go/src/pkg/encoding/json/decode.go

1016 lines
24 KiB
Go
Raw Normal View History

// Copyright 2010 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.
// Represents JSON data structure using native Go types: booleans, floats,
// strings, arrays, and maps.
package json
import (
"encoding/base64"
"errors"
"fmt"
"reflect"
"runtime"
"strconv"
"strings"
"unicode"
"unicode/utf16"
"unicode/utf8"
)
// Unmarshal parses the JSON-encoded data and stores the result
// in the value pointed to by v.
//
// Unmarshal uses the inverse of the encodings that
// Marshal uses, allocating maps, slices, and pointers as necessary,
// with the following additional rules:
//
// To unmarshal JSON into a pointer, Unmarshal first handles the case of
// the JSON being the JSON literal null. In that case, Unmarshal sets
// the pointer to nil. Otherwise, Unmarshal unmarshals the JSON into
// the value pointed at by the pointer. If the pointer is nil, Unmarshal
// allocates a new value for it to point to.
//
// To unmarshal JSON into an interface value, Unmarshal unmarshals
// the JSON into the concrete value contained in the interface value.
// If the interface value is nil, that is, has no concrete value stored in it,
// Unmarshal stores one of these in the interface value:
//
// bool, for JSON booleans
// float64, for JSON numbers
// string, for JSON strings
// []interface{}, for JSON arrays
// map[string]interface{}, for JSON objects
// nil for JSON null
//
// If a JSON value is not appropriate for a given target type,
// or if a JSON number overflows the target type, Unmarshal
// skips that field and completes the unmarshalling as best it can.
// If no more serious errors are encountered, Unmarshal returns
// an UnmarshalTypeError describing the earliest such error.
//
func Unmarshal(data []byte, v interface{}) error {
encoding/json: improve performance of Unmarshal on primitive types Skip most of the scanning and parsing logic for simple (non-object/array) JSON values. benchmark old ns/op new ns/op delta BenchmarkUnmarshalInt 948 436 -54.01% BenchmarkUnmarshalUint 930 427 -54.09% BenchmarkUnmarshalString 1407 715 -49.18% BenchmarkUnmarshalFloat 1114 536 -51.89% BenchmarkUnmarshalBool 759 266 -64.95% BenchmarkUnmarshalStruct 8165 8181 +0.20% No significant effects on the go1 benchmarks: benchmark old ns/op new ns/op delta BenchmarkBinaryTree17 9647362752 9596196417 -0.53% BenchmarkFannkuch11 5623613048 5518694872 -1.87% BenchmarkGobDecode 32944041 33165434 +0.67% BenchmarkGobEncode 21237482 21080554 -0.74% BenchmarkGzip 750955920 749861980 -0.15% BenchmarkGunzip 197369742 197886192 +0.26% BenchmarkJSONEncode 79274091 78891137 -0.48% BenchmarkJSONDecode 180257802 175280358 -2.76% BenchmarkMandelbrot200 7396666 7388266 -0.11% BenchmarkParse 11446460 11386550 -0.52% BenchmarkRevcomp 1605152523 1599512029 -0.35% BenchmarkTemplate 204538247 207765574 +1.58% benchmark old MB/s new MB/s speedup BenchmarkGobDecode 23.30 23.14 0.99x BenchmarkGobEncode 36.14 36.41 1.01x BenchmarkGzip 25.84 25.88 1.00x BenchmarkGunzip 98.32 98.06 1.00x BenchmarkJSONEncode 24.48 24.60 1.00x BenchmarkJSONDecode 10.76 11.07 1.03x BenchmarkParse 5.06 5.09 1.01x BenchmarkRevcomp 158.34 158.90 1.00x BenchmarkTemplate 9.49 9.34 0.98x Fixes #3949. R=golang-dev, dave, bradfitz, timo CC=golang-dev https://golang.org/cl/7068043
2013-01-10 17:58:45 -08:00
// skip heavy processing for primitive values
var first byte
var i int
for i, first = range data {
if !isSpace(rune(first)) {
break
}
}
if first != '{' && first != '[' {
rv := reflect.ValueOf(v)
if rv.Kind() != reflect.Ptr || rv.IsNil() {
return &InvalidUnmarshalError{reflect.TypeOf(v)}
}
var d decodeState
d.literalStore(data[i:], rv.Elem(), false)
return d.savedError
}
d := new(decodeState).init(data)
// Quick check for well-formedness.
