filters: import more modern scripts

Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>

2 files changed, 1735 insertions, 0 deletions

diff --git a/filters/html-converters/resources/markdown.pl b/filters/html-converters/resources/markdown.pl
new file mode 100755
index 0000000..abec173
--- /dev/null
+++ b/filters/html-converters/resources/markdown.pl
@@ -0,0 +1,1731 @@
+#!/usr/bin/perl
+
+#
+# Markdown -- A text-to-HTML conversion tool for web writers
+#
+# Copyright (c) 2004 John Gruber
+# <http://daringfireball.net/projects/markdown/>
+#
+
+
+package Markdown;
+require 5.006_000;
+use strict;
+use warnings;
+
+use Digest::MD5 qw(md5_hex);
+use vars qw($VERSION);
+$VERSION = '1.0.1';
+# Tue 14 Dec 2004
+
+## Disabled; causes problems under Perl 5.6.1:
+use utf8;
+binmode( STDOUT, ":utf8" );  # c.f.: http://acis.openlib.org/dev/perl-unicode-struggle.html
+
+
+#
+# Global default settings:
+#
+my $g_empty_element_suffix = " />";     # Change to ">" for HTML output
+my $g_tab_width = 4;
+
+
+#
+# Globals:
+#
+
+# Regex to match balanced [brackets]. See Friedl's
+# "Mastering Regular Expressions", 2nd Ed., pp. 328-331.
+my $g_nested_brackets;
+$g_nested_brackets = qr{
+        (?>                                                             # Atomic matching
+           [^\[\]]+                                                     # Anything other than brackets
+         | 
+           \[
+                 (??{ $g_nested_brackets })             # Recursive set of nested brackets
+           \]
+        )*
+}x;
+
+
+# Table of hash values for escaped characters:
+my %g_escape_table;
+foreach my $char (split //, '\\`*_{}[]()>#+-.!') {
+        $g_escape_table{$char} = md5_hex($char);
+}
+
+
+# Global hashes, used by various utility routines
+my %g_urls;
+my %g_titles;
+my %g_html_blocks;
+
+# Used to track when we're inside an ordered or unordered list
+# (see _ProcessListItems() for details):
+my $g_list_level = 0;
+
+
+#### Blosxom plug-in interface ##########################################
+
+# Set $g_blosxom_use_meta to 1 to use Blosxom's meta plug-in to determine
+# which posts Markdown should process, using a "meta-markup: markdown"
+# header. If it's set to 0 (the default), Markdown will process all
+# entries.
+my $g_blosxom_use_meta = 0;
+
+sub start { 1; }
+sub story {
+        my($pkg, $path, $filename, $story_ref, $title_ref, $body_ref) = @_;
+
+        if ( (! $g_blosxom_use_meta) or
+             (defined($meta::markup) and ($meta::markup =~ /^\s*markdown\s*$/i))
+             ){
+                        $$body_ref  = Markdown($$body_ref);
+     }
+     1;
+}
+
+
+#### Movable Type plug-in interface #####################################
+eval {require MT};  # Test to see if we're running in MT.
+unless ($@) {
+    require MT;
+    import  MT;
+    require MT::Template::Context;
+    import  MT::Template::Context;
+
+        eval {require MT::Plugin};  # Test to see if we're running >= MT 3.0.
