Hi,
Excuse me for the late reply.
I reviewed the patch and adjusted the style to the coding standards.
Attached is the revised version diff'ed against HEAD. Please verify it.
And please be sure to check out CODING_STANDARDS included in the source
package before submitting the patch from now on.
BTW, your code doesn't seem to handle the string that might result in a
string longer than 256 bytes. IMO erealloc() is lacking somewhere. As for
the other part, I see no obvious problems.
Moriyoshi
"Adrian Gartland" <[EMAIL PROTECTED]> wrote:
> New patch applied against the current "php4-latest.tar.gz",
> same location:
> http://support.oregan.net/php/php_htmlspecialchars_iso_2022-jp.patch
>
> On 11 Nov 02, "Moriyoshi Koizumi" <[EMAIL PROTECTED]> wrote:
> > Could you make a patch diff'ed against the latest version of html.c in HEAD
> > branch? determine_charset() issue which you pointed out seems to have been
> > fixed already.
> >
> > Moriyoshi
> >
> > "Adrian Gartland" <[EMAIL PROTECTED]> wrote:
> >
> > > http://support.oregan.net/php/php_htmlspecialchars_iso_2022-jp.patch
> > >
> > > On 11 Nov 02, "Jan Schneider" <[EMAIL PROTECTED]> wrote:
> > > > Zitat von Adrian Gartland <[EMAIL PROTECTED]>:
> > > >
> > > > > Attached is a patch which allows iso-2022-jp (jis) encoded text to be
> > > > > passed through htmlspecialchars when the character set is
> > > > > set to ISO-2022-JP.
> > > > >
> > > > > It should also fix a tiny bug I found in "determine_charset"
> > > > > code where "len" hadn't been set and then doing its
> > > > > charset map walk.
> > > >
> > > > Your attachment didn't go through the mailing list filters. Please post a
> > > > link where the patch can be downloaded.
> > > >
> > > > Jan.
> > > >
> > > > --
> > > > http://www.horde.org - The Horde Project
> > > > http://www.ammma.de - discover your knowledge
> > > > http://www.tip4all.de - Deine private Tippgemeinschaft
> > > >
> > > > --
> > > > PHP Development Mailing List <http://www.php.net/>
> > > > To unsubscribe, visit: http://www.php.net/unsub.php
> > > >
> > > >
> > > >
> > >
> >
> >
> > --
> > PHP Development Mailing List <http://www.php.net/>
> > To unsubscribe, visit: http://www.php.net/unsub.php
> >
> >
> >
>
> --
> Adrian Gartland - Senior Systems Engineer - TV Portal Team
> Oregan Networks UK Ltd Tel: +44 (0) 20 8846 0990
> The White Building, 52-54 Glentham Road Fax: +44 (0) 20 8646 0999
> Barnes, London. SW13 9JJ, United Kingdom WWW: http://www.oregan.net/
--- html.c Mon Nov 18 04:11:27 2002
+++ html.c.next Tue Nov 19 05:51:43 2002
@@ -18,7 +18,7 @@
+----------------------------------------------------------------------+
*/
-/* $Id: html.c,v 1.65 2002/11/16 08:30:31 sebastian Exp $ */
+/* $Id: html.c,v 1.63 2002/11/11 13:31:08 moriyoshi Exp $ */
#include "php.h"
#if PHP_WIN32
@@ -43,7 +43,7 @@
#endif
enum entity_charset { cs_terminator, cs_8859_1, cs_cp1252,
- cs_8859_15, cs_utf_8, cs_big5, cs_gb2312,
+ cs_8859_15, cs_2022_jp, cs_utf_8, cs_big5,
+cs_gb2312,
cs_big5hkscs, cs_sjis, cs_eucjp};
typedef const char *entity_table_t;
@@ -288,6 +288,7 @@
} charset_map[] = {
{ "ISO-8859-1", cs_8859_1 },
{ "ISO8859-1", cs_8859_1 },
+ { "ISO-2022-JP", cs_2022_jp },
{ "ISO-8859-15", cs_8859_15 },
{ "ISO8859-15", cs_8859_15 },
{ "utf-8", cs_utf_8 },
@@ -728,8 +729,138 @@
}
/* }}} */
+/* {{{ next_iso2022_segment
+ * updates whatever psIn is pointing to the end of the multi-byte run