// Avoids filling out half a data structure
// before discovering a JSON syntax error.
err := checkValid(data, &d.scan)
if err != nil {
return err
}
return d.unmarshal(v)
}
// Unmarshaler is the interface implemented by objects
// that can unmarshal a JSON description of themselves.
// The input can be assumed to be a valid encoding of
// a JSON value. UnmarshalJSON must copy the JSON data
// if it wishes to retain the data after returning.
type Unmarshaler interface {
UnmarshalJSON([]byte) error
}
// An UnmarshalTypeError describes a JSON value that was
// not appropriate for a value of a specific Go type.
type UnmarshalTypeError struct {
Value string // description of JSON value - "bool", "array", "number -5"
Type reflect.Type // type of Go value it could not be assigned to
}
func (e *UnmarshalTypeError) Error() string {
return "json: cannot unmarshal " + e.Value + " into Go value of type " + e.Type.String()
}
// An UnmarshalFieldError describes a JSON object key that
// led to an unexported (and therefore unwritable) struct field.
type UnmarshalFieldError struct {
Key string
Type reflect.Type
Field reflect.StructField
}
func (e *UnmarshalFieldError) Error() string {
return "json: cannot unmarshal object key " + strconv.Quote(e.Key) + " into unexported field " + e.Field.Name + " of type " + e.Type.String()
}
// An InvalidUnmarshalError describes an invalid argument passed to Unmarshal.
// (The argument to Unmarshal must be a non-nil pointer.)
type InvalidUnmarshalError struct {
Type reflect.Type
}
func (e *InvalidUnmarshalError) Error() string {
if e.Type == nil {
return "json: Unmarshal(nil)"
}
if e.Type.Kind() != reflect.Ptr {
return "json: Unmarshal(non-pointer " + e.Type.String() + ")"
}
return "json: Unmarshal(nil " + e.Type.String() + ")"
}
func (d *decodeState) unmarshal(v interface{}) (err error) {
defer func() {
if r := recover(); r != nil {
if _, ok := r.(runtime.Error); ok {
panic(r)
}
err = r.(error)
}
}()
rv := reflect.ValueOf(v)
if rv.Kind() != reflect.Ptr || rv.IsNil() {
return &InvalidUnmarshalError{reflect.TypeOf(v)}
}
d.scan.reset()
// We decode rv not rv.Elem because the Unmarshaler interface
// test must be applied at the top level of the value.
d.value(rv)
return d.savedError
}
// A Number represents a JSON number literal.
type Number string
// String returns the literal text of the number.
func (n Number) String() string { return string(n) }
// Float64 returns the number as a float64.
func (n Number) Float64() (float64, error) {
return strconv.ParseFloat(string(n), 64)
}
// Int64 returns the number as an int64.
func (n Number) Int64() (int64, error) {
return strconv.ParseInt(string(n), 10, 64)
}
// decodeState represents the state while decoding a JSON value.
type decodeState struct {
data []byte
off int // read offset in data
scan scanner
nextscan scanner // for calls to nextValue
savedError error
tempstr string // scratch space to avoid some allocations
useNumber bool
}
// errPhase is used for errors that should not happen unless
// there is a bug in the JSON decoder or something is editing
// the data slice while the decoder executes.
var errPhase = errors.New("JSON decoder out of sync - data changing underfoot?")
func (d *decodeState) init(data []byte) *decodeState {
d.data = data
d.off = 0
d.savedError = nil
return d
}
// error aborts the decoding by panicking with err.
func (d *decodeState) error(err error) {
panic(err)
}
// saveError saves the first err it is called with,
// for reporting at the end of the unmarshal.
func (d *decodeState) saveError(err error) {
if d.savedError == nil {
d.savedError = err
}
}
// next cuts off and returns the next full JSON value in d.data[d.off:].
