cmd/go: Fix go get when the fetched XML uses ASCII encoding

Also, add a meaningful error message when an encoding which can't be parsed is found. Fixes #5801. R=golang-dev, bradfitz, rsc CC=golang-dev https://golang.org/cl/12343043

cmd/go: Fix go get when the fetched XML uses ASCII encoding
Also, add a meaningful error message when an encoding which can't be parsed is found. Fixes #5801. R=golang-dev, bradfitz, rsc CC=golang-dev https://golang.org/cl/12343043
bbf14300 · Alberto García Hierro · Brad Fitzpatrick · 869774cb · bbf14300 · bbf14300
Commit bbf14300 authored Aug 02, 2013 by Alberto García Hierro Committed by Brad Fitzpatrick Aug 02, 2013
Hide whitespace changes
Inline Side-by-side

Showing with 29 additions and 4 deletions

src/cmd/go/discovery.go src/cmd/go/discovery.go +20 -2

src/cmd/go/vcs.go src/cmd/go/vcs.go +9 -2

No files found.
--- a/src/cmd/go/discovery.go
+++ b/src/cmd/go/discovery.go
@@ -13,17 +13,35 @@ package main

 import (
 	"encoding/xml"
+	"fmt"
 	"io"
 	"strings"
 )

+// charsetReader returns a reader for the given charset. Currently
+// it only supports UTF-8 and ASCII. Otherwise, it returns a meaningful
+// error which is printed by go get, so the user can find why the package
+// wasn't downloaded if the encoding is not supported. Note that, in
+// order to reduce potential errors, ASCII is treated as UTF-8 (i.e. characters
+// greater than 0x7f are not rejected).
+func charsetReader(charset string, input io.Reader) (io.Reader, error) {
+	switch strings.ToLower(charset) {
+	case "ascii":
+		return input, nil
+	default:
+		return nil, fmt.Errorf("can't decode XML document using charset %q", charset)
+	}
+}
+
 // parseMetaGoImports returns meta imports from the HTML in r.
 // Parsing ends at the end of the <head> section or the beginning of the <body>.
-func parseMetaGoImports(r io.Reader) (imports []metaImport) {
+func parseMetaGoImports(r io.Reader) (imports []metaImport, err error) {
 	d := xml.NewDecoder(r)
+	d.CharsetReader = charsetReader
 	d.Strict = false
+	var t xml.Token
 	for {
-		t, err := d.Token()
+		t, err = d.Token()
 		if err != nil {
 			return
 		}

--- a/src/cmd/go/vcs.go
+++ b/src/cmd/go/vcs.go
@@ -442,7 +442,11 @@ func repoRootForImportDynamic(importPath string) (*repoRoot, error) {
 		return nil, fmt.Errorf("http/https fetch: %v", err)
 	}
 	defer body.Close()
-	metaImport, err := matchGoImport(parseMetaGoImports(body), importPath)
+	imports, err := parseMetaGoImports(body)
+	if err != nil {
+		return nil, fmt.Errorf("parsing %s: %v", importPath, err)
+	}
+	metaImport, err := matchGoImport(imports, importPath)
 	if err != nil {
 		if err != errNoMatch {
 			return nil, fmt.Errorf("parse %s: %v", urlStr, err)
@@ -467,7 +471,10 @@ func repoRootForImportDynamic(importPath string) (*repoRoot, error) {
 		if err != nil {
 			return nil, fmt.Errorf("fetch %s: %v", urlStr, err)
 		}
-		imports := parseMetaGoImports(body)
+		imports, err := parseMetaGoImports(body)
+		if err != nil {
+			return nil, fmt.Errorf("parsing %s: %v", importPath, err)
+		}
 		if len(imports) == 0 {
 			return nil, fmt.Errorf("fetch %s: no go-import meta tag", urlStr)
 		}