adds support for named captures to mb_ereg & mb_ereg_search

`mb_ereg`, `mb_ereg_search_regs` & `mb_ereg_search_getregs`
returned only numbered capturing groups.
Now they return both numbered and named capturing groups.
Fixes Bug #72704.

4 files changed, 185 insertions, 0 deletions

diff --git a/ext/mbstring/php_mbregex.c b/ext/mbstring/php_mbregex.c
index b95f315c88..957ee484ba 100644
--- a/ext/mbstring/php_mbregex.c
+++ b/ext/mbstring/php_mbregex.c
@@ -646,6 +646,50 @@ _php_mb_regex_init_options(const char *parg, size_t narg, OnigOptionType *option
 }
 /* }}} */
 
+
+/*
+ * Callbacks for named subpatterns
+ */
+
+/* {{{ struct mb_ereg_groups_iter_arg */
+typedef struct mb_regex_groups_iter_args {
+	zval		*groups;
+	char		*search_str;
+	int			search_len;
+	OnigRegion	*region;
+} mb_regex_groups_iter_args;
+/* }}} */
+
+/* {{{ mb_ereg_groups_iter */
+static int
+mb_regex_groups_iter(const OnigUChar* name, const OnigUChar* name_end, int ngroup_num, int* group_nums, regex_t* reg, void* parg)
+{
+	mb_regex_groups_iter_args *args = (mb_regex_groups_iter_args *) parg;
+	int i, gn, ref, beg, end;
+
+	for (i = 0; i < ngroup_num; i++) {
+		gn = group_nums[i];
+		ref = onig_name_to_backref_number(reg, name, name_end, args->region);
+		if (ref != gn) {
+			/*
+			 * In case of duplicate groups, keep only the last suceeding one
+			 * to be consistent with preg_match with the PCRE_DUPNAMES option.
+			 */
+			continue;
+		}
+		beg = args->region->beg[gn];
+		end = args->region->end[gn];
+		if (beg >= 0 && beg < end && end <= args->search_len) {
+			add_assoc_stringl_ex(args->groups, (char *)name, name_end - name, &args->search_str[beg], end - beg);
+		} else {
+			add_assoc_bool_ex(args->groups, (char *)name, name_end - name, 0);
+		}
+	}
+
+	return 0;
+}
+/* }}} */
+
 /*
  * php functions
  */
@@ -762,6 +806,11 @@ static void _php_mb_regex_ereg_exec(INTERNAL_FUNCTION_PARAMETERS, int icase)
 				add_index_bool(array, i, 0);
 			}
 		}
+
+		if (onig_number_of_names(re) > 0) {
+			mb_regex_groups_iter_args args = {array, string, string_len, regs};
+			onig_foreach_name(re, mb_regex_groups_iter, &args);
+		}
 	}
 
