plain_text 0.2 → 0.3

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 2c015ed947812371558456375c2933f0d03720082899f8c58c699419eda77f1b
-  data.tar.gz: fafc479d9bb492bd3b3ad140ec7a58d2cc0e7bc49dec4ad80c4111ad1f63e3df
+  metadata.gz: e93dc475c0c5f66817fbe63e6824f1ec9d1a36c487126548eec0dead4dfde3f4
+  data.tar.gz: e7e64d6aa8dd28ea282cd11f0bfc7d0a55476735ec9b6e7db7a638a48e0457d8
 SHA512:
-  metadata.gz: cb7d054e24cc85c64bbb556d4de30b3b54c9b51b409519d9b7f307fbe64dc05dc32e6e7cbeccc027b41c842a31ec5b489e60801b1c1c1f72e587157f62f38391
-  data.tar.gz: aef2b0ebd0c69f694c438cbf8d8e62d6d754d92c5d804553649c681d6c088bd9bb363197d9fb209b184aa49fb44ef5e733268e1d53a19bc7dfef260c86dee88c
+  metadata.gz: e877ab86109aaf3078990ae1ac55f534026ae8ff941f22af38e39d6655356ed9b5a1f69d4d1f7cfc05efcf812e29efe185dba94e97db88c5383d49eb6b487579
+  data.tar.gz: c2cbd7f86fd1779ab0cd18136a44680f58fce87f3c9c8068e8ef7a5c049ed40d47f2a0614f169902780a9a362a0a6bf46fee7f626ef74cf94fb2425266bac1a1

data/ChangeLog

@@ -1,3 +1,19 @@
+-----
+(Version: 0.3)
+2019-10-27  Masa Sakano
+  * Added 3 executables textclean, head.rb, tail.rb in bin/ together with their tests
+  * lib/plaintext.rb refactoring
+    * Added a new constant `DEF_METHOD_OPTS`
+  * bin/countchar refactoring
+
+-----
+(Version: 0.3)
+2019-10-27  Masa Sakano
+  * Added 3 executables textclean, head.rb, tail.rb in bin/ together with their tests
+  * lib/plaintext.rb refactoring
+    * Added a new constant `DEF_METHOD_OPTS`
+  * bin/countchar refactoring
+
 -----
 (Version: 0.2)
 2019-10-27  Masa Sakano

data/README.en.rdoc

@@ -7,8 +7,9 @@ This module provides utility functions and methods to handle plain
 text.  In the namespace, classes Part/Paragraph/Boundary are defined,
 which represent the logical structure of a document and another class
 ParseRule, which describes the rules to parse plain text to produce a Part-type Ruby instance.
-This package also provides a command-line program to count the number
-of characters, especially useful for documents in Asian (CJK) chatacters.
+This package also provides a few command-line programs, such as counting the number
+of characters (especially useful for documents in Asian (CJK)
+chatacters) and advanced head/tail commands.
 
 == Design concept
 
@@ -93,7 +94,10 @@ it is applied to each Paragraph and Section separately to split them further.
 standard methods to apply the rules to an object (either String or
 {PlainText::Part}.
 
-== Command-line tool
+== Command-line tools
+
+All the commands here accept +-h+ (or +--help+) option to print the
+help message.
 
 === countchar 
 
@@ -102,9 +106,54 @@ Counts the number of characters in a file(s) or STDIN.
 The simplest example to run the command-line script is
    countchar YourFile.txt
 
-You may start with
-   countchar --help
-to see the available options.
+=== textclean
+
+Wrapper command of {PlainText.clean_text}.
+Outputs *cleaned* text, such as, truncating more than 3 linebreaks
+into 2.  See the reference of {PlainText.clean_text} for detail.
+
+=== head.rb
+
+This gives advanced functions, in addition to the standard +head+, including
+
+Regexp:: It can accept Ruby Regexp to determine the boundary (beginning to the first-matched line).
+Character-based:: With +--char+ option, it handles the file in units of a chracter, which is especially handy to deal with multi-byte characters like UTF-8.
+Inverse:: It can inverse the counting to ouput everything but initial NUM lines.
+
+A few examples are
+
+  head.rb -n 5 < try.txt
+    # the same as the UNIX head; printing the first 5 lines
+  
+  head.rb -i -n 5 try.txt
+    # printing everything but the first 5 lines
+    # The same as the UNIX command:  tail -n +5
+  
+  head.rb -e '^===+' try.txt
+    # => first line up to the line that begins with more than 3 "="
+  
+  head.rb -x -e '^===+' try.txt
+    # => first line up to the line before what begins with more than 3 "="
+
+The suffix +.rb+ is used to distinguish this command from the UNIX-shell standard command.
+
+=== tail.rb
+
+This gives advanced functions, in addition to the standard +tail+, including
+
+Regexp:: It can accept Ruby Regexp to determine the boundary (last-matched line to the end).
+Character-based:: With +--char+ option, it handles the file in units of a chracter, which is especially handy to deal with multi-byte characters like UTF-8.
+Inverse:: It can inverse the counting to ouput everything but the last NUM lines.
+
+Note the UNIX form of
+
+  tail -n +5
+
+(which I think is a bit counter-intuieive format) is equivalent to
+
+  head.rb -i -n 5
+
+The suffix +.rb+ is used to distinguish this command from the UNIX-shell standard command.
 
 == Miscellaneous
 
@@ -119,13 +168,13 @@ sent by a String instance +s+ = +"XQabXXcXQ"+:
     s.split(/X+Q?/)         #=> ["", "ab", "c"],                   
     s.split(/X+Q?/, -1)     #=> ["", "ab", "c", ""],               
     s.split(/X+(Q?)/, -1)   #=> ["", "Q", "ab", "", "c", "Q", ""], 
-    s.split(/(X+(Q?))/, -1) #=> ["", "XQ", "Q", "ab", "XX", "", "c", "XQ", "Q", ""], 
- 
+    s.split(/(X+(Q?))/, -1) #=> ["", "XQ", "Q", "ab", "XX", "", "c", "XQ", "Q", ""],
+
 With this method,
 
     s.split_with_delimiter(/X+(Q?)/)
                             #=> ["", "XQ", "ab", "XX", "c", "XQ"]
- 
+
 from which the original string is always easily recovered by simple +join+.
 
