saper 0.5.0

Sign up to get free protection for your applications and to get access to all the features.
Files changed (111) hide show
  1. checksums.yaml +7 -0
  2. data/LICENSE +21 -0
  3. data/README.md +126 -0
  4. data/Rakefile +17 -0
  5. data/bin/saper +60 -0
  6. data/lib/lib/json_search.rb +54 -0
  7. data/lib/lib/mechanize.rb +26 -0
  8. data/lib/lib/nokogiri.rb +12 -0
  9. data/lib/saper.rb +37 -0
  10. data/lib/saper/actions/append_with.rb +14 -0
  11. data/lib/saper/actions/convert_to_html.rb +14 -0
  12. data/lib/saper/actions/convert_to_json.rb +14 -0
  13. data/lib/saper/actions/convert_to_markdown.rb +13 -0
  14. data/lib/saper/actions/convert_to_time.rb +15 -0
  15. data/lib/saper/actions/convert_to_xml.rb +14 -0
  16. data/lib/saper/actions/create_atom.rb +18 -0
  17. data/lib/saper/actions/fetch.rb +17 -0
  18. data/lib/saper/actions/find.rb +18 -0
  19. data/lib/saper/actions/find_first.rb +16 -0
  20. data/lib/saper/actions/get_attribute.rb +15 -0
  21. data/lib/saper/actions/get_contents.rb +14 -0
  22. data/lib/saper/actions/get_text.rb +14 -0
  23. data/lib/saper/actions/prepend_with.rb +14 -0
  24. data/lib/saper/actions/remove_after.rb +14 -0
  25. data/lib/saper/actions/remove_before.rb +14 -0
  26. data/lib/saper/actions/remove_matching.rb +14 -0
  27. data/lib/saper/actions/remove_tags.rb +15 -0
  28. data/lib/saper/actions/replace.rb +15 -0
  29. data/lib/saper/actions/run_recipe.rb +24 -0
  30. data/lib/saper/actions/run_recipe_and_save.rb +22 -0
  31. data/lib/saper/actions/save.rb +14 -0
  32. data/lib/saper/actions/select_matching.rb +14 -0
  33. data/lib/saper/actions/set_input.rb +19 -0
  34. data/lib/saper/actions/skip_tags.rb +15 -0
  35. data/lib/saper/actions/split.rb +24 -0
  36. data/lib/saper/arguments/attribute.rb +11 -0
  37. data/lib/saper/arguments/recipe.rb +42 -0
  38. data/lib/saper/arguments/text.rb +11 -0
  39. data/lib/saper/arguments/timezone.rb +11 -0
  40. data/lib/saper/arguments/variable.rb +11 -0
  41. data/lib/saper/arguments/xpath.rb +11 -0
  42. data/lib/saper/core/action.rb +209 -0
  43. data/lib/saper/core/argument.rb +106 -0
  44. data/lib/saper/core/browser.rb +87 -0
  45. data/lib/saper/core/dsl.rb +68 -0
  46. data/lib/saper/core/error.rb +47 -0
  47. data/lib/saper/core/item.rb +70 -0
  48. data/lib/saper/core/keychain.rb +18 -0
  49. data/lib/saper/core/logger.rb +74 -0
  50. data/lib/saper/core/namespace.rb +139 -0
  51. data/lib/saper/core/recipe.rb +134 -0
  52. data/lib/saper/core/runtime.rb +237 -0
  53. data/lib/saper/core/type.rb +45 -0
  54. data/lib/saper/items/atom.rb +64 -0
  55. data/lib/saper/items/document.rb +66 -0
  56. data/lib/saper/items/html.rb +85 -0
  57. data/lib/saper/items/json.rb +67 -0
  58. data/lib/saper/items/markdown.rb +36 -0
  59. data/lib/saper/items/nothing.rb +15 -0
  60. data/lib/saper/items/text.rb +54 -0
  61. data/lib/saper/items/time.rb +42 -0
  62. data/lib/saper/items/url.rb +34 -0
  63. data/lib/saper/items/xml.rb +79 -0
  64. data/lib/saper/version.rb +3 -0
  65. data/spec/actions/append_with_spec.rb +30 -0
  66. data/spec/actions/convert_to_html_spec.rb +24 -0
  67. data/spec/actions/convert_to_json_spec.rb +24 -0
