nodoc:
|
283
|
+
|
284
|
+
# Either +nil+, <tt>:close</tt>, or <tt>:self</tt>
|
285
|
+
attr_reader :closing
|
286
|
+
|
287
|
+
# Either +nil+, or a hash of attributes for this node.
|
288
|
+
attr_reader :attributes
|
289
|
+
|
290
|
+
# The name of this tag.
|
291
|
+
attr_reader :name
|
292
|
+
|
293
|
+
# Create a new node as a child of the given parent, using the given content
|
294
|
+
# to describe the node. It will be parsed and the node name, attributes and
|
295
|
+
# closing status extracted.
|
296
|
+
def initialize(parent, line, pos, name, attributes, closing)
|
297
|
+
super(parent, line, pos)
|
298
|
+
@name = name
|
299
|
+
@attributes = attributes
|
300
|
+
@closing = closing
|
301
|
+
end
|
302
|
+
|
303
|
+
# A convenience for obtaining an attribute of the node. Returns +nil+ if
|
304
|
+
# the node has no attributes.
|
305
|
+
def [](attr)
|
306
|
+
@attributes ? @attributes[attr] : nil
|
307
|
+
end
|
308
|
+
|
309
|
+
# Returns non-+nil+ if this tag can contain child nodes.
|
310
|
+
def childless?(xml = false)
|
311
|
+
return false if xml && @closing.nil?
|
312
|
+
!@closing.nil? ||
|
313
|
+
@name =~ /^(img|br|hr|link|meta|area|base|basefont|
|
314
|
+
col|frame|input|isindex|param)$/ox
|
315
|
+
end
|
316
|
+
|
317
|
+
# Returns a textual representation of the node
|
318
|
+
def to_s
|
319
|
+
if @closing == :close
|
320
|
+
"</#{@name}>"
|
321
|
+
else
|
322
|
+
s = "<#{@name}"
|
323
|
+
@attributes.each do |k,v|
|
324
|
+
s << " #{k}"
|
325
|
+
s << "=\"#{v}\"" if String === v
|
326
|
+
end
|
327
|
+
s << " /" if @closing == :self
|
328
|
+
s << ">"
|
329
|
+
@children.each { |child| s << child.to_s }
|
330
|
+
s << "</#{@name}>" if @closing != :self && !@children.empty?
|
331
|
+
s
|
332
|
+
end
|
333
|
+
end
|
334
|
+
|
335
|
+
# If either the node or any of its children meet the given conditions, the
|
336
|
+
# matching node is returned. Otherwise, +nil+ is returned. (See the
|
337
|
+
# description of the valid conditions in the +match+ method.)
|
338
|
+
def find(conditions)
|
339
|
+
match(conditions) && self || super
|
340
|
+
end
|
341
|
+
|
342
|
+
# Returns +true+, indicating that this node represents an HTML tag.
|
343
|
+
def tag?
