docdiff 0.6.4 → 0.6.6

data/lib/docdiff/document.rb

@@ -1,129 +1,149 @@
 # Document class, a part of DocDiff
 # 2004-01-14.. Hisashi MORITA
 
-require 'docdiff/charstring'
+require "docdiff/charstring"
 
-class EncodingDetectionFailure < Exception
+class EncodingDetectionFailure < StandardError
 end
-class EOLDetectionFailure < Exception
+
+class EOLDetectionFailure < StandardError
 end
 
 class DocDiff
-class Document
-
-  def initialize(str, enc = nil, e = nil)
-    @body = str
-    @body.extend CharString
-    if enc
-      @body.encoding = enc
-    elsif !@body.encoding
-      guessed_encoding = CharString.guess_encoding(str)
-      if guessed_encoding == "UNKNOWN"
-        raise EncodingDetectionFailure, "encoding not specified, and auto detection failed."
+  class Document
+    def initialize(str, enc = nil, e = nil)
+      @body = str
+      @body.extend(CharString)
+      if enc
+        @body.encoding = enc
+      elsif !@body.encoding
+        guessed_encoding = CharString.guess_encoding(str)
+        if guessed_encoding == "UNKNOWN"
+          raise EncodingDetectionFailure, "encoding not specified, and auto detection failed."
         # @body.encoding = 'ASCII' # default to ASCII <= BAD!
-      else
-	@body.encoding = guessed_encoding
+        else
+          @body.encoding = guessed_encoding
+        end
       end
-    end
-    if e
-      @body.eol = e
-    else
-      guessed_eol = CharString.guess_eol(str)
-      if guessed_eol == "UNKNOWN"
-        raise EOLDetectionFailure, "eol not specified, and auto detection failed."
-        # @body.eol = 'LF' # default to LF
+      if e
+        @body.eol = e
       else
-        @body.eol = guessed_eol
+        guessed_eol = CharString.guess_eol(str)
+        if guessed_eol == "UNKNOWN"
+          raise EOLDetectionFailure, "eol not specified, and auto detection failed."
+        # @body.eol = 'LF' # default to LF
+        else
+          @body.eol = guessed_eol
+        end
       end
     end
-  end
-  def encoding()
-    @body.encoding
-  end
-  def encoding=(cs)
-    @body.encoding = cs
-  end
-  def eol()
-    @body.eol
-  end
-  def eol=(eolstr)
-    @body.eol = eolstr
-  end
 
-  def split_to_line()
-    @body.split_to_line
-  end
-  def split_to_word()
-    @body.split_to_word
-  end
-  def split_to_char()
-    @body.split_to_char
-  end
-  def split_to_byte()
-    @body.split_to_byte
-  end
+    def encoding
+      @body.encoding
+    end
 
-  def count_line()
-    @body.count_line
-  end
-  def count_blank_line()
-    @body.count_blank_line
-  end
-  def count_empty_line()
-    @body.count_empty_line
-  end
-  def count_graph_line()
-    @body.count_graph_line
-  end
+    def encoding=(cs)
+      @body.encoding = cs
+    end
 
-  def count_word()
-    @body.count_word
-  end
-  def count_latin_word()
-    @body.count_latin_word
-  end
-  def count_ja_word()
-    @body.count_ja_word
-  end
-  def count_valid_word()
-    @body.count_valid_word
-  end
-  def count_latin_valid_word()
-    @body.count_latin_valid_word
-  end
-  def count_ja_valid_word()
-    @body.count_ja_valid_word
-  end
+    def eol
+      @body.eol
+    end
 
-  def count_char()
-    @body.count_char
-  end
-  def count_blank_char()
-    @body.count_blank_char
-  end
-  def count_graph_char()
-    @body.count_graph_char
-  end
-  def count_latin_blank_char()
-    @body.count_latin_blank_char
-  end
-  def count_latin_graph_char()
-    @body.count_latin_graph_char
-  end
-  def count_ja_blank_char()
-    @body.count_ja_blank_char
-  end
-  def count_ja_graph_char()
-    @body.count_ja_graph_char
-  end
+    def eol=(eolstr)
+      @body.eol = eolstr
+    end
 
