1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177
|
package token
import (
"errors"
"fmt"
"strconv"
"strings"
"time"
)
// Character type for character
type Character byte
const (
// SequenceEntryCharacter character for sequence entry
SequenceEntryCharacter Character = '-'
// MappingKeyCharacter character for mapping key
MappingKeyCharacter Character = '?'
// MappingValueCharacter character for mapping value
MappingValueCharacter Character = ':'
// CollectEntryCharacter character for collect entry
CollectEntryCharacter Character = ','
// SequenceStartCharacter character for sequence start
SequenceStartCharacter Character = '['
// SequenceEndCharacter character for sequence end
SequenceEndCharacter Character = ']'
// MappingStartCharacter character for mapping start
MappingStartCharacter Character = '{'
// MappingEndCharacter character for mapping end
MappingEndCharacter Character = '}'
// CommentCharacter character for comment
CommentCharacter Character = '#'
// AnchorCharacter character for anchor
AnchorCharacter Character = '&'
// AliasCharacter character for alias
AliasCharacter Character = '*'
// TagCharacter character for tag
TagCharacter Character = '!'
// LiteralCharacter character for literal
LiteralCharacter Character = '|'
// FoldedCharacter character for folded
FoldedCharacter Character = '>'
// SingleQuoteCharacter character for single quote
SingleQuoteCharacter Character = '\''
// DoubleQuoteCharacter character for double quote
DoubleQuoteCharacter Character = '"'
// DirectiveCharacter character for directive
DirectiveCharacter Character = '%'
// SpaceCharacter character for space
SpaceCharacter Character = ' '
// LineBreakCharacter character for line break
LineBreakCharacter Character = '\n'
)
// Type type identifier for token
type Type int
const (
// UnknownType reserve for invalid type
UnknownType Type = iota
// DocumentHeaderType type for DocumentHeader token
DocumentHeaderType
// DocumentEndType type for DocumentEnd token
DocumentEndType
// SequenceEntryType type for SequenceEntry token
SequenceEntryType
// MappingKeyType type for MappingKey token
MappingKeyType
// MappingValueType type for MappingValue token
MappingValueType
// MergeKeyType type for MergeKey token
MergeKeyType
// CollectEntryType type for CollectEntry token
CollectEntryType
// SequenceStartType type for SequenceStart token
SequenceStartType
// SequenceEndType type for SequenceEnd token
SequenceEndType
// MappingStartType type for MappingStart token
MappingStartType
// MappingEndType type for MappingEnd token
MappingEndType
// CommentType type for Comment token
CommentType
// AnchorType type for Anchor token
AnchorType
// AliasType type for Alias token
AliasType
// TagType type for Tag token
TagType
// LiteralType type for Literal token
LiteralType
// FoldedType type for Folded token
FoldedType
// SingleQuoteType type for SingleQuote token
SingleQuoteType
// DoubleQuoteType type for DoubleQuote token
DoubleQuoteType
// DirectiveType type for Directive token
DirectiveType
// SpaceType type for Space token
SpaceType
// NullType type for Null token
NullType
// ImplicitNullType type for implicit Null token.
// This is used when explicit keywords such as null or ~ are not specified.
// It is distinguished during encoding and output as an empty string.