|
344
|
+
true
|
345
|
+
end
|
346
|
+
|
347
|
+
# Returns +true+ if the node meets any of the given conditions. The
|
348
|
+
# +conditions+ parameter must be a hash of any of the following keys
|
349
|
+
# (all are optional):
|
350
|
+
#
|
351
|
+
# * <tt>:tag</tt>: the node name must match the corresponding value
|
352
|
+
# * <tt>:attributes</tt>: a hash. The node's values must match the
|
353
|
+
# corresponding values in the hash.
|
354
|
+
# * <tt>:parent</tt>: a hash. The node's parent must match the
|
355
|
+
# corresponding hash.
|
356
|
+
# * <tt>:child</tt>: a hash. At least one of the node's immediate children
|
357
|
+
# must meet the criteria described by the hash.
|
358
|
+
# * <tt>:ancestor</tt>: a hash. At least one of the node's ancestors must
|
359
|
+
# meet the criteria described by the hash.
|
360
|
+
# * <tt>:descendant</tt>: a hash. At least one of the node's descendants
|
361
|
+
# must meet the criteria described by the hash.
|
362
|
+
# * <tt>:sibling</tt>: a hash. At least one of the node's siblings must
|
363
|
+
# meet the criteria described by the hash.
|
364
|
+
# * <tt>:after</tt>: a hash. The node must be after any sibling meeting
|
365
|
+
# the criteria described by the hash, and at least one sibling must match.
|
366
|
+
# * <tt>:before</tt>: a hash. The node must be before any sibling meeting
|
367
|
+
# the criteria described by the hash, and at least one sibling must match.
|
368
|
+
# * <tt>:children</tt>: a hash, for counting children of a node. Accepts the
|
369
|
+
# keys:
|
370
|
+
# ** <tt>:count</tt>: either a number or a range which must equal (or
|
371
|
+
# include) the number of children that match.
|
372
|
+
# ** <tt>:less_than</tt>: the number of matching children must be less than
|
373
|
+
# this number.
|
374
|
+
# ** <tt>:greater_than</tt>: the number of matching children must be
|
375
|
+
# greater than this number.
|
376
|
+
# ** <tt>:only</tt>: another hash consisting of the keys to use
|
377
|
+
# to match on the children, and only matching children will be
|
378
|
+
# counted.
|
379
|
+
#
|
380
|
+
# Conditions are matched using the following algorithm:
|
381
|
+
#
|
382
|
+
# * if the condition is a string, it must be a substring of the value.
|
383
|
+
# * if the condition is a regexp, it must match the value.
|
384
|
+
# * if the condition is a number, the value must match number.to_s.
|
385
|
+
# * if the condition is +true+, the value must not be +nil+.
|
386
|
+
# * if the condition is +false+ or +nil+, the value must be +nil+.
|
387
|
+
#
|
388
|
+
# Usage:
|
389
|
+
#
|
390
|
+
# # test if the node is a "span" tag
|
391
|
+
# node.match :tag => "span"
|
392
|
+
#
|
393
|
+
# # test if the node's parent is a "div"
|
394
|
+
# node.match :parent => { :tag => "div" }
|
395
|
+
#
|
396
|
+
# # test if any of the node's ancestors are "table" tags
|
397
|
+
# node.match :ancestor => { :tag => "table" }
|
398
|
+
#
|
399
|
+
# # test if any of the node's immediate children are "em" tags
|
400
|
+
# node.match :child => { :tag => "em" }
|
401
|
+
#
|
402
|
+
# # test if any of the node's descendants are "strong" tags
|
403
|
+
# node.match :descendant => { :tag => "strong" }
|
404
|
+
#
|
405
|
+
# # test if the node has between 2 and 4 span tags as immediate children
|
406
|
+
# node.match :children => { :count => 2..4, :only => { :tag => "span" } }
|
407
|
+
#
|
408
|
+
# # get funky: test to see if the node is a "div", has a "ul" ancestor
|
409
|
+
# # and an "li" parent (with "class" = "enum"), and whether or not it has
|
410
|
+
# # a "span" descendant that contains # text matching /hello world/:
|
411
|
+
# node.match :tag => "div",
|
412
|
+
# :ancestor => { :tag => "ul" },
|
413
|
+
# :parent => { :tag => "li",
|
414
|
+
# :attributes => { :class => "enum" } },
|
415
|
+
# :descendant => { :tag => "span",
|
416
|
+
# :child => /hello world/ }
|
417
|
+
def match(conditions)
|
418
|
+
conditions = validate_conditions(conditions)
|
419
|
+
# check content of child nodes
|
420
|
+
if conditions[:content]
|
421
|
+
if children.empty?
