Migrate go yaml

go.mod

@@ -28,13 +28,15 @@ require (
 	github.com/docker/go-connections v0.5.0 // indirect
 	github.com/docker/go-units v0.5.0 // indirect
 	github.com/emicklei/go-restful/v3 v3.12.0 // indirect
+	github.com/fatih/color v1.17.0 // indirect
 	github.com/felixge/httpsnoop v1.0.4 // indirect
 	github.com/fxamacker/cbor/v2 v2.6.0 // indirect
 	github.com/go-logr/logr v1.4.2 // indirect
 	github.com/go-logr/stdr v1.2.2 // indirect
 	github.com/go-openapi/jsonpointer v0.21.0 // indirect
 	github.com/go-openapi/jsonreference v0.21.0 // indirect
 	github.com/go-openapi/swag v0.23.0 // indirect
+	github.com/goccy/go-yaml v1.11.3 // indirect
 	github.com/gogo/protobuf v1.3.2 // indirect
 	github.com/golang/protobuf v1.5.4 // indirect
 	github.com/google/gnostic-models v0.6.8 // indirect
@@ -45,6 +47,8 @@ require (
 	github.com/josharian/intern v1.0.0 // indirect
 	github.com/json-iterator/go v1.1.12 // indirect
 	github.com/mailru/easyjson v0.7.7 // indirect
+	github.com/mattn/go-colorable v0.1.13 // indirect
+	github.com/mattn/go-isatty v0.0.20 // indirect
 	github.com/moby/docker-image-spec v1.3.1 // indirect
 	github.com/moby/spdystream v0.2.0 // indirect
 	github.com/modern-go/concurrent v0.0.0-20180306012644-bacd9c7ef1dd // indirect
@@ -66,10 +70,11 @@ require (
 	go.opentelemetry.io/proto/otlp v1.2.0 // indirect
 	golang.org/x/net v0.26.0 // indirect
 	golang.org/x/oauth2 v0.20.0 // indirect
-	golang.org/x/sys v0.21.0 // indirect
+	golang.org/x/sys v0.22.0 // indirect
 	golang.org/x/term v0.21.0 // indirect
 	golang.org/x/text v0.16.0 // indirect
 	golang.org/x/time v0.5.0 // indirect
+	golang.org/x/xerrors v0.0.0-20231012003039-104605ab7028 // indirect
 	google.golang.org/grpc v1.64.0 // indirect
 	google.golang.org/protobuf v1.34.1 // indirect
 	gopkg.in/inf.v0 v0.9.1 // indirect