// The next value is known to be an object or array, not a literal.
func (d *decodeState) next() []byte {
c := d.data[d.off]
item, rest, err := nextValue(d.data[d.off:], &d.nextscan)
if err != nil {
d.error(err)
}
d.off = len(d.data) - len(rest)
// Our scanner has seen the opening brace/bracket
// and thinks we're still in the middle of the object.
// invent a closing brace/bracket to get it out.
if c == '{' {
d.scan.step(&d.scan, '}')
} else {
d.scan.step(&d.scan, ']')
}
return item
}
// scanWhile processes bytes in d.data[d.off:] until it
// receives a scan code not equal to op.
// It updates d.off and returns the new scan code.
func (d *decodeState) scanWhile(op int) int {
var newOp int
for {
if d.off >= len(d.data) {
newOp = d.scan.eof()
d.off = len(d.data) + 1 // mark processed EOF with len+1
} else {
c := int(d.data[d.off])
d.off++
newOp = d.scan.step(&d.scan, c)
}
if newOp != op {
break
}
}
return newOp
}
// value decodes a JSON value from d.data[d.off:] into the value.
// it updates d.off to point past the decoded value.
func (d *decodeState) value(v reflect.Value) {
if !v.IsValid() {
_, rest, err := nextValue(d.data[d.off:], &d.nextscan)
if err != nil {
d.error(err)
}
d.off = len(d.data) - len(rest)
// d.scan thinks we're still at the beginning of the item.
// Feed in an empty string - the shortest, simplest value -
// so that it knows we got to the end of the value.
if d.scan.redo {
// rewind.
d.scan.redo = false
d.scan.step = stateBeginValue
}
d.scan.step(&d.scan, '"')
d.scan.step(&d.scan, '"')
return
}
switch op := d.scanWhile(scanSkipSpace); op {
default:
d.error(errPhase)
case scanBeginArray:
d.array(v)
case scanBeginObject:
d.object(v)
case scanBeginLiteral:
d.literal(v)
}
}
// indirect walks down v allocating pointers as needed,
// until it gets to a non-pointer.
// if it encounters an Unmarshaler, indirect stops and returns that.
// if decodingNull is true, indirect stops at the last pointer so it can be set to nil.
func (d *decodeState) indirect(v reflect.Value, decodingNull bool) (Unmarshaler, reflect.Value) {
// If v is a named type and is addressable,
// start with its address, so that if the type has pointer methods,
// we find them.
if v.Kind() != reflect.Ptr && v.Type().Name() != "" && v.CanAddr() {
v = v.Addr()
}
for {
// Load value from interface, but only if the result will be
// usefully addressable.
if v.Kind() == reflect.Interface && !v.IsNil() {
e := v.Elem()
if e.Kind() == reflect.Ptr && !e.IsNil() && (!decodingNull || e.Elem().Kind() == reflect.Ptr) {
v = e
continue
}
}
if v.Kind() != reflect.Ptr {
break
}
if v.Elem().Kind() != reflect.Ptr && decodingNull && v.CanSet() {
break
}
if v.IsNil() {
v.Set(reflect.New(v.Type().Elem()))
}
if v.Type().NumMethod() > 0 {
if unmarshaler, ok := v.Interface().(Unmarshaler); ok {
return unmarshaler, reflect.Value{}
}
}
v = v.Elem()
}
return nil, v
}
// array consumes an array from d.data[d.off-1:], decoding into the value v.
// the first byte of the array ('[') has been read already.
func (d *decodeState) array(v reflect.Value) {
// Check for unmarshaler.
unmarshaler, pv := d.indirect(v, false)
if unmarshaler != nil {
d.off--
err := unmarshaler.UnmarshalJSON(d.next())
if err != nil {
d.error(err)
}
return
}
v = pv
// Check type of target.
switch v.Kind() {
case reflect.Interface:
if v.NumMethod() == 0 {
// Decoding into nil interface? Switch to non-reflect code.
v.Set(reflect.ValueOf(d.arrayInterface()))
return
}
// Otherwise it's invalid.
