gjson/gjson.go

1256 lines
24 KiB
Go

// Package gjson provides searching for json strings.
package gjson
import (
"strconv"
"github.com/tidwall/match"
)
// Type is Result type
type Type int
const (
// Null is a null json value
Null Type = iota
// False is a json false boolean
False
// Number is json number
Number
// String is a json string
String
// True is a json true boolean
True
// JSON is a raw block of JSON
JSON
)
// Result represents a json value that is returned from Get().
type Result struct {
// Type is the json type
Type Type
// Raw is the raw json
Raw string
// Str is the json string
Str string
// Num is the json number
Num float64
}
// String returns a string representation of the value.
func (t Result) String() string {
switch t.Type {
default:
return "null"
case False:
return "false"
case Number:
return strconv.FormatFloat(t.Num, 'f', -1, 64)
case String:
return t.Str
case JSON:
return t.Raw
case True:
return "true"
}
}
// Bool returns an boolean representation.
func (t Result) Bool() bool {
switch t.Type {
default:
return false
case True:
return true
case String:
return t.Str != "" && t.Str != "0"
case Number:
return t.Num != 0
}
}
// Int returns an integer representation.
func (t Result) Int() int64 {
switch t.Type {
default:
return 0
case True:
return 1
case String:
n, _ := strconv.ParseInt(t.Str, 10, 64)
return n
case Number:
return int64(t.Num)
}
}
// Float returns an float64 representation.
func (t Result) Float() float64 {
switch t.Type {
default:
return 0
case True:
return 1
case String:
n, _ := strconv.ParseFloat(t.Str, 64)
return n
case Number:
return t.Num
}
}
// Array returns back an array of children. The result must be a JSON array.
func (t Result) Array() []Result {
if t.Type != JSON {
return nil
}
r := t.arrayOrMap('[', false)
return r.a
}
// Map returns back an map of children. The result should be a JSON array.
func (t Result) Map() map[string]Result {
if t.Type != JSON {
return map[string]Result{}
}
r := t.arrayOrMap('{', false)
return r.o
}
// Get searches result for the specified path.
// The result should be a JSON array or object.
func (t Result) Get(path string) Result {
return Get(t.Raw, path)
}
type arrayOrMapResult struct {
a []Result
ai []interface{}
o map[string]Result
oi map[string]interface{}
vc byte
}
func (t Result) arrayOrMap(vc byte, valueize bool) (r arrayOrMapResult) {
var json = t.Raw
var i int
var value Result
var count int
var key Result
if vc == 0 {
for ; i < len(json); i++ {
if json[i] == '{' || json[i] == '[' {
r.vc = json[i]
i++
break
}
if json[i] > ' ' {
goto end
}
}
} else {
for ; i < len(json); i++ {
if json[i] == vc {
i++
break
}
if json[i] > ' ' {
goto end
}
}
r.vc = vc
}
if r.vc == '{' {
if valueize {
r.oi = make(map[string]interface{})
} else {
r.o = make(map[string]Result)
}
} else {
if valueize {
r.ai = make([]interface{}, 0)
} else {
r.a = make([]Result, 0)
}
}
for ; i < len(json); i++ {
if json[i] <= ' ' {
continue
}
// get next value
if json[i] == ']' || json[i] == '}' {
break
}
switch json[i] {
default:
if (json[i] >= '0' && json[i] <= '9') || json[i] == '-' {
value.Type = Number
value.Raw, value.Num = tonum(json[i:])
} else {
continue
}
case '{', '[':
value.Type = JSON
value.Raw = squash(json[i:])
case 'n':
value.Type = Null
value.Raw = tolit(json[i:])
case 't':
value.Type = True
value.Raw = tolit(json[i:])
case 'f':
value.Type = False
value.Raw = tolit(json[i:])
case '"':
value.Type = String
value.Raw, value.Str = tostr(json[i:])
}
i += len(value.Raw) - 1
if r.vc == '{' {
if count%2 == 0 {
key = value
} else {
if valueize {
r.oi[key.Str] = value.Value()
} else {
r.o[key.Str] = value
}
}
count++
} else {
if valueize {
r.ai = append(r.ai, value.Value())
} else {
r.a = append(r.a, value)
}
}
}
end:
return
}
// Parse parses the json and returns a result
func Parse(json string) Result {
var value Result
for i := 0; i < len(json); i++ {
if json[i] == '{' || json[i] == '[' {
value.Type = JSON
value.Raw = json[i:] // just take the entire raw
break
}
if json[i] <= ' ' {
continue
}
switch json[i] {
default:
if (json[i] >= '0' && json[i] <= '9') || json[i] == '-' {
value.Type = Number
value.Raw, value.Num = tonum(json[i:])
} else {
return Result{}
}
case 'n':
value.Type = Null
value.Raw = tolit(json[i:])
case 't':
value.Type = True
value.Raw = tolit(json[i:])
case 'f':
value.Type = False
value.Raw = tolit(json[i:])
case '"':
value.Type = String
value.Raw, value.Str = tostr(json[i:])
}
break
}
return value
}
func squash(json string) string {
// expects that the lead character is a '[' or '{'
// squash the value, ignoring all nested arrays and objects.
