encoding/csv: add Reader.InputOffset method

Fixes #43401.

Change-Id: I2498e77e41d845130d95012bc8623bfb29c0dda1
Reviewed-on: https://go-review.googlesource.com/c/go/+/405675
TryBot-Result: Gopher Robot <gobot@golang.org>
Run-TryBot: Ian Lance Taylor <iant@golang.org>
Run-TryBot: Ian Lance Taylor <iant@google.com>
Auto-Submit: Ian Lance Taylor <iant@google.com>
Reviewed-by: Ian Lance Taylor <iant@google.com>
Reviewed-by: Dmitri Shuralyov <dmitshur@google.com>

1 files changed, 15 insertions, 3 deletions

diff --git a/src/encoding/csv/reader.go b/src/encoding/csv/reader.go
index f860f4f25f..90a37e6074 100644
--- a/src/encoding/csv/reader.go
+++ b/src/encoding/csv/reader.go
@@ -149,6 +149,9 @@ type Reader struct {
 	// numLine is the current line being read in the CSV file.
 	numLine int
 
+	// offset is the input stream byte offset of the current reader position.
+	offset int64
+
 	// rawBuffer is a line buffer only used by the readLine method.
 	rawBuffer []byte
 
@@ -210,6 +213,13 @@ func (r *Reader) FieldPos(field int) (line, column int) {
 	return p.line, p.col
 }
 
+// InputOffset returns the input stream byte offset of the current reader
+// position. The offset gives the location of the end of the most recently
+// read row and the beginning of the next row.
+func (r *Reader) InputOffset() int64 {
+	return r.offset
+}
+
 // pos holds the position of a field in the current line.
 type position struct {
 	line, col int
@@ -247,14 +257,16 @@ func (r *Reader) readLine() ([]byte, error) {
 		}
 		line = r.rawBuffer
 	}
-	if len(line) > 0 && err == io.EOF {
+	readSize := len(line)
+	if readSize > 0 && err == io.EOF {
 		err = nil
 		// For backwards compatibility, drop trailing \r before EOF.
-		if line[len(line)-1] == '\r' {
-			line = line[:len(line)-1]
+		if line[readSize-1] == '\r' {
+			line = line[:readSize-1]
 		}
 	}
 	r.numLine++
+	r.offset += int64(readSize)
 	// Normalize \r\n to \n on all input lines.
 	if n := len(line); n >= 2 && line[n-2] == '\r' && line[n-1] == '\n' {
 		line[n-2] = '\n'