regexp: add (*Regexp).SubexpIndex

SubexpIndex returns the index of the first subexpression with the given name,
or -1 if there is no subexpression with that name.

Fixes #32420

Change-Id: Ie1f9d22d50fb84e18added80a9d9a9f6dca8ffc4
Reviewed-on: https://go-review.googlesource.com/c/go/+/187919
Run-TryBot: Ian Lance Taylor <[email protected]>
TryBot-Result: Gobot Gobot <[email protected]>
Reviewed-by: Daniel Martí <[email protected]>

Author: sylvinus

src/regexp/all_test.go

@@ -418,24 +418,32 @@ func TestLiteralPrefix(t *testing.T) {
 	}
 }
 
+type subexpIndex struct {
+	name  string
+	index int
+}
+
 type subexpCase struct {
-	input string
-	num   int
-	names []string
+	input   string
+	num     int
+	names   []string
+	indices []subexpIndex
 }
 
+var emptySubexpIndices = []subexpIndex{{"", -1}, {"missing", -1}}
+
 var subexpCases = []subexpCase{
-	{``, 0, nil},
-	{`.*`, 0, nil},
-	{`abba`, 0, nil},
-	{`ab(b)a`, 1, []string{"", ""}},
-	{`ab(.*)a`, 1, []string{"", ""}},
-	{`(.*)ab(.*)a`, 2, []string{"", "", ""}},
-	{`(.*)(ab)(.*)a`, 3, []string{"", "", "", ""}},
-	{`(.*)((a)b)(.*)a`, 4, []string{"", "", "", "", ""}},
-	{`(.*)(\(ab)(.*)a`, 3, []string{"", "", "", ""}},
-	{`(.*)(\(a\)b)(.*)a`, 3, []string{"", "", "", ""}},
-	{`(?P<foo>.*)(?P<bar>(a)b)(?P<foo>.*)a`, 4, []string{"", "foo", "bar", "", "foo"}},
+	{``, 0, nil, emptySubexpIndices},
+	{`.*`, 0, nil, emptySubexpIndices},
+	{`abba`, 0, nil, emptySubexpIndices},
+	{`ab(b)a`, 1, []string{"", ""}, emptySubexpIndices},
+	{`ab(.*)a`, 1, []string{"", ""}, emptySubexpIndices},
+	{`(.*)ab(.*)a`, 2, []string{"", "", ""}, emptySubexpIndices},
+	{`(.*)(ab)(.*)a`, 3, []string{"", "", "", ""}, emptySubexpIndices},
+	{`(.*)((a)b)(.*)a`, 4, []string{"", "", "", "", ""}, emptySubexpIndices},
+	{`(.*)(\(ab)(.*)a`, 3, []string{"", "", "", ""}, emptySubexpIndices},
+	{`(.*)(\(a\)b)(.*)a`, 3, []string{"", "", "", ""}, emptySubexpIndices},
+	{`(?P<foo>.*)(?P<bar>(a)b)(?P<foo>.*)a`, 4, []string{"", "foo", "bar", "", "foo"}, []subexpIndex{{"", -1}, {"missing", -1}, {"foo", 1}, {"bar", 2}}},
 }
 
 func TestSubexp(t *testing.T) {
@@ -458,6 +466,12 @@ func TestSubexp(t *testing.T) {
 				}
 			}
 		}
+		for _, subexp := range c.indices {
+			index := re.SubexpIndex(subexp.name)
+			if index != subexp.index {
+				t.Errorf("%q: SubexpIndex(%q) = %d, want %d", c.input, subexp.name, index, subexp.index)
+			}
+		}
 	}
 }
 

src/regexp/example_test.go

@@ -280,6 +280,19 @@ func ExampleRegexp_SubexpNames() {
 	// Turing Alan
 }
 
+func ExampleRegexp_SubexpIndex() {
+	re := regexp.MustCompile(`(?P<first>[a-zA-Z]+) (?P<last>[a-zA-Z]+)`)
+	fmt.Println(re.MatchString("Alan Turing"))
+	matches := re.FindStringSubmatch("Alan Turing")
+	lastIndex := re.SubexpIndex("last")
+	fmt.Printf("last => %d\n", lastIndex)
+	fmt.Println(matches[lastIndex])
+	// Output:
+	// true
+	// last => 2
+	// Turing
+}
+
 func ExampleRegexp_Split() {
 	a := regexp.MustCompile(`a`)
 	fmt.Println(a.Split("banana", -1))

src/regexp/regexp.go

@@ -345,6 +345,24 @@ func (re *Regexp) SubexpNames() []string {
 	return re.subexpNames
 }
 
+// SubexpIndex returns the index of the first subexpression with the given name,
+// or -1 if there is no subexpression with that name.
+//
+// Note that multiple subexpressions can be written using the same name, as in
+// (?P<bob>a+)(?P<bob>b+), which declares two subexpressions named "bob".
+// In this case, SubexpIndex returns the index of the leftmost such subexpression
+// in the regular expression.
+func (re *Regexp) SubexpIndex(name string) int {
+	if name != "" {
+		for i, s := range re.subexpNames {
+			if name == s {
+				return i
+			}
+		}
+	}
+	return -1
+}
+
 const endOfText rune = -1
 
 // input abstracts different representations of the input text. It provides