docdiff 0.6.5 → 0.6.6

data/devutil/jis0208_test.rb

@@ -0,0 +1,196 @@
+#!/usr/bin/env ruby
+# frozen_string_literal: true
+
+require "test/unit"
+require_relative "jis0208"
+
+class TestCaseJIS0208 < Test::Unit::TestCase
+  # internal methods
+
+  def test_utf16_to_utf8
+    # "\xE3\x80\x80": U+3000 IDEOGRAPHIC SPACE in UTF-8
+    expected = String.new("\xE3\x80\x80", encoding: Encoding::ASCII_8BIT)
+    actual = JIS0208.new.utf16_to_utf8(["3000"].pack("H*"))
+    assert_equal(expected, actual)
+  end
+
+  def test_characters
+    expected = String.new("\xE3\x80\x80", encoding: Encoding::ASCII_8BIT)
+    actual = JIS0208.new.characters[1][1][:u8]
+    assert_equal(expected, actual)
+  end
+
+  def test_char
+    expected = "\\xe3\\x80\\x80"
+    actual = JIS0208.new.char(1, 1, "UTF-8")
+    assert_equal(expected, actual)
+  end
+
+  # EUC-JP expressions
+
+  def test_euc_ja_alnum
+    exps = JIS0208.new.euc_ja_alnum
+    expected = ["\\xa3\\xb0", "\\xa3\\xfa", 62]
+    assert_equal(expected, [exps.first, exps.last, exps.size])
+  end
+
+  def test_euc_ja_blank
+    exps = JIS0208.new.euc_ja_blank
+    expected = ["\\xa1\\xa1", "\\xa1\\xa1", 1]
+    assert_equal(expected, [exps.first, exps.last, exps.size])
+  end
+
+  def test_euc_ja_print
+    exps = JIS0208.new.euc_ja_print
+    expected = ["\\xa3\\xb0", "\\xa1\\xa1", 355]
+    assert_equal(expected, [exps.first, exps.last, exps.size])
+  end
+
+  def test_euc_ja_graph
+    exps = JIS0208.new.euc_ja_graph
+    expected = ["\\xa3\\xb0", "\\xa8\\xc0", 354]
+    assert_equal(expected, [exps.first, exps.last, exps.size])
+  end
+
+  def test_euc_ja_punct
+    exps = JIS0208.new.euc_ja_punct
+    expected = ["\\xa1\\xa2", "\\xa8\\xc0", 292]
+    assert_equal(expected, [exps.first, exps.last, exps.size])
+  end
+
+  def test_euc_ja_space
+    exps = JIS0208.new.euc_ja_space
+    expected = ["\\xa1\\xa1", "\\xa1\\xa1", 1]
+    assert_equal(expected, [exps.first, exps.last, exps.size])
+  end
+
+  def test_euc_hiragana
+    exps = JIS0208.new.euc_hiragana
+    expected = ["\\xa4\\xa1", "\\xa4\\xf3", 83]
+    assert_equal(expected, [exps.first, exps.last, exps.size])
+  end
+
+  def test_euc_katakana
+    exps = JIS0208.new.euc_katakana
+    expected = ["\\xa5\\xa1", "\\xa5\\xf6", 86]
+    assert_equal(expected, [exps.first, exps.last, exps.size])
+  end
+
+  def test_euc_kanji
+    exps = JIS0208.new.euc_kanji
+    expected = ["\\xb0\\xa1-\\xb0\\xfe", "\\xf4\\xa1-\\xf4\\xa6", 69]
+    assert_equal(expected, [exps.first, exps.last, exps.size])
+  end
+
+  # Shift-JIS (CP932) expressions
+
+  def test_sjis_ja_alnum
+    exps = JIS0208.new.sjis_ja_alnum
+    expected = ["\\x82\\x4f", "\\x82\\x9a", 62]
+    assert_equal(expected, [exps.first, exps.last, exps.size])
+  end
+
+  def test_sjis_ja_blank
+    exps = JIS0208.new.sjis_ja_blank
+    expected = ["\\x81\\x40", "\\x81\\x40", 1]
+    assert_equal(expected, [exps.first, exps.last, exps.size])
+  end
+
+  def test_sjis_ja_print
+    exps = JIS0208.new.sjis_ja_print
