Enhance zend_dump_op_array to Properly Represent Non-Printable Characters (GH-15680)

This change enhances `zend_dump_op_array` to properly represent non-printable characters in strings. This is useful for debugging purposes, as it allows developers to see the actual content of strings that contain non-printable characters.

Author: WangYihang

Zend/Optimizer/zend_dump.c

@@ -67,10 +67,8 @@ void zend_dump_const(const zval *zv)
 			fprintf(stderr, " float(%g)", Z_DVAL_P(zv));
 			break;
 		case IS_STRING:;
-			zend_string *escaped_string = php_addcslashes(Z_STR_P(zv), "\"\\", 2);
-
+			zend_string *escaped_string = php_repr_str(Z_STR_P(zv)->val, Z_STR_P(zv)->len);
 			fprintf(stderr, " string(\"%s\")", ZSTR_VAL(escaped_string));
-
 			zend_string_release(escaped_string);
 			break;
 		case IS_ARRAY:

ext/opcache/tests/match/002.phpt

@@ -44,16 +44,14 @@ test:
      ; (lines=2, args=0, vars=0, tmps=0)
      ; (after optimizer)
      ; %s
-0000 ECHO string("No match
-")
+0000 ECHO string("No match\n")
 0001 RETURN null
 
 test2:
      ; (lines=2, args=0, vars=0, tmps=0)
      ; (after optimizer)
      ; %s
-0000 ECHO string("No match
-")
+0000 ECHO string("No match\n")
 0001 RETURN null
 No match
 No match

ext/opcache/tests/match/005.phpt

@@ -0,0 +1,36 @@
+--TEST--
+Match expression mixed jump table
+--INI--
+opcache.enable=1
+opcache.enable_cli=1
+opcache.opt_debug_level=0x20000
+zend_test.observer.enabled=0
+--EXTENSIONS--
+opcache
+--FILE--
+<?php
+return <<<EOT
+\x00\x01\x02\x03\x04\x05\x06\x07\x08\x09\x0a\x0b\x0c\x0d\x0e\x0f
+\x10\x11\x12\x13\x14\x15\x16\x17\x18\x19\x1a\x1b\x1c\x1d\x1e\x1f
+\x20\x21\x22\x23\x24\x25\x26\x27\x28\x29\x2a\x2b\x2c\x2d\x2e\x2f
+\x30\x31\x32\x33\x34\x35\x36\x37\x38\x39\x3a\x3b\x3c\x3d\x3e\x3f
+\x40\x41\x42\x43\x44\x45\x46\x47\x48\x49\x4a\x4b\x4c\x4d\x4e\x4f
+\x50\x51\x52\x53\x54\x55\x56\x57\x58\x59\x5a\x5b\x5c\x5d\x5e\x5f
+\x60\x61\x62\x63\x64\x65\x66\x67\x68\x69\x6a\x6b\x6c\x6d\x6e\x6f
+\x70\x71\x72\x73\x74\x75\x76\x77\x78\x79\x7a\x7b\x7c\x7d\x7e\x7f
+\x80\x81\x82\x83\x84\x85\x86\x87\x88\x89\x8a\x8b\x8c\x8d\x8e\x8f
+\x90\x91\x92\x93\x94\x95\x96\x97\x98\x99\x9a\x9b\x9c\x9d\x9e\x9f
+\xa0\xa1\xa2\xa3\xa4\xa5\xa6\xa7\xa8\xa9\xaa\xab\xac\xad\xae\xaf
+\xb0\xb1\xb2\xb3\xb4\xb5\xb6\xb7\xb8\xb9\xba\xbb\xbc\xbd\xbe\xbf
+\xc0\xc1\xc2\xc3\xc4\xc5\xc6\xc7\xc8\xc9\xca\xcb\xcc\xcd\xce\xcf
+\xd0\xd1\xd2\xd3\xd4\xd5\xd6\xd7\xd8\xd9\xda\xdb\xdc\xdd\xde\xdf
+\xe0\xe1\xe2\xe3\xe4\xe5\xe6\xe7\xe8\xe9\xea\xeb\xec\xed\xee\xef
+\xf0\xf1\xf2\xf3\xf4\xf5\xf6\xf7\xf8\xf9\xfa\xfb\xfc\xfd\xfe\xff
+EOT;
+?>
+--EXPECTF--
+$_main:
+     ; (lines=1, args=0, vars=0, tmps=0)
+     ; (after optimizer)
+     ; %s.php:1-21
+0000 RETURN string("\x00\x01\x02\x03\x04\x05\x06\x07\x08\t\n\x0b\x0c\r\x0e\x0f\n\x10\x11\x12\x13\x14\x15\x16\x17\x18\x19\x1a\x1b\x1c\x1d\x1e\x1f\n !\"#$%&'()*+,-./\n0123456789:;<=>?\n@ABCDEFGHIJKLMNO\nPQRSTUVWXYZ[\\]^_\n`abcdefghijklmno\npqrstuvwxyz{|}~\x7f\n\x80\x81\x82\x83\x84\x85\x86\x87\x88\x89\x8a\x8b\x8c\x8d\x8e\x8f\n\x90\x91\x92\x93\x94\x95\x96\x97\x98\x99\x9a\x9b\x9c\x9d\x9e\x9f\n\xa0\xa1\xa2\xa3\xa4\xa5\xa6\xa7\xa8\xa9\xaa\xab\xac\xad\xae\xaf\n\xb0\xb1\xb2\xb3\xb4\xb5\xb6\xb7\xb8\xb9\xba\xbb\xbc\xbd\xbe\xbf\n\xc0\xc1\xc2\xc3\xc4\xc5\xc6\xc7\xc8\xc9\xca\xcb\xcc\xcd\xce\xcf\n\xd0\xd1\xd2\xd3\xd4\xd5\xd6\xd7\xd8\xd9\xda\xdb\xdc\xdd\xde\xdf\n\xe0\xe1\xe2\xe3\xe4\xe5\xe6\xe7\xe8\xe9\xea\xeb\xec\xed\xee\xef\n\xf0\xf1\xf2\xf3\xf4\xf5\xf6\xf7\xf8\xf9\xfa\xfb\xfc\xfd\xfe\xff")

