function __construct($path)
{
$this->page = preg_replace('{^\.(?:/|$)}', '', $path);
- $this->link = preg_replace('{(?:/index)?\.html$}', '', $this->page);
- if (file_exists($this->page)) {
- $this->raw = file_get_contents($this->page);
-
- if (preg_match_all('{
- \G <meta \s+ property="( [^"]+ )" \s+ content="( [^"]* )" > \s*
- }x', $this->raw, $meta)) {
- $matchlen = array_sum(array_map('strlen', $meta[0]));
- $this->raw = substr($this->raw, $matchlen); # delete matched contents
- $this->meta = array_combine($meta[1], $meta[2]); # [property => content]
- }
+ $this->link = preg_replace('{(?:(?:/|^)index)?\.html$}', '', $this->page);
+ $this->raw($this->page);
+ }
- @list ($this->preface, $this->title, $this->body) =
- preg_split('{<h2>(.*?)</h2>\s*}', $this->raw, 2, PREG_SPLIT_DELIM_CAPTURE);
+ function raw($page)
+ {
+ if (!file_exists($page)) {
+ return;
}
+ $this->raw = file_get_contents($page);
+
+ if (preg_match_all('{
+ \G <meta \s+ property="( [^"]+ )" \s+ content="( [^"]* )" > \s*
+ }x', $this->raw, $meta)) {
+ $matchlen = array_sum(array_map('strlen', $meta[0]));
+ $this->raw = substr($this->raw, $matchlen); # delete matched contents
+ $this->meta = array_combine($meta[1], $meta[2]); # [property => content]
+ }
+
+ @list ($this->preface, $this->title, $this->body) =
+ preg_split('{<h2>(.*?)</h2>\s*}s', $this->raw, 2, PREG_SPLIT_DELIM_CAPTURE);
}
function __get($col)
return $this->$col = $this->$col(); # run method and cache
}
+ function handler()
+ {
+ $path = $this->link;
+ $this->path = '';
+ $this->restricted = FALSE;
+ while (TRUE) {
+ if (file_exists("$path/.private")) {
+ $this->restricted = $path;
+ }
+
+ if (file_exists("$path/index.php")) {
+ return $path;
+ }
+
+ $up = strrpos($path, '/');
+ $this->path = substr($path, $up) . $this->path;
+ $path = substr($path, 0, $up);
+ if ($up === FALSE) {
+ break;
+ }
+ }
+ return;
+ }
+
function safetitle()
{
return trim($this->meta['og:title'] ?? strip_tags($this->title));
function story()
{
if ( preg_match('{
- \n (?: < (?: p | figure [^>]* ) >\s* )+ (<img\ [^>]*>) | \n <hr\ />
+ (?: < (?: p | figure [^>]* ) >\s* )+ (<img\ [^>]*>) | \n <hr\ />
}x', $this->body, $img, PREG_OFFSET_CAPTURE) ) {
# strip part after matching divider (image)
if (isset($img[1])) {
return $override;
}
+ # paragraph contents following the page header if any
+ $offset = strpos($this->raw, '</h2>');
+ $offset = $offset ? $offset + 5 : 0;
if (preg_match('{
- </h2> (?: \s+ | <p\sclass="nav\b.*?</p> | <div[^>]*> )* <p> \s* (.*?) </p>
- }sx', $this->raw, $bodyp, PREG_OFFSET_CAPTURE)) {
- # fallback paragraph contents following the page header
- if ($bodyp[1][1] < 256) {
- return $bodyp[1][0];
- }
- }
-
- # starting paragraph for documents without title (assumed simple/partial)
- if (strpos($this->raw, '<h2') === FALSE and preg_match('{
- \A <p> \s* (.*?) </p>
- }sx', $this->raw, $bodyp)) {
+ \G (?> \s+ | <aside\b.*?</aside> | <div [^>]*> | \[\[[^]]*\]\] )* <p> \s* (.*?) </p>
+ }sx', $this->raw, $bodyp, 0, $offset)) {
return $bodyp[1];
}
}
# ignore symlinks, original contents only
return FALSE;
}
+ if ($current->isDir()) {
+ # traverse subdirectories unless untracked in any amount
+ return !file_exists("$current/.gitignore");
+ }
# match **/*.html
- return $current->isDir()
- || preg_match('/\.html$/', $current->getFilename());
+ return preg_match('/(?<!\.inc)\.html$/', $current->getFilename());
}
);
}