fallthrough
default:
d.saveError(&UnmarshalTypeError{"array", v.Type()})
d.off--
d.next()
return
case reflect.Array:
case reflect.Slice:
break
}
i := 0
for {
// Look ahead for ] - can only happen on first iteration.
op := d.scanWhile(scanSkipSpace)
if op == scanEndArray {
break
}
// Back up so d.value can have the byte we just read.
d.off--
d.scan.undo(op)
// Get element of array, growing if necessary.
if v.Kind() == reflect.Slice {
// Grow slice if necessary
if i >= v.Cap() {
newcap := v.Cap() + v.Cap()/2
if newcap < 4 {
newcap = 4
}
newv := reflect.MakeSlice(v.Type(), v.Len(), newcap)
reflect.Copy(newv, v)
v.Set(newv)
}
if i >= v.Len() {
v.SetLen(i + 1)
}
}
if i < v.Len() {
// Decode into element.
d.value(v.Index(i))
} else {
// Ran out of fixed array: skip.
d.value(reflect.Value{})
}
i++
// Next token must be , or ].
op = d.scanWhile(scanSkipSpace)
if op == scanEndArray {
break
}
if op != scanArrayValue {
d.error(errPhase)
}
}
if i < v.Len() {
if v.Kind() == reflect.Array {
// Array. Zero the rest.
z := reflect.Zero(v.Type().Elem())
for ; i < v.Len(); i++ {
v.Index(i).Set(z)
}
} else {
v.SetLen(i)
}
}
if i == 0 && v.Kind() == reflect.Slice {
v.Set(reflect.MakeSlice(v.Type(), 0, 0))
}
}
// object consumes an object from d.data[d.off-1:], decoding into the value v.
// the first byte of the object ('{') has been read already.
func (d *decodeState) object(v reflect.Value) {
// Check for unmarshaler.
unmarshaler, pv := d.indirect(v, false)
if unmarshaler != nil {
d.off--
err := unmarshaler.UnmarshalJSON(d.next())
if err != nil {
d.error(err)
}
return
}
v = pv
// Decoding into nil interface? Switch to non-reflect code.
if v.Kind() == reflect.Interface && v.NumMethod() == 0 {
v.Set(reflect.ValueOf(d.objectInterface()))
return
}
// Check type of target: struct or map[string]T
switch v.Kind() {
case reflect.Map:
// map must have string kind
t := v.Type()
if t.Key().Kind() != reflect.String {
d.saveError(&UnmarshalTypeError{"object", v.Type()})
break
}
if v.IsNil() {
v.Set(reflect.MakeMap(t))
}
case reflect.Struct:
default:
d.saveError(&UnmarshalTypeError{"object", v.Type()})
d.off--
d.next() // skip over { } in input
return
}
var mapElem reflect.Value
for {
// Read opening " of string key or closing }.
op := d.scanWhile(scanSkipSpace)
if op == scanEndObject {
// closing } - can only happen on first iteration.
break
}
if op != scanBeginLiteral {
d.error(errPhase)
}
// Read string key.
start := d.off - 1
op = d.scanWhile(scanContinue)
item := d.data[start : d.off-1]
key, ok := unquote(item)
if !ok {
d.error(errPhase)
}
// Figure out field corresponding to key.
var subv reflect.Value
destring := false // whether the value is wrapped in a string to be decoded first
if v.Kind() == reflect.Map {
elemType := v.Type().Elem()
if !mapElem.IsValid() {
mapElem = reflect.New(elemType).Elem()
} else {
mapElem.Set(reflect.Zero(elemType))
}
subv = mapElem
} else {
var f *field
fields := cachedTypeFields(v.Type())
for i := range fields {
ff := &fields[i]
if ff.name == key {
f = ff
break
}
if f == nil && strings.EqualFold(ff.name, key) {
f = ff
}
}
if f != nil {
subv = v
destring = f.quoted
for _, i := range f.index {
if subv.Kind() == reflect.Ptr {
if subv.IsNil() {
subv.Set(reflect.New(subv.Type().Elem()))
}
subv = subv.Elem()
}
subv = subv.Field(i)
}
} else {
// To give a good error, a quick scan for unexported fields in top level.
