", $text);
- }
- return $text;
- }
-
- function mdwp_strip_p($t) { return preg_replace('{?p>}i', '', $t); }
-
- function mdwp_hide_tags($text) {
- global $mdwp_hidden_tags, $mdwp_placeholders;
- return str_replace($mdwp_hidden_tags, $mdwp_placeholders, $text);
- }
- function mdwp_show_tags($text) {
- global $mdwp_hidden_tags, $mdwp_placeholders;
- return str_replace($mdwp_placeholders, $mdwp_hidden_tags, $text);
- }
-}
-
-
-### bBlog Plugin Info ###
-
-function identify_modifier_markdown() {
- return array(
- 'name' => 'markdown',
- 'type' => 'modifier',
- 'nicename' => 'PHP Markdown Extra',
- 'description' => 'A text-to-HTML conversion tool for web writers',
- 'authors' => 'Michel Fortin and John Gruber',
- 'licence' => 'GPL',
- 'version' => MARKDOWNEXTRA_VERSION,
- 'help' => 'Markdown syntax allows you to write using an easy-to-read, easy-to-write plain text format. Based on the original Perl version by John Gruber. More...',
- );
-}
-
-
-### Smarty Modifier Interface ###
-
-function smarty_modifier_markdown($text) {
- return Markdown($text);
-}
-
-
-### Textile Compatibility Mode ###
-
-# Rename this file to "classTextile.php" and it can replace Textile everywhere.
-
-if (strcasecmp(substr(__FILE__, -16), "classTextile.php") == 0) {
- # Try to include PHP SmartyPants. Should be in the same directory.
- @include_once 'smartypants.php';
- # Fake Textile class. It calls Markdown instead.
- class Textile {
- function TextileThis($text, $lite='', $encode='') {
- if ($lite == '' && $encode == '') $text = Markdown($text);
- if (function_exists('SmartyPants')) $text = SmartyPants($text);
- return $text;
- }
- # Fake restricted version: restrictions are not supported for now.
- function TextileRestricted($text, $lite='', $noimage='') {
- return $this->TextileThis($text, $lite);
- }
- # Workaround to ensure compatibility with TextPattern 4.0.3.
- function blockLite($text) { return $text; }
- }
-}
-
-
-
-#
-# Markdown Parser Class
-#
-
-class Markdown_Parser {
-
- ### Configuration Variables ###
-
- # Change to ">" for HTML output.
- var $empty_element_suffix = MARKDOWN_EMPTY_ELEMENT_SUFFIX;
- var $tab_width = MARKDOWN_TAB_WIDTH;
-
- # Change to `true` to disallow markup or entities.
- var $no_markup = false;
- var $no_entities = false;
-
- # Predefined urls and titles for reference links and images.
- var $predef_urls = array();
- var $predef_titles = array();
-
-
- ### Parser Implementation ###
-
- # Regex to match balanced [brackets].
- # Needed to insert a maximum bracked depth while converting to PHP.
- var $nested_brackets_depth = 6;
- var $nested_brackets_re;
-
- var $nested_url_parenthesis_depth = 4;
- var $nested_url_parenthesis_re;
-
- # Table of hash values for escaped characters:
- var $escape_chars = '\`*_{}[]()>#+-.!';
- var $escape_chars_re;
-
-
- function Markdown_Parser() {
- #
- # Constructor function. Initialize appropriate member variables.
- #
- $this->_initDetab();
- $this->prepareItalicsAndBold();
-
- $this->nested_brackets_re =
- str_repeat('(?>[^\[\]]+|\[', $this->nested_brackets_depth).
- str_repeat('\])*', $this->nested_brackets_depth);
-
- $this->nested_url_parenthesis_re =
- str_repeat('(?>[^()\s]+|\(', $this->nested_url_parenthesis_depth).
- str_repeat('(?>\)))*', $this->nested_url_parenthesis_depth);
-
- $this->escape_chars_re = '['.preg_quote($this->escape_chars).']';
-
- # Sort document, block, and span gamut in ascendent priority order.
- asort($this->document_gamut);
- asort($this->block_gamut);
- asort($this->span_gamut);
- }
-
-
- # Internal hashes used during transformation.
- var $urls = array();
- var $titles = array();
- var $html_hashes = array();
-
- # Status flag to avoid invalid nesting.
- var $in_anchor = false;
-
-
- function setup() {
- #
- # Called before the transformation process starts to setup parser
- # states.
- #
- # Clear global hashes.
- $this->urls = $this->predef_urls;
- $this->titles = $this->predef_titles;
- $this->html_hashes = array();
-
- $this->in_anchor = false;
- }
-
- function teardown() {
- #
- # Called after the transformation process to clear any variable
- # which may be taking up memory unnecessarly.
- #
- $this->urls = array();
- $this->titles = array();
- $this->html_hashes = array();
- }
-
-
- function transform($text) {
- #
- # Main function. Performs some preprocessing on the input text
- # and pass it through the document gamut.
- #
- $this->setup();
-
- # Remove UTF-8 BOM and marker character in input, if present.
- $text = preg_replace('{^\xEF\xBB\xBF|\x1A}', '', $text);
-
- # Standardize line endings:
- # DOS to Unix and Mac to Unix
- $text = preg_replace('{\r\n?}', "\n", $text);
-
- # Make sure $text ends with a couple of newlines:
- $text .= "\n\n";
-
- # Convert all tabs to spaces.
- $text = $this->detab($text);
-
- # Turn block-level HTML blocks into hash entries
- $text = $this->hashHTMLBlocks($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 /[ ]*\n+/ .
- $text = preg_replace('/^[ ]+$/m', '', $text);
-
- # Run document gamut methods.
- foreach ($this->document_gamut as $method => $priority) {
- $text = $this->$method($text);
- }
-
- $this->teardown();
-
- return $text . "\n";
- }
-
- var $document_gamut = array(
- # Strip link definitions, store in hashes.
- "stripLinkDefinitions" => 20,
-
- "runBasicBlockGamut" => 30,
- );
-
-
- function stripLinkDefinitions($text) {
- #
- # Strips link definitions from text, stores the URLs and titles in
- # hash references.
- #
- $less_than_tab = $this->tab_width - 1;
-
- # Link defs are in the form: ^[id]: url "optional title"
- $text = preg_replace_callback('{
- ^[ ]{0,'.$less_than_tab.'}\[(.+)\][ ]?: # id = $1
- [ ]*
- \n? # maybe *one* newline
- [ ]*
- (?:
- <(.+?)> # url = $2
- |
- (\S+?) # url = $3
- )
- [ ]*
- \n? # maybe one newline
- [ ]*
- (?:
- (?<=\s) # lookbehind for whitespace
- ["(]
- (.*?) # title = $4
- [")]
- [ ]*
- )? # title is optional
- (?:\n+|\Z)
- }xm',
- array(&$this, '_stripLinkDefinitions_callback'),
- $text);
- return $text;
- }
- function _stripLinkDefinitions_callback($matches) {
- $link_id = strtolower($matches[1]);
- $url = $matches[2] == '' ? $matches[3] : $matches[2];
- $this->urls[$link_id] = $url;
- $this->titles[$link_id] =& $matches[4];
- return ''; # String that will replace the block
- }
-
-
- function hashHTMLBlocks($text) {
- if ($this->no_markup) return $text;
-
- $less_than_tab = $this->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
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:
- #
- # * List "a" is made of tags which can be both inline or block-level.
- # These will be treated block-level when the start tag is alone on
- # its line, otherwise they're not matched here and will be taken as
- # inline later.
- # * List "b" is made of tags which are always block-level;
- #
- $block_tags_a_re = 'ins|del';
- $block_tags_b_re = 'p|div|h[1-6]|blockquote|pre|table|dl|ol|ul|address|'.
- 'script|noscript|form|fieldset|iframe|math|svg|'.
- 'article|section|nav|aside|hgroup|header|footer|'.
- 'figure';
-
- # Regular expression for the content of a block tag.
- $nested_tags_level = 4;
- $attr = '
- (?> # optional tag attributes
- \s # starts with whitespace
- (?>
- [^>"/]+ # text outside quotes
- |
- /+(?!>) # slash not followed by ">"
- |
- "[^"]*" # text inside double quotes (tolerate ">")
- |
- \'[^\']*\' # text inside single quotes (tolerate ">")
- )*
- )?
- ';
- $content =
- str_repeat('
- (?>
- [^<]+ # content without tag
- |
- <\2 # nested opening tag
- '.$attr.' # attributes
- (?>
- />
- |
- >', $nested_tags_level). # end of opening tag
- '.*?'. # last level nested tag content
- str_repeat('
- \2\s*> # closing nested tag
- )
- |
- <(?!/\2\s*> # other tags with a different name
- )
- )*',
- $nested_tags_level);
- $content2 = str_replace('\2', '\3', $content);
-
- # First, look for nested blocks, e.g.:
- #
- #
- # tags for inner block must be indented.
- #
- #
- #
- # 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 `
` and stop at the first `
`.
- $text = preg_replace_callback('{(?>
- (?>
- (?<=\n\n) # Starting after a blank line
- | # or
- \A\n? # the beginning of the doc
- )
- ( # save in $1
-
- # Match from `\n` to `\n`, handling nested tags
- # in between.
-
- [ ]{0,'.$less_than_tab.'}
- <('.$block_tags_b_re.')# start tag = $2
- '.$attr.'> # attributes followed by > and \n
- '.$content.' # content, support nesting
- \2> # the matching end tag
- [ ]* # trailing spaces/tabs
- (?=\n+|\Z) # followed by a newline or end of document
-
- | # Special version for tags of group a.
-
- [ ]{0,'.$less_than_tab.'}
- <('.$block_tags_a_re.')# start tag = $3
- '.$attr.'>[ ]*\n # attributes followed by >
- '.$content2.' # content, support nesting
- \3> # the matching end tag
- [ ]* # trailing spaces/tabs
- (?=\n+|\Z) # followed by a newline or end of document
-
- | # Special case just for . It was easier to make a special
- # case than to make the other regex more complicated.
-
- [ ]{0,'.$less_than_tab.'}
- <(hr) # start tag = $2
- '.$attr.' # attributes
- /?> # the matching end tag
- [ ]*
- (?=\n{2,}|\Z) # followed by a blank line or end of document
-
- | # Special case for standalone HTML comments:
-
- [ ]{0,'.$less_than_tab.'}
- (?s:
-
- )
- [ ]*
- (?=\n{2,}|\Z) # followed by a blank line or end of document
-
- | # PHP and ASP-style processor instructions ( and <%)
-
- [ ]{0,'.$less_than_tab.'}
- (?s:
- <([?%]) # $2
- .*?
- \2>
- )
- [ ]*
- (?=\n{2,}|\Z) # followed by a blank line or end of document
-
- )
- )}Sxmi',
- array(&$this, '_hashHTMLBlocks_callback'),
- $text);
-
- return $text;
- }
- function _hashHTMLBlocks_callback($matches) {
- $text = $matches[1];
- $key = $this->hashBlock($text);
- return "\n\n$key\n\n";
- }
-
-
- function hashPart($text, $boundary = 'X') {
- #
- # Called whenever a tag must be hashed when a function insert an atomic
- # element in the text stream. Passing $text to through this function gives
- # a unique text-token which will be reverted back when calling unhash.
- #
- # The $boundary argument specify what character should be used to surround
- # the token. By convension, "B" is used for block elements that needs not
- # to be wrapped into paragraph tags at the end, ":" is used for elements
- # that are word separators and "X" is used in the general case.
- #
- # Swap back any tag hash found in $text so we do not have to `unhash`
- # multiple times at the end.
- $text = $this->unhash($text);
-
- # Then hash the block.
- static $i = 0;
- $key = "$boundary\x1A" . ++$i . $boundary;
- $this->html_hashes[$key] = $text;
- return $key; # String that will replace the tag.
- }
-
-
- function hashBlock($text) {
- #
- # Shortcut function for hashPart with block-level boundaries.
- #
- return $this->hashPart($text, 'B');
- }
-
-
- var $block_gamut = array(
- #
- # These are all the transformations that form block-level
- # tags like paragraphs, headers, and list items.
- #
- "doHeaders" => 10,
- "doHorizontalRules" => 20,
-
- "doLists" => 40,
- "doCodeBlocks" => 50,
- "doBlockQuotes" => 60,
- );
-
- function runBlockGamut($text) {
- #
- # Run block gamut tranformations.
- #
- # We need to escape raw HTML in Markdown source before doing anything
- # else. This need to be done for each block, and not only at the
- # begining in the Markdown function since hashed blocks can be part of
- # list items and could have been indented. Indented blocks would have
- # been seen as a code block in a previous pass of hashHTMLBlocks.
- $text = $this->hashHTMLBlocks($text);
-
- return $this->runBasicBlockGamut($text);
- }
-
- function runBasicBlockGamut($text) {
- #
- # Run block gamut tranformations, without hashing HTML blocks. This is
- # useful when HTML blocks are known to be already hashed, like in the first
- # whole-document pass.
- #
- foreach ($this->block_gamut as $method => $priority) {
- $text = $this->$method($text);
- }
-
- # Finally form paragraph and restore hashed blocks.
- $text = $this->formParagraphs($text);
-
- return $text;
- }
-
-
- function doHorizontalRules($text) {
- # Do Horizontal Rules:
- return preg_replace(
- '{
- ^[ ]{0,3} # Leading space
- ([-*_]) # $1: First marker
- (?> # Repeated marker group
- [ ]{0,2} # Zero, one, or two spaces.
- \1 # Marker character
- ){2,} # Group repeated at least twice
- [ ]* # Tailing spaces
- $ # End of line.
- }mx',
- "\n".$this->hashBlock("empty_element_suffix")."\n",
- $text);
- }
-
-
- var $span_gamut = array(
- #
- # These are all the transformations that occur *within* block-level
- # tags like paragraphs, headers, and list items.
- #
- # Process character escapes, code spans, and inline HTML
- # in one shot.
- "parseSpan" => -30,
-
- # Process anchor and image tags. Images must come first,
- # because ![foo][f] looks like an anchor.
- "doImages" => 10,
- "doAnchors" => 20,
-
- # Make links out of things like ``
- # Must come after doAnchors, because you can use < and >
- # delimiters in inline links like [this]().
- "doAutoLinks" => 30,
- "encodeAmpsAndAngles" => 40,
-
- "doItalicsAndBold" => 50,
- "doHardBreaks" => 60,
- );
-
- function runSpanGamut($text) {
- #
- # Run span gamut tranformations.
- #
- foreach ($this->span_gamut as $method => $priority) {
- $text = $this->$method($text);
- }
-
- return $text;
- }
-
-
- function doHardBreaks($text) {
- # Do hard breaks:
- return preg_replace_callback('/ {2,}\n/',
- array(&$this, '_doHardBreaks_callback'), $text);
- }
- function _doHardBreaks_callback($matches) {
- return $this->hashPart(" empty_element_suffix\n");
- }
-
-
- function doAnchors($text) {
- #
- # Turn Markdown link shortcuts into XHTML tags.
- #
- if ($this->in_anchor) return $text;
- $this->in_anchor = true;
-
- #
- # First, handle reference-style links: [link text] [id]
- #
- $text = preg_replace_callback('{
- ( # wrap whole match in $1
- \[
- ('.$this->nested_brackets_re.') # link text = $2
- \]
-
- [ ]? # one optional space
- (?:\n[ ]*)? # one optional newline followed by spaces
-
- \[
- (.*?) # id = $3
- \]
- )
- }xs',
- array(&$this, '_doAnchors_reference_callback'), $text);
-
- #
- # Next, inline-style links: [link text](url "optional title")
- #
- $text = preg_replace_callback('{
- ( # wrap whole match in $1
- \[
- ('.$this->nested_brackets_re.') # link text = $2
- \]
- \( # literal paren
- [ \n]*
- (?:
- <(.+?)> # href = $3
- |
- ('.$this->nested_url_parenthesis_re.') # href = $4
- )
- [ \n]*
- ( # $5
- ([\'"]) # quote char = $6
- (.*?) # Title = $7
- \6 # matching quote
- [ \n]* # ignore any spaces/tabs between closing quote and )
- )? # title is optional
- \)
- )
- }xs',
- array(&$this, '_doAnchors_inline_callback'), $text);
-
- #
- # Last, handle reference-style shortcuts: [link text]
- # These must come last in case you've also got [link text][1]
- # or [link text](/foo)
- #
- $text = preg_replace_callback('{
- ( # wrap whole match in $1
- \[
- ([^\[\]]+) # link text = $2; can\'t contain [ or ]
- \]
- )
- }xs',
- array(&$this, '_doAnchors_reference_callback'), $text);
-
- $this->in_anchor = false;
- return $text;
- }
- function _doAnchors_reference_callback($matches) {
- $whole_match = $matches[1];
- $link_text = $matches[2];
- $link_id =& $matches[3];
-
- if ($link_id == "") {
- # for shortcut links like [this][] or [this].
