diff options
author | Péter Szilágyi <peterke@gmail.com> | 2016-10-29 01:05:01 +0800 |
---|---|---|
committer | Felix Lange <fjl@twurst.com> | 2016-10-29 01:05:01 +0800 |
commit | 289b30715d097edafd5562f66cb3567a70b2d330 (patch) | |
tree | 7eaaa6da97c84727469303b986e364606ece57ce /vendor/golang.org/x/net/html/charset/charset.go | |
parent | 77703045765343c489ded2f43e3ed0f332c5f148 (diff) | |
download | dexon-289b30715d097edafd5562f66cb3567a70b2d330.tar dexon-289b30715d097edafd5562f66cb3567a70b2d330.tar.gz dexon-289b30715d097edafd5562f66cb3567a70b2d330.tar.bz2 dexon-289b30715d097edafd5562f66cb3567a70b2d330.tar.lz dexon-289b30715d097edafd5562f66cb3567a70b2d330.tar.xz dexon-289b30715d097edafd5562f66cb3567a70b2d330.tar.zst dexon-289b30715d097edafd5562f66cb3567a70b2d330.zip |
Godeps, vendor: convert dependency management to trash (#3198)
This commit converts the dependency management from Godeps to the vendor
folder, also switching the tool from godep to trash. Since the upstream tool
lacks a few features proposed via a few PRs, until those PRs are merged in
(if), use github.com/karalabe/trash.
You can update dependencies via trash --update.
All dependencies have been updated to their latest version.
Parts of the build system are reworked to drop old notions of Godeps and
invocation of the go vet command so that it doesn't run against the vendor
folder, as that will just blow up during vetting.
The conversion drops OpenCL (and hence GPU mining support) from ethash and our
codebase. The short reasoning is that there's noone to maintain and having
opencl libs in our deps messes up builds as go install ./... tries to build
them, failing with unsatisfied link errors for the C OpenCL deps.
golang.org/x/net/context is not vendored in. We expect it to be fetched by the
user (i.e. using go get). To keep ci.go builds reproducible the package is
"vendored" in build/_vendor.
Diffstat (limited to 'vendor/golang.org/x/net/html/charset/charset.go')
-rw-r--r-- | vendor/golang.org/x/net/html/charset/charset.go | 257 |
1 files changed, 257 insertions, 0 deletions
diff --git a/vendor/golang.org/x/net/html/charset/charset.go b/vendor/golang.org/x/net/html/charset/charset.go new file mode 100644 index 000000000..13bed1599 --- /dev/null +++ b/vendor/golang.org/x/net/html/charset/charset.go @@ -0,0 +1,257 @@ +// 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 charset provides common text encodings for HTML documents. +// +// The mapping from encoding labels to encodings is defined at +// https://encoding.spec.whatwg.org/. +package charset // import "golang.org/x/net/html/charset" + +import ( + "bytes" + "fmt" + "io" + "mime" + "strings" + "unicode/utf8" + + "golang.org/x/net/html" + "golang.org/x/text/encoding" + "golang.org/x/text/encoding/charmap" + "golang.org/x/text/encoding/htmlindex" + "golang.org/x/text/transform" +) + +// Lookup returns the encoding with the specified label, and its canonical +// name. It returns nil and the empty string if label is not one of the +// standard encodings for HTML. Matching is case-insensitive and ignores +// leading and trailing whitespace. Encoders will use HTML escape sequences for +// runes that are not supported by the character set. +func Lookup(label string) (e encoding.Encoding, name string) { + e, err := htmlindex.Get(label) + if err != nil { + return nil, "" + } + name, _ = htmlindex.Name(e) + return &htmlEncoding{e}, name +} + +type htmlEncoding struct{ encoding.Encoding } + +func (h *htmlEncoding) NewEncoder() *encoding.Encoder { + // HTML requires a non-terminating legacy encoder. We use HTML escapes to + // substitute unsupported code points. + return encoding.HTMLEscapeUnsupported(h.Encoding.NewEncoder()) +} + +// DetermineEncoding determines the encoding of an HTML document by examining +// up to the first 1024 bytes of content and the declared Content-Type. +// +// See http://www.whatwg.org/specs/web-apps/current-work/multipage/parsing.html#determining-the-character-encoding +func DetermineEncoding(content []byte, contentType string) (e encoding.Encoding, name string, certain bool) { + if len(content) > 1024 { + content = content[:1024] + } + + for _, b := range boms { + if