BlackForestBytes/goext
20
0
Fork 0
Code Actions

added gojson as a go/json fork (tag go1.20.2)

Browse Source
This commit is contained in:
Mike Schwörer 2023-04-20 14:30:24 +02:00
parent c13db6802e
commit d780c7965f
Signed by: Mikescher
GPG Key ID: D3C7172E0A70F8CF
23 changed files with 10496 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

541
gojson/bench_test.go Normal file
View File

@ -0,0 +1,541 @@
// 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.
// Large data benchmark.
// The JSON data is a summary of agl's changes in the
// go, webkit, and chromium open source projects.
// We benchmark converting between the JSON form
// and in-memory data structures.
package json
import (
"bytes"
"compress/gzip"
"fmt"
"internal/testenv"
"io"
"os"
"reflect"
"regexp"
"runtime"
"strings"
"sync"
"testing"
)
type codeResponse struct {
Tree *codeNode `json:"tree"`
Username string `json:"username"`
}
type codeNode struct {
Name string `json:"name"`
Kids []*codeNode `json:"kids"`
CLWeight float64 `json:"cl_weight"`
Touches int `json:"touches"`
MinT int64 `json:"min_t"`
MaxT int64 `json:"max_t"`
MeanT int64 `json:"mean_t"`
}
var codeJSON []byte
var codeStruct codeResponse
func codeInit() {
f, err := os.Open("testdata/code.json.gz")
if err != nil {
panic(err)
}
defer f.Close()
gz, err := gzip.NewReader(f)
if err != nil {
panic(err)
}
data, err := io.ReadAll(gz)
if err != nil {
panic(err)
}
codeJSON = data
if err := Unmarshal(codeJSON, &codeStruct); err != nil {
panic("unmarshal code.json: " + err.Error())
}
if data, err = Marshal(&codeStruct); err != nil {
panic("marshal code.json: " + err.Error())
}
if !bytes.Equal(data, codeJSON) {
println("different lengths", len(data), len(codeJSON))
for i := 0; i < len(data) && i < len(codeJSON); i++ {
if data[i] != codeJSON[i] {
println("re-marshal: changed at byte", i)
println("orig: ", string(codeJSON[i-10:i+10]))
println("new: ", string(data[i-10:i+10]))
break
}
}
panic("re-marshal code.json: different result")
}
}
func BenchmarkCodeEncoder(b *testing.B) {
b.ReportAllocs()
if codeJSON == nil {
b.StopTimer()
codeInit()
b.StartTimer()
}
b.RunParallel(func(pb *testing.PB) {
enc := NewEncoder(io.Discard)
for pb.Next() {
if err := enc.Encode(&codeStruct); err != nil {
b.Fatal("Encode:", err)
}
}
})
b.SetBytes(int64(len(codeJSON)))
}
func BenchmarkCodeEncoderError(b *testing.B) {
b.ReportAllocs()
if codeJSON == nil {
b.StopTimer()
codeInit()
b.StartTimer()
}
// Trigger an error in Marshal with cyclic data.
type Dummy struct {
Name string
Next *Dummy
}
dummy := Dummy{Name: "Dummy"}
dummy.Next = &dummy
b.RunParallel(func(pb *testing.PB) {
enc := NewEncoder(io.Discard)
for pb.Next() {
if err := enc.Encode(&codeStruct); err != nil {
b.Fatal("Encode:", err)
}
if _, err := Marshal(dummy); err == nil {
b.Fatal("expect an error here")
}
}
})
b.SetBytes(int64(len(codeJSON)))
}
func BenchmarkCodeMarshal(b *testing.B) {
b.ReportAllocs()
if codeJSON == nil {
b.StopTimer()
codeInit()
b.StartTimer()
}
b.RunParallel(func(pb *testing.PB) {
for pb.Next() {
if _, err := Marshal(&codeStruct); err != nil {
b.Fatal("Marshal:", err)
}
}
})
b.SetBytes(int64(len(codeJSON)))
}
func BenchmarkCodeMarshalError(b *testing.B) {
b.ReportAllocs()
if codeJSON == nil {
b.StopTimer()
codeInit()
b.StartTimer()
}
// Trigger an error in Marshal with cyclic data.
type Dummy struct {
Name string
Next *Dummy
}
dummy := Dummy{Name: "Dummy"}
dummy.Next = &dummy
b.RunParallel(func(pb *testing.PB) {
for pb.Next() {
if _, err := Marshal(&codeStruct); err != nil {
b.Fatal("Marshal:", err)
}
if _, err := Marshal(dummy); err == nil {
b.Fatal("expect an error here")
}
}
})
b.SetBytes(int64(len(codeJSON)))
}
func benchMarshalBytes(n int) func(*testing.B) {
sample := []byte("hello world")
// Use a struct pointer, to avoid an allocation when passing it as an
// interface parameter to Marshal.
v := &struct {
Bytes []byte
}{
bytes.Repeat(sample, (n/len(sample))+1)[:n],
}
return func(b *testing.B) {
for i := 0; i < b.N; i++ {
if _, err := Marshal(v); err != nil {
b.Fatal("Marshal:", err)
}
}
}
}
func benchMarshalBytesError(n int) func(*testing.B) {
sample := []byte("hello world")
// Use a struct pointer, to avoid an allocation when passing it as an
// interface parameter to Marshal.
v := &struct {
Bytes []byte
}{
bytes.Repeat(sample, (n/len(sample))+1)[:n],
}
// Trigger an error in Marshal with cyclic data.
type Dummy struct {
Name string
Next *Dummy
}
dummy := Dummy{Name: "Dummy"}
dummy.Next = &dummy
return func(b *testing.B) {
for i := 0; i < b.N; i++ {
if _, err := Marshal(v); err != nil {
b.Fatal("Marshal:", err)
}
if _, err := Marshal(dummy); err == nil {
b.Fatal("expect an error here")
}
}
}
}
func BenchmarkMarshalBytes(b *testing.B) {
b.ReportAllocs()
// 32 fits within encodeState.scratch.
b.Run("32", benchMarshalBytes(32))
// 256 doesn't fit in encodeState.scratch, but is small enough to
// allocate and avoid the slower base64.NewEncoder.
b.Run("256", benchMarshalBytes(256))
// 4096 is large enough that we want to avoid allocating for it.
b.Run("4096", benchMarshalBytes(4096))
}
func BenchmarkMarshalBytesError(b *testing.B) {
b.ReportAllocs()
// 32 fits within encodeState.scratch.
b.Run("32", benchMarshalBytesError(32))
// 256 doesn't fit in encodeState.scratch, but is small enough to
// allocate and avoid the slower base64.NewEncoder.
b.Run("256", benchMarshalBytesError(256))
// 4096 is large enough that we want to avoid allocating for it.
b.Run("4096", benchMarshalBytesError(4096))
}
func BenchmarkCodeDecoder(b *testing.B) {
b.ReportAllocs()
if codeJSON == nil {
b.StopTimer()
codeInit()
b.StartTimer()
}
b.RunParallel(func(pb *testing.PB) {
var buf bytes.Buffer
dec := NewDecoder(&buf)
var r codeResponse
for pb.Next() {
buf.Write(codeJSON)
// hide EOF
buf.WriteByte('\n')
buf.WriteByte('\n')
buf.WriteByte('\n')
if err := dec.Decode(&r); err != nil {
b.Fatal("Decode:", err)
}
}
})
b.SetBytes(int64(len(codeJSON)))
}
func BenchmarkUnicodeDecoder(b *testing.B) {
b.ReportAllocs()
j := []byte(`"\uD83D\uDE01"`)
b.SetBytes(int64(len(j)))
r := bytes.NewReader(j)
dec := NewDecoder(r)
var out string
b.ResetTimer()
for i := 0; i < b.N; i++ {
if err := dec.Decode(&out); err != nil {
b.Fatal("Decode:", err)
}
r.Seek(0, 0)
}
}
func BenchmarkDecoderStream(b *testing.B) {
b.ReportAllocs()
b.StopTimer()
var buf bytes.Buffer
dec := NewDecoder(&buf)
buf.WriteString(`"` + strings.Repeat("x", 1000000) + `"` + "\n\n\n")
var x any
if err := dec.Decode(&x); err != nil {
b.Fatal("Decode:", err)
}
ones := strings.Repeat(" 1\n", 300000) + "\n\n\n"
b.StartTimer()
for i := 0; i < b.N; i++ {
if i%300000 == 0 {
buf.WriteString(ones)
}
x = nil
if err := dec.Decode(&x); err != nil || x != 1.0 {
b.Fatalf("Decode: %v after %d", err, i)
}
}
}
func BenchmarkCodeUnmarshal(b *testing.B) {
b.ReportAllocs()
if codeJSON == nil {
b.StopTimer()
codeInit()
b.StartTimer()
}
b.RunParallel(func(pb *testing.PB) {
for pb.Next() {
var r codeResponse
if err := Unmarshal(codeJSON, &r); err != nil {
b.Fatal("Unmarshal:", err)
}
}
})
b.SetBytes(int64(len(codeJSON)))
}
func BenchmarkCodeUnmarshalReuse(b *testing.B) {
b.ReportAllocs()
if codeJSON == nil {
b.StopTimer()
codeInit()
b.StartTimer()
}
b.RunParallel(func(pb *testing.PB) {
var r codeResponse
for pb.Next() {
if err := Unmarshal(codeJSON, &r); err != nil {
b.Fatal("Unmarshal:", err)
}
}
})
b.SetBytes(int64(len(codeJSON)))
}
func BenchmarkUnmarshalString(b *testing.B) {
b.ReportAllocs()
data := []byte(`"hello, world"`)
b.RunParallel(func(pb *testing.PB) {
var s string
for pb.Next() {
if err := Unmarshal(data, &s); err != nil {
b.Fatal("Unmarshal:", err)
}
}
})
}
func BenchmarkUnmarshalFloat64(b *testing.B) {
b.ReportAllocs()
data := []byte(`3.14`)
b.RunParallel(func(pb *testing.PB) {
var f float64
for pb.Next() {
if err := Unmarshal(data, &f); err != nil {
b.Fatal("Unmarshal:", err)
}
}
})
}
func BenchmarkUnmarshalInt64(b *testing.B) {
b.ReportAllocs()
data := []byte(`3`)
b.RunParallel(func(pb *testing.PB) {
var x int64
for pb.Next() {
if err := Unmarshal(data, &x); err != nil {
b.Fatal("Unmarshal:", err)
}
}
})
}
func BenchmarkIssue10335(b *testing.B) {
b.ReportAllocs()
j := []byte(`{"a":{ }}`)
b.RunParallel(func(pb *testing.PB) {
var s struct{}
for pb.Next() {
if err := Unmarshal(j, &s); err != nil {
b.Fatal(err)
}
}
})
}
func BenchmarkIssue34127(b *testing.B) {
b.ReportAllocs()
j := struct {
Bar string `json:"bar,string"`
}{
Bar: `foobar`,
}
b.RunParallel(func(pb *testing.PB) {
for pb.Next() {
if _, err := Marshal(&j); err != nil {
b.Fatal(err)
}
}
})
}
func BenchmarkUnmapped(b *testing.B) {
b.ReportAllocs()
j := []byte(`{"s": "hello", "y": 2, "o": {"x": 0}, "a": [1, 99, {"x": 1}]}`)
b.RunParallel(func(pb *testing.PB) {
var s struct{}
for pb.Next() {
if err := Unmarshal(j, &s); err != nil {
b.Fatal(err)
}
}
})
}
func BenchmarkTypeFieldsCache(b *testing.B) {
b.ReportAllocs()
var maxTypes int = 1e6
if testenv.Builder() != "" {
maxTypes = 1e3 // restrict cache sizes on builders
}
// Dynamically generate many new types.
types := make([]reflect.Type, maxTypes)
fs := []reflect.StructField{{
Type: reflect.TypeOf(""),
Index: []int{0},
}}
for i := range types {
fs[0].Name = fmt.Sprintf("TypeFieldsCache%d", i)
types[i] = reflect.StructOf(fs)
}
// clearClear clears the cache. Other JSON operations, must not be running.
clearCache := func() {
fieldCache = sync.Map{}
}
// MissTypes tests the performance of repeated cache misses.
// This measures the time to rebuild a cache of size nt.
for nt := 1; nt <= maxTypes; nt *= 10 {
ts := types[:nt]
b.Run(fmt.Sprintf("MissTypes%d", nt), func(b *testing.B) {
nc := runtime.GOMAXPROCS(0)
for i := 0; i < b.N; i++ {
clearCache()
var wg sync.WaitGroup
for j := 0; j < nc; j++ {
wg.Add(1)
go func(j int) {
for _, t := range ts[(j*len(ts))/nc : ((j+1)*len(ts))/nc] {
cachedTypeFields(t)
}
wg.Done()
}(j)
}
wg.Wait()
}
})
}
// HitTypes tests the performance of repeated cache hits.
// This measures the average time of each cache lookup.
for nt := 1; nt <= maxTypes; nt *= 10 {
// Pre-warm a cache of size nt.
clearCache()
for _, t := range types[:nt] {
cachedTypeFields(t)
}
b.Run(fmt.Sprintf("HitTypes%d", nt), func(b *testing.B) {
b.RunParallel(func(pb *testing.PB) {
for pb.Next() {
cachedTypeFields(types[0])
}
})
})
}
}
func BenchmarkEncodeMarshaler(b *testing.B) {
b.ReportAllocs()
m := struct {
A int
B RawMessage
}{}
b.RunParallel(func(pb *testing.PB) {
enc := NewEncoder(io.Discard)
for pb.Next() {
if err := enc.Encode(&m); err != nil {
b.Fatal("Encode:", err)
}
}
})
}
func BenchmarkEncoderEncode(b *testing.B) {
b.ReportAllocs()
type T struct {
X, Y string
}
v := &T{"foo", "bar"}
b.RunParallel(func(pb *testing.PB) {
for pb.Next() {
if err := NewEncoder(io.Discard).Encode(v); err != nil {
b.Fatal(err)
}
}
})
}
func BenchmarkNumberIsValid(b *testing.B) {
s := "-61657.61667E+61673"
for i := 0; i < b.N; i++ {
isValidNumber(s)
}
}
func BenchmarkNumberIsValidRegexp(b *testing.B) {
var jsonNumberRegexp = regexp.MustCompile(`^-?(?:0|[1-9]\d*)(?:\.\d+)?(?:[eE][+-]?\d+)?$`)
s := "-61657.61667E+61673"
for i := 0; i < b.N; i++ {
jsonNumberRegexp.MatchString(s)
}
}

