text_extractor 0.5.2 → 0.6.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 536459e92aed84134a79cc83b43582806dc241b7c6e1f634da83f33cbc204fb9
-  data.tar.gz: 7840132fc524f8c6a5ec564e5e99a53adb58854e18fc292265f12a149dfd0c44
+  metadata.gz: bc66aa843889a7f5396d26c41d7756fb56b2157563d7aa8640732867d32750c4
+  data.tar.gz: d491b948b0baece51042436d5d9d934d6800e26255bbf4a73f8f815b1aedda44
 SHA512:
-  metadata.gz: 9ba4320ef35cef8e1a313c37cb800c9ea2dd716564f0105f94839f48d03ca17e02a53a96cadc40aa9475113cb48e87f866f9f56c7a75e7bed84b94db15e9c741
-  data.tar.gz: acebe63b3cedf8c1c1e4acca41030ffb86d1782fc71612e6f4200a18d6e953b3e3d7f41f28da269a1fb579e9e93e11b406b32e51a9d211d057156d2b2ecd5884
+  metadata.gz: 4111f9a6090fb6314fea8e164b9bd6fedb669bdfd8abe8031cbfbedc3c0e52df83f7ff2c0377bf00aa53340ee8423c7ab7d203d770114d1a756d09b4d0869b29
+  data.tar.gz: 48fa9d25532211f7473cd9535ad3740fe34cc79fc0f0628df35399c7711a303d16f5cc0182367fdfb4968bd1e47e6a608fa5e36d239ae9738d92afc8a232d221

data/lib/text_extractor.rb

@@ -8,37 +8,53 @@ require_relative 'text_extractor/inline_value'
 
 # represents an extractor definition
 class TextExtractor
+  @append_newline = false
+
+  singleton_class.instance_eval do
+    attr_accessor :append_newline
+  end
+
   attr_reader :records, :values
 
-  # rubocop: disable Metrics/MethodLength
   def initialize(&block)
     raise "#{self.class}.new requires a block" unless block
+
+    initialize_options
+    initialize_collections
+    instance_exec(&block)
+    @append_guards.each { |g| guard(**g, &g[:block]) }
+  end
+
+  def initialize_options
+    @factory = nil
+    @section_delimiter = nil
+    @section_terminator = nil
+    @strip = nil
+    @append_newline = nil
+  end
+
+  def initialize_collections
     @values = {}
     @fill = {}
     @values = {}
     @records = []
     @filldowns = []
     @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+/
-    FLOAT = /\d+\.?|\d*\.\d+/
-    RATIONAL = %r{\d+/\d+}
-    IPV4 = /[0-9.]{7,15}/
-    IPV6 = /[:a-fA-F0-9\.]{2,45}/
+    INTEGER = /\d+/.freeze
+    FLOAT = /\d+\.?|\d*\.\d+/.freeze
+    RATIONAL = %r{\d+/\d+}.freeze
+    IPV4 = /[0-9.]{7,15}/.freeze
+    IPV6 = /[:a-fA-F0-9\.]{2,45}/.freeze
     IPADDR = Regexp.union(IPV4, IPV6)
-    IPV4_NET = %r{#{IPV4}/\d{1,2}}
-    IPV6_NET = %r{#{IPV6}\/\d{1,3}}
+    IPV4_NET = %r{#{IPV4}/\d{1,2}}.freeze
+    IPV6_NET = %r{#{IPV6}\/\d{1,3}}.freeze
     IPNETADDR = Regexp.union(IPV4_NET, IPV6_NET)
-    TRUE = /y|yes|t|true|on/i
-    FALSE = /n|no|f|false|off/i
+    TRUE = /y|yes|t|true|on/i.freeze
+    FALSE = /n|no|f|false|off/i.freeze
     BOOLEAN = Regexp.union(TRUE, FALSE)
   end
 
@@ -78,8 +94,16 @@ class TextExtractor
     value(id, re) { |val| IPAddr.new(val) }
   end
 
+  def append_newline(activate = nil)
+    return TextExtractor.append_newline if activate.nil? && @append_newline.nil?
+    return @append_newline if activate.nil?
+
+    @append_newline = activate
+  end
+
   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 = []
@@ -91,6 +115,17 @@ class TextExtractor
     @section_terminator = terminator
   end
 
