redcloth.rb

来自「用ruby on rails写的一个博客程序,还不错..ruby on rail」· RB 代码 · 共 1,131 行 · 第 1/3 页

                "#{ sta }<#{ ht }#{ atts }>#{ content }</#{ ht }>"

            end
        end
    end

    LINK_RE = /
            ([\s\[{(]|[#{PUNCT}])?     # $pre
            "                          # start
            (#{C})                     # $atts
            ([^"]+?)                   # $text
            \s?
            (?:\(([^)]+?)\)(?="))?     # $title
            ":
            (\S+?)                     # $url
            (\/)?                      # $slash
            ([^\w\/;]*?)               # $post
            (?=<|\s|$)
        /x 

    def inline_textile_link( text ) 
        text.gsub!( LINK_RE ) do |m|
            pre,atts,text,title,url,slash,post = $~[1..7]

            url, url_title = check_refs( url )
            title ||= url_title
            
            atts = pba( atts )
            atts = " href=\"#{ url }#{ slash }\"#{ atts }"
            atts << " title=\"#{ title }\"" if title
            atts = shelve( atts ) if atts
            
            "#{ pre }<a#{ atts }>#{ text }</a>#{ post }"
        end
    end

    MARKDOWN_REFLINK_RE = /
            \[([^\[\]]+)\]      # $text
            [ ]?                # opt. space
            (?:\n[ ]*)?         # one optional newline followed by spaces
            \[(.*?)\]           # $id
        /x 

    def inline_markdown_reflink( text ) 
        text.gsub!( MARKDOWN_REFLINK_RE ) do |m|
            text, id = $~[1..2]

            if id.empty?
                url, title = check_refs( text )
            else
                url, title = check_refs( id )
            end
            
            atts = " href=\"#{ url }\""
            atts << " title=\"#{ title }\"" if title
            atts = shelve( atts )
            
            "<a#{ atts }>#{ text }</a>"
        end
    end

    MARKDOWN_LINK_RE = /
            \[([^\[\]]+)\]      # $text
            \(                  # open paren
            [ \t]*              # opt space
            <?(.+?)>?           # $href
            [ \t]*              # opt space
            (?:                 # whole title
            (['"])              # $quote
            (.*?)               # $title
            \3                  # matching quote
            )?                  # title is optional
            \)
        /x 

    def inline_markdown_link( text ) 
        text.gsub!( MARKDOWN_LINK_RE ) do |m|
            text, url, quote, title = $~[1..4]

            atts = " href=\"#{ url }\""
            atts << " title=\"#{ title }\"" if title
            atts = shelve( atts )
            
            "<a#{ atts }>#{ text }</a>"
        end
    end

    TEXTILE_REFS_RE =  /(^ *)\[([^\n]+?)\](#{HYPERLINK})(?=\s|$)/
    MARKDOWN_REFS_RE = /(^ *)\[([^\n]+?)\]:\s+<?(#{HYPERLINK})>?(?:\s+"((?:[^"]|\\")+)")?(?=\s|$)/m

    def refs( text )
        @rules.each do |rule_name|
            method( rule_name ).call( text ) if rule_name.to_s.match /^refs_/
        end
    end

    def refs_textile( text ) 
        text.gsub!( TEXTILE_REFS_RE ) do |m|
            flag, url = $~[2..3]
            @urlrefs[flag.downcase] = [url, nil]
            nil
        end
    end
    
    def refs_markdown( text )
        text.gsub!( MARKDOWN_REFS_RE ) do |m|
            flag, url = $~[2..3]
            title = $~[6]
            @urlrefs[flag.downcase] = [url, title]
            nil
        end
    end

    def check_refs( text ) 
        ret = @urlrefs[text.downcase] if text
        ret || [text, nil]
    end

