From 1abfaba47f3c1c4352eb728afcd4b6871b7bb4a0 Mon Sep 17 00:00:00 2001
From: Andreas Gohr <andi@splitbrain.org>
Date: Tue, 21 Feb 2006 22:26:05 +0100
Subject: [PATCH] fixes for utf-8 to/from unicode conversion
The functions utf8_to unicode and unicode_to_utf8 didn't work correctly
with some 3 and 4 byte strings. This exchanges those functions against
two more sophisticated ones. It also adds unit testing for them.
darcs-hash:20060221212605-7ad00-7bfefe8c9615d5a7f3b33c279ce79d4200d4778c.gz
---
_test/cases/inc/utf8_unicode.test.php | 60 ++++++
_test/cases/inc/utf8_utf16be.test.php | 2 +-
inc/utf8.php | 297 ++++++++++++++++++++++----
3 files changed, 312 insertions(+), 47 deletions(-)
create mode 100644 _test/cases/inc/utf8_unicode.test.php
diff --git a/_test/cases/inc/utf8_unicode.test.php b/_test/cases/inc/utf8_unicode.test.php
new file mode 100644
index 000000000..453aad216
--- /dev/null
+++ b/_test/cases/inc/utf8_unicode.test.php
@@ -0,0 +1,60 @@
+<?php
+
+require_once DOKU_INC.'inc/utf8.php';
+
+// use no mbstring help here
+if(!defined('UTF8_NOMBSTRING')) define('UTF8_NOMBSTRING',1);
+
+class utf8_unicode_test extends UnitTestCase {
+
+ function test_from_1byte(){
+ $in = 'a';
+ $out = array(97);
+ $this->assertEqual(utf8_to_unicode($in),$out);
+ }
+
+ function test_from_2byte(){
+ $in = "\xc3\xbc";
+ $out = array(252);
+ $this->assertEqual(utf8_to_unicode($in),$out);
+ }
+
+ function test_from_3byte(){
+ $in = "\xe2\x99\x8a";
+ $out = array(9802);
+ $this->assertEqual(utf8_to_unicode($in),$out);
+ }
+
+ function test_from_4byte(){
+ $in = "\xf4\x80\x80\x81";
+ $out = array(1048577);
+ $this->assertEqual(utf8_to_unicode($in),$out);
+ }
+
+ function test_to_1byte(){
+ $out = 'a';
+ $in = array(97);
+ $this->assertEqual(unicode_to_utf8($in),$out);
+ }
+
+ function test_to_2byte(){
+ $out = "\xc3\xbc";
+ $in = array(252);
+ $this->assertEqual(unicode_to_utf8($in),$out);
+ }
+
+ function test_to_3byte(){
+ $out = "\xe2\x99\x8a";
+ $in = array(9802);
+ $this->assertEqual(unicode_to_utf8($in),$out);
+ }
+
+ function test_to_4byte(){
+ $out = "\xf4\x80\x80\x81";
+ $in = array(1048577);
+ $this->assertEqual(unicode_to_utf8($in),$out);
+ }
+
+}
+
+//Setup VIM: ex: et ts=4 enc=utf-8 :
diff --git a/_test/cases/inc/utf8_utf16be.test.php b/_test/cases/inc/utf8_utf16be.test.php
index 2d79ca35a..3a346da51 100644
--- a/_test/cases/inc/utf8_utf16be.test.php
+++ b/_test/cases/inc/utf8_utf16be.test.php
@@ -3,7 +3,7 @@
require_once DOKU_INC.'inc/utf8.php';
// use no mbstring help here
-define('UTF8_NOMBSTRING',1);
+if(!defined('UTF8_NOMBSTRING')) define('UTF8_NOMBSTRING',1);
class utf8_utf16be_test extends UnitTestCase {
// some chars from various code regions
diff --git a/inc/utf8.php b/inc/utf8.php
index 3a223d3fb..ecb2dc89b 100644
--- a/inc/utf8.php
+++ b/inc/utf8.php
@@ -382,61 +382,266 @@ function utf8_tohtml ($str) {
}
/**
- * This function returns any UTF-8 encoded text as a list of
- * Unicode values:
+ * Takes an UTF-8 string and returns an array of ints representing the
+ * Unicode characters. Astral planes are supported ie. the ints in the
+ * output can be > 0xFFFF. Occurrances of the BOM are ignored. Surrogates
+ * are not allowed.