+    expected = ["\\x82\\x4f", "\\x81\\x40", 355]
+    assert_equal(expected, [exps.first, exps.last, exps.size])
+  end
+
+  def test_sjis_ja_graph
+    exps = JIS0208.new.sjis_ja_graph
+    expected = ["\\x82\\x4f", "\\x84\\xbe", 354]
+    assert_equal(expected, [exps.first, exps.last, exps.size])
+  end
+
+  def test_sjis_ja_punct
+    exps = JIS0208.new.sjis_ja_punct
+    expected = ["\\x81\\x41", "\\x84\\xbe", 292]
+    assert_equal(expected, [exps.first, exps.last, exps.size])
+  end
+
+  def test_sjis_ja_space
+    exps = JIS0208.new.sjis_ja_space
+    expected = ["\\x81\\x40", "\\x81\\x40", 1]
+    assert_equal(expected, [exps.first, exps.last, exps.size])
+  end
+
+  def test_sjis_hiragana
+    exps = JIS0208.new.sjis_hiragana
+    expected = ["\\x82\\x9f", "\\x82\\xf1", 83]
+    assert_equal(expected, [exps.first, exps.last, exps.size])
+  end
+
+  def test_sjis_katakana
+    exps = JIS0208.new.sjis_katakana
+    expected = ["\\x83\\x40", "\\x83\\x96", 86]
+    assert_equal(expected, [exps.first, exps.last, exps.size])
+  end
+
+  def test_sjis_kanji
+    exps = JIS0208.new.sjis_kanji
+    expected = ["\\x88\\x9f-\\x88\\xfc", "\\xea\\x9f-\\xea\\xa4", 69] # FIXME
+    assert_equal(expected, [exps.first, exps.last, exps.size])
+  end
+
+  # UTF-8 expressions
+
+  def test_utf8_ja_alnum
+    exps = JIS0208.new.utf8_ja_alnum
+    expected = ["\\xef\\xbc\\x90", "\\xef\\xbd\\x9a", 62]
+    assert_equal(expected, [exps.first, exps.last, exps.size])
+  end
+
+  def test_utf8_ja_blank
+    exps = JIS0208.new.utf8_ja_blank
+    expected = ["\\xe3\\x80\\x80", "\\xe3\\x80\\x80", 1]
+    assert_equal(expected, [exps.first, exps.last, exps.size])
+  end
+
+  def test_utf8_ja_print
+    exps = JIS0208.new.utf8_ja_print
+    expected = ["\\xef\\xbc\\x90", "\\xe3\\x80\\x80", 355]
+    assert_equal(expected, [exps.first, exps.last, exps.size])
+  end
+
+  def test_utf8_ja_graph
+    exps = JIS0208.new.utf8_ja_graph
+    expected = ["\\xef\\xbc\\x90", "\\xe2\\x95\\x82", 354]
+    assert_equal(expected, [exps.first, exps.last, exps.size])
+  end
+
+  def test_utf8_ja_punct
+    exps = JIS0208.new.utf8_ja_punct
+    expected = ["\\xe3\\x80\\x81", "\\xe2\\x95\\x82", 292]
+    assert_equal(expected, [exps.first, exps.last, exps.size])
+  end
+
+  def test_utf8_ja_space
+    exps = JIS0208.new.utf8_ja_space
+    expected = ["\\xe3\\x80\\x80", "\\xe3\\x80\\x80", 1]
+    assert_equal(expected, [exps.first, exps.last, exps.size])
+  end
+
+  def test_utf8_hiragana
+    exps = JIS0208.new.utf8_hiragana
+    expected = ["\\xe3\\x81\\x81", "\\xe3\\x82\\x93", 83]
+    assert_equal(expected, [exps.first, exps.last, exps.size])
+  end
+
+  def test_utf8_katakana
+    exps = JIS0208.new.utf8_katakana
+    expected = ["\\xe3\\x82\\xa1", "\\xe3\\x83\\xb6", 86]
+    assert_equal(expected, [exps.first, exps.last, exps.size])
+  end
+
+  def test_utf8_kanji
+    exps = JIS0208.new.utf8_kanji
+    expected = ["\\xe4\\xba\\x9c", "\\xe7\\x86\\x99", 6355]
+    assert_equal(expected, [exps.first, exps.last, exps.size])
+  end
+end

