text_alignment 0.12.2 → 0.12.4

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 3c2a36fe4cfde7dfb76f554fd4afcae7cb5a03e455887621217f5e5e633b20b3
-  data.tar.gz: f63070c6f423bc15d0fc8c742a21238a104a1b2c1d3fe56ac436effa8ef8eacf
+  metadata.gz: ef51eeed4c82f3ddc211a1474a35c8b61a621ed7acb6bd801a62885c2c342448
+  data.tar.gz: 15b1d020f78a96e152459324d921092c5bd39477f856417fd30e4283d22399ea
 SHA512:
-  metadata.gz: '078a41bc6ab9b16e7747be6a3bb15aff4b23a1161bcea0b653a93f04d673799afcac2109cd1ce8d1a95c99c5c07d36842e3698c9f0997500e653fb4ab939e04a'
-  data.tar.gz: ce44d334779d43b3057317537f615ebf39b8049639d3e50c4e14272c952b76a5df2b060cfd3a15f1d28372c11a795ef8bf43cb04de32b5a78ce2f44433edddfb
+  metadata.gz: 473a18002d40bf3db81e0f42ffe3fbcc3ff5b1281964c2d5391a57b34ff07ff973ca86e5fe34dcbe2537410b46105e05a60772ffc27ed6667443062558201952
+  data.tar.gz: a8ddf9b9a2bd19b1e7303fcdf83fd862bbe8b601f2de88aa59c5d51b5a7184a0ee00fde86877390267ffd3cf8619c6a52bffabd9cb5b95be4ab34d20f81e1fab

data/lib/text_alignment/char_mapping.rb

@@ -78,6 +78,34 @@ TextAlignment::CHAR_MAPPING = [
 	['"', "''"]
 ]
 
+# build a string of every Unicode whitespace codepoint \s covers:
+ALL_WS = [
+	"\u0009", # CHARACTER TABULATION
+	"\u000A", # LINE FEED
+	"\u000B", # LINE TABULATION
+	"\u000C", # FORM FEED
+	"\u000D", # CARRIAGE RETURN
+	"\u0020", # SPACE
+	"\u0085", # NEXT LINE
+	"\u00A0", # NO-BREAK SPACE
+	"\u1680", # OGHAM SPACE MARK
+	"\u2000", # EN QUAD
+	"\u2001", # EM QUAD
+	"\u2002", # EN SPACE
+	"\u2003", # EM SPACE
+	"\u2004", # THREE-PER-EM SPACE
+	"\u2005", # FOUR-PER-EM SPACE
+	"\u2006", # SIX-PER-EM SPACE
+	"\u2007", # FIGURE SPACE
+	"\u2008", # PUNCTUATION SPACE
+	"\u2009", # THIN SPACE
+	"\u200A", # HAIR SPACE
+	"\u2028", # LINE SEPARATOR
+	"\u2029", # PARAGRAPH SEPARATOR
+	"\u202F", # NARROW NO-BREAK SPACE
+	"\u205F", # MEDIUM MATHEMATICAL SPACE
+	"\u3000", # IDEOGRAPHIC SPACE
+].join
 
 class TextAlignment::CharMapping
 	attr_reader :mapped_text, :index_enmap
@@ -101,11 +129,11 @@ class TextAlignment::CharMapping
 	end
 
 	def enmap_position(position)
-		@index_enmap[position] || raise(ArgumentError, "Unusual position of annotation: #{position}")
+		@index_enmap[position]
 	end
 
 	def demap_position(position)
-		@index_demap[position] || raise(ArgumentError, "Unusual position of annotation: #{position}")
+		@index_demap[position]
 	end
 
 	def enmap_denotations(denotations)
@@ -113,23 +141,6 @@ class TextAlignment::CharMapping
 
 		denotations.map do |d|
 			d.dup.merge(span:{begin:enmap_position(d[:span][:begin]), end:enmap_position(d[:span][:end])})
-		rescue ArgumentError => e
-			snippet_begin = d[:span][:begin] - 5
-			if snippet_begin < 0
-				snippet_begin = 0
-			end
-			snippet_end = d[:span][:end] + 5
-			if snippet_end > @text.length
-				snippet_end = @text.length
-			end
-			snippet = @text[snippet_begin ... d[:span][:begin]] + '[' + @text[d[:span][:begin] ... d[:span][:end]] + ']' + @text[d[:span][:end] ... snippet_end]
-			if snippet_begin > 0
-				snippet = '...' + snippet
-			end
-			if snippet_end < @text.length
-				snippet = snippet + '...'
-			end
-			raise ArgumentError, e.message + " (#{snippet})"
 		end
 	end
 
@@ -214,11 +225,15 @@ class TextAlignment::CharMapping
 	end
 
 	def squeeze_ws_1!(text)
-		text.gsub!(/\s{2,}/, ' ')
+		# Below should have (almost) the same semantics as text.gsub!(/\s{2,}/, ' ')
+		non_space_ws = ALL_WS.delete(" ")
+		text.tr!(non_space_ws, " ")
+		text.squeeze!(" ")
 	end
 
 	def squeeze_ws_0!(text)
-		text.gsub!(/\s+/, '')
+		# Below should have the same semantics as text.gsub!(/\s+/, '')
+		text.delete!(ALL_WS)
 	end
 
 end

data/lib/text_alignment/text_alignment.rb

@@ -40,12 +40,12 @@ class TextAlignment::TextAlignment
 		end
 
 		@mapped_text = @text_mapping.mapped_text
-		denotations_mapped = @text_mapping.enmap_denotations(denotations)
 
 		## To generate the block_alignment of the input text against the reference text
 		@blocks = if r = whole_block_alignment(@mapped_text, @mapped_reference_text, @cultivation_map)
 			r
 		else
+			denotations_mapped = @text_mapping.enmap_denotations(denotations)
 			find_block_alignment(@mapped_text, @mapped_reference_text, denotations_mapped, @cultivation_map)
 		end
 
@@ -343,7 +343,7 @@ class TextAlignment::TextAlignment
 
 		## term-based alignment
 		tblocks = if denotations
-			denotations_in_scope = denotations.select{|d| d[:span][:begin] >= b1 && d[:span][:end] <= e1}.
+			denotations_in_scope = denotations.select{|d| d[:span][:begin] && d[:span][:end] && d[:span][:begin] >= b1 && d[:span][:end] <= e1}.
 							sort{|d1, d2| d1[:span][:begin] <=> d2[:span][:begin] || d2[:span][:end] <=> d1[:span][:end] }.
 							map{|d| d.merge(lex:str1[d[:span][:begin] ... d[:span][:end]])}
 

data/lib/text_alignment/version.rb

@@ -1,3 +1,3 @@
 class TextAlignment
-	VERSION = '0.12.2'
+	VERSION = '0.12.4'
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: text_alignment
 version: !ruby/object:Gem::Version
-  version: 0.12.2
+  version: 0.12.4
 platform: ruby
 authors:
 - Jin-Dong Kim
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2024-01-03 00:00:00.000000000 Z
+date: 2025-05-22 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: ruby-dictionary
@@ -111,7 +111,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubygems_version: 3.4.19
+rubygems_version: 3.4.10
 signing_key: 
 specification_version: 4
 summary: Ruby class for aligning two character strings