motion-kramdown 0.5.0

data/lib/kramdown/options.rb

@@ -0,0 +1,584 @@
+# -*- coding: utf-8 -*-
+#
+#--
+# Copyright (C) 2009-2014 Thomas Leitner <t_leitner@gmx.at>
+#
+# This file is part of kramdown which is licensed under the MIT.
+#++
+#
+
+# RM equire 'yaml'
+
+module Kramdown
+
+  # This module defines all options that are used by parsers and/or converters as well as providing
+  # methods to deal with the options.
+  module Options
+
+    # Helper class introducing a boolean type for specifying boolean values (+true+ and +false+) as
+    # option types.
+    class Boolean
+
+      # Return +true+ if +other+ is either +true+ or +false+
+      def self.===(other)
+        FalseClass === other || TrueClass === other
+      end
+
+    end
+
+    # ----------------------------
+    # :section: Option definitions
+    #
+    # This sections describes the methods that can be used on the Options module.
+    # ----------------------------
+
+    # Struct class for storing the definition of an option.
+    Definition = Struct.new(:name, :type, :default, :desc, :validator)
+
+    # Allowed option types.
+    ALLOWED_TYPES = [String, Integer, Float, Symbol, Boolean, Object]
+
+    @options = {}
+
+    # Define a new option called +name+ (a Symbol) with the given +type+ (String, Integer, Float,
+    # Symbol, Boolean, Object), default value +default+ and the description +desc+. If a block is
+    # specified, it should validate the value and either raise an error or return a valid value.
+    #
+    # The type 'Object' should only be used for complex types for which none of the other types
+    # suffices. A block needs to be specified when using type 'Object' and it has to cope with
+    # a value given as string and as the opaque type.
+    def self.define(name, type, default, desc, &block)
+      name = name.to_sym
+      raise ArgumentError, "Option name #{name} is already used" if @options.has_key?(name)
+      raise ArgumentError, "Invalid option type #{type} specified" if !ALLOWED_TYPES.include?(type)
+      raise ArgumentError, "Invalid type for default value" if !(type === default) && !default.nil?
+      raise ArgumentError, "Missing validator block" if type == Object && block.nil?
+      @options[name] = Definition.new(name, type, default, desc, block)
+    end
+
+    # Return all option definitions.
+    def self.definitions
+      @options
+    end
+
+    # Return +true+ if an option called +name+ is defined.
+    def self.defined?(name)
+      @options.has_key?(name.to_sym)
+    end
+
+    # Return a Hash with the default values for all options.
+    def self.defaults
+      temp = {}
+      @options.each {|n, o| temp[o.name] = o.default}
+      temp
+    end
+
+    # Merge the #defaults Hash with the *parsed* options from the given Hash, i.e. only valid option
+    # names are considered and their value is run through the #parse method.
+    def self.merge(hash)
+      temp = defaults
+      hash.each do |k,v|
+        k = k.to_sym
+        @options.has_key?(k) ? temp[k] = parse(k, v) : temp[k] = v
+      end
+      temp
+    end
+
+    # Parse the given value +data+ as if it was a value for the option +name+ and return the parsed
+    # value with the correct type.
+    #
+    # If +data+ already has the correct type, it is just returned. Otherwise it is converted to a
+    # String and then to the correct type.
+    def self.parse(name, data)
+      name = name.to_sym
+      raise ArgumentError, "No option named #{name} defined" if !@options.has_key?(name)
+      if !(@options[name].type === data)
+        data = data.to_s
+        data = if @options[name].type == String
+                 data
+               elsif @options[name].type == Integer
+                 Integer(data) rescue raise Kramdown::Error, "Invalid integer value for option '#{name}': '#{data}'"
+               elsif @options[name].type == Float
+                 Float(data) rescue raise Kramdown::Error, "Invalid float value for option '#{name}': '#{data}'"
+               elsif @options[name].type == Symbol
+                 str_to_sym(data)
+               elsif @options[name].type == Boolean
+                 data.downcase.strip != 'false' && !data.empty?
+               end
+      end
+      data = @options[name].validator[data] if @options[name].validator
+      data
+    end
+
+    # Converts the given String +data+ into a Symbol or +nil+ with the
+    # following provisions:
+    #
+    # - A leading colon is stripped from the string.
+    # - An empty value or a value equal to "nil" results in +nil+.
+    def self.str_to_sym(data)
+      data = data.strip
+      data = data[1..-1] if data[0] == ?:
+      (data.empty? || data == 'nil' ? nil : data.to_sym)
+    end
+
+    # ----------------------------
+    # :section: Option Validators
+    #
+    # This sections contains all pre-defined option validators.