|
422
|
+
return false unless match_condition("", conditions[:content])
|
423
|
+
else
|
424
|
+
return false unless children.find { |child| child.match(conditions[:content]) }
|
425
|
+
end
|
426
|
+
end
|
427
|
+
|
428
|
+
# test the name
|
429
|
+
return false unless match_condition(@name, conditions[:tag]) if conditions[:tag]
|
430
|
+
|
431
|
+
# test attributes
|
432
|
+
(conditions[:attributes] || {}).each do |key, value|
|
433
|
+
return false unless match_condition(self[key], value)
|
434
|
+
end
|
435
|
+
|
436
|
+
# test parent
|
437
|
+
return false unless parent.match(conditions[:parent]) if conditions[:parent]
|
438
|
+
|
439
|
+
# test children
|
440
|
+
return false unless children.find { |child| child.match(conditions[:child]) } if conditions[:child]
|
441
|
+
|
442
|
+
# test ancestors
|
443
|
+
if conditions[:ancestor]
|
444
|
+
return false unless catch :found do
|
445
|
+
p = self
|
446
|
+
throw :found, true if p.match(conditions[:ancestor]) while p = p.parent
|
447
|
+
end
|
448
|
+
end
|
449
|
+
|
450
|
+
# test descendants
|
451
|
+
if conditions[:descendant]
|
452
|
+
return false unless children.find do |child|
|
453
|
+
# test the child
|
454
|
+
child.match(conditions[:descendant]) ||
|
455
|
+
# test the child's descendants
|
456
|
+
child.match(:descendant => conditions[:descendant])
|
457
|
+
end
|
458
|
+
end
|
459
|
+
|
460
|
+
# count children
|
461
|
+
if opts = conditions[:children]
|
462
|
+
matches = children.select do |c|
|
463
|
+
(c.kind_of?(HTML::Tag) and (c.closing == :self or ! c.childless?))
|
464
|
+
end
|
465
|
+
|
466
|
+
matches = matches.select { |c| c.match(opts[:only]) } if opts[:only]
|
467
|
+
opts.each do |key, value|
|
468
|
+
next if key == :only
|
469
|
+
case key
|
470
|
+
when :count
|
471
|
+
if Integer === value
|
472
|
+
return false if matches.length != value
|
473
|
+
else
|
474
|
+
return false unless value.include?(matches.length)
|
475
|
+
end
|
476
|
+
when :less_than
|
477
|
+
return false unless matches.length < value
|
478
|
+
when :greater_than
|
479
|
+
return false unless matches.length > value
|
480
|
+
else raise "unknown count condition #{key}"
|
481
|
+
end
|
482
|
+
end
|
483
|
+
end
|
484
|
+
|
485
|
+
# test siblings
|
486
|
+
if conditions[:sibling] || conditions[:before] || conditions[:after]
|
487
|
+
siblings = parent ? parent.children : []
|
488
|
+
self_index = siblings.index(self)
|
489
|
+
|
490
|
+
if conditions[:sibling]
|
491
|
+
return false unless siblings.detect do |s|
|
492
|
+
s != self && s.match(conditions[:sibling])
|
493
|
+
end
|
494
|
+
end
|
495
|
+
|
496
|
+
if conditions[:before]
|
497
|
+
return false unless siblings[self_index+1..-1].detect do |s|
|
498
|
+
s != self && s.match(conditions[:before])
|
499
|
+
end
|
500
|
+
end
|
501
|
+
|
502
|
+
if conditions[:after]
|
503
|
+
return false unless siblings[0,self_index].detect do |s|
|
504
|
+
s != self && s.match(conditions[:after])
|
505
|
+
end
|
506
|
+
end
|
507
|
+
end
|
508
|
+
|
509
|
+
true
|
510
|
+
end
|
511
|
+
|
512
|
+
def ==(node)
|
513
|
+
return false unless super
|
514
|
+
return false unless closing == node.closing && self.name == node.name
|
515
|
+
attributes == node.attributes
|
516
|
+
end
|
517
|
+
|
518
|
+
private
|
519
|
+
# Match the given value to the given condition.
|
520
|
+
def match_condition(value, condition)
|
521
|
+
case condition
|
522
|
+
when String
|
523
|
+
value && value == condition
|
524
|
+
when Regexp
|
525
|
+
value && value.match(condition)
|
526
|
+
when Numeric
|
527
|
+
value == condition.to_s
|
528
|
+
when true
|
529
|
+
!value.nil?
|
530
|
+
when false, nil
|
531
|
+
value.nil?
|
532
|
+
else
|
533
|
+
false
|
534
|
+
end
|
535
|
+
end
|
536
|
+
end
|
537
|
+
end
|