From 0fafefc07860bff250490b415c2fef98f1b56ce4 Mon Sep 17 00:00:00 2001
From: penguindark <57967770+penguindark@users.noreply.github.com>
Date: Tue, 12 Oct 2021 05:03:23 +0200
Subject: [PATCH] regex: bug fix on find groups indexes (#12152)

---
 vlib/regex/regex_test.v | 61 +++++++++++++++++++++++++++++++++++++++++
 vlib/regex/regex_util.v | 18 +++++++++---
 2 files changed, 75 insertions(+), 4 deletions(-)

diff --git a/vlib/regex/regex_test.v b/vlib/regex/regex_test.v
index e9a3baf1ce..bc1be2dfbb 100644
--- a/vlib/regex/regex_test.v
+++ b/vlib/regex/regex_test.v
@@ -645,3 +645,64 @@ fn test_quantifier_sequences(){
 		assert re_err == regex.err_syntax_error
 	}
 }
+
+// test group index in find
+struct Test_find_groups {
+	src string
+	q string
+	s int // start index
+	e int // end index
+	res []int // groups indexes 
+}
+const (
+find_groups_test_suite = [
+	Test_find_groups{
+		"aabbbccccdd",
+		r"(b+)(c+)",
+		2,
+		9,
+		[2, 5, 5, 9],
+	},
+	Test_find_groups{
+		"aabbbccccdd",
+		r"(a+).*(c+)",
+		0,
+		9,
+		[0, 2, 5, 9],
+	},
+	Test_find_groups{
+		"aabbbccccdd",
+		r"((b+).*)(d+)",
+		2,
+		11,
+		[2, 9, 2, 5, 9, 11],
+	},
+]
+)
+fn test_groups_in_find(){
+	for test_obj in find_groups_test_suite {
+		src_text := test_obj.src
+		query := test_obj.q
+		mut re := regex.regex_opt(query) or { panic(err) }
+		start, end := re.find(src_text)
+		// Debug print do not remove!!
+		/*
+		println("---------")
+		println("src_text:[${src_text}]")
+		println("query   :[${query}]")
+		println("[${start}, ${end}]")
+		println(re.groups)
+		mut gi := 0
+		for gi < re.groups.len {
+			if re.groups[gi] >= 0 {
+				println('${gi / 2} :[${src_text[re.groups[gi]..re.groups[gi + 1]]}]')
+			}
+			gi += 2
+		}
+		*/
+		// check
+		assert start == test_obj.s
+		assert end == test_obj.e
+		assert re.groups == test_obj.res
+	}
+}
\ No newline at end of file
diff --git a/vlib/regex/regex_util.v b/vlib/regex/regex_util.v
index 060d01dabb..fa78f63499 100644
--- a/vlib/regex/regex_util.v
+++ b/vlib/regex/regex_util.v
@@ -194,6 +194,11 @@ pub fn (mut re RE) find(in_txt string) (int, int) {
 			if s >= 0 && e > s {
 				// println("find match in: ${i+s},${i+e} [${in_txt[i+s..i+e]}]")
 				// re.flag = old_flag
+				mut gi := 0
+				for gi < re.groups.len {
+					re.groups[gi] += i
+					gi++
+				}
 				return i + s, i + e
 			}
 			i++
@@ -229,6 +234,11 @@ pub fn (mut re RE) find_from(in_txt string, start int) (int, int) {
 		if s >= 0 && e > s {
 			// println("find match in: ${i+s},${i+e} [${in_txt[i+s..i+e]}]")
 			re.flag = old_flag
+			mut gi := 0
+			for gi < re.groups.len {
+				re.groups[gi] += i
+				gi++
+			}
 			return i + s, i + e
 		} else {
 			i++
@@ -354,12 +364,12 @@ pub fn (mut re RE) replace_by_fn(in_txt string, repl_fn FnReplace) string {
 			if last_end < s {
 				res.write_string(in_txt[last_end..s])
 			}
-
+			/*
 			for g_i in 0 .. re.group_count {
 				re.groups[g_i << 1] += i
 				re.groups[(g_i << 1) + 1] += i
 			}
-
+			*/
 			repl := repl_fn(re, in_txt, s, e)
 			// println("repl res: $repl")
 			res.write_string(repl)
@@ -416,12 +426,12 @@ pub fn (mut re RE) replace(in_txt string, repl_str string) string {
 			if last_end < s {
 				res.write_string(in_txt[last_end..s])
 			}
-
+			/*
 			for g_i in 0 .. re.group_count {
 				re.groups[g_i << 1] += i
 				re.groups[(g_i << 1) + 1] += i
 			}
-
+			*/
 			// repl := repl_fn(re, in_txt, s, e)
 			repl := re.parsed_replace_string(in_txt, repl_str)
 			// println("repl res: $repl")