123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122123124125126127128129130131132133134135136137138139140141142143144145146147148149150151152153154155156157158159160161162163164165166167168169170171172173174175176177178179180181182183184185186187188189190191192193194195196197198199200201202203204205206207208209210211212213214215216217218219220221222223224225226227228229230231232233234235236237238239240241242243244245246247248249250251252253254255256257258259260261262263264265266267268269270271272273274275276277278279280281282283284285286287288289290291292293294295296297298299300301302303304305306307308309310311312313314315316317318319320321322323324325326327328329330331332333334335336337338339340341342343344345346347348349350351352353354355356357358359360361362363364365366367368369370371372373374375376377378379380381382383384385386387388389390391392393394395396397398399400401402403404405406407408409410411412413414415416417418419420421422423424425426427428429430431432433434435436437438439440441442443444445446447448449450451452453454455456457458459460461462463464465466467468469470471472473474475476477478479480481482483484485486487488489490491492493494495496497 |
- // 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 yaml
- import (
- "bytes"
- "encoding"
- "encoding/json"
- "reflect"
- "sort"
- "strings"
- "sync"
- "unicode"
- "unicode/utf8"
- )
- // indirect walks down v allocating pointers as needed,
- // until it gets to a non-pointer.
- // if it encounters an Unmarshaler, indirect stops and returns that.
- // if decodingNull is true, indirect stops at the last pointer so it can be set to nil.
- func indirect(v reflect.Value, decodingNull bool) (json.Unmarshaler, encoding.TextUnmarshaler, reflect.Value) {
- // If v is a named type and is addressable,
- // start with its address, so that if the type has pointer methods,
- // we find them.
- if v.Kind() != reflect.Ptr && v.Type().Name() != "" && v.CanAddr() {
- v = v.Addr()
- }
- for {
- // Load value from interface, but only if the result will be
- // usefully addressable.
- if v.Kind() == reflect.Interface && !v.IsNil() {
- e := v.Elem()
- if e.Kind() == reflect.Ptr && !e.IsNil() && (!decodingNull || e.Elem().Kind() == reflect.Ptr) {
- v = e
- continue
- }
- }
- if v.Kind() != reflect.Ptr {
- break
- }
- if v.Elem().Kind() != reflect.Ptr && decodingNull && v.CanSet() {
- break
- }
- if v.IsNil() {
- v.Set(reflect.New(v.Type().Elem()))
- }
- if v.Type().NumMethod() > 0 {
- if u, ok := v.Interface().(json.Unmarshaler); ok {
- return u, nil, reflect.Value{}
- }
- if u, ok := v.Interface().(encoding.TextUnmarshaler); ok {
- return nil, u, reflect.Value{}
- }
- }
- v = v.Elem()
- }
- return nil, nil, v
- }
- // A field represents a single field found in a struct.
- type field struct {
- name string
- nameBytes []byte // []byte(name)
- equalFold func(s, t []byte) bool // bytes.EqualFold or equivalent
- tag bool
- index []int
- typ reflect.Type
- omitEmpty bool
- quoted bool
- }
- func fillField(f field) field {
- f.nameBytes = []byte(f.name)
- f.equalFold = foldFunc(f.nameBytes)
- return f
- }
- // byName sorts field by name, breaking ties with depth,
- // then breaking ties with "name came from json tag", then
- // breaking ties with index sequence.
- type byName []field
- func (x byName) Len() int { return len(x) }
- func (x byName) Swap(i, j int) { x[i], x[j] = x[j], x[i] }
- func (x byName) Less(i, j int) bool {
- if x[i].name != x[j].name {
- return x[i].name < x[j].name
- }
- if len(x[i].index) != len(x[j].index) {
- return len(x[i].index) < len(x[j].index)
- }
- if x[i].tag != x[j].tag {
- return x[i].tag
- }
- return byIndex(x).Less(i, j)
- }
- // byIndex sorts field by index sequence.
- type byIndex []field
- func (x byIndex) Len() int { return len(x) }
- func (x byIndex) Swap(i, j int) { x[i], x[j] = x[j], x[i] }
- func (x byIndex) Less(i, j int) bool {
- for k, xik := range x[i].index {
- if k >= len(x[j].index) {
- return false
- }
- if xik != x[j].index[k] {
- return xik < x[j].index[k]
- }
- }
- return len(x[i].index) < len(x[j].index)
- }
- // typeFields returns a list of fields that JSON should recognize for the given type.
- // The algorithm is breadth-first search over the set of structs to include - the top struct
- // and then any reachable anonymous structs.
- func typeFields(t reflect.Type) []field {
- // Anonymous fields to explore at the current level and the next.
- current := []field{}
- next := []field{{typ: t}}
- // Count of queued names for current level and the next.
- count := map[reflect.Type]int{}
- nextCount := map[reflect.Type]int{}
- // Types already visited at an earlier level.
- visited := map[reflect.Type]bool{}
- // Fields found.
- var fields []field
- for len(next) > 0 {
- current, next = next, current[:0]
- count, nextCount = nextCount, map[reflect.Type]int{}
- for _, f := range current {
- if visited[f.typ] {
- continue
- }
- visited[f.typ] = true
- // Scan f.typ for fields to include.
- for i := 0; i < f.typ.NumField(); i++ {
- sf := f.typ.Field(i)
- if sf.PkgPath != "" { // unexported
- continue
- }
- tag := sf.Tag.Get("json")
- if tag == "-" {
- continue
- }
- name, opts := parseTag(tag)
- if !isValidTag(name) {
- name = ""
- }
- index := make([]int, len(f.index)+1)
- copy(index, f.index)
- index[len(f.index)] = i
- ft := sf.Type
- if ft.Name() == "" && ft.Kind() == reflect.Ptr {
- // Follow pointer.
- ft = ft.Elem()
- }
- // Record found field and index sequence.
- if name != "" || !sf.Anonymous || ft.Kind() != reflect.Struct {
- tagged := name != ""
- if name == "" {
- name = sf.Name
- }
- fields = append(fields, fillField(field{
- name: name,
- tag: tagged,
- index: index,
- typ: ft,
- omitEmpty: opts.Contains("omitempty"),
- quoted: opts.Contains("string"),
- }))
- if count[f.typ] > 1 {
- // If there were multiple instances, add a second,
- // so that the annihilation code will see a duplicate.
- // It only cares about the distinction between 1 or 2,
- // so don't bother generating any more copies.
- fields = append(fields, fields[len(fields)-1])
- }
- continue
- }
- // Record new anonymous struct to explore in next round.
- nextCount[ft]++
- if nextCount[ft] == 1 {
- next = append(next, fillField(field{name: ft.Name(), index: index, typ: ft}))
- }
- }
- }
- }
- sort.Sort(byName(fields))
- // Delete all fields that are hidden by the Go rules for embedded fields,
- // except that fields with JSON tags are promoted.
- // The fields are sorted in primary order of name, secondary order
- // of field index length. Loop over names; for each name, delete
- // hidden fields by choosing the one dominant field that survives.
- out := fields[:0]
- for advance, i := 0, 0; i < len(fields); i += advance {
- // One iteration per name.
- // Find the sequence of fields with the name of this first field.
- fi := fields[i]
- name := fi.name
- for advance = 1; i+advance < len(fields); advance++ {
- fj := fields[i+advance]
- if fj.name != name {
- break
- }
- }
- if advance == 1 { // Only one field with this name
- out = append(out, fi)
- continue
- }
- dominant, ok := dominantField(fields[i : i+advance])
- if ok {
- out = append(out, dominant)
- }
- }
- fields = out
- sort.Sort(byIndex(fields))
- return fields
- }
- // dominantField looks through the fields, all of which are known to
- // have the same name, to find the single field that dominates the
- // others using Go's embedding rules, modified by the presence of
- // JSON tags. If there are multiple top-level fields, the boolean
- // will be false: This condition is an error in Go and we skip all
- // the fields.
- func dominantField(fields []field) (field, bool) {
- // The fields are sorted in increasing index-length order. The winner
- // must therefore be one with the shortest index length. Drop all
- // longer entries, which is easy: just truncate the slice.
- length := len(fields[0].index)
- tagged := -1 // Index of first tagged field.
- for i, f := range fields {
- if len(f.index) > length {
- fields = fields[:i]
- break
- }
- if f.tag {
- if tagged >= 0 {
- // Multiple tagged fields at the same level: conflict.
- // Return no field.
- return field{}, false
- }
- tagged = i
- }
- }
- if tagged >= 0 {
- return fields[tagged], true
- }
- // All remaining fields have the same length. If there's more than one,
- // we have a conflict (two fields named "X" at the same level) and we
- // return no field.
- if len(fields) > 1 {
- return field{}, false
- }
- return fields[0], true
- }
- var fieldCache struct {
- sync.RWMutex
- m map[reflect.Type][]field
- }
- // cachedTypeFields is like typeFields but uses a cache to avoid repeated work.
- func cachedTypeFields(t reflect.Type) []field {
- fieldCache.RLock()
- f := fieldCache.m[t]
- fieldCache.RUnlock()
- if f != nil {
- return f
- }
- // Compute fields without lock.
- // Might duplicate effort but won't hold other computations back.
