text_extractor 0.3.0 → 0.4.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: c42725b840531e241a7353991f7fec182561a89c
-  data.tar.gz: 07b7639b33d4d7b9380e9674c4a3f6531c3b03ff
+  metadata.gz: 5412586591653945efffad2ce8783c9269e58582
+  data.tar.gz: dc9fdb2f1eaad7bfafab31ad13e3e5eff966ea22
 SHA512:
-  metadata.gz: 9cadfc1dee9915d1b0b259de9b006154486aaba50808246bff28af16630ad6f481e8fba20289d1f60b315f19d98df44320df2af5e33b58096faaa6596163fa54
-  data.tar.gz: 9c3ee7b8a460612908a24bc64cc765aea243da2d2e9462b16630db1402fd6b7f75e2877be55341b968ac708d1b9b06c04b6424f50ecc5b5bafce373c7f5a049d
+  metadata.gz: f8c4a71b402c49c136700eab64daeba10a48938285d1d06e1522bb8bbd47fe1cf5f6962f0d2dcc555fa413164185e50eed069a52ac6bc4b253b1dd973529d09b
+  data.tar.gz: 73117018ffc3542a71aa201ac84ddc5d038881605e3a3fdccabce1d0d65a77137f2b731cac6a4463c8e3902c431fa418e166bcefe0cd6feedb899616a75a9e29

data/lib/text_extractor.rb

@@ -16,6 +16,8 @@ class TextExtractor
     @records = []
     @filldowns = []
     @current_record_values = []
+    @section_delimiter = nil
+    @section_terminator = nil
     instance_exec(&block)
   end
 
@@ -77,6 +79,11 @@ class TextExtractor
     @records << klass.new(instance_exec(&block), **kwargs)
   end
 
+  def section(delimiter, terminator = nil)
+    @section_delimiter = delimiter
+    @section_terminator = terminator
+  end
+
   def filldown(**kwargs, &block)
     raise "#{self.class}.filldown requires a block" unless block
     record(Filldown, **kwargs, &block)
@@ -87,7 +94,19 @@ class TextExtractor
   end
 
   def scan(input)
-    Extraction.new(input, self).scan.extraction_matches
+    prefill = {}
+    sections(input).flat_map { |section|
+      Extraction.new(section, self, prefill).scan.extraction_matches
+    }
+  end
+
+  def sections(input)
+    return [input] unless @section_delimiter
+
+    texts = input.split(@section_delimiter)
+    return texts unless @section_terminator
+
+    texts.map { |section| section + @section_terminator }
   end
 
   def regexps

data/lib/text_extractor/extraction.rb

@@ -3,16 +3,16 @@ class TextExtractor
   class Extraction
     attr_reader :input, :extractor, :re, :pos, :matches, :values
 
-    def initialize(input, extractor)
+    def initialize(input, extractor, fill = {})
       @input = input
       @extractor = extractor
+      @fill = fill
       @pos = 0
       @matches = []
       @last_match = nil
     end
 
     def extraction_matches
-      @fill = {}
       matches.flat_map do |match|
         extraction_match(match)
       end

data/lib/text_extractor/version.rb

@@ -1,5 +1,5 @@
 class TextExtractor
   def self.version
-    '0.3.0'
+    '0.4.0'
   end
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: text_extractor
 version: !ruby/object:Gem::Version
-  version: 0.3.0
+  version: 0.4.0
 platform: ruby
 authors:
 - Ben Miller
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2016-08-23 00:00:00.000000000 Z
+date: 2016-11-28 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: bundler
@@ -88,8 +88,9 @@ required_rubygems_version: !ruby/object:Gem::Requirement
       version: '0'
 requirements: []
 rubyforge_project: 
-rubygems_version: 2.5.1
+rubygems_version: 2.5.2
 signing_key: 
 specification_version: 4
 summary: Easily extract data from text
 test_files: []
+has_rdoc: