konjac 0.2.9.5 → 0.3

data/lib/applescripts/konjac_word_export

@@ -1,110 +0,0 @@
-#!/usr/bin/osascript
--- round up ASCII characters used for formatting in Word
-global bell
-global line_feed
-global form_feed
-global carriage_return
-global format_chars
-
--- strip line breaks and formatting characters
-to strip_line_breaks(this_line)
-  try
-    -- remove last character until no it's no longer an excluded character
-    repeat while last character of this_line is in format_chars
-      set this_line to characters 1 thru -2 of this_line as string
-    end repeat
-    return this_line as text
-  on error
-    return ""
-  end try
-end strip_line_breaks
-
-to get_posix_path(mac_path)
-  set result to POSIX path of mac_path
-end get_posix_path
-
-to extract(filename)
-  tell application "Microsoft Word"
-    activate
-    open filename
-    set active_document to active document
-    set ignored_content to {missing value, "", line_feed}
-    
-    -- set tags path to full path to active presentation with a .tags extension
-    set tags_path to ((path of active_document) & ".diff")
-    
-    -- delete tags file if it already exists
-    tell application "Finder"
-      if exists file tags_path then
-        delete file tags_path
-      end if
-    end tell
-    
-    -- open tags file for writing
-    set tags_file to open for access file tags_path with write permission
-    set eof of tags_file to 0
-
-    write ("--- " & my get_posix_path(path of active_document)) to tags_file
-    write line_feed to tags_file
-    write ("+++ " & my get_posix_path(path of active_document)) to tags_file
-    write line_feed to tags_file
-
-    -- iterate through paragraphs
-    set paragraph_index to 1
-    set current_paragraph to paragraph 1 in active_document
-
-    -- save old delimiters
-    
-    repeat
-      -- get text content if it's available
-      set text_content to my strip_line_breaks(content of text object of current_paragraph) as string
-
-      -- replace "soft returns" (vertical tabs) with real returns
-      set old_delimiters to AppleScript's text item delimiters
-      set AppleScript's text item delimiters to {ASCII character 11}
-      set split_content to every text item of text_content
-      set AppleScript's text item delimiters to old_delimiters
-
-      if text_content is not in ignored_content then
-        write ("@@ " & paragraph_index & " @@") to tags_file
-        write line_feed to tags_file
-        repeat with text_line in split_content
-          write ("-" & text_line) to tags_file as «class utf8»
-          write line_feed to tags_file
-        end repeat
-        repeat with text_line in split_content
-          write ("+" & text_line) to tags_file as «class utf8»
-          write line_feed to tags_file
-        end repeat
-      end if
-
-      -- increment paragraph index
-      set paragraph_index to (paragraph_index + 1)
-
-      -- try to find the next paragraph
-      try
-        set current_paragraph to next paragraph of current_paragraph
-      on error
-        exit repeat
-      end try
-    end repeat
-    
-    -- close everything
-    close access tags_file
-  end tell
-end extract
-
--- initialize global variables, just formatting characters here
-to init_globals()
-  set bell to ASCII character 7
-  set line_feed to ASCII character 10
-  set form_feed to ASCII character 12
-  set carriage_return to ASCII character 13
-  set format_chars to {bell, line_feed, form_feed, carriage_return}
-end init_globals
-
--- main()
-on run argv
-  init_globals()
-  extract(item 1 of argv)
-end

