deblank 0.0.1

data/README.md

@@ -0,0 +1,88 @@
+deblank - remove special characters from filenames
+==================================================
+
+`deblank` is a command line tool (written in [Ruby][Ruby])
+that renames files and replaces or removes special characters
+like spaces, parentheses, or umlauts.
+The new filename will only contain the following characters:
+
+    A-Z a-z 0-9 . _ -
+
+Spaces are replaced by underscores, German umlauts and eszett are
+transliterated, all other invalid characters are removed.
+
+Examples
+--------
+
+Use the program as shown in the examples below.
+
+* `deblank "no space (and parentheses) allowed.txt"`
+
+    renames the file to `no_space_and_parentheses_allowed.txt`
+
+* `deblank "path with spaces/schrödinger.jpg"`
+
+    renames the file to `path with spaces/schroedinger.jpg`
+
+* `deblank -n "no space.txt"`
+
+    no-act mode, only shows what would happen
+
+* `deblank -l`
+
+    lists the used character substitutions
+
+Installation
+------------
+
+You can either
+
+- use `gem install deblank`,
+
+- copy `lib/deblank.rb` under the name `deblank` into your search path,
+
+- clone or download the repository and use `[sudo] rake install`
+  on a Linux machine to install `deblank` and its man page to `/usr/local`.
+
+Requirements
+------------
+
+- Ruby must be installed on your system.
+
+- No additional Ruby gems are needed to run `deblank`.
+
+- `deblank` has been tested with Ruby 1.9.3 on a Linux machine
+  and on Windows (command prompt with code page 850).
+
+Documentation
+-------------
+
+Use `deblank --help` to display a brief help message.
+
+If you installed `deblank` using `rake install` you can read
+its man page with `man deblank`.
+
+Known problems
+--------------
+
+With the Windows command prompt, depending on the used character
+code page there might occur problems due to misinterpreted encoding
+of command line arguments.
+
+Reporting bugs
+--------------
+
+Report bugs on the `deblank` home page: <https://github.com/stomar/deblank/>
+
+License
+-------
+
+Copyright &copy; 2012, Marcus Stollsteimer
+
+`deblank` is free software: you can redistribute it and/or modify
+it under the terms of the GNU General Public License version 3 or later (GPLv3+),
+see [www.gnu.org/licenses/gpl.html](http://www.gnu.org/licenses/gpl.html).
+There is NO WARRANTY, to the extent permitted by law.
+
+
+[Ruby]: http://www.ruby-lang.org/

data/Rakefile

@@ -0,0 +1,73 @@
+# rakefile for the deblank script.
+#
+# Copyright (C) 2012 Marcus Stollsteimer
+
+require 'rake/testtask'
+
+require './lib/deblank'
+
+PROGNAME = Deblank::PROGNAME
+HOMEPAGE = Deblank::HOMEPAGE
+TAGLINE  = Deblank::TAGLINE
+
+BINDIR = '/usr/local/bin'
+MANDIR = '/usr/local/man/man1'
+
+HELP2MAN = 'help2man'
+SED = 'sed'
+
+BINARY = 'lib/deblank.rb'
+BINARYNAME = 'deblank'  # install using this name
+MANPAGE = 'man/deblank.1'
+H2MFILE = 'deblank.h2m'
+
+
+def gemspec_file
+  'deblank.gemspec'
+end
+
+
+task :default => [:test]
+
+Rake::TestTask.new do |t|
+  t.libs << '.'
+  t.pattern = 'test/**/test_*.rb'
+  t.ruby_opts << '-rubygems'
+  t.verbose = true
+  t.warning = true
+end
+
+
+desc 'Install binary and man page'
+task :install => [BINARY, MANPAGE] do
+  mkdir_p BINDIR
+  install(BINARY, "#{BINDIR}/#{BINARYNAME}")
+  mkdir_p MANDIR
+  install(MANPAGE, MANDIR, :mode => 0644)
+end
+
+
+desc 'Uninstall binary and man page'
+task :uninstall do
+  rm "#{BINDIR}/#{BINARYNAME}"
+  manfile = File.basename(MANPAGE)
+  rm "#{MANDIR}/#{manfile}"
+end
+
+
+desc 'Create man page'
+task :man => [MANPAGE]
+
+file MANPAGE => [BINARY, H2MFILE] do
+  sh "#{HELP2MAN} --no-info --name='#{TAGLINE}' --include=#{H2MFILE} -o #{MANPAGE} ./#{BINARY}"
+  sh "#{SED} -i '/\.PP/{N;s/\.PP\\nOptions/.SH OPTIONS/}' #{MANPAGE}"
+  sh "#{SED} -i 's/^License GPL/.br\\nLicense GPL/;s/There is NO WARRANTY/.br\\nThere is NO WARRANTY/' #{MANPAGE}"
+  sh "#{SED} -i 's!%HOMEPAGE%!#{HOMEPAGE}!g' #{MANPAGE}"
+  sh "#{SED} -i 's!%PROGNAME%!#{PROGNAME}!g' #{MANPAGE}"
+end
+
+
+desc 'Build gem'
+task :build => [MANPAGE] do
+  sh "gem build #{gemspec_file}"
+end

