msb-public
/
cloudreve
mirror of https://github.com/cloudreve/Cloudreve
1
0
Code Issues Projects Releases Wiki Activity

Add: internal packages in webdav

Browse Source
pull/247/head
HFO4 5 years ago
parent 327a3c1edf
commit a6d16cc7ba
10 changed files with 7937 additions and 0 deletions
Show Stats Download Patch File Download Diff File

11
pkg/webdav/internal/xml/README
Unescape View File

@ -0,0 +1,11 @@
This is a fork of the encoding/xml package at ca1d6c4, the last commit before
https://go.googlesource.com/go/+/c0d6d33 "encoding/xml: restore Go 1.4 name
space behavior" made late in the lead-up to the Go 1.5 release.
The list of encoding/xml changes is at
https://go.googlesource.com/go/+log/master/src/encoding/xml
This fork is temporary, and I (nigeltao) expect to revert it after Go 1.6 is
released.
See http://golang.org/issue/11841

56
pkg/webdav/internal/xml/atom_test.go
Unescape View File

@ -0,0 +1,56 @@
// Copyright 2011 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 xml
import "time"
var atomValue = &Feed{
XMLName: Name{"http://www.w3.org/2005/Atom", "feed"},
Title: "Example Feed",
Link: []Link{{Href: "http://example.org/"}},
Updated: ParseTime("2003-12-13T18:30:02Z"),
Author: Person{Name: "John Doe"},
Id: "urn:uuid:60a76c80-d399-11d9-b93C-0003939e0af6",
Entry: []Entry{
{
Title: "Atom-Powered Robots Run Amok",
Link: []Link{{Href: "http://example.org/2003/12/13/atom03"}},
Id: "urn:uuid:1225c695-cfb8-4ebb-aaaa-80da344efa6a",
Updated: ParseTime("2003-12-13T18:30:02Z"),
Summary: NewText("Some text."),
},
},
}
var atomXml = `` +
`<feed xmlns="http://www.w3.org/2005/Atom" updated="2003-12-13T18:30:02Z">` +
`<title>Example Feed</title>` +
`<id>urn:uuid:60a76c80-d399-11d9-b93C-0003939e0af6</id>` +
`<link href="http://example.org/"></link>` +
`<author><name>John Doe</name><uri></uri><email></email></author>` +
`<entry>` +
`<title>Atom-Powered Robots Run Amok</title>` +
`<id>urn:uuid:1225c695-cfb8-4ebb-aaaa-80da344efa6a</id>` +
`<link href="http://example.org/2003/12/13/atom03"></link>` +
`<updated>2003-12-13T18:30:02Z</updated>` +
`<author><name></name><uri></uri><email></email></author>` +
`<summary>Some text.</summary>` +
`</entry>` +
`</feed>`
func ParseTime(str string) time.Time {
t, err := time.Parse(time.RFC3339, str)
if err != nil {
panic(err)
}
return t
}
func NewText(text string) Text {
return Text{
Body: text,
}
}

151
pkg/webdav/internal/xml/example_test.go
Unescape View File

@ -0,0 +1,151 @@
// Copyright 2012 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 xml_test
import (
"encoding/xml"
"fmt"
"os"
)
func ExampleMarshalIndent() {
type Address struct {
City, State string
}
type Person struct {
XMLName xml.Name `xml:"person"`
Id int `xml:"id,attr"`
FirstName string `xml:"name>first"`
LastName string `xml:"name>last"`
Age int `xml:"age"`
Height float32 `xml:"height,omitempty"`
Married bool
Address
Comment string `xml:",comment"`
}
v := &Person{Id: 13, FirstName: "John", LastName: "Doe", Age: 42}
v.Comment = " Need more details. "
v.Address = Address{"Hanga Roa", "Easter Island"}
output, err := xml.MarshalIndent(v, " ", " ")
if err != nil {
fmt.Printf("error: %v\n", err)
}
os.Stdout.Write(output)
// Output:
// <person id="13">
// <name>
// <first>John</first>
// <last>Doe</last>
// </name>
// <age>42</age>
// <Married>false</Married>
// <City>Hanga Roa</City>
// <State>Easter Island</State>
// <!-- Need more details. -->
// </person>
}
func ExampleEncoder() {
type Address struct {
City, State string
}
type Person struct {
XMLName xml.Name `xml:"person"`
Id int `xml:"id,attr"`
FirstName string `xml:"name>first"`
LastName string `xml:"name>last"`
Age int `xml:"age"`
Height float32 `xml:"height,omitempty"`
Married bool
Address
Comment string `xml:",comment"`
}
v := &Person{Id: 13, FirstName: "John", LastName: "Doe", Age: 42}
v.Comment = " Need more details. "
v.Address = Address{"Hanga Roa", "Easter Island"}
enc := xml.NewEncoder(os.Stdout)
enc.Indent(" ", " ")
if err := enc.Encode(v); err != nil {
fmt.Printf("error: %v\n", err)
}
// Output:
// <person id="13">
// <name>
// <first>John</first>
// <last>Doe</last>
// </name>
// <age>42</age>
// <Married>false</Married>
// <City>Hanga Roa</City>
// <State>Easter Island</State>
// <!-- Need more details. -->
// </person>
}
// This example demonstrates unmarshaling an XML excerpt into a value with
// some preset fields. Note that the Phone field isn't modified and that
// the XML <Company> element is ignored. Also, the Groups field is assigned
// considering the element path provided in its tag.
func ExampleUnmarshal() {
type Email struct {
Where string `xml:"where,attr"`
Addr string
}
type Address struct {
City, State string
}
type Result struct {
XMLName xml.Name `xml:"Person"`
Name string `xml:"FullName"`
Phone string
Email []Email
Groups []string `xml:"Group>Value"`
Address
}
v := Result{Name: "none", Phone: "none"}
data := `
<Person>
<FullName>Grace R. Emlin</FullName>
<Company>Example Inc.</Company>
<Email where="home">
<Addr>gre@example.com</Addr>
</Email>
<Email where='work'>
<Addr>gre@work.com</Addr>
</Email>
<Group>
<Value>Friends</Value>
<Value>Squash</Value>
</Group>
<City>Hanga Roa</City>
<State>Easter Island</State>
</Person>
`
err := xml.Unmarshal([]byte(data), &v)
if err != nil {
fmt.Printf("error: %v", err)
return
}
fmt.Printf("XMLName: %#v\n", v.XMLName)
fmt.Printf("Name: %q\n", v.Name)
fmt.Printf("Phone: %q\n", v.Phone)
fmt.Printf("Email: %v\n", v.Email)
fmt.Printf("Groups: %v\n", v.Groups)
fmt.Printf("Address: %v\n", v.Address)
// Output:
// XMLName: xml.Name{Space:"", Local:"Person"}
// Name: "Grace R. Emlin"
// Phone: "none"
// Email: [{home gre@example.com} {work gre@work.com}]
// Groups: [Friends Squash]
// Address: {Hanga Roa Easter Island}
}