- $link_id = $link_text;
- }
-
- # lower-case and turn embedded newlines into spaces
- $link_id = strtolower($link_id);
- $link_id = preg_replace('{[ ]?\n}', ' ', $link_id);
-
- if (isset($this->urls[$link_id])) {
- $url = $this->urls[$link_id];
- $url = $this->encodeAttribute($url);
-
- $result = "titles[$link_id] ) ) {
- $title = $this->titles[$link_id];
- $title = $this->encodeAttribute($title);
- $result .= " title=\"$title\"";
- }
-
- $link_text = $this->runSpanGamut($link_text);
- $result .= ">$link_text";
- $result = $this->hashPart($result);
- }
- else {
- $result = $whole_match;
- }
- return $result;
- }
- function _doAnchors_inline_callback($matches) {
- $whole_match = $matches[1];
- $link_text = $this->runSpanGamut($matches[2]);
- $url = $matches[3] == '' ? $matches[4] : $matches[3];
- $title =& $matches[7];
-
- $url = $this->encodeAttribute($url);
-
- $result = "encodeAttribute($title);
- $result .= " title=\"$title\"";
- }
-
- $link_text = $this->runSpanGamut($link_text);
- $result .= ">$link_text";
-
- return $this->hashPart($result);
- }
-
-
- function doImages($text) {
- #
- # Turn Markdown image shortcuts into tags.
- #
- #
- # First, handle reference-style labeled images: ![alt text][id]
- #
- $text = preg_replace_callback('{
- ( # wrap whole match in $1
- !\[
- ('.$this->nested_brackets_re.') # alt text = $2
- \]
-
- [ ]? # one optional space
- (?:\n[ ]*)? # one optional newline followed by spaces
-
- \[
- (.*?) # id = $3
- \]
-
- )
- }xs',
- array(&$this, '_doImages_reference_callback'), $text);
-
- #
- # Next, handle inline images: ![alt text](url "optional title")
- # Don't forget: encode * and _
- #
- $text = preg_replace_callback('{
- ( # wrap whole match in $1
- !\[
- ('.$this->nested_brackets_re.') # alt text = $2
- \]
- \s? # One optional whitespace character
- \( # literal paren
- [ \n]*
- (?:
- <(\S*)> # src url = $3
- |
- ('.$this->nested_url_parenthesis_re.') # src url = $4
- )
- [ \n]*
- ( # $5
- ([\'"]) # quote char = $6
- (.*?) # title = $7
- \6 # matching quote
- [ \n]*
- )? # title is optional
- \)
- )
- }xs',
- array(&$this, '_doImages_inline_callback'), $text);
-
- return $text;
- }
- function _doImages_reference_callback($matches) {
- $whole_match = $matches[1];
- $alt_text = $matches[2];
- $link_id = strtolower($matches[3]);
-
- if ($link_id == "") {
- $link_id = strtolower($alt_text); # for shortcut links like ![this][].
- }
-
- $alt_text = $this->encodeAttribute($alt_text);
- if (isset($this->urls[$link_id])) {
- $url = $this->encodeAttribute($this->urls[$link_id]);
- $result = "titles[$link_id])) {
- $title = $this->titles[$link_id];
- $title = $this->encodeAttribute($title);
- $result .= " title=\"$title\"";
- }
- $result .= $this->empty_element_suffix;
- $result = $this->hashPart($result);
- }
- else {
- # If there's no such link ID, leave intact:
- $result = $whole_match;
- }
-
- return $result;
- }
- function _doImages_inline_callback($matches) {
- $whole_match = $matches[1];
- $alt_text = $matches[2];
- $url = $matches[3] == '' ? $matches[4] : $matches[3];
- $title =& $matches[7];
-
- $alt_text = $this->encodeAttribute($alt_text);
- $url = $this->encodeAttribute($url);
- $result = "encodeAttribute($title);
- $result .= " title=\"$title\""; # $title already quoted
- }
- $result .= $this->empty_element_suffix;
-
- return $this->hashPart($result);
- }
-
-
- function doHeaders($text) {
- # Setext-style headers:
- # Header 1
- # ========
- #
- # Header 2
- # --------
- #
- $text = preg_replace_callback('{ ^(.+?)[ ]*\n(=+|-+)[ ]*\n+ }mx',
- array(&$this, '_doHeaders_callback_setext'), $text);
-
- # atx-style headers:
- # # Header 1
- # ## Header 2
- # ## Header 2 with closing hashes ##
- # ...
- # ###### Header 6
- #
- $text = preg_replace_callback('{
- ^(\#{1,6}) # $1 = string of #\'s
- [ ]*
- (.+?) # $2 = Header text
- [ ]*
- \#* # optional closing #\'s (not counted)
- \n+
- }xm',
- array(&$this, '_doHeaders_callback_atx'), $text);
-
- return $text;
- }
- function _doHeaders_callback_setext($matches) {
- # Terrible hack to check we haven't found an empty list item.
- if ($matches[2] == '-' && preg_match('{^-(?: |$)}', $matches[1]))
- return $matches[0];
-
- $level = $matches[2]{0} == '=' ? 1 : 2;
- $block = "".$this->runSpanGamut($matches[1])."";
- return "\n" . $this->hashBlock($block) . "\n\n";
- }
- function _doHeaders_callback_atx($matches) {
- $level = strlen($matches[1]);
- $block = "".$this->runSpanGamut($matches[2])."";
- return "\n" . $this->hashBlock($block) . "\n\n";
- }
-
-
- function doLists($text) {
- #
- # Form HTML ordered (numbered) and unordered (bulleted) lists.
- #
- $less_than_tab = $this->tab_width - 1;
-
- # Re-usable patterns to match list item bullets and number markers:
- $marker_ul_re = '[*+-]';
- $marker_ol_re = '\d+[\.]';
- $marker_any_re = "(?:$marker_ul_re|$marker_ol_re)";
-
- $markers_relist = array(
- $marker_ul_re => $marker_ol_re,
- $marker_ol_re => $marker_ul_re,
- );
-
- foreach ($markers_relist as $marker_re => $other_marker_re) {
- # Re-usable pattern to match any entirel ul or ol list:
- $whole_list_re = '
- ( # $1 = whole list
- ( # $2
- ([ ]{0,'.$less_than_tab.'}) # $3 = number of spaces
- ('.$marker_re.') # $4 = first list item marker
- [ ]+
- )
- (?s:.+?)
- ( # $5
- \z
- |
- \n{2,}
- (?=\S)
- (?! # Negative lookahead for another list item marker
- [ ]*
- '.$marker_re.'[ ]+
- )
- |
- (?= # Lookahead for another kind of list
- \n
- \3 # Must have the same indentation
- '.$other_marker_re.'[ ]+
- )
- )
- )
- '; // mx
-
- # We use a different prefix before nested lists than top-level lists.
- # See extended comment in _ProcessListItems().
-
- if ($this->list_level) {
- $text = preg_replace_callback('{
- ^
- '.$whole_list_re.'
- }mx',
- array(&$this, '_doLists_callback'), $text);
- }
- else {
- $text = preg_replace_callback('{
- (?:(?<=\n)\n|\A\n?) # Must eat the newline
- '.$whole_list_re.'
- }mx',
- array(&$this, '_doLists_callback'), $text);
- }
- }
-
- return $text;
- }
- function _doLists_callback($matches) {
- # Re-usable patterns to match list item bullets and number markers:
- $marker_ul_re = '[*+-]';
- $marker_ol_re = '\d+[\.]';
- $marker_any_re = "(?:$marker_ul_re|$marker_ol_re)";
-
- $list = $matches[1];
- $list_type = preg_match("/$marker_ul_re/", $matches[4]) ? "ul" : "ol";
-
- $marker_any_re = ( $list_type == "ul" ? $marker_ul_re : $marker_ol_re );
-
- $list .= "\n";
- $result = $this->processListItems($list, $marker_any_re);
-
- $result = $this->hashBlock("<$list_type>\n" . $result . "$list_type>");
- return "\n". $result ."\n\n";
- }
-
- var $list_level = 0;
-
- function processListItems($list_str, $marker_any_re) {
- #
- # Process the contents of a single ordered or unordered list, splitting it
- # into individual list items.
- #
- # The $this->list_level global keeps track of when we're inside a list.
- # Each time we enter a list, we increment it; when we leave a list,
- # we decrement. If it's zero, we're not in a list anymore.
- #
- # We do this because when we're not inside a list, we want to treat
- # something like this:
- #
- # I recommend upgrading to version
- # 8. Oops, now this line is treated
- # as a sub-list.
- #
- # As a single paragraph, despite the fact that the second line starts
- # with a digit-period-space sequence.
- #
- # Whereas when we're inside a list (or sub-list), that line will be
- # treated as the start of a sub-list. What a kludge, huh? This is
- # an aspect of Markdown's syntax that's hard to parse perfectly
- # without resorting to mind-reading. Perhaps the solution is to
- # change the syntax rules such that sub-lists must start with a
- # starting cardinal number; e.g. "1." or "a.".
-
- $this->list_level++;
-
- # trim trailing blank lines:
- $list_str = preg_replace("/\n{2,}\\z/", "\n", $list_str);
-
- $list_str = preg_replace_callback('{
- (\n)? # leading line = $1
- (^[ ]*) # leading whitespace = $2
- ('.$marker_any_re.' # list marker and space = $3
- (?:[ ]+|(?=\n)) # space only required if item is not empty
- )
- ((?s:.*?)) # list item text = $4
- (?:(\n+(?=\n))|\n) # tailing blank line = $5
- (?= \n* (\z | \2 ('.$marker_any_re.') (?:[ ]+|(?=\n))))
- }xm',
- array(&$this, '_processListItems_callback'), $list_str);
-
- $this->list_level--;
- return $list_str;
- }
- function _processListItems_callback($matches) {
- $item = $matches[4];
- $leading_line =& $matches[1];
- $leading_space =& $matches[2];
- $marker_space = $matches[3];
- $tailing_blank_line =& $matches[5];
-
- if ($leading_line || $tailing_blank_line ||
- preg_match('/\n{2,}/', $item))
- {
- # Replace marker with the appropriate whitespace indentation
- $item = $leading_space . str_repeat(' ', strlen($marker_space)) . $item;
- $item = $this->runBlockGamut($this->outdent($item)."\n");
- }
- else {
- # Recursion for sub-lists:
- $item = $this->doLists($this->outdent($item));
- $item = preg_replace('/\n+$/', '', $item);
- $item = $this->runSpanGamut($item);
- }
-
- return "
" . $item . "
\n";
- }
-
-
- function doCodeBlocks($text) {
- #
- # Process Markdown `
` blocks.
- #
- $text = preg_replace_callback('{
- (?:\n\n|\A\n?)
- ( # $1 = the code block -- one or more lines, starting with a space/tab
- (?>
- [ ]{'.$this->tab_width.'} # Lines must start with a tab or a tab-width of spaces
- .*\n+
- )+
- )
- ((?=^[ ]{0,'.$this->tab_width.'}\S)|\Z) # Lookahead for non-space at line-start, or end of doc
- }xm',
- array(&$this, '_doCodeBlocks_callback'), $text);
-
- return $text;
- }
- function _doCodeBlocks_callback($matches) {
- $codeblock = $matches[1];
-
- $codeblock = $this->outdent($codeblock);
- $codeblock = htmlspecialchars($codeblock, ENT_NOQUOTES);
-
- # trim leading newlines and trailing newlines
- $codeblock = preg_replace('/\A\n+|\n+\z/', '', $codeblock);
-
- $codeblock = "
$codeblock\n
";
- return "\n\n".$this->hashBlock($codeblock)."\n\n";
- }
-
-
- function makeCodeSpan($code) {
- #
- # Create a code span markup for $code. Called from handleSpanToken.
- #
- $code = htmlspecialchars(trim($code), ENT_NOQUOTES);
- return $this->hashPart("$code");
- }
-
-
- var $em_relist = array(
- '' => '(?:(? '(?<=\S|^)(? '(?<=\S|^)(? '(?:(? '(?<=\S|^)(? '(?<=\S|^)(? '(?:(? '(?<=\S|^)(? '(?<=\S|^)(?em_relist as $em => $em_re) {
- foreach ($this->strong_relist as $strong => $strong_re) {
- # Construct list of allowed token expressions.
- $token_relist = array();
- if (isset($this->em_strong_relist["$em$strong"])) {
- $token_relist[] = $this->em_strong_relist["$em$strong"];
- }
- $token_relist[] = $em_re;
- $token_relist[] = $strong_re;
-
- # Construct master expression from list.
- $token_re = '{('. implode('|', $token_relist) .')}';
- $this->em_strong_prepared_relist["$em$strong"] = $token_re;
- }
- }
- }
-
- function doItalicsAndBold($text) {
- $token_stack = array('');
- $text_stack = array('');
- $em = '';
- $strong = '';
- $tree_char_em = false;
-
- while (1) {
- #
- # Get prepared regular expression for seraching emphasis tokens
- # in current context.
- #
- $token_re = $this->em_strong_prepared_relist["$em$strong"];
-
- #
- # Each loop iteration search for the next emphasis token.
- # Each token is then passed to handleSpanToken.
- #
- $parts = preg_split($token_re, $text, 2, PREG_SPLIT_DELIM_CAPTURE);
- $text_stack[0] .= $parts[0];
- $token =& $parts[1];
- $text =& $parts[2];
-
- if (empty($token)) {
- # Reached end of text span: empty stack without emitting.
- # any more emphasis.
- while ($token_stack[0]) {
- $text_stack[1] .= array_shift($token_stack);
- $text_stack[0] .= array_shift($text_stack);
- }
- break;
- }
-
- $token_len = strlen($token);
- if ($tree_char_em) {
- # Reached closing marker while inside a three-char emphasis.
- if ($token_len == 3) {
- # Three-char closing marker, close em and strong.
- array_shift($token_stack);
- $span = array_shift($text_stack);
- $span = $this->runSpanGamut($span);
- $span = "$span";
- $text_stack[0] .= $this->hashPart($span);
- $em = '';
- $strong = '';
- } else {
- # Other closing marker: close one em or strong and
- # change current token state to match the other
- $token_stack[0] = str_repeat($token{0}, 3-$token_len);
- $tag = $token_len == 2 ? "strong" : "em";
- $span = $text_stack[0];
- $span = $this->runSpanGamut($span);
- $span = "<$tag>$span$tag>";
- $text_stack[0] = $this->hashPart($span);
- $$tag = ''; # $$tag stands for $em or $strong
- }
- $tree_char_em = false;
- } else if ($token_len == 3) {
- if ($em) {
- # Reached closing marker for both em and strong.
- # Closing strong marker:
- for ($i = 0; $i < 2; ++$i) {
- $shifted_token = array_shift($token_stack);
- $tag = strlen($shifted_token) == 2 ? "strong" : "em";
- $span = array_shift($text_stack);
- $span = $this->runSpanGamut($span);
- $span = "<$tag>$span$tag>";
- $text_stack[0] .= $this->hashPart($span);
- $$tag = ''; # $$tag stands for $em or $strong
- }
- } else {
- # Reached opening three-char emphasis marker. Push on token
- # stack; will be handled by the special condition above.
