rtomayko-rdiscount 1.3.1.1

data/ext/resource.c

@@ -0,0 +1,169 @@
+/* markdown: a C implementation of John Gruber's Markdown markup language.
+ *
+ * Copyright (C) 2007 David L Parsons.
+ * The redistribution terms are provided in the COPYRIGHT file that must
+ * be distributed with this source code.
+ */
+#include <stdio.h>
+#include <string.h>
+#include <stdarg.h>
+#include <stdlib.h>
+#include <time.h>
+#include <ctype.h>
+
+#include "config.h"
+
+#include "cstring.h"
+#include "markdown.h"
+#include "amalloc.h"
+
+/* free a (single) line
+ */
+void
+___mkd_freeLine(Line *ptr)
+{
+    DELETE(ptr->text);
+    free(ptr);
+}
+
+
+/* free a list of lines
+ */
+void
+___mkd_freeLines(Line *p)
+{
+    if (p->next)
+	 ___mkd_freeLines(p->next);
+    ___mkd_freeLine(p);
+}
+
+
+/* bye bye paragraph.
+ */
+void
+___mkd_freeParagraph(Paragraph *p)
+{
+    if (p->next)
+	___mkd_freeParagraph(p->next);
+    if (p->down)
+	___mkd_freeParagraph(p->down);
+    if (p->text)
+	___mkd_freeLines(p->text);
+    if (p->ident)
+	free(p->ident);
+    free(p);
+}
+
+
+/* bye bye footnotes.
+ */
+void
+___mkd_freefootnotes(MMIOT *f)
+{
+    int i;
+
+    if ( f->footnotes ) {
+	for (i=0; i < S(*f->footnotes); i++) {
+	    DELETE(T(*f->footnotes)[i].tag);
+	    DELETE(T(*f->footnotes)[i].link);
+	    DELETE(T(*f->footnotes)[i].title);
+	}
+	DELETE(*f->footnotes);
+	free(f->footnotes);
+    }
+}
+
+
+/* initialize a new MMIOT
+ */
+void
+___mkd_initmmiot(MMIOT *f, void *footnotes)
+{
+    if ( f ) {
+	memset(f, 0, sizeof *f);
+	CREATE(f->in);
+	CREATE(f->out);
+	CREATE(f->Q);
+	if ( footnotes )
+	    f->footnotes = footnotes;
+	else {
+	    f->footnotes = malloc(sizeof f->footnotes[0]);
+	    CREATE(*f->footnotes);
+	}
+    }
+}
+
+
+/* free the contents of a MMIOT, but leave the object alone.
+ */
+void
+___mkd_freemmiot(MMIOT *f, void *footnotes)
+{
+    if ( f ) {
+	DELETE(f->in);
+	DELETE(f->out);
+	DELETE(f->Q);
+	if ( f->footnotes != footnotes )
+	    ___mkd_freefootnotes(f);
+	memset(f, 0, sizeof *f);
+    }
+}
+
+
+/* free lines up to an barrier.
+ */
+void
+___mkd_freeLineRange(Line *anchor, Line *stop)
+{
+    Line *r = anchor->next;
+
+    if ( r != stop ) {
+	while ( r && (r->next != stop) )
+	    r = r->next;
+	if ( r ) r->next = 0;
+	___mkd_freeLines(anchor->next);
+    }
+    anchor->next = 0;
+}
+
+
+/* clean up everything allocated in __mkd_compile()
+ */
+void
+mkd_cleanup(Document *doc)
+{
+    if ( doc ) {
+	if ( doc->ctx ) {
+	    ___mkd_freemmiot(doc->ctx, 0);
+	    free(doc->ctx);
+	}
+
+	if ( doc->code) ___mkd_freeParagraph(doc->code);
+	if ( doc->headers ) ___mkd_freeLines(doc->headers);
+	if ( T(doc->content) ) ___mkd_freeLines(T(doc->content));
+	memset(doc, 0, sizeof doc[0]);
+	free(doc);
+    }
+}
+
+
+/* write output in XML format
+ */
+void
+___mkd_xml(char *p, int size, FILE *out)
+{
+    char c;
+
+    while ( size-- > 0 ) {
+	if ( !isascii(c = *p++) )
+	    continue;
+	switch (c) {
+	case '<': fputs("&lt;", out);   break;
+	case '>': fputs("&gt;", out);   break;
+	case '&': fputs("&amp;", out);  break;
+	case '"': fputs("&quot;", out); break;
+	case '\'':fputs("&apos;", out); break;
+	default:  putc(c,out);          break;
+	}
+    }
+}

