add spell check

Signed-off-by: spacewander <[email protected]>

.github/workflows/.ignore_words

@@ -0,0 +1,6 @@
+socio-economic
+nd
+regArgs
+oders
+ure
+alse

.github/workflows/lint.yml

@@ -0,0 +1,13 @@
+name: Lint
+
+on: pull_request
+
+jobs:
+  misc:
+    runs-on: [self-hosted, X64]
+    steps:
+      - uses: actions/checkout@v4
+      - name: spell check
+        run: |
+          pip install codespell==2.3.0
+          git grep --cached -l '' | xargs codespell  --skip 'fuzz/*,*_test.tmpl,testdata/*,*_test.go,go.mod,go.sum,*.gz' --ignore-words=.github/workflows/.ignore_words

README.md

@@ -211,7 +211,7 @@ ret, err := Encode(v, EscapeHTML) // ret == `{"\u0026\u0026":{"X":"\u003c\u003e"
 
 ### Compact Format
 
-Sonic encodes primitive objects (struct/map...) as compact-format JSON by default, except marshaling `json.RawMessage` or `json.Marshaler`: sonic ensures validating their output JSON but **DONOT** compacting them for performance concerns. We provide the option `encoder.CompactMarshaler` to add compacting process.
+Sonic encodes primitive objects (struct/map...) as compact-format JSON by default, except marshaling `json.RawMessage` or `json.Marshaler`: sonic ensures validating their output JSON but **DO NOT** compacting them for performance concerns. We provide the option `encoder.CompactMarshaler` to add compacting process.
 
 ### Print Error
 
@@ -480,7 +480,7 @@ But `ast.Visitor` is not a very handy API. You might need to write a lot of code
 
 ### Buffer Size
 
-Sonic use memory pool in many places like `encoder.Encode`, `ast.Node.MarshalJSON` to improve performace, which may produce more memory usage (in-use) when server's load is high. See [issue 614](https://github.com/bytedance/sonic/issues/614). Therefore, we introduce some options to let user control the behavior of memory pool. See [option](https://pkg.go.dev/github.com/bytedance/[email protected]/option#pkg-variables) package.
+Sonic use memory pool in many places like `encoder.Encode`, `ast.Node.MarshalJSON` to improve performance, which may produce more memory usage (in-use) when server's load is high. See [issue 614](https://github.com/bytedance/sonic/issues/614). Therefore, we introduce some options to let user control the behavior of memory pool. See [option](https://pkg.go.dev/github.com/bytedance/[email protected]/option#pkg-variables) package.
 
 ### Faster JSON skip
 

api.go

@@ -120,7 +120,7 @@ var (
 
 // API is a binding of specific config.
 // This interface is inspired by github.com/json-iterator/go,
-// and has same behaviors under equavilent config.
+// and has same behaviors under equivalent config.
 type API interface {
     // MarshalToString returns the JSON encoding string of v
     MarshalToString(v interface{}) (string, error)

ast/api_compat.go

@@ -34,7 +34,7 @@ func quote(buf *[]byte, val string) {
     quoteString(buf, val)
 }
 
-// unquote unescapes a internal JSON string (it doesn't count quotas at the begining and end)
+// unquote unescapes an internal JSON string (it doesn't count quotas at the beginning and end)
 func unquote(src string) (string, types.ParsingError) {
     sp := rt.IndexChar(src, -1)
     out, ok := unquoteBytes(rt.BytesFrom(sp, len(src)+2, len(src)+2))

ast/decode.go

@@ -27,7 +27,7 @@ import (
 	"github.com/bytedance/sonic/internal/utils"
 )
 
