You can not select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
545 lines
15 KiB
545 lines
15 KiB
// Copyright (c) 2009 The Go Authors. All rights reserved.
|
|
//
|
|
// Redistribution and use in source and binary forms, with or without
|
|
// modification, are permitted provided that the following conditions are
|
|
// met:
|
|
//
|
|
// * Redistributions of source code must retain the above copyright
|
|
// notice, this list of conditions and the following disclaimer.
|
|
// * Redistributions in binary form must reproduce the above
|
|
// copyright notice, this list of conditions and the following disclaimer
|
|
// in the documentation and/or other materials provided with the
|
|
// distribution.
|
|
// * Neither the name of Google Inc. nor the names of its
|
|
// contributors may be used to endorse or promote products derived from
|
|
// this software without specific prior written permission.
|
|
//
|
|
// THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
|
|
// "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
|
|
// LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
|
|
// A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
|
|
// OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
|
|
// SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
|
|
// LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
|
|
// DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
|
|
// THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
|
|
// (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
|
|
// OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
|
|
|
|
// Package json provides a JSON value parser state machine.
|
|
// This package is almost entirely copied from the Go stdlib.
|
|
// Changes made to it permit users of the package to tell
|
|
// if some slice of bytes is a valid beginning of a json string.
|
|
package json
|
|
|
|
import (
|
|
"fmt"
|
|
)
|
|
|
|
type (
|
|
scanStatus int
|
|
)
|
|
|
|
const (
|
|
parseObjectKey = iota // parsing object key (before colon)
|
|
parseObjectValue // parsing object value (after colon)
|
|
parseArrayValue // parsing array value
|
|
|
|
scanContinue scanStatus = 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
|
|
scanEnd // top-level value ended *before* this byte; known to be first "stop" result
|
|
scanError // hit an error, scanner.err.
|
|
|
|
// This limits the max nesting depth to prevent stack overflow.
|
|
// This is permitted by https://tools.ietf.org/html/rfc7159#section-9
|
|
maxNestingDepth = 10000
|
|
)
|
|
|
|
type (
|
|
scanner struct {
|
|
step func(*scanner, byte) scanStatus
|
|
parseState []int
|
|
endTop bool
|
|
err error
|
|
index int
|
|
}
|
|
)
|
|
|
|
// Scan returns the number of bytes scanned and if there was any error
|
|
// in trying to reach the end of data.
|
|
func Scan(data []byte) (int, error) {
|
|
s := &scanner{}
|
|
_ = checkValid(data, s)
|
|
return s.index, s.err
|
|
}
|
|
|
|
// checkValid verifies that data is valid JSON-encoded data.
|
|
// scan is passed in for use by checkValid to avoid an allocation.
|
|
func checkValid(data []byte, scan *scanner) error {
|
|
scan.reset()
|
|
for _, c := range data {
|
|
scan.index++
|
|
if scan.step(scan, c) == scanError {
|
|
return scan.err
|
|
}
|
|
}
|
|
if scan.eof() == scanError {
|
|
return scan.err
|
|
}
|
|
return nil
|
|
}
|
|
|
|
func isSpace(c byte) bool {
|
|
return c == ' ' || c == '\t' || c == '\r' || c == '\n'
|
|
}
|
|
|
|
func (s *scanner) reset() {
|
|
s.step = stateBeginValue
|
|
s.parseState = s.parseState[0:0]
|
|
s.err = nil
|
|
}
|
|
|
|
// 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() scanStatus {
|
|
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 = fmt.Errorf("unexpected end of JSON input")
|
|
}
|
|
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 scanStatus) scanStatus {
|
|
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
|
|
}
|
|
}
|
|
|
|
// stateBeginValueOrEmpty is the state after reading `[`.
|
|
func stateBeginValueOrEmpty(s *scanner, c byte) scanStatus {
|
|
if c <= ' ' && 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) scanStatus {
|
|
if c <= ' ' && 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) scanStatus {
|
|
if c <= ' ' && 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) scanStatus {
|
|
if c <= ' ' && 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) scanStatus {
|
|
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 c <= ' ' && 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) scanStatus {
|
|
if c != ' ' && c != '\t' && c != '\r' && c != '\n' {
|
|
// 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) scanStatus {
|
|
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) scanStatus {
|
|
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) scanStatus {
|
|
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) scanStatus {
|
|
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) scanStatus {
|
|
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) scanStatus {
|
|
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) scanStatus {
|
|
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) scanStatus {
|
|
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) scanStatus {
|
|
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) scanStatus {
|
|
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) scanStatus {
|
|
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) scanStatus {
|
|
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) scanStatus {
|
|
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) scanStatus {
|
|
if '0' <= c && c <= '9' {
|
|
return scanContinue
|
|
}
|
|
return stateEndValue(s, c)
|
|
}
|
|
|
|
// stateT is the state after reading `t`.
|
|
func stateT(s *scanner, c byte) scanStatus {
|
|
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) scanStatus {
|
|
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) scanStatus {
|
|
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) scanStatus {
|
|
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) scanStatus {
|
|
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) scanStatus {
|
|
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) scanStatus {
|
|
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) scanStatus {
|
|
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) scanStatus {
|
|
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) scanStatus {
|
|
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) scanStatus {
|
|
return scanError
|
|
}
|
|
|
|
// error records an error and switches to the error state.
|
|
func (s *scanner) error(c byte, context string) scanStatus {
|
|
s.step = stateError
|
|
s.err = fmt.Errorf("invalid character <<%c>> %s", c, context)
|
|
return scanError
|
|
}
|