+    # ----------------------------
+
+    # Ensures that the option value +val+ for the option called +name+ is a valid array. The
+    # parameter +val+ can be
+    #
+    # - a comma separated string which is split into an array of values
+    # - or an array.
+    #
+    # Additionally, the array is checked for the correct size.
+    def self.simple_array_validator(val, name, size)
+      if String === val
+        val = val.split(/,/)
+      elsif !(Array === val)
+        raise Kramdown::Error, "Invalid type #{val.class} for option #{name}"
+      end
+      if val.size != size
+        raise Kramdown::Error, "Option #{name} needs exactly #{size} values"
+      end
+      val
+    end
+
+    # Ensures that the option value +val+ for the option called +name+ is a valid hash. The
+    # parameter +val+ can be
+    #
+    # - a hash in YAML format
+    # - or a Ruby Hash object.
+    def self.simple_hash_validator(val, name)
+      if String === val
+        begin
+          val = YAML.load(val)
+        rescue RuntimeError, ArgumentError, SyntaxError
+          raise Kramdown::Error, "Invalid YAML value for option #{name}"
+        end
+      end
+      raise Kramdown::Error, "Invalid type #{val.class} for option #{name}" if !(Hash === val)
+      val
+    end
+
+    # ----------------------------
+    # :section: Option Definitions
+    #
+    # This sections contains all option definitions that are used by the included
+    # parsers/converters.
+    # ----------------------------
+
+    define(:template, String, '', <<EOF)
+The name of an ERB template file that should be used to wrap the output
+or the ERB template itself.
+
+This is used to wrap the output in an environment so that the output can
+be used as a stand-alone document. For example, an HTML template would
+provide the needed header and body tags so that the whole output is a
+valid HTML file. If no template is specified, the output will be just
+the converted text.
+
+When resolving the template file, the given template name is used first.
+If such a file is not found, the converter extension (the same as the
+converter name) is appended. If the file still cannot be found, the
+templates name is interpreted as a template name that is provided by
+kramdown (without the converter extension). If the file is still not
+found, the template name is checked if it starts with 'string://' and if
+it does, this prefix is removed and the rest is used as template
+content.
+
+kramdown provides a default template named 'document' for each converter.
+
+Default: ''
+Used by: all converters
+EOF
+
+    define(:auto_ids, Boolean, true, <<EOF)
+Use automatic header ID generation
+
+If this option is `true`, ID values for all headers are automatically
+generated if no ID is explicitly specified.
+
+Default: true
+Used by: HTML/Latex converter
+EOF
+
+    define(:auto_id_stripping, Boolean, false, <<EOF)
+Strip all formatting from header text for automatic ID generation
+
+If this option is `true`, only the text elements of a header are used
+for generating the ID later (in contrast to just using the raw header
+text line).
+
+This option will be removed in version 2.0 because this will be the
+default then.
+
+Default: false
+Used by: kramdown parser
+EOF
+
+    define(:auto_id_prefix, String, '', <<EOF)
+Prefix used for automatically generated header IDs
+
+This option can be used to set a prefix for the automatically generated
+header IDs so that there is no conflict when rendering multiple kramdown
+documents into one output file separately. The prefix should only
+contain characters that are valid in an ID!
+
+Default: ''
+Used by: HTML/Latex converter
+EOF
+
+    define(:transliterated_header_ids, Boolean, false, <<EOF)
+Transliterate the header text before generating the ID
+
+Only ASCII characters are used in headers IDs. This is not good for
+languages with many non-ASCII characters. By enabling this option
+the header text is transliterated to ASCII as good as possible so that
+the resulting header ID is more useful.
+
+The stringex library needs to be installed for this feature to work!
+
+Default: false
+Used by: HTML/Latex converter
+EOF
+
+    define(:parse_block_html, Boolean, false, <<EOF)
+Process kramdown syntax in block HTML tags
+
+If this option is `true`, the kramdown parser processes the content of
+block HTML tags as text containing block-level elements. Since this is
+not wanted normally, the default is `false`. It is normally better to
+selectively enable kramdown processing via the markdown attribute.
+
+Default: false
+Used by: kramdown parser
+EOF
+
+    define(:parse_span_html, Boolean, true, <<EOF)
+Process kramdown syntax in span HTML tags
+
+If this option is `true`, the kramdown parser processes the content of
+span HTML tags as text containing span-level elements.
+
+Default: true
+Used by: kramdown parser
+EOF
+
+    define(:html_to_native, Boolean, false, <<EOF)
+Convert HTML elements to native elements
+
+If this option is `true`, the parser converts HTML elements to native
+elements. For example, when parsing `<em>hallo</em>` the emphasis tag
+would normally be converted to an `:html` element with tag type `:em`.