data/ext/toc.c

@@ -0,0 +1,62 @@
+/*
+ * toc -- spit out a table of contents based on header blocks
+ *
+ * Copyright (C) 2008 Jjgod Jiang, David L Parsons.
+ * The redistribution terms are provided in the COPYRIGHT file that must
+ * be distributed with this source code.
+ */
+#include "config.h"
+#include <stdio.h>
+#include <stdlib.h>
+#include <ctype.h>
+
+#include "cstring.h"
+#include "markdown.h"
+#include "amalloc.h"
+
+/* write an header index
+ */
+int
+mkd_generatetoc(Document *p, FILE *output)
+{
+    Paragraph *pp;
+
+    int last_hnumber = 0,
+	first_hnumber = 0;
+
+    if ( !(p && p->ctx) ) return -1;
+    if ( ! (p->ctx->flags & TOC) ) return 0;
+
+    for ( pp = p->code; pp ; pp = pp->next ) {
+        if ( pp->typ == HDR && pp->text ) {
+	    
+	    if ( last_hnumber == pp->hnumber )
+		fprintf(output, "%*s</li>\n", pp->hnumber, "");
+	    else while ( last_hnumber > pp->hnumber ) {
+		fprintf(output, "%*s</li>\n%*s</ul>\n",
+				 last_hnumber, "",
+				 last_hnumber-1,"");
+		--last_hnumber;
+	    }
+	    
+	    while ( pp->hnumber > last_hnumber ) {
+		fprintf(output, "\n%*s<ul>\n", pp->hnumber, "");
+		++last_hnumber;
+	    }
+	    fprintf(output, "%*s<li><a href=\"#", pp->hnumber, "");
+	    mkd_string_to_anchor(T(pp->text->text), S(pp->text->text), putc, output);
+	    fprintf(output, "\">");
+	    mkd_text(T(pp->text->text), S(pp->text->text), output, 0);
+	    fprintf(output, "</a>");
+        }
+    }
+
+    while ( last_hnumber > 0 ) {
+        fprintf(output, "%*s</li>\n%*s</ul>\n",
+			last_hnumber, "", last_hnumber, "");
+	--last_hnumber;
+    }
+
+    return 0;
+}
+

data/lib/markdown.rb

@@ -0,0 +1 @@
+require 'rdiscount'

data/lib/rdiscount.rb

@@ -0,0 +1,72 @@
+# Discount is an implementation of John Gruber's Markdown markup
+# language in C. It implements all of the language as described in
+# {Markdown Syntax}[http://daringfireball.net/projects/markdown/syntax]
+# and passes the Markdown 1.0 test suite. The RDiscount extension makes
+# the Discount processor available via a Ruby C Extension library.
+#
+# === Usage
+#
+# RDiscount implements the basic protocol popularized by RedCloth and adopted
+# by BlueCloth:
+#   require 'rdiscount'
+#   markdown = RDiscount.new("Hello World!")
+#   puts markdown.to_html
+#
+# === Replacing BlueCloth
+#
+# Inject RDiscount into your BlueCloth-using code by replacing your bluecloth
+# require statements with the following:
+#   begin
+#     require 'rdiscount'
+#     BlueCloth = RDiscount
+#   rescue LoadError
+#     require 'bluecloth'
+#   end
+#
+class RDiscount
+  VERSION = '1.3.1.1'
+
+  # Original Markdown formatted text.
+  attr_reader :text
+
+  # Set true to have smarty-like quote translation performed.
+  attr_accessor :smart
+
+  # Do not output <style> tags included in the source text.
+  attr_accessor :filter_styles
+
+  # Do not output any raw HTML included in the source text.
+  attr_accessor :filter_html
+
+  # RedCloth compatible line folding -- not used for Markdown but
+  # included for compatibility.
+  attr_accessor :fold_lines
+
+  # Enable Table Of Contents generation
+  attr_accessor :generate_toc
+
+  # Create a RDiscount Markdown processor. The +text+ argument
+  # should be a string containing Markdown text. Additional arguments may be
+  # supplied to set various processing options:
+  #
+  # * <tt>:smart</tt> - Enable SmartyPants processing.
+  # * <tt>:filter_styles</tt> - Do not output <tt><style></tt> tags.
+  # * <tt>:filter_html</tt> - Do not output any raw HTML tags included in
+  #   the source text.
+  # * <tt>:fold_lines</tt> - RedCloth compatible line folding (not used).
+  #
+  # NOTE: The <tt>:filter_styles</tt> extension is not yet implemented.
+  def initialize(text, *extensions)
+    @text  = text
+    @smart = nil
+    @filter_styles = nil
+    @filter_html = nil
+    @fold_lines = nil
+    extensions.each { |e| send("#{e}=", true) }
+  end
+
+end
+
+Markdown = RDiscount unless defined? Markdown
+
+require 'rdiscount.so'