data/bin/deblank

@@ -0,0 +1,5 @@
+#!/usr/bin/ruby -w
+
+require 'deblank'
+
+Deblank::Application.new.run!

data/deblank.gemspec

@@ -0,0 +1,43 @@
+require './lib/deblank'
+
+version  = Deblank::VERSION
+date     = Deblank::DATE
+homepage = Deblank::HOMEPAGE
+tagline  = Deblank::TAGLINE
+
+Gem::Specification.new do |s|
+  s.name              = 'deblank'
+  s.version           = version
+  s.date              = date
+  s.rubyforge_project = 'deblank'
+
+  s.description = 'deblank is a command line tool that ' +
+                  'renames files and replaces or removes special characters ' +
+                  'like spaces, parentheses, or umlauts.'
+  s.summary = "deblank - #{tagline}"
+
+  s.authors = ['Marcus Stollsteimer']
+  s.email = 'sto.mar@web.de'
+  s.homepage = homepage
+
+  s.license = 'GPL-3'
+
+  # s.requirements = ''
+
+  s.executables = ['deblank']
+  s.bindir = 'bin'
+  s.require_path = 'lib'
+  s.test_files = Dir.glob('test/**/test_*.rb')
+
+  s.rdoc_options = ['--charset=UTF-8']
+
+  s.files = %w{
+      README.md
+      Rakefile
+      deblank.gemspec
+      deblank.h2m
+    } +
+    Dir.glob('{bin,lib,man,test}/**/*')
+
+  s.add_development_dependency('rake')
+end

data/deblank.h2m

@@ -0,0 +1,3 @@
+[See also]
+The full documentation for %PROGNAME% is available on
+the project home page: <%HOMEPAGE%>.

