RubyGems - pseudohikiparser - Versions diffs - 0.0.0.4.develop → 0.0.0.5.develop - Mend

pseudohikiparser 0.0.0.4.develop → 0.0.0.5.develop

Files changed (10) hide show

data/LICENSE +23 -0
data/README.md +203 -0
data/bin/pseudohiki2html.rb +28 -11
data/lib/htmlelement.rb +1 -3
data/lib/pseudohiki/blockparser.rb +5 -7
data/lib/pseudohiki/inlineparser.rb +5 -11
data/lib/pseudohiki/treestack.rb +1 -1
data/lib/pseudohiki/version.rb +1 -1
data/test/test_plaintextformat.rb +10 -0
metadata +6 -4

data/LICENSE ADDED Viewed

@@ -0,0 +1,23 @@
+Copyright (c) 2011, HASHIMOTO Naoki
+All rights reserved.
+Redistribution and use in source and binary forms, with or without modification,
+are permitted provided that the following conditions are met:
+* Redistributions of source code must retain the above copyright notice, this
+  list of conditions and the following disclaimer.
+* Redistributions in binary form must reproduce the above copyright notice, this
+  list of conditions and the following disclaimer in the documentation and/or
+  other materials provided with the distribution.
+THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" AND
+ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
+WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
+DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE LIABLE FOR
+ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
+(INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
+LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON
+ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+(INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
+SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.

