Skip to content

Fix #70962: xml_parse_into_struct strips embedded whitespace with XML… #7493

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Closed
wants to merge 3 commits into from
Closed

Fix #70962: xml_parse_into_struct strips embedded whitespace with XML… #7493

Show file tree
Hide file tree
Changes from 1 commit
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
de9857f
Fix #70962: xml_parse_into_struct strips embedded whitespace with XML…
Sep 14, 2021
12c2f34
Fix according to PR comments.
Sep 15, 2021
75a2bcd
Ignore empty "cdata" elements.
Sep 15, 2021
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
33 changes: 33 additions & 0 deletions ext/xml/tests/bug70962.phpt
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,33 @@
--TEST--
Bug #70962: xml_parse_into_struct strips embedded whitespace with XML_OPTION_SKIP_WHITE
--SKIPIF--
<?php
if (!extension_loaded('xml')) die('skip xml extension not available');
?>
--FILE--
<?php
function parseAndOutput($xml)
{
$parser = xml_parser_create();
xml_parser_set_option($parser, XML_OPTION_SKIP_WHITE, 1);

xml_parse_into_struct($parser, $xml, $values);

return $values;
}

$xml = "<a><b>&lt;d&gt;\n &lt;e&gt;</b><c>\n \t</c></a>";

$parsed = parseAndOutput($xml);

// Check embedded whitespace is not getting skipped.
echo $parsed[1]['value'] . "\n";

// Check XML_OPTION_SKIP_WHITE ignores values of tags containing whitespace characters only.
var_dump(isset($parsed[2]['value']));

?>
--EXPECT--
<d>
<e>
bool(false)
Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Nit: missing line break

141 changes: 72 additions & 69 deletions ext/xml/xml.c
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -881,78 +881,81 @@ void _xml_characterDataHandler(void *userData, const XML_Char *s, int len)
}

if (!Z_ISUNDEF(parser->data)) {
size_t i;
int doprint = 0;
zend_string *decoded_value;

decoded_value = xml_utf8_decode(s, len, parser->target_encoding);
for (i = 0; i < ZSTR_LEN(decoded_value); i++) {
switch (ZSTR_VAL(decoded_value)[i]) {
case ' ':
case '\t':
case '\n':
continue;
default:
doprint = 1;
break;
}
if (doprint) {
break;
}
}
if (doprint || (! parser->skipwhite)) {
if (parser->lastwasopen) {
zval *myval;

/* check if the current tag already has a value - if yes append to that! */
if ((myval = zend_hash_str_find(Z_ARRVAL_P(parser->ctag), "value", sizeof("value") - 1))) {
int newlen = Z_STRLEN_P(myval) + ZSTR_LEN(decoded_value);
Z_STR_P(myval) = zend_string_extend(Z_STR_P(myval), newlen, 0);
strncpy(Z_STRVAL_P(myval) + Z_STRLEN_P(myval) - ZSTR_LEN(decoded_value),
ZSTR_VAL(decoded_value), ZSTR_LEN(decoded_value) + 1);
zend_string_release_ex(decoded_value, 0);
} else {
add_assoc_str(parser->ctag, "value", decoded_value);
}

} else {
zval tag;
zval *curtag, *mytype, *myval;

ZEND_HASH_REVERSE_FOREACH_VAL(Z_ARRVAL(parser->data), curtag) {
if ((mytype = zend_hash_str_find(Z_ARRVAL_P(curtag),"type", sizeof("type") - 1))) {
if (!strcmp(Z_STRVAL_P(mytype), "cdata")) {
if ((myval = zend_hash_str_find(Z_ARRVAL_P(curtag), "value", sizeof("value") - 1))) {
int newlen = Z_STRLEN_P(myval) + ZSTR_LEN(decoded_value);
Z_STR_P(myval) = zend_string_extend(Z_STR_P(myval), newlen, 0);
strncpy(Z_STRVAL_P(myval) + Z_STRLEN_P(myval) - ZSTR_LEN(decoded_value),
ZSTR_VAL(decoded_value), ZSTR_LEN(decoded_value) + 1);
zend_string_release_ex(decoded_value, 0);
return;
}
}
}
break;
} ZEND_HASH_FOREACH_END();

if (parser->level <= XML_MAXLEVEL && parser->level > 0) {
array_init(&tag);