data/lib/applescripts/konjac_word_import

@@ -1,139 +0,0 @@
-#!/usr/bin/osascript
-global numbers_as_text
-global line_feed
-global vertical_tab
-global carriage_return
-
--- parses the headers/separators inside the tags file
-to parse_header(header)
-  set at_offset to 4
-  
-  repeat while character at_offset of header is in my numbers_as_text
-    set at_offset to (at_offset + 1)
-  end repeat
-  
-  return at_offset
-end parse_header
-
-to ends_with_forbidden_character(txt)
-  set last_character to character -1 of txt
-
-  if last_character is in {line_feed, carriage_return, vertical_tab}
-    return true
-  else
-    return false
-  end if
-end ends_with_forbidden_character
-
-to get_posix_path(mac_path)
-  set result to POSIX path of mac_path
-end get_posix_path
-
-to import(filename)
-  tell application "Microsoft Word"
-    activate
-    open filename
-    set active_document to active document
-    set ignored_content to {missing value, "", line_feed}
-    
-    -- set tags path to full path to active presentation with a .tags extension
-    set tags_path to ((path of active_document) & ".diff")
-    
-    -- read in tags
-    set tags_file to open for access file tags_path
-    set tags to (read tags_file for (get eof tags_file) ¬
-                   as «class utf8» using delimiter line_feed)
-    set tag_index to 0
-    set tag_length to length of tags
-    close access tags_file
-
-    set text_content to ""
-
-    -- iterate through paragraphs
-    set paragraph_index to 0
-    set prev_paragraph_index to 0
-    set is_new_tag to false
-
-    repeat with current_line in tags
-      if current_line starts with "@@ " then
-        set space_offset to my parse_header(current_line)
-        set paragraph_index to text 4 thru space_offset ¬
-                                 of current_line as number
-        set is_new_tag to true
-      else if current_line starts with "+" then
-        if paragraph_index is not 0 then
-          set prev_paragraph_index to paragraph_index
-
-          -- handle blank lines with soft returns
-          if length of current_line is less than 2
-            set this_content to ""
-          else
-            set this_content to text 2 thru (length of current_line) ¬
-                                  of current_line
-          end if
-
-          -- add to text content, joining with a soft return for multiple lines
-          if text_content is "" then
-            set text_content to this_content
-          else
-            set text_content to (text_content & vertical_tab & this_content)
-          end if
-          set is_new_tag to false
-        end if
-      end if
-
-      -- increment tag index
-      set tag_index to tag_index + 1
-
-      -- write if we've moved to a new tag or reached the end of the file
-      if text_content is not "" and (tag_index is tag_length or is_new_tag)
-        try
-          set current_content to text object of paragraph prev_paragraph_index ¬
-                                   of active document
-          set my_range to create range active document ¬
-                            start (start of content of current_content) ¬
-                            end (end of content of current_content)
-
-          select my_range
-
-          -- FIXME: this is super-ugly
-          if count of paragraphs of selection is greater than 1
-            set my_range to create range active document ¬
-                              start (start of content of text object of selection) ¬
-                              end ((end of content of text object of selection) - 1)
-            select my_range
-            repeat while (count of paragraphs of selection is greater than 1)
-              -- maybe?
-              move start of range my_range by a line item
-              select my_range
-            end repeat
-          end if
-
-          repeat while my ends_with_forbidden_character(content of selection as text)
-            set my_range to create range active document ¬
-                              start (start of content of text object of selection) ¬
-                              end ((end of content of text object of selection) - 1)
-            select my_range
-          end repeat
-
-          type text selection text text_content
-          set text_content to ""
-        end try
-      end if
-    end repeat
-  end tell
-end import
-
--- initialize global variables
-to init_globals()
-  set numbers_as_text to {"1", "2", "3", "4", "5", "6", "7", "8", "9", "0"}
-  set line_feed to ASCII character 10
-  set vertical_tab to ASCII character 11
-  set carriage_return to ASCII character 13
-end init_globals
-
--- main()
-on run argv
-  init_globals()
-  import(item 1 of argv)
-end run

data/lib/konjac/os.rb

@@ -1,51 +0,0 @@
-module Konjac
-  # A module for determining what OS we're using
-  module OS
-    class << self
-      # Override string output
-      def to_s
-        RbConfig::CONFIG["host_os"]
-      end
-
-      # OS is a version of Mac
-      def mac?
-        @mac ||= is? /mac|darwin/
-      end
-      
-      # OS is a version of Linux
-      def linux?
-        @linux ||= is? /linux|cygwin/
-      end
-
-      # OS is a version of Windows
-      def windows?
-        @windows ||= is? /mswin|^win|mingw/
-      end
-
-      # OS is POSIX (well, actually, this makes the somewhat bad assumption
-      # that non-Windows OSes are POSIX)
-      def posix?
-        !windows?
-      end
-
-      # Throws a message if the computer is using a command restricted to Macs
-      def not_a_mac
-        if mac?
-          return false
-        else
-          puts I18n.t(:mac_only)
-          return true
-        end
-      end
-
-
-      private
-
-      # Test whether the +host_os+ configuration parameter matches a specified
-      # regular expression
-      def is?(match)
-        match === RbConfig::CONFIG["host_os"]
-      end
-    end
-  end
-end

