docdiff 0.6.7 → 0.7.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: a0780c057df7a736c77e7e4b3542a18a1ce9335140c1ef141885b1acb06d1b12
-  data.tar.gz: f479c7a739f14c5c3b78d0d5078515982ceb3f61a40c23ec96f5803b4865e837
+  metadata.gz: e84a8c85103e65839c20b2b36b98c2d2991f1f21135a8742da68d130c6dd4290
+  data.tar.gz: 76fde0a2c869bf96b5688d4917e3aa9cadffb44c6b67bcc1c9eb2939a44aecc3
 SHA512:
-  metadata.gz: 6dfa6dd69a1d3e5f4cdb7024c66a628090a9cbce23c7486471e1cd0f3cf242edb6485628218205b0ab2f5e8a8357b551f97a8c12db6c10aa25e844f406f8e19c
-  data.tar.gz: cefeb857d6939c609a13d620a16c2db8db43d1c86a140ebb65a4d2c73a20be3023be0333821d13fc1b42c0a63f550229d2e8890f97fdfae5cb3decc94d0ae11c
+  metadata.gz: cdf66ad98c6047d4a6a858762d79ed1569f21e65401ad2dcfc3a791828cd0407fc5c9411efb567796ddf0f3d45e38bdd68a6739060c7612b9290b111cbced1bd
+  data.tar.gz: 7848047f1904a90934b4bffd4b7539b14380c995af379a3874af1d92bf0ffb145fd4e976567e2fab6a6f167816698415c5c1094e824923a2c236b1d747c27fe9

data/README.md

@@ -1,6 +1,6 @@
 # DocDiff
 
-* English | [Japanese](README_ja.md)
+* English / [Japanese](README_ja.md)
 
 (C) 2000 Hisashi MORITA
 
@@ -10,42 +10,21 @@ Compares two text files by word, by character, or by line
 
 ## Screenshots
 
-<div style="display: grid; grid-template-columns: 1fr 1fr;">
+<p>TTY output<br />
+<img src="doc/img/screenshot-tty-en-ja.png" alt="TTY output"/></p>
 
 <p>HTML output<br />
-<img src="doc/img/screenshot-format-html-firefox.png" alt="HTML output"/></p>
+<img src="doc/img/screenshot-html.png" alt="HTML output"/></p>
 
-<p>HTML output (digest)<br />
-<img src="doc/img/screenshot-format-html-digest-firefox.png" alt="HTML output (digest)" /></p>
+<p>Comparison by character<br />
+<img src="doc/img/screenshot-tty-char.png" alt="Comparison by character"/></p>
 
-<p>tty output<br />
-<img src="doc/img/screenshot-format-tty-rxvtunicode-en.png" alt="tty output" /></p>
-
-<p>tty output (comparing Japanese text)<br />
-<img src="doc/img/screenshot-format-tty-rxvtunicode-ja.png" alt="tty output (comparing Japanese text)" /></p>
-
-<p>tty output<br />
-<img src="doc/img/screenshot-format-tty-xterm-en.png" alt="tty output" /></p>
-
-<p>tty output (comparing Japanese text)<br />
-<img src="doc/img/screenshot-format-tty-xterm-ja.png" alt="tty output (comparing Japanese text)" /></p>
-
-</div>
-
-<p>Comparing English text (codepage 437) on Windows (Cygwin)<br />
-<img src="doc/img/screenshot-format-tty-cmdexe-en.png" alt="Comparing English text (codepage 437) on Windows (Cygwin)" /></p>
-
-<p>Comparing Japanese text (codepage 932) on Windows (Cygwin)<br />
-<img src="doc/img/screenshot-format-tty-cmdexe-ja.png" alt="Comparing Japanese text (codepage 932) on Windows (Cygwin)" /></p>
-
-<p>You can compare text files by line, word, or character (format: tty)<br/>
-<img src="doc/img/screenshot-resolution-linewordchar-xterm.png" alt="You can compare text files by line, word, or character (format: tty)" /></p>
-
-(Screenshots as of version 0.3.2.)
+<p>Digest mode (useful for viewing scattered changes within a long text)<br />
+<img src="doc/img/screenshot-tty-digest-license.png" alt="Digest mode"/></p>
 
 ## Summary
 
-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.
+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 TTY, HTML, Manued, or user-defined markup.
 
 It supports several encodings and end-of-line characters, including ASCII (and other single byte encodings such as ISO-8859-*), UTF-8, EUC-JP, Shift_JIS (Windows-31J), CR, LF, and CRLF.
 
