Unmarshal: WIP

Signed-off-by: Alejandro Mery <amery@jpi.io>

go.mod

@@ -7,6 +7,7 @@ replace asciigoat.org/core => ../core
 require (
 	asciigoat.org/core v0.3.6
 	github.com/mgechev/revive v1.3.3
+	golang.org/x/tools v0.12.0
 )
 
 require (
@@ -21,6 +22,6 @@ require (
 	github.com/mitchellh/go-homedir v1.1.0 // indirect
 	github.com/olekukonko/tablewriter v0.0.5 // indirect
 	github.com/pkg/errors v0.9.1 // indirect
+	golang.org/x/mod v0.12.0 // indirect
 	golang.org/x/sys v0.11.0 // indirect
-	golang.org/x/tools v0.12.0 // indirect
 )

go.sum

@@ -36,6 +36,8 @@ github.com/stretchr/testify v1.8.0/go.mod h1:yNjHg4UonilssWZ8iaSj1OCr/vHnekPRkoO
 github.com/stretchr/testify v1.8.4 h1:CcVxjf3Q8PM0mHUKJCdn+eZZtm5yQwehR5yeSVQQcUk=
 github.com/stretchr/testify v1.8.4/go.mod h1:sz/lmYIOXD/1dqDmKjjqLyZ2RngseejIcXlSw2iwfAo=
 golang.org/x/mod v0.12.0 h1:rmsUpXtvNzj340zd98LZ4KntptpfRHwpFOHG188oHXc=
+golang.org/x/mod v0.12.0/go.mod h1:iBbtSCu2XBx23ZKBPSOrRkjjQPZFPuis4dIYUhu/chs=
+golang.org/x/sync v0.3.0 h1:ftCYgMx6zT/asHUrPw8BLLscYtGznsLAnjq5RH9P66E=
 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 v0.11.0 h1:eG7RXZHdqOJ1i+0lgLgCpSXAp6M3LYlAo6osgSi0xOM=

parser/lexer.go

@@ -1,16 +1,14 @@
 package parser
 
 import (
-	"log"
-
 	"asciigoat.org/core/lexer"
 )
 
 // Run parses the source
 func (p *Parser) Run() error {
 	p.setDefaults()
-
 	p.pos.Reset()
+
 	return lexer.Run(p.lexStart)
 }
 
@@ -24,29 +22,26 @@ func (p *Parser) lexStart() (lexer.StateFn, error) {
 		case IsNewLine(r):
 			// new line
 			p.lexNewLine(r)
-			p.src.Discard()
-			p.pos.StepLine()
+			p.stepLine()
 		case IsSpace(r):
 			// whitespace
-			p.src.Discard()
-			p.pos.Step()
-		case IsCommentStart(r):
-			// switch to comment lexer
-			p.src.UnreadRune()
-			return p.lexComment, nil
-		case IsSectionStart(r):
-			// section
-			p.src.Discard()
-			p.pos.Step()
-			return p.lexSectionStart, nil
+			p.stepRune()
 		default:
-			// entry
+			// token
 			p.src.UnreadRune()
-			return p.lexEntryStart, nil
+			return p.lexToken, nil
 		}
 	}
 }
 
+func (p *Parser) lexToken() (lexer.StateFn, error) {
+	p.src.AcceptAll(IsNotSpace)
+
+	p.pushString(TokenUnknown)
+
+	return p.lexStart, nil
+}
+
 func (p *Parser) lexNewLine(r1 rune) {
 	// r1 is warrantied to be either \n or \r
 	r2, _, err := p.src.ReadRune()
@@ -76,24 +71,3 @@ func (p *Parser) lexNewLine(r1 rune) {
 		panic("unreachable")
 	}
 }
-
-func (p *Parser) lexComment() (lexer.StateFn, error) {
-	// until the end of the line
-	p.src.AcceptAll(IsNotNewLine)
-
-	err := p.OnComment(p.pos, p.src.Emit())
-	return p.lexStart, err
-}
-
-func (*Parser) lexSectionStart() (lexer.StateFn, error) { return nil, nil }
-func (*Parser) lexEntryStart() (lexer.StateFn, error)   { return nil, nil }
-
-func (p *Parser) lexToken() (lexer.StateFn, error) {
-	p.src.AcceptAll(IsNotSpace)
-
-	s := p.src.Emit()
-	log.Printf("%s: %s: %q", p.pos, "token", s)
-	p.pos.StepN(len(s))
-
-	return p.lexStart, nil
-}

parser/lexer_error.go

@@ -13,7 +13,3 @@ func (p *Parser) emitError(content string, err error) (lexer.StateFn, error) {
 		return nil, err
 	}
 }
-
-func (p *Parser) emitInvalidRune(r rune) (lexer.StateFn, error) {
-	return p.emitError(string([]rune{r}), lexer.ErrUnacceptableRune)
-}