data/doc/news.md

@@ -1,5 +1,13 @@
 # News
 
+### 0.6.6 (2026-02-18)
+
+* User-visible changes:
+  - `--encoding` and `--eol` options now accept lowercase values, such as ascii or crlf, as well as ASCII or CRLF.
+* Developer-related changes:
+  - Applied some lint (except for lib/docdiff/diff/).
+  - `make all` now generates docs, tarball, and gem, in addition to running tests.
+
 ### 0.6.5 (2025-12-29)
 
 * User-visible changes:

data/docdiff.gemspec

@@ -1,5 +1,6 @@
 # -*- encoding: utf-8 -*-
-$:.unshift File.expand_path("../lib", __FILE__)
+
+$LOAD_PATH.unshift(File.expand_path("../lib", __FILE__))
 require "docdiff/version"
 
 Gem::Specification.new do |s|
@@ -9,17 +10,18 @@ Gem::Specification.new do |s|
   s.authors     = ["Hisashi Morita"]
   s.email       = ["hisashim@icloud.com"]
   s.homepage    = "https://github.com/hisashim/docdiff"
-  s.summary     = %q{Word-by-word diff}
-  s.description = %q{DocDiff compares two text files and shows the
-                     difference. It can compare files word by word,
-                     character by character, or line by line. It has
-                     several output formats such as HTML, tty, Manued,
-                     or user-defined markup.}
+  s.summary     = "Word-by-word diff"
+  s.description = <<~EOS.chomp
+    DocDiff compares two text files and shows the
+    difference. It can compare files word by word,
+    character by character, or line by line. It has
+    several output formats such as HTML, tty, Manued,
+    or user-defined markup.
+  EOS
 
   s.files         = `git ls-files`.split("\n")
-  s.test_files    = `git ls-files -- {test,spec,features}/*`.split("\n")
-  s.executables   = `git ls-files -- bin/*`.split("\n").map{ |f| File.basename(f) }
+  s.executables   = `git ls-files -- bin/*`.split("\n").map { |f| File.basename(f) }
   s.require_paths = ["lib"]
-  s.required_ruby_version = '>= 3.0'
+  s.required_ruby_version = ">= 3.0"
   s.add_development_dependency "test-unit", "~> 3"
 end

data/lib/doc_diff.rb

@@ -1,35 +1,38 @@
 # DocDiff: word/character-oriented text comparison utility
 # Copyright (C) 2002-2011 Hisashi MORITA
 # Requirements: Ruby (>= 2.0)
-require 'docdiff/difference'
-require 'docdiff/document'
-require 'docdiff/view'
-require 'docdiff/cli'
+require "docdiff/difference"
+require "docdiff/document"
+require "docdiff/view"
+require "docdiff/cli"
 
 class DocDiff
-
-  Author = "Copyright (C) 2002-2011 Hisashi MORITA.\n" +
-           "diff library originates from Ruby/CVS by TANAKA Akira.\n"
-  License = "This software is licensed under so-called modified BSD license.\n" +
-            "See the document for detail.\n"
+  Author = <<~EOS
+    Copyright (C) 2002-2011 Hisashi MORITA.
+    diff library originates from Ruby/CVS by TANAKA Akira.
+  EOS
+  License = <<~EOS
+    This software is licensed under so-called modified BSD license.
+    See the document for detail.
+  EOS
   SystemConfigFileName = File.join(File::Separator, "etc", "docdiff", "docdiff.conf")
-  UserConfigFileName = File.join(ENV['HOME'], "etc", "docdiff", "docdiff.conf")
-  AltUserConfigFileName = File.join(ENV['HOME'], ".docdiff", "docdiff.conf")
+  UserConfigFileName = File.join(ENV["HOME"], "etc", "docdiff", "docdiff.conf")
+  AltUserConfigFileName = File.join(ENV["HOME"], ".docdiff", "docdiff.conf")
   XDGUserConfigFileName =
-    if xdg_config_home = ENV['XDG_CONFIG_HOME'] && !xdg_config_home.empty?
-      File.join(ENV['HOME'], xdg_config_home, "docdiff", "docdiff.conf")
+    if (xdg_config_home = ENV["XDG_CONFIG_HOME"]) && !xdg_config_home.empty?
+      File.join(ENV["HOME"], xdg_config_home, "docdiff", "docdiff.conf")
     else
-      File.join(ENV['HOME'], ".config", "docdiff", "docdiff.conf")
+      File.join(ENV["HOME"], ".config", "docdiff", "docdiff.conf")
     end
   DEFAULT_CONFIG = {
-    :resolution    => "word",
-    :encoding      => "auto",
-    :eol           => "auto",
-    :format        => "html",
-    :cache         => true,
-    :digest        => false,
-    :pager         => nil,
-    :verbose       => false
+    resolution: "word",
+    encoding: "auto",
+    eol: "auto",
+    format: "html",
+    cache: true,
+    digest: false,
+    pager: nil,
+    verbose: false,
   }
 
   def initialize(config: {})
@@ -44,20 +47,17 @@ class DocDiff
   def compare_by_line_word(doc1, doc2)
     lines = compare_by_line(doc1, doc2)
     words = Difference.new
-    lines.each{|line|
+    lines.each do |line|
       if line.first == :change_elt
-        before_change = Document.new(line[1].join,
-                                     doc1.encoding, doc1.eol)
-        after_change  = Document.new(line[2].join,
-                                     doc2.encoding, doc2.eol)
-        Difference.new(before_change.split_to_word,
-                       after_change.split_to_word).each{|word|
+        before_change = Document.new(line[1].join, doc1.encoding, doc1.eol)
+        after_change  = Document.new(line[2].join, doc2.encoding, doc2.eol)
+        Difference.new(before_change.split_to_word, after_change.split_to_word).each do |word|
           words << word
-        }
-      else  # :common_elt_elt, :del_elt, or :add_elt
+        end
+      else # :common_elt_elt, :del_elt, or :add_elt
         words << line
       end
-    }
+    end
     words
   end
 