// the first '[' or '{' has already been read
depth := 1
for i := 1; i < len(json); i++ {
if json[i] >= '"' && json[i] <= '}' {
switch json[i] {
case '"':
i++
s2 := i
for ; i < len(json); i++ {
if json[i] > '\\' {
continue
}
if json[i] == '"' {
// look for an escaped slash
if json[i-1] == '\\' {
n := 0
for j := i - 2; j > s2-1; j-- {
if json[j] != '\\' {
break
}
n++
}
if n%2 == 0 {
continue
}
}
break
}
}
case '{', '[':
depth++
case '}', ']':
depth--
if depth == 0 {
return json[:i+1]
}
}
}
}
return json
}
func tonum(json string) (raw string, num float64) {
for i := 1; i < len(json); i++ {
// less than dash might have valid characters
if json[i] <= '-' {
if json[i] <= ' ' || json[i] == ',' {
// break on whitespace and comma
raw = json[:i]
num, _ = strconv.ParseFloat(raw, 64)
return
}
// could be a '+' or '-'. let's assume so.
continue
}
if json[i] < ']' {
// probably a valid number
continue
}
if json[i] == 'e' || json[i] == 'E' {
// allow for exponential numbers
continue
}
// likely a ']' or '}'
raw = json[:i]
num, _ = strconv.ParseFloat(raw, 64)
return
}
raw = json
num, _ = strconv.ParseFloat(raw, 64)
return
}
func tolit(json string) (raw string) {
for i := 1; i < len(json); i++ {
if json[i] <= 'a' || json[i] >= 'z' {
return json[:i]
}
}
return json
}
func tostr(json string) (raw string, str string) {
// expects that the lead character is a '"'
for i := 1; i < len(json); i++ {
if json[i] > '\\' {
continue
}
if json[i] == '"' {
return json[:i+1], json[1:i]
}
if json[i] == '\\' {
i++
for ; i < len(json); i++ {
if json[i] > '\\' {
continue
}
if json[i] == '"' {
// look for an escaped slash
if json[i-1] == '\\' {
n := 0
for j := i - 2; j > 0; j-- {
if json[j] != '\\' {
break
}
n++
}
if n%2 == 0 {
continue
}
}
break
}
}
return json[:i+1], unescape(json[1:i])
}
}
return json, json[1:]
}
// Exists returns true if value exists.