1223
pkg/webdav/internal/xml/marshal.go
View File

File diff suppressed because it is too large Load Diff

1939
pkg/webdav/internal/xml/marshal_test.go
View File

File diff suppressed because it is too large Load Diff

692
pkg/webdav/internal/xml/read.go
Unescape View File

@ -0,0 +1,692 @@
// Copyright 2009 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 xml
import (
"bytes"
"encoding"
"errors"
"fmt"
"reflect"
"strconv"
"strings"
)
// BUG(rsc): Mapping between XML elements and data structures is inherently flawed:
// an XML element is an order-dependent collection of anonymous
// values, while a data structure is an order-independent collection
// of named values.
// See package json for a textual representation more suitable
// to data structures.
// Unmarshal parses the XML-encoded data and stores the result in
// the value pointed to by v, which must be an arbitrary struct,
// slice, or string. Well-formed data that does not fit into v is
// discarded.
//
// Because Unmarshal uses the reflect package, it can only assign
// to exported (upper case) fields. Unmarshal uses a case-sensitive
// comparison to match XML element names to tag values and struct
// field names.
//
// Unmarshal maps an XML element to a struct using the following rules.
// In the rules, the tag of a field refers to the value associated with the
// key 'xml' in the struct field's tag (see the example above).
//
// * If the struct has a field of type []byte or string with tag
// ",innerxml", Unmarshal accumulates the raw XML nested inside the
// element in that field. The rest of the rules still apply.
//
// * If the struct has a field named XMLName of type xml.Name,
// Unmarshal records the element name in that field.
//
// * If the XMLName field has an associated tag of the form
// "name" or "namespace-URL name", the XML element must have
// the given name (and, optionally, name space) or else Unmarshal
// returns an error.
//
// * If the XML element has an attribute whose name matches a
// struct field name with an associated tag containing ",attr" or
// the explicit name in a struct field tag of the form "name,attr",
// Unmarshal records the attribute value in that field.
//
// * If the XML element contains character data, that data is
// accumulated in the first struct field that has tag ",chardata".
// The struct field may have type []byte or string.
// If there is no such field, the character data is discarded.
//
// * If the XML element contains comments, they are accumulated in
// the first struct field that has tag ",comment". The struct
// field may have type []byte or string. If there is no such
// field, the comments are discarded.
//
// * If the XML element contains a sub-element whose name matches
// the prefix of a tag formatted as "a" or "a>b>c", unmarshal
// will descend into the XML structure looking for elements with the
// given names, and will map the innermost elements to that struct
// field. A tag starting with ">" is equivalent to one starting
// with the field name followed by ">".
//
// * If the XML element contains a sub-element whose name matches
// a struct field's XMLName tag and the struct field has no
// explicit name tag as per the previous rule, unmarshal maps
// the sub-element to that struct field.
//
// * If the XML element contains a sub-element whose name matches a
// field without any mode flags (",attr", ",chardata", etc), Unmarshal
// maps the sub-element to that struct field.
//
// * If the XML element contains a sub-element that hasn't matched any
// of the above rules and the struct has a field with tag ",any",
// unmarshal maps the sub-element to that struct field.
//
// * An anonymous struct field is handled as if the fields of its
// value were part of the outer struct.
//
// * A struct field with tag "-" is never unmarshalled into.
//
// Unmarshal maps an XML element to a string or []byte by saving the
// concatenation of that element's character data in the string or
// []byte. The saved []byte is never nil.
//
// Unmarshal maps an attribute value to a string or []byte by saving
// the value in the string or slice.
//
// Unmarshal maps an XML element to a slice by extending the length of
// the slice and mapping the element to the newly created value.
//
// Unmarshal maps an XML element or attribute value to a bool by
// setting it to the boolean value represented by the string.
//
// Unmarshal maps an XML element or attribute value to an integer or
// floating-point field by setting the field to the result of
// interpreting the string value in decimal. There is no check for
// overflow.
//
// Unmarshal maps an XML element to an xml.Name by recording the
// element name.
//
// Unmarshal maps an XML element to a pointer by setting the pointer
// to a freshly allocated value and then mapping the element to that value.
//
func Unmarshal(data []byte, v interface{}) error {
return NewDecoder(bytes.NewReader(data)).Decode(v)
}
// Decode works like xml.Unmarshal, except it reads the decoder
// stream to find the start element.
func (d *Decoder) Decode(v interface{}) error {
return d.DecodeElement(v, nil)
}
// DecodeElement works like xml.Unmarshal except that it takes
// a pointer to the start XML element to decode into v.
// It is useful when a client reads some raw XML tokens itself
// but also wants to defer to Unmarshal for some elements.
func (d *Decoder) DecodeElement(v interface{}, start *StartElement) error {
val := reflect.ValueOf(v)
if val.Kind() != reflect.Ptr {
return errors.New("non-pointer passed to Unmarshal")
}
return d.unmarshal(val.Elem(), start)
}
// An UnmarshalError represents an error in the unmarshalling process.
type UnmarshalError string
func (e UnmarshalError) Error() string { return string(e) }
// Unmarshaler is the interface implemented by objects that can unmarshal
// an XML element description of themselves.
//
// UnmarshalXML decodes a single XML element
// beginning with the given start element.
// If it returns an error, the outer call to Unmarshal stops and
// returns that error.
// UnmarshalXML must consume exactly one XML element.
// One common implementation strategy is to unmarshal into
// a separate value with a layout matching the expected XML
// using d.DecodeElement, and then to copy the data from
// that value into the receiver.
// Another common strategy is to use d.Token to process the
// XML object one token at a time.
// UnmarshalXML may not use d.RawToken.
type Unmarshaler interface {
UnmarshalXML(d *Decoder, start StartElement) error
}
// UnmarshalerAttr is the interface implemented by objects that can unmarshal
// an XML attribute description of themselves.
//
// UnmarshalXMLAttr decodes a single XML attribute.
// If it returns an error, the outer call to Unmarshal stops and
// returns that error.
// UnmarshalXMLAttr is used only for struct fields with the
// "attr" option in the field tag.
type UnmarshalerAttr interface {
UnmarshalXMLAttr(attr Attr) error
}
// receiverType returns the receiver type to use in an expression like "%s.MethodName".
func receiverType(val interface{}) string {
t := reflect.TypeOf(val)
if t.Name() != "" {
return t.String()
}
return "(" + t.String() + ")"
}
// unmarshalInterface unmarshals a single XML element into val.
// start is the opening tag of the element.
func (p *Decoder) unmarshalInterface(val Unmarshaler, start *StartElement) error {
// Record that decoder must stop at end tag corresponding to start.
p.pushEOF()
p.unmarshalDepth++
err := val.UnmarshalXML(p, *start)
p.unmarshalDepth--
if err != nil {
p.popEOF()
return err
}
if !p.popEOF() {
return fmt.Errorf("xml: %s.UnmarshalXML did not consume entire <%s> element", receiverType(val), start.Name.Local)
}
return nil
}
// unmarshalTextInterface unmarshals a single XML element into val.
// The chardata contained in the element (but not its children)
// is passed to the text unmarshaler.
func (p *Decoder) unmarshalTextInterface(val encoding.TextUnmarshaler, start *StartElement) error {
var buf []byte
depth := 1
for depth > 0 {
t, err := p.Token()
if err != nil {
return err
}
switch t := t.(type) {
case CharData:
if depth == 1 {
buf = append(buf, t...)
}
case StartElement:
depth++
case EndElement:
depth--
}
}
return val.UnmarshalText(buf)
}
// unmarshalAttr unmarshals a single XML attribute into val.
func (p *Decoder) unmarshalAttr(val reflect.Value, attr Attr) error {
if val.Kind() == reflect.Ptr {
if val.IsNil() {
val.Set(reflect.New(val.Type().Elem()))
}
val = val.Elem()
}
if val.CanInterface() && val.Type().Implements(unmarshalerAttrType) {
// This is an unmarshaler with a non-pointer receiver,
// so it's likely to be incorrect, but we do what we're told.
return val.Interface().(UnmarshalerAttr).UnmarshalXMLAttr(attr)
}
if val.CanAddr() {
pv := val.Addr()
if pv.CanInterface() && pv.Type().Implements(unmarshalerAttrType) {
return pv.Interface().(UnmarshalerAttr).UnmarshalXMLAttr(attr)
}
}
// Not an UnmarshalerAttr; try encoding.TextUnmarshaler.
if val.CanInterface() && val.Type().Implements(textUnmarshalerType) {
// This is an unmarshaler with a non-pointer receiver,
// so it's likely to be incorrect, but we do what we're told.
return val.Interface().(encoding.TextUnmarshaler).UnmarshalText([]byte(attr.Value))
}
if val.CanAddr() {
pv := val.Addr()
if pv.CanInterface() && pv.Type().Implements(textUnmarshalerType) {
return pv.Interface().(encoding.TextUnmarshaler).UnmarshalText([]byte(attr.Value))
}
}
copyValue(val, []byte(attr.Value))
return nil
}
var (
unmarshalerType = reflect.TypeOf((*Unmarshaler)(nil)).Elem()