*
- * @author Scott Michael Reynen <scott@randomchaos.com>
- * @link http://www.randomchaos.com/document.php?source=php_and_unicode
- * @see unicode_to_utf8()
+ * If $strict is set to true the function returns false if the input
+ * string isn't a valid UTF-8 octet sequence and raises a PHP error at
+ * level E_USER_WARNING
+ *
+ * Note: this function has been modified slightly in this library to
+ * trigger errors on encountering bad bytes
+ *
+ * @author <hsivonen@iki.fi>
+ * @author Harry Fuecks <hfuecks@gmail.com>
+ * @param string UTF-8 encoded string
+ * @param boolean Check for invalid sequences?
+ * @return mixed array of unicode code points or FALSE if UTF-8 invalid
+ * @see unicode_to_utf8
+ * @link http://hsivonen.iki.fi/php-utf8/
+ * @link http://sourceforge.net/projects/phputf8/
*/
-function utf8_to_unicode( &$str ) {
- $unicode = array();
- $values = array();
- $lookingFor = 1;
-
- for ($i = 0; $i < strlen( $str ); $i++ ) {
- $thisValue = ord( $str[ $i ] );
- if ( $thisValue < 128 ) $unicode[] = $thisValue;
- else {
- if ( count( $values ) == 0 ) $lookingFor = ( $thisValue < 224 ) ? 2 : 3;
- $values[] = $thisValue;
- if ( count( $values ) == $lookingFor ) {
- $number = ( $lookingFor == 3 ) ?
- ( ( $values[0] % 16 ) * 4096 ) + ( ( $values[1] % 64 ) * 64 ) + ( $values[2] % 64 ):
- ( ( $values[0] % 32 ) * 64 ) + ( $values[1] % 64 );
- $unicode[] = $number;
- $values = array();
- $lookingFor = 1;
- }
+function utf8_to_unicode($str,$strict=false) {
+ $mState = 0; // cached expected number of octets after the current octet
+ // until the beginning of the next UTF8 character sequence
+ $mUcs4 = 0; // cached Unicode character
+ $mBytes = 1; // cached expected number of octets in the current sequence
+
+ $out = array();
+
+ $len = strlen($str);
+
+ for($i = 0; $i < $len; $i++) {
+
+ $in = ord($str{$i});
+
+ if ( $mState == 0) {
+
+ // When mState is zero we expect either a US-ASCII character or a
+ // multi-octet sequence.
+ if (0 == (0x80 & ($in))) {
+ // US-ASCII, pass straight through.
+ $out[] = $in;
+ $mBytes = 1;
+
+ } else if (0xC0 == (0xE0 & ($in))) {
+ // First octet of 2 octet sequence
+ $mUcs4 = ($in);
+ $mUcs4 = ($mUcs4 & 0x1F) << 6;
+ $mState = 1;
+ $mBytes = 2;
+
+ } else if (0xE0 == (0xF0 & ($in))) {
+ // First octet of 3 octet sequence
+ $mUcs4 = ($in);
+ $mUcs4 = ($mUcs4 & 0x0F) << 12;
+ $mState = 2;
+ $mBytes = 3;
+
+ } else if (0xF0 == (0xF8 & ($in))) {
+ // First octet of 4 octet sequence
+ $mUcs4 = ($in);
+ $mUcs4 = ($mUcs4 & 0x07) << 18;
+ $mState = 3;
+ $mBytes = 4;
+
+ } else if (0xF8 == (0xFC & ($in))) {
+ /* First octet of 5 octet sequence.
