docdiff 0.6.4 → 0.6.6

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: cde4401e24dbddfd093efe812847c7cc57f12cea257c113bc2625ac2c38361d5
-  data.tar.gz: aa7fd969d604d090f16817dcdb09f2f4a1e5218c2063d3467e29929305afdd41
+  metadata.gz: 610b5b95840b0bc6c176dca519ba0b29f9da90a443f6e84026cded3619154d75
+  data.tar.gz: bd0ea4e230932dadc8bdf6ab4ecb112b56e1594111ebae3903b03c88bcd68394
 SHA512:
-  metadata.gz: b0f085aa58f164c0b6a0d0cfaec0439df555d37fbe1c8dacd66962ab41084ec93cc6d0d13c3852ca9404d62c3941edc4477261b44f9402d0353b71cd3a3f257c
-  data.tar.gz: b5b1bbb4a18524f5d9278f0afac27dc732dde0be686d4b526301219499fa3ef5a073b132a27a4e12a8bbc7bf847c8440c81179453243b1d30190d8901ea05770
+  metadata.gz: 6b281546af7612221702b0579ce26e99504ed76d5198c2894cff6c85371529b48bc3140acce1297f5191b0e3321f5c31a7aa3b222ed100941e1161856d08d521
+  data.tar.gz: aa76e99c2d89826abccf7dbbe64d3979d51389e87c79d491d309dc3589f096b0fdde16c84d0b840f6637dc21dac24bf52b3c9b6b68b6f774bf142db392506eb9

data/Gemfile

@@ -1,16 +1,16 @@
-source 'https://rubygems.org'
+source "https://rubygems.org"
 
 group :darwin do
-  gem 'rb-fsevent'
-  gem 'growl'
+  gem "rb-fsevent"
+  gem "growl"
 end
 
-gem 'guard'
-gem 'guard-test'
+gem "guard"
+gem "guard-test"
 
 group :test do
-  gem 'simplecov', :require => false, :platforms => :ruby_19
-  gem 'rcov', :require => false, :platforms => :ruby_18
+  gem "simplecov", require: false, platforms: :ruby_19
+  gem "rcov", require: false, platforms: :ruby_18
 end
 
 # Specify your gem's dependencies in docdiff.gemspec

data/Guardfile

@@ -1,8 +1,8 @@
 # A sample Guardfile
 # More info at https://github.com/guard/guard#readme
 
-guard 'test', :all_on_start => true do
-   watch(%r{^lib/(.+)\.rb$})     { |m| "test/#{m[1]}_test.rb" }
-   watch(%r{^test/.+_test\.rb$})
-   watch('test/test_helper.rb')  { "test" }
+guard "test", all_on_start: true do
+  watch(%r{^lib/(.+)\.rb$}) { |m| "test/#{m[1]}_test.rb" }
+  watch(%r{^test/.+_test\.rb$})
+  watch("test/test_helper.rb") { "test" }
 end

data/Makefile

@@ -14,12 +14,12 @@ DESTDIR =
 PREFIX  = /usr/local
 datadir = $(DESTDIR)$(PREFIX)/share
 
-all:	$(DOCS)
+all: test docs dist gem
 
 test: $(TESTS)
 	$(RUBY) -I./lib -e 'ARGV.map{|a| require_relative "#{a}"}' $^
 
-docs:	$(DOCS)
+docs: $(DOCS)
 
 %.html: %.md
 	$(MD2HTML) --html-title="$(shell grep '^# .*' $< | head -n 1 | sed 's/^# //')" $< \
@@ -65,8 +65,9 @@ uninstall:
 	-rm -fr $(DESTDIR)/etc/$(PRODUCT)
 	-rm -fr $(datadir)/doc/$(PRODUCT)
 
-dist:
-	git archive --prefix="$(PRODUCT)-$(VERSION)/" --format=tar HEAD --output="$(PRODUCT)-$(VERSION).tar.gz"
+dist: $(PRODUCT)-$(VERSION).tar.gz
+$(PRODUCT)-$(VERSION).tar.gz:
+	git archive --prefix="$(PRODUCT)-$(VERSION)/" --format=tar HEAD --output="$@"
 
 gem: $(PRODUCT)-$(VERSION).gem
 $(PRODUCT)-$(VERSION).gem: $(PRODUCT).gemspec
@@ -74,9 +75,7 @@ $(PRODUCT)-$(VERSION).gem: $(PRODUCT).gemspec
 
 clean:
 	-rm -fr $(DOCS)
-
-distclean: clean
 	-rm -fr $(PRODUCT)-$(VERSION).tar.gz
 	-rm -fr $(PRODUCT)-$(VERSION).gem
 