unmarshalerAttrType = reflect.TypeOf((*UnmarshalerAttr)(nil)).Elem()
textUnmarshalerType = reflect.TypeOf((*encoding.TextUnmarshaler)(nil)).Elem()
)
// Unmarshal a single XML element into val.
func (p *Decoder) unmarshal(val reflect.Value, start *StartElement) error {
// Find start element if we need it.
if start == nil {
for {
tok, err := p.Token()
if err != nil {
return err
}
if t, ok := tok.(StartElement); ok {
start = &t
break
}
}
}
// Load value from interface, but only if the result will be
// usefully addressable.
if val.Kind() == reflect.Interface && !val.IsNil() {
e := val.Elem()
if e.Kind() == reflect.Ptr && !e.IsNil() {
val = e
}
}
if val.Kind() == reflect.Ptr {
if val.IsNil() {
val.Set(reflect.New(val.Type().Elem()))
}
val = val.Elem()
}
if val.CanInterface() && val.Type().Implements(unmarshalerType) {
// This is an unmarshaler with a non-pointer receiver,
// so it's likely to be incorrect, but we do what we're told.
return p.unmarshalInterface(val.Interface().(Unmarshaler), start)
}
if val.CanAddr() {
pv := val.Addr()
if pv.CanInterface() && pv.Type().Implements(unmarshalerType) {
return p.unmarshalInterface(pv.Interface().(Unmarshaler), start)
}
}
if val.CanInterface() && val.Type().Implements(textUnmarshalerType) {
return p.unmarshalTextInterface(val.Interface().(encoding.TextUnmarshaler), start)
}
if val.CanAddr() {
pv := val.Addr()
if pv.CanInterface() && pv.Type().Implements(textUnmarshalerType) {
return p.unmarshalTextInterface(pv.Interface().(encoding.TextUnmarshaler), start)
}
}
var (
data []byte
saveData reflect.Value
comment []byte
saveComment reflect.Value
saveXML reflect.Value
saveXMLIndex int
saveXMLData []byte
saveAny reflect.Value
sv reflect.Value
tinfo *typeInfo
err error
)
switch v := val; v.Kind() {
default:
return errors.New("unknown type " + v.Type().String())
case reflect.Interface:
// TODO: For now, simply ignore the field. In the near
// future we may choose to unmarshal the start
// element on it, if not nil.
return p.Skip()
case reflect.Slice:
typ := v.Type()
if typ.Elem().Kind() == reflect.Uint8 {
// []byte
saveData = v
break
}
// Slice of element values.
// Grow slice.
n := v.Len()
if n >= v.Cap() {
ncap := 2 * n
if ncap < 4 {
ncap = 4
}
new := reflect.MakeSlice(typ, n, ncap)
reflect.Copy(new, v)
v.Set(new)
}
v.SetLen(n + 1)
// Recur to read element into slice.
if err := p.unmarshal(v.Index(n), start); err != nil {
v.SetLen(n)
return err
}
return nil
case reflect.Bool, reflect.Float32, reflect.Float64, reflect.Int, reflect.Int8, reflect.Int16, reflect.Int32, reflect.Int64, reflect.Uint, reflect.Uint8, reflect.Uint16, reflect.Uint32, reflect.Uint64, reflect.Uintptr, reflect.String:
saveData = v
case reflect.Struct:
typ := v.Type()
if typ == nameType {
v.Set(reflect.ValueOf(start.Name))
break
}
sv = v
tinfo, err = getTypeInfo(typ)
if err != nil {
return err
}
// Validate and assign element name.
if tinfo.xmlname != nil {
finfo := tinfo.xmlname
if finfo.name != "" && finfo.name != start.Name.Local {
return UnmarshalError("expected element type <" + finfo.name + "> but have <" + start.Name.Local + ">")
}
if finfo.xmlns != "" && finfo.xmlns != start.Name.Space {
e := "expected element <" + finfo.name + "> in name space " + finfo.xmlns + " but have "
if start.Name.Space == "" {
e += "no name space"
} else {
e += start.Name.Space
}
return UnmarshalError(e)
}
fv := finfo.value(sv)
if _, ok := fv.Interface().(Name); ok {
fv.Set(reflect.ValueOf(start.Name))
}
}
// Assign attributes.
// Also, determine whether we need to save character data or comments.
for i := range tinfo.fields {
finfo := &tinfo.fields[i]
switch finfo.flags & fMode {
case fAttr:
strv := finfo.value(sv)
// Look for attribute.
for _, a := range start.Attr {
if a.Name.Local == finfo.name && (finfo.xmlns == "" || finfo.xmlns == a.Name.Space) {
if err := p.unmarshalAttr(strv, a); err != nil {
return err
}
break
}
}
case fCharData:
if !saveData.IsValid() {
saveData = finfo.value(sv)
}
case fComment:
if !saveComment.IsValid() {
saveComment = finfo.value(sv)
}
case fAny, fAny | fElement:
if !saveAny.IsValid() {
saveAny = finfo.value(sv)
}
case fInnerXml:
if !saveXML.IsValid() {
saveXML = finfo.value(sv)
if p.saved == nil {
saveXMLIndex = 0
p.saved = new(bytes.Buffer)
} else {
saveXMLIndex = p.savedOffset()
}
}
}
}
}
// Find end element.
// Process sub-elements along the way.
Loop:
for {
var savedOffset int
if saveXML.IsValid() {
savedOffset = p.savedOffset()
}
tok, err := p.Token()
if err != nil {
return err
}
switch t := tok.(type) {
case StartElement:
consumed := false
if sv.IsValid() {
consumed, err = p.unmarshalPath(tinfo, sv, nil, &t)
if err != nil {
return err
}
if !consumed && saveAny.IsValid() {
consumed = true
if err := p.unmarshal(saveAny, &t); err != nil {
return err
}
}
}
if !consumed {
if err := p.Skip(); err != nil {
return err
}
}
case EndElement:
if saveXML.IsValid() {
saveXMLData = p.saved.Bytes()[saveXMLIndex:savedOffset]
if saveXMLIndex == 0 {
p.saved = nil
}
}
break Loop
case CharData:
if saveData.IsValid() {
data = append(data, t...)
}
case Comment:
if saveComment.IsValid() {
comment = append(comment, t...)
}
}
}
if saveData.IsValid() && saveData.CanInterface() && saveData.Type().Implements(textUnmarshalerType) {
if err := saveData.Interface().(encoding.TextUnmarshaler).UnmarshalText(data); err != nil {
return err
}
saveData = reflect.Value{}
}
if saveData.IsValid() && saveData.CanAddr() {
pv := saveData.Addr()
if pv.CanInterface() && pv.Type().Implements(textUnmarshalerType) {
if err := pv.Interface().(encoding.TextUnmarshaler).UnmarshalText(data); err != nil {
return err
}
saveData = reflect.Value{}
}
}
if err := copyValue(saveData, data); err != nil {
return err
}
switch t := saveComment; t.Kind() {
case reflect.String:
t.SetString(string(comment))
case reflect.Slice:
t.Set(reflect.ValueOf(comment))
}
switch t := saveXML; t.Kind() {
case reflect.String:
t.SetString(string(saveXMLData))
case reflect.Slice:
t.Set(reflect.ValueOf(saveXMLData))
}
return nil
}
func copyValue(dst reflect.Value, src []byte) (err error) {
dst0 := dst
if dst.Kind() == reflect.Ptr {
if dst.IsNil() {
dst.Set(reflect.New(dst.Type().Elem()))
}
dst = dst.Elem()
}
// Save accumulated data.
switch dst.Kind() {
case reflect.Invalid:
// Probably a comment.
default:
return errors.New("cannot unmarshal into " + dst0.Type().String())
case reflect.Int, reflect.Int8, reflect.Int16, reflect.Int32, reflect.Int64:
itmp, err := strconv.ParseInt(string(src), 10, dst.Type().Bits())
if err != nil {
return err
}
dst.SetInt(itmp)
case reflect.Uint, reflect.Uint8, reflect.Uint16, reflect.Uint32, reflect.Uint64, reflect.Uintptr:
utmp, err := strconv.ParseUint(string(src), 10, dst.Type().Bits())
if err != nil {
return err
}
dst.SetUint(utmp)
case reflect.Float32, reflect.Float64:
ftmp, err := strconv.ParseFloat(string(src), dst.Type().Bits())
if err != nil {
return err
}
dst.SetFloat(ftmp)
case reflect.Bool:
value, err := strconv.ParseBool(strings.TrimSpace(string(src)))
if err != nil {
return err
}
dst.SetBool(value)
case reflect.String:
dst.SetString(string(src))
case reflect.Slice:
if len(src) == 0 {
// non-nil to flag presence
src = []byte{}
}
dst.SetBytes(src)
}
return nil
}
// unmarshalPath walks down an XML structure looking for wanted
// paths, and calls unmarshal on them.
// The consumed result tells whether XML elements have been consumed
// from the Decoder until start's matching end element, or if it's
// still untouched because start is uninteresting for sv's fields.
func (p *Decoder) unmarshalPath(tinfo *typeInfo, sv reflect.Value, parents []string, start *StartElement) (consumed bool, err error) {
recurse := false
Loop:
for i := range tinfo.fields {
finfo := &tinfo.fields[i]
if finfo.flags&fElement == 0 || len(finfo.parents) < len(parents) || finfo.xmlns != "" && finfo.xmlns != start.Name.Space {
continue
}
for j := range parents {
if parents[j] != finfo.parents[j] {
continue Loop
}
}
if len(finfo.parents) == len(parents) && finfo.name == start.Name.Local {
// It's a perfect match, unmarshal the field.
return true, p.unmarshal(finfo.value(sv), start)
}
if len(finfo.parents) > len(parents) && finfo.parents[len(parents)] == start.Name.Local {
// It's a prefix for the field. Break and recurse
// since it's not ok for one field path to be itself
// the prefix for another field path.
recurse = true
// We can reuse the same slice as long as we
// don't try to append to it.
parents = finfo.parents[:len(parents)+1]
break
}
}
if !recurse {
// We have no business with this element.
return false, nil
}
// The element is not a perfect match for any field, but one
// or more fields have the path to this element as a parent
// prefix. Recurse and attempt to match these.
for {
var tok Token
tok, err = p.Token()
if err != nil {
return true, err
}
switch t := tok.(type) {
case StartElement:
consumed2, err := p.unmarshalPath(tinfo, sv, parents, &t)
if err != nil {
return true, err
}
if !consumed2 {
if err := p.Skip(); err != nil {
return true, err
}
}
case EndElement:
return true, nil
}
}
}
// Skip reads tokens until it has consumed the end element
// matching the most recent start element already consumed.
// It recurs if it encounters a start element, so it can be used to
// skip nested structures.
// It returns nil if it finds an end element matching the start
// element; otherwise it returns an error describing the problem.
func (d *Decoder) Skip() error {
for {
tok, err := d.Token()
if err != nil {
return err
}
switch tok.(type) {
case StartElement:
if err := d.Skip(); err != nil {
return err
}
case EndElement:
return nil
}
}
}