@@ -65,32 +65,29 @@ class DocDiff
   def compare_by_line_word_char(doc1, doc2)
     lines = compare_by_line(doc1, doc2)
     lines_and_words = Difference.new
-    lines.each{|line|
+    lines.each do |line|
       if line.first == :change_elt
-        before_change = Document.new(line[1].join,
-                                     doc1.encoding, doc1.eol)
-        after_change  = Document.new(line[2].join,
-                                     doc2.encoding, doc2.eol)
-        Difference.new(before_change.split_to_word,
-                       after_change.split_to_word).each{|word|
+        before_change = Document.new(line[1].join, doc1.encoding, doc1.eol)
+        after_change  = Document.new(line[2].join, doc2.encoding, doc2.eol)
+        Difference.new(before_change.split_to_word, after_change.split_to_word).each do |word|
           lines_and_words << word
-        }
+        end
       else  # :common_elt_elt, :del_elt, or :add_elt
         lines_and_words << line
       end
-    }
+    end
     lines_words_and_chars = Difference.new
-    lines_and_words.each{|line_or_word|
+    lines_and_words.each do |line_or_word|
       if line_or_word.first == :change_elt
         before_change = Document.new(line_or_word[1].join, doc1.encoding, doc1.eol)
         after_change  = Document.new(line_or_word[2].join, doc2.encoding, doc2.eol)
-        Difference.new(before_change.split_to_char, after_change.split_to_char).each{|char|
+        Difference.new(before_change.split_to_char, after_change.split_to_char).each do |char|
           lines_words_and_chars << char
-        }
+        end
       else  # :common_elt_elt, :del_elt, or :add_elt
         lines_words_and_chars << line_or_word
       end
-    }
+    end
     lines_words_and_chars
   end
 
@@ -98,10 +95,10 @@ class DocDiff
     raise "option is nil" if option.nil?
     raise "option[:resolution] is nil" if option[:resolution].nil?
     raise "option[:format] is nil" if option[:format].nil?
-    case
-    when doc1.class == Document && doc2.class == Document # OK
-    when doc1.encoding != nil && doc2.encoding != nil     # OK
-    when doc1.encoding == doc2.encoding && doc1.eol == doc2.eol # OK
+
+    if doc1.class == Document && doc2.class == Document # OK
+    elsif !doc1.encoding.nil? && !doc2.encoding.nil? # OK
+    elsif doc1.encoding == doc2.encoding && doc1.eol == doc2.eol # OK
     else
       raise("Error!  Blame the author (doc1: #{doc1.encoding}, #{doc1.eol}, doc2: #{doc2.encoding}, #{doc2.eol}).")
     end
@@ -114,16 +111,18 @@ class DocDiff
       raise "Unsupported resolution: #{option[:resolution].inspect}"
     end
     view = View.new(difference, doc1.encoding, doc1.eol)
-    user_tags = {:start_common        => (@config[:tag_common_start] ||= ''),
-                 :end_common          => (@config[:tag_common_end] ||= ''),
-                 :start_del           => (@config[:tag_del_start] ||= ''),
-                 :end_del             => (@config[:tag_del_end] ||= ''),
-                 :start_add           => (@config[:tag_add_start] ||= ''),
-                 :end_add             => (@config[:tag_add_end] ||= ''),
-                 :start_before_change => (@config[:tag_change_before_start] ||= ''),
-                 :end_before_change   => (@config[:tag_change_before_end] ||= ''),
-                 :start_after_change  => (@config[:tag_change_after_start] ||= ''),
-                 :end_after_change    => (@config[:tag_change_after_end] ||= '')}
+    user_tags = {
+      start_common:        (@config[:tag_common_start] ||= ""),
+      end_common:          (@config[:tag_common_end] ||= ""),
+      start_del:           (@config[:tag_del_start] ||= ""),
+      end_del:             (@config[:tag_del_end] ||= ""),
+      start_add:           (@config[:tag_add_start] ||= ""),
+      end_add:             (@config[:tag_add_end] ||= ""),
+      start_before_change: (@config[:tag_change_before_start] ||= ""),
+      end_before_change:   (@config[:tag_change_before_end] ||= ""),
+      start_after_change:  (@config[:tag_change_after_start] ||= ""),
+      end_after_change:    (@config[:tag_change_after_end] ||= ""),
+    }
     case option[:digest]
     when true
       case option[:format]
@@ -150,4 +149,4 @@ class DocDiff
     end
     result.join
   end
-end  # class DocDiff
+end