- $em = $token{0};
- $strong = "$em$em";
- array_unshift($token_stack, $token);
- array_unshift($text_stack, '');
- $tree_char_em = true;
- }
- } else if ($token_len == 2) {
- if ($strong) {
- # Unwind any dangling emphasis marker:
- if (strlen($token_stack[0]) == 1) {
- $text_stack[1] .= array_shift($token_stack);
- $text_stack[0] .= array_shift($text_stack);
- }
- # Closing strong marker:
- array_shift($token_stack);
- $span = array_shift($text_stack);
- $span = $this->runSpanGamut($span);
- $span = "$span";
- $text_stack[0] .= $this->hashPart($span);
- $strong = '';
- } else {
- array_unshift($token_stack, $token);
- array_unshift($text_stack, '');
- $strong = $token;
- }
- } else {
- # Here $token_len == 1
- if ($em) {
- if (strlen($token_stack[0]) == 1) {
- # Closing emphasis marker:
- array_shift($token_stack);
- $span = array_shift($text_stack);
- $span = $this->runSpanGamut($span);
- $span = "$span";
- $text_stack[0] .= $this->hashPart($span);
- $em = '';
- } else {
- $text_stack[0] .= $token;
- }
- } else {
- array_unshift($token_stack, $token);
- array_unshift($text_stack, '');
- $em = $token;
- }
- }
- }
- return $text_stack[0];
- }
-
-
- function doBlockQuotes($text) {
- $text = preg_replace_callback('/
- ( # Wrap whole match in $1
- (?>
- ^[ ]*>[ ]? # ">" at the start of a line
- .+\n # rest of the first line
- (.+\n)* # subsequent consecutive lines
- \n* # blanks
- )+
- )
- /xm',
- array(&$this, '_doBlockQuotes_callback'), $text);
-
- return $text;
- }
- function _doBlockQuotes_callback($matches) {
- $bq = $matches[1];
- # trim one level of quoting - trim whitespace-only lines
- $bq = preg_replace('/^[ ]*>[ ]?|^[ ]+$/m', '', $bq);
- $bq = $this->runBlockGamut($bq); # recurse
-
- $bq = preg_replace('/^/m', " ", $bq);
- # These leading spaces cause problem with
content,
- # so we need to fix that:
- $bq = preg_replace_callback('{(\s*
- #
- # Based by a filter by Matthew Wickline, posted to BBEdit-Talk.
- # With some optimizations by Milian Wolff.
- #
- $addr = "mailto:" . $addr;
- $chars = preg_split('/(? $char) {
- $ord = ord($char);
- # Ignore non-ascii chars.
- if ($ord < 128) {
- $r = ($seed * (1 + $key)) % 100; # Pseudo-random function.
- # roughly 10% raw, 45% hex, 45% dec
- # '@' *must* be encoded. I insist.
- if ($r > 90 && $char != '@') /* do nothing */;
- else if ($r < 45) $chars[$key] = ''.dechex($ord).';';
- else $chars[$key] = ''.$ord.';';
- }
- }
-
- $addr = implode('', $chars);
- $text = implode('', array_slice($chars, 7)); # text without `mailto:`
- $addr = "$text";
-
- return $addr;
- }
-
-
- function parseSpan($str) {
- #
- # Take the string $str and parse it into tokens, hashing embeded HTML,
- # escaped characters and handling code spans.
- #
- $output = '';
-
- $span_re = '{
- (
- \\\\'.$this->escape_chars_re.'
- |
- (?no_markup ? '' : '
- |
- # comment
- |
- <\?.*?\?> | <%.*?%> # processing instruction
- |
- <[!$]?[-a-zA-Z0-9:_]+ # regular tags
- (?>
- \s
- (?>[^"\'>]+|"[^"]*"|\'[^\']*\')*
- )?
- >
- |
- <[-a-zA-Z0-9:_]+\s*/> # xml-style empty tag
- |
- [-a-zA-Z0-9:_]+\s*> # closing tag
- ').'
- )
- }xs';
-
- while (1) {
- #
- # Each loop iteration seach for either the next tag, the next
- # openning code span marker, or the next escaped character.
- # Each token is then passed to handleSpanToken.
- #
- $parts = preg_split($span_re, $str, 2, PREG_SPLIT_DELIM_CAPTURE);
-
- # Create token from text preceding tag.
- if ($parts[0] != "") {
- $output .= $parts[0];
- }
-
- # Check if we reach the end.
- if (isset($parts[1])) {
- $output .= $this->handleSpanToken($parts[1], $parts[2]);
- $str = $parts[2];
- }
- else {
- break;
- }
- }
-
- return $output;
- }
-
-
- function handleSpanToken($token, &$str) {
- #
- # Handle $token provided by parseSpan by determining its nature and
- # returning the corresponding value that should replace it.
- #
- switch ($token{0}) {
- case "\\":
- return $this->hashPart("". ord($token{1}). ";");
- case "`":
- # Search for end marker in remaining text.
- if (preg_match('/^(.*?[^`])'.preg_quote($token).'(?!`)(.*)$/sm',
- $str, $matches))
- {
- $str = $matches[2];
- $codespan = $this->makeCodeSpan($matches[1]);
- return $this->hashPart($codespan);
- }
- return $token; // return as text since no ending marker found.
- default:
- return $this->hashPart($token);
- }
- }
-
-
- function outdent($text) {
- #
- # Remove one level of line-leading tabs or spaces
- #
- return preg_replace('/^(\t|[ ]{1,'.$this->tab_width.'})/m', '', $text);
- }
-
-
- # String length function for detab. `_initDetab` will create a function to
- # hanlde UTF-8 if the default function does not exist.
- var $utf8_strlen = 'mb_strlen';
-
- function detab($text) {
- #
- # Replace tabs with the appropriate amount of space.
- #
- # For each line we separate the line in blocks delemited by
- # tab characters. Then we reconstruct every line by adding the
- # appropriate number of space between each blocks.
-
- $text = preg_replace_callback('/^.*\t.*$/m',
- array(&$this, '_detab_callback'), $text);
-
- return $text;
- }
- function _detab_callback($matches) {
- $line = $matches[0];
- $strlen = $this->utf8_strlen; # strlen function for UTF-8.
-
- # Split in blocks.
- $blocks = explode("\t", $line);
- # Add each blocks to the line.
- $line = $blocks[0];
- unset($blocks[0]); # Do not add first block twice.
- foreach ($blocks as $block) {
- # Calculate amount of space, insert spaces, insert block.
- $amount = $this->tab_width -
- $strlen($line, 'UTF-8') % $this->tab_width;
- $line .= str_repeat(" ", $amount) . $block;
- }
- return $line;
- }
- function _initDetab() {
- #
- # Check for the availability of the function in the `utf8_strlen` property
- # (initially `mb_strlen`). If the function is not available, create a
- # function that will loosely count the number of UTF-8 characters with a
- # regular expression.
- #
- if (function_exists($this->utf8_strlen)) return;
- $this->utf8_strlen = create_function('$text', 'return preg_match_all(
- "/[\\\\x00-\\\\xBF]|[\\\\xC0-\\\\xFF][\\\\x80-\\\\xBF]*/",
- $text, $m);');
- }
-
-
- function unhash($text) {
- #
- # Swap back in all the tags hashed by _HashHTMLBlocks.
- #
- return preg_replace_callback('/(.)\x1A[0-9]+\1/',
- array(&$this, '_unhash_callback'), $text);
- }
- function _unhash_callback($matches) {
- return $this->html_hashes[$matches[0]];
- }
-
-}
-
-
-#
-# Markdown Extra Parser Class
-#
-
-class MarkdownExtra_Parser extends Markdown_Parser {
-
- ### Configuration Variables ###
-
- # Prefix for footnote ids.
- var $fn_id_prefix = "";
-
- # Optional title attribute for footnote links and backlinks.
- var $fn_link_title = MARKDOWN_FN_LINK_TITLE;
- var $fn_backlink_title = MARKDOWN_FN_BACKLINK_TITLE;
-
- # Optional class attribute for footnote links and backlinks.
- var $fn_link_class = MARKDOWN_FN_LINK_CLASS;
- var $fn_backlink_class = MARKDOWN_FN_BACKLINK_CLASS;
-
- # Optional class prefix for fenced code block.
- var $code_class_prefix = MARKDOWN_CODE_CLASS_PREFIX;
- # Class attribute for code blocks goes on the `code` tag;
- # setting this to true will put attributes on the `pre` tag instead.
- var $code_attr_on_pre = MARKDOWN_CODE_ATTR_ON_PRE;
-
- # Predefined abbreviations.
- var $predef_abbr = array();
-
-
- ### Parser Implementation ###
-
- function MarkdownExtra_Parser() {
- #
- # Constructor function. Initialize the parser object.
- #
- # Add extra escapable characters before parent constructor
- # initialize the table.
- $this->escape_chars .= ':|';
-
- # Insert extra document, block, and span transformations.
- # Parent constructor will do the sorting.
- $this->document_gamut += array(
- "doFencedCodeBlocks" => 5,
- "stripFootnotes" => 15,
- "stripAbbreviations" => 25,
- "appendFootnotes" => 50,
- );
- $this->block_gamut += array(
- "doFencedCodeBlocks" => 5,
- "doTables" => 15,
- "doDefLists" => 45,
- );
- $this->span_gamut += array(
- "doFootnotes" => 5,
- "doAbbreviations" => 70,
- );
-
- parent::Markdown_Parser();
- }
-
-
- # Extra variables used during extra transformations.
- var $footnotes = array();
- var $footnotes_ordered = array();
- var $footnotes_ref_count = array();
- var $footnotes_numbers = array();
- var $abbr_desciptions = array();
- var $abbr_word_re = '';
-
- # Give the current footnote number.
- var $footnote_counter = 1;
-
-
- function setup() {
- #
- # Setting up Extra-specific variables.
- #
- parent::setup();
-
- $this->footnotes = array();
- $this->footnotes_ordered = array();
- $this->footnotes_ref_count = array();
- $this->footnotes_numbers = array();
- $this->abbr_desciptions = array();
- $this->abbr_word_re = '';
- $this->footnote_counter = 1;
-
- foreach ($this->predef_abbr as $abbr_word => $abbr_desc) {
- if ($this->abbr_word_re)
- $this->abbr_word_re .= '|';
- $this->abbr_word_re .= preg_quote($abbr_word);
- $this->abbr_desciptions[$abbr_word] = trim($abbr_desc);
- }
- }
-
- function teardown() {
- #
- # Clearing Extra-specific variables.
- #
- $this->footnotes = array();
- $this->footnotes_ordered = array();
- $this->footnotes_ref_count = array();
- $this->footnotes_numbers = array();
- $this->abbr_desciptions = array();
- $this->abbr_word_re = '';
-
- parent::teardown();
- }
-
-
- ### Extra Attribute Parser ###
-
- # Expression to use to catch attributes (includes the braces)
- var $id_class_attr_catch_re = '\{((?:[ ]*[#.][-_:a-zA-Z0-9]+){1,})[ ]*\}';
- # Expression to use when parsing in a context when no capture is desired
- var $id_class_attr_nocatch_re = '\{(?:[ ]*[#.][-_:a-zA-Z0-9]+){1,}[ ]*\}';
-
- function doExtraAttributes($tag_name, $attr) {
- #
- # Parse attributes caught by the $this->id_class_attr_catch_re expression
- # and return the HTML-formatted list of attributes.
- #
- # Currently supported attributes are .class and #id.
- #
- if (empty($attr)) return "";
-
- # Split on components
- preg_match_all('/[#.][-_:a-zA-Z0-9]+/', $attr, $matches);
- $elements = $matches[0];
-
- # handle classes and ids (only first id taken into account)
- $classes = array();
- $id = false;
- foreach ($elements as $element) {
- if ($element{0} == '.') {
- $classes[] = substr($element, 1);
- } else if ($element{0} == '#') {
- if ($id === false) $id = substr($element, 1);
- }
- }
-
- # compose attributes as string
- $attr_str = "";
- if (!empty($id)) {
- $attr_str .= ' id="'.$id.'"';
- }
- if (!empty($classes)) {
- $attr_str .= ' class="'.implode(" ", $classes).'"';
- }
- return $attr_str;
- }
-
-
- function stripLinkDefinitions($text) {
- #
- # Strips link definitions from text, stores the URLs and titles in
- # hash references.
- #
- $less_than_tab = $this->tab_width - 1;
-
- # Link defs are in the form: ^[id]: url "optional title"
- $text = preg_replace_callback('{
- ^[ ]{0,'.$less_than_tab.'}\[(.+)\][ ]?: # id = $1
- [ ]*
- \n? # maybe *one* newline
- [ ]*
- (?:
- <(.+?)> # url = $2
- |
- (\S+?) # url = $3
- )
- [ ]*
- \n? # maybe one newline
- [ ]*
- (?:
- (?<=\s) # lookbehind for whitespace
- ["(]
- (.*?) # title = $4
- [")]
- [ ]*
- )? # title is optional
- (?:[ ]* '.$this->id_class_attr_catch_re.' )? # $5 = extra id & class attr
- (?:\n+|\Z)
- }xm',
- array(&$this, '_stripLinkDefinitions_callback'),
- $text);
- return $text;
- }
- function _stripLinkDefinitions_callback($matches) {
- $link_id = strtolower($matches[1]);
- $url = $matches[2] == '' ? $matches[3] : $matches[2];
- $this->urls[$link_id] = $url;
- $this->titles[$link_id] =& $matches[4];
- $this->ref_attr[$link_id] = $this->doExtraAttributes("", $dummy =& $matches[5]);
- return ''; # String that will replace the block
- }
-
-
- ### HTML Block Parser ###
-
- # Tags that are always treated as block tags:
- var $block_tags_re = 'p|div|h[1-6]|blockquote|pre|table|dl|ol|ul|address|form|fieldset|iframe|hr|legend|article|section|nav|aside|hgroup|header|footer|figcaption';
-
- # Tags treated as block tags only if the opening tag is alone on its line:
- var $context_block_tags_re = 'script|noscript|ins|del|iframe|object|source|track|param|math|svg|canvas|audio|video';
-
- # Tags where markdown="1" default to span mode:
- var $contain_span_tags_re = 'p|h[1-6]|li|dd|dt|td|th|legend|address';
-
- # Tags which must not have their contents modified, no matter where
- # they appear:
- var $clean_tags_re = 'script|math|svg';
-
- # Tags that do not need to be closed.
- var $auto_close_tags_re = 'hr|img|param|source|track';
-
-
- function hashHTMLBlocks($text) {
- #
- # Hashify HTML Blocks and "clean tags".
- #
- # 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
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.
- #
- # This works by calling _HashHTMLBlocks_InMarkdown, which then calls
- # _HashHTMLBlocks_InHTML when it encounter block tags. When the markdown="1"
- # attribute is found within a tag, _HashHTMLBlocks_InHTML calls back
- # _HashHTMLBlocks_InMarkdown to handle the Markdown syntax within the tag.
- # These two functions are calling each other. It's recursive!
- #
- if ($this->no_markup) return $text;
-
- #
- # Call the HTML-in-Markdown hasher.
- #
- list($text, ) = $this->_hashHTMLBlocks_inMarkdown($text);
-
- return $text;
- }
- function _hashHTMLBlocks_inMarkdown($text, $indent = 0,
- $enclosing_tag_re = '', $span = false)
- {
- #
- # Parse markdown text, calling _HashHTMLBlocks_InHTML for block tags.
- #
- # * $indent is the number of space to be ignored when checking for code
- # blocks. This is important because if we don't take the indent into
- # account, something like this (which looks right) won't work as expected:
- #
- #
- #
- # Hello World. <-- Is this a Markdown code block or text?
- #
<-- Is this a Markdown code block or a real tag?
- #
- #
- # If you don't like this, just don't indent the tag on which
- # you apply the markdown="1" attribute.
- #
- # * If $enclosing_tag_re is not empty, stops at the first unmatched closing
- # tag with that name. Nested tags supported.
- #
- # * If $span is true, text inside must treated as span. So any double
- # newline will be replaced by a single newline so that it does not create
- # paragraphs.
- #
- # Returns an array of that form: ( processed text , remaining text )
- #
- if ($text === '') return array('', '');
-
- # Regex to check for the presense of newlines around a block tag.
- $newline_before_re = '/(?:^\n?|\n\n)*$/';
- $newline_after_re =
- '{
- ^ # Start of text following the tag.
- (?>[ ]*)? # Optional comment.
- [ ]*\n # Must be followed by newline.
- }xs';
-
- # Regex to match any tag.
- $block_tag_re =
- '{
- ( # $2: Capture whole tag.
- ? # Any opening or closing tag.
- (?> # Tag name.
- '.$this->block_tags_re.' |
- '.$this->context_block_tags_re.' |
- '.$this->clean_tags_re.' |
- (?!\s)'.$enclosing_tag_re.'
- )
- (?:
- (?=[\s"\'/a-zA-Z0-9]) # Allowed characters after tag name.
- (?>
- ".*?" | # Double quotes (can contain `>`)
- \'.*?\' | # Single quotes (can contain `>`)
- .+? # Anything but quotes and `>`.
