[php-src] master: ext/standard: Stop at the first non-name byte in html_entity_decode() (#24142)
| From: | Artem Ukrainskiy via GitHub | Date: | Mon, 26 Oct 2026 12:25:21 +0000 |
| Subject: | [php-src] master: ext/standard: Stop at the first non-name byte in html_entity_decode() (#24142) | ||
| Groups: | php.cvs | ||
| Request: | Send a blank email to php-cvs+get-142738@lists.php.net to get a copy of this message | ||
Author: Artem Ukrainskiy (ArtUkrainskiy)
Committer: GitHub (web-flow)
Pusher: iliaal
Date: 2026-10-26T08:25:18-04:00
Commit: https://github.com/php/php-src/commit/219289d8e79e870b4bf816901117e2ce481a433e
Raw diff: https://github.com/php/php-src/commit/219289d8e79e870b4bf816901117e2ce481a433e.diff
ext/standard: Stop at the first non-name byte in html_entity_decode() (#24142)
Entity names are letters and digits. Scan them and stop at the first other
byte instead of searching for a ';' up to 32 bytes ahead and hashing whatever
is in between. Also skip memchr() when the next byte is already '&'.
Output is unchanged. html_entity_decode() on 4 KB inputs:
only '&' 3.5x faster
only entities 1.1x faster
jQuery source 1.1-1.4x faster
jQuery minified 1.4-1.7x faster
HTML pages, Markdown same
"¶m=value" URLs in text up to 1.07x slower
Changed paths:
M ext/standard/html.c
Diff:
diff --git a/ext/standard/html.c b/ext/standard/html.c
index 4631b980a0b4..41ea6aef4921 100644
--- a/ext/standard/html.c
+++ b/ext/standard/html.c
@@ -845,6 +845,12 @@ static inline size_t write_octet_sequence(unsigned char *buf, enum
entity_charse
}
}
+/* [0-9A-Za-z], independent of the locale */
+static zend_always_inline bool is_entity_name_byte(unsigned char c)
+{
+ return (unsigned char)((c | 0x20) - 'a') < 26 || (unsigned char)(c - '0')
< 10;
+}
+
/* {{{ traverse_for_entities
* Auxiliary function to php_unescape_html_entities().
* - The argument "all" determines if all numeric entities are decode or only those
@@ -867,7 +873,8 @@ static void traverse_for_entities(
const int doctype = flags & ENT_HTML_DOC_TYPE_MASK;
while (current_ptr < input_end) {
- const char *ampersand_ptr = memchr(current_ptr, '&', input_end - current_ptr);
+ /* Runs of '&' would call memchr() for every byte */
+ const char *ampersand_ptr = *current_ptr == '&' ? current_ptr : memchr(current_ptr,
'&', input_end - current_ptr);
if (!ampersand_ptr) {
const size_t tail_len = input_end - current_ptr;
if (tail_len > 0) {
@@ -921,10 +928,13 @@ static void traverse_for_entities(
} else {
/* Processing named entity */
const char *name_start = current_ptr + 1;
- /* Search for ';' */
- const size_t max_search_len = MIN(LONGEST_ENTITY_LENGTH + 1, input_end - name_start);
- const char *semi_colon_ptr = memchr(name_start, ';', max_search_len);
- if (!semi_colon_ptr) {
+ const char *semi_colon_ptr = name_start;
+ const char *const name_limit = name_start + MIN(LONGEST_ENTITY_LENGTH, input_end - name_start -
1);
+ /* A name is letters and digits only, so the first other byte must be the ';' */
+ while (semi_colon_ptr < name_limit && is_entity_name_byte(*semi_colon_ptr)) {
+ semi_colon_ptr++;
+ }
+ if (*semi_colon_ptr != ';') {
goto invalid_incomplete_entity;
} else {
const size_t name_len = semi_colon_ptr - name_start;