data/lib/deblank.rb

@@ -0,0 +1,243 @@
+#!/usr/bin/ruby -w
+# encoding: UTF-8
+# == Name
+#
+# deblank - remove special characters from filenames
+#
+# == Description
+#
+# +deblank+ renames files and replaces or removes special characters
+# like spaces, parentheses, or umlauts.
+#
+# == See also
+#
+# Use <tt>deblank --help</tt> to display a brief help message.
+#
+# == Author
+#
+# Copyright (C) 2012 Marcus Stollsteimer
+#
+# License GPLv3+: GNU GPL version 3 or later <http://gnu.org/licenses/gpl.html>
+
+require 'optparse'
+
+# This module contains the classes for the +deblank+ tool.
+module Deblank
+
+  PROGNAME  = 'deblank'
+  VERSION   = '0.0.1'
+  DATE      = '2012-12-20'
+  HOMEPAGE  = 'https://github.com/stomar/deblank'
+  TAGLINE   = 'remove special characters from filenames'
+
+  COPYRIGHT = "Copyright (C) 2012 Marcus Stollsteimer.\n" +
+              "License GPLv3+: GNU GPL version 3 or later <http://gnu.org/licenses/gpl.html>.\n" +
+              "This is free software: you are free to change and redistribute it.\n" +
+              "There is NO WARRANTY, to the extent permitted by law."
+
+  # Parser for the command line options.
+  # The class method parse! does the job.
+  class Optionparser
+
+    # Parses the command line options from +argv+.
+    # (+argv+ is cleared).
+    # Might print out help or version information.
+    #
+    # +argv+ - array with the command line options
+    #
+    # Returns a hash containing the option parameters.
+    def self.parse!(argv)
+
+      options = {
+        :files  => nil,
+        :simulate => false,
+      }
+
+      opt_parser = OptionParser.new do |opt|
+        opt.banner = "Usage: #{PROGNAME} [options] file[s]"
+        opt.separator ''
+        opt.separator 'deblank renames files and replaces or removes special characters'
+        opt.separator 'like spaces, parentheses, or umlauts.'
+        opt.separator 'The new filename will only contain the following characters:'
+        opt.separator ''
+        opt.separator '    ' << NameConverter::VALID_CHARS
+        opt.separator ''
+        opt.separator 'Spaces are replaced by underscores, German umlauts and eszett are'
+        opt.separator 'transliterated, all other invalid characters are removed.'
+        opt.separator ''
+        opt.separator 'Options'
+        opt.separator ''
+
+        # process --version and --help first,
+        # exit successfully (GNU Coding Standards)
+        opt.on_tail('-h', '--help', 'Print a brief help message and exit.') do
+          puts opt_parser
+          puts "\nReport bugs on the #{PROGNAME} home page: <#{HOMEPAGE}>"
+          exit
+        end
+
+        opt.on_tail('-v', '--version',
+                    'Print a brief version information and exit.') do
+          puts "#{PROGNAME} #{VERSION}"
+          puts COPYRIGHT
+          exit
+        end
+
+        opt.on('-l', '--list',
+               'List the used character substitutions.') do
+          puts NameConverter.substitutions_to_string
+          exit
+        end
+
+        opt.on('-n', '--no-act',
+               'Do not rename files, only display what would happen.') do
+          options[:simulate] = true
+        end
+
+        opt.separator ''
+      end
+      opt_parser.parse!(argv)
+
+      # only file[s] should be left (at least 1 argument)
+      raise(ArgumentError, 'wrong number of arguments')  if argv.size < 1
+
+      options[:files] = Array.new(argv).map do |filename|
+        correct_encoding(filename).encode('UTF-8')
+      end
+      argv.clear
+
+      options
+    end
+
+    # Corrects the encoding for (seemingly) CP850 encoded strings
+    # from `CP850' to `Windows-1252'.
+    #
+    # Returns a copy of +string+ with corrected encoding or +string+.
+    #
+    # [On the Windows test machine (which uses code page 850 for the
+    # command prompt) the command line arguments are interpreted by Ruby
+    # as CP850 encoded strings but actually are Windows-1252 encoded.]
+    def self.correct_encoding(string)
+      return string  unless string.encoding == Encoding::CP850
+
+      string.dup.force_encoding('Windows-1252')
+    end
+  end
+
+  # This module provides a converter method for filenames
+  # (only the base name is modified).
+  module NameConverter
+
+    VALID_CHARS = 'A-Z a-z 0-9 . _ -'  # spaces are ignored, `-' must be last
+
+    SUBSTITUTIONS = {
+      ' ' => '_',
+      'ä' => 'ae',
+      'ö' => 'oe',
+      'ü' => 'ue',
+      'Ä' => 'Ae',
+      'Ö' => 'Oe',
+      'Ü' => 'Ue',
+      'ß' => 'ss'
+    }
+
+    def self.convert(filename)
+      invalid_chars = /[^#{VALID_CHARS.tr(' ', '')}]/
+      basename = File.basename(filename)
+      dir = File.dirname(filename)
+
+      SUBSTITUTIONS.each do |from, to|
+        basename.gsub!(/#{from}/, to)
+      end
+      basename.gsub!(invalid_chars, '')
+
+      dir == '.' ? basename : "#{dir}/#{basename}"
+    end
+
+    def self.substitutions_to_string
+      output = ''
+      SUBSTITUTIONS.each do |from, to|
+        output << "#{from} => #{to}\n"
+      end
+
+      output
+    end
+  end
+
+  # The main program. It's run! method is called
+  # if the script is run from the command line.
+  # It parses the command line arguments and renames the files.
+  class Application
+
+    ERRORCODE = {:general => 1, :usage => 2}
+
+    def initialize
+      begin
+        options = Optionparser.parse!(ARGV)
+        @files = options[:files]
+        @simulate = options[:simulate]
+      rescue => e
+        usage_fail(e.message)
+      end
+    end
+
+    # The main program.
+    def run!
+      message = "This is a dry run, files will not be renamed."
+      warn "#{message}\n#{'-' * message.size}\n"  if @simulate
+
+      @files.each do |filename|
+        unless File.exist?(filename)
+          warn "There is no file `#{filename}'. (Skipped.)"
+          next
+        end
+
+        new_filename = NameConverter.convert(filename)
+
+        # filenames are identical
+        if new_filename == filename
+          warn("`#{filename}' and `#{new_filename}' are the same file. (Skipped.)")
+          next
+        end
+
+        # move file
+        if File.exist?(new_filename)
+          overwrite_ok = ask("File `#{new_filename}' already exists. Overwrite?")
+          next  unless overwrite_ok
+        end
+
+        warn "Moving from `#{filename}' to `#{new_filename}'."
+        File.rename(filename, new_filename)  unless @simulate
+      end   # of each
+    end
+
+    # Asks for yes or no (y/n).
+    #
+    # +question+ - string to be printed
+    #
+    # Returns +true+ if the answer is yes.
+    def ask(question) # :nodoc:
+      loop do
+        $stderr.print "#{question} [y/n] "
+        reply = $stdin.gets.chomp.downcase  # $stdin: avoids gets / ARGV problem
+        return true   if reply == 'y'
+        return false  if reply == 'n'
+        warn "Please answer `y' or `n'."
+      end
+    end
+
+    # Prints an error message and a short help information, then exits.
+    def usage_fail(message) # :nodoc:
+      warn "#{PROGNAME}: #{message}"
+      warn "Use `#{PROGNAME} --help' for valid options."
+      exit ERRORCODE[:usage]
+    end
+  end
+
+### call main method only if called on command line
+
+if __FILE__ == $0
+  Application.new.run!
+end
+
+end  # module