-// Hack: this is used for both checking space and cause firendly compile errors in 32-bit arch.
+// Hack: this is used for both checking space and cause friendly compile errors in 32-bit arch.
 const _Sonic_Not_Support_32Bit_Arch__Checking_32Bit_Arch_Here = (1 << ' ') | (1 << '\t') | (1 << '\r') | (1 << '\n')
 
 var bytesNull   = []byte("null")

ast/iterator.go

@@ -173,7 +173,7 @@ type Scanner func(path Sequence, node *Node) bool
 // ForEach scans one V_OBJECT node's children from JSON head to tail, 
 // and pass the Sequence and Node of corresponding JSON value.
 //
-// Especailly, if the node is not V_ARRAY or V_OBJECT, 
+// Especially, if the node is not V_ARRAY or V_OBJECT,
 // the node itself will be returned and Sequence.Index == -1.
 // 
 // NOTICE: A unsetted node WON'T trigger sc, but its index still counts into Path.Index

ast/node.go

@@ -140,7 +140,7 @@ func (self *Node)  Check() error {
 
 // isRaw returns true if node's underlying value is raw json
 //
-// Deprecated: not concurent safe
+// Deprecated: not concurrent safe
 func (self Node) IsRaw() bool {
     return self.t & _V_RAW != 0
 }
@@ -440,7 +440,7 @@ func (self *Node) String() (string, error) {
     }
 }
 
-// StrictString returns string value (unescaped), includeing V_STRING, V_ANY of string.
+// StrictString returns string value (unescaped), including V_STRING, V_ANY of string.
 // In other cases, it will return empty string.
 func (self *Node) StrictString() (string, error) {
     if err := self.checkRaw(); err != nil {
@@ -509,7 +509,7 @@ func (self *Node) Float64() (float64, error) {
     }
 }
 
-// Float64 exports underlying float64 value, includeing V_NUMBER, V_ANY 
+// Float64 exports underlying float64 value, including V_NUMBER, V_ANY
 func (self *Node) StrictFloat64() (float64, error) {
     if err := self.checkRaw(); err != nil {
         return 0.0, err
@@ -527,7 +527,7 @@ func (self *Node) StrictFloat64() (float64, error) {
     }
 }
 
-/** Sequencial Value Methods **/
+/** Sequential Value Methods **/
 
 // Len returns children count of a array|object|string node
 // WARN: For partially loaded node, it also works but only counts the parsed children
@@ -611,7 +611,7 @@ func (self *Node) Unset(key string) (bool, error) {
     if err := self.should(types.V_OBJECT); err != nil {
         return false, err
     }
-    // NOTICE: must get acurate length before deduct
+    // NOTICE: must get accurate length before deduct
     if err := self.skipAllKey(); err != nil {
         return false, err
     }
@@ -657,7 +657,7 @@ func (self *Node) SetAnyByIndex(index int, val interface{}) (bool, error) {
     return self.SetByIndex(index, NewAny(val))
 }
 
-// UnsetByIndex REOMVE (softly) the node of given index.
+// UnsetByIndex REMOVE (softly) the node of given index.
 //
 // WARN: this will change address of elements, which is a dangerous action.
 // Use Unset() for object or Pop() for array instead.
@@ -957,7 +957,7 @@ func (self *Node) MapUseNumber() (map[string]interface{}, error) {
     return self.toGenericObjectUseNumber()
 }
 
-// MapUseNode scans both parsed and non-parsed chidren nodes, 
+// MapUseNode scans both parsed and non-parsed children nodes,
 // and map them by their keys
 func (self *Node) MapUseNode() (map[string]Node, error) {
     if self.isAny() {
@@ -1102,7 +1102,7 @@ func (self *Node) ArrayUseNumber() ([]interface{}, error) {
     return self.toGenericArrayUseNumber()
 }
 
-// ArrayUseNode copys both parsed and non-parsed chidren nodes, 
+// ArrayUseNode copies both parsed and non-parsed children nodes,
 // and indexes them by original order
 func (self *Node) ArrayUseNode() ([]Node, error) {
     if self.isAny() {
@@ -1147,9 +1147,9 @@ func (self *Node) unsafeArray() (*linkedNodes, error) {
     return (*linkedNodes)(self.p), nil
 }
 
-// Interface loads all children under all pathes from this node,
+// Interface loads all children under all paths from this node,
 // and converts itself as generic type.
-// WARN: all numberic nodes are casted to float64
+// WARN: all numeric nodes are casted to float64
 func (self *Node) Interface() (interface{}, error) {
     if err := self.checkRaw(); err != nil {
         return nil, err
@@ -1193,7 +1193,7 @@ func (self *Node) packAny() interface{} {
 }
 
