contentjson: Import from go1.21.4

common/json/internal/contextjson/fold.go

@@ -0,0 +1,48 @@
+// 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 (
+	"unicode"
+	"unicode/utf8"
+)
+
+// foldName returns a folded string such that foldName(x) == foldName(y)
+// is identical to bytes.EqualFold(x, y).
+func foldName(in []byte) []byte {
+	// This is inlinable to take advantage of "function outlining".
+	var arr [32]byte // large enough for most JSON names
+	return appendFoldedName(arr[:0], in)
+}
+
+func appendFoldedName(out, in []byte) []byte {
+	for i := 0; i < len(in); {
+		// Handle single-byte ASCII.
+		if c := in[i]; c < utf8.RuneSelf {
+			if 'a' <= c && c <= 'z' {
+				c -= 'a' - 'A'
+			}
+			out = append(out, c)
+			i++
+			continue
+		}
+		// Handle multi-byte Unicode.
+		r, n := utf8.DecodeRune(in[i:])
+		out = utf8.AppendRune(out, foldRune(r))
+		i += n
+	}
+	return out
+}
+
+// foldRune is returns the smallest rune for all runes in the same fold set.
+func foldRune(r rune) rune {
+	for {
+		r2 := unicode.SimpleFold(r)
+		if r2 <= r {
+			return r2
+		}
+		r = r2
+	}
+}

common/json/internal/contextjson/indent.go

@@ -0,0 +1,174 @@
+// 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"
+
+// HTMLEscape appends to dst the JSON-encoded src with <, >, &, U+2028 and U+2029
+// characters inside string literals changed to \u003c, \u003e, \u0026, \u2028, \u2029
+// so that the JSON will be safe to embed inside HTML <script> tags.
+// For historical reasons, web browsers don't honor standard HTML
+// escaping within <script> tags, so an alternative JSON encoding must be used.
+func HTMLEscape(dst *bytes.Buffer, src []byte) {
+	dst.Grow(len(src))
+	dst.Write(appendHTMLEscape(dst.AvailableBuffer(), src))
+}
+
+func appendHTMLEscape(dst, src []byte) []byte {
+	// The characters can only appear in string literals,
+	// so just scan the string one byte at a time.
+	start := 0
+	for i, c := range src {
+		if c == '<' || c == '>' || c == '&' {
+			dst = append(dst, src[start:i]...)
+			dst = append(dst, '\\', 'u', '0', '0', hex[c>>4], hex[c&0xF])
+			start = i + 1
+		}
+		// Convert U+2028 and U+2029 (E2 80 A8 and E2 80 A9).
+		if c == 0xE2 && i+2 < len(src) && src[i+1] == 0x80 && src[i+2]&^1 == 0xA8 {
+			dst = append(dst, src[start:i]...)
+			dst = append(dst, '\\', 'u', '2', '0', '2', hex[src[i+2]&0xF])
+			start = i + len("\u2029")
+		}
+	}
+	return append(dst, src[start:]...)
+}
+
+// Compact appends to dst the JSON-encoded src with
+// insignificant space characters elided.
+func Compact(dst *bytes.Buffer, src []byte) error {
+	dst.Grow(len(src))
+	b := dst.AvailableBuffer()
+	b, err := appendCompact(b, src, false)
+	dst.Write(b)
+	return err
+}
+
+func appendCompact(dst, src []byte, escape bool) ([]byte, error) {
+	origLen := len(dst)
+	scan := newScanner()
+	defer freeScanner(scan)
+	start := 0
+	for i, c := range src {
+		if escape && (c == '<' || c == '>' || c == '&') {
+			dst = append(dst, src[start:i]...)
+			dst = append(dst, '\\', 'u', '0', '0', hex[c>>4], 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 {
+			dst = append(dst, src[start:i]...)
+			dst = append(dst, '\\', 'u', '2', '0', '2', hex[src[i+2]&0xF])
+			start = i + len("\u2029")
+		}
+		v := scan.step(scan, c)
+		if v >= scanSkipSpace {
+			if v == scanError {
+				break
+			}
+			dst = append(dst, src[start:i]...)
+			start = i + 1
+		}
+	}
+	if scan.eof() == scanError {
+		return dst[:origLen], scan.err
+	}
+	dst = append(dst, src[start:]...)
+	return dst, nil
+}
+
+func appendNewline(dst []byte, prefix, indent string, depth int) []byte {
+	dst = append(dst, '\n')
+	dst = append(dst, prefix...)
+	for i := 0; i < depth; i++ {
+		dst = append(dst, indent...)
+	}
+	return dst
+}
+
+// indentGrowthFactor specifies the growth factor of indenting JSON input.
+// Empirically, the growth factor was measured to be between 1.4x to 1.8x
+// for some set of compacted JSON with the indent being a single tab.
+// Specify a growth factor slightly larger than what is observed
+// to reduce probability of allocation in appendIndent.
+// A factor no higher than 2 ensures that wasted space never exceeds 50%.
+const indentGrowthFactor = 2
+
+// 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 {
+	dst.Grow(indentGrowthFactor * len(src))
+	b := dst.AvailableBuffer()
+	b, err := appendIndent(b, src, prefix, indent)
+	dst.Write(b)
+	return err
+}
+
+func appendIndent(dst, src []byte, prefix, indent string) ([]byte, error) {
+	origLen := len(dst)
+	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++
+			dst = appendNewline(dst, prefix, indent, depth)
+		}
+
+		// Emit semantically uninteresting bytes
+		// (in particular, punctuation in strings) unmodified.
+		if v == scanContinue {
+			dst = append(dst, 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 = append(dst, c)
+		case ',':
+			dst = append(dst, c)
+			dst = appendNewline(dst, prefix, indent, depth)
+		case ':':
+			dst = append(dst, c, ' ')
+		case '}', ']':
+			if needIndent {
+				// suppress indent in empty object/array
+				needIndent = false
+			} else {
+				depth--
+				dst = appendNewline(dst, prefix, indent, depth)
+			}
+			dst = append(dst, c)
+		default:
+			dst = append(dst, c)
+		}
+	}
+	if scan.eof() == scanError {
+		return dst[:origLen], scan.err
+	}
+	return dst, nil
+}

common/json/internal/contextjson/scanner.go

@@ -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] + "'"
+}

common/json/internal/contextjson/stream.go

@@ -0,0 +1,513 @@
+// 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    []byte
+	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 != "" {
+		enc.indentBuf, err = appendIndent(enc.indentBuf[:0], b, enc.indentPrefix, enc.indentValue)
+		if err != nil {
+			return err
+		}
+		b = enc.indentBuf
+	}
+	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)
+	_ 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)
+}

common/json/internal/contextjson/tables.go

@@ -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,
+}

common/json/internal/contextjson/tags.go

@@ -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
+}