_xml_add_to_info(parser,SKIP_TAGSTART(parser->ltags[parser->level-1]));

add_assoc_string(&tag, "tag", SKIP_TAGSTART(parser->ltags[parser->level-1]));
add_assoc_str(&tag, "value", decoded_value);
add_assoc_string(&tag, "type", "cdata");
add_assoc_long(&tag, "level", parser->level);

zend_hash_next_index_insert(Z_ARRVAL(parser->data), &tag);
} else if (parser->level == (XML_MAXLEVEL + 1)) {
php_error_docref(NULL, E_WARNING, "Maximum depth exceeded - Results truncated");
}
}
} else {
zend_string_release_ex(decoded_value, 0);
}
if (parser->lastwasopen) {
Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Please use tabs (as four spaces) for indentation.

zval *myval;

/* check if the current tag already has a value - if yes append to that! */
if ((myval = zend_hash_str_find(Z_ARRVAL_P(parser->ctag), "value", sizeof("value") - 1))) {
int newlen = Z_STRLEN_P(myval) + ZSTR_LEN(decoded_value);
Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Suggested change
int newlen = Z_STRLEN_P(myval) + ZSTR_LEN(decoded_value);
size_t newlen = Z_STRLEN_P(myval) + ZSTR_LEN(decoded_value);

That was int before this patch, but I think we should fix that right away.

Z_STR_P(myval) = zend_string_extend(Z_STR_P(myval), newlen, 0);
strncpy(Z_STRVAL_P(myval) + Z_STRLEN_P(myval) - ZSTR_LEN(decoded_value),
ZSTR_VAL(decoded_value), ZSTR_LEN(decoded_value) + 1);
zend_string_release_ex(decoded_value, 0);
} else {
size_t i;
int doprint = 0;
if (parser->skipwhite) {
for (i = 0; i < ZSTR_LEN(decoded_value); i++) {
switch (ZSTR_VAL(decoded_value)[i]) {
case ' ':
case '\t':
case '\n':
continue;
default:
doprint = 1;
break;
}
if (doprint) {
break;
}
}
}

if (doprint || !parser->skipwhite) {
add_assoc_str(parser->ctag, "value", decoded_value);
} else {
zend_string_release_ex(decoded_value, 0);
}
}

} else {
zval tag;
zval *curtag, *mytype, *myval;

ZEND_HASH_REVERSE_FOREACH_VAL(Z_ARRVAL(parser->data), curtag) {
if ((mytype = zend_hash_str_find(Z_ARRVAL_P(curtag),"type", sizeof("type") - 1))) {
if (!strcmp(Z_STRVAL_P(mytype), "cdata")) {
if ((myval = zend_hash_str_find(Z_ARRVAL_P(curtag), "value", sizeof("value") - 1))) {
int newlen = Z_STRLEN_P(myval) + ZSTR_LEN(decoded_value);
Z_STR_P(myval) = zend_string_extend(Z_STR_P(myval), newlen, 0);
strncpy(Z_STRVAL_P(myval) + Z_STRLEN_P(myval) - ZSTR_LEN(decoded_value),
ZSTR_VAL(decoded_value), ZSTR_LEN(decoded_value) + 1);
zend_string_release_ex(decoded_value, 0);
return;
}
}
}
break;
} ZEND_HASH_FOREACH_END();

if (parser->level <= XML_MAXLEVEL && parser->level > 0) {
array_init(&tag);

_xml_add_to_info(parser,SKIP_TAGSTART(parser->ltags[parser->level-1]));

add_assoc_string(&tag, "tag", SKIP_TAGSTART(parser->ltags[parser->level-1]));
add_assoc_str(&tag, "value", decoded_value);
add_assoc_string(&tag, "type", "cdata");
add_assoc_long(&tag, "level", parser->level);

zend_hash_next_index_insert(Z_ARRVAL(parser->data), &tag);
} else if (parser->level == (XML_MAXLEVEL + 1)) {
php_error_docref(NULL, E_WARNING, "Maximum depth exceeded - Results truncated");
}
}
}
}
}
Expand Down