+        unless ($@) {
+                require MT::Plugin;
+                import  MT::Plugin;
+                my $plugin = new MT::Plugin({
+                        name => "Markdown",
+                        description => "A plain-text-to-HTML formatting plugin. (Version: $VERSION)",
+                        doc_link => 'http://daringfireball.net/projects/markdown/'
+                });
+                MT->add_plugin( $plugin );
+        }
+
+        MT::Template::Context->add_container_tag(MarkdownOptions => sub {
+                my $ctx  = shift;
+                my $args = shift;
+                my $builder = $ctx->stash('builder');
+                my $tokens = $ctx->stash('tokens');
+
+                if (defined ($args->{'output'}) ) {
+                        $ctx->stash('markdown_output', lc $args->{'output'});
+                }
+
+                defined (my $str = $builder->build($ctx, $tokens) )
+                        or return $ctx->error($builder->errstr);
+                $str;           # return value
+        });
+
+        MT->add_text_filter('markdown' => {
+                label     => 'Markdown',
+                docs      => 'http://daringfireball.net/projects/markdown/',
+                on_format => sub {
+                        my $text = shift;
+                        my $ctx  = shift;
+                        my $raw  = 0;
+                    if (defined $ctx) {
+                        my $output = $ctx->stash('markdown_output'); 
+                                if (defined $output  &&  $output =~ m/^html/i) {
+                                        $g_empty_element_suffix = ">";
+                                        $ctx->stash('markdown_output', '');
+                                }
+                                elsif (defined $output  &&  $output eq 'raw') {
+                                        $raw = 1;
+                                        $ctx->stash('markdown_output', '');
+                                }
+                                else {
+                                        $raw = 0;
+                                        $g_empty_element_suffix = " />";
+                                }
+                        }
+                        $text = $raw ? $text : Markdown($text);
+                        $text;
+                },
+        });
+
+        # If SmartyPants is loaded, add a combo Markdown/SmartyPants text filter:
+        my $smartypants;
+
+        {
+                no warnings "once";
+                $smartypants = $MT::Template::Context::Global_filters{'smarty_pants'};
+        }
+
+        if ($smartypants) {
+                MT->add_text_filter('markdown_with_smartypants' => {
+                        label     => 'Markdown With SmartyPants',
+                        docs      => 'http://daringfireball.net/projects/markdown/',
+                        on_format => sub {
+                                my $text = shift;
+                                my $ctx  = shift;
+                                if (defined $ctx) {
+                                        my $output = $ctx->stash('markdown_output'); 
+                                        if (defined $output  &&  $output eq 'html') {
+                                                $g_empty_element_suffix = ">";
+                                        }
+                                        else {
+                                                $g_empty_element_suffix = " />";
+                                        }
+                                }
+                                $text = Markdown($text);
+                                $text = $smartypants->($text, '1');
+                        },
+                });
+        }
+}
+else {
+#### BBEdit/command-line text filter interface ##########################
+# Needs to be hidden from MT (and Blosxom when running in static mode).
+
+    # We're only using $blosxom::version once; tell Perl not to warn us:
+        no warnings 'once';
+    unless ( defined($blosxom::version) ) {
+                use warnings;
+
+                #### Check for command-line switches: #################
+                my %cli_opts;
+                use Getopt::Long;
+                Getopt::Long::Configure('pass_through');
+                GetOptions(\%cli_opts,
+                        'version',
+                        'shortversion',
+                        'html4tags',
+                );
+                if ($cli_opts{'version'}) {             # Version info
+                        print "\nThis is Markdown, version $VERSION.\n";
+                        print "Copyright 2004 John Gruber\n";
+                        print "http://daringfireball.net/projects/markdown/\n\n";
+                        exit 0;
+                }
+                if ($cli_opts{'shortversion'}) {                # Just the version number string.