data/man/deblank.1

@@ -0,0 +1,42 @@
+.\" DO NOT MODIFY THIS FILE!  It was generated by help2man 1.40.4.
+.TH DEBLANK "1" "December 2012" "deblank 0.0.1" "User Commands"
+.SH NAME
+deblank \- remove special characters from filenames
+.SH SYNOPSIS
+.B deblank
+[\fIoptions\fR] \fIfile\fR[\fIs\fR]
+.SH DESCRIPTION
+deblank renames files and replaces or removes special characters
+like spaces, parentheses, or umlauts.
+The new filename will only contain the following characters:
+.IP
+A\-Z a\-z 0\-9 . _ \-
+.PP
+Spaces are replaced by underscores, German umlauts and eszett are
+transliterated, all other invalid characters are removed.
+.SH OPTIONS
+.TP
+\fB\-l\fR, \fB\-\-list\fR
+List the used character substitutions.
+.TP
+\fB\-n\fR, \fB\-\-no\-act\fR
+Do not rename files, only display what would happen.
+.TP
+\fB\-h\fR, \fB\-\-help\fR
+Print a brief help message and exit.
+.TP
+\fB\-v\fR, \fB\-\-version\fR
+Print a brief version information and exit.
+.SH "REPORTING BUGS"
+Report bugs on the deblank home page: <https://github.com/stomar/deblank>
+.SH COPYRIGHT
+Copyright \(co 2012 Marcus Stollsteimer.
+.br
+License GPLv3+: GNU GPL version 3 or later <http://gnu.org/licenses/gpl.html>.
+.br
+This is free software: you are free to change and redistribute it.
+.br
+There is NO WARRANTY, to the extent permitted by law.
+.SH "SEE ALSO"
+The full documentation for deblank is available on
+the project home page: <https://github.com/stomar/deblank>.