-.PHONY:	all test docs install uninstall dist gem clean distclean
+.PHONY: all test docs install uninstall dist gem clean

data/README.md

@@ -85,6 +85,7 @@ $
 * Runtime requirements:
   - [Ruby](https://www.ruby-lang.org/) (>= 3.0)
 * Development requirements:
+  - [Test::Unit](https://test-unit.github.io/)
   - Make ([GNU Make](https://www.gnu.org/software/make/))
   - [Git](https://git-scm.com/)
   - [md2html](https://github.com/mity/md4c) (for generating documents)

data/README_ja.md

@@ -85,6 +85,7 @@ $
 * 実行時に必要なソフトウェア:
   - [Ruby](https://www.ruby-lang.org/) (>= 3.0)
 * 開発時に必要なソフトウェア:
+  - [Test::Unit](https://test-unit.github.io/)
   - Make ([GNU Make](https://www.gnu.org/software/make/))
   - [Git](https://git-scm.com/)
   - [md2html](https://github.com/mity/md4c)（ドキュメント生成用）

data/Rakefile

@@ -1,12 +1,12 @@
-require 'rake/clean'
-require 'rake/testtask'
-require 'bundler/gem_tasks'
+require "rake/clean"
+require "rake/testtask"
+require "bundler/gem_tasks"
 
-ENV['SOURCE_DATE_EPOCH'] ||= `git show --quiet --format=%ct HEAD`
+ENV["SOURCE_DATE_EPOCH"] ||= `git show --quiet --format=%ct HEAD`
 
 Rake::TestTask.new do |t|
-  t.test_files = FileList['test/*_test.rb']
+  t.test_files = FileList["test/*_test.rb"]
   t.verbose = true
 end
 
-task :default => :test
+task default: :test

data/bin/docdiff

@@ -2,213 +2,6 @@
 # DocDiff: word/character-oriented text comparison utility
 # Copyright (C) 2002-2011 Hisashi MORITA
 # Requirements: Ruby (>= 2.0)
-require 'docdiff'
-require 'optparse'
+require "docdiff"
 