ImplicitNullType
// InfinityType type for Infinity token
InfinityType
// NanType type for Nan token
NanType
// IntegerType type for Integer token
IntegerType
// BinaryIntegerType type for BinaryInteger token
BinaryIntegerType
// OctetIntegerType type for OctetInteger token
OctetIntegerType
// HexIntegerType type for HexInteger token
HexIntegerType
// FloatType type for Float token
FloatType
// StringType type for String token
StringType
// BoolType type for Bool token
BoolType
// InvalidType type for invalid token
InvalidType
)
// String type identifier to text
func (t Type) String() string {
switch t {
case UnknownType:
return "Unknown"
case DocumentHeaderType:
return "DocumentHeader"
case DocumentEndType:
return "DocumentEnd"
case SequenceEntryType:
return "SequenceEntry"
case MappingKeyType:
return "MappingKey"
case MappingValueType:
return "MappingValue"
case MergeKeyType:
return "MergeKey"
case CollectEntryType:
return "CollectEntry"
case SequenceStartType:
return "SequenceStart"
case SequenceEndType:
return "SequenceEnd"
case MappingStartType:
return "MappingStart"
case MappingEndType:
return "MappingEnd"
case CommentType:
return "Comment"
case AnchorType:
return "Anchor"
case AliasType:
return "Alias"
case TagType:
return "Tag"
case LiteralType:
return "Literal"
case FoldedType:
return "Folded"
case SingleQuoteType:
return "SingleQuote"
case DoubleQuoteType:
return "DoubleQuote"
case DirectiveType:
return "Directive"
case SpaceType:
return "Space"
case StringType:
return "String"
case BoolType:
return "Bool"
case IntegerType:
return "Integer"
case BinaryIntegerType:
return "BinaryInteger"
case OctetIntegerType:
return "OctetInteger"
case HexIntegerType:
return "HexInteger"
case FloatType:
return "Float"
case NullType:
return "Null"
case ImplicitNullType:
return "ImplicitNull"
case InfinityType:
return "Infinity"
case NanType:
return "Nan"
case InvalidType:
return "Invalid"
}
return ""
}
// CharacterType type for character category
type CharacterType int
const (
// CharacterTypeIndicator type of indicator character
CharacterTypeIndicator CharacterType = iota
// CharacterTypeWhiteSpace type of white space character
CharacterTypeWhiteSpace
// CharacterTypeMiscellaneous type of miscellaneous character
CharacterTypeMiscellaneous
// CharacterTypeEscaped type of escaped character
CharacterTypeEscaped
// CharacterTypeInvalid type for a invalid token.
CharacterTypeInvalid
)
// String character type identifier to text
func (c CharacterType) String() string {
switch c {
case CharacterTypeIndicator:
return "Indicator"
case CharacterTypeWhiteSpace:
return "WhiteSpace"
case CharacterTypeMiscellaneous:
return "Miscellaneous"
case CharacterTypeEscaped:
return "Escaped"
}
return ""
}
// Indicator type for indicator
type Indicator int
const (
// NotIndicator not indicator
NotIndicator Indicator = iota
// BlockStructureIndicator indicator for block structure ( '-', '?', ':' )
BlockStructureIndicator
// FlowCollectionIndicator indicator for flow collection ( '[', ']', '{', '}', ',' )
FlowCollectionIndicator
// CommentIndicator indicator for comment ( '#' )
CommentIndicator
// NodePropertyIndicator indicator for node property ( '!', '&', '*' )
NodePropertyIndicator
// BlockScalarIndicator indicator for block scalar ( '|', '>' )
BlockScalarIndicator
// QuotedScalarIndicator indicator for quoted scalar ( ''', '"' )
QuotedScalarIndicator
// DirectiveIndicator indicator for directive ( '%' )
DirectiveIndicator
// InvalidUseOfReservedIndicator indicator for invalid use of reserved keyword ( '@', '`' )
InvalidUseOfReservedIndicator
)
// String indicator to text
func (i Indicator) String() string {
switch i {
case NotIndicator:
return "NotIndicator"
case BlockStructureIndicator:
return "BlockStructure"
case FlowCollectionIndicator:
return "FlowCollection"
case CommentIndicator:
return "Comment"
case NodePropertyIndicator:
return "NodeProperty"
case BlockScalarIndicator:
return "BlockScalar"
case QuotedScalarIndicator:
return "QuotedScalar"
case DirectiveIndicator:
return "Directive"
case InvalidUseOfReservedIndicator:
return "InvalidUseOfReserved"
}
return ""
}
var (
reservedNullKeywords = []string{
"null",
"Null",
"NULL",
"~",
}
reservedBoolKeywords = []string{
"true",
"True",
"TRUE",
"false",
"False",
"FALSE",
}
// For compatibility with other YAML 1.1 parsers
// Note that we use these solely for encoding the bool value with quotes.
// go-yaml should not treat these as reserved keywords at parsing time.
// as go-yaml is supposed to be compliant only with YAML 1.2.
reservedLegacyBoolKeywords = []string{
"y",
"Y",
"yes",
"Yes",
"YES",
"n",
"N",
"no",
"No",
"NO",
"on",
"On",
"ON",
"off",
"Off",
"OFF",
}
reservedInfKeywords = []string{
".inf",
".Inf",
".INF",
"-.inf",
"-.Inf",
"-.INF",
}
reservedNanKeywords = []string{
".nan",
".NaN",
".NAN",
}
reservedKeywordMap = map[string]func(string, string, *Position) *Token{}
// reservedEncKeywordMap contains is the keyword map used at encoding time.