+ *
+ * This is illegal because the encoded codepoint must be either
+ * (a) not the shortest form or
+ * (b) outside the Unicode range of 0-0x10FFFF.
+ * Rather than trying to resynchronize, we will carry on until the end
+ * of the sequence and let the later error handling code catch it.
+ */
+ $mUcs4 = ($in);
+ $mUcs4 = ($mUcs4 & 0x03) << 24;
+ $mState = 4;
+ $mBytes = 5;
+
+ } else if (0xFC == (0xFE & ($in))) {
+ // First octet of 6 octet sequence, see comments for 5 octet sequence.
+ $mUcs4 = ($in);
+ $mUcs4 = ($mUcs4 & 1) << 30;
+ $mState = 5;
+ $mBytes = 6;
+
+ } elseif($strict) {
+ /* Current octet is neither in the US-ASCII range nor a legal first
+ * octet of a multi-octet sequence.
+ */
+ trigger_error(
+ 'utf8_to_unicode: Illegal sequence identifier '.
+ 'in UTF-8 at byte '.$i,
+ E_USER_WARNING
+ );
+ return FALSE;
+
+ }
+
+ } else {
+
+ // When mState is non-zero, we expect a continuation of the multi-octet
+ // sequence
+ if (0x80 == (0xC0 & ($in))) {
+
+ // Legal continuation.
+ $shift = ($mState - 1) * 6;
+ $tmp = $in;
+ $tmp = ($tmp & 0x0000003F) << $shift;
+ $mUcs4 |= $tmp;
+
+ /**
+ * End of the multi-octet sequence. mUcs4 now contains the final
+ * Unicode codepoint to be output
+ */
+ if (0 == --$mState) {
+
+ /*
+ * Check for illegal sequences and codepoints.
+ */
+ // From Unicode 3.1, non-shortest form is illegal
+ if (((2 == $mBytes) && ($mUcs4 < 0x0080)) ||
+ ((3 == $mBytes) && ($mUcs4 < 0x0800)) ||
+ ((4 == $mBytes) && ($mUcs4 < 0x10000)) ||
+ (4 < $mBytes) ||
+ // From Unicode 3.2, surrogate characters are illegal
+ (($mUcs4 & 0xFFFFF800) == 0xD800) ||
+ // Codepoints outside the Unicode range are illegal
+ ($mUcs4 > 0x10FFFF)) {
+
+ if($strict){
+ trigger_error(
+ 'utf8_to_unicode: Illegal sequence or codepoint '.
+ 'in UTF-8 at byte '.$i,
+ E_USER_WARNING
+ );
+
+ return FALSE;
+ }
+
+ }
+
+ if (0xFEFF != $mUcs4) {
+ // BOM is legal but we don't want to output it
+ $out[] = $mUcs4;
+ }
+
+ //initialize UTF8 cache
+ $mState = 0;
+ $mUcs4 = 0;
+ $mBytes = 1;
+ }
+
+ } elseif($strict) {
+ /**
+ *((0xC0 & (*in) != 0x80) && (mState != 0))
+ * Incomplete multi-octet sequence.
+ */
+ trigger_error(
+ 'utf8_to_unicode: Incomplete multi-octet '.
+ ' sequence in UTF-8 at byte '.$i,
+ E_USER_WARNING
+ );
+
+ return FALSE;
+ }
+ }
}
- }
- return $unicode;
+ return $out;
}
/**
- * This function converts a Unicode array back to its UTF-8 representation
+ * Takes an array of ints representing the Unicode characters and returns
+ * a UTF-8 string. Astral planes are supported ie. the ints in the
+ * input can be > 0xFFFF. Occurrances of the BOM are ignored. Surrogates
+ * are not allowed.