+If `html_to_native` is `true`, then the emphasis would be converted to a
+native `:em` element.
+
+This is useful for converters that cannot deal with HTML elements.
+
+Default: false
+Used by: kramdown parser
+EOF
+
+    define(:link_defs, Object, {}, <<EOF) do |val|
+Pre-defines link definitions
+
+This option can be used to pre-define link definitions. The value needs
+to be a Hash where the keys are the link identifiers and the values are
+two element Arrays with the link URL and the link title.
+
+If the value is a String, it has to contain a valid YAML hash and the
+hash has to follow the above guidelines.
+
+Default: {}
+Used by: kramdown parser
+EOF
+      val = simple_hash_validator(val, :link_defs)
+      val.each do |k,v|
+        if !(Array === v) || v.size > 2 || v.size < 1
+          raise Kramdown::Error, "Invalid structure for hash value of option #{name}"
+        end
+        v << nil if v.size == 1
+      end
+      val
+    end
+
+    define(:footnote_nr, Integer, 1, <<EOF)
+The number of the first footnote
+
+This option can be used to specify the number that is used for the first
+footnote.
+
+Default: 1
+Used by: HTML converter
+EOF
+
+    define(:enable_coderay, Boolean, true, <<EOF)
+Use coderay for syntax highlighting
+
+If this option is `true`, coderay is used by the HTML converter for
+syntax highlighting the content of code spans and code blocks.
+
+Default: true
+Used by: HTML converter
+EOF
+
+    define(:coderay_wrap, Symbol, :div, <<EOF)
+Defines how the highlighted code should be wrapped
+
+The possible values are :span, :div or nil.
+
+Default: :div
+Used by: HTML converter
+EOF
+
+    define(:coderay_line_numbers, Symbol, :inline, <<EOF)
+Defines how and if line numbers should be shown
+
+The possible values are :table, :inline or nil. If this option is
+nil, no line numbers are shown.
+
+Default: :inline
+Used by: HTML converter
+EOF
+
+    define(:coderay_line_number_start, Integer, 1, <<EOF)
+The start value for the line numbers
+
+Default: 1
+Used by: HTML converter
+EOF
+
+    define(:coderay_tab_width, Integer, 8, <<EOF)
+The tab width used in highlighted code
+
+Used by: HTML converter
+EOF
+
+    define(:coderay_bold_every, Object, 10, <<EOF) do |val|
+Defines how often a line number should be made bold
+
+Can either be an integer or false (to turn off bold line numbers
+completely).
+
+Default: 10
+Used by: HTML converter
+EOF
+      if val == false || val.to_s == 'false'
+        false
+      else
+        Integer(val.to_s) rescue raise Kramdown::Error, "Invalid value for option 'coderay_bold_every'"
+      end
+end
+
+    define(:coderay_css, Symbol, :style, <<EOF)
+Defines how the highlighted code gets styled
+
+Possible values are :class (CSS classes are applied to the code
+elements, one must supply the needed CSS file) or :style (default CSS
+styles are directly applied to the code elements).
+
+Default: style
+Used by: HTML converter
+EOF
+
+    define(:coderay_default_lang, Symbol, nil, <<EOF)
+Sets the default language for highlighting code blocks
+
+If no language is set for a code block, the default language is used
+instead. The value has to be one of the languages supported by coderay
+or nil if no default language should be used.
+
+Default: nil
+Used by: HTML converter
+EOF
+
+    define(:entity_output, Symbol, :as_char, <<EOF)
+Defines how entities are output
+
+The possible values are :as_input (entities are output in the same
+form as found in the input), :numeric (entities are output in numeric
+form), :symbolic (entities are output in symbolic form if possible) or
+:as_char (entities are output as characters if possible, only available
+on Ruby 1.9).
+
+Default: :as_char
+Used by: HTML converter, kramdown converter
+EOF
+
+    define(:toc_levels, Object, (1..6).to_a, <<EOF) do |val|
+Defines the levels that are used for the table of contents
+
+The individual levels can be specified by separating them with commas
+(e.g. 1,2,3) or by using the range syntax (e.g. 1..3). Only the
+specified levels are used for the table of contents.