@@ -54,17 +33,71 @@ It supports several encodings and end-of-line characters, including ASCII (and o
 ### Synopsis
 
 ```
-$ docdiff [options] oldfile newfile
+$ docdiff [options] file1 file2
 ```
 
-e.g.
+Type `docdiff --help` to show command line options.
+
+### Options
 
 ```
-$ docdiff old.txt new.txt > diff.html
+docdiff [options] file1 file2
+      --resolution=RESOLUTION
+                       specify resolution (granularity)
+                       line|word|char (default: word)
+      --line           same as --resolution=line
+      --word           same as --resolution=word
+      --char           same as --resolution=char
+      --encoding=ENCODING
+                       specify character encoding
+                       ASCII|EUC-JP|Shift_JIS|CP932|UTF-8|auto (default: auto)
+                       (try ASCII for single byte encodings such as ISO-8859)
+      --ascii          same as --encoding=ASCII
+      --iso8859        same as --encoding=ASCII
+      --iso8859x       same as --encoding=ASCII (deprecated)
+      --eucjp          same as --encoding=EUC-JP
+      --sjis           same as --encoding=Shift_JIS
+      --cp932          same as --encoding=CP932
+      --utf8           same as --encoding=UTF-8
+      --eol=EOL        specify end-of-line character
+                       CR|LF|CRLF|auto (default: auto)
+      --cr             same as --eol=CR
+      --lf             same as --eol=LF
+      --crlf           same as --eol=CRLF
+      --format=FORMAT  specify output format
+                       tty|manued|html|wdiff|stat|user (default: tty)
+                       (stat is deprecated)
+                       (user tags can be defined in configuration file)
+      --tty            same as --format=tty
+      --manued         same as --format=manued
+      --html           same as --format=html
+      --wdiff          same as --format=wdiff
+      --stat           same as --format=stat (not implemented) (deprecated)
+  -L, --label LABEL    use label instead of file name
+                       (not implemented; exists for compatibility with diff)
+      --digest         digest output, do not show all
+      --summary        same as --digest
+      --display=DISPLAY
+                       specify presentation type (effective only with digest)
+                       inline|block|multi (default: inline)
+                       (experimental feature) (multi is deprecated)
+      --cache          use file cache (not implemented) (deprecated)
+      --pager=PAGER    specify pager
+                       (falls back to $DOCDIFF_PAGER, $PAGER, or none)
+      --no-pager       do not use pager
+      --config-file=FILE
+                       specify configuration file to read
+      --no-config-file do not read configuration files
+      --verbose        run verbosely (not well-supported) (deprecated)
+      --help           show help message
+      --version        show version
+      --license        show license (deprecated)
+      --author         show author(s) (deprecated)
+When invoked as worddiff or chardiff, resolution will be set accordingly.
+Configuration files: /etc/docdiff/docdiff.conf, ~/.config/docdiff/docdiff.conf,
+or ~/etc/docdiff/docdiff.conf (deprecated)
 ```
 
-See the help message for detail (`docdiff --help`).
-
 ### Example
 
 <pre>
@@ -333,7 +366,7 @@ Excuse us this list is far from complete and fails to acknowledge many more who
 ### Formats
 
 * [HTML/XHTML](https://www.w3.org/)
-* tty (Graphic rendition using VT100 / ANSI escape sequences)
+* TTY (Graphic rendition using VT100 / ANSI escape sequences)
   - [VT100](https://vt100.net/docs/tp83/appendixb.html)
   - [ANSI](https://tldp.org/HOWTO/Bash-Prompt-HOWTO/x329.html)
 * [Manued](https://sundayresearch.eu/hitoshi/otherprojects/manued/) ([in Japanese](https://sundayresearch.eu/hitoshi/otherprojects/manued/index-j.html)) (Manuscript Editing Language: a proofreading method for text)

data/README_ja.md

@@ -1,6 +1,6 @@
 # DocDiff
 
-* [English](README.md) | Japanese
+* [English](README.md) / Japanese
 
 (C) 2000 Hisashi MORITA
 
@@ -10,42 +10,21 @@
 
 ## スクリーンショット
 
-<div style="display: grid; grid-template-columns: 1fr 1fr;">
+<p>TTY出力<br />
+<img src="doc/img/screenshot-tty-en-ja.png" alt="TTY output"/></p>
 