+                        print $VERSION;
+                        exit 0;
+                }
+                if ($cli_opts{'html4tags'}) {                   # Use HTML tag style instead of XHTML
+                        $g_empty_element_suffix = ">";
+                }
+
+
+                #### Process incoming text: ###########################
+                my $text;
+                {
+                        local $/;               # Slurp the whole file
+                        $text = <>;
+                }
+        print <<'EOT';
+<style>
+.markdown-body {
+    font-size: 14px;
+    line-height: 1.6;
+    overflow: hidden;
+}
+.markdown-body>*:first-child {
+    margin-top: 0 !important;
+}
+.markdown-body>*:last-child {
+    margin-bottom: 0 !important;
+}
+.markdown-body a.absent {
+    color: #c00;
+}
+.markdown-body a.anchor {
+    display: block;
+    padding-left: 30px;
+    margin-left: -30px;
+    cursor: pointer;
+    position: absolute;
+    top: 0;
+    left: 0;
+    bottom: 0;
+}
+.markdown-body h1, .markdown-body h2, .markdown-body h3, .markdown-body h4, .markdown-body h5, .markdown-body h6 {
+    margin: 20px 0 10px;
+    padding: 0;
+    font-weight: bold;
+    -webkit-font-smoothing: antialiased;
+    cursor: text;
+    position: relative;
+}
+.markdown-body h1 .mini-icon-link, .markdown-body h2 .mini-icon-link, .markdown-body h3 .mini-icon-link, .markdown-body h4 .mini-icon-link, .markdown-body h5 .mini-icon-link, .markdown-body h6 .mini-icon-link {
+    display: none;
+    color: #000;
+}
+.markdown-body h1:hover a.anchor, .markdown-body h2:hover a.anchor, .markdown-body h3:hover a.anchor, .markdown-body h4:hover a.anchor, .markdown-body h5:hover a.anchor, .markdown-body h6:hover a.anchor {
+    text-decoration: none;
+    line-height: 1;
+    padding-left: 0;
+    margin-left: -22px;
+    top: 15%}
+.markdown-body h1:hover a.anchor .mini-icon-link, .markdown-body h2:hover a.anchor .mini-icon-link, .markdown-body h3:hover a.anchor .mini-icon-link, .markdown-body h4:hover a.anchor .mini-icon-link, .markdown-body h5:hover a.anchor .mini-icon-link, .markdown-body h6:hover a.anchor .mini-icon-link {
+    display: inline-block;
+}
+.markdown-body h1 tt, .markdown-body h1 code, .markdown-body h2 tt, .markdown-body h2 code, .markdown-body h3 tt, .markdown-body h3 code, .markdown-body h4 tt, .markdown-body h4 code, .markdown-body h5 tt, .markdown-body h5 code, .markdown-body h6 tt, .markdown-body h6 code {
+    font-size: inherit;
+}
+.markdown-body h1 {
+    font-size: 28px;
+    color: #000;
+}
+.markdown-body h2 {
+    font-size: 24px;
+    border-bottom: 1px solid #ccc;
+    color: #000;
+}
+.markdown-body h3 {
+    font-size: 18px;
+}
+.markdown-body h4 {
+    font-size: 16px;
+}
+.markdown-body h5 {
+    font-size: 14px;
+}
+.markdown-body h6 {
+    color: #777;
+    font-size: 14px;
+}
+.markdown-body p, .markdown-body blockquote, .markdown-body ul, .markdown-body ol, .markdown-body dl, .markdown-body table, .markdown-body pre {
+    margin: 15px 0;
+}
+.markdown-body hr {
+    background: transparent url("/dirty-shade.png") repeat-x 0 0;
+    border: 0 none;
+    color: #ccc;
+    height: 4px;
+    padding: 0;
+}
+.markdown-body>h2:first-child, .markdown-body>h1:first-child, .markdown-body>h1:first-child+h2, .markdown-body>h3:first-child, .markdown-body>h4:first-child, .markdown-body>h5:first-child, .markdown-body>h6:first-child {
+    margin-top: 0;
+    padding-top: 0;
+}
+.markdown-body a:first-child h1, .markdown-body a:first-child h2, .markdown-body a:first-child h3, .markdown-body a:first-child h4, .markdown-body a:first-child h5, .markdown-body a:first-child h6 {
+    margin-top: 0;
+    padding-top: 0;
+}
+.markdown-body h1+p, .markdown-body h2+p, .markdown-body h3+p, .markdown-body h4+p, .markdown-body h5+p, .markdown-body h6+p {
+    margin-top: 0;
+}
+.markdown-body li p.first {
+    display: inline-block;
+}
+.markdown-body ul, .markdown-body ol {
+    padding-left: 30px;
+}
+.markdown-body ul.no-list, .markdown-body ol.no-list {
+    list-style-type: none;
+    padding: 0;
+}
+.markdown-body ul li>:first-child, .markdown-body ul li ul:first-of-type, .markdown-body ul li ol:first-of-type, .markdown-body ol li>:first-child, .markdown-body ol li ul:first-of-type, .markdown-body ol li ol:first-of-type {
+    margin-top: 0px;
+}
+.markdown-body ul li p:last-of-type, .markdown-body ol li p:last-of-type {
+    margin-bottom: 0;
+}
+.markdown-body ul ul, .markdown-body ul ol, .markdown-body ol ol, .markdown-body ol ul {
+    margin-bottom: 0;
+}
+.markdown-body dl {
+    padding: 0;
+}
+.markdown-body dl dt {
+    font-size: 14px;
+    font-weight: bold;
+    font-style: italic;
+    padding: 0;
+    margin: 15px 0 5px;
+}
+.markdown-body dl dt:first-child {
+    padding: 0;
+}
+.markdown-body dl dt>:first-child {
+    margin-top: 0px;
+}
+.markdown-body dl dt>:last-child {
+    margin-bottom: 0px;
+}
+.markdown-body dl dd {