//
// if gjson.Get(json, "name.last").Exists(){
// println("value exists")
// }
func (t Result) Exists() bool {
return t.Type != Null || len(t.Raw) != 0
}
// Value returns one of these types:
//
// bool, for JSON booleans
// float64, for JSON numbers
// Number, for JSON numbers
// string, for JSON string literals
// nil, for JSON null
//
func (t Result) Value() interface{} {
if t.Type == String {
return t.Str
}
switch t.Type {
default:
return nil
case False:
return false
case Number:
return t.Num
case JSON:
r := t.arrayOrMap(0, true)
if r.vc == '{' {
return r.oi
} else if r.vc == '[' {
return r.ai
}
return nil
case True:
return true
}
}
func parseString(json string, i int) (int, string, bool, bool) {
var s = i
for ; i < len(json); i++ {
if json[i] > '\\' {
continue
}
if json[i] == '"' {
return i + 1, json[s-1 : i+1], false, true
}
if json[i] == '\\' {
i++
for ; i < len(json); i++ {
if json[i] > '\\' {
continue
}
if json[i] == '"' {
// look for an escaped slash
if json[i-1] == '\\' {
n := 0
for j := i - 2; j > 0; j-- {
if json[j] != '\\' {
break
}
n++
}
if n%2 == 0 {
continue
}
}
return i + 1, json[s-1 : i+1], true, true
}
}
break
}
}
return i, json[s-1:], false, false
}
func parseNumber(json string, i int) (int, string) {
var s = i
i++
for ; i < len(json); i++ {
if json[i] <= ' ' || json[i] == ',' || json[i] == ']' || json[i] == '}' {
return i, json[s:i]
}
}
return i, json[s:]
}
func parseLiteral(json string, i int) (int, string) {
var s = i
i++
for ; i < len(json); i++ {
if json[i] < 'a' || json[i] > 'z' {
return i, json[s:i]
}
}
return i, json[s:]
}
type arrayPathResult struct {
part string
path string
more bool
alogok bool
arrch bool
alogkey string
query struct {
on bool
path string
op string
value string
}
}
func parseArrayPath(path string) (r arrayPathResult) {
for i := 0; i < len(path); i++ {
if path[i] == '.' {
r.part = path[:i]
r.path = path[i+1:]
r.more = true
return
}
if path[i] == '#' {
r.arrch = true
if i == 0 && len(path) > 1 {
if path[1] == '.' {
r.alogok = true
r.alogkey = path[2:]
r.path = path[:1]
} else if path[1] == '[' {
r.query.on = true
// query
i += 2
// whitespace
for ; i < len(path); i++ {
if path[i] > ' ' {
break
}
}
s := i
for ; i < len(path); i++ {
if path[i] <= ' ' || path[i] == '=' ||
path[i] == '<' || path[i] == '>' ||
path[i] == ']' {
break
}
}
r.query.path = path[s:i]
// whitespace
for ; i < len(path); i++ {
if path[i] > ' ' {
break
}
}
if i < len(path) {
s = i
if path[i] == '<' || path[i] == '>' {
if i < len(path)-1 && path[i+1] == '=' {
i++
}
} else if path[i] == '=' {
if i < len(path)-1 && path[i+1] == '=' {
s++
i++
}
}
i++
r.query.op = path[s:i]
// whitespace
for ; i < len(path); i++ {
if path[i] > ' ' {
break
}
}
s = i
for ; i < len(path); i++ {
if path[i] == '"' {
i++
s2 := i
for ; i < len(path); i++ {
if path[i] > '\\' {
continue
}
if path[i] == '"' {
// look for an escaped slash
if path[i-1] == '\\' {
n := 0
for j := i - 2; j > s2-1; j-- {
if path[j] != '\\' {
break
}
n++
}
if n%2 == 0 {
continue
}
}
break
}
}
} else if path[i] == ']' {
break
}
}
if i > len(path) {
i = len(path)
}
v := path[s:i]
for len(v) > 0 && v[len(v)-1] <= ' ' {
v = v[:len(v)-1]
}
r.query.value = v
}
}
}
continue
}
}
r.part = path
r.path = ""
return
}
type objectPathResult struct {
part string
path string
wild bool
more bool
}
func parseObjectPath(path string) (r objectPathResult) {
for i := 0; i < len(path); i++ {
if path[i] == '.' {
r.part = path[:i]
r.path = path[i+1:]
r.more = true
return
}
if path[i] == '*' || path[i] == '?' {
r.wild = true
continue
}
if path[i] == '\\' {
// go into escape mode. this is a slower path that
// strips off the escape character from the part.
epart := []byte(path[:i])
i++
if i < len(path) {
epart = append(epart, path[i])
i++
for ; i < len(path); i++ {
if path[i] == '\\' {
i++
if i < len(path) {
epart = append(epart, path[i])
}
continue
} else if path[i] == '.' {
r.part = string(epart)
r.path = path[i+1:]
r.more = true
return
} else if path[i] == '*' || path[i] == '?' {
r.wild = true
}
epart = append(epart, path[i])
}
}
// append the last part
r.part = string(epart)
return
}
}
r.part = path
return
}
func parseSquash(json string, i int) (int, string) {
// expects that the lead character is a '[' or '{'
// squash the value, ignoring all nested arrays and objects.