 <p>HTML出力<br />
-<img src="doc/img/screenshot-format-html-firefox.png" alt="HTML output"/></p>
+<img src="doc/img/screenshot-html.png" alt="HTML output"/></p>
 
-<p>HTML出力（ダイジェスト）<br />
-<img src="doc/img/screenshot-format-html-digest-firefox.png" alt="HTML output (digest)" /></p>
+<p>文字ごとの比較<br />
+<img src="doc/img/screenshot-tty-char.png" alt="Comparison by character"/></p>
 
-<p>tty出力<br />
-<img src="doc/img/screenshot-format-tty-rxvtunicode-en.png" alt="tty output" /></p>
-
-<p>tty出力（日本語のテキストを比較）<br />
-<img src="doc/img/screenshot-format-tty-rxvtunicode-ja.png" alt="tty output (comparing Japanese text)" /></p>
-
-<p>tty出力<br />
-<img src="doc/img/screenshot-format-tty-xterm-en.png" alt="tty output" /></p>
-
-<p>tty出力（日本語のテキストを比較）<br />
-<img src="doc/img/screenshot-format-tty-xterm-ja.png" alt="tty output (comparing Japanese text)" /></p>
-
-</div>
-
-<p>英語のテキスト（コードページ437）を比較（Windows上のCygwin環境）<br />
-<img src="doc/img/screenshot-format-tty-cmdexe-en.png" alt="Comparing English text (codepage 437) on Windows (Cygwin)" /></p>
-
-<p>日本語のテキスト（コードページ937）を比較（Windows上のCygwin環境）<br />
-<img src="doc/img/screenshot-format-tty-cmdexe-ja.png" alt="Comparing Japanese text (codepage 932) on Windows (Cygwin)" /></p>
-
-<p>行ごと、単語ごと、文字ごとの比較が可能（フォーマットはtty）<br/>
-<img src="doc/img/screenshot-resolution-linewordchar-xterm.png" alt="You can compare text files by line, word, or character (format: tty)" /></p>
-
-（バージョン0.3.2時点のスクリーンショットです。）
+<p>ダイジェストモード（長いテキスト中に散らばった変更点を確認するのに便利）<br />
+<img src="doc/img/screenshot-tty-digest-license.png" alt="Digest mode"/></p>
 
 ## 概要
 
-DocDiffは2つのテキストファイルを比較してその違いを表示します。単語ごと、文字ごと、そして行ごとにファイルを比較できます。結果を出力する形式は、HTML、tty（文字端末向けのエスケープシーケンス）、Manued（真鵺道という校正用のマークアップ形式）などが用意されており、ユーザ定義のタグを使うこともできます。
+DocDiffは2つのテキストファイルを比較してその違いを表示します。単語ごと、文字ごと、そして行ごとにファイルを比較できます。結果を出力する形式は、TTY（文字端末向けのエスケープシーケンス）、HTML、Manued（真鵺道という校正用のマークアップ形式）などが用意されており、ユーザ定義のタグを使うこともできます。
 
 次のエンコーディング（文字コード）と行末コード（改行文字）をサポートしています: ASCII（およびISO-8859-*などのシングルバイトエンコーディング）、UTF-8、EUC-JP、Shift_JIS（Windows-31J）、そしてCR、LF、CRLF。
 
@@ -54,18 +33,72 @@ DocDiffは2つのテキストファイルを比較してその違いを表示し
 ### 概要
 
 ```
-$ docdiff [options] oldfile newfile
+$ docdiff [options] file1 file2
 ```
 