- )*?
- )?
- > # End of tag.
- |
- # HTML Comment
- |
- <\?.*?\?> | <%.*?%> # Processing instruction
- |
- # CData Block
- '. ( !$span ? ' # If not in span.
- |
- # Indented code block
- (?: ^[ ]*\n | ^ | \n[ ]*\n )
- [ ]{'.($indent+4).'}[^\n]* \n
- (?>
- (?: [ ]{'.($indent+4).'}[^\n]* | [ ]* ) \n
- )*
- |
- # Fenced code block marker
- (?<= ^ | \n )
- [ ]{0,'.($indent+3).'}(?:~{3,}|`{3,})
- [ ]*
- (?:
- \.?[-_:a-zA-Z0-9]+ # standalone class name
- |
- '.$this->id_class_attr_nocatch_re.' # extra attributes
- )?
- [ ]*
- (?= \n )
- ' : '' ). ' # End (if not is span).
- |
- # Code span marker
- # Note, this regex needs to go after backtick fenced
- # code blocks but it should also be kept outside of the
- # "if not in span" condition adding backticks to the parser
- `+
- )
- }xs';
-
-
- $depth = 0; # Current depth inside the tag tree.
- $parsed = ""; # Parsed text that will be returned.
-
- #
- # Loop through every tag until we find the closing tag of the parent
- # or loop until reaching the end of text if no parent tag specified.
- #
- do {
- #
- # Split the text using the first $tag_match pattern found.
- # Text before pattern will be first in the array, text after
- # pattern will be at the end, and between will be any catches made
- # by the pattern.
- #
- $parts = preg_split($block_tag_re, $text, 2,
- PREG_SPLIT_DELIM_CAPTURE);
-
- # If in Markdown span mode, add a empty-string span-level hash
- # after each newline to prevent triggering any block element.
- if ($span) {
- $void = $this->hashPart("", ':');
- $newline = "$void\n";
- $parts[0] = $void . str_replace("\n", $newline, $parts[0]) . $void;
- }
-
- $parsed .= $parts[0]; # Text before current tag.
-
- # If end of $text has been reached. Stop loop.
- if (count($parts) < 3) {
- $text = "";
- break;
- }
-
- $tag = $parts[1]; # Tag to handle.
- $text = $parts[2]; # Remaining text after current tag.
- $tag_re = preg_quote($tag); # For use in a regular expression.
-
- #
- # Check for: Fenced code block marker.
- # Note: need to recheck the whole tag to disambiguate backtick
- # fences from code spans
- #
- if (preg_match('{^\n?([ ]{0,'.($indent+3).'})(~{3,}|`{3,})[ ]*(?:\.?[-_:a-zA-Z0-9]+|'.$this->id_class_attr_nocatch_re.')?[ ]*\n?$}', $tag, $capture)) {
- # Fenced code block marker: find matching end marker.
- $fence_indent = strlen($capture[1]); # use captured indent in re
- $fence_re = $capture[2]; # use captured fence in re
- if (preg_match('{^(?>.*\n)*?[ ]{'.($fence_indent).'}'.$fence_re.'[ ]*(?:\n|$)}', $text,
- $matches))
- {
- # End marker found: pass text unchanged until marker.
- $parsed .= $tag . $matches[0];
- $text = substr($text, strlen($matches[0]));
- }
- else {
- # No end marker: just skip it.
- $parsed .= $tag;
- }
- }
- #
- # Check for: Indented code block.
- #
- else if ($tag{0} == "\n" || $tag{0} == " ") {
- # Indented code block: pass it unchanged, will be handled
- # later.
- $parsed .= $tag;
- }
- #
- # Check for: Code span marker
- # Note: need to check this after backtick fenced code blocks
- #
- else if ($tag{0} == "`") {
- # Find corresponding end marker.
- $tag_re = preg_quote($tag);
- if (preg_match('{^(?>.+?|\n(?!\n))*?(?block_tags_re.')\b}', $tag) ||
- ( preg_match('{^<(?:'.$this->context_block_tags_re.')\b}', $tag) &&
- preg_match($newline_before_re, $parsed) &&
- preg_match($newline_after_re, $text) )
- )
- {
- # Need to parse tag and following text using the HTML parser.
- list($block_text, $text) =
- $this->_hashHTMLBlocks_inHTML($tag . $text, "hashBlock", true);
-
- # Make sure it stays outside of any paragraph by adding newlines.
- $parsed .= "\n\n$block_text\n\n";
- }
- #
- # Check for: Clean tag (like script, math)
- # HTML Comments, processing instructions.
- #
- else if (preg_match('{^<(?:'.$this->clean_tags_re.')\b}', $tag) ||
- $tag{1} == '!' || $tag{1} == '?')
- {
- # Need to parse tag and following text using the HTML parser.
- # (don't check for markdown attribute)
- list($block_text, $text) =
- $this->_hashHTMLBlocks_inHTML($tag . $text, "hashClean", false);
-
- $parsed .= $block_text;
- }
- #
- # Check for: Tag with same name as enclosing tag.
- #
- else if ($enclosing_tag_re !== '' &&
- # Same name as enclosing tag.
- preg_match('{^?(?:'.$enclosing_tag_re.')\b}', $tag))
- {
- #
- # Increase/decrease nested tag count.
- #
- if ($tag{1} == '/') $depth--;
- else if ($tag{strlen($tag)-2} != '/') $depth++;
-
- if ($depth < 0) {
- #
- # Going out of parent element. Clean up and break so we
- # return to the calling function.
- #
- $text = $tag . $text;
- break;
- }
-
- $parsed .= $tag;
- }
- else {
- $parsed .= $tag;
- }
- } while ($depth >= 0);
-
- return array($parsed, $text);
- }
- function _hashHTMLBlocks_inHTML($text, $hash_method, $md_attr) {
- #
- # Parse HTML, calling _HashHTMLBlocks_InMarkdown for block tags.
- #
- # * Calls $hash_method to convert any blocks.
- # * Stops when the first opening tag closes.
- # * $md_attr indicate if the use of the `markdown="1"` attribute is allowed.
- # (it is not inside clean tags)
- #
- # Returns an array of that form: ( processed text , remaining text )
- #
- if ($text === '') return array('', '');
-
- # Regex to match `markdown` attribute inside of a tag.
- $markdown_attr_re = '
- {
- \s* # Eat whitespace before the `markdown` attribute
- markdown
- \s*=\s*
- (?>
- (["\']) # $1: quote delimiter
- (.*?) # $2: attribute value
- \1 # matching delimiter
- |
- ([^\s>]*) # $3: unquoted attribute value
- )
- () # $4: make $3 always defined (avoid warnings)
- }xs';
-
- # Regex to match any tag.
- $tag_re = '{
- ( # $2: Capture whole tag.
- ? # Any opening or closing tag.
- [\w:$]+ # Tag name.
- (?:
- (?=[\s"\'/a-zA-Z0-9]) # Allowed characters after tag name.
- (?>
- ".*?" | # Double quotes (can contain `>`)
- \'.*?\' | # Single quotes (can contain `>`)
- .+? # Anything but quotes and `>`.
- )*?
- )?
- > # End of tag.
- |
- # HTML Comment
- |
- <\?.*?\?> | <%.*?%> # Processing instruction
- |
- # CData Block
- )
- }xs';
-
- $original_text = $text; # Save original text in case of faliure.
-
- $depth = 0; # Current depth inside the tag tree.
- $block_text = ""; # Temporary text holder for current text.
- $parsed = ""; # Parsed text that will be returned.
-
- #
- # Get the name of the starting tag.
- # (This pattern makes $base_tag_name_re safe without quoting.)
- #
- if (preg_match('/^<([\w:$]*)\b/', $text, $matches))
- $base_tag_name_re = $matches[1];
-
- #
- # Loop through every tag until we find the corresponding closing tag.
- #
- do {
- #
- # Split the text using the first $tag_match pattern found.
- # Text before pattern will be first in the array, text after
- # pattern will be at the end, and between will be any catches made
- # by the pattern.
- #
- $parts = preg_split($tag_re, $text, 2, PREG_SPLIT_DELIM_CAPTURE);
-
- if (count($parts) < 3) {
- #
- # End of $text reached with unbalenced tag(s).
- # In that case, we return original text unchanged and pass the
- # first character as filtered to prevent an infinite loop in the
- # parent function.
- #
- return array($original_text{0}, substr($original_text, 1));
- }
-
- $block_text .= $parts[0]; # Text before current tag.
- $tag = $parts[1]; # Tag to handle.
- $text = $parts[2]; # Remaining text after current tag.
-
- #
- # Check for: Auto-close tag (like )
- # Comments and Processing Instructions.
- #
- if (preg_match('{^?(?:'.$this->auto_close_tags_re.')\b}', $tag) ||
- $tag{1} == '!' || $tag{1} == '?')
- {
- # Just add the tag to the block as if it was text.
- $block_text .= $tag;
- }
- else {
- #
- # Increase/decrease nested tag count. Only do so if
- # the tag's name match base tag's.
- #
- if (preg_match('{^?'.$base_tag_name_re.'\b}', $tag)) {
- if ($tag{1} == '/') $depth--;
- else if ($tag{strlen($tag)-2} != '/') $depth++;
- }
-
- #
- # Check for `markdown="1"` attribute and handle it.
- #
- if ($md_attr &&
- preg_match($markdown_attr_re, $tag, $attr_m) &&
- preg_match('/^1|block|span$/', $attr_m[2] . $attr_m[3]))
- {
- # Remove `markdown` attribute from opening tag.
- $tag = preg_replace($markdown_attr_re, '', $tag);
-
- # Check if text inside this tag must be parsed in span mode.
- $this->mode = $attr_m[2] . $attr_m[3];
- $span_mode = $this->mode == 'span' || $this->mode != 'block' &&
- preg_match('{^<(?:'.$this->contain_span_tags_re.')\b}', $tag);
-
- # Calculate indent before tag.
- if (preg_match('/(?:^|\n)( *?)(?! ).*?$/', $block_text, $matches)) {
- $strlen = $this->utf8_strlen;
- $indent = $strlen($matches[1], 'UTF-8');
- } else {
- $indent = 0;
- }
-
- # End preceding block with this tag.
- $block_text .= $tag;
- $parsed .= $this->$hash_method($block_text);
-
- # Get enclosing tag name for the ParseMarkdown function.
- # (This pattern makes $tag_name_re safe without quoting.)
- preg_match('/^<([\w:$]*)\b/', $tag, $matches);
- $tag_name_re = $matches[1];
-
- # Parse the content using the HTML-in-Markdown parser.
- list ($block_text, $text)
- = $this->_hashHTMLBlocks_inMarkdown($text, $indent,
- $tag_name_re, $span_mode);
-
- # Outdent markdown text.
- if ($indent > 0) {
- $block_text = preg_replace("/^[ ]{1,$indent}/m", "",
- $block_text);
- }
-
- # Append tag content to parsed text.
- if (!$span_mode) $parsed .= "\n\n$block_text\n\n";
- else $parsed .= "$block_text";
-
- # Start over with a new block.
- $block_text = "";
- }
- else $block_text .= $tag;
- }
-
- } while ($depth > 0);
-
- #
- # Hash last block text that wasn't processed inside the loop.
- #
- $parsed .= $this->$hash_method($block_text);
-
- return array($parsed, $text);
- }
-
-
- function hashClean($text) {
- #
- # Called whenever a tag must be hashed when a function inserts a "clean" tag
- # in $text, it passes through this function and is automaticaly escaped,
- # blocking invalid nested overlap.
- #
- return $this->hashPart($text, 'C');
- }
-
-
- function doAnchors($text) {
- #
- # Turn Markdown link shortcuts into XHTML tags.
- #
- if ($this->in_anchor) return $text;
- $this->in_anchor = true;
-
- #
- # First, handle reference-style links: [link text] [id]
- #
- $text = preg_replace_callback('{
- ( # wrap whole match in $1
- \[
- ('.$this->nested_brackets_re.') # link text = $2
- \]
-
- [ ]? # one optional space
- (?:\n[ ]*)? # one optional newline followed by spaces
-
- \[
- (.*?) # id = $3
- \]
- )
- }xs',
- array(&$this, '_doAnchors_reference_callback'), $text);
-
- #
- # Next, inline-style links: [link text](url "optional title")
- #
- $text = preg_replace_callback('{
- ( # wrap whole match in $1
- \[
- ('.$this->nested_brackets_re.') # link text = $2
- \]
- \( # literal paren
- [ \n]*
- (?:
- <(.+?)> # href = $3
- |
- ('.$this->nested_url_parenthesis_re.') # href = $4
- )
- [ \n]*
- ( # $5
- ([\'"]) # quote char = $6
- (.*?) # Title = $7
- \6 # matching quote
- [ \n]* # ignore any spaces/tabs between closing quote and )
- )? # title is optional
- \)
- (?:[ ]? '.$this->id_class_attr_catch_re.' )? # $8 = id/class attributes
- )
- }xs',
- array(&$this, '_doAnchors_inline_callback'), $text);
-
- #
- # Last, handle reference-style shortcuts: [link text]
- # These must come last in case you've also got [link text][1]
- # or [link text](/foo)
- #
- $text = preg_replace_callback('{
- ( # wrap whole match in $1
- \[
- ([^\[\]]+) # link text = $2; can\'t contain [ or ]
- \]
- )
- }xs',
- array(&$this, '_doAnchors_reference_callback'), $text);
-
- $this->in_anchor = false;
- return $text;
- }
- function _doAnchors_reference_callback($matches) {
- $whole_match = $matches[1];
- $link_text = $matches[2];
- $link_id =& $matches[3];
-
- if ($link_id == "") {
- # for shortcut links like [this][] or [this].
- $link_id = $link_text;
- }
-
- # lower-case and turn embedded newlines into spaces
- $link_id = strtolower($link_id);
- $link_id = preg_replace('{[ ]?\n}', ' ', $link_id);
-
- if (isset($this->urls[$link_id])) {
- $url = $this->urls[$link_id];
- $url = $this->encodeAttribute($url);
-
- $result = "titles[$link_id] ) ) {
- $title = $this->titles[$link_id];
- $title = $this->encodeAttribute($title);
- $result .= " title=\"$title\"";
- }
- if (isset($this->ref_attr[$link_id]))
- $result .= $this->ref_attr[$link_id];
-
- $link_text = $this->runSpanGamut($link_text);
- $result .= ">$link_text";
- $result = $this->hashPart($result);
- }
- else {
- $result = $whole_match;
- }
- return $result;
- }
- function _doAnchors_inline_callback($matches) {
- $whole_match = $matches[1];
- $link_text = $this->runSpanGamut($matches[2]);
- $url = $matches[3] == '' ? $matches[4] : $matches[3];
- $title =& $matches[7];
- $attr = $this->doExtraAttributes("a", $dummy =& $matches[8]);
-
-
- $url = $this->encodeAttribute($url);
-
- $result = "encodeAttribute($title);
- $result .= " title=\"$title\"";
- }
- $result .= $attr;
-
- $link_text = $this->runSpanGamut($link_text);
- $result .= ">$link_text";
-
- return $this->hashPart($result);
- }
-
-
- function doImages($text) {
- #
- # Turn Markdown image shortcuts into tags.
- #
- #
- # First, handle reference-style labeled images: ![alt text][id]
- #
- $text = preg_replace_callback('{
- ( # wrap whole match in $1
- !\[
- ('.$this->nested_brackets_re.') # alt text = $2
- \]
-
- [ ]? # one optional space
- (?:\n[ ]*)? # one optional newline followed by spaces
-
- \[
- (.*?) # id = $3
- \]
-
- )
- }xs',
- array(&$this, '_doImages_reference_callback'), $text);
-
- #
- # Next, handle inline images: ![alt text](url "optional title")
- # Don't forget: encode * and _
- #
- $text = preg_replace_callback('{
- ( # wrap whole match in $1
- !\[
- ('.$this->nested_brackets_re.') # alt text = $2
- \]
- \s? # One optional whitespace character
- \( # literal paren
- [ \n]*
- (?:
- <(\S*)> # src url = $3
- |
- ('.$this->nested_url_parenthesis_re.') # src url = $4
- )
- [ \n]*
- ( # $5
- ([\'"]) # quote char = $6
- (.*?) # title = $7
- \6 # matching quote
- [ \n]*
- )? # title is optional
- \)
- (?:[ ]? '.$this->id_class_attr_catch_re.' )? # $8 = id/class attributes
- )
- }xs',
- array(&$this, '_doImages_inline_callback'), $text);
-
- return $text;
- }
- function _doImages_reference_callback($matches) {
- $whole_match = $matches[1];
- $alt_text = $matches[2];
- $link_id = strtolower($matches[3]);
-
- if ($link_id == "") {
- $link_id = strtolower($alt_text); # for shortcut links like ![this][].
