regex: fix a bug with find_all, fixes #10799 (#10801)

vlib/regex/regex.v

@@ -334,6 +334,10 @@ fn (mut re RE) reset() {
 	if re.group_csave_flag == true {
 		re.group_csave.clear() // = []int{}
 	}
+
+	// reset state list
+	re.state_list.clear()
+	re.group_stack.clear()
 }
 
 // reset for search mode fail
@@ -1787,6 +1791,10 @@ pub fn (mut re RE) match_base(in_txt &byte, in_txt_len int) (int, int) {
 				re.reset_src()
 				state.match_index = -1
 				state.first_match = -1
+
+				// reset state list
+				re.reset()
+
 				continue
 			}
 

vlib/regex/regex_test.v

@@ -326,7 +326,20 @@ find_all_test_suite = [
 		r".*#[.#]{4}##[.#]{4}##[.#]{4}###",
 		[0, 49],
 		['#.#......##.#..#..##........##....###...##...####']
+	},
+		Test_find_all{
+		"1234 Aa dddd Aaf 12334 Aa opopo Aaf",
+		r"Aa.+Aaf",
+		[5, 16, 23, 35],
+		['Aa dddd Aaf', 'Aa opopo Aaf']
+	},
+		Test_find_all{
+		"@for something @endfor @for something else @endfor altro testo @for body @endfor uno due @for senza dire più @endfor pippo",
+		r"@for.+@endfor",
+		[0, 22, 23, 50, 63, 80, 89, 117],
+		['@for something @endfor', '@for something else @endfor', '@for body @endfor', '@for senza dire più @endfor']
 	}
+
 ]
 )
 

vlib/regex/regex_util.v

@@ -178,21 +178,18 @@ pub fn (mut re RE) find(in_txt string) (int, int) {
 
 	mut i := 0
 	for i < in_txt.len {
-		//--- speed references ---
 		mut s := -1
 		mut e := -1
 		unsafe {
-			tmp_str := tos(in_txt.str + i, in_txt.len - i)
+			// tmp_str := tos(in_txt.str + i, in_txt.len - i)
-			s, e = re.match_string(tmp_str)
+			// println("Check: [$tmp_str]")
-		}
+			s, e = re.match_base(in_txt.str + i, in_txt.len - i + 1)
-		//------------------------
+
-		// s,e := re.find_imp(in_txt[i..])
-		//------------------------
 			if s >= 0 && e > s {
 				// println("find match in: ${i+s},${i+e} [${in_txt[i+s..i+e]}]")
 				// re.flag = old_flag
 				return i + s, i + e
-		} else {
+			}
 			i++
 		}
 	}
@@ -243,30 +240,25 @@ pub fn (mut re RE) find_all(in_txt string) []int {
 
 	mut i := 0
 	mut res := []int{}
-	mut ls := -1
 
 	for i < in_txt.len {
-		//--- speed references ---
 		mut s := -1
 		mut e := -1
 		unsafe {
-			tmp_str := tos(in_txt.str + i, in_txt.len - i)
+			// tmp_str := in_txt[i..]
-			s, e = re.match_string(tmp_str)
+			// tmp_str := tos(in_txt.str + i, in_txt.len - i)
-		}
+			// println("Check: [$tmp_str]")
-		//------------------------
+			s, e = re.match_base(in_txt.str + i, in_txt.len + 1 - i)
-		// s,e := re.find_imp(in_txt[i..])
+
-		//------------------------
+			if s >= 0 && e > s {
-		if s >= 0 && e > s && i + s > ls {
-			// println("find match in: ${i+s},${i+e} [${in_txt[i+s..i+e]}] ls:$ls")
 				res << i + s
 				res << i + e
-			ls = i + s
+				i += e
-			i = i + e
 				continue
-		} else {
-			i++
 			}
 		}
+		i++
+	}
 	// re.flag = old_flag
 	return res
 }
@@ -274,31 +266,32 @@ pub fn (mut re RE) find_all(in_txt string) []int {
 // find_all_str find all the non overlapping occurrences of the match pattern, return a string list
 [direct_array_access]
 pub fn (mut re RE) find_all_str(in_txt string) []string {
+	// old_flag := re.flag
+	// re.flag |= f_src // enable search mode
+
 	mut i := 0
 	mut res := []string{}
-	mut ls := -1
 
 	for i < in_txt.len {
-		//--- speed references ---
 		mut s := -1
 		mut e := -1
 		unsafe {
+			// tmp_str := in_txt[i..]
+			// tmp_str := tos(in_txt.str + i, in_txt.len - i)
+			// println("Check: [$tmp_str]")
+			s, e = re.match_base(in_txt.str + i, in_txt.len + 1 - i)
+
+			if s >= 0 && e > s {
 				tmp_str := tos(in_txt.str + i, in_txt.len - i)
-			s, e = re.find(tmp_str)
+				// println("Found: $s:$e [${tmp_str[s..e]}]")
-		}
+				res << tmp_str[..e]
-		//------------------------
+				i += e
-		// s,e := re.find(in_txt[i..])
-		//------------------------
-		if s >= 0 && e > s && i + s > ls {
-			// println("find match in: ${i+s},${i+e} [${in_txt[i+s..i+e]}] ls:$ls")
-			res << in_txt[i + s..i + e]
-			ls = i + s
-			i = i + e
 				continue
-		} else {
+			}
+		}
 		i++
 	}
-	}
+	// re.flag = old_flag
 	return res
 }