+  STRIP_PROCS = {
+    left: ->(s) { s.split("\n").map(&:lstrip).join("\n") + "\n" },
+    right: ->(s) { s.split("\n").map(&:rstrip).join("\n") + "\n" },
+    both: ->(s) { s.split("\n").map(&:strip).join("\n") + "\n" }
+  }.freeze
+
+  def strip(side = nil)
+    @strip = STRIP_PROCS[side] ||
+             (raise ArgumentError, 'Unknown strip option')
+  end
+
   def factory(object = nil)
     if object
       @factory = object
@@ -101,6 +136,7 @@ class TextExtractor
 
   def filldown(**kwargs, &block)
     raise "#{self.class}.filldown requires a block" unless block
+
     record(Filldown, **kwargs, &block)
   end
 
@@ -110,6 +146,7 @@ class TextExtractor
 
   def guard(**kwargs, &block)
     raise "#{self.class}.guard requires a block" unless block
+
     record(Guard, **kwargs, &block)
   end
 
@@ -119,6 +156,8 @@ class TextExtractor
   end
 
   def scan(input)
+    input = @strip.call(input) if @strip
+    input += "\n" if append_newline && !input.end_with?("\n")
     prefill = {}
     sections(input).flat_map { |section|
       Extraction.new(section, self, prefill).scan.extraction_matches
@@ -136,6 +175,7 @@ class TextExtractor
 
   def skip(**kwargs, &block)
     raise "#{self.class}.skip requires a block" unless block
+
     record(Skip, **kwargs, &block)
   end
 

data/lib/text_extractor/directives.rb

@@ -31,10 +31,12 @@ class TextExtractor
 
     def expand
       return @output if @output
+
       @state = State.new
       scanner = StringScanner.new(@source)
       read_line(scanner) until scanner.eos?
       raise 'Unterminated line group' unless @state.groups.empty?
+
       @output = Regexp.new(@state.target.join(''), @options)
     end
 
@@ -45,14 +47,14 @@ class TextExtractor
     private
 
     DIRECTIVE_MAP = {
-      ' '      => { class: Comment },
-      'any'    => { class: Any },
-      'begin'  => { class: Begin, arguments: :parsed },
+      ' ' => { class: Comment },
+      'any' => { class: Any },
+      'begin' => { class: Begin, arguments: :parsed },
       'capture' => { class: Capture, arguments: :parsed },
-      'end'    => { class: End },
-      'maybe'  => { class: Maybe },
+      'end' => { class: End },
+      'maybe' => { class: Maybe },
       'repeat' => { class: Repeat, arguments: :parse },
-      'rest'   => { class: Rest }
+      'rest' => { class: Rest }
     }.freeze
     private_constant :DIRECTIVE_MAP
 
@@ -97,6 +99,7 @@ class TextExtractor
 
     def parse_directives(full_source)
       return [Comment.new(@state)] if full_source.start_with?(' ')
+
       split_directives(full_source)
         .map { |source| parse_one_directive(source) }
         .each { |directive| @directives << directive }
@@ -105,6 +108,7 @@ class TextExtractor
     def parse_one_directive(source)
       md = source.match(/^[a-z_]+/) || source.match(/^ /)
       raise "Unknown directive(s) in #{@state.current_line}" unless md
+
       word = md[0]
       map = DIRECTIVE_MAP.fetch(word) { raise "Unknown directive #{word}" }
       args = parse_arguments(map[:arguments], md.post_match)
@@ -118,6 +122,7 @@ class TextExtractor
     def parse_arguments(rule, source)
       return [] unless rule
       return rule.call(source) if rule.is_a?(Proc)
+
       source.match(/\(([^)]*)\)/) { |md| md[1] }
     end
   end # class Expander

data/lib/text_extractor/directives/group.rb

@@ -17,6 +17,7 @@ class TextExtractor
 
       def chomp(newline)
         return if @lines.empty? || newline
+
         tail = @lines[-1]
         if tail.is_a?(Array)
           tail = tail[-1] while tail[-1].is_a?(Array)

data/lib/text_extractor/extraction.rb

@@ -27,6 +27,7 @@ class TextExtractor
       loop do
         match = input.match(re, pos)
         break unless match
+
         @pos = match.end(0)
         @matches << match
       end

data/lib/text_extractor/record.rb

@@ -4,17 +4,15 @@ class TextExtractor
   class Record
     attr_reader :regexp, :factory, :values
 