-  def count_byte()
-    @body.count_byte
-  end
+    def split_to_line
+      @body.split_to_line
+    end
 
-  def eol_char()
-    @body.eol_char
-  end
+    def split_to_word
+      @body.split_to_word
+    end
+
+    def split_to_char
+      @body.split_to_char
+    end
 
-end  # class Document
-end  # class DocDiff
+    def split_to_byte
+      @body.split_to_byte
+    end
+
+    def count_line
+      @body.count_line
+    end
+
+    def count_blank_line
+      @body.count_blank_line
+    end
+
+    def count_empty_line
+      @body.count_empty_line
+    end
+
+    def count_graph_line
+      @body.count_graph_line
+    end
+
+    def count_word
+      @body.count_word
+    end
+
+    def count_latin_word
+      @body.count_latin_word
+    end
+
+    def count_ja_word
+      @body.count_ja_word
+    end
+
+    def count_valid_word
+      @body.count_valid_word
+    end
+
+    def count_latin_valid_word
+      @body.count_latin_valid_word
+    end
+
+    def count_ja_valid_word
+      @body.count_ja_valid_word
+    end
+
+    def count_char
+      @body.count_char
+    end
+
+    def count_blank_char
+      @body.count_blank_char
+    end
+
+    def count_graph_char
+      @body.count_graph_char
+    end
+
+    def count_latin_blank_char
+      @body.count_latin_blank_char
+    end
+
+    def count_latin_graph_char
+      @body.count_latin_graph_char
+    end
+
+    def count_ja_blank_char
+      @body.count_ja_blank_char
+    end
+
+    def count_ja_graph_char
+      @body.count_ja_graph_char
+    end
+
+    def count_byte
+      @body.count_byte
+    end
+
+    def eol_char
+      @body.eol_char
+    end
+  end
+end

data/lib/docdiff/encoding/en_ascii.rb

@@ -1,72 +1,78 @@
 # English ASCII encoding module for CharString
 # 2003- Hisashi MORITA
 
-# frozen_string_literal: false
+# frozen_string_literal: true
 
 class DocDiff
-module CharString
-  module ASCII
+  module CharString
+    module ASCII
+      ENCODING = "US-ASCII"
 
-    Encoding = "US-ASCII"
+      CNTRL =
+        "\x00\x01\x02\x03\x04\x05\x06\x07\x08\x09" \
+          "\x0a\x0b\x0c\x0d\x0e\x0f\x10\x11\x12\x13" \
+          "\x14\x15\x16\x17\x18\x19\x1a\x1b\x1c\x1d" \
+          "\x1e\x1f\x7f"
+      SPACE =
+        "\x09\x0a\x0b\x0c\x0d\x20"
+      BLANK =
+        "\x09\x20"
+      DIGIT =
+        "\x30\x31\x32\x33\x34\x35\x36\x37\x38\x39"
+      UPPER =
+        "\x41\x42\x43\x44\x45\x46\x47\x48\x49\x4a" \
+          "\x4b\x4c\x4d\x4e\x4f\x50\x51\x52\x53\x54" \
+          "\x55\x56\x57\x58\x59\x5a"
+      LOWER =
+        "\x61\x62\x63\x64\x65\x66\x67\x68\x69\x6a" \
+          "\x6b\x6c\x6d\x6e\x6f\x70\x71\x72\x73\x74" \
+          "\x75\x76\x77\x78\x79\x7a"
+      ALPHA = UPPER + LOWER
+      ALNUM = DIGIT + ALPHA
+      PUNCT =
+        Regexp.quote(
+          "\x21\x22\x23\x24\x25\x26\x27\x28\x29\x2a" \
+            "\x2b\x2c\x2d\x2e\x2f\x3a\x3b\x3c\x3d\x3e" \
+            "\x3f\x40\x5b\x5c\x5d\x5e\x5f\x60\x7b\x7c" \
+            "\x7d\x7e",
+        )
+      GRAPH = DIGIT + UPPER + LOWER + PUNCT
+      PRINT = "\x20" + GRAPH
+      XDIGIT =
+        DIGIT +
+        "\x41\x42\x43\x44\x45\x46\x61\x62\x63\x64" \
+          "\x65\x66"
 