-e.g.
+コマンドラインオプションについては、`docdiff --help`で出力されるヘルプメッセージを参照してください。
+
+### コマンドラインオプション
 
 ```
-$ docdiff old.txt new.txt > diff.html
+docdiff [options] file1 file2
+      --resolution=RESOLUTION
+                       specify resolution (granularity)
+                       line|word|char (default: word)
+      --line           same as --resolution=line
+      --word           same as --resolution=word
+      --char           same as --resolution=char
+      --encoding=ENCODING
+                       specify character encoding
+                       ASCII|EUC-JP|Shift_JIS|CP932|UTF-8|auto (default: auto)
+                       (try ASCII for single byte encodings such as ISO-8859)
+      --ascii          same as --encoding=ASCII
+      --iso8859        same as --encoding=ASCII
+      --iso8859x       same as --encoding=ASCII (deprecated)
+      --eucjp          same as --encoding=EUC-JP
+      --sjis           same as --encoding=Shift_JIS
+      --cp932          same as --encoding=CP932
+      --utf8           same as --encoding=UTF-8
+      --eol=EOL        specify end-of-line character
+                       CR|LF|CRLF|auto (default: auto)
+      --cr             same as --eol=CR
+      --lf             same as --eol=LF
+      --crlf           same as --eol=CRLF
+      --format=FORMAT  specify output format
+                       tty|manued|html|wdiff|stat|user (default: tty)
+                       (stat is deprecated)
+                       (user tags can be defined in configuration file)
+      --tty            same as --format=tty
+      --manued         same as --format=manued
+      --html           same as --format=html
+      --wdiff          same as --format=wdiff
+      --stat           same as --format=stat (not implemented) (deprecated)
+  -L, --label LABEL    use label instead of file name
+                       (not implemented; exists for compatibility with diff)
+      --digest         digest output, do not show all
+      --summary        same as --digest
+      --display=DISPLAY
+                       specify presentation type (effective only with digest)
+                       inline|block|multi (default: inline)
+                       (experimental feature) (multi is deprecated)
+      --cache          use file cache (not implemented) (deprecated)
+      --pager=PAGER    specify pager
+                       (falls back to $DOCDIFF_PAGER, $PAGER, or none)
+      --no-pager       do not use pager
+      --config-file=FILE
+                       specify configuration file to read
+      --no-config-file do not read configuration files
+      --verbose        run verbosely (not well-supported) (deprecated)
+      --help           show help message
+      --version        show version
+      --license        show license (deprecated)
+      --author         show author(s) (deprecated)
+When invoked as worddiff or chardiff, resolution will be set accordingly.
+Configuration files: /etc/docdiff/docdiff.conf, ~/.config/docdiff/docdiff.conf,
+or ~/etc/docdiff/docdiff.conf (deprecated)
 ```
 
-詳しくはヘルプメッセージを参照してください（`docdiff --help`）。
-
-### 例
+### 実行例
 
 <pre>
 $ cat 01_ja_eucjp_lf.txt
@@ -333,7 +366,7 @@ Diffライブラリ（`lib/docdiff/diff.rb`および`lib/docdiff/diff/*`）は
 ### フォーマット
 
 * [HTML/XHTML](https://www.w3.org/)
-* tty (Graphic rendition using VT100 / ANSI escape sequences)
+* TTY (Graphic rendition using VT100 / ANSI escape sequences)
   - [VT100](https://vt100.net/docs/tp83/appendixb.html)
   - [ANSI](https://tldp.org/HOWTO/Bash-Prompt-HOWTO/x329.html)
 * [Manued](https://sundayresearch.eu/hitoshi/otherprojects/manued/) ([in Japanese](https://sundayresearch.eu/hitoshi/otherprojects/manued/index-j.html)) (Manuscript Editing Language: a proofreading method for text)

data/doc/example/docdiff.conf.example

@@ -21,3 +21,6 @@
 # tag_change_before_end   = '</!->'
 # tag_change_after_start  = '<!+>'
 # tag_change_after_end    = '</!+>'
+#
+## set default output format to html
+# format = html

data/doc/man/docdiff.adoc

@@ -12,7 +12,7 @@ docdiff - character/word-oriented diff
 
 Compares two text files by word, by character, or by line
 
-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.
+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 tty, HTML, Manued, or user-defined markup.
 
 It supports several encodings and end-of-line characters, including ASCII (and other single byte encodings such as ISO-8859-*), UTF-8, EUC-JP, Shift_JIS (Windows-31J), CR, LF, and CRLF.
 
@@ -72,7 +72,7 @@ It supports several encodings and end-of-line characters, including ASCII (and o
 
 *--format*=FORMAT::
   specify output format
-  _tty_|_manued_|_html_|_wdiff_|_stat_|_user_ (default: _html_) (_stat_ is deprecated)
+  _tty_|_manued_|_html_|_wdiff_|_stat_|_user_ (default: _tty_) (_stat_ is deprecated)
   (user tags can be defined in config file)
 
 *--tty*::
@@ -107,7 +107,7 @@ It supports several encodings and end-of-line characters, including ASCII (and o
   use file cache (not implemented) (deprecated)
 
 *--pager*=PAGER::
-  specify pager (if available, $_DOCDIFF_PAGER_ is used by default)
+  specify pager (if available, $_DOCDIFF_PAGER_ or $_PAGER_ is used by default)
 