+ * esc$bxxxxxesc(byyyyy ; psIn = yyyy
+ */
+static const char *next_iso2022_segment(const unsigned char **psIn, int iInLen, const
+char *pcEscapeSafeEnd)
+{
+ const char *sIn = *psIn;
+ const char *pcNextEsc;
+ static const char cEsc = 033;
+ int iSegmentLength;
+ int iRemaining = iInLen;
+
+ pcNextEsc = sIn;
+ if (sIn > pcEscapeSafeEnd) {
+ /* Buffer overrun if we try and spot the escape chars */
+ *psIn = sIn + iInLen;
+ return sIn;
+ } else {
+ while(1) {
+ pcNextEsc++; /* step past the current escape */
+
+ /* search for the closing escape sequence */
+ while (cEsc != *pcNextEsc && iRemaining) {
+ iRemaining--;
+ pcNextEsc++;
+ }
+
+ if (cEsc != *pcNextEsc) {
+ pcNextEsc = NULL;
+ }
+
+
+ if (NULL == pcNextEsc || pcNextEsc > pcEscapeSafeEnd) {
+ *psIn = sIn + iInLen;
+ return sIn;
+ } else {
+ if ('(' == pcNextEsc[1]) {
+ /*End of multi-byte run. */
+
+ iSegmentLength = (pcNextEsc - sIn) + 3;
+ *psIn = sIn + iSegmentLength;
+ return sIn;
+ }
+ }
+ }
+ }
+}
+/* }}} */
+
+/* {{{ next_iso2022_segment
+ * updates whatever psIn is pointing to the end of the multi-byte run
+ * esc$bxxxxxesc(byyyyy ; psIn = yyyy
+ */
+static const char *next_ascii_segment(const unsigned char **psIn, int iInLen)
+{
+ const char *sIn = *psIn;
+ const char *pcNextEsc;
+ static const char cEsc = 033;
+ int iRemaining = iInLen;
+
+ pcNextEsc = sIn;
+
+ while (1) {
+ while (cEsc != *pcNextEsc && iRemaining) {
+ iRemaining--;
+ pcNextEsc++;
+ }
+
+ if (cEsc != *pcNextEsc) {
+ *psIn = sIn + iInLen;
+ return sIn;
+ } else {
+ *psIn = pcNextEsc;
+ return sIn;
+ }
+ }
+}
+/* }}} */
+/* {{{ escape_html_entities_ISO2022
+ * single byte
+ * esc(B -> ASCII
+ * esc(J -> JIS Roman
+ *
+ * double byte
+ * esc$@ -> JIS C 6226-1978
+ * esc$B -> JIS X 0208-1983
+ */
+static char *escape_html_entities_ISO2022(const unsigned char *old, int oldlen, int
+*newlen, int all, int quote_style, const char *hint_charset TSRMLS_DC)
+{
+ char *new;
+ const char *pcStringEnd;
+ const char *pcEscapeSafeEnd;
+ int maxlen, len;
+ static const char cEsc = 033;
+ maxlen = 2 * oldlen;
+ if (maxlen < 128) {
+ maxlen = 128;
+ }
+
+ new = emalloc(maxlen);
+ len=0;
+
+ pcStringEnd = old + oldlen;
+ pcEscapeSafeEnd = pcStringEnd - 3;
+
+ /* break up into encoded and non encoded segments */
+ while (oldlen) {
+ if (cEsc == *old) {
+ const unsigned char *sSegment = next_iso2022_segment(&old,
+oldlen, pcEscapeSafeEnd);
+ int iSegmentLength = old - sSegment;
+ memcpy(new+len, sSegment, iSegmentLength);
+ len += iSegmentLength;
+ oldlen -= iSegmentLength;
+ } else {
+ const unsigned char *sSegment = next_ascii_segment(&old,
+oldlen);
+ int iSegmentLength = old - sSegment;
+ int iNewLen;
+ char *sSpecialChared = php_escape_html_entities((char *)
+sSegment, iSegmentLength, &iNewLen, all, quote_style, NULL TSRMLS_CC);
+
+ memcpy(new+len, sSpecialChared, iNewLen);
+ len += iNewLen;
+ oldlen -= iSegmentLength;
+ efree(sSpecialChared);
+ }
+ }
+
+ *newlen = len;
+ return new;
+}
+/* }}} */
/* {{{ php_escape_html_entities
*/
@@ -739,6 +870,10 @@
char *replaced;
enum entity_charset charset = determine_charset(hint_charset TSRMLS_CC);
int matches_map;
+
+ if (cs_2022_jp == charset) {
+ return escape_html_entities_ISO2022(old, oldlen, newlen, all,
+quote_style, hint_charset TSRMLS_CC);
+ }
maxlen = 2 * oldlen;
if (maxlen < 128)
--
PHP Development Mailing List <http://www.php.net/>
To unsubscribe, visit: http://www.php.net/unsub.php