- }
-
- $alt_text = $this->encodeAttribute($alt_text);
- if (isset($this->urls[$link_id])) {
- $url = $this->encodeAttribute($this->urls[$link_id]);
- $result = "titles[$link_id])) {
- $title = $this->titles[$link_id];
- $title = $this->encodeAttribute($title);
- $result .= " title=\"$title\"";
- }
- if (isset($this->ref_attr[$link_id]))
- $result .= $this->ref_attr[$link_id];
- $result .= $this->empty_element_suffix;
- $result = $this->hashPart($result);
- }
- else {
- # If there's no such link ID, leave intact:
- $result = $whole_match;
- }
-
- return $result;
- }
- function _doImages_inline_callback($matches) {
- $whole_match = $matches[1];
- $alt_text = $matches[2];
- $url = $matches[3] == '' ? $matches[4] : $matches[3];
- $title =& $matches[7];
- $attr = $this->doExtraAttributes("img", $dummy =& $matches[8]);
-
- $alt_text = $this->encodeAttribute($alt_text);
- $url = $this->encodeAttribute($url);
- $result = "encodeAttribute($title);
- $result .= " title=\"$title\""; # $title already quoted
- }
- $result .= $attr;
- $result .= $this->empty_element_suffix;
-
- return $this->hashPart($result);
- }
-
-
- function doHeaders($text) {
- #
- # Redefined to add id and class attribute support.
- #
- # Setext-style headers:
- # Header 1 {#header1}
- # ========
- #
- # Header 2 {#header2 .class1 .class2}
- # --------
- #
- $text = preg_replace_callback(
- '{
- (^.+?) # $1: Header text
- (?:[ ]+ '.$this->id_class_attr_catch_re.' )? # $3 = id/class attributes
- [ ]*\n(=+|-+)[ ]*\n+ # $3: Header footer
- }mx',
- array(&$this, '_doHeaders_callback_setext'), $text);
-
- # atx-style headers:
- # # Header 1 {#header1}
- # ## Header 2 {#header2}
- # ## Header 2 with closing hashes ## {#header3.class1.class2}
- # ...
- # ###### Header 6 {.class2}
- #
- $text = preg_replace_callback('{
- ^(\#{1,6}) # $1 = string of #\'s
- [ ]*
- (.+?) # $2 = Header text
- [ ]*
- \#* # optional closing #\'s (not counted)
- (?:[ ]+ '.$this->id_class_attr_catch_re.' )? # $3 = id/class attributes
- [ ]*
- \n+
- }xm',
- array(&$this, '_doHeaders_callback_atx'), $text);
-
- return $text;
- }
- function _doHeaders_callback_setext($matches) {
- if ($matches[3] == '-' && preg_match('{^- }', $matches[1]))
- return $matches[0];
- $level = $matches[3]{0} == '=' ? 1 : 2;
- $attr = $this->doExtraAttributes("h$level", $dummy =& $matches[2]);
- $block = "".$this->runSpanGamut($matches[1])."";
- return "\n" . $this->hashBlock($block) . "\n\n";
- }
- function _doHeaders_callback_atx($matches) {
- $level = strlen($matches[1]);
- $attr = $this->doExtraAttributes("h$level", $dummy =& $matches[3]);
- $block = "".$this->runSpanGamut($matches[2])."";
- return "\n" . $this->hashBlock($block) . "\n\n";
- }
-
-
- function doTables($text) {
- #
- # Form HTML tables.
- #
- $less_than_tab = $this->tab_width - 1;
- #
- # Find tables with leading pipe.
- #
- # | Header 1 | Header 2
- # | -------- | --------
- # | Cell 1 | Cell 2
- # | Cell 3 | Cell 4
- #
- $text = preg_replace_callback('
- {
- ^ # Start of a line
- [ ]{0,'.$less_than_tab.'} # Allowed whitespace.
- [|] # Optional leading pipe (present)
- (.+) \n # $1: Header row (at least one pipe)
-
- [ ]{0,'.$less_than_tab.'} # Allowed whitespace.
- [|] ([ ]*[-:]+[-| :]*) \n # $2: Header underline
-
- ( # $3: Cells
- (?>
- [ ]* # Allowed whitespace.
- [|] .* \n # Row content.
- )*
- )
- (?=\n|\Z) # Stop at final double newline.
- }xm',
- array(&$this, '_doTable_leadingPipe_callback'), $text);
-
- #
- # Find tables without leading pipe.
- #
- # Header 1 | Header 2
- # -------- | --------
- # Cell 1 | Cell 2
- # Cell 3 | Cell 4
- #
- $text = preg_replace_callback('
- {
- ^ # Start of a line
- [ ]{0,'.$less_than_tab.'} # Allowed whitespace.
- (\S.*[|].*) \n # $1: Header row (at least one pipe)
-
- [ ]{0,'.$less_than_tab.'} # Allowed whitespace.
- ([-:]+[ ]*[|][-| :]*) \n # $2: Header underline
-
- ( # $3: Cells
- (?>
- .* [|] .* \n # Row content
- )*
- )
- (?=\n|\Z) # Stop at final double newline.
- }xm',
- array(&$this, '_DoTable_callback'), $text);
-
- return $text;
- }
- function _doTable_leadingPipe_callback($matches) {
- $head = $matches[1];
- $underline = $matches[2];
- $content = $matches[3];
-
- # Remove leading pipe for each row.
- $content = preg_replace('/^ *[|]/m', '', $content);
-
- return $this->_doTable_callback(array($matches[0], $head, $underline, $content));
- }
- function _doTable_callback($matches) {
- $head = $matches[1];
- $underline = $matches[2];
- $content = $matches[3];
-
- # Remove any tailing pipes for each line.
- $head = preg_replace('/[|] *$/m', '', $head);
- $underline = preg_replace('/[|] *$/m', '', $underline);
- $content = preg_replace('/[|] *$/m', '', $content);
-
- # Reading alignement from header underline.
- $separators = preg_split('/ *[|] */', $underline);
- foreach ($separators as $n => $s) {
- if (preg_match('/^ *-+: *$/', $s)) $attr[$n] = ' align="right"';
- else if (preg_match('/^ *:-+: *$/', $s))$attr[$n] = ' align="center"';
- else if (preg_match('/^ *:-+ *$/', $s)) $attr[$n] = ' align="left"';
- else $attr[$n] = '';
- }
-
- # Parsing span elements, including code spans, character escapes,
- # and inline HTML tags, so that pipes inside those gets ignored.
- $head = $this->parseSpan($head);
- $headers = preg_split('/ *[|] */', $head);
- $col_count = count($headers);
- $attr = array_pad($attr, $col_count, '');
-
- # Write column headers.
- $text = "
";
-
- return $this->hashBlock($text) . "\n";
- }
-
-
- function doDefLists($text) {
- #
- # Form HTML definition lists.
- #
- $less_than_tab = $this->tab_width - 1;
-
- # Re-usable pattern to match any entire dl list:
- $whole_list_re = '(?>
- ( # $1 = whole list
- ( # $2
- [ ]{0,'.$less_than_tab.'}
- ((?>.*\S.*\n)+) # $3 = defined term
- \n?
- [ ]{0,'.$less_than_tab.'}:[ ]+ # colon starting definition
- )
- (?s:.+?)
- ( # $4
- \z
- |
- \n{2,}
- (?=\S)
- (?! # Negative lookahead for another term
- [ ]{0,'.$less_than_tab.'}
- (?: \S.*\n )+? # defined term
- \n?
- [ ]{0,'.$less_than_tab.'}:[ ]+ # colon starting definition
- )
- (?! # Negative lookahead for another definition
- [ ]{0,'.$less_than_tab.'}:[ ]+ # colon starting definition
- )
- )
- )
- )'; // mx
-
- $text = preg_replace_callback('{
- (?>\A\n?|(?<=\n\n))
- '.$whole_list_re.'
- }mx',
- array(&$this, '_doDefLists_callback'), $text);
-
- return $text;
- }
- function _doDefLists_callback($matches) {
- # Re-usable patterns to match list item bullets and number markers:
- $list = $matches[1];
-
- # Turn double returns into triple returns, so that we can make a
- # paragraph for the last item in a list, if necessary:
- $result = trim($this->processDefListItems($list));
- $result = "
\n" . $result . "\n
";
- return $this->hashBlock($result) . "\n\n";
- }
-
-
- function processDefListItems($list_str) {
- #
- # Process the contents of a single definition list, splitting it
- # into individual term and definition list items.
- #
- $less_than_tab = $this->tab_width - 1;
-
- # trim trailing blank lines:
- $list_str = preg_replace("/\n{2,}\\z/", "\n", $list_str);
-
- # Process definition terms.
- $list_str = preg_replace_callback('{
- (?>\A\n?|\n\n+) # leading line
- ( # definition terms = $1
- [ ]{0,'.$less_than_tab.'} # leading whitespace
- (?!\:[ ]|[ ]) # negative lookahead for a definition
- # mark (colon) or more whitespace.
- (?> \S.* \n)+? # actual term (not whitespace).
- )
- (?=\n?[ ]{0,3}:[ ]) # lookahead for following line feed
- # with a definition mark.
- }xm',
- array(&$this, '_processDefListItems_callback_dt'), $list_str);
-
- # Process actual definitions.
- $list_str = preg_replace_callback('{
- \n(\n+)? # leading line = $1
- ( # marker space = $2
- [ ]{0,'.$less_than_tab.'} # whitespace before colon
- \:[ ]+ # definition mark (colon)
- )
- ((?s:.+?)) # definition text = $3
- (?= \n+ # stop at next definition mark,
- (?: # next term or end of text
- [ ]{0,'.$less_than_tab.'} \:[ ] |
-
";
-
- return "\n\n".$this->hashBlock($codeblock)."\n\n";
- }
- function _doFencedCodeBlocks_newlines($matches) {
- return str_repeat(" empty_element_suffix",
- strlen($matches[0]));
- }
-
-
- #
- # Redefining emphasis markers so that emphasis by underscore does not
- # work in the middle of a word.
- #
- var $em_relist = array(
- '' => '(?:(? '(?<=\S|^)(? '(?<=\S|^)(? '(?:(? '(?<=\S|^)(? '(?<=\S|^)(? '(?:(? '(?<=\S|^)(? '(?<=\S|^)(? tags
- #
- # Strip leading and trailing lines:
- $text = preg_replace('/\A\n+|\n+\z/', '', $text);
-
- $grafs = preg_split('/\n{2,}/', $text, -1, PREG_SPLIT_NO_EMPTY);
-
- #
- # Wrap
tags and unhashify HTML blocks
- #
- foreach ($grafs as $key => $value) {
- $value = trim($this->runSpanGamut($value));
-
- # Check if this should be enclosed in a paragraph.
- # Clean tag hashes & block tag hashes are left alone.
- $is_p = !preg_match('/^B\x1A[0-9]+B|^C\x1A[0-9]+C$/', $value);
-
- if ($is_p) {
- $value = "
$value
";
- }
- $grafs[$key] = $value;
- }
-
- # Join grafs in one text, then unhash HTML tags.
- $text = implode("\n\n", $grafs);
-
- # Finish by removing any tag hashes still present in $text.
- $text = $this->unhash($text);
-
- return $text;
- }
-
-
- ### Footnotes
-
- function stripFootnotes($text) {
- #
- # Strips link definitions from text, stores the URLs and titles in
- # hash references.
- #
- $less_than_tab = $this->tab_width - 1;
-
- # Link defs are in the form: [^id]: url "optional title"
- $text = preg_replace_callback('{
- ^[ ]{0,'.$less_than_tab.'}\[\^(.+?)\][ ]?: # note_id = $1
- [ ]*
- \n? # maybe *one* newline
- ( # text = $2 (no blank lines allowed)
- (?:
- .+ # actual text
- |
- \n # newlines but
- (?!\[\^.+?\]:\s)# negative lookahead for footnote marker.
- (?!\n+[ ]{0,3}\S)# ensure line is not blank and followed
- # by non-indented content
- )*
- )
- }xm',
- array(&$this, '_stripFootnotes_callback'),
- $text);
- return $text;
- }
- function _stripFootnotes_callback($matches) {
- $note_id = $this->fn_id_prefix . $matches[1];
- $this->footnotes[$note_id] = $this->outdent($matches[2]);
- return ''; # String that will replace the block
- }
-
-
- function doFootnotes($text) {
- #
- # Replace footnote references in $text [^id] with a special text-token
- # which will be replaced by the actual footnote marker in appendFootnotes.
- #
- if (!$this->in_anchor) {
- $text = preg_replace('{\[\^(.+?)\]}', "F\x1Afn:\\1\x1A:", $text);
- }
- return $text;
- }
-
-
- function appendFootnotes($text) {
- #
- # Append footnote list to text.
- #
- $text = preg_replace_callback('{F\x1Afn:(.*?)\x1A:}',
- array(&$this, '_appendFootnotes_callback'), $text);
-
- if (!empty($this->footnotes_ordered)) {
- $text .= "\n\n";
- $text .= "
";
- }
- return $text;
- }
- function _appendFootnotes_callback($matches) {
- $node_id = $this->fn_id_prefix . $matches[1];
-
- # Create footnote marker only if it has a corresponding footnote *and*
- # the footnote hasn't been used by another marker.
- if (isset($this->footnotes[$node_id])) {
- $num =& $this->footnotes_numbers[$node_id];
- if (!isset($num)) {
- # Transfer footnote content to the ordered list and give it its
- # number
- $this->footnotes_ordered[$node_id] = $this->footnotes[$node_id];
- $this->footnotes_ref_count[$node_id] = 1;
- $num = $this->footnote_counter++;
- $ref_count_mark = '';
- } else {
- $ref_count_mark = $this->footnotes_ref_count[$node_id] += 1;
- }
-
- $attr = " rel=\"footnote\"";
- if ($this->fn_link_class != "") {
- $class = $this->fn_link_class;
- $class = $this->encodeAttribute($class);
- $attr .= " class=\"$class\"";
- }
- if ($this->fn_link_title != "") {
- $title = $this->fn_link_title;
- $title = $this->encodeAttribute($title);
- $attr .= " title=\"$title\"";
- }
-
- $attr = str_replace("%%", $num, $attr);
- $node_id = $this->encodeAttribute($node_id);
-
- return
- "".
- "$num".
- "";
- }
-
- return "[^".$matches[1]."]";
- }
-
-
- ### Abbreviations ###
-
- function stripAbbreviations($text) {
- #
- # Strips abbreviations from text, stores titles in hash references.
- #
- $less_than_tab = $this->tab_width - 1;
-
- # Link defs are in the form: [id]*: url "optional title"
- $text = preg_replace_callback('{
- ^[ ]{0,'.$less_than_tab.'}\*\[(.+?)\][ ]?: # abbr_id = $1
- (.*) # text = $2 (no blank lines allowed)
- }xm',
- array(&$this, '_stripAbbreviations_callback'),
- $text);
- return $text;
- }
- function _stripAbbreviations_callback($matches) {
- $abbr_word = $matches[1];
- $abbr_desc = $matches[2];
- if ($this->abbr_word_re)
- $this->abbr_word_re .= '|';
- $this->abbr_word_re .= preg_quote($abbr_word);
- $this->abbr_desciptions[$abbr_word] = trim($abbr_desc);
- return ''; # String that will replace the block
- }
-
-
- function doAbbreviations($text) {
- #
- # Find defined abbreviations in text and wrap them in elements.
- #
- if ($this->abbr_word_re) {
- // cannot use the /x modifier because abbr_word_re may
- // contain significant spaces:
- $text = preg_replace_callback('{'.
- '(?abbr_word_re.')'.
- '(?![\w\x1A])'.