  68. data/spec/actions/convert_to_markdown_spec.rb +24 -0
  69. data/spec/actions/convert_to_time_spec.rb +37 -0
  70. data/spec/actions/convert_to_xml_spec.rb +24 -0
  71. data/spec/actions/create_atom_spec.rb +31 -0
  72. data/spec/actions/fetch_spec.rb +7 -0
  73. data/spec/actions/find_first_spec.rb +7 -0
  74. data/spec/actions/find_spec.rb +7 -0
  75. data/spec/actions/get_attribute_spec.rb +7 -0
  76. data/spec/actions/get_contents.rb +7 -0
  77. data/spec/actions/get_text.rb +7 -0
  78. data/spec/actions/prepend_with_spec.rb +30 -0
  79. data/spec/actions/remove_after.rb +7 -0
  80. data/spec/actions/remove_before.rb +7 -0
  81. data/spec/actions/replace_spec.rb +7 -0
  82. data/spec/actions/run_recipe_and_save_spec.tmp.rb +52 -0
  83. data/spec/actions/run_recipe_spec.tmp.rb +53 -0
  84. data/spec/actions/save_spec.rb +7 -0
  85. data/spec/actions/select_matching_spec.rb +7 -0
  86. data/spec/actions/set_input_spec.rb +7 -0
  87. data/spec/actions/skip_tags_spec.rb +7 -0
  88. data/spec/actions/split_spec.rb +7 -0
  89. data/spec/core/action_spec.rb +151 -0
  90. data/spec/core/argument_spec.rb +79 -0
  91. data/spec/core/browser_spec.rb +7 -0
  92. data/spec/core/dsl_spec.rb +7 -0
  93. data/spec/core/item_spec.rb +7 -0
  94. data/spec/core/keychain_spec.rb +7 -0
  95. data/spec/core/logger_spec.rb +7 -0
  96. data/spec/core/namespace_spec.rb +18 -0
  97. data/spec/core/recipe_spec.rb +81 -0
  98. data/spec/core/runtime_spec.rb +165 -0
  99. data/spec/core/type_spec.rb +7 -0
  100. data/spec/items/atom_spec.rb +7 -0
  101. data/spec/items/document_spec.rb +7 -0
  102. data/spec/items/html_spec.rb +7 -0
  103. data/spec/items/json_spec.rb +7 -0
  104. data/spec/items/markdown_spec.rb +7 -0
  105. data/spec/items/nothing_spec.rb +7 -0
  106. data/spec/items/text_spec.rb +17 -0
  107. data/spec/items/time_spec.rb +7 -0
  108. data/spec/items/url_spec.rb +7 -0
  109. data/spec/items/xml_spec.rb +17 -0
  110. data/spec/spec_helper.rb +22 -0
  111. metadata +355 -0
@@ -0,0 +1,237 @@
1
+ module Saper
2
+ class Runtime
3
+
4
+ # Returns action input.
5
+ attr_reader :input
6
+
7
+ # Returns action output.
8
+ attr_reader :output
9
+
10
+ # Returns error instance (if any)
11
+ attr_reader :error
12
+
13
+ # Returns action instance.
14
+ attr_reader :action
15
+
16
+ # Returns embedded recipes
17
+ attr_reader :subrecipes
18
+
19
+ # Returns subsequent runtime instances.
20
+ attr_reader :children
21
+
22
+ # Returns the size of action chain.
23
+ attr_reader :depth
24
+
25
+ # Returns a new Saper::Runtime instance.
26
+ # @param stack [Array<Saper::Action>] chain of actions
27
+ # @param input [Object, nil] action input
28
+ # @param options [Hash]
29
+ # @return [Saper::Runtime]
30
+ def initialize(stack = [], input = nil, options = {})
31
+ if stack.is_a?(Recipe)
32
+ stack = stack.actions
33
+ end
34
+ @input = input
35
+ @output = nil
36
+ @error = nil
37
+ @action = nil
38
+ @children = []
39
+ @subrecipes = []
40
+ @options = options
41
+ @depth = stack.size
42
+ @options[:keychain] ||= Keychain.new
43
+ @options[:logger] ||= Logger.new(@options[:log])
44
+ @options[:browser] ||= Browser.new(:logger => logger)
45
+ @options[:variables] ||= {}
46
+ if block_given?