 	if (match_len == 0) {
@@ -1291,6 +1340,15 @@ _php_mb_regex_ereg_search_exec(INTERNAL_FUNCTION_PARAMETERS, int mode)
 					add_index_bool(return_value, i, 0);
 				}
 			}
+			if (onig_number_of_names(MBREX(search_re)) > 0) {
+				mb_regex_groups_iter_args args = {
+					return_value,
+					Z_STRVAL(MBREX(search_str)),
+					Z_STRLEN(MBREX(search_str)),
+					MBREX(search_regs)
+				};
+				onig_foreach_name(MBREX(search_re), mb_regex_groups_iter, &args);
+			}
 			break;
 		default:
 			RETVAL_TRUE;
@@ -1417,6 +1475,15 @@ PHP_FUNCTION(mb_ereg_search_getregs)
 				add_index_bool(return_value, i, 0);
 			}
 		}
+		if (onig_number_of_names(MBREX(search_re)) > 0) {
+			mb_regex_groups_iter_args args = {
+				return_value,
+				Z_STRVAL(MBREX(search_str)),
+				len,
+				MBREX(search_regs)
+			};
+			onig_foreach_name(MBREX(search_re), mb_regex_groups_iter, &args);
+		}
 	} else {
 		RETVAL_FALSE;
 	}
diff --git a/ext/mbstring/tests/mb_ereg_dupnames.phpt b/ext/mbstring/tests/mb_ereg_dupnames.phpt
new file mode 100644
index 0000000000..fcc428c360
--- /dev/null
+++ b/ext/mbstring/tests/mb_ereg_dupnames.phpt
@@ -0,0 +1,37 @@
+--TEST--
+Testing mb_ereg() duplicate named groups
+--SKIPIF--
+<?php
+if (!extension_loaded('mbstring')) die('skip mbstring not enabled');
+function_exists('mb_ereg') or die("skip mb_ereg() is not available in this build");
+?>
+--FILE--
+<?php
+    mb_regex_encoding("UTF-8");
+    $pattern = '\w+((?<punct>？)|(?<punct>！))';
+    mb_ereg($pattern, '中？', $m);
+    var_dump($m);
+    mb_ereg($pattern, '中！', $m);
+    var_dump($m);
+?>
+--EXPECT--
+array(4) {
+  [0]=>
+  string(6) "中？"
+  [1]=>
+  string(3) "？"
+  [2]=>
+  bool(false)
+  ["punct"]=>
+  string(3) "？"
+}
+array(4) {
+  [0]=>
+  string(6) "中！"
+  [1]=>
+  bool(false)
+  [2]=>
+  string(3) "！"
+  ["punct"]=>
+  string(3) "！"
+}
diff --git a/ext/mbstring/tests/mb_ereg_named_subpatterns.phpt b/ext/mbstring/tests/mb_ereg_named_subpatterns.phpt
new file mode 100644
index 0000000000..ed0f85baa3
--- /dev/null
+++ b/ext/mbstring/tests/mb_ereg_named_subpatterns.phpt
@@ -0,0 +1,50 @@
+--TEST--
+Testing mb_ereg() named subpatterns
+--SKIPIF--
+<?php
+if (!extension_loaded('mbstring')) die('skip mbstring not enabled');
+function_exists('mb_ereg') or die("skip mb_ereg() is not available in this build");
+?>
+--FILE--
+<?php
+    mb_regex_encoding("UTF-8");
+    mb_ereg('(?<wsp>\s*)(?<word>\w+)', '  中国', $m);
+    var_dump($m);
+    mb_ereg('(?<wsp>\s*)(?<word>\w+)', '国', $m);
+    var_dump($m);
+    mb_ereg('(\s*)(?<word>\w+)', '  中国', $m);
+    var_dump($m);
+?>
+--EXPECT--
+array(5) {
+  [0]=>
+  string(8) "  中国"
+  [1]=>
+  string(2) "  "
+  [2]=>
+  string(6) "中国"
+  ["wsp"]=>
+  string(2) "  "
+  ["word"]=>
+  string(6) "中国"
+}
+array(5) {
+  [0]=>
+  string(3) "国"
+  [1]=>
+  bool(false)
+  [2]=>
+  string(3) "国"
+  ["wsp"]=>
+  bool(false)
+  ["word"]=>
+  string(3) "国"
+}
+array(3) {
+  [0]=>
+  string(8) "  中国"
+  [1]=>
+  string(6) "中国"
+  ["word"]=>
+  string(6) "中国"
+}
diff --git a/ext/mbstring/tests/mb_ereg_search_named_subpatterns.phpt b/ext/mbstring/tests/mb_ereg_search_named_subpatterns.phpt
new file mode 100644
index 0000000000..f899e9beeb
--- /dev/null
+++ b/ext/mbstring/tests/mb_ereg_search_named_subpatterns.phpt
@@ -0,0 +1,31 @@
+--TEST--
+Testing mb_ereg_search() named capture groups
+--SKIPIF--
+<?php
+if (!extension_loaded('mbstring')) die('skip mbstring not enabled');
+function_exists('mb_ereg_search') or die("skip mb_ereg_search() is not available in this build");
+?>
+--FILE--
+<?php
+    mb_regex_encoding("UTF-8");
+    mb_ereg_search_init('  中国？');
+    mb_ereg_search('(?<wsp>\s*)(?<word>\w+)(?<punct>[？！])');
+    var_dump(mb_ereg_search_getregs());
+?>
+--EXPECT--
+array(7) {
+  [0]=>
+  string(11) "  中国？"
+  [1]=>
+  string(2) "  "
+  [2]=>
+  string(6) "中国"
+  [3]=>
+  string(3) "？"
+  ["punct"]=>
+  string(3) "？"
+  ["wsp"]=>
+  string(2) "  "
+  ["word"]=>
+  string(6) "中国"
+}