- '}',
- array(&$this, '_doAbbreviations_callback'), $text);
- }
- return $text;
- }
- function _doAbbreviations_callback($matches) {
- $abbr = $matches[0];
- if (isset($this->abbr_desciptions[$abbr])) {
- $desc = $this->abbr_desciptions[$abbr];
- if (empty($desc)) {
- return $this->hashPart("$abbr");
- } else {
- $desc = $this->encodeAttribute($desc);
- return $this->hashPart("$abbr");
- }
- } else {
- return $matches[0];
- }
- }
-
-}
-
-
-/*
-
-PHP Markdown Extra
-==================
-
-Description
------------
-
-This is a PHP port of the original Markdown formatter written in Perl
-by John Gruber. This special "Extra" version of PHP Markdown features
-further enhancements to the syntax for making additional constructs
-such as tables and definition list.
-
-Markdown is a text-to-HTML filter; it translates an easy-to-read /
-easy-to-write structured text format into HTML. Markdown's text format
-is mostly similar to that of plain text email, and supports features such
-as headers, *emphasis*, code blocks, blockquotes, and links.
-
-Markdown's syntax is designed not as a generic markup language, but
-specifically to serve as a front-end to (X)HTML. You can use span-level
-HTML tags anywhere in a Markdown document, and you can use block level
-HTML tags (like
and
as well).
-
-For more information about Markdown's syntax, see:
-
-
-
-
-Bugs
-----
-
-To file bug reports please send email to:
-
-
-
-Please include with your report: (1) the example input; (2) the output you
-expected; (3) the output Markdown actually produced.
-
-
-Version History
----------------
-
-See the readme file for detailed release notes for this version.
-
-
-Copyright and License
----------------------
-
-PHP Markdown & Extra
-Copyright (c) 2004-2013 Michel Fortin
-
-All rights reserved.
-
-Based on Markdown
-Copyright (c) 2003-2006 John Gruber
-
-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.
-
-* Neither the name "Markdown" nor the names of its contributors may
- be used to endorse or promote products derived from this software
- without specific prior written permission.
-
-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 owner
-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.
-
-*/
-?>
diff --git a/milfs/includes/mysql b/milfs/includes/mysql
deleted file mode 100644
index e69de29..0000000
diff --git a/milfs/includes/parametrizacion.php b/milfs/includes/parametrizacion.php
deleted file mode 100644
index 4f0ba8f..0000000
--- a/milfs/includes/parametrizacion.php
+++ /dev/null
@@ -1,23 +0,0 @@
-
diff --git a/milfs/includes/simple_html_dom.php b/milfs/includes/simple_html_dom.php
deleted file mode 100644
index bc2cf0a..0000000
--- a/milfs/includes/simple_html_dom.php
+++ /dev/null
@@ -1,1721 +0,0 @@
-size is the "real" number of bytes the dom was created from.
- * but for most purposes, it's a really good estimation.
- * Paperg - Added the forceTagsClosed to the dom constructor. Forcing tags closed is great for malformed html, but it CAN lead to parsing errors.
- * Allow the user to tell us how much they trust the html.
- * Paperg add the text and plaintext to the selectors for the find syntax. plaintext implies text in the innertext of a node. text implies that the tag is a text node.
- * This allows for us to find tags based on the text they contain.
- * Create find_ancestor_tag to see if a tag is - at any level - inside of another specific tag.
- * Paperg: added parse_charset so that we know about the character set of the source document.
- * NOTE: If the user's system has a routine called get_last_retrieve_url_contents_content_type availalbe, we will assume it's returning the content-type header from the
- * last transfer or curl_exec, and we will parse that and use it in preference to any other method of charset detection.
- *
- * Found infinite loop in the case of broken html in restore_noise. Rewrote to protect from that.
- * PaperG (John Schlick) Added get_display_size for "IMG" tags.
- *
- * Licensed under The MIT License
- * Redistributions of files must retain the above copyright notice.
- *
- * @author S.C. Chen
- * @author John Schlick
- * @author Rus Carroll
- * @version 1.5 ($Rev: 196 $)
- * @package PlaceLocalInclude
- * @subpackage simple_html_dom
- */
-
-/**
- * All of the Defines for the classes below.
- * @author S.C. Chen
- */
-define('HDOM_TYPE_ELEMENT', 1);
-define('HDOM_TYPE_COMMENT', 2);
-define('HDOM_TYPE_TEXT', 3);
-define('HDOM_TYPE_ENDTAG', 4);
-define('HDOM_TYPE_ROOT', 5);
-define('HDOM_TYPE_UNKNOWN', 6);
-define('HDOM_QUOTE_DOUBLE', 0);
-define('HDOM_QUOTE_SINGLE', 1);
-define('HDOM_QUOTE_NO', 3);
-define('HDOM_INFO_BEGIN', 0);
-define('HDOM_INFO_END', 1);
-define('HDOM_INFO_QUOTE', 2);
-define('HDOM_INFO_SPACE', 3);
-define('HDOM_INFO_TEXT', 4);
-define('HDOM_INFO_INNER', 5);
-define('HDOM_INFO_OUTER', 6);
-define('HDOM_INFO_ENDSPACE',7);
-define('DEFAULT_TARGET_CHARSET', 'UTF-8');
-define('DEFAULT_BR_TEXT', "\r\n");
-define('DEFAULT_SPAN_TEXT', " ");
-define('MAX_FILE_SIZE', 600000);
-// helper functions
-// -----------------------------------------------------------------------------
-// get html dom from file
-// $maxlen is defined in the code as PHP_STREAM_COPY_ALL which is defined as -1.
-function file_get_html($url, $use_include_path = false, $context=null, $offset = -1, $maxLen=-1, $lowercase = true, $forceTagsClosed=true, $target_charset = DEFAULT_TARGET_CHARSET, $stripRN=true, $defaultBRText=DEFAULT_BR_TEXT, $defaultSpanText=DEFAULT_SPAN_TEXT)
-{
- // We DO force the tags to be terminated.
- $dom = new simple_html_dom(null, $lowercase, $forceTagsClosed, $target_charset, $stripRN, $defaultBRText, $defaultSpanText);
- // For sourceforge users: uncomment the next line and comment the retreive_url_contents line 2 lines down if it is not already done.
- $contents = file_get_contents($url, $use_include_path, $context, $offset);
- // Paperg - use our own mechanism for getting the contents as we want to control the timeout.
- //$contents = retrieve_url_contents($url);
- if (empty($contents) || strlen($contents) > MAX_FILE_SIZE)
- {
- return false;
- }
- // The second parameter can force the selectors to all be lowercase.
- $dom->load($contents, $lowercase, $stripRN);
- return $dom;
-}
-
-// get html dom from string
-function str_get_html($str, $lowercase=true, $forceTagsClosed=true, $target_charset = DEFAULT_TARGET_CHARSET, $stripRN=true, $defaultBRText=DEFAULT_BR_TEXT, $defaultSpanText=DEFAULT_SPAN_TEXT)
-{
- $dom = new simple_html_dom(null, $lowercase, $forceTagsClosed, $target_charset, $stripRN, $defaultBRText, $defaultSpanText);
- if (empty($str) || strlen($str) > MAX_FILE_SIZE)
- {
- $dom->clear();
- return false;
- }
- $dom->load($str, $lowercase, $stripRN);
- return $dom;
-}
-
-// dump html dom tree
-function dump_html_tree($node, $show_attr=true, $deep=0)
-{
- $node->dump($node);
-}
-
-
-/**
- * simple html dom node
- * PaperG - added ability for "find" routine to lowercase the value of the selector.
- * PaperG - added $tag_start to track the start position of the tag in the total byte index
- *
- * @package PlaceLocalInclude
- */
-class simple_html_dom_node
-{
- public $nodetype = HDOM_TYPE_TEXT;
- public $tag = 'text';
- public $attr = array();
- public $children = array();
- public $nodes = array();
- public $parent = null;
- // The "info" array - see HDOM_INFO_... for what each element contains.
- public $_ = array();
- public $tag_start = 0;
- private $dom = null;
-
- function __construct($dom)
- {
- $this->dom = $dom;
- $dom->nodes[] = $this;
- }
-
- function __destruct()
- {
- $this->clear();
- }
-
- function __toString()
- {
- return $this->outertext();
- }
-
- // clean up memory due to php5 circular references memory leak...
- function clear()
- {
- $this->dom = null;
- $this->nodes = null;
- $this->parent = null;
- $this->children = null;
- }
-
- // dump node's tree
- function dump($show_attr=true, $deep=0)
- {
- $lead = str_repeat(' ', $deep);
-
- echo $lead.$this->tag;
- if ($show_attr && count($this->attr)>0)
- {
- echo '(';
- foreach ($this->attr as $k=>$v)
- echo "[$k]=>\"".$this->$k.'", ';
- echo ')';
- }
- echo "\n";
-
- if ($this->nodes)
- {
- foreach ($this->nodes as $c)
- {
- $c->dump($show_attr, $deep+1);
- }
- }
- }
-
-
- // Debugging function to dump a single dom node with a bunch of information about it.
- function dump_node($echo=true)
- {
-
- $string = $this->tag;
- if (count($this->attr)>0)
- {
- $string .= '(';
- foreach ($this->attr as $k=>$v)
- {
- $string .= "[$k]=>\"".$this->$k.'", ';
- }
- $string .= ')';
- }
- if (count($this->_)>0)
- {
- $string .= ' $_ (';
- foreach ($this->_ as $k=>$v)
- {
- if (is_array($v))
- {
- $string .= "[$k]=>(";
- foreach ($v as $k2=>$v2)
- {
- $string .= "[$k2]=>\"".$v2.'", ';
- }
- $string .= ")";
- } else {
- $string .= "[$k]=>\"".$v.'", ';
- }
- }
- $string .= ")";
- }
-
- if (isset($this->text))
- {
- $string .= " text: (" . $this->text . ")";
- }
-
- $string .= " HDOM_INNER_INFO: '";
- if (isset($node->_[HDOM_INFO_INNER]))
- {
- $string .= $node->_[HDOM_INFO_INNER] . "'";
- }
- else
- {
- $string .= ' NULL ';
- }
-
- $string .= " children: " . count($this->children);
- $string .= " nodes: " . count($this->nodes);
- $string .= " tag_start: " . $this->tag_start;
- $string .= "\n";
-
- if ($echo)
- {
- echo $string;
- return;
- }
- else
- {
- return $string;
- }
- }
-
- // returns the parent of node
- // If a node is passed in, it will reset the parent of the current node to that one.
- function parent($parent=null)
- {
- // I am SURE that this doesn't work properly.
- // It fails to unset the current node from it's current parents nodes or children list first.
- if ($parent !== null)
- {
- $this->parent = $parent;
- $this->parent->nodes[] = $this;
- $this->parent->children[] = $this;
- }
-
- return $this->parent;
- }
-
- // verify that node has children
- function has_child()
- {
- return !empty($this->children);
- }
-
- // returns children of node
- function children($idx=-1)
- {
- if ($idx===-1)
- {
- return $this->children;
- }
- if (isset($this->children[$idx])) return $this->children[$idx];
- return null;
- }
-
- // returns the first child of node
- function first_child()
- {
- if (count($this->children)>0)
- {
- return $this->children[0];
- }
- return null;
- }
-
- // returns the last child of node
- function last_child()
- {
- if (($count=count($this->children))>0)
- {
- return $this->children[$count-1];
- }
- return null;
- }
-
- // returns the next sibling of node
- function next_sibling()
- {
- if ($this->parent===null)
- {
- return null;
- }
-
- $idx = 0;
- $count = count($this->parent->children);
- while ($idx<$count && $this!==$this->parent->children[$idx])
- {
- ++$idx;
- }
- if (++$idx>=$count)
- {
- return null;
- }
- return $this->parent->children[$idx];
- }
-
- // returns the previous sibling of node
- function prev_sibling()
- {
- if ($this->parent===null) return null;
- $idx = 0;
- $count = count($this->parent->children);
- while ($idx<$count && $this!==$this->parent->children[$idx])
- ++$idx;
- if (--$idx<0) return null;
- return $this->parent->children[$idx];
- }
-
- // function to locate a specific ancestor tag in the path to the root.
- function find_ancestor_tag($tag)
- {
- global $debugObject;
- if (is_object($debugObject)) { $debugObject->debugLogEntry(1); }
-
- // Start by including ourselves in the comparison.
- $returnDom = $this;
-
- while (!is_null($returnDom))
- {
- if (is_object($debugObject)) { $debugObject->debugLog(2, "Current tag is: " . $returnDom->tag); }
-
- if ($returnDom->tag == $tag)
- {
- break;
- }
- $returnDom = $returnDom->parent;
- }
- return $returnDom;
- }
-
- // get dom node's inner html
- function innertext()
- {
- if (isset($this->_[HDOM_INFO_INNER])) return $this->_[HDOM_INFO_INNER];
- if (isset($this->_[HDOM_INFO_TEXT])) return $this->dom->restore_noise($this->_[HDOM_INFO_TEXT]);
-
- $ret = '';
- foreach ($this->nodes as $n)
- $ret .= $n->outertext();
- return $ret;
- }
-
- // get dom node's outer text (with tag)
- function outertext()
- {
- global $debugObject;
- if (is_object($debugObject))
- {
- $text = '';
- if ($this->tag == 'text')
- {
- if (!empty($this->text))
- {
- $text = " with text: " . $this->text;
- }
- }
- $debugObject->debugLog(1, 'Innertext of tag: ' . $this->tag . $text);
- }
-
- if ($this->tag==='root') return $this->innertext();
-
- // trigger callback
- if ($this->dom && $this->dom->callback!==null)
- {
- call_user_func_array($this->dom->callback, array($this));
- }
-
- if (isset($this->_[HDOM_INFO_OUTER])) return $this->_[HDOM_INFO_OUTER];
- if (isset($this->_[HDOM_INFO_TEXT])) return $this->dom->restore_noise($this->_[HDOM_INFO_TEXT]);
-
- // render begin tag
- if ($this->dom && $this->dom->nodes[$this->_[HDOM_INFO_BEGIN]])
- {
- $ret = $this->dom->nodes[$this->_[HDOM_INFO_BEGIN]]->makeup();
- } else {
- $ret = "";
- }
-
- // render inner text
- if (isset($this->_[HDOM_INFO_INNER]))
- {
- // If it's a br tag... don't return the HDOM_INNER_INFO that we may or may not have added.
- if ($this->tag != "br")
- {
- $ret .= $this->_[HDOM_INFO_INNER];
- }
- } else {
- if ($this->nodes)
- {
- foreach ($this->nodes as $n)
- {
- $ret .= $this->convert_text($n->outertext());
- }
- }
- }
-
- // render end tag
- if (isset($this->_[HDOM_INFO_END]) && $this->_[HDOM_INFO_END]!=0)
- $ret .= ''.$this->tag.'>';
- return $ret;
- }
-
- // get dom node's plain text
- function text()
- {
- if (isset($this->_[HDOM_INFO_INNER])) return $this->_[HDOM_INFO_INNER];
- switch ($this->nodetype)
- {
- case HDOM_TYPE_TEXT: return $this->dom->restore_noise($this->_[HDOM_INFO_TEXT]);
- case HDOM_TYPE_COMMENT: return '';
- case HDOM_TYPE_UNKNOWN: return '';
- }
- if (strcasecmp($this->tag, 'script')===0) return '';
- if (strcasecmp($this->tag, 'style')===0) return '';
-
- $ret = '';
- // In rare cases, (always node type 1 or HDOM_TYPE_ELEMENT - observed for some span tags, and some p tags) $this->nodes is set to NULL.
- // NOTE: This indicates that there is a problem where it's set to NULL without a clear happening.
- // WHY is this happening?
- if (!is_null($this->nodes))
- {
- foreach ($this->nodes as $n)
- {
- $ret .= $this->convert_text($n->text());
- }
-
- // If this node is a span... add a space at the end of it so multiple spans don't run into each other. This is plaintext after all.
- if ($this->tag == "span")
- {
- $ret .= $this->dom->default_span_text;
- }
-
-
- }
- return $ret;
- }
-
- function xmltext()
- {
- $ret = $this->innertext();
- $ret = str_ireplace('', '', $ret);
- return $ret;
- }
-
- // build node's text with tag
- function makeup()
- {
- // text, comment, unknown
- if (isset($this->_[HDOM_INFO_TEXT])) return $this->dom->restore_noise($this->_[HDOM_INFO_TEXT]);
-
- $ret = '<'.$this->tag;
- $i = -1;
-
- foreach ($this->attr as $key=>$val)
- {
- ++$i;
-
- // skip removed attribute
- if ($val===null || $val===false)
- continue;
-
- $ret .= $this->_[HDOM_INFO_SPACE][$i][0];
- //no value attr: nowrap, checked selected...