*
- * @author Scott Michael Reynen <scott@randomchaos.com>
- * @link http://www.randomchaos.com/document.php?source=php_and_unicode
- * @see utf8_to_unicode()
+ * If $strict is set to true the function returns false if the input
+ * array contains ints that represent surrogates or are outside the
+ * Unicode range and raises a PHP error at level E_USER_WARNING
+ *
+ * Note: this function has been modified slightly in this library to use
+ * output buffering to concatenate the UTF-8 string (faster) as well as
+ * reference the array by it's keys
+ *
+ * @param array of unicode code points representing a string
+ * @param boolean Check for invalid sequences?
+ * @return mixed UTF-8 string or FALSE if array contains invalid code points
+ * @author <hsivonen@iki.fi>
+ * @author Harry Fuecks <hfuecks@gmail.com>
+ * @see utf8_to_unicode
+ * @link http://hsivonen.iki.fi/php-utf8/
+ * @link http://sourceforge.net/projects/phputf8/
*/
-function unicode_to_utf8( &$str ) {
- if (!is_array($str)) return '';
-
- $utf8 = '';
- foreach( $str as $unicode ) {
- if ( $unicode < 128 ) {
- $utf8.= chr( $unicode );
- } elseif ( $unicode < 2048 ) {
- $utf8.= chr( 192 + ( ( $unicode - ( $unicode % 64 ) ) / 64 ) );
- $utf8.= chr( 128 + ( $unicode % 64 ) );
- } else {
- $utf8.= chr( 224 + ( ( $unicode - ( $unicode % 4096 ) ) / 4096 ) );
- $utf8.= chr( 128 + ( ( ( $unicode % 4096 ) - ( $unicode % 64 ) ) / 64 ) );
- $utf8.= chr( 128 + ( $unicode % 64 ) );
+function unicode_to_utf8($arr,$strict=false) {
+ if (!is_array($arr)) return '';
+ ob_start();
+
+ foreach (array_keys($arr) as $k) {
+
+ # ASCII range (including control chars)
+ if ( ($arr[$k] >= 0) && ($arr[$k] <= 0x007f) ) {
+
+ echo chr($arr[$k]);
+
+ # 2 byte sequence
+ } else if ($arr[$k] <= 0x07ff) {
+
+ echo chr(0xc0 | ($arr[$k] >> 6));
+ echo chr(0x80 | ($arr[$k] & 0x003f));
+
+ # Byte order mark (skip)
+ } else if($arr[$k] == 0xFEFF) {
+
+ // nop -- zap the BOM
+
+ # Test for illegal surrogates
+ } else if ($arr[$k] >= 0xD800 && $arr[$k] <= 0xDFFF) {
+
+ // found a surrogate
+ if($strict){
+ trigger_error(
+ 'unicode_to_utf8: Illegal surrogate '.
+ 'at index: '.$k.', value: '.$arr[$k],
+ E_USER_WARNING
+ );
+ return FALSE;
+ }
+
+ # 3 byte sequence
+ } else if ($arr[$k] <= 0xffff) {
+
+ echo chr(0xe0 | ($arr[$k] >> 12));
+ echo chr(0x80 | (($arr[$k] >> 6) & 0x003f));
+ echo chr(0x80 | ($arr[$k] & 0x003f));
+
+ # 4 byte sequence
+ } else if ($arr[$k] <= 0x10ffff) {
+
+ echo chr(0xf0 | ($arr[$k] >> 18));
+ echo chr(0x80 | (($arr[$k] >> 12) & 0x3f));
+ echo chr(0x80 | (($arr[$k] >> 6) & 0x3f));
+ echo chr(0x80 | ($arr[$k] & 0x3f));
+
+ } elseif($strict) {
+
+ trigger_error(
+ 'unicode_to_utf8: Codepoint out of Unicode range '.
+ 'at index: '.$k.', value: '.$arr[$k],
+ E_USER_WARNING
+ );
+
+ // out of range
+ return FALSE;
+ }
}
- }
- return $utf8;
+
+ $result = ob_get_contents();
+ ob_end_clean();
+ return $result;
}
/**
--
GitLab