go.sum

@@ -23,6 +23,8 @@ github.com/emicklei/go-restful/v3 v3.12.0 h1:y2DdzBAURM29NFF94q6RaY4vjIH1rtwDapw
 github.com/emicklei/go-restful/v3 v3.12.0/go.mod h1:6n3XBCmQQb25CM2LCACGz8ukIrRry+4bhvbpWn3mrbc=
 github.com/evanphx/json-patch v4.12.0+incompatible h1:4onqiflcdA9EOZ4RxV643DvftH5pOlLGNtQ5lPWQu84=
 github.com/evanphx/json-patch v4.12.0+incompatible/go.mod h1:50XU6AFN0ol/bzJsmQLiYLvXMP4fmwYFNcr97nuDLSk=
+github.com/fatih/color v1.17.0 h1:GlRw1BRJxkpqUCBKzKOw098ed57fEsKeNjpTe3cSjK4=
+github.com/fatih/color v1.17.0/go.mod h1:YZ7TlrGPkiz6ku9fK3TLD/pl3CpsiFyu8N92HLgmosI=
 github.com/felixge/httpsnoop v1.0.4 h1:NFTV2Zj1bL4mc9sqWACXbQFVBBg2W3GPvqp8/ESS2Wg=
 github.com/felixge/httpsnoop v1.0.4/go.mod h1:m8KPJKqk1gH5J9DgRY2ASl2lWCfGKXixSwevea8zH2U=
 github.com/fxamacker/cbor/v2 v2.6.0 h1:sU6J2usfADwWlYDAFhZBQ6TnLFBHxgesMrQfQgk1tWA=
@@ -41,6 +43,8 @@ github.com/go-openapi/swag v0.23.0/go.mod h1:esZ8ITTYEsH1V2trKHjAN8Ai7xHb8RV+YSZ
 github.com/go-task/slim-sprig v0.0.0-20230315185526-52ccab3ef572 h1:tfuBGBXKqDEevZMzYi5KSi8KkcZtzBcTgAUUtapy0OI=
 github.com/go-task/slim-sprig/v3 v3.0.0 h1:sUs3vkvUymDpBKi3qH1YSqBQk9+9D/8M2mN1vB6EwHI=
 github.com/go-task/slim-sprig/v3 v3.0.0/go.mod h1:W848ghGpv3Qj3dhTPRyJypKRiqCdHZiAzKg9hl15HA8=
+github.com/goccy/go-yaml v1.11.3 h1:B3W9IdWbvrUu2OYQGwvU1nZtvMQJPBKgBUuweJjLj6I=
+github.com/goccy/go-yaml v1.11.3/go.mod h1:wKnAMd44+9JAAnGQpWVEgBzGt3YuTaQ4uXoHvE4m7WU=
 github.com/gogo/protobuf v1.3.2 h1:Ov1cvc58UF3b5XjBnZv7+opcTcQFZebYjWzi34vdm4Q=
 github.com/gogo/protobuf v1.3.2/go.mod h1:P1XiOD3dCwIKUDQYPy72D8LYyHL2YPYrpS2s69NZV8Q=
 github.com/golang/protobuf v1.5.4 h1:i7eJL8qZTpSEXOPTxNKhASYpMn+8e5Q6AdndVa1dWek=
@@ -76,6 +80,11 @@ github.com/kr/text v0.2.0 h1:5Nx0Ya0ZqY2ygV366QzturHI13Jq95ApcVaJBhpS+AY=
 github.com/kr/text v0.2.0/go.mod h1:eLer722TekiGuMkidMxC/pM04lWEeraHUUmBw8l2grE=
 github.com/mailru/easyjson v0.7.7 h1:UGYAvKxe3sBsEDzO8ZeWOSlIQfWFlxbzLZe7hwFURr0=
 github.com/mailru/easyjson v0.7.7/go.mod h1:xzfreul335JAWq5oZzymOObrkdz5UnU4kGfJJLY9Nlc=
+github.com/mattn/go-colorable v0.1.13 h1:fFA4WZxdEF4tXPZVKMLwD8oUnCTTo08duU7wxecdEvA=
+github.com/mattn/go-colorable v0.1.13/go.mod h1:7S9/ev0klgBDR4GtXTXX8a3vIGJpMovkB8vQcUbaXHg=
+github.com/mattn/go-isatty v0.0.16/go.mod h1:kYGgaQfpe5nmfYZH+SKPsOc2e4SrIfOl2e/yFXSvRLM=
+github.com/mattn/go-isatty v0.0.20 h1:xfD0iDuEKnDkl03q4limB+vH+GxLEtL/jb4xVJSWWEY=
+github.com/mattn/go-isatty v0.0.20/go.mod h1:W+V8PltTTMOvKvAeJH7IuucS94S2C6jfK/D7dTCTo3Y=