 Also, {PlainText::Util} contains some miscellaneous methods.
@@ -134,8 +183,6 @@ Also, {PlainText::Util} contains some miscellaneous methods.
 
 Work in progress...
 
-It is still in a preliminary state.
-
 == Install
 
 This script requires {Ruby}[http://www.ruby-lang.org] Version 2.0
@@ -153,6 +200,8 @@ explicitly with your Ruby command as
 
 == Developer's note
 
+The source code is maintained also in {Github}[https://github.com/masasakano/plain_text]
+
 === Tests
 
 Ruby codes under the directory <tt>test/</tt> are the test scripts.

data/bin/countchar

@@ -11,22 +11,17 @@ __EOF__
 
 # Initialising the hash for the command-line options.
 OPTS = {
-  preserve_paragraph: true,
-  boundary_style: true,
-  lbs_style: :t, # :truncate,
-  lb_is_space: false,
-  sps_style: :truncate,
-  delete_asian_space: true,
-  linehead_style: :delete, 
-  linetail_style: :delete, 
-  firstsps_style: :delete,
-  lastsps_style:  :truncate,
   line_i: nil,
   line_f: nil,
   # :chatter => 3,        # Default
   debug: false,
 }
 
+# Load the default values from the Module
+PlainText::DEF_METHOD_OPTS[:count_char].each_key do |ek|
+  OPTS[ek] ||= PlainText::DEF_METHOD_OPTS[:count_char][ek]
+end
+
 # Function to handle the command-line arguments.
 #
 # ARGV will be modified, and the constant variable OPTS is set.
@@ -45,8 +40,9 @@ def handle_argv
 
   opt.parse!(ARGV)
 
+  OPTS[:lbs_style] = OPTS[:lbs_style].to_s[0].to_sym
   unless %i(t d n).include? OPTS[:lbs_style]
-    warn "ERROR: --lbs-style must be one of (t(runcate)|d(elete)|n(one))."; exit 1
+    warn "ERROR: --lbs-style must be one of (t(runcate)|d(elete)|n(one)), but given (#{OPTS[:lbs_style].inspect})"; exit 1
   end
 
   OPTS
@@ -67,20 +63,15 @@ end
 # Handle the command-line options => OPTS
 opts = handle_argv()
 
+valid_keys = PlainText::DEF_METHOD_OPTS[:count_char].keys
+opts.each_key do |ek|
+  opts.delete ek if !valid_keys.include? ek
+end
+
 str = ARGF.read
 
-puts str.count_char(
-       preserve_paragraph: opts[:preserve_paragraph],
-       boundary_style:     opts[:boundary_style],
-       lbs_style:          opts[:lbs_style],
-       lb_is_space:        opts[:lb_is_space],
-       sps_style:          opts[:sps_style],
-       delete_asian_space: opts[:delete_asian_space],
-       linehead_style:     opts[:linehead_style],
-       linetail_style:     opts[:linetail_style],
-       firstsps_style:     opts[:firstsps_style],
-       lastsps_style:      opts[:lastsps_style],
-     )
+puts PlainText.count_char(str, **opts)
+# str.count_char() should be equivalent.
 
 exit
 

data/bin/head.rb

@@ -0,0 +1,87 @@
+#!/usr/bin/env ruby
+# -*- coding: utf-8 -*-
+
+require 'optparse'
+require 'plain_text'
+
+BANNER = <<"__EOF__"
+USAGE: #{File.basename($0)} [options] [INFILE.txt] < STDIN
+  Head command with (multi-byte) character-based manipulation and Regexp.
+__EOF__
+
+# Initialising the hash for the command-line options.
+OPTS = {
+  num: PlainText::DEF_HEADTAIL_N_LINES, 
+  unit: :line,
+  inclusive: true,
+  inverse: false,  # unique option
+  # :chatter => 3,        # Default
+  debug: false,
+}
+
+# Function to handle the command-line arguments.
+#
+# ARGV will be modified, and the constant variable OPTS is set.
+#
+# @return [Hash]  Optional-argument hash.
+#
+def handle_argv
+  opt = OptionParser.new(BANNER)
+  opt.separator "Options:"        # Way to control a help message.
+  opt.on('-n NUM', '--line=NUM', sprintf("Number of lines (Def: %d).", PlainText::DEF_HEADTAIL_N_LINES), Integer) { |v| OPTS[:num]=v }
+  opt.on('-c NUM', '--byte=NUM', sprintf("Number of bytes, instead of lines."), Integer) { |v| OPTS[:unit] = :byte; OPTS[:num]=v }
+  opt.on(  '--char=NUM',    sprintf("Number of characters, instead of lines."), Integer) { |v| OPTS[:unit] = :char; OPTS[:num]=v }
+  opt.on('-e REGEXP', '--regexp=REGEXP', sprintf("Regexp for the boundary, instead of a number.", (!OPTS[:num]).inspect)) {|v| OPTS[:num] = Regexp.new v}
+  opt.on('-x', '--[no-]exclusive', sprintf("The line that matches is excluded? (Def: %s)", (!OPTS[:inclusive]).inspect), FalseClass) {|v| OPTS[:inclusive] = v}
+  opt.on('-i', '--[no-]inverse', sprintf("Inverse the result (print after NUM-th line) (Def: %s)", (!OPTS[:inverse]).inspect), TrueClass) {|v| OPTS[:inverse] = v}
+  # opt.on(  '--version', "Display the version and exits.", TrueClass) {|v| OPTS[:version] = v}  # Consider opts.on_tail
+  # opt.on(  '--[no-]debug', "Debug (Def: false)", TrueClass) {|v| OPTS[:debug] = v}
+  # opt.separator ""        # Way to control a help message.
+  # opt.separator "Note:"
+  # opt.separator " Spaces are truncated in default."
+
+  begin
+    opt.parse!(ARGV)
+  rescue OptionParser::MissingArgument => er
+    # Missing argument like "-b" without a number.
+    warn er
+    exit 1
+  end
+
+  OPTS
+end
+
+
+################################################
+# MAIN
+################################################
+
+$stdout.sync=true
+$stderr.sync=true
+
+class String
+  include PlainText
+end
+
+# Handle the command-line options => OPTS
+opts = handle_argv()
+num_in = opts[:num]
+is_inverse = opts[:inverse]
+
+%i(num inverse debug).each do |ek|
+  opts.delete ek if opts.has_key? ek
+end
+
+str = ARGF.read
+
+# A linebreak guaranteed at the end.
+if is_inverse
+  puts PlainText.head_inverse(str, num_in, **opts)
+else
+  puts PlainText.head(str, num_in, **opts)
+end
+
+exit
+
+__END__
+

