MM-9072/MM-10185 Force-convert the encoding of OpenGraph metadata to UTF-8 (#8631)

* Force-convert non-UTF8 HTML to UTF8 before opengraph processing

* Split the force-encoding function

* Add benchmark Test for the forceHTMLEncodingToUTF8()

```
Running tool: /home/comet/go-v1.9.2/bin/go test -benchmem -run=^$ github.com/mattermost/mattermost-server/app -bench ^BenchmarkForceHTMLEncodingToUTF8$

[03:32:58 KST 2018/04/21] [INFO] (github.com/mattermost/mattermost-server/app.TestMain:28) -test.run used, not creating temporary containers
goos: linux
goarch: amd64
pkg: github.com/mattermost/mattermost-server/app
BenchmarkForceHTMLEncodingToUTF8/with_converting-4         	  100000	     11201 ns/op	   18704 B/op	      32 allocs/op
BenchmarkForceHTMLEncodingToUTF8/without_converting-4      	  300000	      3931 ns/op	    4632 B/op	      13 allocs/op
PASS
ok  	github.com/mattermost/mattermost-server/app	2.703s
Success: Benchmarks passed.
```

* Remove an unnecessary constraint

* Add pre-check if content-type header is already utf-8

* Move the checking for utf-8 into forceHTMLEncodingToUTF8() for testing

* Revert df3f347213faa0d023c26d201fa6531f46391086..HEAD, without Gopkg.lock

1 files changed, 189 insertions, 0 deletions

diff --git a/vendor/golang.org/x/text/encoding/japanese/shiftjis.go b/vendor/golang.org/x/text/encoding/japanese/shiftjis.go
new file mode 100644
index 000000000..16fd8a6e3
--- /dev/null
+++ b/vendor/golang.org/x/text/encoding/japanese/shiftjis.go
@@ -0,0 +1,189 @@
+// Copyright 2013 The Go Authors. All rights reserved.
+// Use of this source code is governed by a BSD-style
+// license that can be found in the LICENSE file.
+
+package japanese
+
+import (
+	"unicode/utf8"
+
+	"golang.org/x/text/encoding"
+	"golang.org/x/text/encoding/internal"
+	"golang.org/x/text/encoding/internal/identifier"
+	"golang.org/x/text/transform"
+)
+
+// ShiftJIS is the Shift JIS encoding, also known as Code Page 932 and
+// Windows-31J.
+var ShiftJIS encoding.Encoding = &shiftJIS
+
+var shiftJIS = internal.Encoding{
+	&internal.SimpleEncoding{shiftJISDecoder{}, shiftJISEncoder{}},
+	"Shift JIS",
+	identifier.ShiftJIS,
+}
+
+type shiftJISDecoder struct{ transform.NopResetter }
+
+func (shiftJISDecoder) Transform(dst, src []byte, atEOF bool) (nDst, nSrc int, err error) {
+	r, size := rune(0), 0
+loop:
+	for ; nSrc < len(src); nSrc += size {
+		switch c0 := src[nSrc]; {
+		case c0 < utf8.RuneSelf:
+			r, size = rune(c0), 1
+
+		case 0xa1 <= c0 && c0 < 0xe0:
+			r, size = rune(c0)+(0xff61-0xa1), 1
+
+		case (0x81 <= c0 && c0 < 0xa0) || (0xe0 <= c0 && c0 < 0xfd):
+			if c0 <= 0x9f {
+				c0 -= 0x70
+			} else {
+				c0 -= 0xb0
+			}
+			c0 = 2*c0 - 0x21
+
+			if nSrc+1 >= len(src) {
+				if !atEOF {
+					err = transform.ErrShortSrc
+					break loop
+				}
+				r, size = '\ufffd', 1
+				goto write
+			}
+			c1 := src[nSrc+1]
+			switch {
+			case c1 < 0x40:
+				r, size = '\ufffd', 1 // c1 is ASCII so output on next round
+				goto write