744
pkg/webdav/internal/xml/read_test.go
Unescape View File

@ -0,0 +1,744 @@
// Copyright 2009 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 xml
import (
"bytes"
"fmt"
"io"
"reflect"
"strings"
"testing"
"time"
)
// Stripped down Atom feed data structures.
func TestUnmarshalFeed(t *testing.T) {
var f Feed
if err := Unmarshal([]byte(atomFeedString), &f); err != nil {
t.Fatalf("Unmarshal: %s", err)
}
if !reflect.DeepEqual(f, atomFeed) {
t.Fatalf("have %#v\nwant %#v", f, atomFeed)
}
}
// hget http://codereview.appspot.com/rss/mine/rsc
const atomFeedString = `
<?xml version="1.0" encoding="utf-8"?>
<feed xmlns="http://www.w3.org/2005/Atom" xml:lang="en-us" updated="2009-10-04T01:35:58+00:00"><title>Code Review - My issues</title><link href="http://codereview.appspot.com/" rel="alternate"></link><link href="http://codereview.appspot.com/rss/mine/rsc" rel="self"></link><id>http://codereview.appspot.com/</id><author><name>rietveld&lt;&gt;</name></author><entry><title>rietveld: an attempt at pubsubhubbub
</title><link href="http://codereview.appspot.com/126085" rel="alternate"></link><updated>2009-10-04T01:35:58+00:00</updated><author><name>email-address-removed</name></author><id>urn:md5:134d9179c41f806be79b3a5f7877d19a</id><summary type="html">
An attempt at adding pubsubhubbub support to Rietveld.
http://code.google.com/p/pubsubhubbub
http://code.google.com/p/rietveld/issues/detail?id=155
The server side of the protocol is trivial:
1. add a &amp;lt;link rel=&amp;quot;hub&amp;quot; href=&amp;quot;hub-server&amp;quot;&amp;gt; tag to all
feeds that will be pubsubhubbubbed.
2. every time one of those feeds changes, tell the hub
with a simple POST request.
I have tested this by adding debug prints to a local hub
server and checking that the server got the right publish
requests.
I can&amp;#39;t quite get the server to work, but I think the bug
is not in my code. I think that the server expects to be
able to grab the feed and see the feed&amp;#39;s actual URL in
the link rel=&amp;quot;self&amp;quot;, but the default value for that drops
the :port from the URL, and I cannot for the life of me
figure out how to get the Atom generator deep inside
django not to do that, or even where it is doing that,
or even what code is running to generate the Atom feed.
(I thought I knew but I added some assert False statements
and it kept running!)
Ignoring that particular problem, I would appreciate
feedback on the right way to get the two values at
the top of feeds.py marked NOTE(rsc).
</summary></entry><entry><title>rietveld: correct tab handling
</title><link href="http://codereview.appspot.com/124106" rel="alternate"></link><updated>2009-10-03T23:02:17+00:00</updated><author><name>email-address-removed</name></author><id>urn:md5:0a2a4f19bb815101f0ba2904aed7c35a</id><summary type="html">
This fixes the buggy tab rendering that can be seen at
http://codereview.appspot.com/116075/diff/1/2
The fundamental problem was that the tab code was
not being told what column the text began in, so it
didn&amp;#39;t know where to put the tab stops. Another problem
was that some of the code assumed that string byte
offsets were the same as column offsets, which is only
true if there are no tabs.
In the process of fixing this, I cleaned up the arguments
to Fold and ExpandTabs and renamed them Break and
_ExpandTabs so that I could be sure that I found all the
call sites. I also wanted to verify that ExpandTabs was
not being used from outside intra_region_diff.py.
</summary></entry></feed> `
type Feed struct {
XMLName Name `xml:"http://www.w3.org/2005/Atom feed"`
Title string `xml:"title"`
Id string `xml:"id"`
Link []Link `xml:"link"`
Updated time.Time `xml:"updated,attr"`
Author Person `xml:"author"`
Entry []Entry `xml:"entry"`
}
type Entry struct {
Title string `xml:"title"`
Id string `xml:"id"`
Link []Link `xml:"link"`
Updated time.Time `xml:"updated"`
Author Person `xml:"author"`
Summary Text `xml:"summary"`
}
type Link struct {
Rel string `xml:"rel,attr,omitempty"`
Href string `xml:"href,attr"`
}
type Person struct {
Name string `xml:"name"`
URI string `xml:"uri"`
Email string `xml:"email"`
InnerXML string `xml:",innerxml"`
}
type Text struct {
Type string `xml:"type,attr,omitempty"`
Body string `xml:",chardata"`
}
var atomFeed = Feed{
XMLName: Name{"http://www.w3.org/2005/Atom", "feed"},
Title: "Code Review - My issues",
Link: []Link{
{Rel: "alternate", Href: "http://codereview.appspot.com/"},
{Rel: "self", Href: "http://codereview.appspot.com/rss/mine/rsc"},
},
Id: "http://codereview.appspot.com/",
Updated: ParseTime("2009-10-04T01:35:58+00:00"),
Author: Person{
Name: "rietveld<>",
InnerXML: "<name>rietveld&lt;&gt;</name>",
},
Entry: []Entry{
{
Title: "rietveld: an attempt at pubsubhubbub\n",
Link: []Link{
{Rel: "alternate", Href: "http://codereview.appspot.com/126085"},
},
Updated: ParseTime("2009-10-04T01:35:58+00:00"),
Author: Person{
Name: "email-address-removed",
InnerXML: "<name>email-address-removed</name>",
},
Id: "urn:md5:134d9179c41f806be79b3a5f7877d19a",
Summary: Text{
Type: "html",
Body: `
An attempt at adding pubsubhubbub support to Rietveld.
http://code.google.com/p/pubsubhubbub
http://code.google.com/p/rietveld/issues/detail?id=155
The server side of the protocol is trivial:
1. add a &lt;link rel=&quot;hub&quot; href=&quot;hub-server&quot;&gt; tag to all
feeds that will be pubsubhubbubbed.
2. every time one of those feeds changes, tell the hub
with a simple POST request.
I have tested this by adding debug prints to a local hub
server and checking that the server got the right publish
requests.
I can&#39;t quite get the server to work, but I think the bug
is not in my code. I think that the server expects to be
able to grab the feed and see the feed&#39;s actual URL in
the link rel=&quot;self&quot;, but the default value for that drops
the :port from the URL, and I cannot for the life of me
figure out how to get the Atom generator deep inside
django not to do that, or even where it is doing that,
or even what code is running to generate the Atom feed.
(I thought I knew but I added some assert False statements
and it kept running!)
Ignoring that particular problem, I would appreciate
feedback on the right way to get the two values at
the top of feeds.py marked NOTE(rsc).
`,
},
},
{
Title: "rietveld: correct tab handling\n",
Link: []Link{
{Rel: "alternate", Href: "http://codereview.appspot.com/124106"},
},
Updated: ParseTime("2009-10-03T23:02:17+00:00"),
Author: Person{
Name: "email-address-removed",
InnerXML: "<name>email-address-removed</name>",
},
Id: "urn:md5:0a2a4f19bb815101f0ba2904aed7c35a",
Summary: Text{
Type: "html",
Body: `
This fixes the buggy tab rendering that can be seen at
http://codereview.appspot.com/116075/diff/1/2
The fundamental problem was that the tab code was
not being told what column the text began in, so it
didn&#39;t know where to put the tab stops. Another problem
was that some of the code assumed that string byte
offsets were the same as column offsets, which is only
true if there are no tabs.
In the process of fixing this, I cleaned up the arguments
to Fold and ExpandTabs and renamed them Break and
_ExpandTabs so that I could be sure that I found all the
call sites. I also wanted to verify that ExpandTabs was
not being used from outside intra_region_diff.py.
`,
},
},
},
}
const pathTestString = `
<Result>
<Before>1</Before>
<Items>
<Item1>
<Value>A</Value>
</Item1>
<Item2>
<Value>B</Value>
</Item2>
<Item1>
<Value>C</Value>
<Value>D</Value>
</Item1>
<_>
<Value>E</Value>
</_>
</Items>
<After>2</After>
</Result>
`
type PathTestItem struct {
Value string
}
type PathTestA struct {
Items []PathTestItem `xml:">Item1"`
Before, After string
}
type PathTestB struct {
Other []PathTestItem `xml:"Items>Item1"`
Before, After string
}
type PathTestC struct {
Values1 []string `xml:"Items>Item1>Value"`
Values2 []string `xml:"Items>Item2>Value"`
Before, After string
}
type PathTestSet struct {
Item1 []PathTestItem
}
type PathTestD struct {
Other PathTestSet `xml:"Items"`
Before, After string
}
type PathTestE struct {
Underline string `xml:"Items>_>Value"`
Before, After string
}
var pathTests = []interface{}{
&PathTestA{Items: []PathTestItem{{"A"}, {"D"}}, Before: "1", After: "2"},
&PathTestB{Other: []PathTestItem{{"A"}, {"D"}}, Before: "1", After: "2"},
&PathTestC{Values1: []string{"A", "C", "D"}, Values2: []string{"B"}, Before: "1", After: "2"},
&PathTestD{Other: PathTestSet{Item1: []PathTestItem{{"A"}, {"D"}}}, Before: "1", After: "2"},
&PathTestE{Underline: "E", Before: "1", After: "2"},
}
func TestUnmarshalPaths(t *testing.T) {
for _, pt := range pathTests {
v := reflect.New(reflect.TypeOf(pt).Elem()).Interface()
if err := Unmarshal([]byte(pathTestString), v); err != nil {
t.Fatalf("Unmarshal: %s", err)
}
if !reflect.DeepEqual(v, pt) {
t.Fatalf("have %#v\nwant %#v", v, pt)
}
}
}
type BadPathTestA struct {
First string `xml:"items>item1"`
Other string `xml:"items>item2"`
Second string `xml:"items"`
}
type BadPathTestB struct {
Other string `xml:"items>item2>value"`
First string `xml:"items>item1"`
Second string `xml:"items>item1>value"`
}
type BadPathTestC struct {
First string
Second string `xml:"First"`
}
type BadPathTestD struct {
BadPathEmbeddedA
BadPathEmbeddedB
}
type BadPathEmbeddedA struct {
First string
}
type BadPathEmbeddedB struct {
Second string `xml:"First"`
}
var badPathTests = []struct {
v, e interface{}
}{
{&BadPathTestA{}, &TagPathError{reflect.TypeOf(BadPathTestA{}), "First", "items>item1", "Second", "items"}},
{&BadPathTestB{}, &TagPathError{reflect.TypeOf(BadPathTestB{}), "First", "items>item1", "Second", "items>item1>value"}},
{&BadPathTestC{}, &TagPathError{reflect.TypeOf(BadPathTestC{}), "First", "", "Second", "First"}},
{&BadPathTestD{}, &TagPathError{reflect.TypeOf(BadPathTestD{}), "First", "", "Second", "First"}},