ext/opcache/tests/opt/dce_009.phpt

@@ -50,10 +50,8 @@ Loop::test:
      ; (lines=3, args=0, vars=0, tmps=0)
      ; (after optimizer)
      ; %sdce_009.php:4-10
-0000 ECHO string("Start
-")
-0001 ECHO string("Done
-")
+0000 ECHO string("Start\n")
+0001 ECHO string("Done\n")
 0002 RETURN null
 
 Loop::test2:

ext/opcache/tests/opt/sccp_032.phpt

@@ -36,8 +36,7 @@ $_main:
 0004 INIT_FCALL 1 %d string("var_export")
 0005 SEND_VAR CV0($x) 1
 0006 DO_ICALL
-0007 ECHO string("
-")
+0007 ECHO string("\n")
 0008 JMP 0003
 0009 FE_FREE V1
 0010 RETURN int(1)

ext/standard/php_string.h

@@ -42,6 +42,7 @@ PHPAPI char *php_strtr(char *str, size_t len, const char *str_from, const char *
 PHPAPI zend_string *php_addslashes(zend_string *str);
 PHPAPI void php_stripslashes(zend_string *str);
 PHPAPI zend_string *php_addcslashes_str(const char *str, size_t len, const char *what, size_t what_len);
+PHPAPI zend_string *php_repr_str(const char *str, size_t len);
 PHPAPI zend_string *php_addcslashes(zend_string *str, const char *what, size_t what_len);
 PHPAPI void php_stripcslashes(zend_string *str);
 PHPAPI zend_string *php_basename(const char *s, size_t len, const char *suffix, size_t sufflen);

ext/standard/string.c

@@ -32,6 +32,8 @@
 #include "scanf.h"
 #include "zend_API.h"
 #include "zend_execute.h"
+#include "zend_string.h"
+#include "php_globals.h"
 #include "basic_functions.h"
 #include "zend_smart_str.h"
 #include <Zend/zend_exceptions.h>
@@ -50,6 +52,19 @@
 #include "Zend/zend_bitset.h"
 #endif
 
+typedef struct {
+    char c;           
+    const char *repr; 
+} char_repr_t;
+
+static const char_repr_t char_reprs[] = {
+    {'\t', "\\t"},
+    {'\n', "\\n"},
+    {'\r', "\\r"},
+    {'"', "\\\""},
+    {'\\', "\\\\"},
+};
+
 /* this is read-only, so it's ok */
 ZEND_SET_ALIGNED(16, static const char hexconvtab[]) = "0123456789abcdef";
 
@@ -3863,6 +3878,55 @@ PHPAPI zend_string *php_addcslashes_str(const char *str, size_t len, const char
 }
 /* }}} */
 
+static const char *get_char_repr(char c) {
+    for (size_t i = 0; i < sizeof(char_reprs) / sizeof(char_reprs[0]); i++) {
+        if (char_reprs[i].c == c) {
+            return char_reprs[i].repr;
+        }
+    }
+    return NULL;
+}
+
+/* {{{ php_repr_str */
+PHPAPI zend_string *php_repr_str(const char *str, size_t len) {
+    size_t new_len = 0;
+    char *repr_str;
+    
+    for (size_t i = 0; i < len; i++) {
+        const char *repr = get_char_repr(str[i]);
+        if (repr) {
+            new_len += strlen(repr);
+        } else if (isprint((unsigned char)str[i])) {
+            new_len += 1;
+        } else {
+            new_len += 4;
+        }
+    }
+    
+    repr_str = emalloc(new_len + 1);
+    
+    size_t pos = 0;
+    for (size_t i = 0; i < len; i++) {
+        const char *repr = get_char_repr(str[i]);
+        if (repr) {
+            size_t len_repr = strlen(repr);
+            memcpy(repr_str + pos, repr, len_repr);
+            pos += len_repr;
+        } else if (isprint((unsigned char)str[i])) {
+            repr_str[pos++] = str[i];
+        } else {
+            pos += snprintf(repr_str + pos, 5, "\\x%02x", (unsigned char)str[i]);
+        }
+    }
+    
+    repr_str[pos] = '\0';
+    zend_string *zend_str = zend_string_init(repr_str, pos, 0);
+    efree(repr_str);
+    
+    return zend_str;
+}
+
+
 /* {{{ php_addcslashes */
 PHPAPI zend_string *php_addcslashes(zend_string *str, const char *what, size_t wlength)
 {