1311
gojson/decode.go Normal file
View File

File diff suppressed because it is too large Load Diff

2574
gojson/decode_test.go Normal file
View File

File diff suppressed because it is too large Load Diff

1417
gojson/encode.go Normal file
View File

File diff suppressed because it is too large Load Diff

1239
gojson/encode_test.go Normal file
View File

File diff suppressed because it is too large Load Diff

73
gojson/example_marshaling_test.go Normal file
View File

@ -0,0 +1,73 @@
// Copyright 2016 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 json_test
import (
"encoding/json"
"fmt"
"log"
"strings"
)
type Animal int
const (
Unknown Animal = iota
Gopher
Zebra
)
func (a *Animal) UnmarshalJSON(b []byte) error {
var s string
if err := json.Unmarshal(b, &s); err != nil {
return err
}
switch strings.ToLower(s) {
default:
*a = Unknown
case "gopher":
*a = Gopher
case "zebra":
*a = Zebra
}
return nil
}
func (a Animal) MarshalJSON() ([]byte, error) {
var s string
switch a {
default:
s = "unknown"
case Gopher:
s = "gopher"
case Zebra:
s = "zebra"
}
return json.Marshal(s)
}
func Example_customMarshalJSON() {
blob := `["gopher","armadillo","zebra","unknown","gopher","bee","gopher","zebra"]`
var zoo []Animal
if err := json.Unmarshal([]byte(blob), &zoo); err != nil {
log.Fatal(err)
}
census := make(map[Animal]int)
for _, animal := range zoo {
census[animal] += 1
}
fmt.Printf("Zoo Census:\n* Gophers: %d\n* Zebras: %d\n* Unknown: %d\n",
census[Gopher], census[Zebra], census[Unknown])
// Output:
// Zoo Census:
// * Gophers: 3
// * Zebras: 2
// * Unknown: 3
}

310
gojson/example_test.go Normal file
View File

@ -0,0 +1,310 @@
// 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 json_test
import (
"bytes"
"encoding/json"
"fmt"
"io"
"log"
"os"
"strings"
)
func ExampleMarshal() {
type ColorGroup struct {
ID int
Name string
Colors []string
}
group := ColorGroup{
ID: 1,
Name: "Reds",
Colors: []string{"Crimson", "Red", "Ruby", "Maroon"},
}
b, err := json.Marshal(group)
if err != nil {
fmt.Println("error:", err)
}
os.Stdout.Write(b)
// Output:
// {"ID":1,"Name":"Reds","Colors":["Crimson","Red","Ruby","Maroon"]}
}
func ExampleUnmarshal() {
var jsonBlob = []byte(`[
{"Name": "Platypus", "Order": "Monotremata"},
{"Name": "Quoll", "Order": "Dasyuromorphia"}
]`)
type Animal struct {
Name string
Order string
}
var animals []Animal
err := json.Unmarshal(jsonBlob, &animals)
if err != nil {
fmt.Println("error:", err)
}
fmt.Printf("%+v", animals)
// Output:
// [{Name:Platypus Order:Monotremata} {Name:Quoll Order:Dasyuromorphia}]
}
// This example uses a Decoder to decode a stream of distinct JSON values.
func ExampleDecoder() {
const jsonStream = `
{"Name": "Ed", "Text": "Knock knock."}
{"Name": "Sam", "Text": "Who's there?"}
{"Name": "Ed", "Text": "Go fmt."}
{"Name": "Sam", "Text": "Go fmt who?"}
{"Name": "Ed", "Text": "Go fmt yourself!"}
`
type Message struct {
Name, Text string
}
dec := json.NewDecoder(strings.NewReader(jsonStream))
for {
var m Message
if err := dec.Decode(&m); err == io.EOF {
break
} else if err != nil {
log.Fatal(err)
}
fmt.Printf("%s: %s\n", m.Name, m.Text)
}
// Output:
// Ed: Knock knock.
// Sam: Who's there?
// Ed: Go fmt.
// Sam: Go fmt who?
// Ed: Go fmt yourself!
}
// This example uses a Decoder to decode a stream of distinct JSON values.
func ExampleDecoder_Token() {
const jsonStream = `
{"Message": "Hello", "Array": [1, 2, 3], "Null": null, "Number": 1.234}
`
dec := json.NewDecoder(strings.NewReader(jsonStream))
for {
t, err := dec.Token()
if err == io.EOF {
break
}
if err != nil {
log.Fatal(err)
}
fmt.Printf("%T: %v", t, t)
if dec.More() {
fmt.Printf(" (more)")
}
fmt.Printf("\n")
}
// Output:
// json.Delim: { (more)
// string: Message (more)
// string: Hello (more)
// string: Array (more)
// json.Delim: [ (more)
// float64: 1 (more)
// float64: 2 (more)
// float64: 3
// json.Delim: ] (more)
// string: Null (more)
// <nil>: <nil> (more)
// string: Number (more)
// float64: 1.234
// json.Delim: }
}
// This example uses a Decoder to decode a streaming array of JSON objects.
func ExampleDecoder_Decode_stream() {
const jsonStream = `
[
{"Name": "Ed", "Text": "Knock knock."},
{"Name": "Sam", "Text": "Who's there?"},
{"Name": "Ed", "Text": "Go fmt."},
{"Name": "Sam", "Text": "Go fmt who?"},
{"Name": "Ed", "Text": "Go fmt yourself!"}
]
`
type Message struct {
Name, Text string
}
dec := json.NewDecoder(strings.NewReader(jsonStream))
// read open bracket
t, err := dec.Token()
if err != nil {
log.Fatal(err)
}
fmt.Printf("%T: %v\n", t, t)
// while the array contains values
for dec.More() {
var m Message
// decode an array value (Message)
err := dec.Decode(&m)
if err != nil {
log.Fatal(err)
}
fmt.Printf("%v: %v\n", m.Name, m.Text)
}
// read closing bracket
t, err = dec.Token()
if err != nil {
log.Fatal(err)
}
fmt.Printf("%T: %v\n", t, t)
// Output:
// json.Delim: [
// Ed: Knock knock.
// Sam: Who's there?
// Ed: Go fmt.
// Sam: Go fmt who?
// Ed: Go fmt yourself!
// json.Delim: ]
}
// This example uses RawMessage to delay parsing part of a JSON message.
func ExampleRawMessage_unmarshal() {
type Color struct {
Space string
Point json.RawMessage // delay parsing until we know the color space
}
type RGB struct {
R uint8
G uint8
B uint8
}
type YCbCr struct {
Y uint8
Cb int8
Cr int8
}
var j = []byte(`[
{"Space": "YCbCr", "Point": {"Y": 255, "Cb": 0, "Cr": -10}},
{"Space": "RGB", "Point": {"R": 98, "G": 218, "B": 255}}
]`)
var colors []Color
err := json.Unmarshal(j, &colors)
if err != nil {
log.Fatalln("error:", err)
}
for _, c := range colors {
var dst any
switch c.Space {
case "RGB":
dst = new(RGB)
case "YCbCr":
dst = new(YCbCr)
}
err := json.Unmarshal(c.Point, dst)
if err != nil {
log.Fatalln("error:", err)
}
fmt.Println(c.Space, dst)
}
// Output:
// YCbCr &{255 0 -10}
// RGB &{98 218 255}
}
// This example uses RawMessage to use a precomputed JSON during marshal.
func ExampleRawMessage_marshal() {
h := json.RawMessage(`{"precomputed": true}`)
c := struct {
Header *json.RawMessage `json:"header"`
Body string `json:"body"`
}{Header: &h, Body: "Hello Gophers!"}
b, err := json.MarshalIndent(&c, "", "\t")
if err != nil {
fmt.Println("error:", err)
}
os.Stdout.Write(b)
// Output:
// {
// "header": {
// "precomputed": true
// },
// "body": "Hello Gophers!"
// }
}
func ExampleIndent() {
type Road struct {
Name string
Number int
}
roads := []Road{
{"Diamond Fork", 29},
{"Sheep Creek", 51},
}
b, err := json.Marshal(roads)
if err != nil {
log.Fatal(err)
}
var out bytes.Buffer
json.Indent(&out, b, "=", "\t")
out.WriteTo(os.Stdout)
// Output:
// [
// = {
// = "Name": "Diamond Fork",
// = "Number": 29
// = },
// = {
// = "Name": "Sheep Creek",
// = "Number": 51
// = }
// =]
}
func ExampleMarshalIndent() {
data := map[string]int{
"a": 1,
"b": 2,
}
b, err := json.MarshalIndent(data, "<prefix>", "<indent>")
if err != nil {
log.Fatal(err)
}
fmt.Println(string(b))
// Output:
// {
// <prefix><indent>"a": 1,
// <prefix><indent>"b": 2
// <prefix>}
}
func ExampleValid() {
goodJSON := `{"example": 1}`
badJSON := `{"example":2:]}}`
fmt.Println(json.Valid([]byte(goodJSON)), json.Valid([]byte(badJSON)))
// Output:
// true false
}
func ExampleHTMLEscape() {
var out bytes.Buffer
json.HTMLEscape(&out, []byte(`{"Name":"<b>HTML content</b>"}`))
out.WriteTo(os.Stdout)
// Output:
//{"Name":"\u003cb\u003eHTML content\u003c/b\u003e"}
}

67
gojson/example_text_marshaling_test.go Normal file
View File

@ -0,0 +1,67 @@
// Copyright 2018 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 json_test
import (
"encoding/json"
"fmt"
"log"
"strings"
)
type Size int
const (
Unrecognized Size = iota
Small
Large
)
func (s *Size) UnmarshalText(text []byte) error {
switch strings.ToLower(string(text)) {
default:
*s = Unrecognized
case "small":
*s = Small
case "large":
*s = Large
}
return nil
}
func (s Size) MarshalText() ([]byte, error) {
var name string
switch s {
default:
name = "unrecognized"
case Small:
name = "small"
case Large:
name = "large"
}
return []byte(name), nil
}
func Example_textMarshalJSON() {
blob := `["small","regular","large","unrecognized","small","normal","small","large"]`
var inventory []Size
if err := json.Unmarshal([]byte(blob), &inventory); err != nil {
log.Fatal(err)
}
counts := make(map[Size]int)
for _, size := range inventory {
counts[size] += 1
}
fmt.Printf("Inventory Counts:\n* Small: %d\n* Large: %d\n* Unrecognized: %d\n",
counts[Small], counts[Large], counts[Unrecognized])
// Output:
// Inventory Counts:
// * Small: 3
// * Large: 2
// * Unrecognized: 3
}