}
func TestUnmarshalBadPaths(t *testing.T) {
for _, tt := range badPathTests {
err := Unmarshal([]byte(pathTestString), tt.v)
if !reflect.DeepEqual(err, tt.e) {
t.Fatalf("Unmarshal with %#v didn't fail properly:\nhave %#v,\nwant %#v", tt.v, err, tt.e)
}
}
}
const OK = "OK"
const withoutNameTypeData = `
<?xml version="1.0" charset="utf-8"?>
<Test3 Attr="OK" />`
type TestThree struct {
XMLName Name `xml:"Test3"`
Attr string `xml:",attr"`
}
func TestUnmarshalWithoutNameType(t *testing.T) {
var x TestThree
if err := Unmarshal([]byte(withoutNameTypeData), &x); err != nil {
t.Fatalf("Unmarshal: %s", err)
}
if x.Attr != OK {
t.Fatalf("have %v\nwant %v", x.Attr, OK)
}
}
func TestUnmarshalAttr(t *testing.T) {
type ParamVal struct {
Int int `xml:"int,attr"`
}
type ParamPtr struct {
Int *int `xml:"int,attr"`
}
type ParamStringPtr struct {
Int *string `xml:"int,attr"`
}
x := []byte(`<Param int="1" />`)
p1 := &ParamPtr{}
if err := Unmarshal(x, p1); err != nil {
t.Fatalf("Unmarshal: %s", err)
}
if p1.Int == nil {
t.Fatalf("Unmarshal failed in to *int field")
} else if *p1.Int != 1 {
t.Fatalf("Unmarshal with %s failed:\nhave %#v,\n want %#v", x, p1.Int, 1)
}
p2 := &ParamVal{}
if err := Unmarshal(x, p2); err != nil {
t.Fatalf("Unmarshal: %s", err)
}
if p2.Int != 1 {
t.Fatalf("Unmarshal with %s failed:\nhave %#v,\n want %#v", x, p2.Int, 1)
}
p3 := &ParamStringPtr{}
if err := Unmarshal(x, p3); err != nil {
t.Fatalf("Unmarshal: %s", err)
}
if p3.Int == nil {
t.Fatalf("Unmarshal failed in to *string field")
} else if *p3.Int != "1" {
t.Fatalf("Unmarshal with %s failed:\nhave %#v,\n want %#v", x, p3.Int, 1)
}
}
type Tables struct {
HTable string `xml:"http://www.w3.org/TR/html4/ table"`
FTable string `xml:"http://www.w3schools.com/furniture table"`
}
var tables = []struct {
xml string
tab Tables
ns string
}{
{
xml: `<Tables>` +
`<table xmlns="http://www.w3.org/TR/html4/">hello</table>` +
`<table xmlns="http://www.w3schools.com/furniture">world</table>` +
`</Tables>`,
tab: Tables{"hello", "world"},
},
{
xml: `<Tables>` +
`<table xmlns="http://www.w3schools.com/furniture">world</table>` +
`<table xmlns="http://www.w3.org/TR/html4/">hello</table>` +
`</Tables>`,
tab: Tables{"hello", "world"},
},
{
xml: `<Tables xmlns:f="http://www.w3schools.com/furniture" xmlns:h="http://www.w3.org/TR/html4/">` +
`<f:table>world</f:table>` +
`<h:table>hello</h:table>` +
`</Tables>`,
tab: Tables{"hello", "world"},
},
{
xml: `<Tables>` +
`<table>bogus</table>` +
`</Tables>`,
tab: Tables{},
},
{
xml: `<Tables>` +
`<table>only</table>` +
`</Tables>`,
tab: Tables{HTable: "only"},
ns: "http://www.w3.org/TR/html4/",
},
{
xml: `<Tables>` +
`<table>only</table>` +
`</Tables>`,
tab: Tables{FTable: "only"},
ns: "http://www.w3schools.com/furniture",
},
{
xml: `<Tables>` +
`<table>only</table>` +
`</Tables>`,
tab: Tables{},
ns: "something else entirely",
},
}
func TestUnmarshalNS(t *testing.T) {
for i, tt := range tables {
var dst Tables
var err error
if tt.ns != "" {
d := NewDecoder(strings.NewReader(tt.xml))
d.DefaultSpace = tt.ns
err = d.Decode(&dst)
} else {
err = Unmarshal([]byte(tt.xml), &dst)
}
if err != nil {
t.Errorf("#%d: Unmarshal: %v", i, err)
continue
}
want := tt.tab
if dst != want {
t.Errorf("#%d: dst=%+v, want %+v", i, dst, want)
}
}
}
func TestRoundTrip(t *testing.T) {
// From issue 7535
const s = `<ex:element xmlns:ex="http://example.com/schema"></ex:element>`
in := bytes.NewBufferString(s)
for i := 0; i < 10; i++ {
out := &bytes.Buffer{}
d := NewDecoder(in)
e := NewEncoder(out)
for {
t, err := d.Token()
if err == io.EOF {
break
}
if err != nil {
fmt.Println("failed:", err)
return
}
e.EncodeToken(t)
}
e.Flush()
in = out
}
if got := in.String(); got != s {
t.Errorf("have: %q\nwant: %q\n", got, s)
}
}
func TestMarshalNS(t *testing.T) {
dst := Tables{"hello", "world"}
data, err := Marshal(&dst)
if err != nil {
t.Fatalf("Marshal: %v", err)
}
want := `<Tables><table xmlns="http://www.w3.org/TR/html4/">hello</table><table xmlns="http://www.w3schools.com/furniture">world</table></Tables>`
str := string(data)
if str != want {
t.Errorf("have: %q\nwant: %q\n", str, want)
}
}
type TableAttrs struct {
TAttr TAttr
}
type TAttr struct {
HTable string `xml:"http://www.w3.org/TR/html4/ table,attr"`
FTable string `xml:"http://www.w3schools.com/furniture table,attr"`
Lang string `xml:"http://www.w3.org/XML/1998/namespace lang,attr,omitempty"`
Other1 string `xml:"http://golang.org/xml/ other,attr,omitempty"`
Other2 string `xml:"http://golang.org/xmlfoo/ other,attr,omitempty"`
Other3 string `xml:"http://golang.org/json/ other,attr,omitempty"`
Other4 string `xml:"http://golang.org/2/json/ other,attr,omitempty"`
}
var tableAttrs = []struct {
xml string
tab TableAttrs
ns string
}{
{
xml: `<TableAttrs xmlns:f="http://www.w3schools.com/furniture" xmlns:h="http://www.w3.org/TR/html4/"><TAttr ` +
`h:table="hello" f:table="world" ` +
`/></TableAttrs>`,
tab: TableAttrs{TAttr{HTable: "hello", FTable: "world"}},
},
{
xml: `<TableAttrs><TAttr xmlns:f="http://www.w3schools.com/furniture" xmlns:h="http://www.w3.org/TR/html4/" ` +
`h:table="hello" f:table="world" ` +
`/></TableAttrs>`,
tab: TableAttrs{TAttr{HTable: "hello", FTable: "world"}},
},
{
xml: `<TableAttrs><TAttr ` +
`h:table="hello" f:table="world" xmlns:f="http://www.w3schools.com/furniture" xmlns:h="http://www.w3.org/TR/html4/" ` +
`/></TableAttrs>`,
tab: TableAttrs{TAttr{HTable: "hello", FTable: "world"}},
},
{
// Default space does not apply to attribute names.
xml: `<TableAttrs xmlns="http://www.w3schools.com/furniture" xmlns:h="http://www.w3.org/TR/html4/"><TAttr ` +
`h:table="hello" table="world" ` +
`/></TableAttrs>`,
tab: TableAttrs{TAttr{HTable: "hello", FTable: ""}},
},
{
// Default space does not apply to attribute names.
xml: `<TableAttrs xmlns:f="http://www.w3schools.com/furniture"><TAttr xmlns="http://www.w3.org/TR/html4/" ` +
`table="hello" f:table="world" ` +
`/></TableAttrs>`,
tab: TableAttrs{TAttr{HTable: "", FTable: "world"}},
},
{
xml: `<TableAttrs><TAttr ` +
`table="bogus" ` +
`/></TableAttrs>`,
tab: TableAttrs{},
},
{
// Default space does not apply to attribute names.
xml: `<TableAttrs xmlns:h="http://www.w3.org/TR/html4/"><TAttr ` +
`h:table="hello" table="world" ` +
`/></TableAttrs>`,
tab: TableAttrs{TAttr{HTable: "hello", FTable: ""}},
ns: "http://www.w3schools.com/furniture",
},
{
// Default space does not apply to attribute names.
xml: `<TableAttrs xmlns:f="http://www.w3schools.com/furniture"><TAttr ` +
`table="hello" f:table="world" ` +
`/></TableAttrs>`,
tab: TableAttrs{TAttr{HTable: "", FTable: "world"}},
ns: "http://www.w3.org/TR/html4/",
},
{
xml: `<TableAttrs><TAttr ` +
`table="bogus" ` +
`/></TableAttrs>`,
tab: TableAttrs{},
ns: "something else entirely",
},
}
func TestUnmarshalNSAttr(t *testing.T) {
for i, tt := range tableAttrs {
var dst TableAttrs
var err error
if tt.ns != "" {
d := NewDecoder(strings.NewReader(tt.xml))
d.DefaultSpace = tt.ns
err = d.Decode(&dst)
} else {
err = Unmarshal([]byte(tt.xml), &dst)
}
if err != nil {
t.Errorf("#%d: Unmarshal: %v", i, err)
continue
}
want := tt.tab
if dst != want {
t.Errorf("#%d: dst=%+v, want %+v", i, dst, want)
}
}
}
func TestMarshalNSAttr(t *testing.T) {
src := TableAttrs{TAttr{"hello", "world", "en_US", "other1", "other2", "other3", "other4"}}
data, err := Marshal(&src)
if err != nil {
t.Fatalf("Marshal: %v", err)
}
want := `<TableAttrs><TAttr xmlns:json_1="http://golang.org/2/json/" xmlns:json="http://golang.org/json/" xmlns:_xmlfoo="http://golang.org/xmlfoo/" xmlns:_xml="http://golang.org/xml/" xmlns:furniture="http://www.w3schools.com/furniture" xmlns:html4="http://www.w3.org/TR/html4/" html4:table="hello" furniture:table="world" xml:lang="en_US" _xml:other="other1" _xmlfoo:other="other2" json:other="other3" json_1:other="other4"></TAttr></TableAttrs>`
str := string(data)
if str != want {
t.Errorf("Marshal:\nhave: %#q\nwant: %#q\n", str, want)
}
var dst TableAttrs
if err := Unmarshal(data, &dst); err != nil {
t.Errorf("Unmarshal: %v", err)
}
if dst != src {
t.Errorf("Unmarshal = %q, want %q", dst, src)
}
}
type MyCharData struct {
body string
}
func (m *MyCharData) UnmarshalXML(d *Decoder, start StartElement) error {
for {
t, err := d.Token()
if err == io.EOF { // found end of element
break
}
if err != nil {
return err
}
if char, ok := t.(CharData); ok {
m.body += string(char)
}
}
return nil
}
var _ Unmarshaler = (*MyCharData)(nil)
func (m *MyCharData) UnmarshalXMLAttr(attr Attr) error {
panic("must not call")
}
type MyAttr struct {
attr string
}
func (m *MyAttr) UnmarshalXMLAttr(attr Attr) error {
m.attr = attr.Value
return nil
}
var _ UnmarshalerAttr = (*MyAttr)(nil)
type MyStruct struct {
Data *MyCharData
Attr *MyAttr `xml:",attr"`
Data2 MyCharData
Attr2 MyAttr `xml:",attr"`
}
func TestUnmarshaler(t *testing.T) {
xml := `<?xml version="1.0" encoding="utf-8"?>
<MyStruct Attr="attr1" Attr2="attr2">
<Data>hello <!-- comment -->world</Data>
<Data2>howdy <!-- comment -->world</Data2>
</MyStruct>
`
var m MyStruct
if err := Unmarshal([]byte(xml), &m); err != nil {
t.Fatal(err)
}
if m.Data == nil || m.Attr == nil || m.Data.body != "hello world" || m.Attr.attr != "attr1" || m.Data2.body != "howdy world" || m.Attr2.attr != "attr2" {
t.Errorf("m=%#+v\n", m)
}
}
type Pea struct {
Cotelydon string
}
type Pod struct {
Pea interface{} `xml:"Pea"`
}
// https://golang.org/issue/6836
func TestUnmarshalIntoInterface(t *testing.T) {
pod := new(Pod)
pod.Pea = new(Pea)
xml := `<Pod><Pea><Cotelydon>Green stuff</Cotelydon></Pea></Pod>`
err := Unmarshal([]byte(xml), pod)
if err != nil {
t.Fatalf("failed to unmarshal %q: %v", xml, err)
}
pea, ok := pod.Pea.(*Pea)
if !ok {
t.Fatalf("unmarshalled into wrong type: have %T want *Pea", pod.Pea)
}
have, want := pea.Cotelydon, "Green stuff"
if have != want {
t.Errorf("failed to unmarshal into interface, have %q want %q", have, want)
}
}