- if ($val===true)
- $ret .= $key;
- else {
- switch ($this->_[HDOM_INFO_QUOTE][$i])
- {
- case HDOM_QUOTE_DOUBLE: $quote = '"'; break;
- case HDOM_QUOTE_SINGLE: $quote = '\''; break;
- default: $quote = '';
- }
- $ret .= $key.$this->_[HDOM_INFO_SPACE][$i][1].'='.$this->_[HDOM_INFO_SPACE][$i][2].$quote.$val.$quote;
- }
- }
- $ret = $this->dom->restore_noise($ret);
- return $ret . $this->_[HDOM_INFO_ENDSPACE] . '>';
- }
-
- // find elements by css selector
- //PaperG - added ability for find to lowercase the value of the selector.
- function find($selector, $idx=null, $lowercase=false)
- {
- $selectors = $this->parse_selector($selector);
- if (($count=count($selectors))===0) return array();
- $found_keys = array();
-
- // find each selector
- for ($c=0; $c<$count; ++$c)
- {
- // The change on the below line was documented on the sourceforge code tracker id 2788009
- // used to be: if (($levle=count($selectors[0]))===0) return array();
- if (($levle=count($selectors[$c]))===0) return array();
- if (!isset($this->_[HDOM_INFO_BEGIN])) return array();
-
- $head = array($this->_[HDOM_INFO_BEGIN]=>1);
-
- // handle descendant selectors, no recursive!
- for ($l=0; $l<$levle; ++$l)
- {
- $ret = array();
- foreach ($head as $k=>$v)
- {
- $n = ($k===-1) ? $this->dom->root : $this->dom->nodes[$k];
- //PaperG - Pass this optional parameter on to the seek function.
- $n->seek($selectors[$c][$l], $ret, $lowercase);
- }
- $head = $ret;
- }
-
- foreach ($head as $k=>$v)
- {
- if (!isset($found_keys[$k]))
- $found_keys[$k] = 1;
- }
- }
-
- // sort keys
- ksort($found_keys);
-
- $found = array();
- foreach ($found_keys as $k=>$v)
- $found[] = $this->dom->nodes[$k];
-
- // return nth-element or array
- if (is_null($idx)) return $found;
- else if ($idx<0) $idx = count($found) + $idx;
- return (isset($found[$idx])) ? $found[$idx] : null;
- }
-
- // seek for given conditions
- // PaperG - added parameter to allow for case insensitive testing of the value of a selector.
- protected function seek($selector, &$ret, $lowercase=false)
- {
- global $debugObject;
- if (is_object($debugObject)) { $debugObject->debugLogEntry(1); }
-
- list($tag, $key, $val, $exp, $no_key) = $selector;
-
- // xpath index
- if ($tag && $key && is_numeric($key))
- {
- $count = 0;
- foreach ($this->children as $c)
- {
- if ($tag==='*' || $tag===$c->tag) {
- if (++$count==$key) {
- $ret[$c->_[HDOM_INFO_BEGIN]] = 1;
- return;
- }
- }
- }
- return;
- }
-
- $end = (!empty($this->_[HDOM_INFO_END])) ? $this->_[HDOM_INFO_END] : 0;
- if ($end==0) {
- $parent = $this->parent;
- while (!isset($parent->_[HDOM_INFO_END]) && $parent!==null) {
- $end -= 1;
- $parent = $parent->parent;
- }
- $end += $parent->_[HDOM_INFO_END];
- }
-
- for ($i=$this->_[HDOM_INFO_BEGIN]+1; $i<$end; ++$i) {
- $node = $this->dom->nodes[$i];
-
- $pass = true;
-
- if ($tag==='*' && !$key) {
- if (in_array($node, $this->children, true))
- $ret[$i] = 1;
- continue;
- }
-
- // compare tag
- if ($tag && $tag!=$node->tag && $tag!=='*') {$pass=false;}
- // compare key
- if ($pass && $key) {
- if ($no_key) {
- if (isset($node->attr[$key])) $pass=false;
- } else {
- if (($key != "plaintext") && !isset($node->attr[$key])) $pass=false;
- }
- }
- // compare value
- if ($pass && $key && $val && $val!=='*') {
- // If they have told us that this is a "plaintext" search then we want the plaintext of the node - right?
- if ($key == "plaintext") {
- // $node->plaintext actually returns $node->text();
- $nodeKeyValue = $node->text();
- } else {
- // this is a normal search, we want the value of that attribute of the tag.
- $nodeKeyValue = $node->attr[$key];
- }
- if (is_object($debugObject)) {$debugObject->debugLog(2, "testing node: " . $node->tag . " for attribute: " . $key . $exp . $val . " where nodes value is: " . $nodeKeyValue);}
-
- //PaperG - If lowercase is set, do a case insensitive test of the value of the selector.
- if ($lowercase) {
- $check = $this->match($exp, strtolower($val), strtolower($nodeKeyValue));
- } else {
- $check = $this->match($exp, $val, $nodeKeyValue);
- }
- if (is_object($debugObject)) {$debugObject->debugLog(2, "after match: " . ($check ? "true" : "false"));}
-
- // handle multiple class
- if (!$check && strcasecmp($key, 'class')===0) {
- foreach (explode(' ',$node->attr[$key]) as $k) {
- // Without this, there were cases where leading, trailing, or double spaces lead to our comparing blanks - bad form.
- if (!empty($k)) {
- if ($lowercase) {
- $check = $this->match($exp, strtolower($val), strtolower($k));
- } else {
- $check = $this->match($exp, $val, $k);
- }
- if ($check) break;
- }
- }
- }
- if (!$check) $pass = false;
- }
- if ($pass) $ret[$i] = 1;
- unset($node);
- }
- // It's passed by reference so this is actually what this function returns.
- if (is_object($debugObject)) {$debugObject->debugLog(1, "EXIT - ret: ", $ret);}
- }
-
- protected function match($exp, $pattern, $value) {
- global $debugObject;
- if (is_object($debugObject)) {$debugObject->debugLogEntry(1);}
-
- switch ($exp) {
- case '=':
- return ($value===$pattern);
- case '!=':
- return ($value!==$pattern);
- case '^=':
- return preg_match("/^".preg_quote($pattern,'/')."/", $value);
- case '$=':
- return preg_match("/".preg_quote($pattern,'/')."$/", $value);
- case '*=':
- if ($pattern[0]=='/') {
- return preg_match($pattern, $value);
- }
- return preg_match("/".$pattern."/i", $value);
- }
- return false;
- }
-
- protected function parse_selector($selector_string) {
- global $debugObject;
- if (is_object($debugObject)) {$debugObject->debugLogEntry(1);}
-
- // pattern of CSS selectors, modified from mootools
- // Paperg: Add the colon to the attrbute, so that it properly finds like google does.
- // Note: if you try to look at this attribute, yo MUST use getAttribute since $dom->x:y will fail the php syntax check.
-// Notice the \[ starting the attbute? and the @? following? This implies that an attribute can begin with an @ sign that is not captured.
-// This implies that an html attribute specifier may start with an @ sign that is NOT captured by the expression.
-// farther study is required to determine of this should be documented or removed.
-// $pattern = "/([\w-:\*]*)(?:\#([\w-]+)|\.([\w-]+))?(?:\[@?(!?[\w-]+)(?:([!*^$]?=)[\"']?(.*?)[\"']?)?\])?([\/, ]+)/is";
- $pattern = "/([\w-:\*]*)(?:\#([\w-]+)|\.([\w-]+))?(?:\[@?(!?[\w-:]+)(?:([!*^$]?=)[\"']?(.*?)[\"']?)?\])?([\/, ]+)/is";
- preg_match_all($pattern, trim($selector_string).' ', $matches, PREG_SET_ORDER);
- if (is_object($debugObject)) {$debugObject->debugLog(2, "Matches Array: ", $matches);}
-
- $selectors = array();
- $result = array();
- //print_r($matches);
-
- foreach ($matches as $m) {
- $m[0] = trim($m[0]);
- if ($m[0]==='' || $m[0]==='/' || $m[0]==='//') continue;
- // for browser generated xpath
- if ($m[1]==='tbody') continue;
-
- list($tag, $key, $val, $exp, $no_key) = array($m[1], null, null, '=', false);
- if (!empty($m[2])) {$key='id'; $val=$m[2];}
- if (!empty($m[3])) {$key='class'; $val=$m[3];}
- if (!empty($m[4])) {$key=$m[4];}
- if (!empty($m[5])) {$exp=$m[5];}
- if (!empty($m[6])) {$val=$m[6];}
-
- // convert to lowercase
- if ($this->dom->lowercase) {$tag=strtolower($tag); $key=strtolower($key);}
- //elements that do NOT have the specified attribute
- if (isset($key[0]) && $key[0]==='!') {$key=substr($key, 1); $no_key=true;}
-
- $result[] = array($tag, $key, $val, $exp, $no_key);
- if (trim($m[7])===',') {
- $selectors[] = $result;
- $result = array();
- }
- }
- if (count($result)>0)
- $selectors[] = $result;
- return $selectors;
- }
-
- function __get($name) {
- if (isset($this->attr[$name]))
- {
- return $this->convert_text($this->attr[$name]);
- }
- switch ($name) {
- case 'outertext': return $this->outertext();
- case 'innertext': return $this->innertext();
- case 'plaintext': return $this->text();
- case 'xmltext': return $this->xmltext();
- default: return array_key_exists($name, $this->attr);
- }
- }
-
- function __set($name, $value) {
- switch ($name) {
- case 'outertext': return $this->_[HDOM_INFO_OUTER] = $value;
- case 'innertext':
- if (isset($this->_[HDOM_INFO_TEXT])) return $this->_[HDOM_INFO_TEXT] = $value;
- return $this->_[HDOM_INFO_INNER] = $value;
- }
- if (!isset($this->attr[$name])) {
- $this->_[HDOM_INFO_SPACE][] = array(' ', '', '');
- $this->_[HDOM_INFO_QUOTE][] = HDOM_QUOTE_DOUBLE;
- }
- $this->attr[$name] = $value;
- }
-
- function __isset($name) {
- switch ($name) {
- case 'outertext': return true;
- case 'innertext': return true;
- case 'plaintext': return true;
- }
- //no value attr: nowrap, checked selected...
- return (array_key_exists($name, $this->attr)) ? true : isset($this->attr[$name]);
- }
-
- function __unset($name) {
- if (isset($this->attr[$name]))
- unset($this->attr[$name]);
- }
-
- // PaperG - Function to convert the text from one character set to another if the two sets are not the same.
- function convert_text($text)
- {
- global $debugObject;
- if (is_object($debugObject)) {$debugObject->debugLogEntry(1);}
-
- $converted_text = $text;
-
- $sourceCharset = "";
- $targetCharset = "";
-
- if ($this->dom)
- {
- $sourceCharset = strtoupper($this->dom->_charset);
- $targetCharset = strtoupper($this->dom->_target_charset);
- }
- if (is_object($debugObject)) {$debugObject->debugLog(3, "source charset: " . $sourceCharset . " target charaset: " . $targetCharset);}
-
- if (!empty($sourceCharset) && !empty($targetCharset) && (strcasecmp($sourceCharset, $targetCharset) != 0))
- {
- // Check if the reported encoding could have been incorrect and the text is actually already UTF-8
- if ((strcasecmp($targetCharset, 'UTF-8') == 0) && ($this->is_utf8($text)))
- {
- $converted_text = $text;
- }
- else
- {
- $converted_text = iconv($sourceCharset, $targetCharset, $text);
- }
- }
-
- // Lets make sure that we don't have that silly BOM issue with any of the utf-8 text we output.
- if ($targetCharset == 'UTF-8')
- {
- if (substr($converted_text, 0, 3) == "\xef\xbb\xbf")
- {
- $converted_text = substr($converted_text, 3);
- }
- if (substr($converted_text, -3) == "\xef\xbb\xbf")
- {
- $converted_text = substr($converted_text, 0, -3);
- }
- }
-
- return $converted_text;
- }
-
- /**
- * Returns true if $string is valid UTF-8 and false otherwise.
- *
- * @param mixed $str String to be tested
- * @return boolean
- */
- static function is_utf8($str)
- {
- $c=0; $b=0;
- $bits=0;
- $len=strlen($str);
- for($i=0; $i<$len; $i++)
- {
- $c=ord($str[$i]);
- if($c > 128)
- {
- if(($c >= 254)) return false;
- elseif($c >= 252) $bits=6;
- elseif($c >= 248) $bits=5;
- elseif($c >= 240) $bits=4;
- elseif($c >= 224) $bits=3;
- elseif($c >= 192) $bits=2;
- else return false;
- if(($i+$bits) > $len) return false;
- while($bits > 1)
- {
- $i++;
- $b=ord($str[$i]);
- if($b < 128 || $b > 191) return false;
- $bits--;
- }
- }
- }
- return true;
- }
- /*
- function is_utf8($string)
- {
- //this is buggy
- return (utf8_encode(utf8_decode($string)) == $string);
- }
- */
-
- /**
- * Function to try a few tricks to determine the displayed size of an img on the page.
- * NOTE: This will ONLY work on an IMG tag. Returns FALSE on all other tag types.
- *
- * @author John Schlick
- * @version April 19 2012
- * @return array an array containing the 'height' and 'width' of the image on the page or -1 if we can't figure it out.
- */
- function get_display_size()
- {
- global $debugObject;
-
- $width = -1;
- $height = -1;
-
- if ($this->tag !== 'img')
- {
- return false;
- }
-
- // See if there is aheight or width attribute in the tag itself.
- if (isset($this->attr['width']))
- {
- $width = $this->attr['width'];
- }
-
- if (isset($this->attr['height']))
- {
- $height = $this->attr['height'];
- }
-
- // Now look for an inline style.
- if (isset($this->attr['style']))
- {
- // Thanks to user gnarf from stackoverflow for this regular expression.
- $attributes = array();
- preg_match_all("/([\w-]+)\s*:\s*([^;]+)\s*;?/", $this->attr['style'], $matches, PREG_SET_ORDER);
- foreach ($matches as $match) {
- $attributes[$match[1]] = $match[2];
- }
-
- // If there is a width in the style attributes:
- if (isset($attributes['width']) && $width == -1)
- {
- // check that the last two characters are px (pixels)
- if (strtolower(substr($attributes['width'], -2)) == 'px')
- {
- $proposed_width = substr($attributes['width'], 0, -2);
- // Now make sure that it's an integer and not something stupid.
- if (filter_var($proposed_width, FILTER_VALIDATE_INT))
- {
- $width = $proposed_width;
- }
- }
- }
-
- // If there is a width in the style attributes:
- if (isset($attributes['height']) && $height == -1)
- {
- // check that the last two characters are px (pixels)
- if (strtolower(substr($attributes['height'], -2)) == 'px')
- {
- $proposed_height = substr($attributes['height'], 0, -2);
- // Now make sure that it's an integer and not something stupid.
- if (filter_var($proposed_height, FILTER_VALIDATE_INT))
- {
- $height = $proposed_height;
- }
- }
- }
-
- }
-
- // Future enhancement:
- // Look in the tag to see if there is a class or id specified that has a height or width attribute to it.
-
- // Far future enhancement
- // Look at all the parent tags of this image to see if they specify a class or id that has an img selector that specifies a height or width
- // Note that in this case, the class or id will have the img subselector for it to apply to the image.
-
- // ridiculously far future development
- // If the class or id is specified in a SEPARATE css file thats not on the page, go get it and do what we were just doing for the ones on the page.
-
- $result = array('height' => $height,
- 'width' => $width);
- return $result;
- }
-
- // camel naming conventions
- function getAllAttributes() {return $this->attr;}
- function getAttribute($name) {return $this->__get($name);}
- function setAttribute($name, $value) {$this->__set($name, $value);}
- function hasAttribute($name) {return $this->__isset($name);}
- function removeAttribute($name) {$this->__set($name, null);}
- function getElementById($id) {return $this->find("#$id", 0);}
- function getElementsById($id, $idx=null) {return $this->find("#$id", $idx);}
- function getElementByTagName($name) {return $this->find($name, 0);}
- function getElementsByTagName($name, $idx=null) {return $this->find($name, $idx);}
- function parentNode() {return $this->parent();}
- function childNodes($idx=-1) {return $this->children($idx);}
- function firstChild() {return $this->first_child();}
- function lastChild() {return $this->last_child();}
- function nextSibling() {return $this->next_sibling();}
- function previousSibling() {return $this->prev_sibling();}
- function hasChildNodes() {return $this->has_child();}
- function nodeName() {return $this->tag;}
- function appendChild($node) {$node->parent($this); return $node;}
-
-}
-
-/**
- * simple html dom parser
- * Paperg - in the find routine: allow us to specify that we want case insensitive testing of the value of the selector.