data/bin/tail.rb

@@ -0,0 +1,87 @@
+#!/usr/bin/env ruby
+# -*- coding: utf-8 -*-
+
+require 'optparse'
+require 'plain_text'
+
+BANNER = <<"__EOF__"
+USAGE: #{File.basename($0)} [options] [INFILE.txt] < STDIN
+  tail command with (multi-byte) character-based manipulation and Regexp.
+__EOF__
+
+# Initialising the hash for the command-line options.
+OPTS = {
+  num: PlainText::DEF_HEADTAIL_N_LINES, 
+  unit: :line,
+  inclusive: true,
+  inverse: false,  # unique option
+  # :chatter => 3,        # Default
+  debug: false,
+}
+
+# Function to handle the command-line arguments.
+#
+# ARGV will be modified, and the constant variable OPTS is set.
+#
+# @return [Hash]  Optional-argument hash.
+#
+def handle_argv
+  opt = OptionParser.new(BANNER)
+  opt.separator "Options:"        # Way to control a help message.
+  opt.on('-n NUM', '--line=NUM', sprintf("Number of lines (Def: %d).", PlainText::DEF_HEADTAIL_N_LINES), Integer) { |v| OPTS[:num]=v }
+  opt.on('-c NUM', '--byte=NUM', sprintf("Number of bytes, instead of lines."), Integer) { |v| OPTS[:unit] = :byte; OPTS[:num]=v }
+  opt.on(  '--char=NUM',    sprintf("Number of characters, instead of lines."), Integer) { |v| OPTS[:unit] = :char; OPTS[:num]=v }
+  opt.on('-e REGEXP', '--regexp=REGEXP', sprintf("Regexp for the boundary, instead of a number.", (!OPTS[:num]).inspect)) {|v| OPTS[:num] = Regexp.new v}
+  opt.on('-x', '--[no-]exclusive', sprintf("The line that matches is excluded? (Def: %s)", (!OPTS[:inclusive]).inspect), FalseClass) {|v| OPTS[:inclusive] = v}
+  opt.on('-i', '--[no-]inverse', sprintf("Inverse the result (print after NUM-th line) (Def: %s)", (!OPTS[:inverse]).inspect), TrueClass) {|v| OPTS[:inverse] = v}
+  # opt.on(  '--version', "Display the version and exits.", TrueClass) {|v| OPTS[:version] = v}  # Consider opts.on_tail
+  # opt.on(  '--[no-]debug', "Debug (Def: false)", TrueClass) {|v| OPTS[:debug] = v}
+  opt.separator ""        # Way to control a help message.
+  opt.separator "Note:"
+  opt.separator "  UNIX command of 'tail -n +5' is equivalent to 'head.rb -i -n 5'"
+
+  begin
+    opt.parse!(ARGV)
+  rescue OptionParser::MissingArgument => er
+    # Missing argument like "-b" without a number.
+    warn er
+    exit 1
+  end
+
+  OPTS
+end
+
+
+################################################
+# MAIN
+################################################
+
+$stdout.sync=true
+$stderr.sync=true
+
+class String
+  include PlainText
+end
+
+# Handle the command-line options => OPTS
+opts = handle_argv()
+num_in = opts[:num]
+is_inverse = opts[:inverse]
+
+%i(num inverse debug).each do |ek|
+  opts.delete ek if opts.has_key? ek
+end
+
+str = ARGF.read
+
+# A linebreak guaranteed at the end.
+if is_inverse
+  puts PlainText.tail_inverse(str, num_in, **opts)
+else
+  puts PlainText.tail(str, num_in, **opts)
+end
+
+exit
+
+__END__
+