371
pkg/webdav/internal/xml/typeinfo.go
Unescape View File

@ -0,0 +1,371 @@
// Copyright 2011 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 xml
import (
"fmt"
"reflect"
"strings"
"sync"
)
// typeInfo holds details for the xml representation of a type.
type typeInfo struct {
xmlname *fieldInfo
fields []fieldInfo
}
// fieldInfo holds details for the xml representation of a single field.
type fieldInfo struct {
idx []int
name string
xmlns string
flags fieldFlags
parents []string
}
type fieldFlags int
const (
fElement fieldFlags = 1 << iota
fAttr
fCharData
fInnerXml
fComment
fAny
fOmitEmpty
fMode = fElement | fAttr | fCharData | fInnerXml | fComment | fAny
)
var tinfoMap = make(map[reflect.Type]*typeInfo)
var tinfoLock sync.RWMutex
var nameType = reflect.TypeOf(Name{})
// getTypeInfo returns the typeInfo structure with details necessary
// for marshalling and unmarshalling typ.
func getTypeInfo(typ reflect.Type) (*typeInfo, error) {
tinfoLock.RLock()
tinfo, ok := tinfoMap[typ]
tinfoLock.RUnlock()
if ok {
return tinfo, nil
}
tinfo = &typeInfo{}
if typ.Kind() == reflect.Struct && typ != nameType {
n := typ.NumField()
for i := 0; i < n; i++ {
f := typ.Field(i)
if f.PkgPath != "" || f.Tag.Get("xml") == "-" {
continue // Private field
}
// For embedded structs, embed its fields.
if f.Anonymous {
t := f.Type
if t.Kind() == reflect.Ptr {
t = t.Elem()
}
if t.Kind() == reflect.Struct {
inner, err := getTypeInfo(t)
if err != nil {
return nil, err
}
if tinfo.xmlname == nil {
tinfo.xmlname = inner.xmlname
}
for _, finfo := range inner.fields {
finfo.idx = append([]int{i}, finfo.idx...)
if err := addFieldInfo(typ, tinfo, &finfo); err != nil {
return nil, err
}
}
continue
}
}
finfo, err := structFieldInfo(typ, &f)
if err != nil {
return nil, err
}
if f.Name == "XMLName" {
tinfo.xmlname = finfo
continue
}
// Add the field if it doesn't conflict with other fields.
if err := addFieldInfo(typ, tinfo, finfo); err != nil {
return nil, err
}
}
}
tinfoLock.Lock()
tinfoMap[typ] = tinfo
tinfoLock.Unlock()
return tinfo, nil
}
// structFieldInfo builds and returns a fieldInfo for f.
func structFieldInfo(typ reflect.Type, f *reflect.StructField) (*fieldInfo, error) {
finfo := &fieldInfo{idx: f.Index}
// Split the tag from the xml namespace if necessary.
tag := f.Tag.Get("xml")
if i := strings.Index(tag, " "); i >= 0 {
finfo.xmlns, tag = tag[:i], tag[i+1:]
}
// Parse flags.
tokens := strings.Split(tag, ",")
if len(tokens) == 1 {
finfo.flags = fElement
} else {
tag = tokens[0]
for _, flag := range tokens[1:] {
switch flag {
case "attr":
finfo.flags |= fAttr
case "chardata":
finfo.flags |= fCharData
case "innerxml":
finfo.flags |= fInnerXml
case "comment":
finfo.flags |= fComment
case "any":
finfo.flags |= fAny
case "omitempty":
finfo.flags |= fOmitEmpty
}
}
// Validate the flags used.
valid := true
switch mode := finfo.flags & fMode; mode {
case 0:
finfo.flags |= fElement
case fAttr, fCharData, fInnerXml, fComment, fAny:
if f.Name == "XMLName" || tag != "" && mode != fAttr {
valid = false
}
default:
// This will also catch multiple modes in a single field.
valid = false
}
if finfo.flags&fMode == fAny {
finfo.flags |= fElement
}
if finfo.flags&fOmitEmpty != 0 && finfo.flags&(fElement|fAttr) == 0 {
valid = false
}
if !valid {
return nil, fmt.Errorf("xml: invalid tag in field %s of type %s: %q",
f.Name, typ, f.Tag.Get("xml"))
}
}
// Use of xmlns without a name is not allowed.
if finfo.xmlns != "" && tag == "" {
return nil, fmt.Errorf("xml: namespace without name in field %s of type %s: %q",
f.Name, typ, f.Tag.Get("xml"))
}
if f.Name == "XMLName" {
// The XMLName field records the XML element name. Don't
// process it as usual because its name should default to
// empty rather than to the field name.
finfo.name = tag
return finfo, nil
}
if tag == "" {
// If the name part of the tag is completely empty, get
// default from XMLName of underlying struct if feasible,
// or field name otherwise.
if xmlname := lookupXMLName(f.Type); xmlname != nil {
finfo.xmlns, finfo.name = xmlname.xmlns, xmlname.name
} else {
finfo.name = f.Name
}
return finfo, nil
}
if finfo.xmlns == "" && finfo.flags&fAttr == 0 {
// If it's an element no namespace specified, get the default
// from the XMLName of enclosing struct if possible.
if xmlname := lookupXMLName(typ); xmlname != nil {
finfo.xmlns = xmlname.xmlns
}
}
// Prepare field name and parents.
parents := strings.Split(tag, ">")
if parents[0] == "" {
parents[0] = f.Name
}
if parents[len(parents)-1] == "" {
return nil, fmt.Errorf("xml: trailing '>' in field %s of type %s", f.Name, typ)
}
finfo.name = parents[len(parents)-1]
if len(parents) > 1 {
if (finfo.flags & fElement) == 0 {
return nil, fmt.Errorf("xml: %s chain not valid with %s flag", tag, strings.Join(tokens[1:], ","))
}
finfo.parents = parents[:len(parents)-1]
}
// If the field type has an XMLName field, the names must match
// so that the behavior of both marshalling and unmarshalling
// is straightforward and unambiguous.
if finfo.flags&fElement != 0 {
ftyp := f.Type
xmlname := lookupXMLName(ftyp)
if xmlname != nil && xmlname.name != finfo.name {
return nil, fmt.Errorf("xml: name %q in tag of %s.%s conflicts with name %q in %s.XMLName",
finfo.name, typ, f.Name, xmlname.name, ftyp)
}
}
return finfo, nil
}
// lookupXMLName returns the fieldInfo for typ's XMLName field
// in case it exists and has a valid xml field tag, otherwise
// it returns nil.
func lookupXMLName(typ reflect.Type) (xmlname *fieldInfo) {
for typ.Kind() == reflect.Ptr {
typ = typ.Elem()
}
if typ.Kind() != reflect.Struct {
return nil
}
for i, n := 0, typ.NumField(); i < n; i++ {
f := typ.Field(i)
if f.Name != "XMLName" {
continue
}
finfo, err := structFieldInfo(typ, &f)
if finfo.name != "" && err == nil {
return finfo
}
// Also consider errors as a non-existent field tag
// and let getTypeInfo itself report the error.
break
}
return nil
}
func min(a, b int) int {
if a <= b {
return a
}
return b
}
// addFieldInfo adds finfo to tinfo.fields if there are no
// conflicts, or if conflicts arise from previous fields that were
// obtained from deeper embedded structures than finfo. In the latter
// case, the conflicting entries are dropped.
// A conflict occurs when the path (parent + name) to a field is
// itself a prefix of another path, or when two paths match exactly.
// It is okay for field paths to share a common, shorter prefix.
func addFieldInfo(typ reflect.Type, tinfo *typeInfo, newf *fieldInfo) error {
var conflicts []int
Loop:
// First, figure all conflicts. Most working code will have none.
for i := range tinfo.fields {
oldf := &tinfo.fields[i]
if oldf.flags&fMode != newf.flags&fMode {
continue
}
if oldf.xmlns != "" && newf.xmlns != "" && oldf.xmlns != newf.xmlns {
continue
}
minl := min(len(newf.parents), len(oldf.parents))
for p := 0; p < minl; p++ {
if oldf.parents[p] != newf.parents[p] {
continue Loop
}
}
if len(oldf.parents) > len(newf.parents) {
if oldf.parents[len(newf.parents)] == newf.name {
conflicts = append(conflicts, i)
}
} else if len(oldf.parents) < len(newf.parents) {
if newf.parents[len(oldf.parents)] == oldf.name {
conflicts = append(conflicts, i)
}
} else {
if newf.name == oldf.name {
conflicts = append(conflicts, i)
}
}
}
// Without conflicts, add the new field and return.
if conflicts == nil {
tinfo.fields = append(tinfo.fields, *newf)
return nil
}
// If any conflict is shallower, ignore the new field.
// This matches the Go field resolution on embedding.
for _, i := range conflicts {
if len(tinfo.fields[i].idx) < len(newf.idx) {
return nil
}
}
// Otherwise, if any of them is at the same depth level, it's an error.
for _, i := range conflicts {
oldf := &tinfo.fields[i]
if len(oldf.idx) == len(newf.idx) {
f1 := typ.FieldByIndex(oldf.idx)
f2 := typ.FieldByIndex(newf.idx)
return &TagPathError{typ, f1.Name, f1.Tag.Get("xml"), f2.Name, f2.Tag.Get("xml")}
}
}
// Otherwise, the new field is shallower, and thus takes precedence,
// so drop the conflicting fields from tinfo and append the new one.
for c := len(conflicts) - 1; c >= 0; c-- {
i := conflicts[c]
copy(tinfo.fields[i:], tinfo.fields[i+1:])
tinfo.fields = tinfo.fields[:len(tinfo.fields)-1]
}
tinfo.fields = append(tinfo.fields, *newf)
return nil
}
// A TagPathError represents an error in the unmarshalling process
// caused by the use of field tags with conflicting paths.
type TagPathError struct {
Struct reflect.Type
Field1, Tag1 string
Field2, Tag2 string
}
func (e *TagPathError) Error() string {
return fmt.Sprintf("%s field %q with tag %q conflicts with field %q with tag %q", e.Struct, e.Field1, e.Tag1, e.Field2, e.Tag2)
}
// value returns v's field value corresponding to finfo.
// It's equivalent to v.FieldByIndex(finfo.idx), but initializes
// and dereferences pointers as necessary.
func (finfo *fieldInfo) value(v reflect.Value) reflect.Value {
for i, x := range finfo.idx {
if i > 0 {
t := v.Type()
if t.Kind() == reflect.Ptr && t.Elem().Kind() == reflect.Struct {
if v.IsNil() {
v.Set(reflect.New(v.Type().Elem()))
}
v = v.Elem()
}
}
v = v.Field(x)
}
return v
}