47
+ yield self
48
+ end
49
+ execute(stack.dup)
50
+ end
51
+
52
+ # Returns volume of incoming traffic (in bytes)
53
+ # @return [Integer]
54
+ def bytes_received
55
+ browser.received
56
+ end
57
+
58
+ # Returns volume of outgoing traffic (in bytes)
59
+ # @return [Integer]
60
+ def bytes_sent
61
+ browser.sent
62
+ end
63
+
64
+ # Returns number of HTTP requests
65
+ # @return [Integer]
66
+ def http_requests
67
+ browser.requests
68
+ end
69
+
70
+ # Get variable value
71
+ # @param name [Symbol]
72
+ # @return [Object]
73
+ def [](name)
74
+ @options[:variables][name]
75
+ end
76
+
77
+ # Set variable value
78
+ # @param name [Symbol]
79
+ # @param value [Object]
80
+ # @return [Object]
81
+ def []=(name, value)
82
+ @options[:variables][name] = value
83
+ end
84
+
85
+ # Return a hash with all variables
86
+ # @return [Hash]
87
+ def variables
88
+ @options[:variables].dup
89
+ end
90
+
91
+ # Returns descendant runtime instances at a given depth level.
92
+ # @param level [Integer]
93
+ # @return [Array<Saper::Runtime>]
94
+ def descendants(level = 0)
95
+ level < 1 ? [self] : children.map { |i| i.descendants(level - 1) }.flatten
96
+ end
97
+
98
+ # Returns runtime results.
99
+ # @return [Array<Object>, Object]
100
+ def results
101
+ native_results
102
+ end
103
+
104
+ # Returns an array of results.
105
+ # @return [Array]
106
+ def result_array
107
+ native_result_array
108
+ end
109
+
110
+ # Returns `true` if this or any of the subsequent actions produces multiple results.
111
+ # @return [Boolean]
112
+ def multiple?
113
+ (action.nil? ? false : action.multiple?) || children.any?(&:multiple?)
114
+ end
115
+
116
+ # Returns Saper::Browser instance used by runtime.
117
+ # @return [Saper::Browser]
118
+ def browser
119
+ @options[:browser]
120
+ end
121
+
122
+ # Returns Saper::Keychain instance used by runtime.
123
+ # @return [Saper::Keychain]
124
+ def keychain
125
+ @options[:keychain]
126
+ end
127
+
128
+ # Returns Saper::Logger.
129
+ # @return [Saper::Logger]
130
+ def logger
131
+ @options[:logger]
132
+ end
133
+
134
+ # Writes full runtime log to logger instance.
135
+ # @return [void]
136
+ def backtrace
137
+ logger.runtime(self)
138
+ end
139
+
140
+ # Returns access credentials for specified service
141
+ # @param service [Symbol]
142
+ # @return [Object, nil]
143
+ def credentials(service)
144
+ keychain[service]
145
+ end
146
+
147
+ # Runs an arbitrary recipe, specified by ID, block or as instance.
148
+ # @param recipe [Saper::Recipe]
149
+ # @param input [Object, nil]
150
+ # @return [Saper::Runtime]
151
+ def recipe(recipe, input = nil, &block)
152
+ unless recipe.is_a?(Recipe)
153
+ raise RecipeNotFound, recipe
154
+ end
155
+ runtime = Runtime.new(recipe, input, @options.merge(:variables => {}))
156
+ if runtime.error?
157
+ @error = runtime.error
158
+ end
159
+ subrecipes << runtime
160
+ runtime.non_native_results
161
+ end
162
+
163
+ # Returns `true` if action raised no errors.
164
+ # @return [Boolean]
165
+ def success?
166
+ error.nil?
167
+ end
168
+
169
+ # Returns `true` if action raised at least one error.
170
+ # @return [Boolean]
171
+ def error?
172
+ !success?
173
+ end
174
+
175
+ # Returns runtime results as JSON.
176
+ # @return [Array]
177
+ def to_json(*args)
178
+ JSON.generate(non_native_results)
179
+ end
180
+
181
+ # Returns runtime results as Saper::Item instances.
