Twitter-compatible API - don't strip XML-illegal chars from JSON output

[quix0rs-gnu-social.git] / lib / util.php

diff --git a/lib/util.php b/lib/util.php
index c65adc76bc58b8f4ae97fa37ce5d9a0e3526b550..6ec557b2f915f9ba08e1ab8989caea9a5e0e47e8 100644 (file)
--- a/lib/util.php
+++ b/lib/util.php
@@ -146,7 +146,9 @@ function common_init_language() {
        bind_textdomain_codeset("laconica", "UTF-8");
        textdomain("laconica");
        setlocale(LC_CTYPE, 'C');
-       common_log(LOG_INFO,'Language requested:'.$language.' Locale set:'.$locale_set,__FILE__);
+       if(!$locale_set) {
+               common_log(LOG_INFO,'Language requested:'.$language.' - locale could not be set:',__FILE__);
+       }
 }
 
 define('PAGE_TYPE_PREFS', 'text/html,application/xhtml+xml,application/xml;q=0.3,text/xml;q=0.2');
@@ -711,12 +713,47 @@ function common_render_text($text) {
        $r = htmlspecialchars($text);
 
        $r = preg_replace('/[\x{0}-\x{8}\x{b}-\x{c}\x{e}-\x{19}]/', '', $r);
-       $r = preg_replace('@https?://[^)\]>\s]+@', '<a href="\0" class="extlink">\0</a>', $r);
+       $r = preg_replace_callback('@https?://[^\]>\s]+@', 'common_render_uri_thingy', $r);
        $r = preg_replace('/(^|\s+)#([A-Za-z0-9_\-\.]{1,64})/e', "'\\1#'.common_tag_link('\\2')", $r);
        # XXX: machine tags
        return $r;
 }
 
+function common_render_uri_thingy($matches) {
+       $uri = $matches[0];
+       $trailer = '';
+
+       # Some heuristics for extracting URIs from surrounding punctuation
+       # Strip from trailing text...
+       if (preg_match('/^(.*)([,.:"\']+)$/', $uri, $matches)) {
+               $uri = $matches[1];
+               $trailer = $matches[2];
+       }
+
+       $pairs = array(
+               ']' => '[', # technically disallowed in URIs, but used in Java docs
+               ')' => '(', # far too frequent in Wikipedia and MSDN
+       );
+       $final = substr($uri, -1, 1);
+       if (isset($pairs[$final])) {
+               $openers = substr_count($uri, $pairs[$final]);
+               $closers = substr_count($uri, $final);
+               if ($closers > $openers) {
+                       // Assume the paren was opened outside the URI
+                       $uri = substr($uri, 0, -1);
+                       $trailer = $final . $trailer;
+               }
+       }
+       return '<a href="' . $uri . '" class="extlink">' . $uri . '</a>' . $trailer;
+}
+
+function common_xml_safe_str($str) {
+       $xmlStr = htmlentities(iconv('UTF-8', 'UTF-8//IGNORE', $str), ENT_NOQUOTES, 'UTF-8');
+       
+       // Replace control, formatting, and surrogate characters with '*', ala Twitter
+       return preg_replace('/[\p{Cc}\p{Cf}\p{Cs}]/u', '*', $str);
+}
+
 function common_tag_link($tag) {
        $canonical = common_canonical_tag($tag);
        $url = common_local_url('tag', array('tag' => $canonical));