-# do_config_stuff
-
-default_config = {
-  :resolution    => "word",
-  :encoding      => "auto",
-  :eol           => "auto",
-  :format        => "html",
-  :cache         => true,
-  :digest        => false,
-  :pager         => nil,
-  :verbose       => false
-}
-
-clo = command_line_options = {}
-
-# if invoked as "worddiff" or "chardiff",
-# appropriate resolution is set respectively.
-case File.basename($0, ".*")
-when "worddiff" then; clo[:resolution] = "word"
-when "chardiff" then; clo[:resolution] = "char"
-end
-
-ARGV.options {|o|
-  o.def_option('--resolution=RESOLUTION',
-    resolutions = ['line', 'word', 'char'],
-    'specify resolution (granularity)',
-    "#{resolutions.join('|')} (default: word)"
-    ){|s| clo[:resolution] = (s || "word")}
-  o.def_option('--line', 'same as --resolution=line'){clo[:resolution] = "line"}
-  o.def_option('--word', 'same as --resolution=word'){clo[:resolution] = "word"}
-  o.def_option('--char', 'same as --resolution=char'){clo[:resolution] = "char"}
-
-  o.def_option('--encoding=ENCODING',
-    encodings = ['ASCII', 'EUC-JP', 'Shift_JIS', 'CP932', 'UTF-8', 'auto'],
-    "specify character encoding",
-    "#{encodings.join('|')} (default: auto)",
-    "(try ASCII for single byte encodings such as ISO-8859)"
-    ){|s| clo[:encoding] = (s || "auto")}
-  o.def_option('--ascii', 'same as --encoding=ASCII'){clo[:encoding] = "ASCII"}
-  o.def_option('--iso8859', 'same as --encoding=ASCII'){clo[:encoding] = "ASCII"}
-  o.def_option('--iso8859x', 'same as --encoding=ASCII (deprecated)'){clo[:encoding] = "ASCII"}
-  o.def_option('--eucjp', 'same as --encoding=EUC-JP'){clo[:encoding] = "EUC-JP"}
-  o.def_option('--sjis', 'same as --encoding=Shift_JIS'){clo[:encoding] = "Shift_JIS"}
-  o.def_option('--cp932', 'same as --encoding=CP932'){clo[:encoding] = "CP932"}
-  o.def_option('--utf8', 'same as --encoding=UTF-8'){clo[:encoding] = "UTF-8"}
-
-  o.def_option('--eol=EOL',
-    eols = ['CR','LF','CRLF','auto'],
-    'specify end-of-line character',
-    "#{eols.join('|')} (default: auto)",
-    ){|s| clo[:eol] = (s || "auto")}
-  o.def_option('--cr', 'same as --eol=CR'){clo[:eol] = "CR"}
-  o.def_option('--lf', 'same as --eol=LF'){clo[:eol] = "LF"}
-  o.def_option('--crlf', 'same as --eol=CRLF'){clo[:eol] = "CRLF"}
-
-  o.def_option('--format=FORMAT',
-    formats = ['tty', 'manued', 'html', 'wdiff', 'stat', 'user'],
-    'specify output format',
-    "#{formats.join('|')} (default: html) (stat is deprecated)",
-    '(user tags can be defined in config file)'
-    ){|s| clo[:format] = (s || "manued")}
-  o.def_option('--tty', 'same as --format=tty'){clo[:format] = "tty"}
-  o.def_option('--manued', 'same as --format=manued'){clo[:format] = "manued"}
-  o.def_option('--html', 'same as --format=html'){clo[:format] = "html"}
-  o.def_option('--wdiff', 'same as --format=wdiff'){clo[:format] = "wdiff"}
-  o.def_option('--stat', 'same as --format=stat (not implemented) (deprecated)'){clo[:format] = "stat"}
-
-  o.def_option('--label LABEL', '-L LABEL',
-    'use label instead of file name (not implemented; exists for compatibility with diff)'
-    ){|s1, s2| clo[:label1], clo[:label2] = s1, s2}
-
-  o.def_option('--digest', 'digest output, do not show all'){clo[:digest] = true}
-  o.def_option('--summary', 'same as --digest'){clo[:digest] = true}
-  o.def_option('--display=DISPLAY',
-    display_types = ['inline', 'block', 'multi'],
-    'specify presentation type (effective only with digest; experimental feature)',
-    "#{display_types.join('|')} (default: inline) (multi is deprecated)",
-    ){|s| clo[:display] ||= s.downcase}
-  o.def_option('--cache', 'use file cache (not implemented) (deprecated)'){clo[:cache] = true}
-  o.def_option('--pager=PAGER', String,
-    'specify pager (if available, $DOCDIFF_PAGER is used by default)'
-    ){|s| clo[:pager] = s}
-  o.def_option('--no-pager', 'do not use pager'){clo[:pager] = false}
-  o.def_option('--config-file=FILE', String,
-    'specify config file to read'){|s| clo[:config_file] = s}
-  o.def_option('--no-config-file',
-    'do not read config files'){clo[:no_config_file] = true}
-  o.def_option('--verbose', 'run verbosely (not well-supported) (deprecated)'){clo[:verbose] = true}
-
-  o.def_option('--help', 'show this message'){puts o; exit(0)}
-  o.def_option('--version', 'show version'){puts DocDiff::AppVersion; exit(0)}
-  o.def_option('--license', 'show license (deprecated)'){puts DocDiff::License; exit(0)}