    IMAGE_RE = /
            (<p>|.|^)            # start of line?
            \!                   # opening
            (\<|\=|\>)?          # optional alignment atts
            (#{C})               # optional style,class atts
            (?:\. )?             # optional dot-space
            ([^\s(!]+?)          # presume this is the src
            \s?                  # optional space
            (?:\(((?:[^\(\)]|\([^\)]+\))+?)\))?   # optional title
            \!                   # closing
            (?::#{ HYPERLINK })? # optional href
        /x 

    def inline_textile_image( text ) 
        text.gsub!( IMAGE_RE )  do |m|
            stln,algn,atts,url,title,href,href_a1,href_a2 = $~[1..8]
            atts = pba( atts )
            atts = " src=\"#{ url }\"#{ atts }"
            atts << " title=\"#{ title }\"" if title
            atts << " alt=\"#{ title }\"" 
            # size = @getimagesize($url);
            # if($size) $atts.= " $size[3]";

            href, alt_title = check_refs( href ) if href
            url, url_title = check_refs( url )

            out = ''
            out << "<a#{ shelve( " href=\"#{ href }\"" ) }>" if href
            out << "<img#{ shelve( atts ) } />"
            out << "</a>#{ href_a1 }#{ href_a2 }" if href
            
            if algn 
                algn = h_align( algn )
                if stln == "<p>"
                    out = "<p style=\"float:#{ algn }\">#{ out }"
                else
                    out = "#{ stln }<div style=\"float:#{ algn }\">#{ out }</div>"
                end
            else
                out = stln + out
            end

            out
        end
    end

    def shelve( val ) 
        @shelf << val
        " :redsh##{ @shelf.length }:"
    end
    
    def retrieve( text ) 
        @shelf.each_with_index do |r, i|
            text.gsub!( " :redsh##{ i + 1 }:", r )
        end
    end

    def incoming_entities( text ) 
        ## turn any incoming ampersands into a dummy character for now.
        ## This uses a negative lookahead for alphanumerics followed by a semicolon,
        ## implying an incoming html entity, to be skipped

        text.gsub!( /&(?![#a-z0-9]+;)/i, "x%x%" )
    end

    def no_textile( text ) 
        text.gsub!( /(^|\s)==([^=]+.*?)==(\s|$)?/,
            '\1<notextile>\2</notextile>\3' )
        text.gsub!( /^ *==([^=]+.*?)==/m,
            '\1<notextile>\2</notextile>\3' )
    end

    def clean_white_space( text ) 
        # normalize line breaks
        text.gsub!( /\r\n/, "\n" )
        text.gsub!( /\r/, "\n" )
        text.gsub!( /\t/, '    ' )
        text.gsub!( /^ +$/, '' )
        text.gsub!( /\n{3,}/, "\n\n" )
        text.gsub!( /"$/, "\" " )

        # if entire document is indented, flush
        # to the left side
        flush_left text
    end

    def flush_left( text )
        indt = 0
        if text =~ /^ /
            while text !~ /^ {#{indt}}\S/
                indt += 1
            end unless text.empty?
            if indt.nonzero?
                text.gsub!( /^ {#{indt}}/, '' )
            end
        end
    end

    def footnote_ref( text ) 
        text.gsub!( /\b\[([0-9]+?)\](\s)?/,
            '<sup><a href="#fn\1">\1</a></sup>\2' )
    end
    
    OFFTAGS = /(code|pre|kbd|notextile)/
    OFFTAG_MATCH = /(?:(<\/#{ OFFTAGS }>)|(<#{ OFFTAGS }[^>]*>))(.*?)(?=<\/?#{ OFFTAGS }|\Z)/mi
    OFFTAG_OPEN = /<#{ OFFTAGS }/
    OFFTAG_CLOSE = /<\/?#{ OFFTAGS }/
    HASTAG_MATCH = /(<\/?\w[^\n]*?>)/m
    ALLTAG_MATCH = /(<\/?\w[^\n]*?>)|.*?(?=<\/?\w[^\n]*?>|$)/m

    def glyphs_textile( text, level = 0 )
        if text !~ HASTAG_MATCH
            pgl text
            footnote_ref text
        else
            codepre = 0
            text.gsub!( ALLTAG_MATCH ) do |line|
                ## matches are off if we're between <code>, <pre> etc.
                if $1
                    if line =~ OFFTAG_OPEN
                        codepre += 1
                    elsif line =~ OFFTAG_CLOSE
                        codepre -= 1
                        codepre = 0 if codepre < 0
                    end 
                elsif codepre.zero?
                    glyphs_textile( line, level + 1 )
                else
                    htmlesc( line, :NoQuotes )
                end
                # p [level, codepre, line]

