Fix bug #64011 (get_html_translation_table())

cataphract · cataphract · commit 77ee200097b5 · 2013-01-18T12:10:27.000+01:00
get_html_translation_table() with encoding ISO-8859-1 and HTMLENTITIES
was broken. Only entities for characters U+0000 to U+0040 were being
included in the result.
diff --git a/ext/standard/html.c b/ext/standard/html.c
@@ -1628,8 +1628,8 @@ PHP_FUNCTION(get_html_translation_table)
 			unsigned i, j, k,
 					 max_i, max_j, max_k;
 			/* no mapping to unicode required */
-			if (CHARSET_SINGLE_BYTE(charset)) {
-				max_i = 1; max_j = 1; max_k = 64;
+			if (CHARSET_SINGLE_BYTE(charset)) { /* ISO-8859-1 */
+				max_i = 1; max_j = 4; max_k = 64;
 			} else {
 				max_i = 0x1E; max_j = 64; max_k = 64;
 			}
diff --git a/ext/standard/tests/strings/get_html_translation_table_basic10.phpt b/ext/standard/tests/strings/get_html_translation_table_basic10.phpt
@@ -0,0 +1,121 @@
+--TEST--
+Test get_html_translation_table() function: htmlentities/HTML 4/ISO-8859-1 (bug #64011)
+--FILE--
+<?php
+
+function so($a,$b) { return ord($a) - ord($b); }
+
+$table = HTML_ENTITIES;
+$tt = get_html_translation_table($table, ENT_COMPAT, "ISO-8859-1");
+uksort( $tt, 'so' );
+var_dump( count($tt) );
+print_r( $tt );
+echo "Done\n";
+
+?>
+--EXPECT--
+int(100)
+Array
+(
+    ["] => &quot;
+    [&] => &amp;
+    [<] => &lt;
+    [>] => &gt;
+    [�] => &nbsp;
+    [�] => &iexcl;
+    [�] => &cent;
+    [�] => &pound;
+    [�] => &curren;
+    [�] => &yen;
+    [�] => &brvbar;
+    [�] => &sect;
+    [�] => &uml;
+    [�] => &copy;
+    [�] => &ordf;
+    [�] => &laquo;
+    [�] => &not;
+    [�] => &shy;
+    [�] => &reg;
+    [�] => &macr;
+    [�] => &deg;
+    [�] => &plusmn;
+    [�] => &sup2;
+    [�] => &sup3;
+    [�] => &acute;
+    [�] => &micro;
+    [�] => &para;
+    [�] => &middot;
+    [�] => &cedil;
+    [�] => &sup1;
+    [�] => &ordm;
+    [�] => &raquo;
+    [�] => &frac14;
+    [�] => &frac12;
+    [�] => &frac34;
+    [�] => &iquest;
+    [�] => &Agrave;
+    [�] => &Aacute;
+    [�] => &Acirc;
+    [�] => &Atilde;
+    [�] => &Auml;
+    [�] => &Aring;
+    [�] => &AElig;
+    [�] => &Ccedil;
+    [�] => &Egrave;
+    [�] => &Eacute;
+    [�] => &Ecirc;
+    [�] => &Euml;
+    [�] => &Igrave;
+    [�] => &Iacute;
+    [�] => &Icirc;
+    [�] => &Iuml;
+    [�] => &ETH;
+    [�] => &Ntilde;
+    [�] => &Ograve;
+    [�] => &Oacute;
+    [�] => &Ocirc;
+    [�] => &Otilde;
+    [�] => &Ouml;
+    [�] => &times;
+    [�] => &Oslash;
+    [�] => &Ugrave;
+    [�] => &Uacute;
+    [�] => &Ucirc;
+    [�] => &Uuml;
+    [�] => &Yacute;
+    [�] => &THORN;
+    [�] => &szlig;
+    [�] => &agrave;
+    [�] => &aacute;
+    [�] => &acirc;
+    [�] => &atilde;
+    [�] => &auml;
+    [�] => &aring;
+    [�] => &aelig;
+    [�] => &ccedil;
+    [�] => &egrave;
+    [�] => &eacute;
+    [�] => &ecirc;
+    [�] => &euml;
+    [�] => &igrave;
+    [�] => &iacute;
+    [�] => &icirc;