141
gojson/fold.go Normal file
View File

@ -0,0 +1,141 @@
// Copyright 2013 The Go Authors. All rights reserved.
// Use of this source code is governed by a BSD-style
// license that can be found in the LICENSE file.
package json
import (
"bytes"
"unicode/utf8"
)
const (
caseMask = ^byte(0x20) // Mask to ignore case in ASCII.
kelvin = '\u212a'
smallLongEss = '\u017f'
)
// foldFunc returns one of four different case folding equivalence
// functions, from most general (and slow) to fastest:
//
// 1) bytes.EqualFold, if the key s contains any non-ASCII UTF-8
// 2) equalFoldRight, if s contains special folding ASCII ('k', 'K', 's', 'S')
// 3) asciiEqualFold, no special, but includes non-letters (including _)
// 4) simpleLetterEqualFold, no specials, no non-letters.
//
// The letters S and K are special because they map to 3 runes, not just 2:
// - S maps to s and to U+017F 'ſ' Latin small letter long s
// - k maps to K and to U+212A 'K' Kelvin sign
//
// See https://play.golang.org/p/tTxjOc0OGo
//
// The returned function is specialized for matching against s and
// should only be given s. It's not curried for performance reasons.
func foldFunc(s []byte) func(s, t []byte) bool {
nonLetter := false
special := false // special letter
for _, b := range s {
if b >= utf8.RuneSelf {
return bytes.EqualFold
}
upper := b & caseMask
if upper < 'A' || upper > 'Z' {
nonLetter = true
} else if upper == 'K' || upper == 'S' {
// See above for why these letters are special.
special = true
}
}
if special {
return equalFoldRight
}
if nonLetter {
return asciiEqualFold
}
return simpleLetterEqualFold
}
// equalFoldRight is a specialization of bytes.EqualFold when s is
// known to be all ASCII (including punctuation), but contains an 's',
// 'S', 'k', or 'K', requiring a Unicode fold on the bytes in t.
// See comments on foldFunc.
func equalFoldRight(s, t []byte) bool {
for _, sb := range s {
if len(t) == 0 {
return false
}
tb := t[0]
if tb < utf8.RuneSelf {
if sb != tb {
sbUpper := sb & caseMask
if 'A' <= sbUpper && sbUpper <= 'Z' {
if sbUpper != tb&caseMask {
return false
}
} else {
return false
}
}
t = t[1:]
continue
}
// sb is ASCII and t is not. t must be either kelvin
// sign or long s; sb must be s, S, k, or K.
tr, size := utf8.DecodeRune(t)
switch sb {
case 's', 'S':
if tr != smallLongEss {
return false
}
case 'k', 'K':
if tr != kelvin {
return false
}
default:
return false
}
t = t[size:]
}
return len(t) == 0
}
// asciiEqualFold is a specialization of bytes.EqualFold for use when
// s is all ASCII (but may contain non-letters) and contains no
// special-folding letters.
// See comments on foldFunc.
func asciiEqualFold(s, t []byte) bool {
if len(s) != len(t) {
return false
}
for i, sb := range s {
tb := t[i]
if sb == tb {
continue
}
if ('a' <= sb && sb <= 'z') || ('A' <= sb && sb <= 'Z') {
if sb&caseMask != tb&caseMask {
return false
}
} else {
return false
}
}
return true
}
// simpleLetterEqualFold is a specialization of bytes.EqualFold for
// use when s is all ASCII letters (no underscores, etc) and also
// doesn't contain 'k', 'K', 's', or 'S'.
// See comments on foldFunc.
func simpleLetterEqualFold(s, t []byte) bool {
if len(s) != len(t) {
return false
}
for i, b := range s {
if b&caseMask != t[i]&caseMask {
return false
}
}
return true
}

110
gojson/fold_test.go Normal file
View File

@ -0,0 +1,110 @@
// Copyright 2013 The Go Authors. All rights reserved.
// Use of this source code is governed by a BSD-style
// license that can be found in the LICENSE file.
package json
import (
"bytes"
"strings"
"testing"
"unicode/utf8"
)
var foldTests = []struct {
fn func(s, t []byte) bool
s, t string
want bool
}{
{equalFoldRight, "", "", true},
{equalFoldRight, "a", "a", true},
{equalFoldRight, "", "a", false},
{equalFoldRight, "a", "", false},
{equalFoldRight, "a", "A", true},
{equalFoldRight, "AB", "ab", true},
{equalFoldRight, "AB", "ac", false},
{equalFoldRight, "sbkKc", "ſbKKc", true},
{equalFoldRight, "SbKkc", "ſbKKc", true},
{equalFoldRight, "SbKkc", "ſbKK", false},
{equalFoldRight, "e", "é", false},
{equalFoldRight, "s", "S", true},
{simpleLetterEqualFold, "", "", true},
{simpleLetterEqualFold, "abc", "abc", true},
{simpleLetterEqualFold, "abc", "ABC", true},
{simpleLetterEqualFold, "abc", "ABCD", false},
{simpleLetterEqualFold, "abc", "xxx", false},
{asciiEqualFold, "a_B", "A_b", true},
{asciiEqualFold, "aa@", "aa`", false}, // verify 0x40 and 0x60 aren't case-equivalent
}
func TestFold(t *testing.T) {
for i, tt := range foldTests {
if got := tt.fn([]byte(tt.s), []byte(tt.t)); got != tt.want {
t.Errorf("%d. %q, %q = %v; want %v", i, tt.s, tt.t, got, tt.want)
}
truth := strings.EqualFold(tt.s, tt.t)
if truth != tt.want {
t.Errorf("strings.EqualFold doesn't agree with case %d", i)
}
}
}
func TestFoldAgainstUnicode(t *testing.T) {
var buf1, buf2 []byte
var runes []rune
for i := 0x20; i <= 0x7f; i++ {
runes = append(runes, rune(i))
}
runes = append(runes, kelvin, smallLongEss)
funcs := []struct {
name string
fold func(s, t []byte) bool
letter bool // must be ASCII letter
simple bool // must be simple ASCII letter (not 'S' or 'K')
}{
{
name: "equalFoldRight",
fold: equalFoldRight,
},
{
name: "asciiEqualFold",
fold: asciiEqualFold,
simple: true,
},
{
name: "simpleLetterEqualFold",
fold: simpleLetterEqualFold,
simple: true,
letter: true,
},
}
for _, ff := range funcs {
for _, r := range runes {
if r >= utf8.RuneSelf {
continue
}
if ff.letter && !isASCIILetter(byte(r)) {
continue
}
if ff.simple && (r == 's' || r == 'S' || r == 'k' || r == 'K') {
continue
}
for _, r2 := range runes {
buf1 = append(utf8.AppendRune(append(buf1[:0], 'x'), r), 'x')
buf2 = append(utf8.AppendRune(append(buf2[:0], 'x'), r2), 'x')
want := bytes.EqualFold(buf1, buf2)
if got := ff.fold(buf1, buf2); got != want {
t.Errorf("%s(%q, %q) = %v; want %v", ff.name, buf1, buf2, got, want)
}
}
}
}
}
func isASCIILetter(b byte) bool {
return ('A' <= b && b <= 'Z') || ('a' <= b && b <= 'z')
}

42
gojson/fuzz.go Normal file
View File

@ -0,0 +1,42 @@
// Copyright 2019 The Go Authors. All rights reserved.
// Use of this source code is governed by a BSD-style
// license that can be found in the LICENSE file.
//go:build gofuzz
package json
import (
"fmt"
)
func Fuzz(data []byte) (score int) {
for _, ctor := range []func() any{
func() any { return new(any) },
func() any { return new(map[string]any) },
func() any { return new([]any) },
} {
v := ctor()
err := Unmarshal(data, v)
if err != nil {
continue
}
score = 1
m, err := Marshal(v)
if err != nil {
fmt.Printf("v=%#v\n", v)
panic(err)
}
u := ctor()
err = Unmarshal(m, u)
if err != nil {
fmt.Printf("v=%#v\n", v)
fmt.Printf("m=%s\n", m)
panic(err)
}
}
return
}

83
gojson/fuzz_test.go Normal file
View File

@ -0,0 +1,83 @@
// Copyright 2021 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 json
import (
"bytes"
"io"
"testing"
)
func FuzzUnmarshalJSON(f *testing.F) {
f.Add([]byte(`{
"object": {
"slice": [
1,
2.0,
"3",
[4],
{5: {}}
]
},
"slice": [[]],
"string": ":)",
"int": 1e5,
"float": 3e-9"
}`))
f.Fuzz(func(t *testing.T, b []byte) {
for _, typ := range []func() interface{}{
func() interface{} { return new(interface{}) },
func() interface{} { return new(map[string]interface{}) },
func() interface{} { return new([]interface{}) },
} {
i := typ()
if err := Unmarshal(b, i); err != nil {
return
}
encoded, err := Marshal(i)
if err != nil {
t.Fatalf("failed to marshal: %s", err)
}
if err := Unmarshal(encoded, i); err != nil {
t.Fatalf("failed to roundtrip: %s", err)
}
}
})
}
func FuzzDecoderToken(f *testing.F) {
f.Add([]byte(`{
"object": {
"slice": [
1,
2.0,
"3",
[4],
{5: {}}
]
},
"slice": [[]],
"string": ":)",
"int": 1e5,
"float": 3e-9"
}`))
f.Fuzz(func(t *testing.T, b []byte) {
r := bytes.NewReader(b)
d := NewDecoder(r)
for {
_, err := d.Token()
if err != nil {
if err == io.EOF {
break
}
return
}
}
})
}

143
gojson/indent.go Normal file
View File

@ -0,0 +1,143 @@
// 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.
package json
import (
"bytes"
)
// Compact appends to dst the JSON-encoded src with
// insignificant space characters elided.
func Compact(dst *bytes.Buffer, src []byte) error {
return compact(dst, src, false)
}
func compact(dst *bytes.Buffer, src []byte, escape bool) error {
origLen := dst.Len()
scan := newScanner()
defer freeScanner(scan)
start := 0
for i, c := range src {
if escape && (c == '<' || c == '>' || c == '&') {
if start < i {
dst.Write(src[start:i])
}
dst.WriteString(`\u00`)
dst.WriteByte(hex[c>>4])
dst.WriteByte(hex[c&0xF])
start = i + 1
}
// Convert U+2028 and U+2029 (E2 80 A8 and E2 80 A9).
if escape && c == 0xE2 && i+2 < len(src) && src[i+1] == 0x80 && src[i+2]&^1 == 0xA8 {
if start < i {
dst.Write(src[start:i])
}
dst.WriteString(`\u202`)
dst.WriteByte(hex[src[i+2]&0xF])
start = i + 3
}
v := scan.step(scan, c)
if v >= scanSkipSpace {
if v == scanError {
break
}
if start < i {
dst.Write(src[start:i])
}
start = i + 1
}
}
if scan.eof() == scanError {
dst.Truncate(origLen)
return scan.err
}
if start < len(src) {
dst.Write(src[start:])
}
return nil
}
func newline(dst *bytes.Buffer, prefix, indent string, depth int) {
dst.WriteByte('\n')
dst.WriteString(prefix)
for i := 0; i < depth; i++ {
dst.WriteString(indent)
}
}
// Indent appends to dst an indented form of the JSON-encoded src.
// Each element in a JSON object or array begins on a new,
// indented line beginning with prefix followed by one or more
// copies of indent according to the indentation nesting.
// The data appended to dst does not begin with the prefix nor
// any indentation, to make it easier to embed inside other formatted JSON data.
// Although leading space characters (space, tab, carriage return, newline)
// at the beginning of src are dropped, trailing space characters
// at the end of src are preserved and copied to dst.
// For example, if src has no trailing spaces, neither will dst;
// if src ends in a trailing newline, so will dst.
func Indent(dst *bytes.Buffer, src []byte, prefix, indent string) error {
origLen := dst.Len()
scan := newScanner()
defer freeScanner(scan)
needIndent := false
depth := 0
for _, c := range src {
scan.bytes++
v := scan.step(scan, c)
if v == scanSkipSpace {
continue
}
if v == scanError {
break
}
if needIndent && v != scanEndObject && v != scanEndArray {
needIndent = false
depth++
newline(dst, prefix, indent, depth)
}
// Emit semantically uninteresting bytes
// (in particular, punctuation in strings) unmodified.
if v == scanContinue {
dst.WriteByte(c)
continue
}
// Add spacing around real punctuation.
switch c {
case '{', '[':
// delay indent so that empty object and array are formatted as {} and [].
needIndent = true
dst.WriteByte(c)
case ',':
dst.WriteByte(c)
newline(dst, prefix, indent, depth)
case ':':
dst.WriteByte(c)
dst.WriteByte(' ')
case '}', ']':
if needIndent {
// suppress indent in empty object/array
needIndent = false
} else {
depth--
newline(dst, prefix, indent, depth)
}
dst.WriteByte(c)
default:
dst.WriteByte(c)
}
}
if scan.eof() == scanError {
dst.Truncate(origLen)
return scan.err
}
return nil
}