182
+ # @return [Saper::Item, Array<Saper::Item>]
183
+ def non_native_results
184
+ multiple? ? non_native_result_array : non_native_result_array.first
185
+ end
186
+
187
+ # Returns runtime results as native Ruby objects.
188
+ # @return [Object, Array<Object>]
189
+ def native_results
190
+ multiple? ? native_result_array : native_result_array.first
191
+ end
192
+
193
+ private
194
+
195
+ # Returns runtime results as an array of Saper::Item instances.
196
+ # @return [Array<Saper::Item>]
197
+ def non_native_result_array
198
+ descendants(depth - 1).map(&:output).flatten.compact
199
+ end
200
+
201
+ # Returns runtime results as an array of native Ruby objects.
202
+ # @return [Array<Object>]
203
+ def native_result_array
204
+ non_native_result_array.map { |result| result.is_a?(Item) ? result.to_native : result }
205
+ end
206
+
207
+ # Executes recipes.
208
+ # @return [self]
209
+ def execute(stack)
210
+ @output = input
211
+ @action = stack.shift
212
+ if action.nil?
213
+ return self
214
+ end
215
+ unless action.is_a?(Saper::Action)
216
+ raise ActionExpected, action
217
+ end
218
+ begin
219
+ @output = action.run(input, self)
220
+ rescue Saper::Error => e
221
+ @output = nil
222
+ @error = e
223
+ end
224
+ unless @output.is_a?(Array)
225
+ @output = [@output]
226
+ end
227
+ if stack.empty?
228
+ return self
229
+ end
230
+ @children = @output.map do |item|
231
+ Runtime.new(stack, item, @options.dup)
232
+ end
233
+ self
234
+ end
235
+
236
+ end
237
+ end
@@ -0,0 +1,45 @@
1
+ module Saper
2
+ class Type
3
+
4
+ # Returns a new Type instance of a given type.
5
+ # @param type [Symbol]
6
+ # @return [Saper::Type]
7
+ def self.[](type)
8
+ case type
9
+ when Type then type
10
+ when :attribute then AttributeType.new
11
+ when :document then DocumentType.new
12
+ when :html then HTMLType.new
13
+ when :json then JSONType.new
14
+ when :options then OptionsType.new
15
+ when :regex then RegexType.new
16
+ when :recipe then RecipeType.new
17
+ when :tag then TagType.new
18
+ when :text then TextType.new
19
+ when :url then URLType.new
20
+ when :variable then VariableType.new
21
+ when :xml then XMLType.new
22
+ when :xpath then XPathType.new
23
+ else raise(InvalidType, "Invalid action argument: %s" % type)
24
+ end
25
+ end
26
+
27
+ # Returns normalize value
28
+ def normalize(value)
29
+ value # Note: subclass may override this method.
30
+ end
31
+
32
+ # Returns `true` if specified value matches type.
33
+ # @return [Boolean]
34
+ def valid?(value)
35
+ true # Note: subclass must override this method.
36
+ end
37
+
38
+ # Returns `true` if specified value does not match type.
39
+ # @return [Boolean]
40
+ def invalid?(value)
41
+ not valid?(value)
42
+ end
43
+
44
+ end
45
+ end
@@ -0,0 +1,64 @@
1
+ module Saper
2
+ module Items
3
+ class Atom < Item
4
+
5
+ def self.new(item)
6
+ super case item
7
+ when Hash
8
+ item
9
+ else
10
+ raise(InvalidItem, item)
11
+ end
12
+ end
13
+
14
+ def initialize(hash)
15
+ @atts = hash
16
+ end
17
+
18
+ def serialize
19
+ @atts.dup
20
+ end
21
+
22
+ def to_hash
23
+ @atts.dup
24
+ end
25
+
26
+ def delete(name)
27
+ @atts.delete(name)
28
+ end
29
+
30
+ def [](name)
31
+ @atts[name]
32
+ end
33
+
34
+ def to_yaml(*args)
35
+ @atts.to_yaml(*args)
36
+ end
37
+
38
+ def to_native(object = nil)
39
+ if object.nil?