-    # rubocop: disable Metrics/ParameterLists
     def initialize(
-          regexp,
-          factory: nil,
-          values: [],
-          fill: [],
-          directives: true,
-          inline: [],
-          extractor_values: {},
-          strip: nil,
-          **_kwargs
+      regexp,
+      factory: nil,
+      values: [],
+      fill: [],
+      directives: true,
+      inline: [],
+      extractor_values: {},
+      **_kwargs
     )
       @factory = factory
       @constructor = FactoryAnalyzer.new(factory).to_proc
@@ -22,10 +20,9 @@ class TextExtractor
       @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)
+      @regexp = build_regexp(regexp, directives)
       @fill = Array(fill)
     end
-    # rubocop: enable Metrics/ParameterLists
 
     # @return Array
     def extraction(match, fill)
@@ -37,36 +34,29 @@ class TextExtractor
 
     def build_extraction(extracted)
       return extracted unless @constructor
+
       @constructor.call(extracted)
     end
 
-    def build_regexp(regexp, directives, strip)
-      stripped = strip_regexp(regexp, strip)
-      expanded = expand_regexp(stripped, directives)
-      ignore_regexp(expanded, strip)
+    def build_regexp(regexp, directives)
+      stripped = strip_regexp(regexp)
+      final = expand_regexp(stripped, directives)
+
+      raise EmptyRecordError, 'Empty record detected' if final =~ ''
+
+      final
     end
 
-    def strip_regexp(regexp, strip)
+    def strip_regexp(regexp)
       lines = regexp.source.split("\n")
       prefix = lines.last
       if lines.first =~ /\A\s*\z/ && prefix =~ /\A\s*\z/
         lines.shift
         lines = lines.map { |s| s.gsub(prefix, '') }
-        lines = lines.map(&regexp_line_stripper(strip))
       end
       Regexp.new(lines.join("\n"), regexp.options)
     end
 
-    def regexp_line_stripper(strip)
-      case strip
-      when :left  then ->(s) { s.lstrip }
-      when :right then ->(s) { s.rstrip }
-      when :both  then ->(s) { s.strip }
-      when nil, false then ->(s) { s }
-      else raise "Unknown strip option: #{strip}"
-      end
-    end
-
     def expand_regexp(regexp, directives)
       if directives
         expander = Directives.new(regexp)
@@ -80,21 +70,6 @@ class TextExtractor
       end
     end
 
-    def ignore_regexp(regexp, strip)
-      return regexp unless strip
-      lines = regexp.source.split("\n").map(&regexp_line_ignorer(strip))
-      Regexp.new(lines.join("\n"), regexp.options)
-    end
-
-    def regexp_line_ignorer(strip)
-      case strip
-      when :left  then ->(s) { "\[ \\t\\r\\f]*#{s}" }
-      when :right then ->(s) { "#{s}\[ \\t\\r\\f]*" }
-      when :both  then ->(s) { "\[ \\t\\r\\f]*#{s}\[ \\t\\r\\f]*" }
-      else raise "Unknown ignore whitespace option: #{strip}"
-      end
-    end
-
     def match(string, pos = 0)
       @regexp.match(string, pos)
     end
@@ -178,4 +153,6 @@ class TextExtractor
       end
     end # class FactoryAnalyzer
   end # class Record
+
+  class EmptyRecordError < StandardError; end
 end # class TextExtractor

data/lib/text_extractor/version.rb

@@ -1,5 +1,5 @@
 class TextExtractor
   def self.version
-    '0.5.2'
+    '0.6.0'
   end
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: text_extractor
 version: !ruby/object:Gem::Version
-  version: 0.5.2
+  version: 0.6.0
 platform: ruby
 authors:
 - Ben Miller
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2018-08-15 00:00:00.000000000 Z
+date: 2020-04-23 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: bundler
@@ -16,14 +16,14 @@ dependencies:
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '1.0'
+        version: '2.0'
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '1.0'
+        version: '2.0'
 - !ruby/object:Gem::Dependency
   name: minitest
   requirement: !ruby/object:Gem::Requirement
@@ -44,28 +44,28 @@ dependencies:
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '10.0'
+        version: '13.0'
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '10.0'
+        version: '13.0'
 - !ruby/object:Gem::Dependency
   name: rubocop
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '0.54'
+        version: '0.82'
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '0.54'
+        version: '0.82'
 description: 
 email: bjmllr@gmail.com
 executables: []
@@ -104,7 +104,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
       version: '0'
 requirements: []
 rubyforge_project: 
-rubygems_version: 2.7.3
+rubygems_version: 2.7.6.2
 signing_key: 
 specification_version: 4
 summary: Easily extract data from text