data/bin/textclean

@@ -0,0 +1,103 @@
+#!/usr/bin/env ruby
+# -*- coding: utf-8 -*-
+
+require 'optparse'
+require 'plain_text'
+
+BANNER = <<"__EOF__"
+USAGE: #{File.basename($0)} [options] [INFILE.txt] < STDIN
+  Clean the text file INFILE (or STDIN), unifying linebreaks, and outputs it.
+__EOF__
+
+# Initialising the hash for the command-line options.
+OPTS = {
+  line_i: nil,
+  line_f: nil,
+  # :chatter => 3,        # Default
+  debug: false,
+}
+
+# Load the default values from the Module
+PlainText::DEF_METHOD_OPTS[:clean_text].each_key do |ek|
+  OPTS[ek] ||= PlainText::DEF_METHOD_OPTS[:clean_text][ek]
+end
+
+# Function to handle the command-line arguments.
+#
+# ARGV will be modified, and the constant variable OPTS is set.
+#
+# @return [Hash]  Optional-argument hash.
+#
+def handle_argv
+  opt = OptionParser.new(BANNER)
+  opt.on(  '--[no-]preserve_paragraph', sprintf("Preserved paragraph structures? (Def: %s)", OPTS[:preserve_paragraph].inspect), TrueClass) {|v| OPTS[:preserve_paragraph] = v}
+  opt.on(  '--boundary-style=STYLE', sprintf("One of (t(runcate)(2)|d(elete)|n(one)) (Def: truncate).")) { |v| OPTS[:boundary_style]=v.strip }
+  opt.on(  '--lbs-style=STYLE', sprintf("One of (t(runcate)|d(elete)|n(one)) (Def: %s).", OPTS[:lbs_style])) { |v| OPTS[:lbs_style]=v.strip }
+  opt.on(  '--[no-]lb-is-space', sprintf("Linebraeks are equivalent to spaces? (Def: %s)", OPTS[:lb_is_space].inspect), TrueClass) {|v| OPTS[:lb_is_space] = v}
+  opt.on(  '--sps-style=STYLE', sprintf("One of (t(runcate)|d(elete)|n(one)) (Def: %s).", OPTS[:sps_style])) { |v| OPTS[:sps_style]=v.strip }
+  opt.on(  '--[no-]delete-asian-space', sprintf("Deletes spaces between, before or after a CJK character? (Def: %s)", OPTS[:delete_asian_space].inspect), TrueClass) {|v| OPTS[:delete_asian_space] = v}
+  opt.on(  '--linehead-style=STYLE', sprintf("One of (t(runcate)|d(elete)|n(one)) (Def: %s).", OPTS[:linehead_style])) { |v| OPTS[:linehead_style]=v.strip }
+  opt.on(  '--linetail-style=STYLE', sprintf("One of (t(runcate)|d(elete)|n(one)) (Def: %s).", OPTS[:linetail_style])) { |v| OPTS[:linetail_style]=v.strip }
+  opt.on(  '--firstlbs-style=STYLE', sprintf("One of (t(runcate)|d(elete)|n(one)) (Def: %s).", OPTS[:firstlbs_style])) { |v| OPTS[:firstlbs_style]=v.strip }
+  opt.on(  '--lastsps-style=STYLE', sprintf("One of (t(runcate)|d(elete)|n(one)|m(arkdown)) (Def: %s).", OPTS[:lastsps_style])) { |v| OPTS[:lastsps_style]=v.strip }
+  # opt.on(  '--version', "Display the version and exits.", TrueClass) {|v| OPTS[:version] = v}  # Consider opts.on_tail
+  opt.on(  '--[no-]debug', "Debug (Def: false)", TrueClass) {|v| OPTS[:debug] = v}
+  # opt.separator ""        # Way to control a help message.
+  # opt.separator "Note:"
+  # opt.separator " Spaces are truncated in default."
+
+  opt.parse!(ARGV)
+
+  if (OPTS[:boundary_style].class.method_defined?(:to_str) && 
+      /\A(t(runcate)?(2)?|d(elete)?|n(one)?)\z/ =~ OPTS[:boundary_style])
+    OPTS[:boundary_style] = OPTS[:boundary_style].to_sym
+  end
+
+  %w(lbs sps linehead linetail firstlbs lastsps).each do |ek_head|
+    sym_k = (ek_head+"_style").to_sym
+    trysym = OPTS[sym_k].to_s[0].to_sym  # Symbol of 1 character (nb., NOT boundary_style)
+    if  (!(%i(t d n).include? trysym)   && (sym_k != :lastsps_style) ||
+         !(%i(t d n m).include? trysym) && (sym_k == :lastsps_style))
+      errmsg = sprintf(
+        "ERROR: --%s-style must be one of (t(runcate)|d(elete)%s|n(one)), but given %s.",
+        ek_head,
+        ((ek_head == "lastsps") ? "|m(arkdown)" : ""),
+        OPTS[sym_k].inspect
+      )
+      warn errmsg
+      exit 1
+    end
+    OPTS[sym_k] = trysym
+  end
+
+  OPTS
+end
+
+
+################################################
+# MAIN
+################################################
+
+$stdout.sync=true
+$stderr.sync=true
+
+class String
+  include PlainText
+end
+
+# Handle the command-line options => OPTS
+opts = handle_argv()
+
+valid_keys = PlainText::DEF_METHOD_OPTS[:clean_text].keys
+opts.each_key do |ek|
+  opts.delete ek if !valid_keys.include? ek
+end
+
+str = ARGF.read
+
+print PlainText.clean_text(str, **opts)
+
+exit
+
+__END__
+

data/lib/plain_text.rb

@@ -25,6 +25,36 @@ module PlainText
   # Default number of lines to extract for {#head} and {#tail}
   DEF_HEADTAIL_N_LINES = 10
 
+  # Default options for class/instance methods
+  DEF_METHOD_OPTS = {
+    :clean_text => {
+      preserve_paragraph: true,
+      boundary_style: true,  # If unspecified, will be replaced with lb_out * 2
+      lbs_style: :truncate,
+      lb_is_space: false,
+      sps_style: :truncate,
+      delete_asian_space: true,
+      linehead_style: :none,
+      linetail_style: :delete,
+      firstlbs_style: :delete,
+      lastsps_style:  :truncate,
+      lb: $/,
+      lb_out: nil,           # If unspecified, will be replaced with lb
+    },
+    :count_char => {
+      lbs_style: :delete,
+      linehead_style: :delete,
+      lastsps_style: :delete,
+      lb_out: "\n",
+    },
+  }
+
+  # Adjusts DEF_METHOD_OPTS[:count_char]
+  DEF_METHOD_OPTS[:clean_text].each_key do |ek|
+    # %i(preserve_paragraph boundary_style lb_is_space sps_style delete_asian_space linetail_style firstlbs_style lb).each do |ek|
+    DEF_METHOD_OPTS[:count_char][ek] ||= DEF_METHOD_OPTS[:clean_text][ek]
+  end
+
   # Call instance method as a Module function
   #
   # The return String includes {PlainText} as Singleton.
@@ -39,33 +69,39 @@ module PlainText
   end
 
   # If the class of the obj does not "include" this module, do so in the singular class.
-  # 
+  #
   # @param obj [Object] Maybe String. For which a singular class def is run, if the condition is met.
   # @return [TrueClass, NilClass] true if the singular class def is run. Else nil.
   def self.extend_this(obj)
-    return nil if defined? obj.delete_spaces_bw_cjk_european! 
+    return nil if defined? obj.delete_spaces_bw_cjk_european!
     obj.extend(PlainText)
     true
   end
 