1998
pkg/webdav/internal/xml/xml.go
View File

File diff suppressed because it is too large Load Diff

752
pkg/webdav/internal/xml/xml_test.go
Unescape View File

@ -0,0 +1,752 @@
// Copyright 2009 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 xml
import (
"bytes"
"fmt"
"io"
"reflect"
"strings"
"testing"
"unicode/utf8"
)
const testInput = `
<?xml version="1.0" encoding="UTF-8"?>
<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Transitional//EN"
"http://www.w3.org/TR/xhtml1/DTD/xhtml1-transitional.dtd">
<body xmlns:foo="ns1" xmlns="ns2" xmlns:tag="ns3" ` +
"\r\n\t" + ` >
<hello lang="en">World &lt;&gt;&apos;&quot; &#x767d;&#40300;翔</hello>
<query>&何; &is-it;</query>
<goodbye />
<outer foo:attr="value" xmlns:tag="ns4">
<inner/>
</outer>
<tag:name>
<![CDATA[Some text here.]]>
</tag:name>
</body><!-- missing final newline -->`
var testEntity = map[string]string{"何": "What", "is-it": "is it?"}
var rawTokens = []Token{
CharData("\n"),
ProcInst{"xml", []byte(`version="1.0" encoding="UTF-8"`)},
CharData("\n"),
Directive(`DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Transitional//EN"
"http://www.w3.org/TR/xhtml1/DTD/xhtml1-transitional.dtd"`),
CharData("\n"),
StartElement{Name{"", "body"}, []Attr{{Name{"xmlns", "foo"}, "ns1"}, {Name{"", "xmlns"}, "ns2"}, {Name{"xmlns", "tag"}, "ns3"}}},
CharData("\n "),
StartElement{Name{"", "hello"}, []Attr{{Name{"", "lang"}, "en"}}},
CharData("World <>'\" 白鵬翔"),
EndElement{Name{"", "hello"}},
CharData("\n "),
StartElement{Name{"", "query"}, []Attr{}},
CharData("What is it?"),
EndElement{Name{"", "query"}},
CharData("\n "),
StartElement{Name{"", "goodbye"}, []Attr{}},
EndElement{Name{"", "goodbye"}},
CharData("\n "),
StartElement{Name{"", "outer"}, []Attr{{Name{"foo", "attr"}, "value"}, {Name{"xmlns", "tag"}, "ns4"}}},
CharData("\n "),
StartElement{Name{"", "inner"}, []Attr{}},
EndElement{Name{"", "inner"}},
CharData("\n "),
EndElement{Name{"", "outer"}},
CharData("\n "),
StartElement{Name{"tag", "name"}, []Attr{}},
CharData("\n "),
CharData("Some text here."),
CharData("\n "),
EndElement{Name{"tag", "name"}},
CharData("\n"),
EndElement{Name{"", "body"}},
Comment(" missing final newline "),
}
var cookedTokens = []Token{
CharData("\n"),
ProcInst{"xml", []byte(`version="1.0" encoding="UTF-8"`)},
CharData("\n"),
Directive(`DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Transitional//EN"
"http://www.w3.org/TR/xhtml1/DTD/xhtml1-transitional.dtd"`),
CharData("\n"),
StartElement{Name{"ns2", "body"}, []Attr{{Name{"xmlns", "foo"}, "ns1"}, {Name{"", "xmlns"}, "ns2"}, {Name{"xmlns", "tag"}, "ns3"}}},
CharData("\n "),
StartElement{Name{"ns2", "hello"}, []Attr{{Name{"", "lang"}, "en"}}},
CharData("World <>'\" 白鵬翔"),
EndElement{Name{"ns2", "hello"}},
CharData("\n "),
StartElement{Name{"ns2", "query"}, []Attr{}},
CharData("What is it?"),
EndElement{Name{"ns2", "query"}},
CharData("\n "),
StartElement{Name{"ns2", "goodbye"}, []Attr{}},
EndElement{Name{"ns2", "goodbye"}},
CharData("\n "),
StartElement{Name{"ns2", "outer"}, []Attr{{Name{"ns1", "attr"}, "value"}, {Name{"xmlns", "tag"}, "ns4"}}},
CharData("\n "),
StartElement{Name{"ns2", "inner"}, []Attr{}},
EndElement{Name{"ns2", "inner"}},
CharData("\n "),
EndElement{Name{"ns2", "outer"}},
CharData("\n "),
StartElement{Name{"ns3", "name"}, []Attr{}},
CharData("\n "),
CharData("Some text here."),
CharData("\n "),
EndElement{Name{"ns3", "name"}},
CharData("\n"),
EndElement{Name{"ns2", "body"}},
Comment(" missing final newline "),
}
const testInputAltEncoding = `
<?xml version="1.0" encoding="x-testing-uppercase"?>
<TAG>VALUE</TAG>`
var rawTokensAltEncoding = []Token{
CharData("\n"),
ProcInst{"xml", []byte(`version="1.0" encoding="x-testing-uppercase"`)},
CharData("\n"),
StartElement{Name{"", "tag"}, []Attr{}},
CharData("value"),
EndElement{Name{"", "tag"}},
}
var xmlInput = []string{
// unexpected EOF cases
"<",
"<t",
"<t ",
"<t/",
"<!",
"<!-",
"<!--",
"<!--c-",
"<!--c--",
"<!d",
"<t></",
"<t></t",
"<?",
"<?p",
"<t a",
"<t a=",
"<t a='",
"<t a=''",
"<t/><![",
"<t/><![C",
"<t/><![CDATA[d",
"<t/><![CDATA[d]",
"<t/><![CDATA[d]]",
// other Syntax errors
"<>",
"<t/a",
"<0 />",
"<?0 >",
// "<!0 >", // let the Token() caller handle
"</0>",
"<t 0=''>",
"<t a='&'>",
"<t a='<'>",
"<t>&nbspc;</t>",
"<t a>",
"<t a=>",
"<t a=v>",
// "<![CDATA[d]]>", // let the Token() caller handle
"<t></e>",
"<t></>",
"<t></t!",
"<t>cdata]]></t>",
}
func TestRawToken(t *testing.T) {
d := NewDecoder(strings.NewReader(testInput))
d.Entity = testEntity
testRawToken(t, d, testInput, rawTokens)
}
const nonStrictInput = `
<tag>non&entity</tag>
<tag>&unknown;entity</tag>
<tag>&#123</tag>
<tag>&#zzz;</tag>
<tag>&なまえ3;</tag>
<tag>&lt-gt;</tag>
<tag>&;</tag>
<tag>&0a;</tag>
`
var nonStringEntity = map[string]string{"": "oops!", "0a": "oops!"}
var nonStrictTokens = []Token{
CharData("\n"),
StartElement{Name{"", "tag"}, []Attr{}},
CharData("non&entity"),
EndElement{Name{"", "tag"}},
CharData("\n"),
StartElement{Name{"", "tag"}, []Attr{}},
CharData("&unknown;entity"),
EndElement{Name{"", "tag"}},
CharData("\n"),
StartElement{Name{"", "tag"}, []Attr{}},
CharData("&#123"),
EndElement{Name{"", "tag"}},
CharData("\n"),
StartElement{Name{"", "tag"}, []Attr{}},
CharData("&#zzz;"),
EndElement{Name{"", "tag"}},
CharData("\n"),
StartElement{Name{"", "tag"}, []Attr{}},
CharData("&なまえ3;"),
EndElement{Name{"", "tag"}},
CharData("\n"),
StartElement{Name{"", "tag"}, []Attr{}},
CharData("&lt-gt;"),
EndElement{Name{"", "tag"}},
CharData("\n"),
StartElement{Name{"", "tag"}, []Attr{}},
CharData("&;"),
EndElement{Name{"", "tag"}},
CharData("\n"),
StartElement{Name{"", "tag"}, []Attr{}},
CharData("&0a;"),
EndElement{Name{"", "tag"}},
CharData("\n"),
}
func TestNonStrictRawToken(t *testing.T) {
d := NewDecoder(strings.NewReader(nonStrictInput))
d.Strict = false
testRawToken(t, d, nonStrictInput, nonStrictTokens)
}
type downCaser struct {
t *testing.T
r io.ByteReader
}
func (d *downCaser) ReadByte() (c byte, err error) {
c, err = d.r.ReadByte()
if c >= 'A' && c <= 'Z' {
c += 'a' - 'A'
}
return
}
func (d *downCaser) Read(p []byte) (int, error) {
d.t.Fatalf("unexpected Read call on downCaser reader")
panic("unreachable")
}
func TestRawTokenAltEncoding(t *testing.T) {
d := NewDecoder(strings.NewReader(testInputAltEncoding))
d.CharsetReader = func(charset string, input io.Reader) (io.Reader, error) {
if charset != "x-testing-uppercase" {
t.Fatalf("unexpected charset %q", charset)
}
return &downCaser{t, input.(io.ByteReader)}, nil
}
testRawToken(t, d, testInputAltEncoding, rawTokensAltEncoding)
}
func TestRawTokenAltEncodingNoConverter(t *testing.T) {
d := NewDecoder(strings.NewReader(testInputAltEncoding))
token, err := d.RawToken()
if token == nil {
t.Fatalf("expected a token on first RawToken call")
}
if err != nil {
t.Fatal(err)
}
token, err = d.RawToken()
if token != nil {
t.Errorf("expected a nil token; got %#v", token)
}
if err == nil {
t.Fatalf("expected an error on second RawToken call")
}
const encoding = "x-testing-uppercase"
if !strings.Contains(err.Error(), encoding) {
t.Errorf("expected error to contain %q; got error: %v",
encoding, err)
}
}
func testRawToken(t *testing.T, d *Decoder, raw string, rawTokens []Token) {
lastEnd := int64(0)
for i, want := range rawTokens {
start := d.InputOffset()
have, err := d.RawToken()
end := d.InputOffset()
if err != nil {
t.Fatalf("token %d: unexpected error: %s", i, err)
}
if !reflect.DeepEqual(have, want) {
var shave, swant string
if _, ok := have.(CharData); ok {
shave = fmt.Sprintf("CharData(%q)", have)
} else {
shave = fmt.Sprintf("%#v", have)
}
if _, ok := want.(CharData); ok {
swant = fmt.Sprintf("CharData(%q)", want)
} else {
swant = fmt.Sprintf("%#v", want)
}
t.Errorf("token %d = %s, want %s", i, shave, swant)
}
// Check that InputOffset returned actual token.
switch {
case start < lastEnd:
t.Errorf("token %d: position [%d,%d) for %T is before previous token", i, start, end, have)
case start >= end:
// Special case: EndElement can be synthesized.
if start == end && end == lastEnd {
break
}
t.Errorf("token %d: position [%d,%d) for %T is empty", i, start, end, have)
case end > int64(len(raw)):
t.Errorf("token %d: position [%d,%d) for %T extends beyond input", i, start, end, have)
default:
text := raw[start:end]
if strings.ContainsAny(text, "<>") && (!strings.HasPrefix(text, "<") || !strings.HasSuffix(text, ">")) {
t.Errorf("token %d: misaligned raw token %#q for %T", i, text, have)
}
}
lastEnd = end
}
}
// Ensure that directives (specifically !DOCTYPE) include the complete
// text of any nested directives, noting that < and > do not change
// nesting depth if they are in single or double quotes.
var nestedDirectivesInput = `
<!DOCTYPE [<!ENTITY rdf "http://www.w3.org/1999/02/22-rdf-syntax-ns#">]>
<!DOCTYPE [<!ENTITY xlt ">">]>
<!DOCTYPE [<!ENTITY xlt "<">]>
<!DOCTYPE [<!ENTITY xlt '>'>]>
<!DOCTYPE [<!ENTITY xlt '<'>]>
<!DOCTYPE [<!ENTITY xlt '">'>]>
<!DOCTYPE [<!ENTITY xlt "'<">]>
`
var nestedDirectivesTokens = []Token{
CharData("\n"),
Directive(`DOCTYPE [<!ENTITY rdf "http://www.w3.org/1999/02/22-rdf-syntax-ns#">]`),
CharData("\n"),
Directive(`DOCTYPE [<!ENTITY xlt ">">]`),
CharData("\n"),
Directive(`DOCTYPE [<!ENTITY xlt "<">]`),
CharData("\n"),
Directive(`DOCTYPE [<!ENTITY xlt '>'>]`),
CharData("\n"),
Directive(`DOCTYPE [<!ENTITY xlt '<'>]`),
CharData("\n"),
Directive(`DOCTYPE [<!ENTITY xlt '">'>]`),
CharData("\n"),
Directive(`DOCTYPE [<!ENTITY xlt "'<">]`),
CharData("\n"),
}
func TestNestedDirectives(t *testing.T) {