// This is supposed to be a superset of reservedKeywordMap,
// and used to quote legacy keywords present in YAML 1.1 or lesser for compatibility reasons,
// even though this library is supposed to be YAML 1.2-compliant.
reservedEncKeywordMap = map[string]func(string, string, *Position) *Token{}
)
func reservedKeywordToken(typ Type, value, org string, pos *Position) *Token {
return &Token{
Type: typ,
CharacterType: CharacterTypeMiscellaneous,
Indicator: NotIndicator,
Value: value,
Origin: org,
Position: pos,
}
}
func init() {
for _, keyword := range reservedNullKeywords {
f := func(value, org string, pos *Position) *Token {
return reservedKeywordToken(NullType, value, org, pos)
}
reservedKeywordMap[keyword] = f
reservedEncKeywordMap[keyword] = f
}
for _, keyword := range reservedBoolKeywords {
f := func(value, org string, pos *Position) *Token {
return reservedKeywordToken(BoolType, value, org, pos)
}
reservedKeywordMap[keyword] = f
reservedEncKeywordMap[keyword] = f
}
for _, keyword := range reservedLegacyBoolKeywords {
reservedEncKeywordMap[keyword] = func(value, org string, pos *Position) *Token {
return reservedKeywordToken(BoolType, value, org, pos)
}
}
for _, keyword := range reservedInfKeywords {
reservedKeywordMap[keyword] = func(value, org string, pos *Position) *Token {
return reservedKeywordToken(InfinityType, value, org, pos)
}
}
for _, keyword := range reservedNanKeywords {
reservedKeywordMap[keyword] = func(value, org string, pos *Position) *Token {
return reservedKeywordToken(NanType, value, org, pos)
}
}
}
// ReservedTagKeyword type of reserved tag keyword
type ReservedTagKeyword string
const (
// IntegerTag `!!int` tag
IntegerTag ReservedTagKeyword = "!!int"
// FloatTag `!!float` tag
FloatTag ReservedTagKeyword = "!!float"
// NullTag `!!null` tag
NullTag ReservedTagKeyword = "!!null"
// SequenceTag `!!seq` tag
SequenceTag ReservedTagKeyword = "!!seq"
// MappingTag `!!map` tag
MappingTag ReservedTagKeyword = "!!map"
// StringTag `!!str` tag
StringTag ReservedTagKeyword = "!!str"
// BinaryTag `!!binary` tag
BinaryTag ReservedTagKeyword = "!!binary"
// OrderedMapTag `!!omap` tag
OrderedMapTag ReservedTagKeyword = "!!omap"
// SetTag `!!set` tag
SetTag ReservedTagKeyword = "!!set"
// TimestampTag `!!timestamp` tag
TimestampTag ReservedTagKeyword = "!!timestamp"
// BooleanTag `!!bool` tag
BooleanTag ReservedTagKeyword = "!!bool"
// MergeTag `!!merge` tag
MergeTag ReservedTagKeyword = "!!merge"
)
var (
// ReservedTagKeywordMap map for reserved tag keywords
ReservedTagKeywordMap = map[ReservedTagKeyword]func(string, string, *Position) *Token{
IntegerTag: func(value, org string, pos *Position) *Token {
return &Token{
Type: TagType,
CharacterType: CharacterTypeIndicator,
Indicator: NodePropertyIndicator,
Value: value,
Origin: org,
Position: pos,
}
},
FloatTag: func(value, org string, pos *Position) *Token {
return &Token{
Type: TagType,
CharacterType: CharacterTypeIndicator,
Indicator: NodePropertyIndicator,
Value: value,
Origin: org,
Position: pos,
}
},
NullTag: func(value, org string, pos *Position) *Token {
return &Token{
Type: TagType,
CharacterType: CharacterTypeIndicator,
Indicator: NodePropertyIndicator,
Value: value,
Origin: org,
Position: pos,
}
},
SequenceTag: func(value, org string, pos *Position) *Token {
return &Token{
Type: TagType,
CharacterType: CharacterTypeIndicator,
Indicator: NodePropertyIndicator,
Value: value,
Origin: org,
Position: pos,
}
},
MappingTag: func(value, org string, pos *Position) *Token {
return &Token{
Type: TagType,
CharacterType: CharacterTypeIndicator,
Indicator: NodePropertyIndicator,
Value: value,
Origin: org,
Position: pos,
}
},
StringTag: func(value, org string, pos *Position) *Token {
return &Token{
Type: TagType,
CharacterType: CharacterTypeIndicator,
Indicator: NodePropertyIndicator,