st := v.Type()
for i := 0; i < st.NumField(); i++ {
f := st.Field(i)
if f.PkgPath != "" && strings.EqualFold(f.Name, key) {
d.saveError(&UnmarshalFieldError{key, st, f})
}
}
}
}
// Read : before value.
if op == scanSkipSpace {
op = d.scanWhile(scanSkipSpace)
}
if op != scanObjectKey {
d.error(errPhase)
}
// Read value.
if destring {
d.value(reflect.ValueOf(&d.tempstr))
d.literalStore([]byte(d.tempstr), subv, true)
} else {
d.value(subv)
}
// Write value back to map;
// if using struct, subv points into struct already.
if v.Kind() == reflect.Map {
kv := reflect.ValueOf(key).Convert(v.Type().Key())
v.SetMapIndex(kv, subv)
}
// Next token must be , or }.
op = d.scanWhile(scanSkipSpace)
if op == scanEndObject {
break
}
if op != scanObjectValue {
d.error(errPhase)
}
}
}
// literal consumes a literal from d.data[d.off-1:], decoding into the value v.
// The first byte of the literal has been read already
// (that's how the caller knows it's a literal).
func (d *decodeState) literal(v reflect.Value) {
// All bytes inside literal return scanContinue op code.
start := d.off - 1
op := d.scanWhile(scanContinue)
// Scan read one byte too far; back up.
d.off--
d.scan.undo(op)
d.literalStore(d.data[start:d.off], v, false)
}
// convertNumber converts the number literal s to a float64 or a Number
// depending on the setting of d.useNumber.
func (d *decodeState) convertNumber(s string) (interface{}, error) {
if d.useNumber {
return Number(s), nil
}
f, err := strconv.ParseFloat(s, 64)
if err != nil {
return nil, &UnmarshalTypeError{"number " + s, reflect.TypeOf(0.0)}
}
return f, nil
}
var numberType = reflect.TypeOf(Number(""))
// literalStore decodes a literal stored in item into v.
//
// fromQuoted indicates whether this literal came from unwrapping a
// string from the ",string" struct tag option. this is used only to
// produce more helpful error messages.
func (d *decodeState) literalStore(item []byte, v reflect.Value, fromQuoted bool) {
// Check for unmarshaler.
if len(item) == 0 {
//Empty string given
d.saveError(fmt.Errorf("json: invalid use of ,string struct tag, trying to unmarshal %q into %v", item, v.Type()))
return
}
wantptr := item[0] == 'n' // null
unmarshaler, pv := d.indirect(v, wantptr)
if unmarshaler != nil {
err := unmarshaler.UnmarshalJSON(item)
if err != nil {
d.error(err)
}
return
}
v = pv
switch c := item[0]; c {
case 'n': // null
switch v.Kind() {
case reflect.Interface, reflect.Ptr, reflect.Map, reflect.Slice:
v.Set(reflect.Zero(v.Type()))
// otherwise, ignore null for primitives/string
}
case 't', 'f': // true, false
value := c == 't'
switch v.Kind() {
default:
if fromQuoted {
d.saveError(fmt.Errorf("json: invalid use of ,string struct tag, trying to unmarshal %q into %v", item, v.Type()))
} else {
d.saveError(&UnmarshalTypeError{"bool", v.Type()})
}
case reflect.Bool:
v.SetBool(value)
case reflect.Interface:
if v.NumMethod() == 0 {
v.Set(reflect.ValueOf(value))
} else {
d.saveError(&UnmarshalTypeError{"bool", v.Type()})
}
}
case '"': // string
s, ok := unquoteBytes(item)
if !ok {
if fromQuoted {
d.error(fmt.Errorf("json: invalid use of ,string struct tag, trying to unmarshal %q into %v", item, v.Type()))
} else {
d.error(errPhase)
}
}
switch v.Kind() {
default:
d.saveError(&UnmarshalTypeError{"string", v.Type()})
case reflect.Slice:
if v.Type() != byteSliceType {
d.saveError(&UnmarshalTypeError{"string", v.Type()})
break
}
b := make([]byte, base64.StdEncoding.DecodedLen(len(s)))