118
gojson/number_test.go Normal file
View File

@ -0,0 +1,118 @@
// 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 json
import (
"regexp"
"testing"
)
func TestNumberIsValid(t *testing.T) {
// From: https://stackoverflow.com/a/13340826
var jsonNumberRegexp = regexp.MustCompile(`^-?(?:0|[1-9]\d*)(?:\.\d+)?(?:[eE][+-]?\d+)?$`)
validTests := []string{
"0",
"-0",
"1",
"-1",
"0.1",
"-0.1",
"1234",
"-1234",
"12.34",
"-12.34",
"12E0",
"12E1",
"12e34",
"12E-0",
"12e+1",
"12e-34",
"-12E0",
"-12E1",
"-12e34",
"-12E-0",
"-12e+1",
"-12e-34",
"1.2E0",
"1.2E1",
"1.2e34",
"1.2E-0",
"1.2e+1",
"1.2e-34",
"-1.2E0",
"-1.2E1",
"-1.2e34",
"-1.2E-0",
"-1.2e+1",
"-1.2e-34",
"0E0",
"0E1",
"0e34",
"0E-0",
"0e+1",
"0e-34",
"-0E0",
"-0E1",
"-0e34",
"-0E-0",
"-0e+1",
"-0e-34",
}
for _, test := range validTests {
if !isValidNumber(test) {
t.Errorf("%s should be valid", test)
}
var f float64
if err := Unmarshal([]byte(test), &f); err != nil {
t.Errorf("%s should be valid but Unmarshal failed: %v", test, err)
}
if !jsonNumberRegexp.MatchString(test) {
t.Errorf("%s should be valid but regexp does not match", test)
}
}
invalidTests := []string{
"",
"invalid",
"1.0.1",
"1..1",
"-1-2",
"012a42",
"01.2",
"012",
"12E12.12",
"1e2e3",
"1e+-2",
"1e--23",
"1e",
"e1",
"1e+",
"1ea",
"1a",
"1.a",
"1.",
"01",
"1.e1",
}
for _, test := range invalidTests {
if isValidNumber(test) {
t.Errorf("%s should be invalid", test)
}
var f float64
if err := Unmarshal([]byte(test), &f); err == nil {
t.Errorf("%s should be invalid but unmarshal wrote %v", test, f)
}
if jsonNumberRegexp.MatchString(test) {
t.Errorf("%s should be invalid but matches regexp", test)
}
}
}

610
gojson/scanner.go Normal file
View File

@ -0,0 +1,610 @@
// 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.
package json
// JSON value parser state machine.
// Just about at the limit of what is reasonable to write by hand.
// Some parts are a bit tedious, but overall it nicely factors out the
// otherwise common code from the multiple scanning functions
// in this package (Compact, Indent, checkValid, etc).
//
// This file starts with two simple examples using the scanner
// before diving into the scanner itself.
import (
"strconv"
"sync"
)
// Valid reports whether data is a valid JSON encoding.
func Valid(data []byte) bool {
scan := newScanner()
defer freeScanner(scan)
return checkValid(data, scan) == nil
}
// checkValid verifies that data is valid JSON-encoded data.
// scan is passed in for use by checkValid to avoid an allocation.
// checkValid returns nil or a SyntaxError.
func checkValid(data []byte, scan *scanner) error {
scan.reset()
for _, c := range data {
scan.bytes++
if scan.step(scan, c) == scanError {
return scan.err
}
}
if scan.eof() == scanError {
return scan.err
}
return nil
}
// A SyntaxError is a description of a JSON syntax error.
// Unmarshal will return a SyntaxError if the JSON can't be parsed.
type SyntaxError struct {
msg string // description of error
Offset int64 // error occurred after reading Offset bytes
}
func (e *SyntaxError) Error() string { return e.msg }
// A scanner is a JSON scanning state machine.
// Callers call scan.reset and then pass bytes in one at a time
// by calling scan.step(&scan, c) for each byte.
// The return value, referred to as an opcode, tells the
// caller about significant parsing events like beginning
// and ending literals, objects, and arrays, so that the
// caller can follow along if it wishes.
// The return value scanEnd indicates that a single top-level
// JSON value has been completed, *before* the byte that
// just got passed in. (The indication must be delayed in order
// to recognize the end of numbers: is 123 a whole value or
// the beginning of 12345e+6?).
type scanner struct {
// The step is a func to be called to execute the next transition.
// Also tried using an integer constant and a single func
// with a switch, but using the func directly was 10% faster
// on a 64-bit Mac Mini, and it's nicer to read.
step func(*scanner, byte) int
// Reached end of top-level value.
endTop bool
// Stack of what we're in the middle of - array values, object keys, object values.
parseState []int
// Error that happened, if any.
err error
// total bytes consumed, updated by decoder.Decode (and deliberately
// not set to zero by scan.reset)
bytes int64
}
var scannerPool = sync.Pool{
New: func() any {
return &scanner{}
},
}
func newScanner() *scanner {
scan := scannerPool.Get().(*scanner)
// scan.reset by design doesn't set bytes to zero
scan.bytes = 0
scan.reset()
return scan
}
func freeScanner(scan *scanner) {
// Avoid hanging on to too much memory in extreme cases.
if len(scan.parseState) > 1024 {
scan.parseState = nil
}
scannerPool.Put(scan)
}
// These values are returned by the state transition functions
// assigned to scanner.state and the method scanner.eof.
// They give details about the current state of the scan that
// callers might be interested to know about.
// It is okay to ignore the return value of any particular
// call to scanner.state: if one call returns scanError,
// every subsequent call will return scanError too.
const (
// Continue.
scanContinue = iota // uninteresting byte
scanBeginLiteral // end implied by next result != scanContinue
scanBeginObject // begin object
scanObjectKey // just finished object key (string)
scanObjectValue // just finished non-last object value
scanEndObject // end object (implies scanObjectValue if possible)
scanBeginArray // begin array
scanArrayValue // just finished array value
scanEndArray // end array (implies scanArrayValue if possible)
scanSkipSpace // space byte; can skip; known to be last "continue" result
// Stop.
scanEnd // top-level value ended *before* this byte; known to be first "stop" result
scanError // hit an error, scanner.err.
)
// These values are stored in the parseState stack.
// They give the current state of a composite value
// being scanned. If the parser is inside a nested value
// the parseState describes the nested state, outermost at entry 0.
const (
parseObjectKey = iota // parsing object key (before colon)
parseObjectValue // parsing object value (after colon)
parseArrayValue // parsing array value
)
// This limits the max nesting depth to prevent stack overflow.
// This is permitted by https://tools.ietf.org/html/rfc7159#section-9
const maxNestingDepth = 10000
// reset prepares the scanner for use.
// It must be called before calling s.step.
func (s *scanner) reset() {
s.step = stateBeginValue
s.parseState = s.parseState[0:0]
s.err = nil
s.endTop = false
}
// eof tells the scanner that the end of input has been reached.
// It returns a scan status just as s.step does.
func (s *scanner) eof() int {
if s.err != nil {
return scanError
}
if s.endTop {
return scanEnd
}
s.step(s, ' ')
if s.endTop {
return scanEnd
}
if s.err == nil {
s.err = &SyntaxError{"unexpected end of JSON input", s.bytes}
}
return scanError
}
// pushParseState pushes a new parse state p onto the parse stack.
// an error state is returned if maxNestingDepth was exceeded, otherwise successState is returned.
func (s *scanner) pushParseState(c byte, newParseState int, successState int) int {
s.parseState = append(s.parseState, newParseState)
if len(s.parseState) <= maxNestingDepth {
return successState
}
return s.error(c, "exceeded max depth")
}
// popParseState pops a parse state (already obtained) off the stack
// and updates s.step accordingly.
func (s *scanner) popParseState() {
n := len(s.parseState) - 1
s.parseState = s.parseState[0:n]
if n == 0 {
s.step = stateEndTop
s.endTop = true
} else {
s.step = stateEndValue
}
}
func isSpace(c byte) bool {
return c <= ' ' && (c == ' ' || c == '\t' || c == '\r' || c == '\n')
}
// stateBeginValueOrEmpty is the state after reading `[`.
func stateBeginValueOrEmpty(s *scanner, c byte) int {
if isSpace(c) {
return scanSkipSpace
}
if c == ']' {
return stateEndValue(s, c)
}
return stateBeginValue(s, c)
}
// stateBeginValue is the state at the beginning of the input.
func stateBeginValue(s *scanner, c byte) int {
if isSpace(c) {
return scanSkipSpace
}
switch c {
case '{':
s.step = stateBeginStringOrEmpty
return s.pushParseState(c, parseObjectKey, scanBeginObject)
case '[':
s.step = stateBeginValueOrEmpty
return s.pushParseState(c, parseArrayValue, scanBeginArray)
case '"':
s.step = stateInString
return scanBeginLiteral
case '-':
s.step = stateNeg
return scanBeginLiteral
case '0': // beginning of 0.123
s.step = state0
return scanBeginLiteral
case 't': // beginning of true
s.step = stateT
return scanBeginLiteral
case 'f': // beginning of false
s.step = stateF
return scanBeginLiteral
case 'n': // beginning of null
s.step = stateN
return scanBeginLiteral
}
if '1' <= c && c <= '9' { // beginning of 1234.5
s.step = state1
return scanBeginLiteral
}
return s.error(c, "looking for beginning of value")
}
// stateBeginStringOrEmpty is the state after reading `{`.
func stateBeginStringOrEmpty(s *scanner, c byte) int {
if isSpace(c) {
return scanSkipSpace
}
if c == '}' {
n := len(s.parseState)
s.parseState[n-1] = parseObjectValue
return stateEndValue(s, c)
}
return stateBeginString(s, c)
}
// stateBeginString is the state after reading `{"key": value,`.
func stateBeginString(s *scanner, c byte) int {
if isSpace(c) {
return scanSkipSpace
}
if c == '"' {
s.step = stateInString
return scanBeginLiteral
}
return s.error(c, "looking for beginning of object key string")
}
// stateEndValue is the state after completing a value,
// such as after reading `{}` or `true` or `["x"`.
func stateEndValue(s *scanner, c byte) int {
n := len(s.parseState)
if n == 0 {
// Completed top-level before the current byte.
s.step = stateEndTop
s.endTop = true
return stateEndTop(s, c)
}
if isSpace(c) {
s.step = stateEndValue
return scanSkipSpace
}
ps := s.parseState[n-1]
switch ps {
case parseObjectKey:
if c == ':' {
s.parseState[n-1] = parseObjectValue
s.step = stateBeginValue
return scanObjectKey
}
return s.error(c, "after object key")
case parseObjectValue:
if c == ',' {
s.parseState[n-1] = parseObjectKey
s.step = stateBeginString
return scanObjectValue
}
if c == '}' {
s.popParseState()
return scanEndObject
}
return s.error(c, "after object key:value pair")
case parseArrayValue:
if c == ',' {
s.step = stateBeginValue
return scanArrayValue
}
if c == ']' {
s.popParseState()
return scanEndArray
}
return s.error(c, "after array element")
}
return s.error(c, "")
}
// stateEndTop is the state after finishing the top-level value,
// such as after reading `{}` or `[1,2,3]`.
// Only space characters should be seen now.
func stateEndTop(s *scanner, c byte) int {
if !isSpace(c) {
// Complain about non-space byte on next call.
s.error(c, "after top-level value")
}
return scanEnd
}
// stateInString is the state after reading `"`.
func stateInString(s *scanner, c byte) int {
if c == '"' {
s.step = stateEndValue
return scanContinue
}
if c == '\\' {
s.step = stateInStringEsc
return scanContinue
}
if c < 0x20 {
return s.error(c, "in string literal")
}
return scanContinue
}
// stateInStringEsc is the state after reading `"\` during a quoted string.
func stateInStringEsc(s *scanner, c byte) int {
switch c {
case 'b', 'f', 'n', 'r', 't', '\\', '/', '"':
s.step = stateInString
return scanContinue
case 'u':
s.step = stateInStringEscU
return scanContinue
}
return s.error(c, "in string escape code")
}
// stateInStringEscU is the state after reading `"\u` during a quoted string.
func stateInStringEscU(s *scanner, c byte) int {
if '0' <= c && c <= '9' || 'a' <= c && c <= 'f' || 'A' <= c && c <= 'F' {
s.step = stateInStringEscU1
return scanContinue
}
// numbers
return s.error(c, "in \\u hexadecimal character escape")
}
// stateInStringEscU1 is the state after reading `"\u1` during a quoted string.
func stateInStringEscU1(s *scanner, c byte) int {
if '0' <= c && c <= '9' || 'a' <= c && c <= 'f' || 'A' <= c && c <= 'F' {
s.step = stateInStringEscU12
return scanContinue
}
// numbers
return s.error(c, "in \\u hexadecimal character escape")
}
// stateInStringEscU12 is the state after reading `"\u12` during a quoted string.
func stateInStringEscU12(s *scanner, c byte) int {
if '0' <= c && c <= '9' || 'a' <= c && c <= 'f' || 'A' <= c && c <= 'F' {
s.step = stateInStringEscU123
return scanContinue
}
// numbers
return s.error(c, "in \\u hexadecimal character escape")
}
// stateInStringEscU123 is the state after reading `"\u123` during a quoted string.
func stateInStringEscU123(s *scanner, c byte) int {
if '0' <= c && c <= '9' || 'a' <= c && c <= 'f' || 'A' <= c && c <= 'F' {
s.step = stateInString
return scanContinue
}
// numbers
return s.error(c, "in \\u hexadecimal character escape")
}
// stateNeg is the state after reading `-` during a number.
func stateNeg(s *scanner, c byte) int {
if c == '0' {
s.step = state0
return scanContinue
}
if '1' <= c && c <= '9' {
s.step = state1
return scanContinue
}
return s.error(c, "in numeric literal")
}
// state1 is the state after reading a non-zero integer during a number,
// such as after reading `1` or `100` but not `0`.
func state1(s *scanner, c byte) int {
if '0' <= c && c <= '9' {
s.step = state1
return scanContinue
}
return state0(s, c)
}
// state0 is the state after reading `0` during a number.
func state0(s *scanner, c byte) int {
if c == '.' {
s.step = stateDot
return scanContinue
}
if c == 'e' || c == 'E' {
s.step = stateE
return scanContinue
}
return stateEndValue(s, c)
}
// stateDot is the state after reading the integer and decimal point in a number,
// such as after reading `1.`.
func stateDot(s *scanner, c byte) int {
if '0' <= c && c <= '9' {
s.step = stateDot0
return scanContinue
}
return s.error(c, "after decimal point in numeric literal")
}
// stateDot0 is the state after reading the integer, decimal point, and subsequent
// digits of a number, such as after reading `3.14`.
func stateDot0(s *scanner, c byte) int {
if '0' <= c && c <= '9' {
return scanContinue
}
if c == 'e' || c == 'E' {
s.step = stateE
return scanContinue
}
return stateEndValue(s, c)
}
// stateE is the state after reading the mantissa and e in a number,
// such as after reading `314e` or `0.314e`.
func stateE(s *scanner, c byte) int {
if c == '+' || c == '-' {
s.step = stateESign
return scanContinue
}
return stateESign(s, c)
}
// stateESign is the state after reading the mantissa, e, and sign in a number,
// such as after reading `314e-` or `0.314e+`.
func stateESign(s *scanner, c byte) int {
if '0' <= c && c <= '9' {
s.step = stateE0
return scanContinue
}
return s.error(c, "in exponent of numeric literal")
}
// stateE0 is the state after reading the mantissa, e, optional sign,
// and at least one digit of the exponent in a number,
// such as after reading `314e-2` or `0.314e+1` or `3.14e0`.
func stateE0(s *scanner, c byte) int {
if '0' <= c && c <= '9' {
return scanContinue
}
return stateEndValue(s, c)
}
// stateT is the state after reading `t`.
func stateT(s *scanner, c byte) int {
if c == 'r' {
s.step = stateTr
return scanContinue
}
return s.error(c, "in literal true (expecting 'r')")
}
// stateTr is the state after reading `tr`.
func stateTr(s *scanner, c byte) int {
if c == 'u' {
s.step = stateTru
return scanContinue
}
return s.error(c, "in literal true (expecting 'u')")
}
// stateTru is the state after reading `tru`.
func stateTru(s *scanner, c byte) int {
if c == 'e' {
s.step = stateEndValue
return scanContinue
}
return s.error(c, "in literal true (expecting 'e')")
}
// stateF is the state after reading `f`.
func stateF(s *scanner, c byte) int {
if c == 'a' {
s.step = stateFa
return scanContinue
}
return s.error(c, "in literal false (expecting 'a')")
}
// stateFa is the state after reading `fa`.
func stateFa(s *scanner, c byte) int {
if c == 'l' {
s.step = stateFal
return scanContinue
}
return s.error(c, "in literal false (expecting 'l')")
}
// stateFal is the state after reading `fal`.
func stateFal(s *scanner, c byte) int {
if c == 's' {
s.step = stateFals
return scanContinue
}
return s.error(c, "in literal false (expecting 's')")
}
// stateFals is the state after reading `fals`.
func stateFals(s *scanner, c byte) int {
if c == 'e' {
s.step = stateEndValue
return scanContinue
}
return s.error(c, "in literal false (expecting 'e')")
}
// stateN is the state after reading `n`.
func stateN(s *scanner, c byte) int {
if c == 'u' {
s.step = stateNu
return scanContinue
}
return s.error(c, "in literal null (expecting 'u')")
}
// stateNu is the state after reading `nu`.
func stateNu(s *scanner, c byte) int {
if c == 'l' {
s.step = stateNul
return scanContinue
}
return s.error(c, "in literal null (expecting 'l')")
}
// stateNul is the state after reading `nul`.
func stateNul(s *scanner, c byte) int {
if c == 'l' {
s.step = stateEndValue
return scanContinue
}
return s.error(c, "in literal null (expecting 'l')")
}
// stateError is the state after reaching a syntax error,
// such as after reading `[1}` or `5.1.2`.
func stateError(s *scanner, c byte) int {
return scanError
}
// error records an error and switches to the error state.
func (s *scanner) error(c byte, context string) int {
s.step = stateError
s.err = &SyntaxError{"invalid character " + quoteChar(c) + " " + context, s.bytes}
return scanError
}
// quoteChar formats c as a quoted character literal.
func quoteChar(c byte) string {
// special cases - different from quoted strings
if c == '\'' {
return `'\''`
}
if c == '"' {
return `'"'`
}
// use quoted string with different quotation marks
s := strconv.Quote(string(c))
return "'" + s[1:len(s)-1] + "'"
}