d := NewDecoder(strings.NewReader(nestedDirectivesInput))
for i, want := range nestedDirectivesTokens {
have, err := d.Token()
if err != nil {
t.Fatalf("token %d: unexpected error: %s", i, err)
}
if !reflect.DeepEqual(have, want) {
t.Errorf("token %d = %#v want %#v", i, have, want)
}
}
}
func TestToken(t *testing.T) {
d := NewDecoder(strings.NewReader(testInput))
d.Entity = testEntity
for i, want := range cookedTokens {
have, err := d.Token()
if err != nil {
t.Fatalf("token %d: unexpected error: %s", i, err)
}
if !reflect.DeepEqual(have, want) {
t.Errorf("token %d = %#v want %#v", i, have, want)
}
}
}
func TestSyntax(t *testing.T) {
for i := range xmlInput {
d := NewDecoder(strings.NewReader(xmlInput[i]))
var err error
for _, err = d.Token(); err == nil; _, err = d.Token() {
}
if _, ok := err.(*SyntaxError); !ok {
t.Fatalf(`xmlInput "%s": expected SyntaxError not received`, xmlInput[i])
}
}
}
type allScalars struct {
True1 bool
True2 bool
False1 bool
False2 bool
Int int
Int8 int8
Int16 int16
Int32 int32
Int64 int64
Uint int
Uint8 uint8
Uint16 uint16
Uint32 uint32
Uint64 uint64
Uintptr uintptr
Float32 float32
Float64 float64
String string
PtrString *string
}
var all = allScalars{
True1: true,
True2: true,
False1: false,
False2: false,
Int: 1,
Int8: -2,
Int16: 3,
Int32: -4,
Int64: 5,
Uint: 6,
Uint8: 7,
Uint16: 8,
Uint32: 9,
Uint64: 10,
Uintptr: 11,
Float32: 13.0,
Float64: 14.0,
String: "15",
PtrString: &sixteen,
}
var sixteen = "16"
const testScalarsInput = `<allscalars>
<True1>true</True1>
<True2>1</True2>
<False1>false</False1>
<False2>0</False2>
<Int>1</Int>
<Int8>-2</Int8>
<Int16>3</Int16>
<Int32>-4</Int32>
<Int64>5</Int64>
<Uint>6</Uint>
<Uint8>7</Uint8>
<Uint16>8</Uint16>
<Uint32>9</Uint32>
<Uint64>10</Uint64>
<Uintptr>11</Uintptr>
<Float>12.0</Float>
<Float32>13.0</Float32>
<Float64>14.0</Float64>
<String>15</String>
<PtrString>16</PtrString>
</allscalars>`
func TestAllScalars(t *testing.T) {
var a allScalars
err := Unmarshal([]byte(testScalarsInput), &a)
if err != nil {
t.Fatal(err)
}
if !reflect.DeepEqual(a, all) {
t.Errorf("have %+v want %+v", a, all)
}
}
type item struct {
Field_a string
}
func TestIssue569(t *testing.T) {
data := `<item><Field_a>abcd</Field_a></item>`
var i item
err := Unmarshal([]byte(data), &i)
if err != nil || i.Field_a != "abcd" {
t.Fatal("Expecting abcd")
}
}
func TestUnquotedAttrs(t *testing.T) {
data := "<tag attr=azAZ09:-_\t>"
d := NewDecoder(strings.NewReader(data))
d.Strict = false
token, err := d.Token()
if _, ok := err.(*SyntaxError); ok {
t.Errorf("Unexpected error: %v", err)
}
if token.(StartElement).Name.Local != "tag" {
t.Errorf("Unexpected tag name: %v", token.(StartElement).Name.Local)
}
attr := token.(StartElement).Attr[0]
if attr.Value != "azAZ09:-_" {
t.Errorf("Unexpected attribute value: %v", attr.Value)
}
if attr.Name.Local != "attr" {
t.Errorf("Unexpected attribute name: %v", attr.Name.Local)
}
}
func TestValuelessAttrs(t *testing.T) {
tests := [][3]string{
{"<p nowrap>", "p", "nowrap"},
{"<p nowrap >", "p", "nowrap"},
{"<input checked/>", "input", "checked"},
{"<input checked />", "input", "checked"},
}
for _, test := range tests {
d := NewDecoder(strings.NewReader(test[0]))
d.Strict = false
token, err := d.Token()
if _, ok := err.(*SyntaxError); ok {
t.Errorf("Unexpected error: %v", err)
}
if token.(StartElement).Name.Local != test[1] {
t.Errorf("Unexpected tag name: %v", token.(StartElement).Name.Local)
}
attr := token.(StartElement).Attr[0]
if attr.Value != test[2] {
t.Errorf("Unexpected attribute value: %v", attr.Value)
}
if attr.Name.Local != test[2] {
t.Errorf("Unexpected attribute name: %v", attr.Name.Local)
}
}
}
func TestCopyTokenCharData(t *testing.T) {
data := []byte("same data")
var tok1 Token = CharData(data)
tok2 := CopyToken(tok1)
if !reflect.DeepEqual(tok1, tok2) {
t.Error("CopyToken(CharData) != CharData")
}
data[1] = 'o'
if reflect.DeepEqual(tok1, tok2) {
t.Error("CopyToken(CharData) uses same buffer.")
}
}
func TestCopyTokenStartElement(t *testing.T) {
elt := StartElement{Name{"", "hello"}, []Attr{{Name{"", "lang"}, "en"}}}
var tok1 Token = elt
tok2 := CopyToken(tok1)
if tok1.(StartElement).Attr[0].Value != "en" {
t.Error("CopyToken overwrote Attr[0]")
}
if !reflect.DeepEqual(tok1, tok2) {
t.Error("CopyToken(StartElement) != StartElement")
}
tok1.(StartElement).Attr[0] = Attr{Name{"", "lang"}, "de"}
if reflect.DeepEqual(tok1, tok2) {
t.Error("CopyToken(CharData) uses same buffer.")
}
}
func TestSyntaxErrorLineNum(t *testing.T) {
testInput := "<P>Foo<P>\n\n<P>Bar</>\n"
d := NewDecoder(strings.NewReader(testInput))
var err error
for _, err = d.Token(); err == nil; _, err = d.Token() {
}
synerr, ok := err.(*SyntaxError)
if !ok {
t.Error("Expected SyntaxError.")
}
if synerr.Line != 3 {
t.Error("SyntaxError didn't have correct line number.")
}
}
func TestTrailingRawToken(t *testing.T) {
input := `<FOO></FOO> `
d := NewDecoder(strings.NewReader(input))
var err error
for _, err = d.RawToken(); err == nil; _, err = d.RawToken() {
}
if err != io.EOF {
t.Fatalf("d.RawToken() = _, %v, want _, io.EOF", err)
}
}
func TestTrailingToken(t *testing.T) {
input := `<FOO></FOO> `
d := NewDecoder(strings.NewReader(input))
var err error
for _, err = d.Token(); err == nil; _, err = d.Token() {
}
if err != io.EOF {
t.Fatalf("d.Token() = _, %v, want _, io.EOF", err)
}
}
func TestEntityInsideCDATA(t *testing.T) {
input := `<test><![CDATA[ &val=foo ]]></test>`
d := NewDecoder(strings.NewReader(input))
var err error
for _, err = d.Token(); err == nil; _, err = d.Token() {
}
if err != io.EOF {
t.Fatalf("d.Token() = _, %v, want _, io.EOF", err)
}
}
var characterTests = []struct {
in string
err string
}{
{"\x12<doc/>", "illegal character code U+0012"},
{"<?xml version=\"1.0\"?>\x0b<doc/>", "illegal character code U+000B"},
{"\xef\xbf\xbe<doc/>", "illegal character code U+FFFE"},
{"<?xml version=\"1.0\"?><doc>\r\n<hiya/>\x07<toots/></doc>", "illegal character code U+0007"},
{"<?xml version=\"1.0\"?><doc \x12='value'>what's up</doc>", "expected attribute name in element"},
{"<doc>&abc\x01;</doc>", "invalid character entity &abc (no semicolon)"},
{"<doc>&\x01;</doc>", "invalid character entity & (no semicolon)"},
{"<doc>&\xef\xbf\xbe;</doc>", "invalid character entity &\uFFFE;"},
{"<doc>&hello;</doc>", "invalid character entity &hello;"},
}
func TestDisallowedCharacters(t *testing.T) {
for i, tt := range characterTests {
d := NewDecoder(strings.NewReader(tt.in))
var err error
for err == nil {
_, err = d.Token()
}
synerr, ok := err.(*SyntaxError)
if !ok {
t.Fatalf("input %d d.Token() = _, %v, want _, *SyntaxError", i, err)
}
if synerr.Msg != tt.err {
t.Fatalf("input %d synerr.Msg wrong: want %q, got %q", i, tt.err, synerr.Msg)
}
}
}
type procInstEncodingTest struct {
expect, got string
}
var procInstTests = []struct {
input string
expect [2]string
}{
{`version="1.0" encoding="utf-8"`, [2]string{"1.0", "utf-8"}},
{`version="1.0" encoding='utf-8'`, [2]string{"1.0", "utf-8"}},
{`version="1.0" encoding='utf-8' `, [2]string{"1.0", "utf-8"}},
{`version="1.0" encoding=utf-8`, [2]string{"1.0", ""}},
{`encoding="FOO" `, [2]string{"", "FOO"}},
}
func TestProcInstEncoding(t *testing.T) {
for _, test := range procInstTests {
if got := procInst("version", test.input); got != test.expect[0] {
t.Errorf("procInst(version, %q) = %q; want %q", test.input, got, test.expect[0])
}
if got := procInst("encoding", test.input); got != test.expect[1] {
t.Errorf("procInst(encoding, %q) = %q; want %q", test.input, got, test.expect[1])
}
}
}
// Ensure that directives with comments include the complete
// text of any nested directives.
var directivesWithCommentsInput = `
<!DOCTYPE [<!-- a comment --><!ENTITY rdf "http://www.w3.org/1999/02/22-rdf-syntax-ns#">]>
<!DOCTYPE [<!ENTITY go "Golang"><!-- a comment-->]>
<!DOCTYPE <!-> <!> <!----> <!-->--> <!--->--> [<!ENTITY go "Golang"><!-- a comment-->]>
`
var directivesWithCommentsTokens = []Token{
CharData("\n"),
Directive(`DOCTYPE [<!ENTITY rdf "http://www.w3.org/1999/02/22-rdf-syntax-ns#">]`),
CharData("\n"),
Directive(`DOCTYPE [<!ENTITY go "Golang">]`),
CharData("\n"),
Directive(`DOCTYPE <!-> <!> [<!ENTITY go "Golang">]`),
CharData("\n"),
}
func TestDirectivesWithComments(t *testing.T) {
d := NewDecoder(strings.NewReader(directivesWithCommentsInput))
for i, want := range directivesWithCommentsTokens {
have, err := d.Token()
if err != nil {
t.Fatalf("token %d: unexpected error: %s", i, err)
}
if !reflect.DeepEqual(have, want) {
t.Errorf("token %d = %#v want %#v", i, have, want)
}
}
}
// Writer whose Write method always returns an error.
type errWriter struct{}
func (errWriter) Write(p []byte) (n int, err error) { return 0, fmt.Errorf("unwritable") }
func TestEscapeTextIOErrors(t *testing.T) {
expectErr := "unwritable"
err := EscapeText(errWriter{}, []byte{'A'})
if err == nil || err.Error() != expectErr {
t.Errorf("have %v, want %v", err, expectErr)
}
}
func TestEscapeTextInvalidChar(t *testing.T) {
input := []byte("A \x00 terminated string.")
expected := "A \uFFFD terminated string."
buff := new(bytes.Buffer)
if err := EscapeText(buff, input); err != nil {
t.Fatalf("have %v, want nil", err)
}
text := buff.String()
if text != expected {
t.Errorf("have %v, want %v", text, expected)
}
}
func TestIssue5880(t *testing.T) {
type T []byte
data, err := Marshal(T{192, 168, 0, 1})
if err != nil {
t.Errorf("Marshal error: %v", err)
}
if !utf8.Valid(data) {
t.Errorf("Marshal generated invalid UTF-8: %x", data)
}
}
Write Preview
Loading…
Cancel
Save