data/test/test_nameconverter.rb

@@ -0,0 +1,34 @@
+#!/usr/bin/ruby -w
+# encoding: UTF-8
+#
+# test_nameconverter.rb: Unit tests for the deblank script.
+#
+# Copyright (C) 2012 Marcus Stollsteimer
+
+require 'minitest/spec'
+require 'minitest/autorun'
+require 'deblank'
+
+
+describe Deblank::NameConverter do
+
+  before do
+    @nc = Deblank::NameConverter
+  end
+
+  it 'does not change the path name' do
+    @nc.convert('path with spaces/file.txt').must_equal 'path with spaces/file.txt'
+  end
+
+  it 'replaces spaces by underscores' do
+    @nc.convert('file with spaces.txt').must_equal 'file_with_spaces.txt'
+  end
+
+  it 'removes parentheses' do
+    @nc.convert('file_(another).txt').must_equal 'file_another.txt'
+  end
+
+  it 'transliterates umlauts and eszett' do
+    @nc.convert('Ä_Ö_Ü_ä_ö_ü_ß.txt').must_equal 'Ae_Oe_Ue_ae_oe_ue_ss.txt'
+  end
+end

data/test/test_optionparser.rb

@@ -0,0 +1,49 @@
+#!/usr/bin/ruby -w
+# encoding: UTF-8
+#
+# test_optionparser.rb: Unit tests for the deblank script.
+#
+# Copyright (C) 2012 Marcus Stollsteimer
+
+require 'minitest/spec'
+require 'minitest/autorun'
+require 'deblank'
+
+
+describe Deblank::Optionparser do
+
+  before do
+    @parser = Deblank::Optionparser
+    @arg = "test_ä.txt"
+    @arg_Win_1252_labeled_as_CP850 = "test_\xE4.txt".force_encoding('CP850')
+    @arg_Win_1252 = "test_\xE4.txt".force_encoding('Windows-1252')
+  end
+
+  it 'can correct encoding from (seemingly) CP850 to Windows-1252' do
+    arg = @arg_Win_1252_labeled_as_CP850
+    arg.encoding.must_equal Encoding::CP850
+    corrected_arg = @parser.correct_encoding(arg)
+    corrected_arg.encoding.must_equal Encoding::Windows_1252
+  end
+
+  it 'encodes (seemingly) CP850 encoded filenames into UTF-8' do
+    options = @parser.parse!([@arg_Win_1252_labeled_as_CP850])
+    filename = options[:files].first
+    filename.encoding.must_equal Encoding::UTF_8
+    filename.must_equal @arg
+  end
+
+  it 'encodes Windows-1252 encoded filenames into UTF-8' do
+    options = @parser.parse!([@arg_Win_1252])
+    filename = options[:files].first
+    filename.encoding.must_equal Encoding::UTF_8
+    filename.must_equal @arg
+  end
+
+  it 'encodes UTF-8 encoded filenames into UTF-8' do
+    options = @parser.parse!([@arg])
+    filename = options[:files].first
+    filename.encoding.must_equal Encoding::UTF_8
+    filename.must_equal @arg
+  end
+end

metadata

@@ -0,0 +1,76 @@
+--- !ruby/object:Gem::Specification
+name: deblank
+version: !ruby/object:Gem::Version
+  version: 0.0.1
+  prerelease: 
+platform: ruby
+authors:
+- Marcus Stollsteimer
+autorequire: 
+bindir: bin
+cert_chain: []
+date: 2012-12-20 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: rake
+  requirement: !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: '0'
+description: deblank is a command line tool that renames files and replaces or removes
+  special characters like spaces, parentheses, or umlauts.
+email: sto.mar@web.de
+executables:
+- deblank
+extensions: []
+extra_rdoc_files: []
+files:
+- README.md
+- Rakefile
+- deblank.gemspec
+- deblank.h2m
+- bin/deblank
+- lib/deblank.rb
+- man/deblank.1
+- test/test_nameconverter.rb
+- test/test_optionparser.rb
+homepage: https://github.com/stomar/deblank
+licenses:
+- GPL-3
+post_install_message: 
+rdoc_options:
+- --charset=UTF-8
+require_paths:
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement
+  none: false
+  requirements:
+  - - ! '>='
+    - !ruby/object:Gem::Version
+      version: '0'
+required_rubygems_version: !ruby/object:Gem::Requirement
+  none: false
+  requirements:
+  - - ! '>='
+    - !ruby/object:Gem::Version
+      version: '0'
+requirements: []
+rubyforge_project: deblank
+rubygems_version: 1.8.24
+signing_key: 
+specification_version: 3
+summary: deblank - remove special characters from filenames
+test_files:
+- test/test_nameconverter.rb
+- test/test_optionparser.rb
+has_rdoc: