// letter and any letter following a hyphen to upper case;
// the rest are converted to lowercase. For example, the
// canonical key for "accept-encoding" is "Accept-Encoding".
+// MIME header keys are assumed to be ASCII only.
func CanonicalMIMEHeaderKey(s string) string {
// Quick check for canonical encoding.
upper := true
return s
}
+const toLower = 'a' - 'A'
+
// canonicalMIMEHeaderKey is like CanonicalMIMEHeaderKey but is
// allowed to mutate the provided byte slice before returning the
// string.
func canonicalMIMEHeaderKey(a []byte) string {
- // Canonicalize: first letter upper case
- // and upper case after each dash.
- // (Host, User-Agent, If-Modified-Since).
- // MIME headers are ASCII only, so no Unicode issues.
+ // Look for it in commonHeaders , so that we can avoid an
+ // allocation by sharing the strings among all users
+ // of textproto. If we don't find it, a has been canonicalized
+ // so just return string(a).
upper := true
- for i, v := range a {
- if v == ' ' {
+ lo := 0
+ hi := len(commonHeaders)
+ for i := 0; i < len(a); i++ {
+ // Canonicalize: first letter upper case
+ // and upper case after each dash.
+ // (Host, User-Agent, If-Modified-Since).
+ // MIME headers are ASCII only, so no Unicode issues.
+ if a[i] == ' ' {
a[i] = '-'
upper = true
continue
}
- if upper && 'a' <= v && v <= 'z' {
- a[i] = v + 'A' - 'a'
+ c := a[i]
+ if upper && 'a' <= c && c <= 'z' {
+ c -= toLower
+ } else if !upper && 'A' <= c && c <= 'Z' {
+ c += toLower
}
- if !upper && 'A' <= v && v <= 'Z' {
- a[i] = v + 'a' - 'A'
+ a[i] = c
+ upper = c == '-' // for next time
+
+ if lo < hi {
+ for lo < hi && (len(commonHeaders[lo]) <= i || commonHeaders[lo][i] < c) {
+ lo++
+ }
+ for hi > lo && commonHeaders[hi-1][i] > c {
+ hi--
+ }
}
- upper = v == '-'
+ }
+ if lo < hi && len(commonHeaders[lo]) == len(a) {
+ return commonHeaders[lo]
}
return string(a)
}
+
+var commonHeaders = []string{
+ "Accept",
+ "Accept-Charset",
+ "Accept-Encoding",
+ "Accept-Language",
+ "Accept-Ranges",
+ "Cache-Control",
+ "Cc",
+ "Connection",
+ "Content-Id",
+ "Content-Language",
+ "Content-Length",
+ "Content-Transfer-Encoding",
+ "Content-Type",
+ "Date",
+ "Dkim-Signature",
+ "Etag",
+ "Expires",
+ "From",
+ "Host",
+ "If-Modified-Since",
+ "If-None-Match",
+ "In-Reply-To",
+ "Last-Modified",
+ "Location",
+ "Message-Id",
+ "Mime-Version",
+ "Pragma",
+ "Received",
+ "Return-Path",
+ "Server",
+ "Set-Cookie",
+ "Subject",
+ "To",
+ "User-Agent",
+ "Via",
+ "X-Forwarded-For",
+ "X-Imforwards",
+ "X-Powered-By",
+}
{"uSER-aGENT", "User-Agent"},
{"user-agent", "User-Agent"},
{"USER-AGENT", "User-Agent"},
+ {"üser-agenT", "üser-Agent"}, // non-ASCII unchanged
}
func TestCanonicalMIMEHeaderKey(t *testing.T) {
}
}
+func TestCommonHeaders(t *testing.T) {
+ // need to disable the commonHeaders-based optimization
+ // during this check, or we'd not be testing anything
+ oldch := commonHeaders
+ commonHeaders = []string{}
+ defer func() { commonHeaders = oldch }()
+
+ last := ""
+ for _, h := range oldch {
+ if last > h {
+ t.Errorf("%v is out of order", h)
+ }
+ if last == h {
+ t.Errorf("%v is duplicated", h)
+ }
+ if canon := CanonicalMIMEHeaderKey(h); h != canon {
+ t.Errorf("%v is not canonical", h)
+ }
+ last = h
+ }
+}
+
+var clientHeaders = strings.Replace(`Host: golang.org
+Connection: keep-alive
+Cache-Control: max-age=0
+Accept: application/xml,application/xhtml+xml,text/html;q=0.9,text/plain;q=0.8,image/png,*/*;q=0.5
+User-Agent: Mozilla/5.0 (X11; U; Linux x86_64; en-US) AppleWebKit/534.3 (KHTML, like Gecko) Chrome/6.0.472.63 Safari/534.3
+Accept-Encoding: gzip,deflate,sdch
+Accept-Language: en-US,en;q=0.8,fr-CH;q=0.6
+Accept-Charset: ISO-8859-1,utf-8;q=0.7,*;q=0.3
+COOKIE: __utma=000000000.0000000000.0000000000.0000000000.0000000000.00; __utmb=000000000.0.00.0000000000; __utmc=000000000; __utmz=000000000.0000000000.00.0.utmcsr=code.google.com|utmccn=(referral)|utmcmd=referral|utmcct=/p/go/issues/detail
+Non-Interned: test
+
+`, "\n", "\r\n", -1)
+
+var serverHeaders = strings.Replace(`Content-Type: text/html; charset=utf-8
+Content-Encoding: gzip
+Date: Thu, 27 Sep 2012 09:03:33 GMT
+Server: Google Frontend
+Cache-Control: private
+Content-Length: 2298
+VIA: 1.1 proxy.example.com:80 (XXX/n.n.n-nnn)
+Connection: Close
+Non-Interned: test
+
+`, "\n", "\r\n", -1)
+
func BenchmarkReadMIMEHeader(b *testing.B) {
var buf bytes.Buffer
br := bufio.NewReader(&buf)
r := NewReader(br)
for i := 0; i < b.N; i++ {
- buf.WriteString("User-Agent: not mozilla\r\nContent-Length: 23452\r\nContent-Type: text/html; charset-utf8\r\nFoo-Bar: foobar\r\nfoo-bar: some more string\r\n\r\n")
+ var want int
+ var find string
+ if (i & 1) == 1 {
+ buf.WriteString(clientHeaders)
+ want = 10
+ find = "Cookie"
+ } else {
+ buf.WriteString(serverHeaders)
+ want = 9
+ find = "Via"
+ }
+ h, err := r.ReadMIMEHeader()
+ if err != nil {
+ b.Fatal(err)
+ }
+ if len(h) != want {
+ b.Fatalf("wrong number of headers: got %d, want %d", len(h), want)
+ }
+ if _, ok := h[find]; !ok {
+ b.Fatalf("did not find key %s", find)
+ }
+ }
+}
+
+func BenchmarkUncommon(b *testing.B) {
+ var buf bytes.Buffer
+ br := bufio.NewReader(&buf)
+ r := NewReader(br)
+ for i := 0; i < b.N; i++ {
+ buf.WriteString("uncommon-header-for-benchmark: foo\r\n\r\n")
h, err := r.ReadMIMEHeader()
if err != nil {
b.Fatal(err)
}
- if len(h) != 4 {
- b.Fatalf("want 4")
+ if _, ok := h["Uncommon-Header-For-Benchmark"]; !ok {
+ b.Fatal("Missing result header.")
}
}
}