Value: value,
Origin: org,
Position: pos,
}
},
BinaryTag: func(value, org string, pos *Position) *Token {
return &Token{
Type: TagType,
CharacterType: CharacterTypeIndicator,
Indicator: NodePropertyIndicator,
Value: value,
Origin: org,
Position: pos,
}
},
OrderedMapTag: func(value, org string, pos *Position) *Token {
return &Token{
Type: TagType,
CharacterType: CharacterTypeIndicator,
Indicator: NodePropertyIndicator,
Value: value,
Origin: org,
Position: pos,
}
},
SetTag: func(value, org string, pos *Position) *Token {
return &Token{
Type: TagType,
CharacterType: CharacterTypeIndicator,
Indicator: NodePropertyIndicator,
Value: value,
Origin: org,
Position: pos,
}
},
TimestampTag: func(value, org string, pos *Position) *Token {
return &Token{
Type: TagType,
CharacterType: CharacterTypeIndicator,
Indicator: NodePropertyIndicator,
Value: value,
Origin: org,
Position: pos,
}
},
BooleanTag: func(value, org string, pos *Position) *Token {
return &Token{
Type: TagType,
CharacterType: CharacterTypeIndicator,
Indicator: NodePropertyIndicator,
Value: value,
Origin: org,
Position: pos,
}
},
MergeTag: func(value, org string, pos *Position) *Token {
return &Token{
Type: TagType,
CharacterType: CharacterTypeIndicator,
Indicator: NodePropertyIndicator,
Value: value,
Origin: org,
Position: pos,
}
},
}
)
type NumberType string
const (
NumberTypeDecimal NumberType = "decimal"
NumberTypeBinary NumberType = "binary"
NumberTypeOctet NumberType = "octet"
NumberTypeHex NumberType = "hex"
NumberTypeFloat NumberType = "float"
)
type NumberValue struct {
Type NumberType
Value any
Text string
}
func ToNumber(value string) *NumberValue {
num, err := toNumber(value)
if err != nil {
return nil
}
return num
}
func isNumber(value string) bool {
num, err := toNumber(value)
if err != nil {
var numErr *strconv.NumError
if errors.As(err, &numErr) && errors.Is(numErr.Err, strconv.ErrRange) {
return true
}
return false
}
return num != nil
}
func toNumber(value string) (*NumberValue, error) {
if len(value) == 0 {
return nil, nil
}
if strings.HasPrefix(value, "_") {
return nil, nil
}
dotCount := strings.Count(value, ".")
if dotCount > 1 {
return nil, nil
}
isNegative := strings.HasPrefix(value, "-")
normalized := strings.ReplaceAll(strings.TrimPrefix(strings.TrimPrefix(value, "+"), "-"), "_", "")
var (
typ NumberType
base int
)
switch {
case strings.HasPrefix(normalized, "0x"):
normalized = strings.TrimPrefix(normalized, "0x")
base = 16
typ = NumberTypeHex
case strings.HasPrefix(normalized, "0o"):
normalized = strings.TrimPrefix(normalized, "0o")
base = 8
typ = NumberTypeOctet
case strings.HasPrefix(normalized, "0b"):
normalized = strings.TrimPrefix(normalized, "0b")
base = 2
typ = NumberTypeBinary
case strings.HasPrefix(normalized, "0") && len(normalized) > 1 && dotCount == 0:
base = 8
typ = NumberTypeOctet
case dotCount == 1:
typ = NumberTypeFloat
default:
typ = NumberTypeDecimal
base = 10
}
text := normalized
if isNegative {
text = "-" + text
}
var v any
if typ == NumberTypeFloat {
f, err := strconv.ParseFloat(text, 64)
if err != nil {
return nil, err
}
v = f
} else if isNegative {
i, err := strconv.ParseInt(text, base, 64)
if err != nil {
return nil, err
}
v = i
} else {
u, err := strconv.ParseUint(text, base, 64)
if err != nil {
return nil, err
}
v = u
}
return &NumberValue{
Type: typ,
Value: v,
Text: text,
}, nil
}
// This is a subset of the formats permitted by the regular expression
// defined at http://yaml.org/type/timestamp.html. Note that time.Parse
// cannot handle: "2001-12-14 21:59:43.10 -5" from the examples.
var timestampFormats = []string{
time.RFC3339Nano,
"2006-01-02t15:04:05.999999999Z07:00", // RFC3339Nano with lower-case "t".
time.DateTime,
time.DateOnly,
// Not in examples, but to preserve backward compatibility by quoting time values.