301
gojson/scanner_test.go Normal file
View File

@ -0,0 +1,301 @@
// 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.
package json
import (
"bytes"
"math"
"math/rand"
"reflect"
"testing"
)
var validTests = []struct {
data string
ok bool
}{
{`foo`, false},
{`}{`, false},
{`{]`, false},
{`{}`, true},
{`{"foo":"bar"}`, true},
{`{"foo":"bar","bar":{"baz":["qux"]}}`, true},
}
func TestValid(t *testing.T) {
for _, tt := range validTests {
if ok := Valid([]byte(tt.data)); ok != tt.ok {
t.Errorf("Valid(%#q) = %v, want %v", tt.data, ok, tt.ok)
}
}
}
// Tests of simple examples.
type example struct {
compact string
indent string
}
var examples = []example{
{`1`, `1`},
{`{}`, `{}`},
{`[]`, `[]`},
{`{"":2}`, "{\n\t\"\": 2\n}"},
{`[3]`, "[\n\t3\n]"},
{`[1,2,3]`, "[\n\t1,\n\t2,\n\t3\n]"},
{`{"x":1}`, "{\n\t\"x\": 1\n}"},
{ex1, ex1i},
{"{\"\":\"<>&\u2028\u2029\"}", "{\n\t\"\": \"<>&\u2028\u2029\"\n}"}, // See golang.org/issue/34070
}
var ex1 = `[true,false,null,"x",1,1.5,0,-5e+2]`
var ex1i = `[
true,
false,
null,
"x",
1,
1.5,
0,
-5e+2
]`
func TestCompact(t *testing.T) {
var buf bytes.Buffer
for _, tt := range examples {
buf.Reset()
if err := Compact(&buf, []byte(tt.compact)); err != nil {
t.Errorf("Compact(%#q): %v", tt.compact, err)
} else if s := buf.String(); s != tt.compact {
t.Errorf("Compact(%#q) = %#q, want original", tt.compact, s)
}
buf.Reset()
if err := Compact(&buf, []byte(tt.indent)); err != nil {
t.Errorf("Compact(%#q): %v", tt.indent, err)
continue
} else if s := buf.String(); s != tt.compact {
t.Errorf("Compact(%#q) = %#q, want %#q", tt.indent, s, tt.compact)
}
}
}
func TestCompactSeparators(t *testing.T) {
// U+2028 and U+2029 should be escaped inside strings.
// They should not appear outside strings.
tests := []struct {
in, compact string
}{
{"{\"\u2028\": 1}", "{\"\u2028\":1}"},
{"{\"\u2029\" :2}", "{\"\u2029\":2}"},
}
for _, tt := range tests {
var buf bytes.Buffer
if err := Compact(&buf, []byte(tt.in)); err != nil {
t.Errorf("Compact(%q): %v", tt.in, err)
} else if s := buf.String(); s != tt.compact {
t.Errorf("Compact(%q) = %q, want %q", tt.in, s, tt.compact)
}
}
}
func TestIndent(t *testing.T) {
var buf bytes.Buffer
for _, tt := range examples {
buf.Reset()
if err := Indent(&buf, []byte(tt.indent), "", "\t"); err != nil {
t.Errorf("Indent(%#q): %v", tt.indent, err)
} else if s := buf.String(); s != tt.indent {
t.Errorf("Indent(%#q) = %#q, want original", tt.indent, s)
}
buf.Reset()
if err := Indent(&buf, []byte(tt.compact), "", "\t"); err != nil {
t.Errorf("Indent(%#q): %v", tt.compact, err)
continue
} else if s := buf.String(); s != tt.indent {
t.Errorf("Indent(%#q) = %#q, want %#q", tt.compact, s, tt.indent)
}
}
}
// Tests of a large random structure.
func TestCompactBig(t *testing.T) {
initBig()
var buf bytes.Buffer
if err := Compact(&buf, jsonBig); err != nil {
t.Fatalf("Compact: %v", err)
}
b := buf.Bytes()
if !bytes.Equal(b, jsonBig) {
t.Error("Compact(jsonBig) != jsonBig")
diff(t, b, jsonBig)
return
}
}
func TestIndentBig(t *testing.T) {
t.Parallel()
initBig()
var buf bytes.Buffer
if err := Indent(&buf, jsonBig, "", "\t"); err != nil {
t.Fatalf("Indent1: %v", err)
}
b := buf.Bytes()
if len(b) == len(jsonBig) {
// jsonBig is compact (no unnecessary spaces);
// indenting should make it bigger
t.Fatalf("Indent(jsonBig) did not get bigger")
}
// should be idempotent
var buf1 bytes.Buffer
if err := Indent(&buf1, b, "", "\t"); err != nil {
t.Fatalf("Indent2: %v", err)
}
b1 := buf1.Bytes()
if !bytes.Equal(b1, b) {
t.Error("Indent(Indent(jsonBig)) != Indent(jsonBig)")
diff(t, b1, b)
return
}
// should get back to original
buf1.Reset()
if err := Compact(&buf1, b); err != nil {
t.Fatalf("Compact: %v", err)
}
b1 = buf1.Bytes()
if !bytes.Equal(b1, jsonBig) {
t.Error("Compact(Indent(jsonBig)) != jsonBig")
diff(t, b1, jsonBig)
return
}
}
type indentErrorTest struct {
in string
err error
}
var indentErrorTests = []indentErrorTest{
{`{"X": "foo", "Y"}`, &SyntaxError{"invalid character '}' after object key", 17}},
{`{"X": "foo" "Y": "bar"}`, &SyntaxError{"invalid character '\"' after object key:value pair", 13}},
}
func TestIndentErrors(t *testing.T) {
for i, tt := range indentErrorTests {
slice := make([]uint8, 0)
buf := bytes.NewBuffer(slice)
if err := Indent(buf, []uint8(tt.in), "", ""); err != nil {
if !reflect.DeepEqual(err, tt.err) {
t.Errorf("#%d: Indent: %#v", i, err)
continue
}
}
}
}
func diff(t *testing.T, a, b []byte) {
for i := 0; ; i++ {
if i >= len(a) || i >= len(b) || a[i] != b[i] {
j := i - 10
if j < 0 {
j = 0
}
t.Errorf("diverge at %d: «%s» vs «%s»", i, trim(a[j:]), trim(b[j:]))
return
}
}
}
func trim(b []byte) []byte {
if len(b) > 20 {
return b[0:20]
}
return b
}
// Generate a random JSON object.
var jsonBig []byte
func initBig() {
n := 10000
if testing.Short() {
n = 100
}
b, err := Marshal(genValue(n))
if err != nil {
panic(err)
}
jsonBig = b
}
func genValue(n int) any {
if n > 1 {
switch rand.Intn(2) {
case 0:
return genArray(n)
case 1:
return genMap(n)
}
}
switch rand.Intn(3) {
case 0:
return rand.Intn(2) == 0
case 1:
return rand.NormFloat64()
case 2:
return genString(30)
}
panic("unreachable")
}
func genString(stddev float64) string {
n := int(math.Abs(rand.NormFloat64()*stddev + stddev/2))
c := make([]rune, n)
for i := range c {
f := math.Abs(rand.NormFloat64()*64 + 32)
if f > 0x10ffff {
f = 0x10ffff
}
c[i] = rune(f)
}
return string(c)
}
func genArray(n int) []any {
f := int(math.Abs(rand.NormFloat64()) * math.Min(10, float64(n/2)))
if f > n {
f = n
}
if f < 1 {
f = 1
}
x := make([]any, f)
for i := range x {
x[i] = genValue(((i+1)*n)/f - (i*n)/f)
}
return x
}
func genMap(n int) map[string]any {
f := int(math.Abs(rand.NormFloat64()) * math.Min(10, float64(n/2)))
if f > n {
f = n
}
if n > 0 && f == 0 {
f = 1
}
x := make(map[string]any)
for i := 0; i < f; i++ {
x[genString(10)] = genValue(((i+1)*n)/f - (i*n)/f)
}
return x
}