-  # Module function of {#count_char}
+  # Count the number of characters
+  #
+  # See {PlainText#clean_text!} for the optional parameters.  The defaults of a few of the optional parameters are different from it,
+  # such as the default for +lb_out+ is +"\n"+ (newline, so that a line-break is 1 byte in size).
+  # It is so that this method is more optimized for East-Asian (CJK) characters, given this method is most useful for CJK Strings,
+  # whereas, for European alphabets, counting the number of words, rather than characters as in this method, would be more standard.
   #
   # @param instr [String] String for which the number of chars is counted
   # @param (see #count_char)
   # @return [Integer]
   def self.count_char(instr, *rest,
-                 lbs_style: :delete,
-                 linehead_style: :delete,
-                 lastsps_style: :delete,
-                 lb_out: "\n",
-                 **k)
-    clean_text(instr, *rest, lbs_style: lbs_style, lastsps_style: lastsps_style, lb_out: lb_out, **k).size
+        lbs_style:      DEF_METHOD_OPTS[:count_char][:lbs_style],
+        linehead_style: DEF_METHOD_OPTS[:count_char][:linehead_style],
+        lastsps_style:  DEF_METHOD_OPTS[:count_char][:lastsps_style],
+        lb_out:         DEF_METHOD_OPTS[:count_char][:lb_out],
+        **k
+      )
+    clean_text(instr, *rest, lbs_style: lbs_style, linehead_style: linehead_style, lastsps_style: lastsps_style, lb_out: lb_out, **k).size
   end
 
 
   # Cleans the text
   #
-  # Such as, removing extra spaces, normalising the linebreaks, etc. 
+  # Such as, removing extra spaces, normalising the linebreaks, etc.
   #
   # In default,
   #
@@ -77,9 +113,9 @@ module PlainText
   # * Trailing white spaces in each line are deleted: +linetail_style=:delete+
   # * Line-breaks at the beginning of the entire input string are deleted: +firstlbs_style=:delete+
   # * Trailing white spaces and line-breaks at the end of the entire input string are truncated into a single linebreak: +lastsps_style=:truncate+
-  # 
+  #
   # For a String with predominantly CJK characters, the following setting is recommended:
-  # 
+  #
   # * +lbs_style: :delete+
   # * +delete_asian_space: true+ (Default)
   #
@@ -111,26 +147,26 @@ module PlainText
   #
   def self.clean_text(
         prt,
-        preserve_paragraph: true,
-        boundary_style: true,  # If unspecified, will be replaced with lb_out * 2
-        lbs_style: :truncate,
-        lb_is_space: false,
-        sps_style: :truncate,
-        delete_asian_space: true,
-        linehead_style: :none,
-        linetail_style: :delete, 
-        firstlbs_style: :delete,
-        lastsps_style:  :truncate,
-        lb: $/,
-        lb_out: nil,           # If unspecified, will be replaced with lb
+        preserve_paragraph: DEF_METHOD_OPTS[:clean_text][:preserve_paragraph],
+        boundary_style:     DEF_METHOD_OPTS[:clean_text][:boundary_style], # If unspecified, will be replaced with lb_out * 2
+        lbs_style:      DEF_METHOD_OPTS[:clean_text][:lbs_style],
+        lb_is_space:    DEF_METHOD_OPTS[:clean_text][:lb_is_space],
+        sps_style:      DEF_METHOD_OPTS[:clean_text][:sps_style],
+        delete_asian_space: DEF_METHOD_OPTS[:clean_text][:delete_asian_space],
+        linehead_style: DEF_METHOD_OPTS[:clean_text][:linehead_style],
+        linetail_style: DEF_METHOD_OPTS[:clean_text][:linetail_style],
+        firstlbs_style: DEF_METHOD_OPTS[:clean_text][:firstlbs_style],
+        lastsps_style:  DEF_METHOD_OPTS[:clean_text][:lastsps_style],
+        lb:     DEF_METHOD_OPTS[:clean_text][:lb],
+        lb_out: DEF_METHOD_OPTS[:clean_text][:lb_out], # If unspecified, will be replaced with lb
         is_debug: false
       )
 
-isdebug = true if prt == "\n  \n abc\n\n \ndef\n\n \n\n"
+#isdebug = true if prt == "foo\n\n\nbar\n"
     lb_out ||= lb  # Output linebreak
     boundary_style = lb_out*2 if true       == boundary_style
     boundary_style = ""       if [:delete, :d].include? boundary_style
-    lastsps_style  = lb_out   if :linebreak == lastsps_style 
+    lastsps_style  = lb_out   if :linebreak == lastsps_style
 
     if !prt.class.method_defined? :last_significant_element
       # Construct a Part instance from the given String.
@@ -172,7 +208,7 @@ isdebug = true if prt == "\n  \n abc\n\n \ndef\n\n \n\n"
     clean_text_file_head_tail!( prt,
       firstlbs_style: firstlbs_style,
       lastsps_style:  lastsps_style,
-      is_debug: isdebug
+      is_debug: is_debug
     )
 
     # Replaces the linebreaks to the specified one
@@ -254,13 +290,13 @@ isdebug = true if prt == "\n  \n abc\n\n \ndef\n\n \n\n"
   # Class methods (Private)
   ##########
 
-  # @param prt [PlainText:Part] (see Plaintext.clean_text#prt)
-  # @param boundary_style (see Plaintext.clean_text#boundary_style)
+  # @param prt [PlainText:Part] (see PlainText.clean_text)
+  # @param boundary_style (see PlainText.clean_text)
   # @return [void]
   #
-  # @see Plaintext.clean_text
+  # @see PlainText.clean_text
   def self.clean_text_boundary!( prt,
-        boundary_style: $/*2,
+        boundary_style: ,
         is_debug: false
       )
 
@@ -280,20 +316,20 @@ isdebug = true if prt == "\n  \n abc\n\n \ndef\n\n \n\n"
   end # self.clean_text_boundary!
   private_class_method :clean_text_boundary!
 