// the first '[' or '{' has already been read
s := i
i++
depth := 1
for ; i < len(json); i++ {
if json[i] >= '"' && json[i] <= '}' {
switch json[i] {
case '"':
i++
s2 := i
for ; i < len(json); i++ {
if json[i] > '\\' {
continue
}
if json[i] == '"' {
// look for an escaped slash
if json[i-1] == '\\' {
n := 0
for j := i - 2; j > s2-1; j-- {
if json[j] != '\\' {
break
}
n++
}
if n%2 == 0 {
continue
}
}
break
}
}
case '{', '[':
depth++
case '}', ']':
depth--
if depth == 0 {
i++
return i, json[s:i]
}
}
}
}
return i, json[s:]
}
func parseObject(c *parseContext, i int, path string) (int, bool) {
var pmatch, kesc, vesc, ok, hit bool
var key, val string
rp := parseObjectPath(path)
for i < len(c.json) {
for ; i < len(c.json); i++ {
if c.json[i] == '"' {
// parse_key_string
// this is slightly different from getting s string value
// because we don't need the outer quotes.
i++
var s = i
for ; i < len(c.json); i++ {
if c.json[i] > '\\' {
continue
}
if c.json[i] == '"' {
i, key, kesc, ok = i+1, c.json[s:i], false, true
goto parse_key_string_done
}
if c.json[i] == '\\' {
i++
for ; i < len(c.json); i++ {
if c.json[i] > '\\' {
continue
}
if c.json[i] == '"' {
// look for an escaped slash
if c.json[i-1] == '\\' {
n := 0
for j := i - 2; j > 0; j-- {
if c.json[j] != '\\' {
break
}
n++
}
if n%2 == 0 {
continue
}
}
i, key, kesc, ok = i+1, c.json[s:i], true, true
goto parse_key_string_done
}
}
break
}
}
i, key, kesc, ok = i, c.json[s:], false, false
parse_key_string_done:
break
}
if c.json[i] == '}' {
return i + 1, false
}
}
if !ok {
return i, false
}
if rp.wild {
if kesc {
pmatch = match.Match(unescape(key), rp.part)
} else {
pmatch = match.Match(key, rp.part)
}
} else {
if kesc {
pmatch = rp.part == unescape(key)
} else {
pmatch = rp.part == key
}
}
hit = pmatch && !rp.more
for ; i < len(c.json); i++ {
switch c.json[i] {
default:
continue
case '"':
i++
i, val, vesc, ok = parseString(c.json, i)
if !ok {
return i, false
}
if hit {
if vesc {
c.value.Str = unescape(val[1 : len(val)-1])
} else {
c.value.Str = val[1 : len(val)-1]
}
c.value.Raw = val
c.value.Type = String
return i, true
}
case '{':
if pmatch && !hit {
i, hit = parseObject(c, i+1, rp.path)
if hit {
return i, true
}
} else {
i, val = parseSquash(c.json, i)
if hit {
c.value.Raw = val
c.value.Type = JSON
return i, true
}
}
case '[':
if pmatch && !hit {
i, hit = parseArray(c, i+1, rp.path)
if hit {
return i, true
}
} else {
i, val = parseSquash(c.json, i)
if hit {
c.value.Raw = val
c.value.Type = JSON
return i, true
}
}
case '-', '0', '1', '2', '3', '4', '5', '6', '7', '8', '9':
i, val = parseNumber(c.json, i)
if hit {
c.value.Raw = val
c.value.Type = Number
c.value.Num, _ = strconv.ParseFloat(val, 64)
return i, true
}
case 't', 'f', 'n':
vc := c.json[i]
i, val = parseLiteral(c.json, i)
if hit {
c.value.Raw = val
switch vc {
case 't':
c.value.Type = True
case 'f':
c.value.Type = False
}
return i, true
}
}
break
}
}
return i, false
}
func queryMatches(rp *arrayPathResult, value Result) bool {
rpv := rp.query.value
if len(rpv) > 2 && rpv[0] == '"' && rpv[len(rpv)-1] == '"' {
rpv = rpv[1 : len(rpv)-1]
}
switch value.Type {
case String:
switch rp.query.op {
case "=":
return value.Str == rpv
case "<":
return value.Str < rpv
case "<=":
return value.Str <= rpv
case ">":