 github.com/moby/docker-image-spec v1.3.1 h1:jMKff3w6PgbfSa69GfNg+zN/XLhfXJGnEx3Nl2EsFP0=
 github.com/moby/docker-image-spec v1.3.1/go.mod h1:eKmb5VW8vQEh/BAr2yvVNvuiJuY6UIocYsFu/DxxRpo=
 github.com/moby/spdystream v0.2.0 h1:cjW1zVyyoiM0T7b6UoySUFqzXMoqRckQtXwGPiBhOM8=
@@ -185,8 +194,12 @@ golang.org/x/sys v0.0.0-20190215142949-d0b11bdaac8a/go.mod h1:STP8DvDyc/dI5b8T5h
 golang.org/x/sys v0.0.0-20190412213103-97732733099d/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
 golang.org/x/sys v0.0.0-20200930185726-fdedc70b468f/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
 golang.org/x/sys v0.0.0-20210616094352-59db8d763f22/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
+golang.org/x/sys v0.0.0-20220811171246-fbc7d0a398ab/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
+golang.org/x/sys v0.6.0/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
 golang.org/x/sys v0.21.0 h1:rF+pYz3DAGSQAxAu1CbC7catZg4ebC4UIeIhKxBZvws=
 golang.org/x/sys v0.21.0/go.mod h1:/VUhepiaJMQUp4+oa/7Zr1D23ma6VTLIYjOOTFZPUcA=
+golang.org/x/sys v0.22.0 h1:RI27ohtqKCnwULzJLqkv897zojh5/DwS/ENaMzUOaWI=
+golang.org/x/sys v0.22.0/go.mod h1:/VUhepiaJMQUp4+oa/7Zr1D23ma6VTLIYjOOTFZPUcA=
 golang.org/x/term v0.21.0 h1:WVXCp+/EBEHOj53Rvu+7KiT/iElMrO8ACK16SMZ3jaA=
 golang.org/x/term v0.21.0/go.mod h1:ooXLefLobQVslOqselCNF4SxFAaoS6KujMbsGzSDmX0=
 golang.org/x/text v0.3.0/go.mod h1:NqM8EUOU14njkJ3fqMW+pc6Ldnwhi/IjpwHt7yyuwOQ=
@@ -205,6 +218,8 @@ golang.org/x/xerrors v0.0.0-20190717185122-a985d3407aa7/go.mod h1:I/5z698sn9Ka8T
 golang.org/x/xerrors v0.0.0-20191011141410-1b5146add898/go.mod h1:I/5z698sn9Ka8TeJc9MKroUUfqBBauWjQqLJ2OPfmY0=
 golang.org/x/xerrors v0.0.0-20191204190536-9bdfabe68543/go.mod h1:I/5z698sn9Ka8TeJc9MKroUUfqBBauWjQqLJ2OPfmY0=
 golang.org/x/xerrors v0.0.0-20200804184101-5ec99f83aff1/go.mod h1:I/5z698sn9Ka8TeJc9MKroUUfqBBauWjQqLJ2OPfmY0=
+golang.org/x/xerrors v0.0.0-20231012003039-104605ab7028 h1:+cNy6SZtPcJQH3LJVLOSmiC7MMxXNOb3PU/VUEz+EhU=
+golang.org/x/xerrors v0.0.0-20231012003039-104605ab7028/go.mod h1:NDW/Ps6MPRej6fsCIbMTohpP40sJ/P/vI1MoTEGwX90=
 google.golang.org/genproto/googleapis/api v0.0.0-20240318140521-94a12d6c2237 h1:RFiFrvy37/mpSpdySBDrUdipW/dHwsRwh3J3+A9VgT4=
 google.golang.org/genproto/googleapis/api v0.0.0-20240318140521-94a12d6c2237/go.mod h1:Z5Iiy3jtmioajWHDGFk7CeugTyHtPvMHA4UTmUkyalE=
 google.golang.org/genproto/googleapis/rpc v0.0.0-20240318140521-94a12d6c2237 h1:NnYq6UN9ReLM9/Y01KWNOWyI5xQ9kbIms5GGJVwS/Yc=