-  # @param prt [PlainText:Part] (see Plaintext.clean_text#prt)
-  # @param lbs_style (see Plaintext.clean_text#lbs_style)
-  # @param sps_style (see Plaintext.clean_text#sps_style)
-  # @param lb_is_space (see Plaintext.clean_text#lb_is_space)
-  # @param delete_asian_space (see Plaintext.clean_text#delete_asian_space)
+  # @param prt [PlainText:Part] (see PlainText.clean_text)
+  # @param lbs_style (see PlainText.clean_text)
+  # @param sps_style (see PlainText.clean_text)
+  # @param lb_is_space (see PlainText.clean_text)
+  # @param delete_asian_space (see PlainText.clean_text)
   # @return [void]
   #
-  # @see Plaintext.clean_text
+  # @see PlainText.clean_text
   def self.clean_text_lbs_sps!(
         prt,
-        lbs_style: :truncate,
-        lb_is_space: false,
-        sps_style: :truncate,
-        delete_asian_space: true,
+        lbs_style:          ,
+        lb_is_space:        ,
+        sps_style:          ,
+        delete_asian_space: ,
         is_debug: false
       )
 
@@ -328,16 +364,16 @@ isdebug = true if prt == "\n  \n abc\n\n \ndef\n\n \n\n"
   end # self.clean_text_lbs_sps!
   private_class_method :clean_text_lbs_sps!
 
-  # @param prt [PlainText:Part] (see Plaintext.clean_text#prt)
-  # @param linehead_style [Symbol, String] (see Plaintext.clean_text#linehead_style)
-  # @param linetail_style [Symbol, String] (see Plaintext.clean_text#linetail_style)
+  # @param prt [PlainText:Part] (see PlainText.clean_text)
+  # @param linehead_style [Symbol, String] (see PlainText.clean_text)
+  # @param linetail_style [Symbol, String] (see PlainText.clean_text)
   # @return [void]
   #
-  # @see Plaintext.clean_text
+  # @see PlainText.clean_text
   def self.clean_text_line_head_tail!(
         prt,
-        linehead_style: :none,
-        linetail_style: :delete, 
+        linehead_style: ,
+        linetail_style: ,
         is_debug: false
       )
 
@@ -371,16 +407,16 @@ isdebug = true if prt == "\n  \n abc\n\n \ndef\n\n \n\n"
   end # self.clean_text_line_head_tail!
   private_class_method :clean_text_line_head_tail!
 
-  # @param prt [PlainText:Part] (see Plaintext.clean_text#prt)
-  # @param firstlbs_style [Symbol, String] (see Plaintext.clean_text#firstlbs_style)
-  # @param lastsps_style [Symbol, String]  (see Plaintext.clean_text#lastsps_style)
+  # @param prt [PlainText:Part] (see PlainText.clean_text#prt)
+  # @param firstlbs_style [Symbol, String] (see PlainText.clean_text#firstlbs_style)
+  # @param lastsps_style [Symbol, String]  (see PlainText.clean_text#lastsps_style)
   # @return [void]
   #
-  # @see Plaintext.clean_text
+  # @see PlainText.clean_text
   def self.clean_text_file_head_tail!(
         prt,
-        firstlbs_style: :delete,
-        lastsps_style:  :truncate,
+        firstlbs_style: ,
+        lastsps_style:  ,
         is_debug: false
       )
 
@@ -452,19 +488,18 @@ isdebug = true if prt == "\n  \n abc\n\n \ndef\n\n \n\n"
   #
   # uses Part to transform a Paragraph into a Part
   #
-  # @param prt [PlainText:Part] (see Plaintext.clean_text#prt)
-  # @param sps_style (see Plaintext.clean_text#sps_style)
+  # @param prt [PlainText:Part] (see PlainText.clean_text)
+  # @param sps_style (see PlainText.clean_text)
   # @return [void]
   #
-  # @see Plaintext.clean_text
+  # @see PlainText.clean_text
   def self.clean_text_sps!(
         prt,
-        sps_style: :truncate,
+        sps_style: ,
         is_debug: false
       )
 
     prt.parts.each do |e_pa|
-      ru = ParseRule
       # Each line treated as a Paragraph, and [[:space:]]+ between them as a Boundary.
       # Then, to work on anything within a line except for line-head/tail is easy.
       prt_para = Part.parse(e_pa, rule: ParseRule::RuleEachLineStrip).map_parts { |e_li|
@@ -490,21 +525,16 @@ isdebug = true if prt == "\n  \n abc\n\n \ndef\n\n \n\n"
   ####################################################
 
   # Count the number of characters
-  # 
-  # See {PlainText#clean_text!} for the optional parameters.  The defaults of a few of the optional parameters are different from {PlainText#clean_text!},
-  # such as the default for +lb_out+ is "\n" (so that a line-break is 1 byte in size).
+  #
+  # See {PlainText.count_char} and further {PlainText.clean_text!} for the optional parameters.  The defaults of a few of the optional parameters are different from the latter,
+  # such as the default for +lb_out+ is +"\n"+ (newline, so that a line-break is 1 byte in size).
   # It is so that this method is more optimized for East-Asian (CJK) characters, given this method is most useful for CJK Strings,
   # whereas, for European alphabets, counting the number of words, rather than characters as in this method, would be more standard.
   #
-  # @param (see PlainText#clean_text!)
+  # @param (see {PlainText.count_char})
   # @return [Integer]
-  def count_char(*rest,
-                 lbs_style: :delete,
-                 linehead_style: :delete,
-                 lastsps_style: :none,
-                 lb_out: "\n",
-                 **k)
-    PlainText.clean_text(self, *rest, lbs_style: lbs_style, lastsps_style: lastsps_style, lb_out: lb_out, **k).size
+  def count_char(*rest, **k)
+    PlainText.public_send(__method__, self, *rest, **k)
   end
 
   # Delete all the spaces between CJK and European characters or numbers.
@@ -732,7 +762,7 @@ isdebug = true if prt == "\n  \n abc\n\n \ndef\n\n \n\n"
   # till the last one is returned.  "The next line" means (1) the line immediately after the match
   # if the matched string has the linebreak at the end, or (2) the line after the first linebreak after the matched string,
   # where the trailing characters after the matched string to the linebreak (inclusive) is ignored.
-  # 
+  #
   # = Tips =
   # To specify the *last* line that matches the Regexp, consider prefixing +(?:.*)+ with the option +m+,
   # e.g., +/(?:.*)ABC/m+

data/plain_text.gemspec

@@ -5,9 +5,9 @@ require 'date'
 
