X-Git-Url: http://git.shiar.nl/minimedit.git/blobdiff_plain/022d44c8ddf33f855e6ed33cae6ad9ae103e074d..9c6d004933372ae88ff79a7625a3628aa447a5e6:/article.inc.php diff --git a/article.inc.php b/article.inc.php index 5de1492..a6a4ef8 100644 --- a/article.inc.php +++ b/article.inc.php @@ -16,10 +16,17 @@ function showdate($parts) class ArchiveArticle { + public $raw, $preface, $title, $body; + function __construct($path) { $this->page = $path; $this->link = preg_replace('{(?:/index)?\.html$}', '', $path); + if (file_exists($this->page)) { + $this->raw = file_get_contents($this->page); + @list ($this->preface, $this->title, $this->body) = + preg_split('{

(.*?)

\s*}', $this->raw, 2, PREG_SPLIT_DELIM_CAPTURE); + } } function __get($col) @@ -27,22 +34,10 @@ class ArchiveArticle return $this->$col = $this->$col(); # run method and cache } - function file() - { - if (!file_exists($this->page)) return; - return fopen($this->page, 'r'); - } - - function title() - { - return preg_replace('{

(.*)

\s*}', '\1', fgets($this->file)); - } - function safetitle() { return trim(strip_tags($this->title)); } - function name() { return $this->safetitle ?: $this->link; @@ -52,7 +47,6 @@ class ArchiveArticle { return filemtime($this->page); } - function lastiso() { return date(DATE_ATOM, $this->last); @@ -64,12 +58,10 @@ class ArchiveArticle array_shift($ymd); return $ymd; } - function dateiso() { return implode('-', $this->dateparts()) . 'T12:00:00+02:00'; } - function date() { return showdate($this->dateparts); @@ -77,23 +69,40 @@ class ArchiveArticle function story() { - $this->title; - $rest = fread($this->file, filesize($this->page)); if ( preg_match('{ \n (?: < (?: p | figure [^>]* ) >\s* )+ (]*>) | \n - }x', $rest, $img, PREG_OFFSET_CAPTURE) ) { + }x', $this->body, $img, PREG_OFFSET_CAPTURE) ) { # strip part after matching divider (image) if (isset($img[1])) { $this->img = $img[1][0]; } - return substr($rest, 0, $img[0][1]); + return substr($this->body, 0, $img[0][1]); } - return $rest; + return $this->body; } - function teaser() { - if (preg_match('{

(.*?)

}s', $this->story, $bodyp)) { + if (preg_match('{ + ]* content="([^">]*)" + }x', $this->preface, $meta)) { + # prefer specific page description if found (assume before title) + #TODO: strip from body contents + return $meta[1]; + } + + 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)) { return $bodyp[1]; } } @@ -104,14 +113,12 @@ class ArchiveArticle $this->story; return $this->img; } - function image() { if ( preg_match('/\bsrc="([^"]*)"/', $this->img, $src) ) { return $src[1]; } } - function thumb($size = '300x') { if (!$this->image or $this->image[0] !== '/') return;