                line
            end
        end
    end

    def rip_offtags( text )
        if text =~ /<.*>/
            ## strip and encode <pre> content
            codepre, used_offtags = 0, {}
            text.gsub!( OFFTAG_MATCH ) do |line|
                if $3
                    offtag, aftertag = $4, $5
                    codepre += 1
                    used_offtags[offtag] = true
                    if codepre - used_offtags.length > 0
                        htmlesc( line, :NoQuotes ) unless used_offtags['notextile']
                        @pre_list.last << line
                        line = ""
                    else
                        htmlesc( aftertag, :NoQuotes ) if aftertag and not used_offtags['notextile']
                        line = "<redpre##{ @pre_list.length }>"
                        @pre_list << "#{ $3 }#{ aftertag }"
                    end
                elsif $1 and codepre > 0
                    if codepre - used_offtags.length > 0
                        htmlesc( line, :NoQuotes ) unless used_offtags['notextile']
                        @pre_list.last << line
                        line = ""
                    end
                    codepre -= 1 unless codepre.zero?
                    used_offtags = {} if codepre.zero?
                end 
                line
            end
        end
        text
    end

    def smooth_offtags( text )
        unless @pre_list.empty?
            ## replace <pre> content
            text.gsub!( /<redpre#(\d+)>/ ) { @pre_list[$1.to_i] }
        end
    end

    def inline( text ) 
        [/^inline_/, /^glyphs_/].each do |meth_re|
            @rules.each do |rule_name|
                method( rule_name ).call( text ) if rule_name.to_s.match( meth_re )
            end
        end
    end

    def h_align( text ) 
        H_ALGN_VALS[text]
    end

    def v_align( text ) 
        V_ALGN_VALS[text]
    end

    def textile_popup_help( name, windowW, windowH )
        ' <a target="_blank" href="http://hobix.com/textile/#' + helpvar + '" onclick="window.open(this.href, \'popupwindow\', \'width=' + windowW + ',height=' + windowH + ',scrollbars,resizable\'); return false;">' + name + '</a><br />'
    end

    # HTML cleansing stuff
    BASIC_TAGS = {
        'a' => ['href', 'title'],
        'img' => ['src', 'alt', 'title'],
        'br' => [],
        'i' => nil,
        'u' => nil, 
        'b' => nil,
        'pre' => nil,
        'kbd' => nil,
        'code' => ['lang'],
        'cite' => nil,
        'strong' => nil,
        'em' => nil,
        'ins' => nil,
        'sup' => nil,
        'sub' => nil,
        'del' => nil,
        'table' => nil,
        'tr' => nil,
        'td' => ['colspan', 'rowspan'],
        'th' => nil,
        'ol' => nil,
        'ul' => nil,
        'li' => nil,
        'p' => nil,
        'h1' => nil,
        'h2' => nil,
        'h3' => nil,
        'h4' => nil,
        'h5' => nil,
        'h6' => nil, 
        'blockquote' => ['cite']
    }

    def clean_html( text, tags = BASIC_TAGS )
        text.gsub!( /<!\[CDATA\[/, '' )
        text.gsub!( /<(\/*)(\w+)([^>]*)>/ ) do
            raw = $~
            tag = raw[2].downcase
            if tags.has_key? tag
                pcs = [tag]
                tags[tag].each do |prop|
                    ['"', "'", ''].each do |q|
                        q2 = ( q != '' ? q : '\s' )
                        if raw[3] =~ /#{prop}\s*=\s*#{q}([^#{q2}]+)#{q}/i
                            attrv = $1
                            next if prop == 'src' and attrv =~ %r{^(?!http)\w+:}
                            pcs << "#{prop}=\"#{$1.gsub('"', '\\"')}\""
                            break
                        end
                    end
                end if tags[tag]
                "<#{raw[1]}#{pcs.join " "}>"
            else
                " "
            end
        end
    end
end