 Gem::Specification.new do |s|
   s.name = %q{plain_text}.sub(/.*/){|c| (c == File.basename(Dir.pwd)) ? c : raise("ERROR: s.name=(#{c}) in gemspec seems wrong!")}
-  s.version = "0.2"
+  s.version = "0.3"
   # s.required_rubygems_version = Gem::Requirement.new(">= 0") if s.respond_to? :required_rubygems_version=
-  %w(countchar).each do |f|
+  %w(countchar textclean head.rb tail.rb).each do |f|
     path = s.bindir+'/'+f
     File.executable?(path) ? s.executables << f : raise("ERROR: Executable (#{path}) is not executable!")
   end

data/test/testcountchar.rb

@@ -0,0 +1,46 @@
+# -*- encoding: utf-8 -*-
+
+# Tests of an executable.
+#
+# @author: M. Sakano (Wise Babel Ltd)
+
+require 'open3'
+
+$stdout.sync=true
+$stderr.sync=true
+# print '$LOAD_PATH=';p $LOAD_PATH
+
+#################################################
+# Unit Test
+#################################################
+
+gem "minitest"
+# require 'minitest/unit'
+require 'minitest/autorun'
+
+class TestUnitCountchar < MiniTest::Test
+  T = true
+  F = false
+  SCFNAME = File.basename(__FILE__)
+  EXE = "%s/../bin/%s" % [File.dirname(__FILE__), File.basename(__FILE__).sub(/^test_?(.+)\.rb/, '\1')]
+
+  def setup
+  end
+
+  def teardown
+  end
+
+  def test_countchar01
+    o, e, s = Open3.capture3 EXE
+    assert_equal 0, s.exitstatus, "error is raised: STDOUT="+o.inspect+" STDERR="+(e.empty? ? '""' : ":\n"+e)
+    assert_equal "0", o.chomp
+    assert_empty e
+
+    stin = "foo\n\n\nbar\n"
+    o, e, s = Open3.capture3 EXE, stdin_data: stin
+    assert_equal 0, s.exitstatus
+    assert_equal stin.size-2, o.to_i
+    assert_empty e
+  end
+end # class TestUnitCountchar < MiniTest::Test
+

data/test/testhead_rb.rb

@@ -0,0 +1,70 @@
+# -*- encoding: utf-8 -*-
+
+# Tests of an executable.
+#
+# @author: M. Sakano (Wise Babel Ltd)
+
+require 'open3'
+
+$stdout.sync=true
+$stderr.sync=true
+# print '$LOAD_PATH=';p $LOAD_PATH
+
+#################################################
+# Unit Test
+#################################################
+
+gem "minitest"
+# require 'minitest/unit'
+require 'minitest/autorun'
+
+class TestUnitHeadRb < MiniTest::Test
+  T = true
+  F = false
+  SCFNAME = File.basename(__FILE__)
+  EXE = "%s/../bin/%s" % [File.dirname(__FILE__), File.basename(__FILE__).sub(/^test_?(.+)\.rb/, '\1').sub(/_rb$/, '.rb')]
+
+  def setup
+  end
+
+  def teardown
+  end
+
+  def test_countchar01
+    o, e, s = Open3.capture3 EXE
+    assert_equal 0, s.exitstatus, "error is raised: STDOUT="+o.inspect+" STDERR="+(e.empty? ? '""' : ":\n"+e)
+    assert_equal "\n", o
+    assert_empty e
+
+    stin = "1\n2\n3\n4\n5\n6\n7\n8\n9\nA\nB\n"
+    o, e, s = Open3.capture3 EXE, stdin_data: stin
+    assert_equal 0, s.exitstatus
+    assert_equal stin[0..19], o
+    assert_empty e
+
+    o, e, s = Open3.capture3 EXE+' -i', stdin_data: stin
+    assert_equal 0, s.exitstatus
+    assert_equal stin[20..-1], o, "Wrong! STDOUT="+o.inspect+" STDERR="+(e.empty? ? '""' : ":\n"+e)
+    assert_empty e
+
+    o, e, s = Open3.capture3 EXE+' -n 10', stdin_data: stin
+    assert_equal 0, s.exitstatus
+    assert_equal stin[0..19], o
+    assert_empty e
+
+    o, e, s = Open3.capture3 EXE+' -b', stdin_data: stin
+    assert_equal 1, s.exitstatus, "error is raised: STDOUT="+o.inspect+" STDERR="+(e.empty? ? '""' : ":\n"+e)
+    assert_match(/missing/i, e)
+
+    o, e, s = Open3.capture3 EXE+' -e "[5-9]"', stdin_data: stin
+    assert_equal 0, s.exitstatus
+    assert_equal stin[0..9], o, "Wrong! STDOUT="+o.inspect+" STDERR="+(e.empty? ? '""' : ":\n"+e)
+    assert_empty e
+
+    o, e, s = Open3.capture3 EXE+' -e "[5-9]" -x', stdin_data: stin
+    assert_equal 0, s.exitstatus, "error is raised: STDOUT="+o.inspect+" STDERR="+(e.empty? ? '""' : ":\n"+e)
+    assert_equal stin[0..7], o, "Wrong! STDOUT="+o.inspect+" STDERR="+(e.empty? ? '""' : ":\n"+e)
+    assert_empty e
+  end
+end # class TestUnitHeadRb < MiniTest::Test
+