 // InterfaceUseNumber works same with Interface()
-// except numberic nodes  are casted to json.Number
+// except numeric nodes are casted to json.Number
 func (self *Node) InterfaceUseNumber() (interface{}, error) {
     if err := self.checkRaw(); err != nil {
         return nil, err

decoder/decoder_compat.go

@@ -192,5 +192,5 @@ func (s SyntaxError) Error() string {
      return (*json.SyntaxError)(unsafe.Pointer(&s)).Error()
 }
 
-// MismatchTypeError represents dismatching between json and object
-type MismatchTypeError json.UnmarshalTypeError
+// MismatchTypeError represents mismatching between json and object
+type MismatchTypeError json.UnmarshalTypeError

decoder/decoder_native.go

@@ -30,7 +30,7 @@ type Decoder = api.Decoder
 // SyntaxError represents json syntax error
 type SyntaxError = api.SyntaxError
 
-// MismatchTypeError represents dismatching between json and object
+// MismatchTypeError represents mismatching between json and object
 type MismatchTypeError = api.MismatchTypeError
 
 // Options for decode.

docs/INTRODUCTION.md

@@ -14,7 +14,7 @@ Therefore, we decided to **develop a brand-new JSON library with high performanc
 Before starting our design, we need to figure out some questions:
 
 ### Why is Json-iterator faster than Standard Library?
-First of all, the **schema-based processing mechanism** used by the standard library is commendable, in which the parser can obtain meta information in advance when scanning, thereby shortening the time of branch selection. However, its original implementation did not make good use of this mechanism, instead, **it spent a lot of time reflecting to obtain meta info of schema**. Meanwhile, The approach of json-iterator is: Interprete structure as field-by-field encoding and decoding functions, and then assembled and cached them, minimizing the performance loss cost by reflection. But does it work once and for all? No. In practical tests, we found that **the deeper and larger the input JSON got, the smaller the gap between json-iterator and other libraries gradually became** - eventually event got surpassed:
+First of all, the **schema-based processing mechanism** used by the standard library is commendable, in which the parser can obtain meta information in advance when scanning, thereby shortening the time of branch selection. However, its original implementation did not make good use of this mechanism, instead, **it spent a lot of time reflecting to obtain meta info of schema**. Meanwhile, The approach of json-iterator is: Interpret structure as field-by-field encoding and decoding functions, and then assembled and cached them, minimizing the performance loss cost by reflection. But does it work once and for all? No. In practical tests, we found that **the deeper and larger the input JSON got, the smaller the gap between json-iterator and other libraries gradually became** - eventually event got surpassed:
 ![Scalability](./imgs/introduction-1.png) 
 
 The reason is that **this implementation transforms into a large number of interface encapsulations and function calls**, followed by function-call losses:

internal/decoder/api/decoder_arm64.go

@@ -30,7 +30,7 @@ var (
 
 
 func init() {
-    // whe in aarch64. we enable all optimize
+    // when in aarch64, we enable all optimization
 	envs.EnableOptDec()
 	envs.EnableFastMap()
 }

internal/decoder/jitdec/assembler_regabi_amd64.go

@@ -67,7 +67,7 @@ import (
  */
 
 const (
-    _FP_args   = 72     // 72 bytes to pass and spill register arguements
+    _FP_args   = 72     // 72 bytes to pass and spill register arguments
     _FP_fargs  = 80     // 80 bytes for passing arguments to other Go functions
     _FP_saves  = 48     // 48 bytes for saving the registers before CALL instructions
     _FP_locals = 144    // 144 bytes for local variables
@@ -203,9 +203,9 @@ var (
 var _VAR_fl = jit.Ptr(_SP, _FP_fargs + _FP_saves + 112)
 
