OStatus discover fixes:

* Subscription::start was sometimes passing users instead of profiles to hooks, which broke OStatus subscription notifications; now normalizing to profiles for processing.
* H-card parsing would trigger a lot of PHP warnings and notices in hKit. Now suppressing warnings and notices for the duration of the call to keep them out of output when display_errors is on.
* H-card parsing would trigger a PHP fatal error if the source page was not well-formed XML and Tidy was not present on the system. Switched normalization to use the PHP DOM module which is always present, as we have no need for Tidy's extra features here.
* Trying to fetch avatars from Google profiles failed and triggered a PHP warning due to the relative URL not being resolved during h-card parsing. Now passing profile page URL into hKit by sneaking a <base> tag in while we normalize the HTML source.
* Profile pages without a "Link" header could trigger PHP notices due to a bad NULL -> array(NULL) conversion in LinkHeader::getLink(). Now checking that there was a return value before converting single return value into array.

2 files changed, 71 insertions, 44 deletions

diff --git a/plugins/OStatus/lib/discoveryhints.php b/plugins/OStatus/lib/discoveryhints.php
index db13793dd..4da2ec0f1 100644
--- a/plugins/OStatus/lib/discoveryhints.php
+++ b/plugins/OStatus/lib/discoveryhints.php
@@ -65,17 +65,22 @@ class DiscoveryHints {
     {
         common_debug("starting tidy");
 
-        $body = self::_tidy($body);
+        $body = self::_tidy($body, $url);
 
         common_debug("done with tidy");
 
         set_include_path(get_include_path() . PATH_SEPARATOR . INSTALLDIR . '/plugins/OStatus/extlib/hkit/');
         require_once('hkit.class.php');
 
-        $h	= new hKit;
+        // hKit code is not clean for notices and warnings
+        $old = error_reporting();
+        error_reporting($old & ~E_NOTICE & ~E_WARNING);
 
+        $h	= new hKit;
         $hcards = $h->getByString('hcard', $body);
 
+        error_reporting($old);
+
         if (empty($hcards)) {
             return array();
         }
@@ -144,39 +149,61 @@ class DiscoveryHints {
         return $hints;
     }
 
-    private static function _tidy($body)
+    /**
+     * hKit needs well-formed XML for its parsing.
+     * We'll take the HTML body here and normalize it to XML.
+     *
+     * @param string $body HTML document source, possibly not-well-formed
+     * @param string $url source URL
+     * @return string well-formed XML document source
+     * @throws Exception if HTML parsing failed.
+     */
+    private static function _tidy($body, $url)
     {
-        if (function_exists('tidy_parse_string')) {
-            common_debug("Tidying with extension");
-            $text = tidy_parse_string($body);
-            $text = tidy_clean_repair($text);
-            return $body;
-        } else if ($fullpath = self::_findProgram('tidy')) {
-            common_debug("Tidying with program $fullpath");
-            $tempfile = tempnam('/tmp', 'snht'); // statusnet hcard tidy
-            file_put_contents($tempfile, $source);
-            exec("$fullpath -utf8 -indent -asxhtml -numeric -bare -quiet $tempfile", $tidy);
-            unlink($tempfile);
-            return implode("\n", $tidy);
-        } else {
-            common_debug("Not tidying.");
-            return $body;
+        if (empty($body)) {
+            throw new Exception("Empty HTML could not be parsed.");
         }
-    }
-
-    private static function _findProgram($name)
-    {
-        $path = $_ENV['PATH'];
-
-        $parts = explode(':', $path);
-
-        foreach ($parts as $part) {
-            $fullpath = $part . '/' . $name;
-            if (is_executable($fullpath)) {
-                return $fullpath;
+        $dom = new DOMDocument();
+
+        // Some HTML errors will trigger warnings, but still work.
+        $old = error_reporting();
+        error_reporting($old & ~E_WARNING);
+        
+        $ok = $dom->loadHTML($body);
+
+        error_reporting($old);
+        
+        if ($ok) {
+            // hKit doesn't give us a chance to pass the source URL for
+            // resolving relative links, such as the avatar photo on a
+            // Google profile. We'll slip it into a <base> tag if there's
+            // not already one present.
+            $bases = $dom->getElementsByTagName('base');
+            if ($bases && $bases->length >= 1) {
+                $base = $bases->item(0);
+                if ($base->hasAttribute('href')) {
+                    $base->setAttribute('href', $url);
+                }
+            } else {
+                $base = $dom->createElement('base');
+                $base->setAttribute('href', $url);
+                $heads = $dom->getElementsByTagName('head');
+                if ($heads || $heads->length) {
+                    $head = $heads->item(0);
+                } else {
+                    $head = $dom->createElement('head');
+                    $root = $dom->documentRoot;
+                    if ($root->firstChild) {
+                        $root->insertBefore($head, $root->firstChild);
+                    } else {
+                        $root->appendChild($head);
+                    }
+                }
+                $head->appendChild($base);
             }
+            return $dom->saveXML();
+        } else {
+            throw new Exception("Invalid HTML could not be parsed.");
         }
-
-        return null;
     }
 }
diff --git a/plugins/OStatus/lib/linkheader.php b/plugins/OStatus/lib/linkheader.php
index 2f6c66dc9..afcd66d26 100644
--- a/plugins/OStatus/lib/linkheader.php
+++ b/plugins/OStatus/lib/linkheader.php
@@ -43,21 +43,21 @@ class LinkHeader
     static function getLink($response, $rel=null, $type=null)
     {
         $headers = $response->getHeader('Link');
+        if ($headers) {
+            // Can get an array or string, so try to simplify the path
+            if (!is_array($headers)) {
+                $headers = array($headers);
+            }
 
-        // Can get an array or string, so try to simplify the path
-        if (!is_array($headers)) {
-            $headers = array($headers);
-        }
-
-        foreach ($headers as $header) {
-            $lh = new LinkHeader($header);
+            foreach ($headers as $header) {
+                $lh = new LinkHeader($header);
 
-            if ((is_null($rel) || $lh->rel == $rel) &&
-                (is_null($type) || $lh->type == $type)) {
-                return $lh->href;
+                if ((is_null($rel) || $lh->rel == $rel) &&
+                    (is_null($type) || $lh->type == $type)) {
+                    return $lh->href;
+                }
             }
         }
-
         return null;
     }
-}
\ No newline at end of file
+}