+    margin: 0 0 15px;
+    padding: 0 15px;
+}
+.markdown-body dl dd>:first-child {
+    margin-top: 0px;
+}
+.markdown-body dl dd>:last-child {
+    margin-bottom: 0px;
+}
+.markdown-body blockquote {
+    border-left: 4px solid #DDD;
+    padding: 0 15px;
+    color: #777;
+}
+.markdown-body blockquote>:first-child {
+    margin-top: 0px;
+}
+.markdown-body blockquote>:last-child {
+    margin-bottom: 0px;
+}
+.markdown-body table th {
+    font-weight: bold;
+}
+.markdown-body table th, .markdown-body table td {
+    border: 1px solid #ccc;
+    padding: 6px 13px;
+}
+.markdown-body table tr {
+    border-top: 1px solid #ccc;
+    background-color: #fff;
+}
+.markdown-body table tr:nth-child(2n) {
+    background-color: #f8f8f8;
+}
+.markdown-body img {
+    max-width: 100%;
+    -moz-box-sizing: border-box;
+    box-sizing: border-box;
+}
+.markdown-body span.frame {
+    display: block;
+    overflow: hidden;
+}
+.markdown-body span.frame>span {
+    border: 1px solid #ddd;
+    display: block;
+    float: left;
+    overflow: hidden;
+    margin: 13px 0 0;
+    padding: 7px;
+    width: auto;
+}
+.markdown-body span.frame span img {
+    display: block;
+    float: left;
+}
+.markdown-body span.frame span span {
+    clear: both;
+    color: #333;
+    display: block;
+    padding: 5px 0 0;
+}
+.markdown-body span.align-center {
+    display: block;
+    overflow: hidden;
+    clear: both;
+}
+.markdown-body span.align-center>span {
+    display: block;
+    overflow: hidden;
+    margin: 13px auto 0;
+    text-align: center;
+}
+.markdown-body span.align-center span img {
+    margin: 0 auto;
+    text-align: center;
+}
+.markdown-body span.align-right {
+    display: block;
+    overflow: hidden;
+    clear: both;
+}
+.markdown-body span.align-right>span {
+    display: block;
+    overflow: hidden;
+    margin: 13px 0 0;
+    text-align: right;
+}
+.markdown-body span.align-right span img {
+    margin: 0;
+    text-align: right;
+}
+.markdown-body span.float-left {
+    display: block;
+    margin-right: 13px;
+    overflow: hidden;
+    float: left;
+}
+.markdown-body span.float-left span {
+    margin: 13px 0 0;
+}
+.markdown-body span.float-right {
+    display: block;
+    margin-left: 13px;
+    overflow: hidden;
+    float: right;
+}
+.markdown-body span.float-right>span {
+    display: block;
+    overflow: hidden;
+    margin: 13px auto 0;
+    text-align: right;
+}
+.markdown-body code, .markdown-body tt {
+    margin: 0 2px;
+    padding: 0px 5px;
+    border: 1px solid #eaeaea;
+    background-color: #f8f8f8;
+    border-radius: 3px;
+}
+.markdown-body code {
+    white-space: nowrap;
+}
+.markdown-body pre>code {
+    margin: 0;
+    padding: 0;
+    white-space: pre;
+    border: none;
+    background: transparent;
+}
+.markdown-body .highlight pre, .markdown-body pre {
+    background-color: #f8f8f8;
+    border: 1px solid #ccc;
+    font-size: 13px;
+    line-height: 19px;
+    overflow: auto;
+    padding: 6px 10px;
+    border-radius: 3px;
+}
+.markdown-body pre code, .markdown-body pre tt {
+    margin: 0;
+    padding: 0;
+    background-color: transparent;
+    border: none;
+}
+</style>
+EOT
+        print "<div class='markdown-body'>";
+        print Markdown($text);
+        print "</div>";
+    }
+}
+
+
+
+sub Markdown {
+#
+# Main function. The order in which other subs are called here is
+# essential. Link and image substitutions need to happen before
+# _EscapeSpecialChars(), so that any *'s or _'s in the <a>
+# and <img> tags get encoded.
+#
+        my $text = shift;
+
+        # Clear the global hashes. If we don't clear these, you get conflicts
+        # from other articles when generating a page which contains more than
+        # one article (e.g. an index page that shows the N most recent
+        # articles):
+        %g_urls = ();
+        %g_titles = ();
+        %g_html_blocks = ();
+
+
+        # Standardize line endings:
+        $text =~ s{\r\n}{\n}g;  # DOS to Unix
+        $text =~ s{\r}{\n}g;    # Mac to Unix
+
+        # Make sure $text ends with a couple of newlines:
+        $text .= "\n\n";
+
+        # Convert all tabs to spaces.
+        $text = _Detab($text);
+
+        # Strip any lines consisting only of spaces and tabs.
+        # This makes subsequent regexen easier to write, because we can
+        # match consecutive blank lines with /\n+/ instead of something
+        # contorted like /[ \t]*\n+/ .
+        $text =~ s/^[ \t]+$//mg;
+
+        # Turn block-level HTML blocks into hash entries
+        $text = _HashHTMLBlocks($text);
+
+        # Strip link definitions, store in hashes.
+        $text = _StripLinkDefinitions($text);
+
+        $text = _RunBlockGamut($text);
+
+        $text = _UnescapeSpecialChars($text);
+
+        return $text . "\n";
+}
+
+
+sub _StripLinkDefinitions {
+#
+# Strips link definitions from text, stores the URLs and titles in
+# hash references.