- f = typeFields(t)
- if f == nil {
- f = []field{}
- }
- fieldCache.Lock()
- if fieldCache.m == nil {
- fieldCache.m = map[reflect.Type][]field{}
- }
- fieldCache.m[t] = f
- fieldCache.Unlock()
- return f
- }
- func isValidTag(s string) bool {
- if s == "" {
- return false
- }
- for _, c := range s {
- switch {
- case strings.ContainsRune("!#$%&()*+-./:<=>?@[]^_{|}~ ", c):
- // Backslash and quote chars are reserved, but
- // otherwise any punctuation chars are allowed
- // in a tag name.
- default:
- if !unicode.IsLetter(c) && !unicode.IsDigit(c) {
- return false
- }
- }
- }
- return true
- }
- const (
- caseMask = ^byte(0x20) // Mask to ignore case in ASCII.
- kelvin = '\u212a'
- smallLongEss = '\u017f'
- )
- // foldFunc returns one of four different case folding equivalence
- // functions, from most general (and slow) to fastest:
- //
- // 1) bytes.EqualFold, if the key s contains any non-ASCII UTF-8
- // 2) equalFoldRight, if s contains special folding ASCII ('k', 'K', 's', 'S')
- // 3) asciiEqualFold, no special, but includes non-letters (including _)
- // 4) simpleLetterEqualFold, no specials, no non-letters.
- //
- // The letters S and K are special because they map to 3 runes, not just 2:
- // * S maps to s and to U+017F 'ſ' Latin small letter long s
- // * k maps to K and to U+212A 'K' Kelvin sign
- // See http://play.golang.org/p/tTxjOc0OGo
- //
- // The returned function is specialized for matching against s and
- // should only be given s. It's not curried for performance reasons.
- func foldFunc(s []byte) func(s, t []byte) bool {
- nonLetter := false
- special := false // special letter
- for _, b := range s {
- if b >= utf8.RuneSelf {
- return bytes.EqualFold
- }
- upper := b & caseMask
- if upper < 'A' || upper > 'Z' {
- nonLetter = true
- } else if upper == 'K' || upper == 'S' {
- // See above for why these letters are special.
- special = true
- }
- }
- if special {
- return equalFoldRight
- }
- if nonLetter {
- return asciiEqualFold
- }
- return simpleLetterEqualFold
- }
- // equalFoldRight is a specialization of bytes.EqualFold when s is
- // known to be all ASCII (including punctuation), but contains an 's',
- // 'S', 'k', or 'K', requiring a Unicode fold on the bytes in t.
- // See comments on foldFunc.
- func equalFoldRight(s, t []byte) bool {
- for _, sb := range s {
- if len(t) == 0 {
- return false
- }
- tb := t[0]
- if tb < utf8.RuneSelf {
- if sb != tb {
- sbUpper := sb & caseMask
- if 'A' <= sbUpper && sbUpper <= 'Z' {
- if sbUpper != tb&caseMask {
- return false
- }
- } else {
- return false
- }
- }
- t = t[1:]
- continue
- }
- // sb is ASCII and t is not. t must be either kelvin
- // sign or long s; sb must be s, S, k, or K.
- tr, size := utf8.DecodeRune(t)
- switch sb {
- case 's', 'S':
- if tr != smallLongEss {
- return false
- }
- case 'k', 'K':
- if tr != kelvin {
- return false
- }
- default:
- return false
- }
- t = t[size:]
- }
- if len(t) > 0 {
- return false
- }
- return true
- }
- // asciiEqualFold is a specialization of bytes.EqualFold for use when
- // s is all ASCII (but may contain non-letters) and contains no
- // special-folding letters.
- // See comments on foldFunc.
- func asciiEqualFold(s, t []byte) bool {
- if len(s) != len(t) {
- return false
- }
- for i, sb := range s {
- tb := t[i]
- if sb == tb {
- continue
- }
- if ('a' <= sb && sb <= 'z') || ('A' <= sb && sb <= 'Z') {
- if sb&caseMask != tb&caseMask {
- return false
- }
- } else {
- return false
- }
- }
- return true
- }
- // simpleLetterEqualFold is a specialization of bytes.EqualFold for
- // use when s is all ASCII letters (no underscores, etc) and also
- // doesn't contain 'k', 'K', 's', or 'S'.
- // See comments on foldFunc.
- func simpleLetterEqualFold(s, t []byte) bool {
- if len(s) != len(t) {
- return false
- }
- for i, b := range s {
- if b&caseMask != t[i]&caseMask {
- return false
- }
- }
- return true
- }
- // 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) {
- if idx := strings.Index(tag, ","); idx != -1 {
- return tag[:idx], tagOptions(tag[idx+1:])
- }
- return tag, tagOptions("")
- }
- // 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 next string
- i := strings.Index(s, ",")
- if i >= 0 {
- s, next = s[:i], s[i+1:]
- }
- if s == optionName {
- return true
- }
- s = next
- }
- return false
- }
|