return value.Str > rpv
case ">=":
return value.Str >= rpv
}
case Number:
rpvn, _ := strconv.ParseFloat(rpv, 64)
switch rp.query.op {
case "=":
return value.Num == rpvn
case "<":
return value.Num < rpvn
case "<=":
return value.Num <= rpvn
case ">":
return value.Num > rpvn
case ">=":
return value.Num >= rpvn
}
case True:
switch rp.query.op {
case "=":
return rpv == "true"
case ">":
return rpv == "false"
case ">=":
return true
}
case False:
switch rp.query.op {
case "=":
return rpv == "false"
case "<":
return rpv == "true"
case "<=":
return true
}
}
return false
}
func parseArray(c *parseContext, i int, path string) (int, bool) {
var pmatch, vesc, ok, hit bool
var val string
var h int
var alog []int
var partidx int
rp := parseArrayPath(path)
if !rp.arrch {
n, err := strconv.ParseUint(rp.part, 10, 64)
if err != nil {
partidx = -1
} else {
partidx = int(n)
}
}
for i < len(c.json) {
if !rp.arrch {
pmatch = partidx == h
hit = pmatch && !rp.more
}
h++
if rp.alogok {
alog = append(alog, i)
}
for ; i < len(c.json); i++ {
switch c.json[i] {
default:
continue
case '"':
i++
i, val, vesc, ok = parseString(c.json, i)
if !ok {
return i, false
}
if hit {
if rp.alogok {
break
}
if vesc {
c.value.Str = unescape(val[1 : len(val)-1])
} else {
c.value.Str = val[1 : len(val)-1]
}
c.value.Raw = val
c.value.Type = String
return i, true
}
case '{':
if pmatch && !hit {
i, hit = parseObject(c, i+1, rp.path)
if hit {
if rp.alogok {
break
}
return i, true
}
} else {
i, val = parseSquash(c.json, i)
if rp.query.on {
res := Get(val, rp.query.path)
if queryMatches(&rp, res) {
if rp.more {
c.value = Get(val, rp.path)
} else {
c.value.Raw = val
c.value.Type = JSON
}
return i, true
}
} else if hit {
if rp.alogok {
break
}
c.value.Raw = val
c.value.Type = JSON
return i, true
}
}
case '[':
if pmatch && !hit {
i, hit = parseArray(c, i+1, rp.path)
if hit {
if rp.alogok {
break
}
return i, true
}
} else {
i, val = parseSquash(c.json, i)
if hit {
if rp.alogok {
break
}
c.value.Raw = val
c.value.Type = JSON
return i, true
}
}
case '-', '0', '1', '2', '3', '4', '5', '6', '7', '8', '9':
i, val = parseNumber(c.json, i)
if hit {
if rp.alogok {
break
}
c.value.Raw = val
c.value.Type = Number
c.value.Num, _ = strconv.ParseFloat(val, 64)
return i, true
}
case 't', 'f', 'n':
vc := c.json[i]
i, val = parseLiteral(c.json, i)
if hit {
if rp.alogok {
break
}
c.value.Raw = val
switch vc {
case 't':
c.value.Type = True
case 'f':
c.value.Type = False
}
return i, true
}
case ']':
if rp.arrch && rp.part == "#" {
if rp.alogok {
var jsons = make([]byte, 0, 64)
jsons = append(jsons, '[')
for j := 0; j < len(alog); j++ {
res := Get(c.json[alog[j]:], rp.alogkey)
if res.Exists() {
if j > 0 {
jsons = append(jsons, ',')
}
jsons = append(jsons, []byte(res.Raw)...)
}
}
jsons = append(jsons, ']')
c.value.Type = JSON
c.value.Raw = string(jsons)
return i + 1, true
} else {
if rp.alogok {
break
}
c.value.Raw = val
c.value.Type = Number
c.value.Num = float64(h - 1)
return i + 1, true
}
}
return i + 1, false
}
break
}
}
return i, false
}
// Get searches json for the specified path.
// A path is in dot syntax, such as "name.last" or "age".
// This function expects that the json is well-formed, and does not validate.
// Invalid json will not panic, but it may return back unexpected results.