data/README.md ADDED Viewed

@@ -0,0 +1,203 @@
+PseudoHikiParser
+================
+PseudoHikiParser is a converter of texts written in a [Hiki](http://hikiwiki.org/en/) like notation, into html or other formats.
+Currently, only a limited range of notations can be converted into HTML4 or XHTML1.0.
+I am writing this tool with following objectives in mind,
+* provide some additional features that do not exist in the original Hiki notation
+ * make the notation more line oriented
+ * allow to assign ids to elements such as headings
+* support several formats other than HTML
+ * The visitor pattern is adopted for the implementation, so you only have to add a visitor class to support a certain format.
+And, it would not be compatible with the original Hiki notation.
+## License
+BSD 2-Clause License
+## Installation
+```
+gem install pseudohikiparser --pre
+```
+## Usage
+### Samples
+[A sample text](https://github.com/nico-hn/PseudoHikiParser/blob/develop/samples/wikipage.txt) in Hiki notation and [a result of conversion](http://htmlpreview.github.com/?https://github.com/nico-hn/PseudoHikiParser/blob/develop/samples/wikipage.html), and [another result of conversion](http://htmlpreview.github.com/?https://github.com/nico-hn/PseudoHikiParser/blob/develop/samples/wikipage_with_toc.html)
+You will find those samples in [develop branch](https://github.com/nico-hn/PseudoHikiParser/tree/develop/samples).
+### pseudohiki2html.rb
+After the installation of PseudoHikiParser, you could use a command, _pseudohiki2html.rb_.
+_Please note that pseudohiki2html.rb is currently provided as a showcase of PseudoHikiParser, and the options will be continuously changed at this stage of development._
+Typing the following lines at the command prompt:
+```
+pseudohiki2html.rb <<TEXT
+!! The first heading
+The first paragraph
+TEXT
+```
+will return the following result to stdout:
+```html
+<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN"
+  "http://www.w3.org/TR/html4/loose.dtd">
+<html lang="en">
+<head>
+<meta content="en" http-equiv="Content-Language">
+<meta content="text/html; charset=UTF-8" http-equiv="Content-Type">
+<meta content="text/javascript" http-equiv="Content-Script-Type">
+<title>-</title>
+<link href="default.css" rel="stylesheet" type="text/css">
+</head>
+<body>
+<div class="section h2">
+<h2> The first heading
+</h2>
+<p>
+The first paragraph
+</p>
+<!-- end of section h2 -->
+</div>
+</body>
+</html>
+```
+And if you specify a file name with `--output` option:
+```
+pseudohiki2html.rb --output first_example.html <<TEXT
+!! The first heading
+The first paragraph
+TEXT
+```
+the result will be saved in first_example.html.
+For more options, please try `pseudohiki2html.rb --help`
+### module PseudoHiki
+If you save the lines below as a ruby script and execute it:
+```
+#!/usr/bin/env ruby
+require 'pseudohikiparser'
+plain = <<TEXT
+!! The first heading
+The first paragraph
+TEXT
+tree = PseudoHiki::BlockParser.parse(plain.lines.to_a)
+html = PseudoHiki::HtmlFormat.format(tree)
+puts html
+```
+you will get the following output:
+```
+<div class="section h2">
+<h2> The first heading
+</h2>
+<p>
+The first paragraph
+</p>
+<!-- end of section h2 -->
+</div>
+```
+Other than PseudoHiki::HtmlFormat, you can choose PseudoHiki::XhtmlFormat, PseudoHiki::Xhtml5Format, PseudoHiki::PlainTextFormat.
+## Development status of features from the original [Hiki notation](http://hikiwiki.org/en/TextFormattingRules.html)
+* Paragraphs - Usable
+* Links
+ * WikiNames - Not supported (and would never be)
+ * Linking to other Wiki pages - Not supported as well
+ * Linking to an arbitrary URL - Maybe usable
+* Preformatted text - Usable
+* Text decoration - Partly supported
+ * Currently, there is no means of escaping tags for inline decorations.
+ * The notation with backquote tags(``) for inline literals is not supported.
+* Headings - Usable
+* Horizontal lines - Usable
+* Lists - Usable
+* Quotations - Usable
+* Definitions - Usable
+* Tables - Usable
+* Comments - Usable
+* Plugins - Not supported (and will not be compatible with the original one)
+## Additional Features
+### Already Implemented
+#### Assigning ids
+If you add [name_of_id], just after the marks that denote heading or list type items, it becomes the id attribute of resulting html elements. Below is an example.
+```
+!![heading_id]heading
+*[list_id]list
+```
+will be rendered as
+```html
+<div class="section h2">
+<h2 id="HEADING_ID">heading
+</h2>
+<ul>
+<li id="LIST_ID">list
+</li>
+</ul>
+<!-- end of section h2 -->
+</div>
+```
+### Partly Implemented
+#### A visitor that removes markups and returns plain texts
+The visitor, [PlainTextFormat](https://github.com/nico-hn/PseudoHikiParser/blob/develop/lib/pseudohiki/plaintextformat.rb) is currently available only in the [develop branch](https://github.com/nico-hn/PseudoHikiParser/tree/develop). Below are examples
+```
+:tel:03-xxxx-xxxx
+::03-yyyy-yyyy
+:fax:03-xxxx-xxxx
+```
+will be rendered as
+```
+tel:	03-xxxx-xxxx
+	03-yyyy-yyyy
+fax:	03-xxxx-xxxx
+```
+And
+```
+||cell 1-1||>>cell 1-2,3,4||cell 1-5
+||cell 2-1||^>cell 2-2,3 3-2,3||cell 2-4||cell 2-5
+||cell 3-1||cell 3-4||cell 3-5
+||cell 4-1||cell 4-2||cell 4-3||cell 4-4||cell 4-5
+```
+will be rendered as
+```
+cell 1-1	cell 1-2,3,4	==	==	cell 1-5
+cell 2-1	cell 2-2,3 3-2,3	==	cell 2-4	cell 2-5
+cell 3-1	||	||	cell 3-4	cell 3-5
+cell 4-1	cell 4-2	cell 4-3	cell 4-4	cell 4-5
+```
+#### A visitor for HTML5
+The visitor, [Xhtml5Format](https://github.com/nico-hn/PseudoHikiParser/blob/develop/lib/pseudohiki/htmlformat.rb#L225) is currently available only in the [develop branch](https://github.com/nico-hn/PseudoHikiParser/tree/develop).
+### Not Implemented Yet