"15:4",
}
func isTimestamp(value string) bool {
for _, format := range timestampFormats {
if _, err := time.Parse(format, value); err == nil {
return true
}
}
return false
}
// IsNeedQuoted checks whether the value needs quote for passed string or not
func IsNeedQuoted(value string) bool {
if value == "" {
return true
}
if _, exists := reservedEncKeywordMap[value]; exists {
return true
}
if isNumber(value) {
return true
}
if value == "-" {
return true
}
first := value[0]
switch first {
case '*', '&', '[', '{', '}', ']', ',', '!', '|', '>', '%', '\'', '"', '@', ' ', '`':
return true
}
last := value[len(value)-1]
switch last {
case ':', ' ':
return true
}
if isTimestamp(value) {
return true
}
for i, c := range value {
switch c {
case '#', '\\':
return true
case ':', '-':
if i+1 < len(value) && value[i+1] == ' ' {
return true
}
}
}
return false
}
// LiteralBlockHeader detect literal block scalar header
func LiteralBlockHeader(value string) string {
lbc := DetectLineBreakCharacter(value)
switch {
case !strings.Contains(value, lbc):
return ""
case strings.HasSuffix(value, fmt.Sprintf("%s%s", lbc, lbc)):
return "|+"
case strings.HasSuffix(value, lbc):
return "|"
default:
return "|-"
}
}
// New create reserved keyword token or number token and other string token.
func New(value string, org string, pos *Position) *Token {
fn := reservedKeywordMap[value]
if fn != nil {
return fn(value, org, pos)
}
if num := ToNumber(value); num != nil {
tk := &Token{
Type: IntegerType,
CharacterType: CharacterTypeMiscellaneous,
Indicator: NotIndicator,
Value: value,
Origin: org,
Position: pos,
}
switch num.Type {
case NumberTypeFloat:
tk.Type = FloatType
case NumberTypeBinary:
tk.Type = BinaryIntegerType
case NumberTypeOctet:
tk.Type = OctetIntegerType
case NumberTypeHex:
tk.Type = HexIntegerType
}
return tk
}
return String(value, org, pos)
}
// Position type for position in YAML document
type Position struct {
Line int
Column int
Offset int
IndentNum int
IndentLevel int
}
// String position to text
func (p *Position) String() string {
return fmt.Sprintf("[level:%d,line:%d,column:%d,offset:%d]", p.IndentLevel, p.Line, p.Column, p.Offset)
}
// Token type for token
type Token struct {
// Type is a token type.
Type Type
// CharacterType is a character type.
CharacterType CharacterType
// Indicator is a indicator type.
Indicator Indicator
// Value is a string extracted with only meaningful characters, with spaces and such removed.
Value string
// Origin is a string that stores the original text as-is.
Origin string
// Error keeps error message for InvalidToken.
Error string
// Position is a token position.
Position *Position
// Next is a next token reference.
Next *Token
// Prev is a previous token reference.
Prev *Token
}
// PreviousType previous token type
func (t *Token) PreviousType() Type {
if t.Prev != nil {
return t.Prev.Type
}
return UnknownType
}
// NextType next token type
func (t *Token) NextType() Type {
if t.Next != nil {
return t.Next.Type
}
return UnknownType
}
// AddColumn append column number to current position of column
func (t *Token) AddColumn(col int) {
if t == nil {
return
}
t.Position.Column += col
}
// Clone copy token ( preserve Prev/Next reference )
func (t *Token) Clone() *Token {
if t == nil {
return nil
}
copied := *t
if t.Position != nil {
pos := *(t.Position)
copied.Position = &pos
}
return &copied
}
// Dump outputs token information to stdout for debugging.