data/test/testtail_rb.rb

@@ -0,0 +1,70 @@
+# -*- encoding: utf-8 -*-
+
+# Tests of an executable.
+#
+# @author: M. Sakano (Wise Babel Ltd)
+
+require 'open3'
+
+$stdout.sync=true
+$stderr.sync=true
+# print '$LOAD_PATH=';p $LOAD_PATH
+
+#################################################
+# Unit Test
+#################################################
+
+gem "minitest"
+# require 'minitest/unit'
+require 'minitest/autorun'
+
+class TestUnitTailRb < MiniTest::Test
+  T = true
+  F = false
+  SCFNAME = File.basename(__FILE__)
+  EXE = "%s/../bin/%s" % [File.dirname(__FILE__), File.basename(__FILE__).sub(/^test_?(.+)\.rb/, '\1').sub(/_rb$/, '.rb')]
+
+  def setup
+  end
+
+  def teardown
+  end
+
+  def test_countchar01
+    o, e, s = Open3.capture3 EXE
+    assert_equal 0, s.exitstatus, "error is raised: STDOUT="+o.inspect+" STDERR="+(e.empty? ? '""' : ":\n"+e)
+    assert_equal "\n", o
+    assert_empty e
+
+    stin = "1\n2\n3\n4\n5\n6\n7\n8\n9\nA\nB\n"
+    o, e, s = Open3.capture3 EXE, stdin_data: stin
+    assert_equal 0, s.exitstatus
+    assert_equal stin[2..-1], o
+    assert_empty e
+
+    o, e, s = Open3.capture3 EXE+' -i', stdin_data: stin
+    assert_equal 0, s.exitstatus
+    assert_equal stin[0..1], o, "Wrong! STDOUT="+o.inspect+" STDERR="+(e.empty? ? '""' : ":\n"+e)
+    assert_empty e
+
+    o, e, s = Open3.capture3 EXE+' -n 10', stdin_data: stin
+    assert_equal 0, s.exitstatus
+    assert_equal stin[2..-1], o
+    assert_empty e
+
+    o, e, s = Open3.capture3 EXE+' -b', stdin_data: stin
+    assert_equal 1, s.exitstatus, "error is raised: STDOUT="+o.inspect+" STDERR="+(e.empty? ? '""' : ":\n"+e)
+    assert_match(/missing/i, e)
+
+    o, e, s = Open3.capture3 EXE+' -e "[5-9]"', stdin_data: stin
+    assert_equal 0, s.exitstatus
+    assert_equal stin[-6..-1], o, "Wrong! STDOUT="+o.inspect+" STDERR="+(e.empty? ? '""' : ":\n"+e)
+    assert_empty e
+
+    o, e, s = Open3.capture3 EXE+' -e "[5-9]" -x', stdin_data: stin
+    assert_equal 0, s.exitstatus, "error is raised: STDOUT="+o.inspect+" STDERR="+(e.empty? ? '""' : ":\n"+e)
+    assert_equal stin[-4..-1], o, "Wrong! STDOUT="+o.inspect+" STDERR="+(e.empty? ? '""' : ":\n"+e)
+    assert_empty e
+  end
+end # class TestUnitTailRb < MiniTest::Test
+

data/test/testtextclean.rb

@@ -0,0 +1,52 @@
+# -*- encoding: utf-8 -*-
+
+# Tests of an executable.
+#
+# @author: M. Sakano (Wise Babel Ltd)
+
+require 'open3'
+
+$stdout.sync=true
+$stderr.sync=true
+# print '$LOAD_PATH=';p $LOAD_PATH
+
+#################################################
+# Unit Test
+#################################################
+
+gem "minitest"
+# require 'minitest/unit'
+require 'minitest/autorun'
+
+class TestUnitTextclean < MiniTest::Test
+  T = true
+  F = false
+  SCFNAME = File.basename(__FILE__)
+  EXE = "%s/../bin/%s" % [File.dirname(__FILE__), File.basename(__FILE__).sub(/^test_?(.+)\.rb/, '\1')]
+
+  def setup
+  end
+
+  def teardown
+  end
+
+  def test_textclean01
+    o, e, s = Open3.capture3 EXE
+    assert_equal 0, s.exitstatus, "error is raised: STDOUT="+o.inspect+" STDERR="+(e.empty? ? '""' : ":\n"+e)
+    assert_equal "", o.chomp
+    assert_empty e
+
+    stin = "foo\n\n\nbar\n"
+    s2   = "foo\n\nbar\n"
+    #o, e, s = Open3.capture3 EXE, stdin_data: stin
+    #assert_equal 0, s.exitstatus
+    #assert_equal s2, o
+    #assert_empty e
+
+    o, e, s = Open3.capture3 EXE+' --lastsps-style=delete', stdin_data: stin
+    assert_equal 0, s.exitstatus
+    assert_equal s2.chop.chomp, o, "Wrong! STDOUT="+o.inspect+" STDERR="+(e.empty? ? '""' : ":\n"+e)
+    assert_empty e
+  end
+end # class TestUnitTextclean < MiniTest::Test
+

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: plain_text
 version: !ruby/object:Gem::Version
-  version: '0.2'
+  version: '0.3'
 platform: ruby
 authors:
 - Masa Sakano
@@ -17,6 +17,9 @@ description: This module provides utility functions and methods to handle plain
 email: 
 executables:
 - countchar
+- textclean
+- head.rb
+- tail.rb
 extensions: []
 extra_rdoc_files:
 - README.en.rdoc
@@ -28,6 +31,9 @@ files:
 - README.en.rdoc
 - Rakefile
 - bin/countchar
+- bin/head.rb
+- bin/tail.rb
+- bin/textclean
 - lib/plain_text.rb
 - lib/plain_text/parse_rule.rb
 - lib/plain_text/part.rb
@@ -40,6 +46,10 @@ files:
 - test/test_plain_text_parse_rule.rb
 - test/test_plain_text_part.rb
 - test/test_plain_text_split.rb
+- test/testcountchar.rb
+- test/testhead_rb.rb
+- test/testtail_rb.rb
+- test/testtextclean.rb
 homepage: https://www.wisebabel.com
 licenses:
 - MIT
@@ -67,6 +77,10 @@ specification_version: 4
 summary: Module to handle Plain-Text
 test_files:
 - test/test_plain_text_parse_rule.rb
+- test/testtail_rb.rb
 - test/test_plain_text_part.rb
 - test/test_plain_text.rb
+- test/testcountchar.rb
+- test/testtextclean.rb
 - test/test_plain_text_split.rb
+- test/testhead_rb.rb