parser: WIP

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

go.mod

@@ -2,7 +2,12 @@ module asciigoat.org/ini
 
 go 1.19
 
-require github.com/mgechev/revive v1.3.3
+replace asciigoat.org/core => ../core
+
+require (
+	asciigoat.org/core v0.3.4
+	github.com/mgechev/revive v1.3.3
+)
 
 require (
 	github.com/BurntSushi/toml v1.3.2 // indirect

parser/lexer.go

@@ -0,0 +1,99 @@
+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)
+}
+
+func (p *Parser) lexStart() (lexer.StateFn, error) {
+	for {
+		r, _, err := p.src.ReadRune()
+		switch {
+		case err != nil:
+			// read error
+			return p.emitError("", err)
+		case IsNewLine(r):
+			// new line
+			p.lexNewLine(r)
+			p.src.Discard()
+			p.pos.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
+		default:
+			// entry
+			p.src.UnreadRune()
+			return p.lexEntryStart, nil
+		}
+	}
+}
+
+func (p *Parser) lexNewLine(r1 rune) {
+	// r1 is warrantied to be either \n or \r
+	r2, _, err := p.src.ReadRune()
+
+	switch r1 {
+	case '\r':
+		switch {
+		case r2 == '\n':
+			// CR LN
+		case err == nil:
+			// CR
+			p.src.UnreadRune()
+		default:
+			// CR EOF
+		}
+	case '\n':
+		switch {
+		case r2 == '\r':
+			// LN CR
+		case err == nil:
+			// LN
+			p.src.UnreadRune()
+		default:
+			// LN EOF
+		}
+	default:
+		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

@@ -0,0 +1,19 @@
+package parser
+
+import "asciigoat.org/core/lexer"
+
+func (p *Parser) emitError(content string, err error) (lexer.StateFn, error) {
+	err2 := p.OnError(p.pos, content, err)
+	switch {
+	case err2 != nil:
+		// return wrapped error
+		return nil, err2
+	default:
+		// return original error
+		return nil, err
+	}
+}
+
+func (p *Parser) emitInvalidRune(r rune) (lexer.StateFn, error) {
+	return p.emitError(string([]rune{r}), lexer.ErrUnacceptableRune)
+}

parser/lexer_runes.go

@@ -0,0 +1,20 @@
+package parser
+
+import "asciigoat.org/core/lexer"
+
+var (
+	// IsNewLine tells if a rune represents a line break or the start of one
+	IsNewLine = lexer.NewIsIn("\n\r")
+	// IsSpace tells if a rune is considered whitespace by unicode
+	IsSpace = lexer.IsSpace
+	// IsNotNewLine tells if a rune is anything other than line breaks
+	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 == '['
+}

parser/parser.go

@@ -0,0 +1,63 @@
+// Package parser parses dosini-style files
+package parser
+
+import (
+	"io"
+
+	"asciigoat.org/core/lexer"
+)
+
+// Parser parses a dosini-style document
+type Parser struct {
+	src *lexer.Reader
+
+	pos lexer.Position
+
+	OnSection func(pos lexer.Position, name, subname string, hasSubname bool) error
+	OnField   func(pos lexer.Position, key, value string) error
+	OnComment func(pos lexer.Position, comment string) error
+	OnError   func(pos lexer.Position, content string, err error) error
+}
+
+func defaultOnSection(_ lexer.Position, _, _ string, _ bool) error { return nil }
+func defaultOnField(_ lexer.Position, _, _ string) error           { return nil }
+func defaultOnComment(_ lexer.Position, _ string) error            { return nil }
+
+func defaultOnError(pos lexer.Position, content string, err error) error {
+	return &lexer.Error{
+		Line:    pos.Line,
+		Column:  pos.Column,
+		Content: content,
+		Err:     err,
+	}
+}
+
+func (p *Parser) setDefaults() {
+	if p.OnSection == nil {
+		p.OnSection = defaultOnSection
+	}
+
+	if p.OnField == nil {
+		p.OnField = defaultOnField
+	}
+
+	if p.OnComment == nil {
+		p.OnComment = defaultOnComment
+	}
+
+	if p.OnError == nil {
+		p.OnError = defaultOnError
+	}
+}
+
+// NewParser creates a dosini-style parser using
+// an [io.Reader] as source
+func NewParser(r io.Reader) *Parser {
+	if r == nil {
+		return nil
+	}
+
+	return &Parser{
+		src: lexer.NewReader(r),
+	}
+}