515
gojson/stream.go Normal file
View File

@ -0,0 +1,515 @@
// 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.
package json
import (
"bytes"
"errors"
"io"
)
// A Decoder reads and decodes JSON values from an input stream.
type Decoder struct {
r io.Reader
buf []byte
d decodeState
scanp int // start of unread data in buf
scanned int64 // amount of data already scanned
scan scanner
err error
tokenState int
tokenStack []int
}
// NewDecoder returns a new decoder that reads from r.
//
// The decoder introduces its own buffering and may
// read data from r beyond the JSON values requested.
func NewDecoder(r io.Reader) *Decoder {
return &Decoder{r: r}
}
// UseNumber causes the Decoder to unmarshal a number into an interface{} as a
// Number instead of as a float64.
func (dec *Decoder) UseNumber() { dec.d.useNumber = true }
// DisallowUnknownFields causes the Decoder to return an error when the destination
// is a struct and the input contains object keys which do not match any
// non-ignored, exported fields in the destination.
func (dec *Decoder) DisallowUnknownFields() { dec.d.disallowUnknownFields = true }
// Decode reads the next JSON-encoded value from its
// input and stores it in the value pointed to by v.
//
// See the documentation for Unmarshal for details about
// the conversion of JSON into a Go value.
func (dec *Decoder) Decode(v any) error {
if dec.err != nil {
return dec.err
}
if err := dec.tokenPrepareForDecode(); err != nil {
return err
}
if !dec.tokenValueAllowed() {
return &SyntaxError{msg: "not at beginning of value", Offset: dec.InputOffset()}
}
// Read whole value into buffer.
n, err := dec.readValue()
if err != nil {
return err
}
dec.d.init(dec.buf[dec.scanp : dec.scanp+n])
dec.scanp += n
// Don't save err from unmarshal into dec.err:
// the connection is still usable since we read a complete JSON
// object from it before the error happened.
err = dec.d.unmarshal(v)
// fixup token streaming state
dec.tokenValueEnd()
return err
}
// Buffered returns a reader of the data remaining in the Decoder's
// buffer. The reader is valid until the next call to Decode.
func (dec *Decoder) Buffered() io.Reader {
return bytes.NewReader(dec.buf[dec.scanp:])
}
// readValue reads a JSON value into dec.buf.
// It returns the length of the encoding.
func (dec *Decoder) readValue() (int, error) {
dec.scan.reset()
scanp := dec.scanp
var err error
Input:
// help the compiler see that scanp is never negative, so it can remove
// some bounds checks below.
for scanp >= 0 {
// Look in the buffer for a new value.
for ; scanp < len(dec.buf); scanp++ {
c := dec.buf[scanp]
dec.scan.bytes++
switch dec.scan.step(&dec.scan, c) {
case scanEnd:
// scanEnd is delayed one byte so we decrement
// the scanner bytes count by 1 to ensure that
// this value is correct in the next call of Decode.
dec.scan.bytes--
break Input
case scanEndObject, scanEndArray:
// scanEnd is delayed one byte.
// We might block trying to get that byte from src,
// so instead invent a space byte.
if stateEndValue(&dec.scan, ' ') == scanEnd {
scanp++
break Input
}
case scanError:
dec.err = dec.scan.err
return 0, dec.scan.err
}
}
// Did the last read have an error?
// Delayed until now to allow buffer scan.
if err != nil {
if err == io.EOF {
if dec.scan.step(&dec.scan, ' ') == scanEnd {
break Input
}
if nonSpace(dec.buf) {
err = io.ErrUnexpectedEOF
}
}
dec.err = err
return 0, err
}
n := scanp - dec.scanp
err = dec.refill()
scanp = dec.scanp + n
}
return scanp - dec.scanp, nil
}
func (dec *Decoder) refill() error {
// Make room to read more into the buffer.
// First slide down data already consumed.
if dec.scanp > 0 {
dec.scanned += int64(dec.scanp)
n := copy(dec.buf, dec.buf[dec.scanp:])
dec.buf = dec.buf[:n]
dec.scanp = 0
}
// Grow buffer if not large enough.
const minRead = 512
if cap(dec.buf)-len(dec.buf) < minRead {
newBuf := make([]byte, len(dec.buf), 2*cap(dec.buf)+minRead)
copy(newBuf, dec.buf)
dec.buf = newBuf
}
// Read. Delay error for next iteration (after scan).
n, err := dec.r.Read(dec.buf[len(dec.buf):cap(dec.buf)])
dec.buf = dec.buf[0 : len(dec.buf)+n]
return err
}
func nonSpace(b []byte) bool {
for _, c := range b {
if !isSpace(c) {
return true
}
}
return false
}
// An Encoder writes JSON values to an output stream.
type Encoder struct {
w io.Writer
err error
escapeHTML bool
indentBuf *bytes.Buffer
indentPrefix string
indentValue string
}
// NewEncoder returns a new encoder that writes to w.
func NewEncoder(w io.Writer) *Encoder {
return &Encoder{w: w, escapeHTML: true}
}
// Encode writes the JSON encoding of v to the stream,
// followed by a newline character.
//
// See the documentation for Marshal for details about the
// conversion of Go values to JSON.
func (enc *Encoder) Encode(v any) error {
if enc.err != nil {
return enc.err
}
e := newEncodeState()
defer encodeStatePool.Put(e)
err := e.marshal(v, encOpts{escapeHTML: enc.escapeHTML})
if err != nil {
return err
}
// Terminate each value with a newline.
// This makes the output look a little nicer
// when debugging, and some kind of space
// is required if the encoded value was a number,
// so that the reader knows there aren't more
// digits coming.
e.WriteByte('\n')
b := e.Bytes()
if enc.indentPrefix != "" || enc.indentValue != "" {
if enc.indentBuf == nil {
enc.indentBuf = new(bytes.Buffer)
}
enc.indentBuf.Reset()
err = Indent(enc.indentBuf, b, enc.indentPrefix, enc.indentValue)
if err != nil {
return err
}
b = enc.indentBuf.Bytes()
}
if _, err = enc.w.Write(b); err != nil {
enc.err = err
}
return err
}
// SetIndent instructs the encoder to format each subsequent encoded
// value as if indented by the package-level function Indent(dst, src, prefix, indent).
// Calling SetIndent("", "") disables indentation.
func (enc *Encoder) SetIndent(prefix, indent string) {
enc.indentPrefix = prefix
enc.indentValue = indent
}
// SetEscapeHTML specifies whether problematic HTML characters
// should be escaped inside JSON quoted strings.
// The default behavior is to escape &, <, and > to \u0026, \u003c, and \u003e
// to avoid certain safety problems that can arise when embedding JSON in HTML.
//
// In non-HTML settings where the escaping interferes with the readability
// of the output, SetEscapeHTML(false) disables this behavior.
func (enc *Encoder) SetEscapeHTML(on bool) {
enc.escapeHTML = on
}
// RawMessage is a raw encoded JSON value.
// It implements Marshaler and Unmarshaler and can
// be used to delay JSON decoding or precompute a JSON encoding.
type RawMessage []byte
// MarshalJSON returns m as the JSON encoding of m.
func (m RawMessage) MarshalJSON() ([]byte, error) {
if m == nil {
return []byte("null"), nil
}
return m, nil
}
// UnmarshalJSON sets *m to a copy of data.
func (m *RawMessage) UnmarshalJSON(data []byte) error {
if m == nil {
return errors.New("json.RawMessage: UnmarshalJSON on nil pointer")
}
*m = append((*m)[0:0], data...)
return nil
}
var _ Marshaler = (*RawMessage)(nil)
var _ Unmarshaler = (*RawMessage)(nil)
// A Token holds a value of one of these types:
//
// Delim, for the four JSON delimiters [ ] { }
// bool, for JSON booleans
// float64, for JSON numbers
// Number, for JSON numbers
// string, for JSON string literals
// nil, for JSON null
type Token any
const (
tokenTopValue = iota
tokenArrayStart
tokenArrayValue
tokenArrayComma
tokenObjectStart
tokenObjectKey
tokenObjectColon
tokenObjectValue
tokenObjectComma
)
// advance tokenstate from a separator state to a value state
func (dec *Decoder) tokenPrepareForDecode() error {
// Note: Not calling peek before switch, to avoid
// putting peek into the standard Decode path.
// peek is only called when using the Token API.
switch dec.tokenState {
case tokenArrayComma:
c, err := dec.peek()
if err != nil {
return err
}
if c != ',' {
return &SyntaxError{"expected comma after array element", dec.InputOffset()}
}
dec.scanp++
dec.tokenState = tokenArrayValue
case tokenObjectColon:
c, err := dec.peek()
if err != nil {
return err
}
if c != ':' {
return &SyntaxError{"expected colon after object key", dec.InputOffset()}
}
dec.scanp++
dec.tokenState = tokenObjectValue
}
return nil
}
func (dec *Decoder) tokenValueAllowed() bool {
switch dec.tokenState {
case tokenTopValue, tokenArrayStart, tokenArrayValue, tokenObjectValue:
return true
}
return false
}
func (dec *Decoder) tokenValueEnd() {
switch dec.tokenState {
case tokenArrayStart, tokenArrayValue:
dec.tokenState = tokenArrayComma
case tokenObjectValue:
dec.tokenState = tokenObjectComma
}
}
// A Delim is a JSON array or object delimiter, one of [ ] { or }.
type Delim rune
func (d Delim) String() string {
return string(d)
}
// Token returns the next JSON token in the input stream.
// At the end of the input stream, Token returns nil, io.EOF.
//
// Token guarantees that the delimiters [ ] { } it returns are
// properly nested and matched: if Token encounters an unexpected
// delimiter in the input, it will return an error.
//
// The input stream consists of basic JSON values—bool, string,
// number, and null—along with delimiters [ ] { } of type Delim
// to mark the start and end of arrays and objects.
// Commas and colons are elided.
func (dec *Decoder) Token() (Token, error) {
for {
c, err := dec.peek()
if err != nil {
return nil, err
}
switch c {
case '[':
if !dec.tokenValueAllowed() {
return dec.tokenError(c)
}
dec.scanp++
dec.tokenStack = append(dec.tokenStack, dec.tokenState)
dec.tokenState = tokenArrayStart
return Delim('['), nil
case ']':
if dec.tokenState != tokenArrayStart && dec.tokenState != tokenArrayComma {
return dec.tokenError(c)
}
dec.scanp++
dec.tokenState = dec.tokenStack[len(dec.tokenStack)-1]
dec.tokenStack = dec.tokenStack[:len(dec.tokenStack)-1]
dec.tokenValueEnd()
return Delim(']'), nil
case '{':
if !dec.tokenValueAllowed() {
return dec.tokenError(c)
}
dec.scanp++
dec.tokenStack = append(dec.tokenStack, dec.tokenState)
dec.tokenState = tokenObjectStart
return Delim('{'), nil
case '}':
if dec.tokenState != tokenObjectStart && dec.tokenState != tokenObjectComma {
return dec.tokenError(c)
}
dec.scanp++
dec.tokenState = dec.tokenStack[len(dec.tokenStack)-1]
dec.tokenStack = dec.tokenStack[:len(dec.tokenStack)-1]
dec.tokenValueEnd()
return Delim('}'), nil
case ':':
if dec.tokenState != tokenObjectColon {
return dec.tokenError(c)
}
dec.scanp++
dec.tokenState = tokenObjectValue
continue
case ',':
if dec.tokenState == tokenArrayComma {
dec.scanp++
dec.tokenState = tokenArrayValue
continue
}
if dec.tokenState == tokenObjectComma {
dec.scanp++
dec.tokenState = tokenObjectKey
continue
}
return dec.tokenError(c)
case '"':
if dec.tokenState == tokenObjectStart || dec.tokenState == tokenObjectKey {
var x string
old := dec.tokenState
dec.tokenState = tokenTopValue
err := dec.Decode(&x)
dec.tokenState = old
if err != nil {
return nil, err
}
dec.tokenState = tokenObjectColon
return x, nil
}
fallthrough
default:
if !dec.tokenValueAllowed() {
return dec.tokenError(c)
}
var x any
if err := dec.Decode(&x); err != nil {
return nil, err
}
return x, nil
}
}
}
func (dec *Decoder) tokenError(c byte) (Token, error) {
var context string
switch dec.tokenState {
case tokenTopValue:
context = " looking for beginning of value"
case tokenArrayStart, tokenArrayValue, tokenObjectValue:
context = " looking for beginning of value"
case tokenArrayComma:
context = " after array element"
case tokenObjectKey:
context = " looking for beginning of object key string"
case tokenObjectColon:
context = " after object key"
case tokenObjectComma:
context = " after object key:value pair"
}
return nil, &SyntaxError{"invalid character " + quoteChar(c) + context, dec.InputOffset()}
}
// More reports whether there is another element in the
// current array or object being parsed.
func (dec *Decoder) More() bool {
c, err := dec.peek()
return err == nil && c != ']' && c != '}'
}
func (dec *Decoder) peek() (byte, error) {
var err error
for {
for i := dec.scanp; i < len(dec.buf); i++ {
c := dec.buf[i]
if isSpace(c) {
continue
}
dec.scanp = i
return c, nil
}
// buffer has been scanned, now report any error
if err != nil {
return 0, err
}
err = dec.refill()
}
}
// InputOffset returns the input stream byte offset of the current decoder position.
// The offset gives the location of the end of the most recently returned token
// and the beginning of the next token.
func (dec *Decoder) InputOffset() int64 {
return dec.scanned + int64(dec.scanp)
}