+    [�] => &iuml;
+    [�] => &eth;
+    [�] => &ntilde;
+    [�] => &ograve;
+    [�] => &oacute;
+    [�] => &ocirc;
+    [�] => &otilde;
+    [�] => &ouml;
+    [�] => &divide;
+    [�] => &oslash;
+    [�] => &ugrave;
+    [�] => &uacute;
+    [�] => &ucirc;
+    [�] => &uuml;
+    [�] => &yacute;
+    [�] => &thorn;
+    [�] => &yuml;
+)
+Done

-Original file line number
+Diff line change
@@ @@ -0,0 +1,121 @@ @@
 +--TEST--
 +Test get_html_translation_table() function: htmlentities/HTML 4/ISO-8859-1 (bug #64011)
 +--FILE--
 +<?php
++
 +function so($a,$b) { return ord($a) - ord($b); }
++
 +$table = HTML_ENTITIES;
 +$tt = get_html_translation_table($table, ENT_COMPAT, "ISO-8859-1");
 +uksort( $tt, 'so' );
 +var_dump( count($tt) );
 +print_r( $tt );
 +echo "Done\n";
++
 +?>
 +--EXPECT--
 +int(100)
 +Array
 +(
 +    ["] => &quot;
 +    [&] => &amp;
 +    [<] => &lt;
 +    [>] => &gt;
 +    [ ] => &nbsp;
 +    [¡] => &iexcl;
 +    [¢] => &cent;
 +    [£] => &pound;
 +    [¤] => &curren;
 +    [¥] => &yen;
 +    [¦] => &brvbar;
 +    [§] => &sect;
 +    [¨] => &uml;
 +    [©] => &copy;
 +    [ª] => &ordf;
 +    [«] => &laquo;
 +    [¬] => &not;
 +    [] => &shy;
 +    [®] => &reg;
 +    [¯] => &macr;
 +    [°] => &deg;
 +    [±] => &plusmn;
 +    [²] => &sup2;
 +    [³] => &sup3;
 +    [´] => &acute;
 +    [µ] => &micro;
 +    [¶] => &para;
 +    [·] => &middot;
 +    [¸] => &cedil;
 +    [¹] => &sup1;
 +    [º] => &ordm;
 +    [»] => &raquo;
 +    [¼] => &frac14;
 +    [½] => &frac12;
 +    [¾] => &frac34;
 +    [¿] => &iquest;
 +    [À] => &Agrave;
 +    [Á] => &Aacute;
 +    [Â] => &Acirc;
 +    [Ã] => &Atilde;
 +    [Ä] => &Auml;
 +    [Å] => &Aring;
 +    [Æ] => &AElig;
 +    [Ç] => &Ccedil;
 +    [È] => &Egrave;
 +    [É] => &Eacute;
 +    [Ê] => &Ecirc;
 +    [Ë] => &Euml;
 +    [Ì] => &Igrave;
 +    [Í] => &Iacute;
 +    [Î] => &Icirc;
 +    [Ï] => &Iuml;
 +    [Ð] => &ETH;
 +    [Ñ] => &Ntilde;
 +    [Ò] => &Ograve;
 +    [Ó] => &Oacute;
 +    [Ô] => &Ocirc;
 +    [Õ] => &Otilde;
 +    [Ö] => &Ouml;
 +    [×] => &times;
 +    [Ø] => &Oslash;
 +    [Ù] => &Ugrave;
 +    [Ú] => &Uacute;
 +    [Û] => &Ucirc;
 +    [Ü] => &Uuml;
 +    [Ý] => &Yacute;
 +    [Þ] => &THORN;
 +    [ß] => &szlig;
 +    [à] => &agrave;
 +    [á] => &aacute;
 +    [â] => &acirc;
 +    [ã] => &atilde;
 +    [ä] => &auml;
 +    [å] => &aring;
 +    [æ] => &aelig;
 +    [ç] => &ccedil;
 +    [è] => &egrave;
 +    [é] => &eacute;
 +    [ê] => &ecirc;
 +    [ë] => &euml;
 +    [ì] => &igrave;
 +    [í] => &iacute;
 +    [î] => &icirc;
 +    [ï] => &iuml;
 +    [ð] => &eth;
 +    [ñ] => &ntilde;
 +    [ò] => &ograve;
 +    [ó] => &oacute;
 +    [ô] => &ocirc;
 +    [õ] => &otilde;
 +    [ö] => &ouml;
 +    [÷] => &divide;
 +    [ø] => &oslash;
 +    [ù] => &ugrave;
 +    [ú] => &uacute;
 +    [û] => &ucirc;
 +    [ü] => &uuml;
 +    [ý] => &yacute;
 +    [þ] => &thorn;
 +    [ÿ] => &yuml;
 +)
 +Done