+
+Default: 1..6
+Used by: HTML/Latex converter
+EOF
+      if String === val
+        if val =~ /^(\d)\.\.(\d)$/
+          val = Range.new($1.to_i, $2.to_i).to_a
+        elsif val =~ /^\d(?:,\d)*$/
+          val = val.split(/,/).map {|s| s.to_i}.uniq
+        else
+          raise Kramdown::Error, "Invalid syntax for option toc_levels"
+        end
+      elsif Array === val
+        val = val.map {|s| s.to_i}.uniq
+      else
+        raise Kramdown::Error, "Invalid type #{val.class} for option toc_levels"
+      end
+      if val.any? {|i| !(1..6).include?(i)}
+        raise Kramdown::Error, "Level numbers for option toc_levels have to be integers from 1 to 6"
+      end
+      val
+    end
+
+    define(:line_width, Integer, 72, <<EOF)
+Defines the line width to be used when outputting a document
+
+Default: 72
+Used by: kramdown converter
+EOF
+
+    define(:latex_headers, Object, %w{section subsection subsubsection paragraph subparagraph subparagraph}, <<EOF) do |val|
+Defines the LaTeX commands for different header levels
+
+The commands for the header levels one to six can be specified by
+separating them with commas.
+
+Default: section,subsection,subsubsection,paragraph,subparagraph,subparagraph
+Used by: Latex converter
+EOF
+      simple_array_validator(val, :latex_headers, 6)
+    end
+
+    define(:smart_quotes, Object, %w{lsquo rsquo ldquo rdquo}, <<EOF) do |val|
+Defines the HTML entity names or code points for smart quote output
+
+The entities identified by entity name or code point that should be
+used for, in order, a left single quote, a right single quote, a left
+double and a right double quote are specified by separating them with
+commas.
+
+Default: lsquo,rsquo,ldquo,rdquo
+Used by: HTML/Latex converter
+EOF
+      val = simple_array_validator(val, :smart_quotes, 4)
+      # RM val.map! {|v| Integer(v) rescue v} TODO
+      val
+    end
+
+    define(:remove_block_html_tags, Boolean, true, <<EOF)
+Remove block HTML tags
+
+If this option is `true`, the RemoveHtmlTags converter removes
+block HTML tags.
+
+Default: true
+Used by: RemoveHtmlTags converter
+EOF
+
+    define(:remove_span_html_tags, Boolean, false, <<EOF)
+Remove span HTML tags
+
+If this option is `true`, the RemoveHtmlTags converter removes
+span HTML tags.
+
+Default: false
+Used by: RemoveHtmlTags converter
+EOF
+
+    define(:header_offset, Integer, 0, <<EOF)
+Sets the output offset for headers
+
+If this option is c (may also be negative) then a header with level n
+will be output as a header with level c+n. If c+n is lower than 1,
+level 1 will be used. If c+n is greater than 6, level 6 will be used.
+
+Default: 0
+Used by: HTML converter, Kramdown converter, Latex converter
+EOF
+
+    define(:hard_wrap, Boolean, true, <<EOF)
+Interprets line breaks literally
+
+Insert HTML `<br />` tags inside paragraphs where the original Markdown
+document had newlines (by default, Markdown ignores these newlines).
+
+Default: true
+Used by: GFM parser
+EOF
+
+    define(:syntax_highlighter, Symbol, :coderay, <<EOF)
+Set the syntax highlighter
+
+Specifies the syntax highlighter that should be used for highlighting
+code blocks and spans. If this option is set to +nil+, no syntax
+highlighting is done.
+
+Options for the syntax highlighter can be set with the
+syntax_highlighter_opts configuration option.
+
+Default: coderay
+Used by: HTML converter
+EOF
+
+    define(:syntax_highlighter_opts, Object, {}, <<EOF) do |val|
+Set the syntax highlighter options
+
+Specifies options for the syntax highlighter set via the
+syntax_highlighter configuration option.
+
+The value needs to be a hash with key-value pairs that are understood by
+the used syntax highlighter.
+
+Default: {}
+Used by: HTML converter
+EOF
+      val = simple_hash_validator(val, :syntax_highlighter_opts)
+      val.keys.each do |k|
+        val[k.kind_of?(String) ? str_to_sym(k) : k] = val.delete(k)
+      end
+      val
+    end
+
+    define(:math_engine, Symbol, :mathjax, <<EOF)
+Set the math engine
+
+Specifies the math engine that should be used for converting math
+blocks/spans. If this option is set to +nil+, no math engine is used and
+the math blocks/spans are output as is.
+
+Options for the selected math engine can be set with the
+math_engine_opts configuration option.
+
+Default: mathjax
+Used by: HTML converter
+EOF
+
+    define(:math_engine_opts, Object, {}, <<EOF) do |val|
+Set the math engine options
+
+Specifies options for the math engine set via the math_engine
+configuration option.
+
+The value needs to be a hash with key-value pairs that are understood by
+the used math engine.