internal/yaml/parser.go

@@ -2,10 +2,14 @@
 
 import (
 	"fmt"
-
-	"gopkg.in/yaml.v3"
+	"github.com/goccy/go-yaml"
+	"github.com/goccy/go-yaml/ast"
+	"github.com/goccy/go-yaml/token"
+	"strings"
 )
 
+const BoolTag token.ReservedTagKeyword = "!!bool"
+
 // New creates a new YAML parser.
 func New() Parser {
 	return &parser{}
@@ -16,8 +20,9 @@
 	return &node{
 		typeID:   TypeIDString,
 		tag:      "!!null",
-		contents: nil,
 		value:    "",
+		contents: nil,
+		nodeMap:  nil,
 	}
 }
 
@@ -63,15 +68,16 @@
 	tag      string
 	contents []Node
 	value    string
+	nodeMap  map[string]Node
 }
 
 func (n node) MapKeys() []string {
 	if n.typeID != TypeIDMap {
 		panic(fmt.Errorf("node is not a map, cannot call MapKeys"))
 	}
-	result := make([]string, len(n.contents)/2)
-	for i := 0; i < len(n.contents); i += 2 {
-		result[i/2] = n.contents[i].Value()
+	result := make([]string, 0)
+	for k := range n.nodeMap {
+		result = append(result, k)
 	}
 	return result
 }
@@ -80,10 +86,8 @@
 	if n.typeID != TypeIDMap {
 		panic(fmt.Errorf("node is not a map, cannot call MapKey"))
 	}
-	for i := 0; i < len(n.contents); i += 2 {
-		if key == n.contents[i].Raw() {
-			return n.contents[i+1], true
-		}
+	if value, ok := n.nodeMap[key]; ok {
+		return value, true
 	}
 	return nil, false
 }
@@ -93,11 +97,9 @@
 	case TypeIDString:
 		return n.value
 	case TypeIDMap:
-		result := make(map[string]any, len(n.contents)/2)
-		for i := 0; i < len(n.contents); i += 2 {
-			key := n.contents[i].Raw().(string)
-			value := n.contents[i+1].Raw()
-			result[key] = value
+		result := make(map[string]any, len(n.nodeMap))
+		for key, value := range n.nodeMap {
+			result[key] = value.Raw()
 		}
 		return result
 	case TypeIDSequence:
@@ -130,45 +132,126 @@
 type parser struct {
 }
 
+func removeLeftLF(src string) string {
+	return strings.TrimLeft(strings.TrimLeft(strings.TrimLeft(src, "\r"), "\n"), "\r\n")
+}
+
+func RemoveAllLineEndSpaces(src string) string {
+	var strBuilder strings.Builder
+	for _, k := range strings.Split(src, "\n") {
+		s := strings.TrimRight(k, "\r ")
+		strBuilder.WriteString(s + "\n")
+	}
+	return strBuilder.String()
+}
+
 func (p parser) Parse(data []byte) (Node, error) {
-	var n yaml.Node
+	// goccy's yaml decoder has a bug involving trailing spaces before
+	// the line end character
+	out := RemoveAllLineEndSpaces(fmt.Sprintf("msg1: abc '\n'\nmsg2: def\nmsg3: ghi"))
+	fmt.Printf("%v\n", out)
+
+	//trimmedData := RemoveAllLineEndSpaces(string(data))
+	var n ast.Node
 	if err := yaml.Unmarshal(data, &n); err != nil {
 		return nil, err
 	}
+	if n == nil {
+		return node{}, fmt.Errorf("empty YAML file given")
+	}
 	return p.transform(&n)
 }
 