func (t *Token) Dump() {
fmt.Printf(
"[TYPE]:%q [CHARTYPE]:%q [INDICATOR]:%q [VALUE]:%q [ORG]:%q [POS(line:column:level:offset)]: %d:%d:%d:%d\n",
t.Type, t.CharacterType, t.Indicator, t.Value, t.Origin, t.Position.Line, t.Position.Column, t.Position.IndentLevel, t.Position.Offset,
)
}
// Tokens type of token collection
type Tokens []*Token
func (t Tokens) InvalidToken() *Token {
for _, tt := range t {
if tt.Type == InvalidType {
return tt
}
}
return nil
}
func (t *Tokens) add(tk *Token) {
tokens := *t
if len(tokens) == 0 {
tokens = append(tokens, tk)
} else {
last := tokens[len(tokens)-1]
last.Next = tk
tk.Prev = last
tokens = append(tokens, tk)
}
*t = tokens
}
// Add append new some tokens
func (t *Tokens) Add(tks ...*Token) {
for _, tk := range tks {
t.add(tk)
}
}
// Dump dump all token structures for debugging
func (t Tokens) Dump() {
for _, tk := range t {
fmt.Print("- ")
tk.Dump()
}
}
// String create token for String
func String(value string, org string, pos *Position) *Token {
return &Token{
Type: StringType,
CharacterType: CharacterTypeMiscellaneous,
Indicator: NotIndicator,
Value: value,
Origin: org,
Position: pos,
}
}
// SequenceEntry create token for SequenceEntry
func SequenceEntry(org string, pos *Position) *Token {
return &Token{
Type: SequenceEntryType,
CharacterType: CharacterTypeIndicator,
Indicator: BlockStructureIndicator,
Value: string(SequenceEntryCharacter),
Origin: org,
Position: pos,
}
}
// MappingKey create token for MappingKey
func MappingKey(pos *Position) *Token {
return &Token{
Type: MappingKeyType,
CharacterType: CharacterTypeIndicator,
Indicator: BlockStructureIndicator,
Value: string(MappingKeyCharacter),
Origin: string(MappingKeyCharacter),
Position: pos,
}
}
// MappingValue create token for MappingValue
func MappingValue(pos *Position) *Token {
return &Token{
Type: MappingValueType,
CharacterType: CharacterTypeIndicator,
Indicator: BlockStructureIndicator,
Value: string(MappingValueCharacter),
Origin: string(MappingValueCharacter),
Position: pos,
}
}
// CollectEntry create token for CollectEntry
func CollectEntry(org string, pos *Position) *Token {
return &Token{
Type: CollectEntryType,
CharacterType: CharacterTypeIndicator,
Indicator: FlowCollectionIndicator,
Value: string(CollectEntryCharacter),
Origin: org,
Position: pos,
}
}
// SequenceStart create token for SequenceStart
func SequenceStart(org string, pos *Position) *Token {
return &Token{
Type: SequenceStartType,
CharacterType: CharacterTypeIndicator,
Indicator: FlowCollectionIndicator,
Value: string(SequenceStartCharacter),
Origin: org,
Position: pos,
}
}
// SequenceEnd create token for SequenceEnd
func SequenceEnd(org string, pos *Position) *Token {
return &Token{
Type: SequenceEndType,
CharacterType: CharacterTypeIndicator,
Indicator: FlowCollectionIndicator,
Value: string(SequenceEndCharacter),
Origin: org,
Position: pos,
}
}
// MappingStart create token for MappingStart
func MappingStart(org string, pos *Position) *Token {
return &Token{
Type: MappingStartType,
CharacterType: CharacterTypeIndicator,
Indicator: FlowCollectionIndicator,
Value: string(MappingStartCharacter),
Origin: org,
Position: pos,
}
}
// MappingEnd create token for MappingEnd
func MappingEnd(org string, pos *Position) *Token {
return &Token{
Type: MappingEndType,
CharacterType: CharacterTypeIndicator,
Indicator: FlowCollectionIndicator,
Value: string(MappingEndCharacter),
Origin: org,
Position: pos,
}
}
// Comment create token for Comment
func Comment(value string, org string, pos *Position) *Token {
return &Token{
Type: CommentType,
CharacterType: CharacterTypeIndicator,
Indicator: CommentIndicator,
Value: value,
Origin: org,
Position: pos,
}
}