-    CNTRL =     "\x00\x01\x02\x03\x04\x05\x06\x07\x08\x09" \
-                "\x0a\x0b\x0c\x0d\x0e\x0f\x10\x11\x12\x13" \
-                "\x14\x15\x16\x17\x18\x19\x1a\x1b\x1c\x1d" \
-                "\x1e\x1f\x7f"
-    SPACE =     "\x09\x0a\x0b\x0c\x0d\x20"
-    BLANK =     "\x09\x20"
-    DIGIT =     "\x30\x31\x32\x33\x34\x35\x36\x37\x38\x39"
-    UPPER =     "\x41\x42\x43\x44\x45\x46\x47\x48\x49\x4a" \
-                "\x4b\x4c\x4d\x4e\x4f\x50\x51\x52\x53\x54" \
-                "\x55\x56\x57\x58\x59\x5a"
-    LOWER =     "\x61\x62\x63\x64\x65\x66\x67\x68\x69\x6a" \
-                "\x6b\x6c\x6d\x6e\x6f\x70\x71\x72\x73\x74" \
-                "\x75\x76\x77\x78\x79\x7a"
-    ALPHA =     UPPER + LOWER
-    ALNUM =     DIGIT + ALPHA
-    PUNCT =     "\x21\x22\x23\x24\x25\x26\x27\x28\x29\x2a" \
-                "\x2b\x2c\x2d\x2e\x2f\x3a\x3b\x3c\x3d\x3e" \
-                "\x3f\x40\x5b\x5c\x5d\x5e\x5f\x60\x7b\x7c" \
-                "\x7d\x7e"
-    GRAPH =     DIGIT + UPPER + LOWER + PUNCT
-    PRINT =     "\x20" + GRAPH
-    XDIGIT =    DIGIT +
-                "\x41\x42\x43\x44\x45\x46\x61\x62\x63\x64" \
-                "\x65\x66"
+      JA_BLANK = "" # kludge...
+      JA_GRAPH = "" # kludge...
 
-    JA_BLANK =  "" # kludge...
-    JA_GRAPH =  "" # kludge...
+      WORD_REGEXP_SRC = [
+        "(?:[#{GRAPH}]+[#{BLANK}]?)",
+        "|(?:[#{SPACE}]+)",
+        "|(?:.+?)",
+      ].join
 
-    PUNCT.replace(Regexp.quote(PUNCT)) # kludge to avoid warning "character class has `[' without escape"
-    PRINT.replace(Regexp.quote(PRINT)) # kludge to avoid warning "character class has `[' without escape"
-    GRAPH.replace(Regexp.quote(GRAPH)) # kludge to avoid warning "character class has `[' without escape"
+      # override default method, as ASCII has no Japanese in it
+      def count_ja_graph_char
+        0
+      end
 
-    WORD_REGEXP_SRC = ["(?:[#{GRAPH}]+[#{BLANK}]?)", 
-                       "|(?:[#{SPACE}]+)", 
-                       "|(?:.+?)"].join
+      # override default method, as ASCII has no Japanese in it
+      def count_ja_blank_char
+        0
+      end
 
-    # override default method, as ASCII has no Japanese in it
-    def count_ja_graph_char()
-      0
-    end
-
-    # override default method, as ASCII has no Japanese in it
-    def count_ja_blank_char()
-      0
-    end
+      # override default method, as ASCII has no Japanese in it
+      def count_ja_word
+        0
+      end
 
-    # override default method, as ASCII has no Japanese in it
-    def count_ja_word()
-      0
-    end
+      # override default method, as ASCII has no Japanese in it
+      def count_ja_valid_word
+        0
+      end
 
-    # override default method, as ASCII has no Japanese in it
-    def count_ja_valid_word()
-      0
+      CharString.register_encoding(self)
     end
-
-    CharString.register_encoding(self)
-
-  end  # module ASCII
-end  # module CharString
-end  # class DocDiff
+  end
+end