-  o.def_option('--author', 'show author(s) (deprecated)'){puts DocDiff::Author; exit(0)}
-
-  o.on_tail("When invoked as worddiff or chardiff, resolution will be set accordingly.",
-    "Config files: /etc/docdiff/docdiff.conf, ~/.config/docdiff/docdiff.conf (or ~/etc/docdiff/docdiff.conf (deprecated))")
-
-  o.parse!
-} or exit(1)
-
-docdiff = DocDiff.new()
-docdiff.config.update(default_config)
-unless clo[:no_config_file] == true # process_commandline_option
-  message = docdiff.process_config_file(DocDiff::SystemConfigFileName)
-  if clo[:verbose] == true || docdiff.config[:verbose] == true
-    STDERR.print message
-  end
-  #    message = docdiff.process_config_file(DocDiff::UserConfigFileName)
-  case
-  when [File.exist?(DocDiff::UserConfigFileName),
-        File.exist?(DocDiff::AltUserConfigFileName),
-        File.exist?(DocDiff::XDGUserConfigFileName)].count(true) >= 2
-    raise <<~EOS
-      #{DocDiff::UserConfigFileName}, #{DocDiff::AltUserConfigFileName}, and \
-      #{DocDiff::XDGUserConfigFileName} cannot be used at the same time. \
-      Keep one and remove or rename the others.
-    EOS
-  when File.exist?(DocDiff::UserConfigFileName)
-    message = docdiff.process_config_file(DocDiff::UserConfigFileName)
-  when File.exist?(DocDiff::AltUserConfigFileName)
-    message = docdiff.process_config_file(DocDiff::AltUserConfigFileName)
-  when File.exist?(DocDiff::XDGUserConfigFileName)
-    message = docdiff.process_config_file(DocDiff::XDGUserConfigFileName)
-  end
-  if clo[:verbose] == true || docdiff.config[:verbose] == true
-    STDERR.print message
-  end
-end
-unless clo[:config_file].nil?
-  if File.exist?(clo[:config_file])
-    message = docdiff.process_config_file(clo[:config_file])
-  else
-    raise "#{clo[:config_file]} does not exist."
-  end
-  if clo[:verbose] == true || docdiff.config[:verbose] == true
-    STDERR.print message
-  end
-end
-docdiff.config.update(clo)
-
-docdiff.config[:pager] =
-  if (pager = docdiff.config[:pager]).is_a?(String) && !pager.empty?
-    pager
-  elsif (pager = docdiff.config[:pager]) == false
-    pager
-  elsif (pager = ENV['DOCDIFF_PAGER']) && !pager.empty?
-    pager
-  end
-
-# config stuff done
-
-# process the documents
-
-file1_content = nil
-file2_content = nil
-raise "Try `#{File.basename($0)} --help' for more information." if ARGV[0].nil?
-raise "Specify at least 2 target files." unless ARGV[0] && ARGV[1]
-ARGV[0] = "/dev/stdin" if ARGV[0] == "-"
-ARGV[1] = "/dev/stdin" if ARGV[1] == "-"
-raise "No such file: #{ARGV[0]}." unless FileTest.exist?(ARGV[0])
-raise "No such file: #{ARGV[1]}." unless FileTest.exist?(ARGV[1])
-raise "#{ARGV[0]} is not readable." unless FileTest.readable?(ARGV[0])
-raise "#{ARGV[1]} is not readable." unless FileTest.readable?(ARGV[1])
-File.open(ARGV[0], "r"){|f| file1_content = f.read}
-File.open(ARGV[1], "r"){|f| file2_content = f.read}
-
-doc1 = nil
-doc2 = nil
-
-encoding1 = docdiff.config[:encoding]
-encoding2 = docdiff.config[:encoding]
-eol1 = docdiff.config[:eol]
-eol2 = docdiff.config[:eol]
-
-if docdiff.config[:encoding] == "auto"
-  encoding1 = DocDiff::CharString.guess_encoding(file1_content)
-  encoding2 = DocDiff::CharString.guess_encoding(file2_content)
-  case
-  when (encoding1 == "UNKNOWN" or encoding2 == "UNKNOWN")
-    raise "Document encoding unknown (#{encoding1}, #{encoding2})."
-  when encoding1 != encoding2
-    raise "Document encoding mismatch (#{encoding1}, #{encoding2})."
-  end
-end
-
-if docdiff.config[:eol] == "auto"
-  eol1 = DocDiff::CharString.guess_eol(file1_content)
-  eol2 = DocDiff::CharString.guess_eol(file2_content)
-  case
-  when (eol1.nil? or eol2.nil?)
-    raise "Document eol is nil (#{eol1.inspect}, #{eol2.inspect}).  The document might be empty."
-  when (eol1 == 'UNKNOWN' or eol2 == 'UNKNOWN')
-    raise "Document eol unknown (#{eol1.inspect}, #{eol2.inspect})."
-  when (eol1 != eol2)
-    raise "Document eol mismatch (#{eol1}, #{eol2})."
-  end
-end
-
-doc1 = DocDiff::Document.new(file1_content, encoding1, eol1)
-doc2 = DocDiff::Document.new(file2_content, encoding2, eol2)
-
-output = docdiff.run(doc1, doc2,
-  {:resolution => docdiff.config[:resolution],
-    :format     => docdiff.config[:format],
-    :digest     => docdiff.config[:digest],
-    :display    => docdiff.config[:display]})
-docdiff.print_or_write_to_pager(output, docdiff.config[:pager])
+DocDiff::CLI.run

