text_alignment 0.11.5 → 0.11.6

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: abf4387fb9ea598d924eb0a7369ca58ec0be7cdd35ac89abc57647d665c00207
-  data.tar.gz: 30ab0ccea5c04cae8132a70872cf5de4704ce7fd4e2104f7fddc6527794424c5
+  metadata.gz: 5ed6071b0293e9b7fa86acf4a737c80c9d784f453d3fb77992e3d9f1acc02bbe
+  data.tar.gz: 7a57b7afbe21061d9aac2f96cd9f7a3c83ff2f01b6c3973905f7681a40463287
 SHA512:
-  metadata.gz: 2033123f2289c991b2a53826921ca19489f7f39c53918df5f962e321b1f3ff0996760e9df302872d07a7e638e6c56ad86428d1ce773d6e14c54180ad2360b1be
-  data.tar.gz: a902ca48bba502af787deb3abf6c5a2b4c9a121394452ef25e95c61212ee0cfa4e991f83315bc6e03a52d45ead909acedeaf0abd9cdc278ccc58b7cb315ab556
+  metadata.gz: 141158c2f6b80975bacf68babc713b06d809f02b96cfd7accdecb00c6b4c362b9d130e29820074be7b89ac53c7cc93f850ec3d7ea9796eaad5021d441528e82b
+  data.tar.gz: 8bc4cc9ca9becc1c5638b6501268d33dd7700e8369d7c20c1ec6fd9ef11e9fd73e6a1354cb37376af250c8462e945cccf08417ba6d258f08660c53eb418e4658

data/bin/align_annotations

@@ -2,6 +2,7 @@
 require 'text_alignment'
 require 'json'
 require 'pp'
+require 'optparse'
 
 def read_annotations(filename)
 	case File.extname(filename)
@@ -108,24 +109,46 @@ def align_mannotations(source_annotations, reference_text, alignment, debug = fa
 end
 
 
+## Options
+overlap_p = false
+debug_p = false
+
+## command line option processing
+require 'optparse'
+optparse = OptionParser.new do |opts|
+	opts.banner = "Usage: align_annotations [options] target_annotations(.json|.txt) reference_text(.json|.txt)"
+
+	opts.on('-o', '--overlap', 'tells it to assume there may be overlapping texts.') do
+		overlap_p = true
+	end
+
+	opts.on('-d', '--debug', 'tells it to show debugging information.') do
+		debug_p = true
+	end
+
+	opts.on('-h', '--help', 'displays this screen.') do
+		puts opts
+		exit
+	end
+end
+
+optparse.parse!
+
 unless ARGV.length == 2
-	warn "align_annotations target_annotations(.json|.txt) reference_annotations(.json|.txt)"
-	exit
+	puts optparse.help
+	exit 1
 end
 
 source_annotations = read_annotations(ARGV[0])
 reference_text = read_text(ARGV[1])
 
-alignment = TextAlignment::TextAlignment.new(reference_text, true)
+alignment = TextAlignment::TextAlignment.new(reference_text, !overlap_p)
 
 target_annotations = if source_annotations.class == Array
-	# align_mannotations(source_annotations, reference_text, alignment, true)
-	align_mannotations(source_annotations, reference_text, alignment, false)
+	align_mannotations(source_annotations, reference_text, alignment, debug_p)
 else
-	# denotations = align_denotations(source_annotations[:denotations], source_annotations[:text], alignment)
-	denotations = align_denotations(source_annotations[:denotations], source_annotations[:text], alignment, false)
+	denotations = align_denotations(source_annotations[:denotations], source_annotations[:text], alignment, debug_p)
 	source_annotations.merge({text:reference_text, denotations:denotations})
 end
 
-# pp alignment.block_alignment
-# puts target_annotations.to_json
+puts target_annotations.to_json

data/lib/text_alignment/char_mapping.rb

@@ -108,7 +108,7 @@ class TextAlignment::CharMapping
 	def enmap_text(_text, char_mapping)
 		text = _text.dup
 
-		# To execute the single letter mapping
+		# To execute the single letter mapping replacement
 		char_mapping.each do |one, long|
 			text.gsub!(one, long) if long.length == 1
 		end

data/lib/text_alignment/mixed_alignment.rb

@@ -147,13 +147,24 @@ class TextAlignment::MixedAlignment
 		# recoverbility
 		count_nws =	sdiff.count{|d| d.old_element =~ /\S/}
 		count_nws_match =	sdiff.count{|d| d.action == '=' && d.old_element =~ /\S/}
-
 		coverage = count_nws_match.to_f / count_nws
 
 		# fragmentation rate
-		count_ofrag = sdiff.count{|d| d.old_element =~ /\s/} + 1
-		count_frag = sdiff.collect{|d| (d.action == '=') && (d.old_element =~/\s/) ? ' ' : d.action}.join.scan(/=+/).count
-		rate_frag = count_ofrag.to_f / count_frag
+		frag_str = sdiff.collect do |d|
+			case d.action
+			when '='
+				'='
+			when '-'
+				''
+			when '+'
+				(d.new_element =~ /\S/) ? '+' : ''
+			else
+				''
+			end
+		end.join.sub(/^[^=]++/, '').sub(/[^=]+$/, '')
+
+		count_frag = frag_str.scan(/=+/).count
+		rate_frag = 1.0 / count_frag
 
 		similarity = coverage * rate_frag
 	end

data/lib/text_alignment/version.rb

@@ -1,3 +1,3 @@
 class TextAlignment
-	VERSION = '0.11.5'
+	VERSION = '0.11.6'
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: text_alignment
 version: !ruby/object:Gem::Version
-  version: 0.11.5
+  version: 0.11.6
 platform: ruby
 authors:
 - Jin-Dong Kim
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2021-03-25 00:00:00.000000000 Z
+date: 2021-03-27 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: ruby-dictionary