// When the value is found it's returned immediately.
//
// A path is a series of keys seperated by a dot.
// A key may contain special wildcard characters '*' and '?'.
// To access an array value use the index as the key.
// To get the number of elements in an array or to access a child path, use the '#' character.
// The dot and wildcard character can be escaped with '\'.
//
// {
// "name": {"first": "Tom", "last": "Anderson"},
// "age":37,
// "children": ["Sara","Alex","Jack"],
// "friends": [
// {"first": "James", "last": "Murphy"},
// {"first": "Roger", "last": "Craig"}
// ]
// }
// "name.last" >> "Anderson"
// "age" >> 37
// "children.#" >> 3
// "children.1" >> "Alex"
// "child*.2" >> "Jack"
// "c?ildren.0" >> "Sara"
// "friends.#.first" >> [ "James", "Roger" ]
//
func Get(json, path string) Result {
var i int
var c = &parseContext{json: json}
for ; i < len(c.json); i++ {
if c.json[i] == '{' {
i++
parseObject(c, i, path)
break
}
if c.json[i] == '[' {
i++
parseArray(c, i, path)
break
}
}
return c.value
}
type parseContext struct {
json string
value Result
}
// unescape unescapes a string
func unescape(json string) string { //, error) {
var str = make([]byte, 0, len(json))
for i := 0; i < len(json); i++ {
switch {
default:
str = append(str, json[i])
case json[i] < ' ':
return "" //, errors.New("invalid character in string")
case json[i] == '\\':
i++
if i >= len(json) {
return "" //, errors.New("invalid escape sequence")
}
switch json[i] {
default:
return "" //, errors.New("invalid escape sequence")
case '\\':
str = append(str, '\\')
case '/':
str = append(str, '/')
case 'b':
str = append(str, '\b')
case 'f':
str = append(str, '\f')
case 'n':
str = append(str, '\n')
case 'r':
str = append(str, '\r')
case 't':
str = append(str, '\t')
case '"':
str = append(str, '"')
case 'u':
if i+5 > len(json) {
return "" //, errors.New("invalid escape sequence")
}
i++
// extract the codepoint
var code int
for j := i; j < i+4; j++ {
switch {
default:
return "" //, errors.New("invalid escape sequence")
case json[j] >= '0' && json[j] <= '9':
code += (int(json[j]) - '0') << uint(12-(j-i)*4)
case json[j] >= 'a' && json[j] <= 'f':
code += (int(json[j]) - 'a' + 10) << uint(12-(j-i)*4)
case json[j] >= 'a' && json[j] <= 'f':
code += (int(json[j]) - 'a' + 10) << uint(12-(j-i)*4)
}
}
str = append(str, []byte(string(code))...)
i += 3 // only 3 because we will increment on the for-loop
}
}
}
return string(str) //, nil
}
// Less return true if a token is less than another token.
// The caseSensitive paramater is used when the tokens are Strings.
// The order when comparing two different type is:
//
// Null < False < Number < String < True < JSON
//
func (t Result) Less(token Result, caseSensitive bool) bool {
if t.Type < token.Type {
return true
}
if t.Type > token.Type {
return false
}
if t.Type == String {
if caseSensitive {
return t.Str < token.Str
}
return stringLessInsensitive(t.Str, token.Str)
}
if t.Type == Number {
return t.Num < token.Num
}
return t.Raw < token.Raw
}
func stringLessInsensitive(a, b string) bool {
for i := 0; i < len(a) && i < len(b); i++ {
if a[i] >= 'A' && a[i] <= 'Z' {
if b[i] >= 'A' && b[i] <= 'Z' {
// both are uppercase, do nothing
if a[i] < b[i] {
return true
} else if a[i] > b[i] {
return false
}
} else {
// a is uppercase, convert a to lowercase
if a[i]+32 < b[i] {
return true
} else if a[i]+32 > b[i] {
return false
}
}
} else if b[i] >= 'A' && b[i] <= 'Z' {
// b is uppercase, convert b to lowercase
if a[i] < b[i]+32 {
return true
} else if a[i] > b[i]+32 {
return false
}
} else {
// neither are uppercase
if a[i] < b[i] {
return true
} else if a[i] > b[i] {
return false
}
}
}
return len(a) < len(b)
}