diff options
author | Hyeseong Kim <cometkim.kr@gmail.com> | 2018-05-01 01:54:11 +0900 |
---|---|---|
committer | Christopher Speller <crspeller@gmail.com> | 2018-04-30 09:54:11 -0700 |
commit | e73f1d73143ebba9c7e80d21c45bba9b61f2611c (patch) | |
tree | e84e85d12308ae5624643ff7768f55be45c3350c /vendor/golang.org/x/text/encoding/htmlindex/htmlindex.go | |
parent | 9c5815ee41f29e27774d17382d9a4bd10d208545 (diff) | |
download | chat-e73f1d73143ebba9c7e80d21c45bba9b61f2611c.tar.gz chat-e73f1d73143ebba9c7e80d21c45bba9b61f2611c.tar.bz2 chat-e73f1d73143ebba9c7e80d21c45bba9b61f2611c.zip |
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
Diffstat (limited to 'vendor/golang.org/x/text/encoding/htmlindex/htmlindex.go')
-rw-r--r-- | vendor/golang.org/x/text/encoding/htmlindex/htmlindex.go | 86 |
1 files changed, 86 insertions, 0 deletions
diff --git a/vendor/golang.org/x/text/encoding/htmlindex/htmlindex.go b/vendor/golang.org/x/text/encoding/htmlindex/htmlindex.go new file mode 100644 index 000000000..bdc7d15dd --- /dev/null +++ b/vendor/golang.org/x/text/encoding/htmlindex/htmlindex.go @@ -0,0 +1,86 @@ +// Copyright 2015 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. + +//go:generate go run gen.go + +// Package htmlindex maps character set encoding names to Encodings as +// recommended by the W3C for use in HTML 5. See http://www.w3.org/TR/encoding. +package htmlindex + +// TODO: perhaps have a "bare" version of the index (used by this package) that +// is not pre-loaded with all encodings. Global variables in encodings prevent +// the linker from being able to purge unneeded tables. This means that +// referencing all encodings, as this package does for the default index, links +// in all encodings unconditionally. +// +// This issue can be solved by either solving the linking issue (see +// https://github.com/golang/go/issues/6330) or refactoring the encoding tables +// (e.g. moving the tables to internal packages that do not use global +// variables). + +// TODO: allow canonicalizing names + +import ( + "errors" + "strings" + "sync" + + "golang.org/x/text/encoding" + "golang.org/x/text/encoding/internal/identifier" + "golang.org/x/text/language" +) + +var ( + errInvalidName = errors.New("htmlindex: invalid encoding name") + errUnknown = errors.New("htmlindex: unknown Encoding") + errUnsupported = errors.New("htmlindex: this encoding is not supported") +) + +var ( + matcherOnce sync.Once + matcher language.Matcher +) + +// LanguageDefault returns the canonical name of the default encoding for a +// given language. +func LanguageDefault(tag language.Tag) string { + matcherOnce.Do(func() { + tags := []language.Tag{} + for _, t := range strings.Split(locales, " ") { + tags = append(tags, language.MustParse(t)) + } + matcher = language.NewMatcher(tags, language.PreferSameScript(true)) + }) + _, i, _ := matcher.Match(tag) + return canonical[localeMap[i]] // Default is Windows-1252. +} + +// Get returns an Encoding for one of the names listed in +// http://www.w3.org/TR/encoding using the Default Index. Matching is case- +// insensitive. +func Get(name string) (encoding.Encoding, error) { + x, ok := nameMap[strings.ToLower(strings.TrimSpace(name))] + if !ok { + return nil, errInvalidName + } + return encodings[x], nil +} + +// Name reports the canonical name of the given Encoding. It will return +// an error if e is not associated with a supported encoding scheme. +func Name(e encoding.Encoding) (string, error) { + id, ok := e.(identifier.Interface) + if !ok { + return "", errUnknown + } + mib, _ := id.ID() + if mib == 0 { + return "", errUnknown + } + v, ok := mibMap[mib] + if !ok { + return "", errUnsupported + } + return canonical[v], nil +} |