// Anchor create token for Anchor
func Anchor(org string, pos *Position) *Token {
return &Token{
Type: AnchorType,
CharacterType: CharacterTypeIndicator,
Indicator: NodePropertyIndicator,
Value: string(AnchorCharacter),
Origin: org,
Position: pos,
}
}
// Alias create token for Alias
func Alias(org string, pos *Position) *Token {
return &Token{
Type: AliasType,
CharacterType: CharacterTypeIndicator,
Indicator: NodePropertyIndicator,
Value: string(AliasCharacter),
Origin: org,
Position: pos,
}
}
// Tag create token for Tag
func Tag(value string, org string, pos *Position) *Token {
fn := ReservedTagKeywordMap[ReservedTagKeyword(value)]
if fn != nil {
return fn(value, org, pos)
}
return &Token{
Type: TagType,
CharacterType: CharacterTypeIndicator,
Indicator: NodePropertyIndicator,
Value: value,
Origin: org,
Position: pos,
}
}
// Literal create token for Literal
func Literal(value string, org string, pos *Position) *Token {
return &Token{
Type: LiteralType,
CharacterType: CharacterTypeIndicator,
Indicator: BlockScalarIndicator,
Value: value,
Origin: org,
Position: pos,
}
}
// Folded create token for Folded
func Folded(value string, org string, pos *Position) *Token {
return &Token{
Type: FoldedType,
CharacterType: CharacterTypeIndicator,
Indicator: BlockScalarIndicator,
Value: value,
Origin: org,
Position: pos,
}
}
// SingleQuote create token for SingleQuote
func SingleQuote(value string, org string, pos *Position) *Token {
return &Token{
Type: SingleQuoteType,
CharacterType: CharacterTypeIndicator,
Indicator: QuotedScalarIndicator,
Value: value,
Origin: org,
Position: pos,
}
}
// DoubleQuote create token for DoubleQuote
func DoubleQuote(value string, org string, pos *Position) *Token {
return &Token{
Type: DoubleQuoteType,
CharacterType: CharacterTypeIndicator,
Indicator: QuotedScalarIndicator,
Value: value,
Origin: org,
Position: pos,
}
}
// Directive create token for Directive
func Directive(org string, pos *Position) *Token {
return &Token{
Type: DirectiveType,
CharacterType: CharacterTypeIndicator,
Indicator: DirectiveIndicator,
Value: string(DirectiveCharacter),
Origin: org,
Position: pos,
}
}
// Space create token for Space
func Space(pos *Position) *Token {
return &Token{
Type: SpaceType,
CharacterType: CharacterTypeWhiteSpace,
Indicator: NotIndicator,
Value: string(SpaceCharacter),
Origin: string(SpaceCharacter),
Position: pos,
}
}
// MergeKey create token for MergeKey
func MergeKey(org string, pos *Position) *Token {
return &Token{
Type: MergeKeyType,
CharacterType: CharacterTypeMiscellaneous,
Indicator: NotIndicator,
Value: "<<",
Origin: org,
Position: pos,
}
}
// DocumentHeader create token for DocumentHeader
func DocumentHeader(org string, pos *Position) *Token {
return &Token{
Type: DocumentHeaderType,
CharacterType: CharacterTypeMiscellaneous,
Indicator: NotIndicator,
Value: "---",
Origin: org,
Position: pos,
}
}
// DocumentEnd create token for DocumentEnd
func DocumentEnd(org string, pos *Position) *Token {
return &Token{
Type: DocumentEndType,
CharacterType: CharacterTypeMiscellaneous,
Indicator: NotIndicator,
Value: "...",
Origin: org,
Position: pos,
}
}
func Invalid(err string, org string, pos *Position) *Token {
return &Token{
Type: InvalidType,
CharacterType: CharacterTypeInvalid,
Indicator: NotIndicator,
Value: org,
Origin: org,
Error: err,
Position: pos,
}
}
// DetectLineBreakCharacter detect line break character in only one inside scalar content scope.
func DetectLineBreakCharacter(src string) string {
nc := strings.Count(src, "\n")
rc := strings.Count(src, "\r")
rnc := strings.Count(src, "\r\n")
switch {
case nc == rnc && rc == rnc:
return "\r\n"
case rc > nc:
return "\r"
default:
return "\n"
}
}
|