n, err := base64.StdEncoding.Decode(b, s)
if err != nil {
d.saveError(err)
break
}
v.Set(reflect.ValueOf(b[0:n]))
case reflect.String:
v.SetString(string(s))
case reflect.Interface:
if v.NumMethod() == 0 {
v.Set(reflect.ValueOf(string(s)))
} else {
d.saveError(&UnmarshalTypeError{"string", v.Type()})
}
}
default: // number
if c != '-' && (c < '0' || c > '9') {
if fromQuoted {
d.error(fmt.Errorf("json: invalid use of ,string struct tag, trying to unmarshal %q into %v", item, v.Type()))
} else {
d.error(errPhase)
}
}
s := string(item)
switch v.Kind() {
default:
if v.Kind() == reflect.String && v.Type() == numberType {
v.SetString(s)
break
}
if fromQuoted {
d.error(fmt.Errorf("json: invalid use of ,string struct tag, trying to unmarshal %q into %v", item, v.Type()))
} else {
d.error(&UnmarshalTypeError{"number", v.Type()})
}
case reflect.Interface:
n, err := d.convertNumber(s)
if err != nil {
d.saveError(err)
break
}
if v.NumMethod() != 0 {
d.saveError(&UnmarshalTypeError{"number", v.Type()})
break
}
v.Set(reflect.ValueOf(n))
case reflect.Int, reflect.Int8, reflect.Int16, reflect.Int32, reflect.Int64:
n, err := strconv.ParseInt(s, 10, 64)
if err != nil || v.OverflowInt(n) {
d.saveError(&UnmarshalTypeError{"number " + s, v.Type()})
break
}
v.SetInt(n)
case reflect.Uint, reflect.Uint8, reflect.Uint16, reflect.Uint32, reflect.Uint64, reflect.Uintptr:
n, err := strconv.ParseUint(s, 10, 64)
if err != nil || v.OverflowUint(n) {
d.saveError(&UnmarshalTypeError{"number " + s, v.Type()})
break
}
v.SetUint(n)
case reflect.Float32, reflect.Float64:
n, err := strconv.ParseFloat(s, v.Type().Bits())
if err != nil || v.OverflowFloat(n) {
d.saveError(&UnmarshalTypeError{"number " + s, v.Type()})
break
}
v.SetFloat(n)
}
}
}
// The xxxInterface routines build up a value to be stored
// in an empty interface. They are not strictly necessary,
// but they avoid the weight of reflection in this common case.
// valueInterface is like value but returns interface{}
func (d *decodeState) valueInterface() interface{} {
switch d.scanWhile(scanSkipSpace) {
default:
d.error(errPhase)
case scanBeginArray:
return d.arrayInterface()
case scanBeginObject:
return d.objectInterface()
case scanBeginLiteral:
return d.literalInterface()
}
panic("unreachable")
}
// arrayInterface is like array but returns []interface{}.
func (d *decodeState) arrayInterface() []interface{} {
var v []interface{}
for {
// Look ahead for ] - can only happen on first iteration.
op := d.scanWhile(scanSkipSpace)
if op == scanEndArray {
break
}
// Back up so d.value can have the byte we just read.
d.off--
d.scan.undo(op)
v = append(v, d.valueInterface())
// Next token must be , or ].
op = d.scanWhile(scanSkipSpace)
if op == scanEndArray {
break
}
if op != scanArrayValue {
d.error(errPhase)
}
}
return v
}
// objectInterface is like object but returns map[string]interface{}.
func (d *decodeState) objectInterface() map[string]interface{} {
m := make(map[string]interface{})
for {
// Read opening " of string key or closing }.
op := d.scanWhile(scanSkipSpace)
if op == scanEndObject {
// closing } - can only happen on first iteration.
break
}
if op != scanBeginLiteral {
d.error(errPhase)
}
// Read string key.
start := d.off - 1
op = d.scanWhile(scanContinue)
item := d.data[start : d.off-1]
key, ok := unquote(item)
if !ok {
d.error(errPhase)
}
// Read : before value.
if op == scanSkipSpace {
op = d.scanWhile(scanSkipSpace)
}
if op != scanObjectKey {
d.error(errPhase)
}
// Read value.