-func (p parser) transform(n *yaml.Node) (Node, error) {
-	var t TypeID
-	switch n.Kind {
-	case 0:
-		return nil, fmt.Errorf("empty YAML file given")
-	case yaml.MappingNode:
-		t = TypeIDMap
-	case yaml.SequenceNode:
-		t = TypeIDSequence
-	case yaml.ScalarNode:
-		t = TypeIDString
-	case yaml.DocumentNode:
-		return p.transform(n.Content[0])
+// transform converts an instance of goccy's yaml ast to the arcaflow engine's
+// yaml ast
+func (p parser) transform(n *ast.Node) (node, error) {
+	arcaNode := node{contents: make([]Node, 0), nodeMap: make(map[string]Node)}
+	var childArcaNode node
+	var err error
+	switch (*n).Type() {
+	case ast.TagType:
+		// tag nodes do not exist in the engine's yaml ast, so they need to be
+		// replaced by their child value node
+		tagNode := (*n).(*ast.TagNode)
+		tagExplicit := string(token.ReservedTagKeyword(tagNode.GetToken().Value))
+		childArcaNode, err = p.transform(&tagNode.Value)
+		if err == nil {
+			childArcaNode.tag = tagExplicit
+			arcaNode = childArcaNode
+		}
+	case ast.DocumentType:
+		docNode := (*n).(*ast.DocumentNode)
+		// recursively transform nodes in non-empty container nodes
+		arcaNode, err = p.transform(&docNode.Body)
+	case ast.MappingType:
+		arcaNode.typeID = TypeIDMap
+		arcaNode.tag = string(token.MappingTag)
+		mappingNode := (*n).(*ast.MappingNode)
+		// recursively transform nodes in non-empty container nodes
+		arcaNode, err = p.fillNodeMap(mappingNode.MapRange(), arcaNode)
+	case ast.MappingValueType:
+		arcaNode.typeID = TypeIDMap
+		arcaNode.tag = string(token.MappingTag)
+		mappingValueNode := (*n).(*ast.MappingValueNode)
+		// recursively transform nodes in non-empty container nodes
+		arcaNode, err = p.fillNodeMap(mappingValueNode.MapRange(), arcaNode)
+	case ast.SequenceType:
+		arcaNode.typeID = TypeIDSequence
+		arcaNode.tag = string(token.SequenceTag)
+		sequenceNode := (*n).(*ast.SequenceNode)
+		// recursively transform nodes in non-empty container nodes
+		for _, subNode := range sequenceNode.Values {
+			childArcaNode, err = p.transform(&subNode)
+			if err != nil {
+				return node{}, err
+			}
+			arcaNode.contents = append(arcaNode.contents, childArcaNode)
+		}
+	case ast.LiteralType:
+		arcaNode.tag = string(token.StringTag)
+		arcaNode.typeID = TypeIDString
+		literalNode := (*n).(*ast.LiteralNode)
+		scalarNode := any(literalNode.Value).(ast.ScalarNode)
+		arcaNode.value = fmt.Sprintf("%v", scalarNode.GetValue())
+	case ast.NullType:
+		arcaNode.tag = string(token.NullTag)
+		arcaNode.value = (*n).GetToken().Value
+	case ast.FloatType:
+		arcaNode.tag = string(token.FloatTag)
+		arcaNode.typeID = TypeIDString
+		// must use token to get expected significant figures for numbers with
+		// trailing zeros after decimal
+		arcaNode.value = (*n).GetToken().Value
+	case ast.BoolType:
+		arcaNode.tag = string(BoolTag)
+		arcaNode.typeID = TypeIDString
+		scalarNode := (*n).(ast.ScalarNode)
+		arcaNode.value = fmt.Sprintf("%v", scalarNode.GetValue())
+	case ast.IntegerType:
+		arcaNode.tag = string(token.IntegerTag)
+		arcaNode.typeID = TypeIDString
+		scalarNode := (*n).(ast.ScalarNode)
+		arcaNode.value = fmt.Sprintf("%v", scalarNode.GetValue())
+	case ast.StringType:
+		arcaNode.tag = string(token.StringTag)
+		arcaNode.typeID = TypeIDString
+		scalarNode := (*n).(ast.ScalarNode)
+		arcaNode.value = fmt.Sprintf("%v", scalarNode.GetValue())
 	default:
-		return nil, fmt.Errorf("unsupported node type: %d", n.Kind)
+		return node{}, fmt.Errorf("unsupported node type: %s", (*n).Type())
 	}
+	return arcaNode, nil
+}
 
-	contents := make([]Node, len(n.Content))
-	for i, subNode := range n.Content {
-		subContent, err := p.transform(subNode)
+func (p parser) fillNodeMap(mapIter *ast.MapNodeIter, arcaNode node) (node, error) {
+	for mapIter.Next() {
+		subNodeKey := mapIter.Key().String()
+		subNode := mapIter.Value()
+		subContent, err := p.transform(&subNode)
 		if err != nil {
-			return nil, err
+			return node{}, err
 		}
-		contents[i] = subContent
+		arcaNode.nodeMap[subNodeKey] = subContent
 	}
-
-	return &node{
-		t,
-		n.Tag,
-		contents,
-		n.Value,
-	}, nil
-
+	return arcaNode, nil
 }