data/rdiscount.gemspec

@@ -0,0 +1,47 @@
+Gem::Specification.new do |s|
+  s.name = 'rdiscount'
+  s.version = '1.3.1.1'
+  s.summary = "Fast Implementation of Gruber's Markdown in C"
+  s.date = '2009-01-31'
+  s.email = 'r@tomayko.com'
+  s.homepage = 'http://github.com/rtomayko/rdiscount'
+  s.has_rdoc = true
+  s.authors = ["Ryan Tomayko", "Andrew White"]
+  # = MANIFEST =
+  s.files = %w[
+    COPYING
+    README.markdown
+    Rakefile
+    bin/rdiscount
+    ext/amalloc.h
+    ext/config.h
+    ext/cstring.h
+    ext/docheader.c
+    ext/dumptree.c
+    ext/extconf.rb
+    ext/generate.c
+    ext/markdown.c
+    ext/markdown.h
+    ext/mkdio.c
+    ext/mkdio.h
+    ext/rbstrio.c
+    ext/rbstrio.h
+    ext/rdiscount.c
+    ext/resource.c
+    ext/toc.c
+    lib/markdown.rb
+    lib/rdiscount.rb
+    rdiscount.gemspec
+    test/benchmark.rb
+    test/benchmark.txt
+    test/markdown_test.rb
+    test/rdiscount_test.rb
+  ]
+  # = MANIFEST =
+  s.test_files = ["test/markdown_test.rb", "test/rdiscount_test.rb"]
+  s.extra_rdoc_files = ["COPYING"]
+  s.extensions = ["ext/extconf.rb"]
+  s.executables = ["rdiscount"]
+  s.require_paths = ["lib"]
+  s.rubyforge_project = 'wink'
+end

data/test/benchmark.rb

@@ -0,0 +1,56 @@
+require 'rubygems'
+
+iterations = 100
+test_file = "#{File.dirname(__FILE__)}/benchmark.txt"
+implementations = %w[BlueCloth RDiscount Maruku PEGMarkdown]
+
+# Attempt to require each implementation and remove any that are not
+# installed.
+implementations.reject! do |class_name|
+  begin
+    module_path =
+      if class_name == 'PEGMarkdown'
+        'peg_markdown'
+      else
+        class_name.downcase
+      end
+    require module_path
+    false
+  rescue LoadError => boom
+    module_path.tr! '_', '-'
+    puts "#{class_name} excluded. Try: gem install #{module_path}"
+    true
+  end
+end
+
+# Grab actual class objects.
+implementations.map! { |class_name| Object.const_get(class_name) }
+
+# The actual benchmark.
+def benchmark(implementation, text, iterations)
+  start = Time.now
+  iterations.times do |i|
+    implementation.new(text).to_html
+  end
+  Time.now - start
+end
+
+# Read test file
+test_data = File.read(test_file)
+
+# Prime the pump
+puts "Spinning up ..."
+implementations.each { |impl| benchmark(impl, test_data, 1) }
+
+# Run benchmarks; gather results.
+puts "Running benchmarks ..."
+results =
+  implementations.inject([]) do |r,impl|
+    GC.start
+    r << [ impl, benchmark(impl, test_data, iterations) ]
+  end
+
+puts "Results for #{iterations} iterations:"
+results.each do |impl,time|
+  printf "  %10s %09.06fs total time, %09.06fs average\n", "#{impl}:", time, time / iterations
+end

