Class: TextExtractor

Inherits:
Object
  • Object
show all
Defined in:
lib/text_extractor.rb,
lib/text_extractor/value.rb,
lib/text_extractor/record.rb,
lib/text_extractor/version.rb,
lib/text_extractor/filldown.rb,
lib/text_extractor/directives.rb,
lib/text_extractor/extraction.rb,
lib/text_extractor/inline_value.rb,
lib/text_extractor/directives/group.rb,
lib/text_extractor/directives/classes.rb

Overview

represents an extractor definition

Defined Under Namespace

Modules: Patterns Classes: Directives, Extraction, Filldown, InlineValue, Record, State, Value

Instance Attribute Summary collapse

Class Method Summary collapse

Instance Method Summary collapse

Constructor Details

#initialize(&block) ⇒ TextExtractor

Returns a new instance of TextExtractor.



11
12
13
14
15
16
17
18
19
20
21
22
# File 'lib/text_extractor.rb', line 11

def initialize(&block)
  raise "#{self.class}.new requires a block" unless block
  @values = {}
  @fill = {}
  @values = {}
  @records = []
  @filldowns = []
  @current_record_values = []
  @section_delimiter = nil
  @section_terminator = nil
  instance_exec(&block)
end

Instance Attribute Details

#recordsObject (readonly)

Returns the value of attribute records.



9
10
11
# File 'lib/text_extractor.rb', line 9

def records
  @records
end

#valuesObject (readonly)

Returns the value of attribute values.



9
10
11
# File 'lib/text_extractor.rb', line 9

def values
  @values
end

Class Method Details

.expand_directives(re) ⇒ Object



7
8
9
# File 'lib/text_extractor/directives.rb', line 7

def self.expand_directives(re)
  Directives.new(re).expand
end

.versionObject



2
3
4
# File 'lib/text_extractor/version.rb', line 2

def self.version
  '0.4.0'
end

Instance Method Details

#boolean(id, re = Patterns::BOOLEAN) ⇒ Object



51
52
53
# File 'lib/text_extractor.rb', line 51

def boolean(id, re = Patterns::BOOLEAN)
  value(id, re) { |val| !val.match(Patterns::FALSE) }
end

#filldown(**kwargs, &block) ⇒ Object



87
88
89
90
# File 'lib/text_extractor.rb', line 87

def filldown(**kwargs, &block)
  raise "#{self.class}.filldown requires a block" unless block
  record(Filldown, **kwargs, &block)
end

#find_record_for(match) ⇒ Object



92
93
94
# File 'lib/text_extractor.rb', line 92

def find_record_for(match)
  records[records.length.times.find_index { |i| match["__#{i}"] }]
end

#float(id, re = Patterns::FLOAT) ⇒ Object



59
60
61
# File 'lib/text_extractor.rb', line 59

def float(id, re = Patterns::FLOAT)
  value(id, re) { |val| Float(val) }
end

#inline(id, &block) ⇒ Object



47
48
49
# File 'lib/text_extractor.rb', line 47

def inline(id, &block)
  @values[id] = InlineValue.new(id, &block)
end

#integer(id, re = Patterns::INTEGER) ⇒ Object



55
56
57
# File 'lib/text_extractor.rb', line 55

def integer(id, re = Patterns::INTEGER)
  value(id, re) { |val| Integer(val) }
end

#ipaddr(id, re = Patterns::IPADDR) ⇒ Object



67
68
69
# File 'lib/text_extractor.rb', line 67

def ipaddr(id, re = Patterns::IPADDR)
  value(id, re) { |val| IPAddr.new(val) }
end

#ipnetaddr(id, re = Patterns::IPNETADDR) ⇒ Object



71
72
73
# File 'lib/text_extractor.rb', line 71

def ipnetaddr(id, re = Patterns::IPNETADDR)
  value(id, re) { |val| IPAddr.new(val) }
end

#rational(id, re = Patterns::RATIONAL) ⇒ Object



63
64
65
# File 'lib/text_extractor.rb', line 63

def rational(id, re = Patterns::RATIONAL)
  value(id, re) { |val| Rational(val) }
end

#record(klass = Record, **kwargs, &block) ⇒ Object



75
76
77
78
79
80
# File 'lib/text_extractor.rb', line 75

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

#regexpsObject



112
113
114
115
116
# File 'lib/text_extractor.rb', line 112

def regexps
  @records.map.with_index do |record, i|
    Regexp.new("(?<__#{i}>#{record.source})", record.options)
  end
end

#scan(input) ⇒ Object



96
97
98
99
100
101
# File 'lib/text_extractor.rb', line 96

def scan(input)
  prefill = {}
  sections(input).flat_map { |section|
    Extraction.new(section, self, prefill).scan.extraction_matches
  }
end

#section(delimiter, terminator = nil) ⇒ Object



82
83
84
85
# File 'lib/text_extractor.rb', line 82

def section(delimiter, terminator = nil)
  @section_delimiter = delimiter
  @section_terminator = terminator
end

#sections(input) ⇒ Object



103
104
105
106
107
108
109
110
# File 'lib/text_extractor.rb', line 103

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

#to_reObject



118
119
120
# File 'lib/text_extractor.rb', line 118

def to_re
  Regexp.union(*regexps)
end

#value(id, re, &block) ⇒ Object



39
40
41
42
43
44
45
# File 'lib/text_extractor.rb', line 39

def value(id, re, &block)
  val = @values[id] = Value.new(id, re, &block)
  define_singleton_method(id) do
    @current_record_values << val
    "(?<#{id}>#{re.source})"
  end
end