 *--no-pager*::
   do not use pager

data/doc/news.md

@@ -1,5 +1,16 @@
 # News
 
+### 0.7.0 (2026-04-05)
+
+* User-visible changes:
+  - Default output format changed from html to tty. (breaking change)
+    - If you prefer the old behaviour, add `format = html` to your configuration file (e.g. `~/.config/docdiff/docdiff.conf`).
+  - Enabled automatic pager activation via `$PAGER`. (breaking change)
+  - Changed line number format in digest mode to `L1, L1` and `(L1), LL1-2` (previously `1,1` and `(1),1-2`). (somewhat breaking change)
+  - Updated screenshots in README.
+* Developer-related changes:
+  - Renamed methods: `split_to_foo` to `to_foo`, `line` to `lines`, etc.
+
 ### 0.6.7 (2026-02-25)
 
 * User-visible changes:

data/docdiff.gemspec

@@ -15,7 +15,7 @@ Gem::Specification.new do |s|
     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,
+    several output formats such as tty, HTML, Manued,
     or user-defined markup.
   EOS
 

data/lib/doc_diff.rb

@@ -28,7 +28,7 @@ class DocDiff
     resolution: "word",
     encoding: "auto",
     eol: "auto",
-    format: "html",
+    format: "tty",
     cache: true,
     digest: false,
     pager: nil,
@@ -41,7 +41,7 @@ class DocDiff
   attr_accessor :config
 
   def compare_by_line(doc1, doc2)
-    Difference.new(doc1.split_to_line, doc2.split_to_line)
+    Difference.new(doc1.to_lines, doc2.to_lines)
   end
 
   def compare_by_line_word(doc1, doc2)
@@ -51,7 +51,7 @@ class DocDiff
       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 do |word|
+        Difference.new(before_change.to_words, after_change.to_words).each do |word|
           words << word
         end
       else # :common_elt_elt, :del_elt, or :add_elt
@@ -69,7 +69,7 @@ class DocDiff
       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 do |word|
+        Difference.new(before_change.to_words, after_change.to_words).each do |word|
           lines_and_words << word
         end
       else  # :common_elt_elt, :del_elt, or :add_elt
@@ -81,7 +81,7 @@ class DocDiff
       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 do |char|
+        Difference.new(before_change.to_chars, after_change.to_chars).each do |char|
           lines_words_and_chars << char
         end
       else  # :common_elt_elt, :del_elt, or :add_elt

data/lib/docdiff/charstring.rb

@@ -97,36 +97,36 @@ class DocDiff
     # Note that some languages (like Japanese) do not have 'word' or 'phrase',
     # thus some of the following methods are not 'linguistically correct'.
 
-    def count_byte
-      split_to_byte.size
+    def count_bytes
+      to_bytes.size
     end
 
-    def count_char  # eol = 1 char
-      split_to_char.size
+    def count_chars  # eol = 1 char
+      to_chars.size
     end
 
-    def count_graph_char
-      count_latin_graph_char + count_ja_graph_char
+    def count_graph_chars
+      count_latin_graph_chars + count_ja_graph_chars
     end
 
-    def count_blank_char
-      count_latin_blank_char + count_ja_blank_char
+    def count_blank_chars
+      count_latin_blank_chars + count_ja_blank_chars
     end
 
-    def count_word
-      split_to_word.size
+    def count_words
+      to_words.size
     end
 
-    def count_valid_word
-      count_latin_valid_word + count_ja_valid_word
+    def count_valid_words
+      count_latin_valid_words + count_ja_valid_words
     end
 
-    def count_line  # this is common to all encodings.
-      split_to_line.size
+    def count_lines  # this is common to all encodings.
+      to_lines.size
     end
 
-    def count_empty_line
-      split_to_line.count { |line| /^(?:#{eol_char})|^$/m.match(line) }
+    def count_empty_lines
+      to_lines.count { |line| /^(?:#{eol_char})|^$/m.match(line) }
     end
 
     # for Ruby-1.9
@@ -146,11 +146,11 @@ class DocDiff
       end
     end
 
-    def split_to_byte
+    def to_bytes
       encode("ASCII-8BIT").scan(/./nm)
     end
 
-    def split_to_char
+    def to_chars
       re =
         if eol_char # sometimes string has no end-of-line char
           Regexp.new("(?:#{eol_char})|(?:.)", Regexp::MULTILINE)
@@ -160,52 +160,52 @@ class DocDiff
       encode("UTF-8").scan(re).map { |e| e.encode(encoding) }
     end
 