+#
+        my $text = shift;
+        my $less_than_tab = $g_tab_width - 1;
+
+        # Link defs are in the form: ^[id]: url "optional title"
+        while ($text =~ s{
+                                                ^[ ]{0,$less_than_tab}\[(.+)\]: # id = $1
+                                                  [ \t]*
+                                                  \n?                           # maybe *one* newline
+                                                  [ \t]*
+                                                <?(\S+?)>?                      # url = $2
+                                                  [ \t]*
+                                                  \n?                           # maybe one newline
+                                                  [ \t]*
+                                                (?:
+                                                        (?<=\s)                 # lookbehind for whitespace
+                                                        ["(]
+                                                        (.+?)                   # title = $3
+                                                        [")]
+                                                        [ \t]*
+                                                )?      # title is optional
+                                                (?:\n+|\Z)
+                                        }
+                                        {}mx) {
+                $g_urls{lc $1} = _EncodeAmpsAndAngles( $2 );    # Link IDs are case-insensitive
+                if ($3) {
+                        $g_titles{lc $1} = $3;
+                        $g_titles{lc $1} =~ s/"/&quot;/g;
+                }
+        }
+
+        return $text;
+}
+
+
+sub _HashHTMLBlocks {
+        my $text = shift;
+        my $less_than_tab = $g_tab_width - 1;
+
+        # Hashify HTML blocks:
+        # We only want to do this for block-level HTML tags, such as headers,
+        # lists, and tables. That's because we still want to wrap <p>s around
+        # "paragraphs" that are wrapped in non-block-level tags, such as anchors,
+        # phrase emphasis, and spans. The list of tags we're looking for is
+        # hard-coded:
+        my $block_tags_a = qr/p|div|h[1-6]|blockquote|pre|table|dl|ol|ul|script|noscript|form|fieldset|iframe|math|ins|del/;
+        my $block_tags_b = qr/p|div|h[1-6]|blockquote|pre|table|dl|ol|ul|script|noscript|form|fieldset|iframe|math/;
+
+        # First, look for nested blocks, e.g.:
+        #       <div>
+        #               <div>
+        #               tags for inner block must be indented.
+        #               </div>
+        #       </div>
+        #
+        # The outermost tags must start at the left margin for this to match, and
+        # the inner nested divs must be indented.
+        # We need to do this before the next, more liberal match, because the next
+        # match will start at the first `<div>` and stop at the first `</div>`.
+        $text =~ s{
+                                (                                               # save in $1
+                                        ^                                       # start of line  (with /m)
+                                        <($block_tags_a)        # start tag = $2
+                                        \b                                      # word break
+                                        (.*\n)*?                        # any number of lines, minimally matching
+                                        </\2>                           # the matching end tag
+                                        [ \t]*                          # trailing spaces/tabs
+                                        (?=\n+|\Z)      # followed by a newline or end of document
+                                )
+                        }{
+                                my $key = md5_hex($1);
+                                $g_html_blocks{$key} = $1;
+                                "\n\n" . $key . "\n\n";
+                        }egmx;
+
+
+        #
+        # Now match more liberally, simply from `\n<tag>` to `</tag>\n`
+        #
+        $text =~ s{
+                                (                                               # save in $1
+                                        ^                                       # start of line  (with /m)
+                                        <($block_tags_b)        # start tag = $2
+                                        \b                                      # word break
+                                        (.*\n)*?                        # any number of lines, minimally matching
+                                        .*</\2>                         # the matching end tag
+                                        [ \t]*                          # trailing spaces/tabs
+                                        (?=\n+|\Z)      # followed by a newline or end of document
+                                )
+                        }{
+                                my $key = md5_hex($1);
+                                $g_html_blocks{$key} = $1;
+                                "\n\n" . $key . "\n\n";
+                        }egmx;
+        # Special case just for <hr />. It was easier to make a special case than
+        # to make the other regex more complicated.     
+        $text =~ s{
+                                (?:
+                                        (?<=\n\n)               # Starting after a blank line
+                                        |                               # or
+                                        \A\n?                   # the beginning of the doc
+                                )
+                                (                                               # save in $1
+                                        [ ]{0,$less_than_tab}
+                                        <(hr)                           # start tag = $2
+                                        \b                                      # word break
+                                        ([^<>])*?                       # 
+                                        /?>                                     # the matching end tag
+                                        [ \t]*
+                                        (?=\n{2,}|\Z)           # followed by a blank line or end of document
+                                )
+                        }{
+