cmd/vet: allow spaces in struct tag values.

The validateStructTag code now closely mimics the StructTag.Get code in
package reflect.

This addresses the comment raised on issue #9500:
https://github.com/golang/go/issues/9500#issuecomment-70218780

See also https://go-review.googlesource.com/3953

Change-Id: I583f7447dbc5a2d7ecbb393d9bb6b1515cb10b18
Reviewed-on: https://go-review.googlesource.com/3952
Reviewed-by: Rob Pike <r@golang.org>

2 files changed, 46 insertions, 20 deletions

diff --git a/cmd/vet/structtag.go b/cmd/vet/structtag.go
index a2b7d30..e8164a4 100644
--- a/cmd/vet/structtag.go
+++ b/cmd/vet/structtag.go
@@ -11,8 +11,6 @@ import (
 	"go/ast"
 	"reflect"
 	"strconv"
-	"strings"
-	"unicode"
 )
 
 func init() {
@@ -68,33 +66,55 @@ var (
 
 // validateStructTag parses the struct tag and returns an error if it is not
 // in the canonical format, which is a space-separated list of key:"value"
-// settings.
+// settings. The value may contain spaces.
 func validateStructTag(tag string) error {
-	elems := strings.Split(tag, " ")
-	for _, elem := range elems {
-		if elem == "" {
-			continue
+	// This code is based on the StructTag.Get code in package reflect.
+
+	for tag != "" {
+		// Skip leading space.
+		i := 0
+		for i < len(tag) && tag[i] == ' ' {
+			i++
 		}
-		fields := strings.SplitN(elem, ":", 2)
-		if len(fields) != 2 {
-			return errTagSyntax
+		tag = tag[i:]
+		if tag == "" {
+			break
+		}
+
+		// Scan to colon. A space, a quote or a control character is a syntax error.
+		// Strictly speaking, control chars include the range [0x7f, 0x9f], not just
+		// [0x00, 0x1f], but in practice, we ignore the multi-byte control characters
+		// as it is simpler to inspect the tag's bytes than the tag's runes.
+		i = 0
+		for i < len(tag) && tag[i] > ' ' && tag[i] != ':' && tag[i] != '"' && tag[i] != 0x7f {
+			i++
+		}
+		if i == 0 {
+			return errTagKeySyntax
 		}
-		key, value := fields[0], fields[1]
-		if len(key) == 0 || len(value) < 2 {
+		if i+1 >= len(tag) || tag[i] != ':' {
 			return errTagSyntax
 		}
-		// Key must not contain control characters or quotes.
-		for _, r := range key {
-			if r == '"' || unicode.IsControl(r) {
-				return errTagKeySyntax
+		if tag[i+1] != '"' {
+			return errTagValueSyntax
+		}
+		tag = tag[i+1:]
+
+		// Scan quoted string to find value.
+		i = 1
+		for i < len(tag) && tag[i] != '"' {
+			if tag[i] == '\\' {
+				i++
 			}
+			i++
 		}
-		if value[0] != '"' || value[len(value)-1] != '"' {
+		if i >= len(tag) {
 			return errTagValueSyntax
 		}
-		// Value must be quoted string
-		_, err := strconv.Unquote(value)
-		if err != nil {
+		qvalue := string(tag[:i+1])
+		tag = tag[i+1:]
+
+		if _, err := strconv.Unquote(qvalue); err != nil {
 			return errTagValueSyntax
 		}
 	}
diff --git a/cmd/vet/testdata/structtag.go b/cmd/vet/testdata/structtag.go
index 1e1ebf8..6878f56 100644
--- a/cmd/vet/testdata/structtag.go
+++ b/cmd/vet/testdata/structtag.go
@@ -11,8 +11,14 @@ type StructTagTest struct {
 	B   int "\tx:\"y\""        // ERROR "not compatible with reflect.StructTag.Get: bad syntax for struct tag key"
 	C   int "x:\"y\"\tx:\"y\"" // ERROR "not compatible with reflect.StructTag.Get"
 	D   int "x:`y`"            // ERROR "not compatible with reflect.StructTag.Get: bad syntax for struct tag value"
+	E   int "ct\brl:\"char\""  // ERROR "not compatible with reflect.StructTag.Get: bad syntax for struct tag pair"
+	F   int `:"emptykey"`      // ERROR "not compatible with reflect.StructTag.Get: bad syntax for struct tag key"
+	G   int `x:"noEndQuote`    // ERROR "not compatible with reflect.StructTag.Get: bad syntax for struct tag value"
+	H   int `x:"trunc\x0"`     // ERROR "not compatible with reflect.StructTag.Get: bad syntax for struct tag value"
 	OK0 int `x:"y" u:"v" w:""`
 	OK1 int `x:"y:z" u:"v" w:""` // note multiple colons.
+	OK2 int "k0:\"values contain spaces\" k1:\"literal\ttabs\" k2:\"and\\tescaped\\tabs\""
+	OK3 int `under_scores:"and" CAPS:"ARE_OK"`
 }
 
 type UnexportedEncodingTagTest struct {