X-Git-Url: http://git.shiar.nl/minimedit.git/blobdiff_plain/674f6d3f070bcd8a08b725619e80fac0c9f72f1e..772961fd4e9be46ad340cad1e55ee5f28cc5b968:/article.inc.php diff --git a/article.inc.php b/article.inc.php index a39b897..acd219d 100644 --- a/article.inc.php +++ b/article.inc.php @@ -16,26 +16,35 @@ function showdate($parts) class ArchiveArticle { - public $raw, $preface, $title, $body; - public $meta = []; + public $raw, $title, $body; # file contents + public $meta = []; # head metadata properties function __construct($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 \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); + } + + function raw($page) + { + if (!file_exists($page)) { + return; + } + $this->raw = file_get_contents($page); + + if (preg_match_all('{ + \G \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('{

(.*?)

\s*}', $this->raw, 2, PREG_SPLIT_DELIM_CAPTURE); + // find significant contents + $this->body = preg_replace('{}s', '', $this->raw); + if (preg_match('{

(.*?)

\s*(.*)}s', $this->body, $titlematch)) { + list (, $this->title, $this->body) = $titlematch; } } @@ -44,6 +53,36 @@ class ArchiveArticle 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 restricted() + { + $this->handler; + return $this->restricted; + } + function safetitle() { return trim($this->meta['og:title'] ?? strip_tags($this->title)); @@ -80,7 +119,7 @@ class ArchiveArticle function story() { if ( preg_match('{ - \n (?: < (?: p | figure [^>]* ) >\s* )+ (]*>) | \n + (?: < (?: p | figure [^>]* ) >\s* )+ (]*>) | \n }x', $this->body, $img, PREG_OFFSET_CAPTURE) ) { # strip part after matching divider (image) if (isset($img[1])) { @@ -98,19 +137,10 @@ class ArchiveArticle return $override; } + # paragraph contents following the page header if any if (preg_match('{ - (?: \s+ | | ]*> )*

\s* (.*?)

- }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, ' \s* (.*?)

- }sx', $this->raw, $bodyp)) { + \G (?> \s+ |
]*> | \[\[[^]]*\]\] )*

\s* (.*?)

+ }sx', $this->body, $bodyp, 0)) { return $bodyp[1]; } } @@ -157,9 +187,12 @@ class PageSearch # ignore symlinks, original contents only return FALSE; } + if ($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('/(?getFilename()); } ); }