parser/lexer_queue.go

@@ -0,0 +1,44 @@
+package parser
+
+import "log"
+
+func (p *Parser) push(tok Token) {
+	n := len(p.queue)
+	p.queue = append(p.queue, tok)
+
+	log.Printf("queue[%v]: %s", n, tok)
+}
+
+func (p *Parser) pushString(typ TokenType) {
+	s := p.src.Emit()
+
+	el := Token{
+		Type:     typ,
+		Value:    s,
+		Position: p.pos,
+	}
+
+	p.pos.StepN(len(s))
+
+	p.push(el)
+}
+
+// stepLine discards the data and moves the position
+// to the next line
+func (p *Parser) stepLine() {
+	p.src.Discard()
+	p.pos.StepLine()
+}
+
+// stepRune discards the data and moves the position
+// on rune forward on the same line
+func (p *Parser) stepRune() {
+	p.src.Discard()
+	p.pos.Step()
+}
+
+func (p *Parser) stepString() string {
+	s := p.src.Emit()
+	p.pos.StepN(len(s))
+	return s
+}

parser/lexer_runes.go

@@ -11,10 +11,9 @@ var (
 	IsNotNewLine = lexer.NewIsNot(IsNewLine)
 	// IsNotSpace tells if a rune is anything other than whitespace
 	IsNotSpace = lexer.NewIsNot(IsSpace)
-
-	IsCommentStart = lexer.NewIsIn(";#")
 )
 
-func IsSectionStart(r rune) bool {
-	return r == '['
+// IsSpaceNotNewLine indicates a rune is whitespace but not a new line
+func IsSpaceNotNewLine(r rune) bool {
+	return IsSpace(r) && !IsNewLine(r)
 }

parser/parser.go

@@ -11,7 +11,8 @@ import (
 type Parser struct {
 	src *lexer.Reader
 
-	pos lexer.Position
+	pos   lexer.Position
+	queue []Token
 
 	// OnSection is called after a [section] is parsed.
 	// Returning an error will abort the process.

parser/token.go

@@ -0,0 +1,41 @@
+package parser
+
+//go:generate go run golang.org/x/tools/cmd/stringer -type=TokenType
+import (
+	"fmt"
+
+	"asciigoat.org/core/lexer"
+)
+
+// A TokenType is a type of Token
+type TokenType uint
+
+const (
+	// TokenUnknown represents a Token that hasn't been identified
+	TokenUnknown TokenType = iota
+	// TokenSectionName represents the section name between the squared brackets
+	TokenSectionName
+	// TokenSectionSubname represents a secondary name in the section represented
+	// between quotes after the section name.
+	// e.g.
+	// [section_name "section_subname"]
+	TokenSectionSubname
+	// TokenComment represents a comment, including the initial ';' or '#' until
+	// the end of the line
+	TokenComment
+	// TokenFieldKey represents a field name in a `key = value` entry
+	TokenFieldKey
+	// TokenFieldValue represents a field value in a `key = value` entry
+	TokenFieldValue
+)
+
+// A Token is an element from the document
+type Token struct {
+	Type     TokenType
+	Position lexer.Position
+	Value    string
+}
+
+func (t Token) String() string {
+	return fmt.Sprintf("%v:%v: %s: %q", t.Position.Line, t.Position.Column, t.Type, t.Value)
+}

parser/tokentype_string.go

@@ -0,0 +1,28 @@
+// Code generated by "stringer -type=TokenType"; DO NOT EDIT.
+
+package parser
+
+import "strconv"
+
+func _() {
+	// An "invalid array index" compiler error signifies that the constant values have changed.
+	// Re-run the stringer command to generate them again.
+	var x [1]struct{}
+	_ = x[TokenUnknown-0]
+	_ = x[TokenSectionName-1]
+	_ = x[TokenSectionSubname-2]
+	_ = x[TokenComment-3]
+	_ = x[TokenFieldKey-4]
+	_ = x[TokenFieldValue-5]
+}
+
+const _TokenType_name = "TokenUnknownTokenSectionNameTokenSectionSubnameTokenCommentTokenFieldKeyTokenFieldValue"
+
+var _TokenType_index = [...]uint8{0, 12, 28, 47, 59, 72, 87}
+
+func (i TokenType) String() string {
+	if i >= TokenType(len(_TokenType_index)-1) {
+		return "TokenType(" + strconv.FormatInt(int64(i), 10) + ")"
+	}
+	return _TokenType_name[_TokenType_index[i]:_TokenType_index[i+1]]
+}

tools/tools.go

@@ -4,4 +4,5 @@ package tools
 
 import (
 	_ "github.com/mgechev/revive"
+	_ "golang.org/x/tools/cmd/stringer"
 )