m[key] = d.valueInterface()
// Next token must be , or }.
op = d.scanWhile(scanSkipSpace)
if op == scanEndObject {
break
}
if op != scanObjectValue {
d.error(errPhase)
}
}
return m
}
// literalInterface is like literal but returns an interface value.
func (d *decodeState) literalInterface() interface{} {
// All bytes inside literal return scanContinue op code.
start := d.off - 1
op := d.scanWhile(scanContinue)
// Scan read one byte too far; back up.
d.off--
d.scan.undo(op)
item := d.data[start:d.off]
switch c := item[0]; c {
case 'n': // null
return nil
case 't', 'f': // true, false
return c == 't'
case '"': // string
s, ok := unquote(item)
if !ok {
d.error(errPhase)
}
return s
default: // number
if c != '-' && (c < '0' || c > '9') {
d.error(errPhase)
}
n, err := d.convertNumber(string(item))
if err != nil {
d.saveError(err)
}
return n
}
panic("unreachable")
}
// getu4 decodes \uXXXX from the beginning of s, returning the hex value,
// or it returns -1.
func getu4(s []byte) rune {
if len(s) < 6 || s[0] != '\\' || s[1] != 'u' {
return -1
}
r, err := strconv.ParseUint(string(s[2:6]), 16, 64)
if err != nil {
return -1
}
return rune(r)
}
// unquote converts a quoted JSON string literal s into an actual string t.
// The rules are different than for Go, so cannot use strconv.Unquote.
func unquote(s []byte) (t string, ok bool) {
s, ok = unquoteBytes(s)
t = string(s)
return
}
func unquoteBytes(s []byte) (t []byte, ok bool) {
if len(s) < 2 || s[0] != '"' || s[len(s)-1] != '"' {
return
}
s = s[1 : len(s)-1]
// Check for unusual characters. If there are none,
// then no unquoting is needed, so return a slice of the
// original bytes.
r := 0
for r < len(s) {
c := s[r]
if c == '\\' || c == '"' || c < ' ' {
break
}
if c < utf8.RuneSelf {
r++
continue
}
rr, size := utf8.DecodeRune(s[r:])
if rr == utf8.RuneError && size == 1 {
break
}
r += size
}
if r == len(s) {
return s, true
}
b := make([]byte, len(s)+2*utf8.UTFMax)
w := copy(b, s[0:r])
for r < len(s) {
// Out of room? Can only happen if s is full of
// malformed UTF-8 and we're replacing each
// byte with RuneError.
if w >= len(b)-2*utf8.UTFMax {
nb := make([]byte, (len(b)+utf8.UTFMax)*2)
copy(nb, b[0:w])
b = nb
}
switch c := s[r]; {
case c == '\\':
r++
if r >= len(s) {
return
}
switch s[r] {
default:
return
case '"', '\\', '/', '\'':
b[w] = s[r]
r++
w++
case 'b':
b[w] = '\b'
r++
w++
case 'f':
b[w] = '\f'
r++
w++
case 'n':
b[w] = '\n'
r++
w++
case 'r':
b[w] = '\r'
r++
w++
case 't':
b[w] = '\t'
r++
w++
case 'u':
r--
rr := getu4(s[r:])
if rr < 0 {
return
}
r += 6
if utf16.IsSurrogate(rr) {
rr1 := getu4(s[r:])
if dec := utf16.DecodeRune(rr, rr1); dec != unicode.ReplacementChar {
// A valid pair; consume.
r += 6
w += utf8.EncodeRune(b[w:], dec)
break
}
// Invalid surrogate; fall back to replacement rune.
rr = unicode.ReplacementChar
}
w += utf8.EncodeRune(b[w:], rr)
}
// Quote, control characters are invalid.
case c == '"', c < ' ':
return
// ASCII
case c < utf8.RuneSelf:
b[w] = c
r++
w++
// Coerce to well-formed UTF-8.
default:
rr, size := utf8.DecodeRune(s[r:])
r += size
w += utf8.EncodeRune(b[w:], rr)
}
}
return b[0:w], true
}