bytes.HasPrefix(content, b.bom) { + e, name = Lookup(b.enc) + return e, name, true + } + } + + if _, params, err := mime.ParseMediaType(contentType); err == nil { + if cs, ok := params["charset"]; ok { + if e, name = Lookup(cs); e != nil { + return e, name, true + } + } + } + + if len(content) > 0 { + e, name = prescan(content) + if e != nil { + return e, name, false + } + } + + // Try to detect UTF-8. + // First eliminate any partial rune at the end. + for i := len(content) - 1; i >= 0 && i > len(content)-4; i-- { + b := content[i] + if b < 0x80 { + break + } + if utf8.RuneStart(b) { + content = content[:i] + break + } + } + hasHighBit := false + for _, c := range content { + if c >= 0x80 { + hasHighBit = true + break + } + } + if hasHighBit && utf8.Valid(content) { + return encoding.Nop, "utf-8", false + } + + // TODO: change default depending on user's locale? + return charmap.Windows1252, "windows-1252", false +} + +// NewReader returns an io.Reader that converts the content of r to UTF-8. +// It calls DetermineEncoding to find out what r's encoding is. +func NewReader(r io.Reader, contentType string) (io.Reader, error) { + preview := make([]byte, 1024) + n, err := io.ReadFull(r, preview) + switch { + case err == io.ErrUnexpectedEOF: + preview = preview[:n] + r = bytes.NewReader(preview) + case err != nil: + return nil, err + default: + r = io.MultiReader(bytes.NewReader(preview), r) + } + + if e, _, _ := DetermineEncoding(preview, contentType); e != encoding.Nop { + r = transform.NewReader(r, e.NewDecoder()) + } + return r, nil +} + +// NewReaderLabel returns a reader that converts from the specified charset to +// UTF-8. It uses Lookup to find the encoding that corresponds to label, and +// returns an error if Lookup returns nil. It is suitable for use as +// encoding/xml.Decoder's CharsetReader function. +func NewReaderLabel(label string, input io.Reader) (io.Reader, error) { + e, _ := Lookup(label) + if e == nil { + return nil, fmt.Errorf("unsupported charset: %q", label) + } + return transform.NewReader(input, e.NewDecoder()), nil +} + +func prescan(content []byte) (e encoding.Encoding, name string) { + z := html.NewTokenizer(bytes.NewReader(content)) + for { + switch z.Next() { + case html.ErrorToken: + return nil, "" + + case html.StartTagToken, html.SelfClosingTagToken: + tagName, hasAttr := z.TagName() + if !bytes.Equal(tagName, []byte("meta")) { + continue + } + attrList := make(map[string]bool) + gotPragma := false + + const ( + dontKnow = iota + doNeedPragma + doNotNeedPragma + ) + needPragma := dontKnow + + name = "" + e = nil + for hasAttr { + var key, val []byte + key, val, hasAttr = z.TagAttr() + ks := string(key) + if attrList[ks] { + continue + } + attrList[ks] = true + for i, c := range val { + if 'A' <= c && c <= 'Z' { + val[i] = c + 0x20 + } + } + + switch ks { + case "http-equiv": + if bytes.Equal(val, []byte("content-type")) { + gotPragma = true + } + + case "content": + if e == nil { + name = fromMetaElement(string(val)) + if name != "" { + e, name = Lookup(name) + if e != nil { + needPragma = doNeedPragma + } + } + } + + case "charset": + e, name = Lookup(string(val)) + needPragma = doNotNeedPragma + } + } + + if needPragma == dontKnow || needPragma == doNeedPragma && !gotPragma { + continue + } + + if strings.HasPrefix(name, "utf-16") { + name = "utf-8" + e = encoding.Nop + } + + if e != nil { + return e, name + } + } + } +} + +func fromMetaElement(s string) string { + for s != "" { + csLoc := strings.Index(s, "charset") + if csLoc == -1 { + return "" + } + s = s[csLoc+len("charset"):] + s = strings.TrimLeft(s, " \t\n\f\r") + if !strings.HasPrefix(s, "=") { + continue + } + s = s[1:] + s = strings.TrimLeft(s, " \t\n\f\r") + if s == "" { + return "" + } + if q := s[0]; q == '"' || q == '\'' { + s = s[1:] + closeQuote := strings.IndexRune(s, rune(q)) + if closeQuote == -1 { + return "" + } + return s[:closeQuote] + } + + end := strings.IndexAny(s, "; \t\n\f\r") + if end == -1 { + end = len(s) + } + return s[:end] + } + return "" +} + +var boms = []struct { + bom []byte + enc string +}{ + {[]byte{0xfe, 0xff}, "utf-16be"}, + {[]byte{0xff, 0xfe}, "utf-16le"}, + {[]byte{0xef, 0xbb, 0xbf}, "utf-8"}, +} |