497
gojson/stream_test.go Normal file
View File

@ -0,0 +1,497 @@
// 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.
package json
import (
"bytes"
"io"
"log"
"net"
"net/http"
"net/http/httptest"
"reflect"
"runtime/debug"
"strings"
"testing"
)
// Test values for the stream test.
// One of each JSON kind.
var streamTest = []any{
0.1,
"hello",
nil,
true,
false,
[]any{"a", "b", "c"},
map[string]any{"K": "Kelvin", "ß": "long s"},
3.14, // another value to make sure something can follow map
}
var streamEncoded = `0.1
"hello"
null
true
false
["a","b","c"]
{"ß":"long s","K":"Kelvin"}
3.14
`
func TestEncoder(t *testing.T) {
for i := 0; i <= len(streamTest); i++ {
var buf strings.Builder
enc := NewEncoder(&buf)
// Check that enc.SetIndent("", "") turns off indentation.
enc.SetIndent(">", ".")
enc.SetIndent("", "")
for j, v := range streamTest[0:i] {
if err := enc.Encode(v); err != nil {
t.Fatalf("encode #%d: %v", j, err)
}
}
if have, want := buf.String(), nlines(streamEncoded, i); have != want {
t.Errorf("encoding %d items: mismatch", i)
diff(t, []byte(have), []byte(want))
break
}
}
}
func TestEncoderErrorAndReuseEncodeState(t *testing.T) {
// Disable the GC temporarily to prevent encodeState's in Pool being cleaned away during the test.
percent := debug.SetGCPercent(-1)
defer debug.SetGCPercent(percent)
// Trigger an error in Marshal with cyclic data.
type Dummy struct {
Name string
Next *Dummy
}
dummy := Dummy{Name: "Dummy"}
dummy.Next = &dummy
var buf bytes.Buffer
enc := NewEncoder(&buf)
if err := enc.Encode(dummy); err == nil {
t.Errorf("Encode(dummy) == nil; want error")
}
type Data struct {
A string
I int
}
data := Data{A: "a", I: 1}
if err := enc.Encode(data); err != nil {
t.Errorf("Marshal(%v) = %v", data, err)
}
var data2 Data
if err := Unmarshal(buf.Bytes(), &data2); err != nil {
t.Errorf("Unmarshal(%v) = %v", data2, err)
}
if data2 != data {
t.Errorf("expect: %v, but get: %v", data, data2)
}
}
var streamEncodedIndent = `0.1
"hello"
null
true
false
[
>."a",
>."b",
>."c"
>]
{
>."ß": "long s",
>."K": "Kelvin"
>}
3.14
`
func TestEncoderIndent(t *testing.T) {
var buf strings.Builder
enc := NewEncoder(&buf)
enc.SetIndent(">", ".")
for _, v := range streamTest {
enc.Encode(v)
}
if have, want := buf.String(), streamEncodedIndent; have != want {
t.Error("indented encoding mismatch")
diff(t, []byte(have), []byte(want))
}
}
type strMarshaler string
func (s strMarshaler) MarshalJSON() ([]byte, error) {
return []byte(s), nil
}
type strPtrMarshaler string
func (s *strPtrMarshaler) MarshalJSON() ([]byte, error) {
return []byte(*s), nil
}
func TestEncoderSetEscapeHTML(t *testing.T) {
var c C
var ct CText
var tagStruct struct {
Valid int `json:"<>&#! "`
Invalid int `json:"\\"`
}
// This case is particularly interesting, as we force the encoder to
// take the address of the Ptr field to use its MarshalJSON method. This
// is why the '&' is important.
marshalerStruct := &struct {
NonPtr strMarshaler
Ptr strPtrMarshaler
}{`"<str>"`, `"<str>"`}
// https://golang.org/issue/34154
stringOption := struct {
Bar string `json:"bar,string"`
}{`<html>foobar</html>`}
for _, tt := range []struct {
name string
v any
wantEscape string
want string
}{
{"c", c, `"\u003c\u0026\u003e"`, `"<&>"`},
{"ct", ct, `"\"\u003c\u0026\u003e\""`, `"\"<&>\""`},
{`"<&>"`, "<&>", `"\u003c\u0026\u003e"`, `"<&>"`},
{
"tagStruct", tagStruct,
`{"\u003c\u003e\u0026#! ":0,"Invalid":0}`,
`{"<>&#! ":0,"Invalid":0}`,
},
{
`"<str>"`, marshalerStruct,
`{"NonPtr":"\u003cstr\u003e","Ptr":"\u003cstr\u003e"}`,
`{"NonPtr":"<str>","Ptr":"<str>"}`,
},
{
"stringOption", stringOption,
`{"bar":"\"\\u003chtml\\u003efoobar\\u003c/html\\u003e\""}`,
`{"bar":"\"<html>foobar</html>\""}`,
},
} {
var buf strings.Builder
enc := NewEncoder(&buf)
if err := enc.Encode(tt.v); err != nil {
t.Errorf("Encode(%s): %s", tt.name, err)
continue
}
if got := strings.TrimSpace(buf.String()); got != tt.wantEscape {
t.Errorf("Encode(%s) = %#q, want %#q", tt.name, got, tt.wantEscape)
}
buf.Reset()
enc.SetEscapeHTML(false)
if err := enc.Encode(tt.v); err != nil {
t.Errorf("SetEscapeHTML(false) Encode(%s): %s", tt.name, err)
continue
}
if got := strings.TrimSpace(buf.String()); got != tt.want {
t.Errorf("SetEscapeHTML(false) Encode(%s) = %#q, want %#q",
tt.name, got, tt.want)
}
}
}
func TestDecoder(t *testing.T) {
for i := 0; i <= len(streamTest); i++ {
// Use stream without newlines as input,
// just to stress the decoder even more.
// Our test input does not include back-to-back numbers.
// Otherwise stripping the newlines would
// merge two adjacent JSON values.
var buf bytes.Buffer
for _, c := range nlines(streamEncoded, i) {
if c != '\n' {
buf.WriteRune(c)
}
}
out := make([]any, i)
dec := NewDecoder(&buf)
for j := range out {
if err := dec.Decode(&out[j]); err != nil {
t.Fatalf("decode #%d/%d: %v", j, i, err)
}
}
if !reflect.DeepEqual(out, streamTest[0:i]) {
t.Errorf("decoding %d items: mismatch", i)
for j := range out {
if !reflect.DeepEqual(out[j], streamTest[j]) {
t.Errorf("#%d: have %v want %v", j, out[j], streamTest[j])
}
}
break
}
}
}
func TestDecoderBuffered(t *testing.T) {
r := strings.NewReader(`{"Name": "Gopher"} extra `)
var m struct {
Name string
}
d := NewDecoder(r)
err := d.Decode(&m)
if err != nil {
t.Fatal(err)
}
if m.Name != "Gopher" {
t.Errorf("Name = %q; want Gopher", m.Name)
}
rest, err := io.ReadAll(d.Buffered())
if err != nil {
t.Fatal(err)
}
if g, w := string(rest), " extra "; g != w {
t.Errorf("Remaining = %q; want %q", g, w)
}
}
func nlines(s string, n int) string {
if n <= 0 {
return ""
}
for i, c := range s {
if c == '\n' {
if n--; n == 0 {
return s[0 : i+1]
}
}
}
return s
}
func TestRawMessage(t *testing.T) {
var data struct {
X float64
Id RawMessage
Y float32
}
const raw = `["\u0056",null]`
const msg = `{"X":0.1,"Id":["\u0056",null],"Y":0.2}`
err := Unmarshal([]byte(msg), &data)
if err != nil {
t.Fatalf("Unmarshal: %v", err)
}
if string([]byte(data.Id)) != raw {
t.Fatalf("Raw mismatch: have %#q want %#q", []byte(data.Id), raw)
}
b, err := Marshal(&data)
if err != nil {
t.Fatalf("Marshal: %v", err)
}
if string(b) != msg {
t.Fatalf("Marshal: have %#q want %#q", b, msg)
}
}
func TestNullRawMessage(t *testing.T) {
var data struct {
X float64
Id RawMessage
IdPtr *RawMessage
Y float32
}
const msg = `{"X":0.1,"Id":null,"IdPtr":null,"Y":0.2}`
err := Unmarshal([]byte(msg), &data)
if err != nil {
t.Fatalf("Unmarshal: %v", err)
}
if want, got := "null", string(data.Id); want != got {
t.Fatalf("Raw mismatch: have %q, want %q", got, want)
}
if data.IdPtr != nil {
t.Fatalf("Raw pointer mismatch: have non-nil, want nil")
}
b, err := Marshal(&data)
if err != nil {
t.Fatalf("Marshal: %v", err)
}
if string(b) != msg {
t.Fatalf("Marshal: have %#q want %#q", b, msg)
}
}
var blockingTests = []string{
`{"x": 1}`,
`[1, 2, 3]`,
}
func TestBlocking(t *testing.T) {
for _, enc := range blockingTests {
r, w := net.Pipe()
go w.Write([]byte(enc))
var val any
// If Decode reads beyond what w.Write writes above,
// it will block, and the test will deadlock.
if err := NewDecoder(r).Decode(&val); err != nil {
t.Errorf("decoding %s: %v", enc, err)
}
r.Close()
w.Close()
}
}
type tokenStreamCase struct {
json string
expTokens []any
}
type decodeThis struct {
v any
}
var tokenStreamCases = []tokenStreamCase{
// streaming token cases
{json: `10`, expTokens: []any{float64(10)}},
{json: ` [10] `, expTokens: []any{
Delim('['), float64(10), Delim(']')}},
{json: ` [false,10,"b"] `, expTokens: []any{
Delim('['), false, float64(10), "b", Delim(']')}},
{json: `{ "a": 1 }`, expTokens: []any{
Delim('{'), "a", float64(1), Delim('}')}},
{json: `{"a": 1, "b":"3"}`, expTokens: []any{
Delim('{'), "a", float64(1), "b", "3", Delim('}')}},
{json: ` [{"a": 1},{"a": 2}] `, expTokens: []any{
Delim('['),
Delim('{'), "a", float64(1), Delim('}'),
Delim('{'), "a", float64(2), Delim('}'),
Delim(']')}},
{json: `{"obj": {"a": 1}}`, expTokens: []any{
Delim('{'), "obj", Delim('{'), "a", float64(1), Delim('}'),
Delim('}')}},
{json: `{"obj": [{"a": 1}]}`, expTokens: []any{
Delim('{'), "obj", Delim('['),
Delim('{'), "a", float64(1), Delim('}'),
Delim(']'), Delim('}')}},
// streaming tokens with intermittent Decode()
{json: `{ "a": 1 }`, expTokens: []any{
Delim('{'), "a",
decodeThis{float64(1)},
Delim('}')}},
{json: ` [ { "a" : 1 } ] `, expTokens: []any{
Delim('['),
decodeThis{map[string]any{"a": float64(1)}},
Delim(']')}},
{json: ` [{"a": 1},{"a": 2}] `, expTokens: []any{
Delim('['),
decodeThis{map[string]any{"a": float64(1)}},
decodeThis{map[string]any{"a": float64(2)}},
Delim(']')}},
{json: `{ "obj" : [ { "a" : 1 } ] }`, expTokens: []any{
Delim('{'), "obj", Delim('['),
decodeThis{map[string]any{"a": float64(1)}},
Delim(']'), Delim('}')}},
{json: `{"obj": {"a": 1}}`, expTokens: []any{
Delim('{'), "obj",
decodeThis{map[string]any{"a": float64(1)}},
Delim('}')}},
{json: `{"obj": [{"a": 1}]}`, expTokens: []any{
Delim('{'), "obj",
decodeThis{[]any{
map[string]any{"a": float64(1)},
}},
Delim('}')}},
{json: ` [{"a": 1} {"a": 2}] `, expTokens: []any{
Delim('['),
decodeThis{map[string]any{"a": float64(1)}},
decodeThis{&SyntaxError{"expected comma after array element", 11}},
}},
{json: `{ "` + strings.Repeat("a", 513) + `" 1 }`, expTokens: []any{
Delim('{'), strings.Repeat("a", 513),
decodeThis{&SyntaxError{"expected colon after object key", 518}},
}},
{json: `{ "\a" }`, expTokens: []any{
Delim('{'),
&SyntaxError{"invalid character 'a' in string escape code", 3},
}},
{json: ` \a`, expTokens: []any{
&SyntaxError{"invalid character '\\\\' looking for beginning of value", 1},
}},
}
func TestDecodeInStream(t *testing.T) {
for ci, tcase := range tokenStreamCases {
dec := NewDecoder(strings.NewReader(tcase.json))
for i, etk := range tcase.expTokens {
var tk any
var err error
if dt, ok := etk.(decodeThis); ok {
etk = dt.v
err = dec.Decode(&tk)
} else {
tk, err = dec.Token()
}
if experr, ok := etk.(error); ok {
if err == nil || !reflect.DeepEqual(err, experr) {
t.Errorf("case %v: Expected error %#v in %q, but was %#v", ci, experr, tcase.json, err)
}
break
} else if err == io.EOF {
t.Errorf("case %v: Unexpected EOF in %q", ci, tcase.json)
break
} else if err != nil {
t.Errorf("case %v: Unexpected error '%#v' in %q", ci, err, tcase.json)
break
}
if !reflect.DeepEqual(tk, etk) {
t.Errorf(`case %v: %q @ %v expected %T(%v) was %T(%v)`, ci, tcase.json, i, etk, etk, tk, tk)
break
}
}
}
}
// Test from golang.org/issue/11893
func TestHTTPDecoding(t *testing.T) {
const raw = `{ "foo": "bar" }`
ts := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
w.Write([]byte(raw))
}))
defer ts.Close()
res, err := http.Get(ts.URL)
if err != nil {
log.Fatalf("GET failed: %v", err)
}
defer res.Body.Close()
foo := struct {
Foo string
}{}
d := NewDecoder(res.Body)
err = d.Decode(&foo)
if err != nil {
t.Fatalf("Decode: %v", err)
}
if foo.Foo != "bar" {
t.Errorf("decoded %q; want \"bar\"", foo.Foo)
}
// make sure we get the EOF the second time
err = d.Decode(&foo)
if err != io.EOF {
t.Errorf("err = %v; want io.EOF", err)
}
}