 var (
-    _VAR_et = jit.Ptr(_SP, _FP_fargs + _FP_saves + 120) // save dismatched type
+    _VAR_et = jit.Ptr(_SP, _FP_fargs + _FP_saves + 120) // save mismatched type
     _VAR_pc = jit.Ptr(_SP, _FP_fargs + _FP_saves + 128) // save skip return pc
-    _VAR_ic = jit.Ptr(_SP, _FP_fargs + _FP_saves + 136) // save dismatched position
+    _VAR_ic = jit.Ptr(_SP, _FP_fargs + _FP_saves + 136) // save mismatched position
 )
 
 type _Assembler struct {
@@ -1361,7 +1361,7 @@ func (self *_Assembler) _asm_OP_num(_ *_Instr) {
     self.Emit("MOVQ", _R9, _VAR_pc)
     self.Sjmp("JMP"  , _LB_skip_one)
 
-    /* assgin string */
+    /* assign string */
     self.Link("_num_next_{n}")
     self.slice_from_r(_AX, 0)
     self.Emit("BTQ", jit.Imm(_F_copy_string), _ARG_fv)

internal/decoder/jitdec/compiler.go

@@ -736,7 +736,7 @@ func (self *_Compiler) compilePtr(p *_Program, sp int, et reflect.Type) {
         self.tab[et] = true
 
         /* not inline the pointer type
-        * recursing the defined pointer type's elem will casue issue379.
+        * recursing the defined pointer type's elem will cause issue379.
         */
         self.compileOps(p, sp, et)
     }

internal/decoder/jitdec/pools.go

@@ -63,8 +63,8 @@ type _Decoder func(
     vp unsafe.Pointer,
     sb *_Stack,
     fv uint64,
-    sv string, // DO NOT pass value to this arguement, since it is only used for local _VAR_sv
-    vk unsafe.Pointer, // DO NOT pass value to this arguement, since it is only used for local _VAR_vk
+    sv string, // DO NOT pass value to this argument, since it is only used for local _VAR_sv
+    vk unsafe.Pointer, // DO NOT pass value to this argument, since it is only used for local _VAR_vk
 ) (int, error)
 
 var _KeepAlive struct {

internal/decoder/optdec/compiler.go

@@ -177,7 +177,7 @@ func (c *compiler) compilePtr(vt reflect.Type) decFunc {
 	c.enter(vt)
 	defer c.exit(vt)
 
-	// specail logic for Named Ptr, issue 379
+	// special logic for Named Ptr, issue 379
 	if reflect.PtrTo(vt.Elem()) != vt {
 		c.namedPtr = true
 		return &ptrDecoder{
@@ -432,7 +432,7 @@ func (c *compiler) tryCompilePtrUnmarshaler(vt reflect.Type, strOpt bool) decFun
 
 	/* check for `encoding.TextMarshaler` with pointer receiver */
 	if pt.Implements(encodingTextUnmarshalerType) {
-		/* TextUnmarshal not support ,strig tag */
+		/* TextUnmarshal not support, string tag */
 		if strOpt {
 			panicForInvalidStrType(vt)
 		}

internal/decoder/optdec/helper.go

@@ -11,7 +11,7 @@ import (
 
 
 func SkipNumberFast(json string, start int) (int, bool) {
-	// find the number ending, we pasred in native, it alway valid
+	// find the number ending, we parsed in native, it always valid
 	pos := start
 	for pos < len(json) && json[pos] != ']' && json[pos] != '}' && json[pos] != ',' {
 		if json[pos] >= '0' && json[pos] <= '9' || json[pos] == '.' || json[pos] == '-' || json[pos] == '+' || json[pos] == 'e' || json[pos] == 'E' {
@@ -40,7 +40,7 @@ func ValidNumberFast(raw string) bool {
 		return false
 	}
 