data/bin/pseudohiki2html.rb CHANGED Viewed

@@ -22,7 +22,8 @@ OPTIONS = {
   :template => nil,
   :output => nil,
   :force => false,
-  :toc => nil
+  :toc => nil,
+  :split_main_heading => false
 }
 ENCODING_REGEXP = {
@@ -37,7 +38,7 @@ HTML_VERSIONS = %w(html4 xhtml1 html5)
 FILE_HEADER_PAT = /^(\xef\xbb\xbf)?\/\//
 WRITTEN_OPTION_PAT = {}
 OPTIONS.keys.each {|opt| WRITTEN_OPTION_PAT[opt] = /^(\xef\xbb\xbf)?\/\/#{opt}:\s*(.*)$/ }
-HEADING_WITH_ID_PAT = /^(!{2,3})\[([A-Za-z][0-9A-Za-z_\-.:]*)\]/o
+HEADING_WITH_ID_PAT = /^(!{2,3})\[([A-Za-z][0-9A-Za-z_\-.:]*)\]\s*/o
 PlainFormat = PlainTextFormat.create
@@ -46,7 +47,12 @@ class InputManager
     @formatter ||= OPTIONS.html_template.new
   end
+  def to_plain(line)
+    PlainFormat.format(BlockParser.parse(line.lines.to_a)).to_s.chomp
+  end
   def create_table_of_contents(lines)
+    return "" unless OPTIONS[:toc]
     toc_lines = lines.grep(HEADING_WITH_ID_PAT).map do |line|
       m = HEADING_WITH_ID_PAT.match(line)
       heading_depth, id = m[1].length, m[2].upcase
@@ -55,7 +61,15 @@ class InputManager
     OPTIONS.formatter.format(BlockParser.parse(toc_lines))
   end
-  def create_main(toc, body)
+  def split_main_heading(input_lines)
+    return "" unless OPTIONS[:split_main_heading]
+    h1_pos = input_lines.find_index {|line| /^![^!]/o =~ line }
+    return "" unless h1_pos
+    tree = BlockParser.parse([input_lines.delete_at(h1_pos)])
+    OPTIONS.formatter.format(tree)
+  end
+  def create_main(toc, body, h1)
     return nil unless OPTIONS[:toc]
     toc_container = formatter.create_element("section").tap do |element|
       element["id"] = "toc"
@@ -68,6 +82,7 @@ class InputManager
     end
     main = formatter.create_element("section").tap do |element|
       element["id"] = "main"
+      element.push h1 unless h1.empty?
       element.push toc_container
       element.push contents_container
     end
@@ -88,11 +103,12 @@ class InputManager
   end
   def compose_html(input_lines)
+    h1 = split_main_heading(input_lines)
     css = OPTIONS[:css]
     toc = create_table_of_contents(input_lines)
     body = compose_body(input_lines)
     title = OPTIONS.title
-    main = create_main(toc,body)
+    main = create_main(toc,body, h1)
     if OPTIONS[:template]
       erb = ERB.new(OPTIONS.read_template_file)
@@ -107,10 +123,6 @@ class InputManager
   end
 end
-def to_plain(line)
-  PlainFormat.format(BlockParser.parse(line.lines.to_a)).to_s.chomp
-end
 def win32?
   true if RUBY_PLATFORM =~ /win/i
 end
@@ -228,7 +240,7 @@ end
 OptionParser.new("** Convert texts written in a Hiki-like notation into HTML **
 USAGE: #{File.basename(__FILE__)} [options]") do |opt|
   opt.on("-h [html_version]", "--html_version [=html_version]",
-         "HTML version to be used. Choose html4 or xhtml1 (default: #{OPTIONS[:html_version]})") do |version|
+         "HTML version to be used. Choose html4, xhtml1 or html5 (default: #{OPTIONS[:html_version]})") do |version|
     OPTIONS.set_html_version(version)
   end
@@ -254,7 +266,7 @@ USAGE: #{File.basename(__FILE__)} [options]") do |opt|
   end
   opt.on("-C [path_to_css_file]", "--embed-css [=path_to_css_file]",
-           "Set the path to a css file to be used (default: not to embed)") do |path_to_css_file|
+           "Set the path to a css file to embed (default: not to embed)") do |path_to_css_file|
     OPTIONS[:embed_css] = path_to_css_file
   end
@@ -284,6 +296,11 @@ USAGE: #{File.basename(__FILE__)} [options]") do |opt|
     OPTIONS[:toc] = toc_title
   end
+  opt.on("-s", "--split-main-heading",
+         "Split the first h1 element") do |should_be_split|
+    OPTIONS[:split_main_heading] = should_be_split
+  end
   opt.parse!
 end
@@ -304,7 +321,7 @@ when 1
   OPTIONS.read_input_filename(ARGV[0])
 end
-input_lines = ARGF.lines.to_a
+input_lines = ARGF.readlines
 OPTIONS.set_options_from_input_file(input_lines)
 OPTIONS.default_title = OPTIONS.input_file_basename