data/test/benchmark.txt

@@ -0,0 +1,306 @@
+Markdown: Basics
+================
+
+<ul id="ProjectSubmenu">
+    <li><a href="/projects/markdown/" title="Markdown Project Page">Main</a></li>
+    <li><a class="selected" title="Markdown Basics">Basics</a></li>
+    <li><a href="/projects/markdown/syntax" title="Markdown Syntax Documentation">Syntax</a></li>
+    <li><a href="/projects/markdown/license" title="Pricing and License Information">License</a></li>
+    <li><a href="/projects/markdown/dingus" title="Online Markdown Web Form">Dingus</a></li>
+</ul>
+
+
+Getting the Gist of Markdown's Formatting Syntax
+------------------------------------------------
+
+This page offers a brief overview of what it's like to use Markdown.
+The [syntax page] [s] provides complete, detailed documentation for
+every feature, but Markdown should be very easy to pick up simply by
+looking at a few examples of it in action. The examples on this page
+are written in a before/after style, showing example syntax and the
+HTML output produced by Markdown.
+
+It's also helpful to simply try Markdown out; the [Dingus] [d] is a
+web application that allows you type your own Markdown-formatted text
+and translate it to XHTML.
+
+**Note:** This document is itself written using Markdown; you
+can [see the source for it by adding '.text' to the URL] [src].
+
+  [s]: /projects/markdown/syntax  "Markdown Syntax"
+  [d]: /projects/markdown/dingus  "Markdown Dingus"
+  [src]: /projects/markdown/basics.text
+
+
+## Paragraphs, Headers, Blockquotes ##
+
+A paragraph is simply one or more consecutive lines of text, separated
+by one or more blank lines. (A blank line is any line that looks like a
+blank line -- a line containing nothing spaces or tabs is considered
+blank.) Normal paragraphs should not be intended with spaces or tabs.
+
+Markdown offers two styles of headers: *Setext* and *atx*.
+Setext-style headers for `<h1>` and `<h2>` are created by
+"underlining" with equal signs (`=`) and hyphens (`-`), respectively.
+To create an atx-style header, you put 1-6 hash marks (`#`) at the
+beginning of the line -- the number of hashes equals the resulting
+HTML header level.
+
+Blockquotes are indicated using email-style '`>`' angle brackets.
+
+Markdown:
+
+    A First Level Header
+    ====================
+    
+    A Second Level Header
+    ---------------------
+
+    Now is the time for all good men to come to
+    the aid of their country. This is just a
+    regular paragraph.
+
+    The quick brown fox jumped over the lazy
+    dog's back.
+    
+    ### Header 3
+
+    > This is a blockquote.
+    > 
+    > This is the second paragraph in the blockquote.
+    >
+    > ## This is an H2 in a blockquote
+
+
+Output:
+
+    <h1>A First Level Header</h1>
+    
+    <h2>A Second Level Header</h2>
+    
+    <p>Now is the time for all good men to come to
+    the aid of their country. This is just a
+    regular paragraph.</p>
+    
+    <p>The quick brown fox jumped over the lazy
+    dog's back.</p>
+    
+    <h3>Header 3</h3>
+    
+    <blockquote>
+        <p>This is a blockquote.</p>
+        
+        <p>This is the second paragraph in the blockquote.</p>
+        
+        <h2>This is an H2 in a blockquote</h2>
+    </blockquote>
+
+
+
+### Phrase Emphasis ###
+
+Markdown uses asterisks and underscores to indicate spans of emphasis.
+
+Markdown:
+
+    Some of these words *are emphasized*.
+    Some of these words _are emphasized also_.
+    
+    Use two asterisks for **strong emphasis**.
+    Or, if you prefer, __use two underscores instead__.
+
+Output:
+
+    <p>Some of these words <em>are emphasized</em>.
+    Some of these words <em>are emphasized also</em>.</p>
+    
+    <p>Use two asterisks for <strong>strong emphasis</strong>.
+    Or, if you prefer, <strong>use two underscores instead</strong>.</p>
+   
+
+
+## Lists ##
+
+Unordered (bulleted) lists use asterisks, pluses, and hyphens (`*`,
+`+`, and `-`) as list markers. These three markers are
+interchangable; this:
+
+    *   Candy.
+    *   Gum.
+    *   Booze.
+
+this:
+
+    +   Candy.
+    +   Gum.
+    +   Booze.
+
+and this:
+
+    -   Candy.
+    -   Gum.
+    -   Booze.
+