+			case c1 < 0x7f:
+				c0--
+				c1 -= 0x40
+			case c1 == 0x7f:
+				r, size = '\ufffd', 1 // c1 is ASCII so output on next round
+				goto write
+			case c1 < 0x9f:
+				c0--
+				c1 -= 0x41
+			case c1 < 0xfd:
+				c1 -= 0x9f
+			default:
+				r, size = '\ufffd', 2
+				goto write
+			}
+			r, size = '\ufffd', 2
+			if i := int(c0)*94 + int(c1); i < len(jis0208Decode) {
+				r = rune(jis0208Decode[i])
+				if r == 0 {
+					r = '\ufffd'
+				}
+			}
+
+		case c0 == 0x80:
+			r, size = 0x80, 1
+
+		default:
+			r, size = '\ufffd', 1
+		}
+	write:
+		if nDst+utf8.RuneLen(r) > len(dst) {
+			err = transform.ErrShortDst
+			break loop
+		}
+		nDst += utf8.EncodeRune(dst[nDst:], r)
+	}
+	return nDst, nSrc, err
+}
+
+type shiftJISEncoder struct{ transform.NopResetter }
+
+func (shiftJISEncoder) Transform(dst, src []byte, atEOF bool) (nDst, nSrc int, err error) {
+	r, size := rune(0), 0
+loop:
+	for ; nSrc < len(src); nSrc += size {
+		r = rune(src[nSrc])
+
+		// Decode a 1-byte rune.
+		if r < utf8.RuneSelf {
+			size = 1
+
+		} else {
+			// Decode a multi-byte rune.
+			r, size = utf8.DecodeRune(src[nSrc:])
+			if size == 1 {
+				// All valid runes of size 1 (those below utf8.RuneSelf) were
+				// handled above. We have invalid UTF-8 or we haven't seen the
+				// full character yet.
+				if !atEOF && !utf8.FullRune(src[nSrc:]) {
+					err = transform.ErrShortSrc
+					break loop
+				}
+			}
+
+			// func init checks that the switch covers all tables.
+			switch {
+			case encode0Low <= r && r < encode0High:
+				if r = rune(encode0[r-encode0Low]); r>>tableShift == jis0208 {
+					goto write2
+				}
+			case encode1Low <= r && r < encode1High:
+				if r = rune(encode1[r-encode1Low]); r>>tableShift == jis0208 {
+					goto write2
+				}
+			case encode2Low <= r && r < encode2High:
+				if r = rune(encode2[r-encode2Low]); r>>tableShift == jis0208 {
+					goto write2
+				}
+			case encode3Low <= r && r < encode3High:
+				if r = rune(encode3[r-encode3Low]); r>>tableShift == jis0208 {
+					goto write2
+				}
+			case encode4Low <= r && r < encode4High:
+				if r = rune(encode4[r-encode4Low]); r>>tableShift == jis0208 {
+					goto write2
+				}
+			case encode5Low <= r && r < encode5High:
+				if 0xff61 <= r && r < 0xffa0 {
+					r -= 0xff61 - 0xa1
+					goto write1
+				}
+				if r = rune(encode5[r-encode5Low]); r>>tableShift == jis0208 {
+					goto write2
+				}
+			}
+			err = internal.ErrASCIIReplacement
+			break
+		}
+
+	write1:
+		if nDst >= len(dst) {
+			err = transform.ErrShortDst
+			break
+		}
+		dst[nDst] = uint8(r)
+		nDst++
+		continue
+
+	write2:
+		j1 := uint8(r>>codeShift) & codeMask
+		j2 := uint8(r) & codeMask
+		if nDst+2 > len(dst) {
+			err = transform.ErrShortDst
+			break loop
+		}
+		if j1 <= 61 {
+			dst[nDst+0] = 129 + j1/2
+		} else {
+			dst[nDst+0] = 193 + j1/2
+		}
+		if j1&1 == 0 {
+			dst[nDst+1] = j2 + j2/63 + 64
+		} else {
+			dst[nDst+1] = j2 + 159
+		}
+		nDst += 2
+		continue
+	}
+	return nDst, nSrc, err
+}