data/lib/htmlelement.rb CHANGED Viewed

@@ -4,9 +4,7 @@ require 'kconv'
 class HtmlElement
   class Children < Array
-    def to_s
-      self.join
-    end
+    alias to_s join
   end
   module CHARSET

data/lib/pseudohiki/blockparser.rb CHANGED Viewed

@@ -311,14 +311,12 @@ module PseudoHiki
       @stack.current_node.breakable?(breaker)
     end
+    def in_link_tag?(preceding_str)
+      preceding_str[-2,2] == "[[" or preceding_str[-1,1] == "|"
+    end
     def tagfy_link(line)
-      line.gsub(URI_RE) do |url|
-        unless ($`)[-2,2] == "[[" or ($`)[-1,1] == "|"
-          "[[#{url}]]"
-        else
-          url
-        end
-      end
+      line.gsub(URI_RE) {|url| in_link_tag?($`) ? url : "[[#{url}]]" }
     end
     def select_leaf_type(line)

data/lib/pseudohiki/inlineparser.rb CHANGED Viewed

@@ -142,21 +142,15 @@ module PseudoHiki
       end
       def push(token)
-        if self.empty?
-          super(parse_first_token(token))
-        else
-          super(token)
-        end
+        return super(token) unless self.empty?
+        super(parse_first_token(token))
       end
     end
     def treated_as_node_end(token)
-      if token == TableSep
-        self.pop
-        return (self.push TableCellNode.new)
-      end
-      super(token)
+      return super(token) unless token == TableSep
+      self.pop
+      self.push TableCellNode.new
     end
     def parse

data/lib/pseudohiki/treestack.rb CHANGED Viewed

@@ -1,7 +1,6 @@
 #!/usr/bin/env ruby
 class TreeStack
   class NotLeafError < Exception; end
   module Mergeable; end
@@ -59,6 +58,7 @@ class TreeStack
       nil
     end
   end
   attr_reader :node_end, :last_leaf
   def initialize(root_node=Node.new)

data/lib/pseudohiki/version.rb CHANGED Viewed

@@ -1,3 +1,3 @@
 module PseudoHiki
-  VERSION = "0.0.0.4.develop"
+  VERSION = "0.0.0.5.develop"
 end

data/test/test_plaintextformat.rb CHANGED Viewed

@@ -64,6 +64,16 @@ TEXT
                  @verbose_formatter.format(tree).to_s)
   end
+  def test_link_url2
+    text = <<TEXT
+!![develepment_status] Development status of features from the original [[Hiki notation|http://hikiwiki.org/en/TextFormattingRules.html]]
+TEXT
+    tree = BlockParser.parse(text.lines.to_a)
+    assert_equal(" Development status of features from the original Hiki notation\n", @formatter.format(tree).to_s)
+    assert_equal(" Development status of features from the original Hiki notation (http://hikiwiki.org/en/TextFormattingRules.html)\n",
+                 @verbose_formatter.format(tree).to_s)
+  end
   def test_link_image
     text = <<TEXT
 A test string with an [[image|image.jpg]] is here.

metadata CHANGED Viewed

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: pseudohikiparser
 version: !ruby/object:Gem::Version
-  version: 0.0.0.4.develop
+  version: 0.0.0.5.develop
   prerelease: 8
 platform: ruby
 authors:
@@ -9,7 +9,7 @@ authors:
 autorequire:
 bindir: bin
 cert_chain: []
-date: 2013-09-10 00:00:00.000000000 Z
+date: 2013-10-19 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: bundler
@@ -52,6 +52,8 @@ executables:
 extensions: []
 extra_rdoc_files: []
 files:
+- README.md
+- LICENSE
 - lib/pseudohikiparser.rb
 - lib/pseudohiki/treestack.rb
 - lib/pseudohiki/inlineparser.rb
@@ -71,9 +73,9 @@ files:
 - test/test_htmlformat.rb
 - test/test_htmlplugin.rb
 - bin/pseudohiki2html.rb
-homepage: https://github.com/hashimoto-naoki/PseudoHikiParser/wiki
+homepage: https://github.com/nico-hn/PseudoHikiParser/wiki
 licenses:
-- Not decided yet
+- BSD 2-Clause license
 post_install_message:
 rdoc_options: []
 require_paths: