regex: added default support for long queries (#12635)

Author: penguindark

vlib/regex/regex_opt.v

@@ -40,7 +40,7 @@ pub fn regex_opt(pattern string) ?RE {
 	re.prog = []Token{len: pattern.len + 1} // max program length, can not be longer then the pattern
 	re.cc = []CharClass{len: pattern.len} // can not be more char class the the length of the pattern
 	re.group_csave_flag = false // enable continuos group saving
-	re.group_max_nested = 128 // set max 128 group nested
+	re.group_max_nested = pattern.len >> 1 // set max 128 group nested
 	re.group_max = pattern.len >> 1 // we can't have more groups than the half of the pattern legth
 
 	re.group_stack = []int{len: re.group_max, init: -1}

vlib/regex/regex_test.v

@@ -1,5 +1,6 @@
 import regex
 import rand
+import strings
 
 /******************************************************************************
 *
@@ -720,3 +721,42 @@ fn test_errors(){
 	}
 	assert count == err_query_list.len
 }
+
+
+fn test_long_query() {
+    test_len := 32768
+    mut buf := strings.new_builder(test_len * 3)
+    base_string := rand.string(test_len)
+
+    for c in base_string {
+        buf.write_b(`(`)
+        buf.write_b(c)
+        buf.write_b(`)`)
+    }
+
+    mut query := buf.str()
+    
+    //println(base_string)
+    //println(buf.str())
+
+    // test 1
+    mut re := regex.regex_opt(query) or { panic(err) }
+    mut start, mut end := re.match_string(base_string)
+    //println("$start, $end")
+    assert start >= 0 && end == base_string.len
+
+    // test 2
+    buf.clear()
+    for c in base_string {
+        buf.write_b(`(`)
+        buf.write_b(c)
+    }
+    for _ in 0..base_string.len {
+        buf.write_b(`)`)
+    }
+    query = buf.str()
+    re = regex.regex_opt(query) or { panic(err) }
+    start, end = re.match_string(base_string)
+    //println("$start, $end")
+    assert start >= 0 && end == base_string.len
+}

vlib/regex/regex_util.v

@@ -21,7 +21,7 @@ pub fn regex_base(pattern string) (RE, int, int) {
 	re.prog = []Token{len: pattern.len + 1} // max program length, can not be longer then the pattern
 	re.cc = []CharClass{len: pattern.len} // can not be more char class the the length of the pattern
 	re.group_csave_flag = false // enable continuos group saving
-	re.group_max_nested = 128 // set max 128 group nested
+	re.group_max_nested = pattern.len >> 1 // set max 128 group nested
 	re.group_max = pattern.len >> 1 // we can't have more groups than the half of the pattern legth
 
 	re.group_stack = []int{len: re.group_max, init: -1}
@@ -63,7 +63,7 @@ pub fn (re RE) get_group_by_name(in_txt string, group_name string) string {
 // get_group_by_id get a group string by its id
 pub fn (re RE) get_group_by_id(in_txt string, group_id int) string {
 	if group_id < (re.groups.len >> 1) {
-		index := group_id << 1
+		index := group_id * 2
 		start := re.groups[index]
 		end := re.groups[index + 1]
 		if start >= 0 && end > start {
@@ -76,7 +76,7 @@ pub fn (re RE) get_group_by_id(in_txt string, group_id int) string {
 // get_group_by_id get a group boundaries by its id
 pub fn (re RE) get_group_bounds_by_id(group_id int) (int, int) {
 	if group_id < re.group_count {
-		index := group_id << 1
+		index := group_id * 2
 		return re.groups[index], re.groups[index + 1]
 	}
 	return -1, -1
@@ -366,8 +366,8 @@ pub fn (mut re RE) replace_by_fn(in_txt string, repl_fn FnReplace) string {
 			}
 			/*
 			for g_i in 0 .. re.group_count {
-				re.groups[g_i << 1] += i
-				re.groups[(g_i << 1) + 1] += i
+				re.groups[g_i * 2] += i
+				re.groups[(g_i * 2) + 1] += i
 			}
 			*/
 			repl := repl_fn(re, in_txt, s, e)
@@ -428,8 +428,8 @@ pub fn (mut re RE) replace(in_txt string, repl_str string) string {
 			}
 			/*
 			for g_i in 0 .. re.group_count {
-				re.groups[g_i << 1] += i
-				re.groups[(g_i << 1) + 1] += i
+				re.groups[g_i * 2] += i
+				re.groups[(g_i * 2) + 1] += i
 			}
 			*/
 			// repl := repl_fn(re, in_txt, s, e)