40
+ return to_native(to_hash)
41
+ end
42
+ if object.is_a?(Hash)
43
+ return Hash[object.map { |key, value| [key, to_native(value)] }]
44
+ end
45
+ if object.is_a?(Array)
46
+ return object.map { |key, value| to_native(value) }
47
+ end
48
+ if object.is_a?(Item)
49
+ return object.to_native
50
+ end
51
+ object
52
+ end
53
+
54
+ def to_json(*args)
55
+ to_hash.to_json(*args)
56
+ end
57
+
58
+ def to_s
59
+ "{ %s }" % @atts.map { |key, value| "%s = %s" % [key, value] }.join(", ")
60
+ end
61
+
62
+ end
63
+ end
64
+ end
@@ -0,0 +1,66 @@
1
+ module Saper
2
+ module Items
3
+ class Document < Item
4
+
5
+ def self.new(item)
6
+ super case item
7
+ when Mechanize::File
8
+ item
9
+ else
10
+ raise(InvalidItem, item)
11
+ end
12
+ end
13
+
14
+ def initialize(mechanize)
15
+ @mech = mechanize
16
+ end
17
+
18
+ def uri
19
+ @mech.uri.to_s
20
+ end
21
+
22
+ def body
23
+ @mech.body
24
+ end
25
+
26
+ def size
27
+ body.size
28
+ end
29
+
30
+ def mime
31
+ content_type.split(";").first
32
+ end
33
+
34
+ def charset
35
+ content_type.include?("charset=") ? content_type.split("charset=").last : nil
36
+ end
37
+
38
+ def to_text
39
+ body
40
+ end
41
+
42
+ def to_html
43
+ HTML.new(body)
44
+ end
45
+
46
+ def to_xml
47
+ XML.new(body)
48
+ end
49
+
50
+ def to_json
51
+ JSON.new(body)
52
+ end
53
+
54
+ def to_native
55
+ @body
56
+ end
57
+
58
+ private
59
+
60
+ def content_type
61
+ @mech['content-type'] || ""
62
+ end
63
+
64
+ end
65
+ end
66
+ end
@@ -0,0 +1,85 @@
1
+ module Saper
2
+ module Items
3
+ class HTML < Item
4
+
5
+ def self.new(item)
6
+ super case item
7
+ when Nokogiri::XML::Element
8
+ item
9
+ when Nokogiri::HTML
10
+ item
11
+ when Text
12
+ parse(item.to_s)
13
+ when String
14
+ parse(item)
15
+ else
16
+ raise(InvalidItem, item)
17
+ end
18
+ end
19
+
20
+ def self.parse(string, uri = nil, charset = nil)
21
+ begin
22
+ Nokogiri::HTML.parse(string, uri, charset)
23
+ rescue
24
+ raise(InvalidItem, string)
25
+ end
26
+ end
27
+
28
+ def initialize(noko)
29
+ @noko = noko
30
+ # Force UTF-8 encoding
31
+ # https://github.com/sparklemotion/nokogiri/issues/117
32
+ @noko.document.encoding = 'UTF-8'
33
+ end
34
+
35
+ def name
36
+ @noko.name
37
+ end
38
+
39
+ def [](name)
40
+ @noko[name]
41
+ end
42
+
43
+ def find(xpath)
44
+ find_all(xpath).first
45
+ end
46
+
47
+ def find_all(xpath)
48
+ @noko.search(xpath).map { |element| HTML.new(element) }
49
+ end
50
+
51
+ def remove_children_with_content(xpath)
52
+ @noko.search(xpath).each { |item| item.remove }; self
53
+ end
54
+
55
+ def remove_children_preserving_content(xpath)
56
+ @noko.search(xpath).each { |item| item.replace(item.children) }; self
57
+ end
58
+
59
+ def remove(tag)
60
+ remove_children_preserving_content(tag)
61
+ end
62
+
63
+ def inner_html
64
+ @noko.inner_html
65
+ end
66
+
67
+ def inner_text
68
+ @noko.inner_text
69
+ end
70
+
71
+ def to_markdown
72
+ Markdown.new self
73
+ end
74
+
75
+ def to_native
76
+ inner_html
77
+ end
78
+
79
+ def to_s
80
+ inner_html
81
+ end
82
+
83
+ end
84
+ end
85
+ end