Sha256: 54d198d153ba71bdaf407208549f40ab7d23dedf21c3c6d2aaae27f7f300e950
Contents?: true
Size: 1.3 KB
Versions: 23
Compression:
Stored size: 1.3 KB
Contents
# encoding: UTF-8
# Copyright 2012 Twitter, Inc
# http://www.apache.org/licenses/LICENSE-2.0
module TwitterCldr
module Segmentation
class BreakIterator
attr_reader :locale, :options
def initialize(locale = TwitterCldr.locale, options = {})
@locale = locale
@options = options
end
def each_sentence(str, &block)
iter = iterator_for('sentence')
iter.each_segment(str, &block)
end
def each_word(str, &block)
iter = iterator_for('word')
iter.each_segment(str, &block)
end
def each_grapheme_cluster(str, &block)
iter = iterator_for('grapheme')
iter.each_segment(str, &block)
end
def each_line(str, &block)
iter = iterator_for('line')
iter.each_segment(str, &block)
end
private
def iterator_for(boundary_type)
iterator_cache[boundary_type] ||= begin
rule_set = RuleSet.create(locale, boundary_type, options)
case boundary_type
when 'line'
LineIterator.new(rule_set)
when 'word'
WordIterator.new(rule_set)
else
SegmentIterator.new(rule_set)
end
end
end
def iterator_cache
@iterator_cache ||= {}
end
end
end
end
Version data entries
23 entries across 23 versions & 1 rubygems