encoding/xml: expose decoder line and column

The existing implementation of the xml decoder uses the line number
only for reporting syntax errors. The line number of the last read
token and the column within the line is useful for the users even
in non-error conditions.

Fixes #45628

Change-Id: I37b5033ff5ff8411793d8f5180f96aa4537e83f5
Reviewed-on: https://go-review.googlesource.com/c/go/+/311270
Run-TryBot: Ian Lance Taylor <iant@golang.org>
TryBot-Result: Gopher Robot <gobot@golang.org>
Reviewed-by: Ian Lance Taylor <iant@golang.org>
Reviewed-by: Emmanuel Odeke <emmanuel@orijtech.com>
Trust: Emmanuel Odeke <emmanuel@orijtech.com>

2 files changed, 48 insertions, 0 deletions

diff --git a/src/encoding/xml/xml.go b/src/encoding/xml/xml.go
index ef51252dcb..a7a02f5b57 100644
--- a/src/encoding/xml/xml.go
+++ b/src/encoding/xml/xml.go
@@ -216,6 +216,7 @@ type Decoder struct {
 	ns             map[string]string
 	err            error
 	line           int
+	linestart      int64
 	offset         int64
 	unmarshalDepth int
 }
@@ -919,6 +920,7 @@ func (d *Decoder) getc() (b byte, ok bool) {
 	}
 	if b == '\n' {
 		d.line++
+		d.linestart = d.offset + 1
 	}
 	d.offset++
 	return b, true
@@ -931,6 +933,13 @@ func (d *Decoder) InputOffset() int64 {
 	return d.offset
 }
 
+// InputPos retuns the line of the current decoder position and the 1 based
+// input position of the line. The position gives the location of the end of the
+// most recently returned token.
+func (d *Decoder) InputPos() (line, column int) {
+	return d.line, int(d.offset-d.linestart) + 1
+}
+
 // Return saved offset.
 // If we did ungetc (nextByte >= 0), have to back up one.
 func (d *Decoder) savedOffset() int {
diff --git a/src/encoding/xml/xml_test.go b/src/encoding/xml/xml_test.go
index ab1dbf849b..8f0d97b6a6 100644
--- a/src/encoding/xml/xml_test.go
+++ b/src/encoding/xml/xml_test.go
@@ -502,6 +502,45 @@ func TestSyntax(t *testing.T) {
 	}
 }
 
+func TestInputLinePos(t *testing.T) {
+	testInput := `<root>
+<?pi
+ ?>  <elt
+att
+=
+"val">
+<![CDATA[
+]]><!--
+
+--></elt>
+</root>`
+	linePos := [][]int{
+		{1, 7},
+		{2, 1},
+		{3, 4},
+		{3, 6},
+		{6, 7},
+		{7, 1},
+		{8, 4},
+		{10, 4},
+		{10, 10},
+		{11, 1},
+		{11, 8},
+	}
+	dec := NewDecoder(strings.NewReader(testInput))
+	for _, want := range linePos {
+		if _, err := dec.Token(); err != nil {
+			t.Errorf("Unexpected error: %v", err)
+			continue
+		}
+
+		gotLine, gotCol := dec.InputPos()
+		if gotLine != want[0] || gotCol != want[1] {
+			t.Errorf("dec.InputPos() = %d,%d, want %d,%d", gotLine, gotCol, want[0], want[1])
+		}
+	}
+}
+
 type allScalars struct {
 	True1     bool
 	True2     bool