+
+Default: {}
+Used by: HTML converter
+EOF
+      val = simple_hash_validator(val, :math_engine_opts)
+      val.keys.each do |k|
+        val[k.kind_of?(String) ? str_to_sym(k) : k] = val.delete(k)
+      end
+      val
+    end
+
+  end
+
+end

data/lib/kramdown/parser/base.rb

@@ -0,0 +1,130 @@
+# -*- coding: utf-8 -*-
+#
+#--
+# Copyright (C) 2009-2014 Thomas Leitner <t_leitner@gmx.at>
+#
+# This file is part of kramdown which is licensed under the MIT.
+#++
+#
+
+# RM require 'kramdown/utils/string_scanner'
+
+module Kramdown
+
+  module Parser
+
+    # == \Base class for parsers
+    #
+    # This class serves as base class for parsers. It provides common methods that can/should be
+    # used by all parsers, especially by those using StringScanner(Kramdown) for parsing.
+    #
+    # A parser object is used as a throw-away object, i.e. it is only used for storing the needed
+    # state information during parsing. Therefore one can't instantiate a parser object directly but
+    # only use the Base::parse method.
+    #
+    # == Implementing a parser
+    #
+    # Implementing a new parser is rather easy: just derive a new class from this class and put it
+    # in the Kramdown::Parser module -- the latter is needed so that the auto-detection of the new
+    # parser works correctly. Then you need to implement the +#parse+ method which has to contain
+    # the parsing code.
+    #
+    # Have a look at the Base::parse, Base::new and Base#parse methods for additional information!
+    class Base
+
+      # The hash with the parsing options.
+      attr_reader :options
+
+      # The array with the parser warnings.
+      attr_reader :warnings
+
+      # The original source string.
+      attr_reader :source
+
+      # The root element of element tree that is created from the source string.
+      attr_reader :root
+
+      # Initialize the parser object with the +source+ string and the parsing +options+.
+      #
+      # The @root element, the @warnings array and @text_type (specifies the default type for newly
+      # created text nodes) are automatically initialized.
+      def initialize(source, options)
+        @source = source
+        @options = Kramdown::Options.merge(options)
+        @root = Element.new(:root, nil, nil, :encoding => (source.encoding rescue nil), :location => 1)
+        @warnings = []
+        @text_type = :text
+      end
+      private_class_method(:new, :allocate)
+
+      # Parse the +source+ string into an element tree, possibly using the parsing +options+, and
+      # return the root element of the element tree and an array with warning messages.
+      #
+      # Initializes a new instance of the calling class and then calls the +#parse+ method that must
+      # be implemented by each subclass.
+      def self.parse(source, options = {})
+        parser = new(source, options)
+        parser.parse
+        [parser.root, parser.warnings]
+      end
+
+      # Parse the source string into an element tree.
+      #
+      # The parsing code should parse the source provided in @source and build an element tree the
+      # root of which should be @root.
+      #
+      # This is the only method that has to be implemented by sub-classes!
+      def parse
+        raise NotImplementedError
+      end
+
+      # Add the given warning +text+ to the warning array.
+      def warning(text)
+        @warnings << text
+        #TODO: add position information
+      end
+
+      # Modify the string +source+ to be usable by the parser (unifies line ending characters to
+      # +\n+ and makes sure +source+ ends with a new line character).
+      def adapt_source(source)
+        if source.respond_to?(:encode)
+          raise "The encoding of the source text is not valid!" if !source.valid_encoding?
+          source = source.encode('UTF-8')
+        end
+        source.gsub(/\r\n?/, "\n").chomp + "\n"
+      end
+
+      # This helper method adds the given +text+ either to the last element in the +tree+ if it is a
+      # +type+ element or creates a new text element with the given +type+.
+      def add_text(text, tree = @tree, type = @text_type)
+        last = tree.children.last
+        if last && last.type == type
+          last.value << text
+        elsif !text.empty?
+          tree.children << Element.new(type, text, nil, :location => (last && last.options[:location] || tree.options[:location]))
+        end
+      end
+
+      # Extract the part of the StringScanner +strscan+ backed string specified by the +range+. This
+      # method works correctly under Ruby 1.8 and Ruby 1.9.
+      def extract_string(range, strscan)
+        result = nil
+        if strscan.string.respond_to?(:encoding)
+          begin
+            enc = strscan.string.encoding
+            strscan.string.force_encoding('ASCII-8BIT')
+            result = strscan.string[range].force_encoding(enc)
+          ensure
+            strscan.string.force_encoding(enc)
+          end
+        else
+          result = strscan.string[range]
+        end
+        result
+      end
+
+    end
+
+  end
+
+end