+all produce the same output:
+
+    <ul>
+    <li>Candy.</li>
+    <li>Gum.</li>
+    <li>Booze.</li>
+    </ul>
+
+Ordered (numbered) lists use regular numbers, followed by periods, as
+list markers:
+
+    1.  Red
+    2.  Green
+    3.  Blue
+
+Output:
+
+    <ol>
+    <li>Red</li>
+    <li>Green</li>
+    <li>Blue</li>
+    </ol>
+
+If you put blank lines between items, you'll get `<p>` tags for the
+list item text. You can create multi-paragraph list items by indenting
+the paragraphs by 4 spaces or 1 tab:
+
+    *   A list item.
+    
+        With multiple paragraphs.
+
+    *   Another item in the list.
+
+Output:
+
+    <ul>
+    <li><p>A list item.</p>
+    <p>With multiple paragraphs.</p></li>
+    <li><p>Another item in the list.</p></li>
+    </ul>
+    
+
+
+### Links ###
+
+Markdown supports two styles for creating links: *inline* and
+*reference*. With both styles, you use square brackets to delimit the
+text you want to turn into a link.
+
+Inline-style links use parentheses immediately after the link text.
+For example:
+
+    This is an [example link](http://example.com/).
+
+Output:
+
+    <p>This is an <a href="http://example.com/">
+    example link</a>.</p>
+
+Optionally, you may include a title attribute in the parentheses:
+
+    This is an [example link](http://example.com/ "With a Title").
+
+Output:
+
+    <p>This is an <a href="http://example.com/" title="With a Title">
+    example link</a>.</p>
+
+Reference-style links allow you to refer to your links by names, which
+you define elsewhere in your document:
+
+    I get 10 times more traffic from [Google][1] than from
+    [Yahoo][2] or [MSN][3].
+
+    [1]: http://google.com/        "Google"
+    [2]: http://search.yahoo.com/  "Yahoo Search"
+    [3]: http://search.msn.com/    "MSN Search"
+
+Output:
+
+    <p>I get 10 times more traffic from <a href="http://google.com/"
+    title="Google">Google</a> than from <a href="http://search.yahoo.com/"
+    title="Yahoo Search">Yahoo</a> or <a href="http://search.msn.com/"
+    title="MSN Search">MSN</a>.</p>
+
+The title attribute is optional. Link names may contain letters,
+numbers and spaces, but are *not* case sensitive:
+
+    I start my morning with a cup of coffee and
+    [The New York Times][NY Times].
+
+    [ny times]: http://www.nytimes.com/
+
+Output:
+
+    <p>I start my morning with a cup of coffee and
+    <a href="http://www.nytimes.com/">The New York Times</a>.</p>
+
+
+### Images ###
+
+Image syntax is very much like link syntax.
+
+Inline (titles are optional):
+
+    ![alt text](/path/to/img.jpg "Title")
+
+Reference-style:
+
+    ![alt text][id]
+
+    [id]: /path/to/img.jpg "Title"
+
+Both of the above examples produce the same output:
+
+    <img src="/path/to/img.jpg" alt="alt text" title="Title" />
+
+
+
+### Code ###
+
+In a regular paragraph, you can create code span by wrapping text in
+backtick quotes. Any ampersands (`&`) and angle brackets (`<` or
+`>`) will automatically be translated into HTML entities. This makes
+it easy to use Markdown to write about HTML example code:
+
+    I strongly recommend against using any `<blink>` tags.
+
+    I wish SmartyPants used named entities like `&mdash;`
+    instead of decimal-encoded entites like `&#8212;`.
+
+Output:
+
+    <p>I strongly recommend against using any
+    <code>&lt;blink&gt;</code> tags.</p>
+    
+    <p>I wish SmartyPants used named entities like
+    <code>&amp;mdash;</code> instead of decimal-encoded
+    entites like <code>&amp;#8212;</code>.</p>
+
+
+To specify an entire block of pre-formatted code, indent every line of
+the block by 4 spaces or 1 tab. Just like with code spans, `&`, `<`,
+and `>` characters will be escaped automatically.
+
+Markdown:
+
+    If you want your page to validate under XHTML 1.0 Strict,
+    you've got to put paragraph tags in your blockquotes:
+
+        <blockquote>
+            <p>For example.</p>
+        </blockquote>
+
+Output:
+
+    <p>If you want your page to validate under XHTML 1.0 Strict,
+    you've got to put paragraph tags in your blockquotes:</p>
+    
+    <pre><code>&lt;blockquote&gt;
+        &lt;p&gt;For example.&lt;/p&gt;
+    &lt;/blockquote&gt;
+    </code></pre>