text_extractor 0.4.0 → 0.5.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
-SHA1:
-  metadata.gz: 5412586591653945efffad2ce8783c9269e58582
-  data.tar.gz: dc9fdb2f1eaad7bfafab31ad13e3e5eff966ea22
+SHA256:
+  metadata.gz: 6d814b19dedf7312cee41b86de5ac98115240908b9a5ef17d343eb5450d2d608
+  data.tar.gz: d365e26b0ba0a97d5ec25854767248ceff60f91c0808a24b06cf2fb425b87864
 SHA512:
-  metadata.gz: f8c4a71b402c49c136700eab64daeba10a48938285d1d06e1522bb8bbd47fe1cf5f6962f0d2dcc555fa413164185e50eed069a52ac6bc4b253b1dd973529d09b
-  data.tar.gz: 73117018ffc3542a71aa201ac84ddc5d038881605e3a3fdccabce1d0d65a77137f2b731cac6a4463c8e3902c431fa418e166bcefe0cd6feedb899616a75a9e29
+  metadata.gz: e39cfa57ff12e5df3011e729627c37948b658c8c82447398c1547b94486b0ef46cd0b4f6491e598375010c3882ca23a2fa5288d407cddaebc88d74996712f9e7
+  data.tar.gz: 1a680465ce5f430100b01ec9b2fdc68f51813b280b03d886454f8c0c61d7cafee72a7097e53c2cedcf09d2cb399ff56931719978207e648cf6ef9d2401844022

data/lib/text_extractor.rb

@@ -1,6 +1,8 @@
 require_relative 'text_extractor/extraction'
 require_relative 'text_extractor/filldown'
+require_relative 'text_extractor/guard'
 require_relative 'text_extractor/record'
+require_relative 'text_extractor/skip'
 require_relative 'text_extractor/value'
 require_relative 'text_extractor/inline_value'
 
@@ -8,6 +10,7 @@ require_relative 'text_extractor/inline_value'
 class TextExtractor
   attr_reader :records, :values
 
+  # rubocop: disable Metrics/MethodLength
   def initialize(&block)
     raise "#{self.class}.new requires a block" unless block
     @values = {}
@@ -18,8 +21,11 @@ class TextExtractor
     @current_record_values = []
     @section_delimiter = nil
     @section_terminator = nil
+    @append_guards = []
     instance_exec(&block)
+    @append_guards.each { |g| guard(**g, &g[:block]) }
   end
+  # rubocop: enable Metrics/MethodLength
 
   module Patterns
     INTEGER = /\d+/
@@ -28,8 +34,8 @@ class TextExtractor
     IPV4 = /[0-9.]{7,15}/
     IPV6 = /[:a-fA-F0-9\.]{2,45}/
     IPADDR = Regexp.union(IPV4, IPV6)
-    IPV4_NET = /#{IPV4}\/\d{1,2}/
-    IPV6_NET = /#{IPV6}\/\d{1,3}/
+    IPV4_NET = %r{#{IPV4}/\d{1,2}}
+    IPV6_NET = %r{#{IPV6}\/\d{1,3}}
     IPNETADDR = Regexp.union(IPV4_NET, IPV6_NET)
     TRUE = /y|yes|t|true|on/i
     FALSE = /n|no|f|false|off/i
@@ -75,6 +81,7 @@ class TextExtractor
   def record(klass = Record, **kwargs, &block)
     raise "#{self.class}.record requires a block" unless block
     kwargs[:extractor_values] = values
+    kwargs[:factory] ||= @factory if @factory
     kwargs[:values] = @current_record_values = []
     @records << klass.new(instance_exec(&block), **kwargs)
   end
@@ -84,6 +91,14 @@ class TextExtractor
     @section_terminator = terminator
   end
 
+  def factory(object = nil)
+    if object
+      @factory = object
+    else
+      @factory
+    end
+  end
+
   def filldown(**kwargs, &block)
     raise "#{self.class}.filldown requires a block" unless block
     record(Filldown, **kwargs, &block)
@@ -93,6 +108,16 @@ class TextExtractor
     records[records.length.times.find_index { |i| match["__#{i}"] }]
   end
 
+  def guard(**kwargs, &block)
+    raise "#{self.class}.guard requires a block" unless block
+    record(Guard, **kwargs, &block)
+  end
+
+  def guards(*guard_args)
+    guard_args = Guards::DEFAULT if guard_args.empty?
+    @append_guards = guard_args
+  end
+
   def scan(input)
     prefill = {}
     sections(input).flat_map { |section|
@@ -109,6 +134,11 @@ class TextExtractor
     texts.map { |section| section + @section_terminator }
   end
 
+  def skip(**kwargs, &block)
+    raise "#{self.class}.skip requires a block" unless block
+    record(Skip, **kwargs, &block)
+  end
+
   def regexps
     @records.map.with_index do |record, i|
       Regexp.new("(?<__#{i}>#{record.source})", record.options)

data/lib/text_extractor/directives/classes.rb

@@ -61,8 +61,7 @@ class TextExtractor
 
     # text that will be omitted from the regexp
     class Comment < Directive
-      def call
-      end
+      def call; end
     end
 