-    def count_latin_graph_char
+    def count_latin_graph_chars
       re = Regexp.new("[#{Encodings["UTF-8"]::GRAPH}]", Regexp::MULTILINE)
       encode("UTF-8").scan(re).size
     end
 
-    def count_ja_graph_char
+    def count_ja_graph_chars
       re = Regexp.new("[#{Encodings["UTF-8"]::JA_GRAPH}]", Regexp::MULTILINE)
       encode("UTF-8").scan(re).size
     end
 
-    def count_latin_blank_char
+    def count_latin_blank_chars
       re = Regexp.new("[#{Encodings["UTF-8"]::BLANK}]", Regexp::MULTILINE)
       encode("UTF-8").scan(re).size
     end
 
-    def count_ja_blank_char
+    def count_ja_blank_chars
       re = Regexp.new("[#{Encodings["UTF-8"]::JA_BLANK}]", Regexp::MULTILINE)
       encode("UTF-8").scan(re).size
     end
 
-    def split_to_word
+    def to_words
       re = Regexp.new(Encodings["UTF-8"]::WORD_REGEXP_SRC, Regexp::MULTILINE)
       encode("UTF-8").scan(re).map { |e| e.encode(encoding) }
     end
 
-    def count_latin_word
+    def count_latin_words
       re = Regexp.new("[#{Encodings["UTF-8"]::PRINT}]", Regexp::MULTILINE)
-      split_to_word.count { |word| re.match(word.encode("UTF-8")) }
+      to_words.count { |word| re.match(word.encode("UTF-8")) }
     end
 
-    def count_ja_word
+    def count_ja_words
       re = Regexp.new("[#{Encodings["UTF-8"]::JA_PRINT}]", Regexp::MULTILINE)
-      split_to_word.count { |word| re.match(word.encode("UTF-8")) }
+      to_words.count { |word| re.match(word.encode("UTF-8")) }
     end
 
-    def count_latin_valid_word
+    def count_latin_valid_words
       re = Regexp.new("[#{Encodings["UTF-8"]::ALNUM}]", Regexp::MULTILINE)
-      split_to_word.count { |word| re.match(word.encode("UTF-8")) }
+      to_words.count { |word| re.match(word.encode("UTF-8")) }
     end
 
-    def count_ja_valid_word
+    def count_ja_valid_words
       re = Regexp.new("[#{Encodings["UTF-8"]::JA_GRAPH}]", Regexp::MULTILINE)
-      split_to_word.count { |word| re.match(word.encode("UTF-8")) }
+      to_words.count { |word| re.match(word.encode("UTF-8")) }
     end
 
-    def split_to_line
+    def to_lines
       raise <<~EOS.chomp unless EOLChars[eol]
         EOLChars[eol] is #{EOLChars[eol].inspect}: eol not specified or auto-detection failed.
       EOS
@@ -219,16 +219,16 @@ class DocDiff
       encode("UTF-8").scan(re).map { |e| e.encode(encoding) }
     end
 
-    def count_graph_line
+    def count_graph_lines
       graph = (Encodings["UTF-8"]::GRAPH + Encodings["UTF-8"]::JA_GRAPH).chars.uniq.join
       re = Regexp.new("[#{Regexp.quote(graph)}]", Regexp::MULTILINE)
-      split_to_line.count { |line| re.match(line.encode("UTF-8")) }
+      to_lines.count { |line| re.match(line.encode("UTF-8")) }
     end
 
-    def count_blank_line
+    def count_blank_lines
       blank = (Encodings["UTF-8"]::BLANK + Encodings["UTF-8"]::JA_BLANK).chars.uniq.join
       re = Regexp.new("^[#{blank}]+(?:#{eol_char})?", Regexp::MULTILINE)
-      split_to_line.count { |line| re.match(line.encode("UTF-8")) }
+      to_lines.count { |line| re.match(line.encode("UTF-8")) }
     end
 
     # load encoding modules
@@ -236,10 +236,6 @@ class DocDiff
     require "docdiff/encoding/ja_eucjp"
     require "docdiff/encoding/ja_sjis"
     require "docdiff/encoding/ja_utf8"
-    alias_method :to_bytes, :split_to_byte
-    alias_method :to_chars, :split_to_char
-    alias_method :to_words, :split_to_word
-    alias_method :to_lines, :split_to_line
 
     module CR
       EOL = "CR"