text_extractor 0.2.0 → 0.3.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 78291099c84221f93ff6068099d736bc6703579b
-  data.tar.gz: 8a65b9164e395200fac46207b6b313dfa8084a2b
+  metadata.gz: c42725b840531e241a7353991f7fec182561a89c
+  data.tar.gz: 07b7639b33d4d7b9380e9674c4a3f6531c3b03ff
 SHA512:
-  metadata.gz: 7b18d39bde364c3417ccd18ff4ce8f072568e3e63b838b1bdce46b25cffd6b7356dbf2f4e9b1f6fd816368ce0aa194a1e6cc9f4ccd584f579a85eb795b264ddd
-  data.tar.gz: a99721d0d2a48b5364dd301415334fdd85563664144d3d4a216c70d2c39ecd7654b64b9e49c78f582bb762c4dae8d33abc809b45807328f35b010fc3aff31482
+  metadata.gz: 9cadfc1dee9915d1b0b259de9b006154486aaba50808246bff28af16630ad6f481e8fba20289d1f60b315f19d98df44320df2af5e33b58096faaa6596163fa54
+  data.tar.gz: 9c3ee7b8a460612908a24bc64cc765aea243da2d2e9462b16630db1402fd6b7f75e2877be55341b968ac708d1b9b06c04b6424f50ecc5b5bafce373c7f5a049d

data/lib/text_extractor.rb

@@ -2,6 +2,7 @@ require_relative 'text_extractor/extraction'
 require_relative 'text_extractor/filldown'
 require_relative 'text_extractor/record'
 require_relative 'text_extractor/value'
+require_relative 'text_extractor/inline_value'
 
 # represents an extractor definition
 class TextExtractor
@@ -41,6 +42,10 @@ class TextExtractor
     end
   end
 
+  def inline(id, &block)
+    @values[id] = InlineValue.new(id, &block)
+  end
+
   def boolean(id, re = Patterns::BOOLEAN)
     value(id, re) { |val| !val.match(Patterns::FALSE) }
   end
@@ -67,6 +72,7 @@ class TextExtractor
 
   def record(klass = Record, **kwargs, &block)
     raise "#{self.class}.record requires a block" unless block
+    kwargs[:extractor_values] = values
     kwargs[:values] = @current_record_values = []
     @records << klass.new(instance_exec(&block), **kwargs)
   end

data/lib/text_extractor/directives.rb

@@ -25,6 +25,8 @@ class TextExtractor
     def initialize(original)
       @source = original.source
       @options = original.options
+      @output = nil
+      @directives = []
     end
 
     def expand
@@ -36,12 +38,17 @@ class TextExtractor
       @output = Regexp.new(@state.target.join(''), @options)
     end
 
+    def values
+      @directives.flat_map(&:values)
+    end
+
     private
 
     DIRECTIVE_MAP = {
       ' '      => { class: Comment },
       'any'    => { class: Any },
       'begin'  => { class: Begin, arguments: :parsed },
+      'capture' => { class: Capture, arguments: :parsed },
       'end'    => { class: End },
       'maybe'  => { class: Maybe },
       'repeat' => { class: Repeat, arguments: :parse },
@@ -92,6 +99,7 @@ class TextExtractor
       return [Comment.new(@state)] if full_source.start_with?(' ')
       split_directives(full_source)
         .map { |source| parse_one_directive(source) }
+        .each { |directive| @directives << directive }
     end
 
     def parse_one_directive(source)

data/lib/text_extractor/directives/classes.rb

@@ -1,3 +1,5 @@
+require 'text_extractor/inline_value'
+
 class TextExtractor
   class Directives
     # base class for line directives
@@ -9,6 +11,10 @@ class TextExtractor
         @argument = argument
         init if respond_to?(:init)
       end
+
+      def values
+        []
+      end
     end
 