- * Paperg - change $size from protected to public so we can easily access it
- * Paperg - added ForceTagsClosed in the constructor which tells us whether we trust the html or not. Default is to NOT trust it.
- *
- * @package PlaceLocalInclude
- */
-class simple_html_dom
-{
- public $root = null;
- public $nodes = array();
- public $callback = null;
- public $lowercase = false;
- // Used to keep track of how large the text was when we started.
- public $original_size;
- public $size;
- protected $pos;
- protected $doc;
- protected $char;
- protected $cursor;
- protected $parent;
- protected $noise = array();
- protected $token_blank = " \t\r\n";
- protected $token_equal = ' =/>';
- protected $token_slash = " />\r\n\t";
- protected $token_attr = ' >';
- // Note that this is referenced by a child node, and so it needs to be public for that node to see this information.
- public $_charset = '';
- public $_target_charset = '';
- protected $default_br_text = "";
- public $default_span_text = "";
-
- // use isset instead of in_array, performance boost about 30%...
- protected $self_closing_tags = array('img'=>1, 'br'=>1, 'input'=>1, 'meta'=>1, 'link'=>1, 'hr'=>1, 'base'=>1, 'embed'=>1, 'spacer'=>1);
- protected $block_tags = array('root'=>1, 'body'=>1, 'form'=>1, 'div'=>1, 'span'=>1, 'table'=>1);
- // Known sourceforge issue #2977341
- // B tags that are not closed cause us to return everything to the end of the document.
- protected $optional_closing_tags = array(
- 'tr'=>array('tr'=>1, 'td'=>1, 'th'=>1),
- 'th'=>array('th'=>1),
- 'td'=>array('td'=>1),
- 'li'=>array('li'=>1),
- 'dt'=>array('dt'=>1, 'dd'=>1),
- 'dd'=>array('dd'=>1, 'dt'=>1),
- 'dl'=>array('dd'=>1, 'dt'=>1),
- 'p'=>array('p'=>1),
- 'nobr'=>array('nobr'=>1),
- 'b'=>array('b'=>1),
- 'option'=>array('option'=>1),
- );
-
- function __construct($str=null, $lowercase=true, $forceTagsClosed=true, $target_charset=DEFAULT_TARGET_CHARSET, $stripRN=true, $defaultBRText=DEFAULT_BR_TEXT, $defaultSpanText=DEFAULT_SPAN_TEXT)
- {
- if ($str)
- {
- if (preg_match("/^http:\/\//i",$str) || is_file($str))
- {
- $this->load_file($str);
- }
- else
- {
- $this->load($str, $lowercase, $stripRN, $defaultBRText, $defaultSpanText);
- }
- }
- // Forcing tags to be closed implies that we don't trust the html, but it can lead to parsing errors if we SHOULD trust the html.
- if (!$forceTagsClosed) {
- $this->optional_closing_array=array();
- }
- $this->_target_charset = $target_charset;
- }
-
- function __destruct()
- {
- $this->clear();
- }
-
- // load html from string
- function load($str, $lowercase=true, $stripRN=true, $defaultBRText=DEFAULT_BR_TEXT, $defaultSpanText=DEFAULT_SPAN_TEXT)
- {
- global $debugObject;
-
- // prepare
- $this->prepare($str, $lowercase, $stripRN, $defaultBRText, $defaultSpanText);
- // strip out comments
- $this->remove_noise("''is");
- // strip out cdata
- $this->remove_noise("''is", true);
- // Per sourceforge http://sourceforge.net/tracker/?func=detail&aid=2949097&group_id=218559&atid=1044037
- // Script tags removal now preceeds style tag removal.
- // strip out ';
-else{
-/* echo generar_miniatura_alto($name,"150");
- echo generar_miniatura_alto($name,"300");
- echo generar_miniatura_alto($name,"600");
- */
- echo generar_miniatura($name,"150");
- echo generar_miniatura($name,"300");
- echo generar_miniatura($name,"600");
- ///$name= "$name?$coordenadas"
-echo " ";
-}
-}
-else echo " ";
-
-}
-else{
-echo "";
-}
-
-function generar_miniatura($file,$width) {
//$archivo = $file;
-$archivo = "$_SESSION[path_images_secure]/full/".$file;
// Ponemos el . antes del nombre del archivo porque estamos considerando que la ruta está a partir del archivo thumb.php
$file_info = getimagesize($archivo);
// Obtenemos la relación de aspecto
$ratio = $file_info[0] / $file_info[1];
// Calculamos las nuevas dimensiones
$newwidth = $width;
$newheight = round($newwidth / $ratio);
// Sacamos la extensión del archivo
$ext = explode(".", $file);
$ext = strtolower($ext[count($ext) - 1]);
if ($ext == "jpeg") $ext = "jpg";
// Dependiendo de la extensión llamamos a distintas funciones
switch ($ext) {
case "jpg":
$img = imagecreatefromjpeg($archivo);
break;
case "png":
$img = imagecreatefrompng($archivo);
break;
case "gif":
$img = imagecreatefromgif($archivo);
break;
}
// Creamos la miniatura
$thumb = imagecreatetruecolor($newwidth, $newheight);
-imagealphablending( $thumb, false );
-imagesavealpha( $thumb, true );
// La redimensionamos
imagecopyresampled($thumb, $img, 0, 0, 0, 0, $newwidth, $newheight, $file_info[0], $file_info[1]);
// La mostramos como jpg
//header("Content-type: image/jpeg");
imagejpeg($thumb,"$_SESSION[path_images_secure]/".$width."/$file", 80);
-imagepng($thumb,"$_SESSION[path_images_secure]/".$width."/$file", 9);
-//imagegif($thumb,"$_SESSION[path_images_secure]/".$width."/$file");
-//imagejpeg($thumb,null, 80);
-}
-function generar_miniatura_alto($file,$alto) {
//$archivo = $file;
-$archivo = "$_SESSION[path_images_secure]/full/".$file;
// Ponemos el . antes del nombre del archivo porque estamos considerando que la ruta está a partir del archivo thumb.php
$file_info = getimagesize($archivo);
// Obtenemos la relación de aspecto
$ratio = $file_info[1]/$file_info[0];
// Calculamos las nuevas dimensiones
-$newheight = $alto;
$newwidth = round($newheight / $ratio);
// Sacamos la extensión del archivo
$ext = explode(".", $file);
$ext = strtolower($ext[count($ext) - 1]);
if ($ext == "jpeg") $ext = "jpg";
// Dependiendo de la extensión llamamos a distintas funciones
switch ($ext) {
case "jpg":
$img = imagecreatefromjpeg($archivo);
break;
case "png":
$img = imagecreatefrompng($archivo);
break;
case "gif":
$img = imagecreatefromgif($archivo);
break;
}
// Creamos la miniatura
$thumb = imagecreatetruecolor($newwidth, $newheight);
-imagealphablending( $thumb, false );
-imagesavealpha( $thumb, true );
// La redimensionamos
imagecopyresampled($thumb, $img, 0, 0, 0, 0, $newwidth, $newheight, $file_info[0], $file_info[1]);
// La mostramos como jpg
//header("Content-type: image/jpeg");
-imagepng($thumb,"$_SESSION[path_images_secure]/".$alto."/$file", 80);
-imagejpeg($thumb,"$_SESSION[path_images_secure]/".$alto."/$file", 80);
-//imagejpeg($thumb,null, 80);
-}
-
-// Convertir un string "1/123" a su representación float
-function exif_float($value) {
- $pos = strpos($value, '/');
- if ($pos === false) return (float) $value;
- $a = (float) substr($value, 0, $pos);
- $b = (float) substr($value, $pos+1);
- return ($b == 0) ? ($a) : ($a / $b);
-}
-
-function leer_exif($file){
- //$file = "/var/www/html/milfs/images/gps.jpg";
- $exif = exif_read_data( $file );
-if ( !empty($exif['GPSLongitude']) && !empty($exif['GPSLatitude']) ) {
- $d = (float) $exif['GPSLongitude'][0];
- $m = exif_float($exif['GPSLongitude'][1] );
- $s = exif_float( $exif['GPSLongitude'][2] );
-
- $gps_longitude = (float) $d + $m/60 + $s/3600;
- if ( $exif['GPSLongitudeRef'] == 'W')
- $gps_longitude = -$gps_longitude;
-
- $d = $exif['GPSLatitude'][0];
- $m = exif_float($exif['GPSLatitude'][1] );
- $s = exif_float( $exif['GPSLatitude'][2] );
-
- $gps_latitude = (float) $d + $m/60 + $s/3600;
- if ( $exif['GPSLatitudeRef'] == 'S')
- $gps_latitude = -$gps_latitude;
- if($gps_latitude !='') {
- $resultado = "../mapa.php?lon=$gps_latitude&lat=$gps_longitude&zoom=18&exif=exif";
- }else{$resultado ="";}
-//$resultado = "$gps_longitude $gps_latitude";
-
- return $resultado;
-}
-}
-
-?>
-
diff --git a/milfs/includes/upload_archivo.php b/milfs/includes/upload_archivo.php
deleted file mode 100644
index 7fe3d58..0000000
--- a/milfs/includes/upload_archivo.php
+++ /dev/null
@@ -1,38 +0,0 @@
-parent.resultadoUploadArchivo(1,"'.$nombre.'","aviso_archivo"); ';
-else{
-echo ' ';
-}
-}
-else echo ' ';
-}
-else{
-echo ' ';
-}
-?>
-
diff --git a/milfs/includes/upload_generico.php b/milfs/includes/upload_generico.php
deleted file mode 100644
index 2fbf843..0000000
--- a/milfs/includes/upload_generico.php
+++ /dev/null
@@ -1,107 +0,0 @@
-
-
-
diff --git a/milfs/index.php b/milfs/index.php
deleted file mode 100644
index 47f1c35..0000000
--- a/milfs/index.php
+++ /dev/null
@@ -1,308 +0,0 @@
-
-processRequests();
-
-$embebido =0;
-if (isset($_REQUEST['form'])) {
- $form = $_REQUEST['form'];
- $opciones["formato"]= $_REQUEST['formato'];
- } else {$form = "";}
- if($form !='') {$embebido = 1;}
-if (isset($_REQUEST['identificador'])) {$identificador = $_REQUEST['identificador'];} else {$identificador = "";}
- if($identificador !='') {$embebido = 1;}
-if (isset($_REQUEST['id'])) {$id = $_REQUEST['id'];} else {$id = "";}
-if (isset($_REQUEST['campo'])) {$campo = $_REQUEST['campo'];} else {$campo = "";}
-if (isset($_REQUEST['consulta'])) {$consulta = $_REQUEST['consulta'];} else {$consulta = "";}
-if (isset($_REQUEST['t'])) {$t = $_REQUEST['t'];} else {$t = "";}
-?>
-
-
-
-
-
-
-
-
-
- printJavascript("xajax/");
- // $xajax->debugOn();
- //$xajax->statusMessagesOn();
- ?>
-
-
-
- ";}else{ echo "";} ?>
-
-
-
-
-
-
-
-
-
- I<3MILFS
-
- xajax_formulario_listado('','contenido','$id')";}
- elseif($campo !=''){$onload ="";}
- elseif($consulta !=''){$onload ="";}
- else{}
-
- if( isset($_REQUEST['psi'])){$onload ="";}
-?>
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
- Los datos que se encuentran en esta página estan asociados al resultado de
- la investigación que se encuentra en http://www.dondeestanmisdatos.info/
- lo que se encuentra en este sitio es un visualización de datos creada a
- partir de los resultados de la investigación después de ser ingresados a la
- plataforma MILFS
-
-
- Esta plataforma nos entrega los datos en forma de una API que puede ser
- consumida en le siguiente enlace:
-
- http://datos.labmde.org/api.php?id=19
-
- Los datos son entregados en formato JSON
- tener este formato permite a las personas recibir
- actualización de los datos de manera automatica y utilizarlo en sus
- aplicaciones como fuente de datos, entre otras.
-
- Especificación de los datos:
-
- El JSON, entrega un ID por cada uno de los campos y también los
- nombres si es necesario, tal como se ve en la siguiente tabla:
-
-
-
-
-
-
-
ID
-
Nombre del Campo
-
-
-
115
-
Isp
-
-
-
125
-
Ong (eff)
-
-
-
124
-
Pais
-
-
-
110
-
1. el psi publica informes de transparencia
-
-
-
116
-
1.1 el informe de transparencia muestra las
- solicitudes que ha hecho el gobierno, a través de diferentes
- entidades del estado, solicitando información de los usuarios.
-
-
-
117
-
1.2 el informe de transparencia indica la frecuencia
- con la cuál la empresa entrega información de los usuarios al
- gobierno
-
-
-
118
-
1.3 el informe de transparencia señala si se ha dado
- respuesta a las solicitudes hechas por el gobierno y muestra el
- procedimiento que han tenido las mismas.
-
-
-
119
-
1.4 el informe de tranparencia evidencia el número
- de usuarios que han sido notificados en el último año en relación
- con el número de solicitudes por parte del gobierno.
-
-
-
120
-
1.5 el informe de transparencia informa el origen de
- las solicitudes para bloqueo y/o retiro de contenidos de internet
- (incluyendo pornografía infantil, infracción al derecho de autor,
- cumplimiento de sus propias políticas, etc.)
-
-
-
121
-
1.6 el informe de transparencia explica con claridad
- el manejo de los datos de los usuarios; si estos han sido
- administrados por terceros y da cuenta de las acciones llevadas a
- cabo por éstos en relación con la protección de datos de los
- usuarios. en caso de gestión por terceros informa si ellos han dado
- información al gobierno por solicitud del mismo.
-
-
-
122
-
1.7 el informe de transparencia indica cuántas veces
- ha procedido la psi a bloquear y/o retirar contenidos de internet.
-
-
-
123
-
1.8 el informe de transparencia informa sobre si ha
- habido defensa de los usuarios cuyo contenido ha sido bloqueado y/o
- retirado y los motivos para ello.
-
-
-
130
-
Comentarios bloque 1
-
-
-
111
-
2.1 ¿el psi notifica al usuario cuando el gobierno
- nacional ha hecho solicitud de información de sus datos?
-
-
-
126
-
2.2 ¿el psi notifica al usuario o usuaria de manera
- oportuna cuando el gobierno nacional ha hecho una solicitud de
- información de sus datos, es decir, dando tiempo a que el usuario
- pueda interponer recursos de ser necesario?
-
-
-
131
-
Comentarios bloque 2
-
-
-
112
-
3. las polÍticas de protección de datos del psi son
- públicas y de fácil acceso para los usuarios y usuarias
-
-
-
132
-
Comentarios bloque 3
-
-
-
113
-
4. el psi publica manuales de cumplimiento de
- obligaciones legales que pueden afectar la intimidad de los usuarios
- y usuarias
-
-
-
133
-
Comentarios bloque 4
-
-
-
127
-
5.1 ¿el psi pública los procedimientos que emplea
- para filtrar/retirar/bloquear contenidos y/o suspender/cancelar
- servicios, indicando además los soportes legales/contractuales que
- lo justifican?
-
-
-
128
-
5.2 ¿el psi específica las motivaciones que la
- llevan a hacer filtros/retiros/bloqueos de contenidos y/o
- suspensión/cancelación de servicios?
-
-
-
129
-
5.3 ¿el psi específica cómo los procedimientos para
- filtrar/retirar/bloquear contenidos y/o suspender/cancelar servicios
- tienen en cuenta el debido proceso? (como mínimo suponen:
- notificación al usuario, oportunidad de defensa, criterios de
- proporcionalidad, etcétera)
-
-
-
134
-
Comentarios bloque 5
-
-
-
-
-
- Las preguntas están organizadas por grupos, y existe un campo de
- "Comentarios" por cada bloque de preguntas y en los datos se puede
- identificar a que pregunta esa asociado cada uno de los comentarios.
-
- También puede descargar los datos en formato CSV (AQUÍ)
- Este archivo tiene como delimitador de campos el
- carácter "pipe" ( | ) y como delimitador de texto las comillas
- dobles ( " " ).
-
-
-
-