data/devutil/Rakefile

@@ -1,9 +1,16 @@
-require 'rake/clean'
+# frozen_string_literal: true
 
-file 'JIS0208.TXT' do |t|
-  sh 'curl -O ftp://ftp.unicode.org/Public/MAPPINGS/OBSOLETE/EASTASIA/JIS/JIS0208.TXT'
+require "rake/clean"
+
+file "JIS0208.TXT" do
+  sh "curl -O ftp://ftp.unicode.org/Public/MAPPINGS/OBSOLETE/EASTASIA/JIS/JIS0208.TXT"
+end
+
+desc "Run unit test"
+task :check => "jis0208_test.rb" do |t|
+  sh "ruby #{t.source}"
 end
 
-task :default => 'JIS0208.TXT'
+task default: :check
 
-CLOBBER.include('JIS0208.TXT')
+CLOBBER.include("JIS0208.TXT")

data/devutil/char_by_charclass.rb

@@ -1,23 +1,46 @@
-#!/usr/bin/ruby
-# test character classes on ASCII characters.
+#!/usr/bin/env ruby
+# frozen_string_literal: true
+
+# Categorize ASCII characters by character classes
 # 2003-03-10 Hisashi MORITA
 
-charclasses = ["[:cntrl:]", 
-               "[:space:]", "[:blank:]", 
-               "[:digit:]", 
-               "[:alpha:]", "[:alnum:]", 
-               "[:punct:]",
-               "[:lower:]", "[:upper:]",  
-               "[:print:]", "[:graph:]", 
-               "[:xdigit:]"]
-chars = (0x00 .. 0xff).to_a
+charclasses = [
+  "[:cntrl:]",
+  "[:space:]",
+  "[:blank:]",
+  "[:digit:]",
+  "[:alpha:]",
+  "[:alnum:]",
+  "[:punct:]",
+  "[:lower:]",
+  "[:upper:]",
+  "[:print:]",
+  "[:graph:]",
+  "[:xdigit:]",
+]
+
+chars = (0x00..0xff).to_a
+
+result =
+  charclasses.map do |charclass|
+    charclass_re = /[#{charclass}]/
+    member_chars =
+      chars.reduce([]) do |acc, char|
+        if charclass_re.match([char].pack("C*"))
+          acc << char
+        else
+          acc
+        end
+      end
+    member_chars_in_hex =
+      member_chars.map { |char| format("\\x%02x", char) }.join
+    member_chars_packed =
+      member_chars.map { |char| [char].pack("C*").inspect[1..-2] }.join
+
+    <<~EOS
+      #{charclass}\t#{member_chars_in_hex}
+      \t\t(#{member_chars_packed})
+    EOS
+  end
 
-charclasses.each{|charclass|
-  member_chars = []
-  chars.each{|char|
-    if Regexp.new("[#{charclass}]") =~ char.to_a.pack("C*")
-      member_chars.push char
-    end
-  }
-  puts "#{charclass}\t#{member_chars.collect{|char|sprintf("\\x%02x", char)}.join}\n\t\t(#{member_chars.collect{|char|char.to_a.pack('C*').inspect[1..-2]}.join})"
-}
+puts result

data/devutil/charclass_by_char.rb

@@ -1,21 +1,42 @@
-#!/usr/bin/ruby
-# test character classes on ASCII characters.
+#!/usr/bin/env ruby
+# frozen_string_literal: true
+
+# List ASCII characters with matching character classes
 # 2003-03-10 Hisashi MORITA
 
-charclasses = ["[:cntrl:]", 
-               "[:space:]", "[:blank:]", 
-               "[:digit:]", 
-               "[:alpha:]", "[:alnum:]", 
-               "[:punct:]",
-               "[:lower:]", "[:upper:]",  
-               "[:print:]", "[:graph:]", 
-               "[:xdigit:]"]
-(0x00 .. 0xff).to_a.each{|char|
-  attribute = []
-  charclasses.each{|charclass|
-    if Regexp.new("[#{charclass}]") =~ char.to_a.pack("C*")
-      attribute.push charclass
-    end
-  }
-  puts "#{sprintf("\\x%02x", char)} (#{char.to_a.pack('C*').inspect})\t#{attribute.join(', ')}"
-}
+charclasses = [
+  "[:cntrl:]",
+  "[:space:]",
+  "[:blank:]",
+  "[:digit:]",
+  "[:alpha:]",
+  "[:alnum:]",
+  "[:punct:]",
+  "[:lower:]",
+  "[:upper:]",
+  "[:print:]",
+  "[:graph:]",
+  "[:xdigit:]",
+]
+
+chars = (0x00..0xff).to_a
+
+result =
+  chars.map do |char|
+    char_packed = [char].pack("C*")
+    attribute =
+      charclasses.reduce([]) do |acc, charclass|
+        if /[#{charclass}]/.match(char_packed)
+          acc << charclass
+        else
+          acc
+        end
+      end
+    hex = format("\\x%02x", char)
+    packed_string = [char].pack("C*").inspect
+    attributes = attribute.join(", ")
+
+    "#{hex} (#{packed_string})\t#{attributes}"
+  end
+
+puts result