     # open a line group
@@ -42,6 +48,17 @@ class TextExtractor
       end
     end
 
+    # capture group that creates a value
+    class Capture < Begin
+      def group(name, *args)
+        CaptureGroup.new(name, *args)
+      end
+
+      def values
+        [InlineValue.new(@argument.to_sym)]
+      end
+    end
+
     # text that will be omitted from the regexp
     class Comment < Directive
       def call

data/lib/text_extractor/directives/group.rb

@@ -42,5 +42,17 @@ class TextExtractor
         ['(?:', *@lines.flat_map { |e| [e, '|'] }[0..-2], ')']
       end
     end
+
+    # a line group that will be captured to a value
+    class CaptureGroup < Group
+      def initialize(name, *args)
+        @name = name
+        @lines = args
+      end
+
+      def join
+        ["(?<#{@name}>", *@lines, ')']
+      end
+    end
   end
 end

data/lib/text_extractor/inline_value.rb

@@ -0,0 +1,13 @@
+require 'text_extractor/value'
+
+class TextExtractor
+  # represents a value given by a .capture directive
+  class InlineValue < Value
+    def initialize(id, &block)
+      @id = id
+      @block = block
+    end
+
+    alias re id
+  end
+end

data/lib/text_extractor/record.rb

@@ -5,12 +5,14 @@ class TextExtractor
     attr_reader :regexp, :factory, :values
 
     def initialize(regexp, factory: nil, values: [], fill: [], directives: true,
-                   strip: nil)
-      @regexp = build_regexp(regexp, directives, strip)
+                   inline: [], extractor_values: {}, strip: nil)
       @factory = factory
       @constructor = FactoryAnalyzer.new(factory).to_proc
+      @extractor_values = extractor_values
       @values = values.map { |val| [val.id, val] }.to_h
+      initialize_inline_values(inline)
       @default_values = values.map { |val| [val.id, nil] }.to_h
+      @regexp = build_regexp(regexp, directives, strip)
       @fill = Array(fill)
     end
 
@@ -55,7 +57,12 @@ class TextExtractor
 
     def expand_regexp(regexp, directives)
       if directives
-        TextExtractor.expand_directives(regexp)
+        expander = Directives.new(regexp)
+        expanded = expander.expand
+        expander.values.each { |value|
+          values[value.id] = @extractor_values.fetch(value.id, value)
+        }
+        expanded
       else
         regexp
       end
@@ -96,9 +103,18 @@ class TextExtractor
       values.keys.map { |id| [id, values[id].convert(match[id])] }.to_h
     end
 
+    def initialize_inline_values(inline_values)
+      inline_values.each do |value|
+        @values[value] = @extractor_values
+                         .fetch(value) { InlineValue.new(value) }
+      end
+    end
+
     # converts the value of the factory option to a constructor proc
     class FactoryAnalyzer
       def initialize(factory)
+        @params = nil
+
         case factory
         when Hash
           @klass, @params = factory.first

data/lib/text_extractor/value.rb

@@ -5,7 +5,7 @@ class TextExtractor
     def initialize(id, re, &block)
       @id = id
       @re = re
-      @block = block if block_given?
+      @block = block
     end
 
     def convert(value)

data/lib/text_extractor/version.rb

@@ -1,5 +1,5 @@
 class TextExtractor
   def self.version
-    '0.2.0'
+    '0.3.0'
   end
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: text_extractor
 version: !ruby/object:Gem::Version
-  version: 0.2.0
+  version: 0.3.0
 platform: ruby
 authors:
 - Ben Miller
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2016-07-13 00:00:00.000000000 Z
+date: 2016-08-23 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: bundler
@@ -64,6 +64,7 @@ files:
 - lib/text_extractor/directives/group.rb
 - lib/text_extractor/extraction.rb
 - lib/text_extractor/filldown.rb
+- lib/text_extractor/inline_value.rb
 - lib/text_extractor/record.rb
 - lib/text_extractor/value.rb
 - lib/text_extractor/version.rb
@@ -92,4 +93,3 @@ signing_key:
 specification_version: 4
 summary: Easily extract data from text
 test_files: []
-has_rdoc: