Fix the problem that UTF8 BOM can cause the parsing of import path and directives to fail.
Fixes #46198
Fixes #46290
Fixes #35726
Change-Id: I2d9995ee82b094bcfa5583f0cb4e8547cb973077
GitHub-Last-Rev:
98abf91377f155266fa60505c0c12beccad38eeb
GitHub-Pull-Request: golang/go#46643
Reviewed-on: https://go-review.googlesource.com/c/go/+/325990
Reviewed-by: Bryan C. Mills <bcmills@google.com>
Trust: Bryan C. Mills <bcmills@google.com>
Trust: Robert Findley <rfindley@google.com>
Run-TryBot: Bryan C. Mills <bcmills@google.com>
TryBot-Result: Go Bot <gobot@golang.org>
import (
"bufio"
+ "bytes"
"errors"
"io"
"unicode/utf8"
nerr int
}
+var bom = []byte{0xef, 0xbb, 0xbf}
+
+func newImportReader(b *bufio.Reader) *importReader {
+ // Remove leading UTF-8 BOM.
+ // Per https://golang.org/ref/spec#Source_code_representation:
+ // a compiler may ignore a UTF-8-encoded byte order mark (U+FEFF)
+ // if it is the first Unicode code point in the source text.
+ if leadingBytes, err := b.Peek(3); err == nil && bytes.Equal(leadingBytes, bom) {
+ b.Discard(3)
+ }
+ return &importReader{b: b}
+}
+
func isIdent(c byte) bool {
return 'A' <= c && c <= 'Z' || 'a' <= c && c <= 'z' || '0' <= c && c <= '9' || c == '_' || c >= utf8.RuneSelf
}
// ReadComments is like io.ReadAll, except that it only reads the leading
// block of comments in the file.
func ReadComments(f io.Reader) ([]byte, error) {
- r := &importReader{b: bufio.NewReader(f)}
+ r := newImportReader(bufio.NewReader(f))
r.peekByte(true)
if r.err == nil && !r.eof {
// Didn't reach EOF, so must have found a non-space byte. Remove it.
// ReadImports is like io.ReadAll, except that it expects a Go file as input
// and stops reading the input once the imports have completed.
func ReadImports(f io.Reader, reportSyntaxError bool, imports *[]string) ([]byte, error) {
- r := &importReader{b: bufio.NewReader(f)}
+ r := newImportReader(bufio.NewReader(f))
r.readKeyword("package")
r.readIdent()
`,
"",
},
+ {
+ "\ufeff𝔻" + `package p; import "x";ℙvar x = 1`,
+ "",
+ },
}
var readCommentsTests = []readTest{
`ā„™package p; import . "x"`,
"",
},
+ {
+ "\ufeff𝔻" + `ℙpackage p; import . "x"`,
+ "",
+ },
{
`// foo
/*/ zot */
+ // asdf
+ ā„™Hello, world`,
+ "",
+ },
+ {
+ "\ufeff𝔻" + `// foo
+
+ /* bar */
+
+ /* quux */ // baz
+
+ /*/ zot */
+
// asdf
ā„™Hello, world`,
"",
in = tt.in[:j] + tt.in[j+len("ā„™"):]
testOut = tt.in[:j]
}
+ d := strings.Index(tt.in, "𝔻")
+ if d >= 0 {
+ in = in[:d] + in[d+len("𝔻"):]
+ testOut = testOut[d+len("𝔻"):]
+ }
r := strings.NewReader(in)
buf, err := read(r)
if err != nil {
--- /dev/null
+# Per https://golang.org/ref/spec#Source_code_representation:
+# a compiler may ignore a UTF-8-encoded byte order mark (U+FEFF)
+# if it is the first Unicode code point in the source text.
+
+go list -f 'Imports: {{.Imports}} EmbedFiles: {{.EmbedFiles}}' .
+stdout '^Imports: \[embed m/hello\] EmbedFiles: \[.*file\]$'
+
+-- go.mod --
+module m
+
+go 1.16
+-- m.go --
+package main
+
+import (
+ _ "embed"
+
+ "m/hello"
+)
+
+//go:embed file
+var s string
+
+-- hello/hello.go --
+package hello
+
+-- file --
import (
"bufio"
+ "bytes"
"errors"
"fmt"
"go/ast"
pos token.Position
}
+var bom = []byte{0xef, 0xbb, 0xbf}
+
func newImportReader(name string, r io.Reader) *importReader {
+ b := bufio.NewReader(r)
+ // Remove leading UTF-8 BOM.
+ // Per https://golang.org/ref/spec#Source_code_representation:
+ // a compiler may ignore a UTF-8-encoded byte order mark (U+FEFF)
+ // if it is the first Unicode code point in the source text.
+ if leadingBytes, err := b.Peek(3); err == nil && bytes.Equal(leadingBytes, bom) {
+ b.Discard(3)
+ }
return &importReader{
- b: bufio.NewReader(r),
+ b: b,
pos: token.Position{
Filename: name,
Line: 1,
`,
"",
},
+ {
+ "\ufeff𝔻" + `package p; import "x";ℙvar x = 1`,
+ "",
+ },
}
var readCommentsTests = []readTest{
`ā„™package p; import . "x"`,
"",
},
+ {
+ "\ufeff𝔻" + `ℙpackage p; import . "x"`,
+ "",
+ },
{
`// foo
/*/ zot */
+ // asdf
+ ā„™Hello, world`,
+ "",
+ },
+ {
+ "\ufeff𝔻" + `// foo
+
+ /* bar */
+
+ /* quux */ // baz
+
+ /*/ zot */
+
// asdf
ā„™Hello, world`,
"",
in = tt.in[:j] + tt.in[j+len("ā„™"):]
testOut = tt.in[:j]
}
+ d := strings.Index(tt.in, "𝔻")
+ if d >= 0 {
+ in = in[:d] + in[d+len("𝔻"):]
+ testOut = testOut[d+len("𝔻"):]
+ }
r := strings.NewReader(in)
buf, err := read(r)
if err != nil {
test:3:14:y
test:3:16:z`,
},
+ {
+ "\ufeffpackage p\nimport \"embed\"\n//go:embed x y z\nvar files embed.FS",
+ `test:3:12:x
+ test:3:14:y
+ test:3:16:z`,
+ },
{
"package p\nimport \"embed\"\nvar s = \"/*\"\n//go:embed x\nvar files embed.FS",
`test:4:12:x`,
"package p\n//go:embed x y z\nvar files embed.FS", // no import, no scan
"",
},
+ {
+ "\ufeffpackage p\n//go:embed x y z\nvar files embed.FS", // no import, no scan
+ "",
+ },
}
func TestReadEmbed(t *testing.T) {