gofront 1.7.0 → 1.9.0

package/stdlib/internal/jsonrt/scanner.go

@@ -0,0 +1,658 @@
+// 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.
+
+//go:build gofront
+
+//gofront:target both
+
+// Package jsonrt is the runtime behind encoding/json in wasm packages: the
+// JSON scanner (adapted from the Go standard library), the encoder state and
+// the decoder state that the per-type codecs generated by the compiler call.
+package jsonrt
+
+import (
+	"io"
+	"strconv"
+)
+
+// Valid reports whether data is a valid JSON encoding.
+func Valid(data []byte) bool {
+	scan := newScanner()
+	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.
+	// Only the first parseStateLen entries are live; the rest is reused room.
+	parseState    []int
+	parseStateLen 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
+}
+
+func newScanner() *scanner {
+	scan := &scanner{}
+	scan.reset()
+	return 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.parseStateLen = 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 newParseState 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 {
+	if s.parseStateLen < len(s.parseState) {
+		s.parseState[s.parseStateLen] = newParseState
+	} else {
+		s.parseState = append(s.parseState, newParseState)
+	}
+	s.parseStateLen++
+	if s.parseStateLen <= 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() {
+	s.parseStateLen--
+	n := s.parseStateLen
+	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 := s.parseStateLen
+		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 := s.parseStateLen
+	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] + "'"
+}
+
+// CheckValid returns nil when data is one valid JSON value, else the
+// *SyntaxError describing the first problem.
+//
+//gofront:native jsonrt.CheckValid
+func CheckValid(data []byte) error {
+	return checkValid(data, newScanner())
+}
+
+// ScanNext reads and returns the bytes of the next single JSON value from r,
+// along with the number of leading whitespace bytes that were skipped.
+// If EOF is encountered before any non-whitespace bytes, it returns io.EOF.
+// If the stream ends before the JSON value completes, it returns io.ErrUnexpectedEOF.
+func ScanNext(r *Reader) ([]byte, int64, error) {
+	var skipped int64
+	var c byte
+	for {
+		b, err := r.ReadByte()
+		if err != nil {
+			return nil, skipped, err
+		}
+		if isSpace(b) {
+			skipped++
+			continue
+		}
+		c = b
+		break
+	}
+
+	scan := newScanner()
+	buf := []byte{c}
+	scan.bytes++
+	if op := scan.step(scan, c); op == scanError {
+		return nil, skipped, scan.err
+	}
+
+	for {
+		b, err := r.ReadByte()
+		if err == io.EOF {
+			op := scan.eof()
+			if op == scanEnd {
+				return buf, skipped, nil
+			}
+			return nil, skipped, io.ErrUnexpectedEOF
+		}
+		if err != nil {
+			return nil, skipped, err
+		}
+		scan.bytes++
+		op := scan.step(scan, b)
+		if op == scanEnd {
+			r.UnreadByte()
+			return buf, skipped, nil
+		}
+		if op == scanError {
+			return nil, skipped, scan.err
+		}
+		buf = append(buf, b)
+	}
+}