data/lib/konjac/tag.rb

@@ -1,50 +0,0 @@
-# coding: utf-8
-module Konjac
-  # A tag containing original text and (if available) its translation, plus the
-  # index of the <w:t> tag extracted from its .docx document
-  class Tag
-    # The index of the <w:t> tag in the cleaned-up XML file output by
-    # Konjac::Word.export_docx_tags
-    attr_accessor :index
-    
-    # The original text
-    attr_accessor :original
-      
-    # The translated text
-    attr_accessor :translated
-
-    # Creates a new tag.
-    #
-    #   t = Tag.new(1, "dog", "犬")
-    def initialize(index, original, translated)
-      @index, @original, @translated = index, original, translated
-    end
-
-    # Converts the Tag into a string for use in .konjac files
-    #
-    # <tt>Tag.new(1, "dog", "犬").to_s</tt> will output
-    #
-    #   [[KJ-1]]
-    #   > dog
-    #   犬
-    #
-    # whereas <tt>Tag.new(2, "cat").to_s</tt> will output
-    #
-    #   [[KJ-2]]
-    #   > cat
-    def to_s
-      "[[KJ-#{index}]]\n> #{original}#{"\n" + translated if translated?}"
-    end
-
-    # Whether the tag has been translated
-    #
-    #   dog = Tag.new(1, "dog", "犬")
-    #   dog.translated? # => true
-    #
-    #   cat = Tag.new(1, "cat", "")
-    #   cat.translated? # => false
-    def translated?
-      !translated.nil? && translated != ""
-    end
-  end
-end

data/lib/konjac/tag_manager.rb

@@ -1,65 +0,0 @@
-module Konjac
-  # A class for managing the tags generated by extraction from {Microsoft
-  # Word}[http://office.microsoft.com/en-us/word/] 2003+ documents
-  class TagManager
-    # A list of the Tag objects current being managed
-    attr_accessor :tags
-
-    # A regex to match lines that start with <tt>-</tt>, that is, lines that
-    # indicate removed text in .diff files
-    OLD_TAG = /^-[^-]/
-
-    # A regex to match lines that start with <tt>+</tt>, that is, lines that
-    # indicate added text in .diff files
-    NEW_TAG = /^\+[^+]/
-
-    # Regex for matching index numbers
-    KONJAC_TAG = /^@@\s(\d+).*@@$/
-
-    # Creates a new TagManager
-    def initialize(path)
-      @tags = []
-      parse_lines File.readlines(path)
-    end
-
-    # Parses the lines of a file into Tag objects
-    def parse_lines(lines)
-      index      = nil
-      orig       = nil
-      trans      = nil
-
-      lines.each do |line|
-        if line =~ KONJAC_TAG
-          # Handle instances where there is no translation
-          unless orig.nil?
-            @tags << Tag.new(index, orig, trans)
-            index = nil
-            orig  = nil
-          end
-
-          index = line.match(KONJAC_TAG)[1].to_i
-        elsif line =~ OLD_TAG
-          orig = line[1..-1].chomp
-        elsif line =~ NEW_TAG
-          trans = line[1..-1].chomp
-          unless index.nil?
-            @tags << Tag.new(index, orig, trans)
-            index = nil
-            orig  = nil
-            trans = nil
-          end
-        end
-      end
-    end
-
-    # A list of all the tags available
-    def all
-      @tags
-    end
-
-    # Finds the <em>nth</em> tag being managed
-    def [](index)
-      @tags[index]
-    end
-  end
-end

data/spec/tag_spec.rb

@@ -1,63 +0,0 @@
-# coding: utf-8
-require File.dirname(__FILE__) + "/spec_helper"
-require "tempfile"
-
-describe Tag do
-  before :each do
-    @tags_file = Tempfile.new(["tags", ".tags"])
-    @tags_file.write <<-eos.gsub(/^\s+/, "")
-                       --- /path/to/old
-                       +++ /path/to/new
-                       @@ 0 @@
-                       -犬
-                       +dog
-                       @@ 1 @@
-                       -何ですか。
-                       +What is it?
-                       @@ 2 @@
-                       -空白
-                       @@ 3 comment @@
-                       -コメント
-                       +Comment
-                       @@ 5 @@
-                       -以上
-                       +--- end --
-                     eos
-    @tags_file.rewind
-    @manager = TagManager.new(@tags_file.path)
-  end
-
-  it "should accurately read a tag" do
-    @manager.all.should_not == nil
-    @manager[0].index.should == 0
-    @manager[0].original.should == "犬"
-    @manager[0].translated.should == "dog"
-  end
-
-  it "should succeed reading multiple tags" do
-    @manager[1].index.should == 1
-    @manager[1].original.should == "何ですか。"
-    @manager[1].translated.should == "What is it?"
-  end
-
-  it "should ignore blank translations" do
-    @manager[2].index.should == 2
-    @manager[2].original.should == "空白"
-    @manager[2].translated.should == nil
-  end
-
-  it "should know whether a tag has been translated" do
-    @manager[0].translated?.should == true
-    @manager[2].translated?.should == false
-  end
-
-  it "should ignore comments and additional info after an index tag" do
-    @manager[3].index.should == 3
-    @manager[3].original.should == "コメント"
-    @manager[3].translated.should == "Comment"
-  end
-
-  it "should skip over blank indexes" do
-    @manager[4].index.should == 5
-  end
-end