218
gojson/tables.go Normal file
View File

@ -0,0 +1,218 @@
// Copyright 2016 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 json
import "unicode/utf8"
// safeSet holds the value true if the ASCII character with the given array
// position can be represented inside a JSON string without any further
// escaping.
//
// All values are true except for the ASCII control characters (0-31), the
// double quote ("), and the backslash character ("\").
var safeSet = [utf8.RuneSelf]bool{
' ': true,
'!': true,
'"': false,
'#': true,
'$': true,
'%': true,
'&': true,
'\'': true,
'(': true,
')': true,
'*': true,
'+': true,
',': true,
'-': true,
'.': true,
'/': true,
'0': true,
'1': true,
'2': true,
'3': true,
'4': true,
'5': true,
'6': true,
'7': true,
'8': true,
'9': true,
':': true,
';': true,
'<': true,
'=': true,
'>': true,
'?': true,
'@': true,
'A': true,
'B': true,
'C': true,
'D': true,
'E': true,
'F': true,
'G': true,
'H': true,
'I': true,
'J': true,
'K': true,
'L': true,
'M': true,
'N': true,
'O': true,
'P': true,
'Q': true,
'R': true,
'S': true,
'T': true,
'U': true,
'V': true,
'W': true,
'X': true,
'Y': true,
'Z': true,
'[': true,
'\\': false,
']': true,
'^': true,
'_': true,
'`': true,
'a': true,
'b': true,
'c': true,
'd': true,
'e': true,
'f': true,
'g': true,
'h': true,
'i': true,
'j': true,
'k': true,
'l': true,
'm': true,
'n': true,
'o': true,
'p': true,
'q': true,
'r': true,
's': true,
't': true,
'u': true,
'v': true,
'w': true,
'x': true,
'y': true,
'z': true,
'{': true,
'|': true,
'}': true,
'~': true,
'\u007f': true,
}
// htmlSafeSet holds the value true if the ASCII character with the given
// array position can be safely represented inside a JSON string, embedded
// inside of HTML <script> tags, without any additional escaping.
//
// All values are true except for the ASCII control characters (0-31), the
// double quote ("), the backslash character ("\"), HTML opening and closing
// tags ("<" and ">"), and the ampersand ("&").
var htmlSafeSet = [utf8.RuneSelf]bool{
' ': true,
'!': true,
'"': false,
'#': true,
'$': true,
'%': true,
'&': false,
'\'': true,
'(': true,
')': true,
'*': true,
'+': true,
',': true,
'-': true,
'.': true,
'/': true,
'0': true,
'1': true,
'2': true,
'3': true,
'4': true,
'5': true,
'6': true,
'7': true,
'8': true,
'9': true,
':': true,
';': true,
'<': false,
'=': true,
'>': false,
'?': true,
'@': true,
'A': true,
'B': true,
'C': true,
'D': true,
'E': true,
'F': true,
'G': true,
'H': true,
'I': true,
'J': true,
'K': true,
'L': true,
'M': true,
'N': true,
'O': true,
'P': true,
'Q': true,
'R': true,
'S': true,
'T': true,
'U': true,
'V': true,
'W': true,
'X': true,
'Y': true,
'Z': true,
'[': true,
'\\': false,
']': true,
'^': true,
'_': true,
'`': true,
'a': true,
'b': true,
'c': true,
'd': true,
'e': true,
'f': true,
'g': true,
'h': true,
'i': true,
'j': true,
'k': true,
'l': true,
'm': true,
'n': true,
'o': true,
'p': true,
'q': true,
'r': true,
's': true,
't': true,
'u': true,
'v': true,
'w': true,
'x': true,
'y': true,
'z': true,
'{': true,
'|': true,
'}': true,
'~': true,
'\u007f': true,
}

120
gojson/tagkey_test.go Normal file
View File

@ -0,0 +1,120 @@
// 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 json
import (
"testing"
)
type basicLatin2xTag struct {
V string `json:"$%-/"`
}
type basicLatin3xTag struct {
V string `json:"0123456789"`
}
type basicLatin4xTag struct {
V string `json:"ABCDEFGHIJKLMO"`
}
type basicLatin5xTag struct {
V string `json:"PQRSTUVWXYZ_"`
}
type basicLatin6xTag struct {
V string `json:"abcdefghijklmno"`
}
type basicLatin7xTag struct {
V string `json:"pqrstuvwxyz"`
}
type miscPlaneTag struct {
V string `json:"色は匂へど"`
}
type percentSlashTag struct {
V string `json:"text/html%"` // https://golang.org/issue/2718
}
type punctuationTag struct {
V string `json:"!#$%&()*+-./:;<=>?@[]^_{|}~ "` // https://golang.org/issue/3546
}
type dashTag struct {
V string `json:"-,"`
}
type emptyTag struct {
W string
}
type misnamedTag struct {
X string `jsom:"Misnamed"`
}
type badFormatTag struct {
Y string `:"BadFormat"`
}
type badCodeTag struct {
Z string `json:" !\"#&'()*+,."`
}
type spaceTag struct {
Q string `json:"With space"`
}
type unicodeTag struct {
W string `json:"Ελλάδα"`
}
var structTagObjectKeyTests = []struct {
raw any
value string
key string
}{
{basicLatin2xTag{"2x"}, "2x", "$%-/"},
{basicLatin3xTag{"3x"}, "3x", "0123456789"},
{basicLatin4xTag{"4x"}, "4x", "ABCDEFGHIJKLMO"},
{basicLatin5xTag{"5x"}, "5x", "PQRSTUVWXYZ_"},
{basicLatin6xTag{"6x"}, "6x", "abcdefghijklmno"},
{basicLatin7xTag{"7x"}, "7x", "pqrstuvwxyz"},
{miscPlaneTag{"いろはにほへと"}, "いろはにほへと", "色は匂へど"},
{dashTag{"foo"}, "foo", "-"},
{emptyTag{"Pour Moi"}, "Pour Moi", "W"},
{misnamedTag{"Animal Kingdom"}, "Animal Kingdom", "X"},
{badFormatTag{"Orfevre"}, "Orfevre", "Y"},
{badCodeTag{"Reliable Man"}, "Reliable Man", "Z"},
{percentSlashTag{"brut"}, "brut", "text/html%"},
{punctuationTag{"Union Rags"}, "Union Rags", "!#$%&()*+-./:;<=>?@[]^_{|}~ "},
{spaceTag{"Perreddu"}, "Perreddu", "With space"},
{unicodeTag{"Loukanikos"}, "Loukanikos", "Ελλάδα"},
}
func TestStructTagObjectKey(t *testing.T) {
for _, tt := range structTagObjectKeyTests {
b, err := Marshal(tt.raw)
if err != nil {
t.Fatalf("Marshal(%#q) failed: %v", tt.raw, err)
}
var f any
err = Unmarshal(b, &f)
if err != nil {
t.Fatalf("Unmarshal(%#q) failed: %v", b, err)
}
for i, v := range f.(map[string]any) {
switch i {
case tt.key:
if s, ok := v.(string); !ok || s != tt.value {
t.Fatalf("Unexpected value: %#q, want %v", s, tt.value)
}
default:
t.Fatalf("Unexpected key: %#q, from %#q", i, b)
}
}
}
}

38
gojson/tags.go Normal file
View File

@ -0,0 +1,38 @@
// 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 json
import (
"strings"
)
// tagOptions is the string following a comma in a struct field's "json"
// tag, or the empty string. It does not include the leading comma.
type tagOptions string
// parseTag splits a struct field's json tag into its name and
// comma-separated options.
func parseTag(tag string) (string, tagOptions) {
tag, opt, _ := strings.Cut(tag, ",")
return tag, tagOptions(opt)
}
// Contains reports whether a comma-separated list of options
// contains a particular substr flag. substr must be surrounded by a
// string boundary or commas.
func (o tagOptions) Contains(optionName string) bool {
if len(o) == 0 {
return false
}
s := string(o)
for s != "" {
var name string
name, s, _ = strings.Cut(s, ",")
if name == optionName {
return true
}
}
return false
}

28
gojson/tags_test.go Normal file
View File

@ -0,0 +1,28 @@
// 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 json
import (
"testing"
)
func TestTagParsing(t *testing.T) {
name, opts := parseTag("field,foobar,foo")
if name != "field" {
t.Fatalf("name = %q, want field", name)
}
for _, tt := range []struct {
opt string
want bool
}{
{"foobar", true},
{"foo", true},
{"bar", false},
} {
if opts.Contains(tt.opt) != tt.want {
t.Errorf("Contains(%q) = %v", tt.opt, !tt.want)
}
}
}

BIN
gojson/testdata/code.json.gz vendored Normal file
View File

Binary file not shown.