-	// check trainling chars
+	// check trailing chars
 	for ret < len(raw) {
 		return false
 	}
@@ -49,7 +49,7 @@ func ValidNumberFast(raw string) bool {
 }
 
 func SkipOneFast2(json string, pos *int) (int, error) {
-	// find the number ending, we pasred in sonic-cpp, it alway valid
+	// find the number ending, we parsed in sonic-cpp, it always valid
 	start := native.SkipOneFast(&json, pos)
 	if start < 0 {
 		return -1, error_syntax(*pos, json, types.ParsingError(-start).Error())
@@ -58,7 +58,7 @@ func SkipOneFast2(json string, pos *int) (int, error) {
 }
 
 func SkipOneFast(json string, pos int) (string, error) {
-	// find the number ending, we pasred in sonic-cpp, it alway valid
+	// find the number ending, we parsed in sonic-cpp, it always valid
 	start := native.SkipOneFast(&json, &pos)
 	if start < 0 {
 		// TODO: details error code

internal/decoder/optdec/native.go

@@ -61,13 +61,13 @@ type node struct {
 	val uint64
 }
 
-// should consitent with native/parser.c
+// should consistent with native/parser.c
 type _nospaceBlock struct {
 	_ [8]byte
 	_ [8]byte
 }
 
-// should consitent with native/parser.c
+// should consistent with native/parser.c
 type nodeBuf struct {
 	ncur    uintptr
 	parent  int64
@@ -84,7 +84,7 @@ func (self *nodeBuf) init(nodes []node) {
 	self.parent = -1
 }
 
-// should consitent with native/parser.c
+// should consistent with native/parser.c
 type Parser struct {
 	Json    string
 	padded	[]byte

internal/decoder/optdec/node.go

@@ -372,7 +372,7 @@ func (val Node) ParseF64(ctx *Context) (float64, bool) {
 }
 
 func (val Node) ParseString(ctx *Context) (string, bool) {
-	// shoud not use AsStrRef
+	// should not use AsStrRef
 	s, ok := val.AsStr(ctx)
 	if !ok {
 		return "", false
@@ -391,7 +391,7 @@ func (val Node) ParseString(ctx *Context) (string, bool) {
 
 
 func (val Node) ParseNumber(ctx *Context) (json.Number, bool) {
-	// shoud not use AsStrRef
+	// should not use AsStrRef
 	s, ok := val.AsStr(ctx)
 	if !ok {
 		return json.Number(""), false

internal/encoder/alg/sort.go

@@ -46,7 +46,7 @@ func radixQsort(kvs []_MapPair, d, maxDepth int) {
         }
 
         // kvs[0:lt] < v = kvs[lt:gt] < kvs[gt:len(kvs)]
-        // Native implemention:
+        // Native implementation:
         //     radixQsort(kvs[:lt], d, maxDepth)
         //     if p > -1 {
         //         radixQsort(kvs[lt:gt], d+1, maxDepth)

internal/encoder/x86/assembler_regabi_amd64.go

@@ -673,7 +673,7 @@ func (self *Assembler) encode_string(doubleQuote bool) {
 	self.Sjmp("JMP", _LB_panic)
 	self.Link("_str_next_{n}")
 
-	/* openning quote, check for double quote */
+	/* opening quote, check for double quote */
 	if !doubleQuote {
 		self.check_size_r(_AX, 2) // SIZE $2
 		self.add_char('"')        // CHAR $'"'

internal/optcaching/fcache.go

@@ -84,7 +84,7 @@ func NewSmallFieldMap (hint int) *SmallFieldMap {
 
 func (self *SmallFieldMap) Set(fields []resolver.FieldMeta) {
 	if len(fields) > 8 {
-		panic("small field map shoud use in small struct")
+		panic("small field map should use in small struct")
 	}
 
 	for i, f := range fields {
@@ -254,7 +254,7 @@ type keysInfo struct {
 
 func (self *NormalFieldMap) Set(fields []resolver.FieldMeta) {
 	if len(fields) <=8 || len(fields) > 128 {
-		panic("normal field map shoud use in small struct")
+		panic("normal field map should use in small struct")
 	}
 
 	// allocate the flat map in []byte
@@ -278,7 +278,7 @@ func (self *NormalFieldMap) Set(fields []resolver.FieldMeta) {
 
 	}
 
-	// add a padding size at last to make it firendly for SIMD.
+	// add a padding size at last to make it friendly for SIMD.
 	self.keys = make([]byte, _HdrSize + 2 * kvLen, _HdrSize + 2 * kvLen + _PaddingSize)
 	self.lowOffset = _HdrSize + kvLen