     # close a line group

data/lib/text_extractor/guard.rb

@@ -0,0 +1,41 @@
+require_relative 'record'
+
+class TextExtractor
+  class Guard < Record
+    def initialize(_regexp, description:, **kwargs)
+      super
+      @description = description
+      @factory ||= :itself.to_proc
+    end
+
+    def extraction(match, _fill)
+      text = @factory.call(match[0])
+      raise GuardError, "#{@description} near #{text.inspect}"
+    end
+  end
+
+  INDENTED = {
+    description: 'indented line',
+    block: proc {
+      /
+      ^[^\n\S]+[^\n]*$
+      /
+    }
+  }.freeze
+
+  UNINDENTED = {
+    description: 'unindented line',
+    block: proc {
+      /
+      ^\S+[^\n]*$
+      /
+    }
+  }.freeze
+
+  DEFAULT = [
+    INDENTED,
+    UNINDENTED
+  ].freeze
+
+  class GuardError < StandardError; end
+end # class TextExtractor

data/lib/text_extractor/record.rb

@@ -4,8 +4,18 @@ class TextExtractor
   class Record
     attr_reader :regexp, :factory, :values
 
-    def initialize(regexp, factory: nil, values: [], fill: [], directives: true,
-                   inline: [], extractor_values: {}, strip: nil)
+    # rubocop: disable Metrics/ParameterLists
+    def initialize(
+          regexp,
+          factory: nil,
+          values: [],
+          fill: [],
+          directives: true,
+          inline: [],
+          extractor_values: {},
+          strip: nil,
+          **_kwargs
+    )
       @factory = factory
       @constructor = FactoryAnalyzer.new(factory).to_proc
       @extractor_values = extractor_values
@@ -15,12 +25,14 @@ class TextExtractor
       @regexp = build_regexp(regexp, directives, strip)
       @fill = Array(fill)
     end
+    # rubocop: enable Metrics/ParameterLists
 
+    # @return Array
     def extraction(match, fill)
       extracted = {}.merge!(@default_values)
-                    .merge!(extract_fills fill)
-                    .merge!(extract_values match)
-      build_extraction(extracted)
+                    .merge!(extract_fills(fill))
+                    .merge!(extract_values(match))
+      [build_extraction(extracted)]
     end
 
     def build_extraction(extracted)
@@ -59,9 +71,9 @@ class TextExtractor
       if directives
         expander = Directives.new(regexp)
         expanded = expander.expand
-        expander.values.each { |value|
+        expander.values.each do |value|
           values[value.id] = @extractor_values.fetch(value.id, value)
-        }
+        end
         expanded
       else
         regexp
@@ -126,7 +138,7 @@ class TextExtractor
       def to_proc
         if @params
           explicit
-        elsif @klass.is_a?(Proc)
+        elsif @klass.respond_to?(:call)
           @klass
         elsif @klass
           implicit

data/lib/text_extractor/skip.rb

@@ -0,0 +1,9 @@
+require_relative 'record'
+
+class TextExtractor
+  class Skip < Record
+    def extraction(*)
+      []
+    end
+  end # class Skip < Record
+end # class TextExtractor

data/lib/text_extractor/value.rb

@@ -10,9 +10,9 @@ class TextExtractor
 
     def convert(value)
       @block ? @block.call(value) : value
-    rescue => e
+    rescue StandardError => e
       raise e.class,
-            "in custom conversion of "\
+            'in custom conversion of '\
             "value(#{id.inspect}, #{re.inspect}): #{e.message}"
     end
   end

data/lib/text_extractor/version.rb

@@ -1,5 +1,5 @@
 class TextExtractor
   def self.version
-    '0.4.0'
+    '0.5.0'
   end
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: text_extractor
 version: !ruby/object:Gem::Version
-  version: 0.4.0
+  version: 0.5.0
 platform: ruby
 authors:
 - Ben Miller
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2016-11-28 00:00:00.000000000 Z
+date: 2018-08-15 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: bundler
@@ -24,6 +24,20 @@ dependencies:
     - - "~>"
       - !ruby/object:Gem::Version
         version: '1.0'
+- !ruby/object:Gem::Dependency
+  name: minitest
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '5.0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '5.0'
 - !ruby/object:Gem::Dependency
   name: rake
   requirement: !ruby/object:Gem::Requirement
@@ -39,19 +53,19 @@ dependencies:
       - !ruby/object:Gem::Version
         version: '10.0'
 - !ruby/object:Gem::Dependency
-  name: minitest
+  name: rubocop
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '5.0'
+        version: '0.54'
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '5.0'
+        version: '0.54'
 description: 
 email: bjmllr@gmail.com
 executables: []
@@ -64,8 +78,10 @@ files:
 - lib/text_extractor/directives/group.rb
 - lib/text_extractor/extraction.rb
 - lib/text_extractor/filldown.rb
+- lib/text_extractor/guard.rb
 - lib/text_extractor/inline_value.rb
 - lib/text_extractor/record.rb
+- lib/text_extractor/skip.rb
 - lib/text_extractor/value.rb
 - lib/text_extractor/version.rb
 homepage: https://github.com/bjmllr/text_extractor
@@ -88,9 +104,8 @@ required_rubygems_version: !ruby/object:Gem::Requirement
       version: '0'
 requirements: []
 rubyforge_project: 
-rubygems_version: 2.5.2
+rubygems_version: 2.7.3
 signing_key: 
 specification_version: 4
 summary: Easily extract data from text
 test_files: []
-has_rdoc: