Implement lexer for new syntax

This commit is contained in:
Brian Picciano 2021-12-26 14:49:43 -07:00
parent b1831a670f
commit e4bdeb8797
4 changed files with 491 additions and 431 deletions

284
gg/lexer.go Normal file
View File

@ -0,0 +1,284 @@
package gg
import (
"bufio"
"fmt"
"io"
"strings"
"unicode"
)
// LexerError is returned by Lexer when an unexpected error occurs parsing a
// stream of LexerTokens.
type LexerError struct {
Err error
Row, Col int
}
func (e *LexerError) Error() string {
return fmt.Sprintf("%d: %d: %s", e.Col, e.Row, e.Err.Error())
}
func (e *LexerError) Unwrap() error {
return e.Err
}
// LexerTokenKind enumerates the different kinds of LexerToken there can be.
type LexerTokenKind string
// Enumeration of LexerTokenKinds.
const (
LexerTokenKindName LexerTokenKind = "name"
LexerTokenKindNumber LexerTokenKind = "number"
LexerTokenKindPunctuation LexerTokenKind = "punctuation"
)
// LexerToken describes a lexigraphical token which is used when deserializing
// Graphs.
type LexerToken struct {
Kind LexerTokenKind
Value string // never empty string
Row, Col int
}
// Lexer is used to parse a string stream into a sequence of tokens which can
// then be parsed by a Parser.
type Lexer interface {
// Next will return a LexerToken or a LexerError. io.EOF (wrapped in a
// LexerError) is returned if the stream being read from is finished.
Next() (LexerToken, error)
}
type lexer struct {
r *bufio.Reader
stringBuilder *strings.Builder
err *LexerError
// these fields are only needed to keep track of the current "cursor"
// position when reading.
lastRow, lastCol int
prevRune rune
}
// NewLexer wraps the io.Reader in a Lexer, which will read the io.Reader as a
// sequence of utf-8 characters and parse it into a sequence of LexerTokens.
func NewLexer(r io.Reader) Lexer {
return &lexer{
r: bufio.NewReader(r),
lastRow: 0,
lastCol: -1,
stringBuilder: new(strings.Builder),
}
}
// nextRowCol returns the row and column number which the next rune in the
// stream would be at.
func (l *lexer) nextRowCol() (int, int) {
if l.prevRune == '\n' {
return l.lastRow + 1, 0
}
return l.lastRow, l.lastCol + 1
}
func (l *lexer) fmtErr(err error) *LexerError {
row, col := l.nextRowCol()
return &LexerError{
Err: err,
Row: row,
Col: col,
}
}
func (l *lexer) fmtErrf(str string, args ...interface{}) *LexerError {
return l.fmtErr(fmt.Errorf(str, args...))
}
// discardRune must _always_ be called only after peekRune.
func (l *lexer) discardRune() {
r, _, err := l.r.ReadRune()
if err != nil {
panic(err)
}
l.lastRow, l.lastCol = l.nextRowCol()
l.prevRune = r
}
func (l *lexer) peekRune() (rune, error) {
r, _, err := l.r.ReadRune()
if err != nil {
return '0', err
} else if err := l.r.UnreadRune(); err != nil {
// since the most recent operation on the bufio.Reader was a ReadRune,
// UnreadRune should never return an error
panic(err)
}
return r, nil
}
// readWhile reads runes until the given predicate returns false, and returns a
// LexerToken of the given kind whose Value is comprised of all runes which
// returned true.
//
// If an error is encountered then both the token (or what's been parsed of it
// so far) and the error are returned.
func (l *lexer) readWhile(
kind LexerTokenKind, pred func(rune) bool,
) (
LexerToken, *LexerError,
) {
row, col := l.nextRowCol()
l.stringBuilder.Reset()
var lexErr *LexerError
for {
r, err := l.peekRune()
if err != nil {
lexErr = l.fmtErrf("peeking next character: %w", err)
break
} else if !pred(r) {
break
}
l.stringBuilder.WriteRune(r)
l.discardRune()
}
return LexerToken{
Kind: kind,
Value: l.stringBuilder.String(),
Row: row, Col: col,
}, lexErr
}
// we only support base-10 integers at the moment.
func isNumber(r rune) bool {
return r == '-' || ('0' <= r && r <= '9')
}
// next can return a token, an error, or both. If an error is returned then no
// further calls to next should occur.
func (l *lexer) next() (LexerToken, *LexerError) {
for {
r, err := l.peekRune()
if err != nil {
return LexerToken{}, l.fmtErrf("peeking next character: %w", err)
}
switch {
case r == '*': // comment
// comments are everything up until a newline
_, err := l.readWhile("", func(r rune) bool {
return r != '\n'
})
if err != nil {
return LexerToken{}, err
}
// terminating newline is deliberately not discarded. Loop and find
// the next token (which will be that newline).
case r == '\n':
// newlines are considered punctuation, not whitespace
l.discardRune()
return LexerToken{
Kind: LexerTokenKindPunctuation,
Value: string(r),
Row: l.lastRow,
Col: l.lastCol,
}, nil
case r == '"' || r == '`':
// reserve double-quote and backtick for string parsing.
l.discardRune()
return LexerToken{}, l.fmtErrf("string parsing not yet implemented")
case unicode.IsLetter(r):
// letters denote the start of a name
return l.readWhile(LexerTokenKindName, func(r rune) bool {
if unicode.In(r, unicode.Letter, unicode.Number, unicode.Mark) {
return true
}
if r == '-' {
return true
}
return false
})
case isNumber(r):
return l.readWhile(LexerTokenKindNumber, isNumber)
case unicode.IsPunct(r) || unicode.IsSymbol(r):
// symbols are also considered punctuation
l.discardRune()
return LexerToken{
Kind: LexerTokenKindPunctuation,
Value: string(r),
Row: l.lastRow,
Col: l.lastCol,
}, nil
case unicode.IsSpace(r):
l.discardRune()
default:
return LexerToken{}, l.fmtErrf("unexpected character %q", r)
}
}
}
func (l *lexer) Next() (LexerToken, error) {
if l.err != nil {
return LexerToken{}, l.err
}
tok, err := l.next()
if err != nil {
l.err = err
if tok.Kind == "" {
return LexerToken{}, l.err
}
}
return tok, nil
}

207
gg/lexer_test.go Normal file
View File

@ -0,0 +1,207 @@
package gg
import (
"errors"
"strconv"
"strings"
"testing"
"github.com/stretchr/testify/assert"
)
type mockReader struct {
body []byte
err error
}
func (r *mockReader) Read(b []byte) (int, error) {
n := copy(b, r.body)
r.body = r.body[n:]
if len(r.body) == 0 {
return n, r.err
}
return n, nil
}
func TestLexer(t *testing.T) {
expErr := errors.New("eof")
tests := []struct {
in string
exp []LexerToken
}{
{in: "", exp: []LexerToken{}},
{in: "* fooo", exp: []LexerToken{}},
{
in: "*\n",
exp: []LexerToken{
{
Kind: LexerTokenKindPunctuation,
Value: "\n",
Row: 0, Col: 1,
},
},
},
{
in: "foo\nbar\n\n",
exp: []LexerToken{
{
Kind: LexerTokenKindName,
Value: "foo",
Row: 0, Col: 0,
},
{
Kind: LexerTokenKindPunctuation,
Value: "\n",
Row: 0, Col: 3,
},
{
Kind: LexerTokenKindName,
Value: "bar",
Row: 1, Col: 0,
},
{
Kind: LexerTokenKindPunctuation,
Value: "\n",
Row: 1, Col: 3,
},
{
Kind: LexerTokenKindPunctuation,
Value: "\n",
Row: 2, Col: 0,
},
},
},
{
in: "foo",
exp: []LexerToken{
{
Kind: LexerTokenKindName,
Value: "foo",
Row: 0, Col: 0,
},
},
},
{
in: "foo bar f-o f0O Foo",
exp: []LexerToken{
{
Kind: LexerTokenKindName,
Value: "foo",
Row: 0, Col: 0,
},
{
Kind: LexerTokenKindName,
Value: "bar",
Row: 0, Col: 4,
},
{
Kind: LexerTokenKindName,
Value: "f-o",
Row: 0, Col: 8,
},
{
Kind: LexerTokenKindName,
Value: "f0O",
Row: 0, Col: 12,
},
{
Kind: LexerTokenKindName,
Value: "Foo",
Row: 0, Col: 16,
},
},
},
{
in: "1 100 -100",
exp: []LexerToken{
{
Kind: LexerTokenKindNumber,
Value: "1",
Row: 0, Col: 0,
},
{
Kind: LexerTokenKindNumber,
Value: "100",
Row: 0, Col: 2,
},
{
Kind: LexerTokenKindNumber,
Value: "-100",
Row: 0, Col: 6,
},
},
},
{
in: "1<2!-3 ()",
exp: []LexerToken{
{
Kind: LexerTokenKindNumber,
Value: "1",
Row: 0, Col: 0,
},
{
Kind: LexerTokenKindPunctuation,
Value: "<",
Row: 0, Col: 1,
},
{
Kind: LexerTokenKindNumber,
Value: "2",
Row: 0, Col: 2,
},
{
Kind: LexerTokenKindPunctuation,
Value: "!",
Row: 0, Col: 3,
},
{
Kind: LexerTokenKindNumber,
Value: "-3",
Row: 0, Col: 4,
},
{
Kind: LexerTokenKindPunctuation,
Value: "(",
Row: 0, Col: 7,
},
{
Kind: LexerTokenKindPunctuation,
Value: ")",
Row: 0, Col: 8,
},
},
},
}
for i, test := range tests {
t.Run(strconv.Itoa(i), func(t *testing.T) {
lexer := NewLexer(&mockReader{body: []byte(test.in), err: expErr})
for i := range test.exp {
tok, err := lexer.Next()
assert.NoError(t, err)
assert.Equal(t, test.exp[i], tok, "test.exp[%d]", i)
}
tok, err := lexer.Next()
assert.ErrorIs(t, err, expErr)
assert.Equal(t, LexerToken{}, tok)
lexErr := new(LexerError)
assert.True(t, errors.As(err, &lexErr))
inParts := strings.Split(test.in, "\n")
assert.ErrorIs(t, lexErr, expErr)
assert.Equal(t, lexErr.Row, len(inParts)-1)
assert.Equal(t, lexErr.Col, len(inParts[len(inParts)-1]))
})
}
}

View File

@ -1,349 +0,0 @@
package lexer
import (
"bufio"
"bytes"
"errors"
"fmt"
"io"
"strings"
)
// TokenType indicates the type of a token
type TokenType string
// Different token types
const (
Identifier TokenType = "identifier"
// Punctuation are tokens which connect two other tokens
Punctuation TokenType = "punctuation"
// Wrapper wraps one or more tokens
Wrapper TokenType = "wrapper"
String TokenType = "string"
Err TokenType = "err"
EOF TokenType = "eof"
)
// Token is a single token which has been read in. All Tokens have a non-empty
// Val
type Token struct {
TokenType
Val string
Row, Col int
}
// Equal returns whether two tokens are of equal type and value
func (tok Token) Equal(tok2 Token) bool {
return tok.TokenType == tok2.TokenType && tok.Val == tok2.Val
}
// Err returns the error contained by the token, if any. Only returns non-nil if
// TokenType is Err or EOF
func (tok Token) Err() error {
if tok.TokenType == Err || tok.TokenType == EOF {
return fmt.Errorf("[line:%d col:%d] %s", tok.Row, tok.Col, tok.Val)
}
return nil
}
func (tok Token) String() string {
var typ string
switch tok.TokenType {
case Identifier:
typ = "ident"
case Punctuation:
typ = "punct"
case String:
typ = "str"
case Err, EOF:
typ = "err"
}
return fmt.Sprintf("%s(%q)", typ, tok.Val)
}
type lexerFn func(*Lexer) lexerFn
// Lexer is used to read in ginger tokens from a source. HasNext() must be
// called before every call to Next()
type Lexer struct {
in *bufio.Reader
out *bytes.Buffer
cur lexerFn
next []Token
row, col int
absRow, absCol int
}
// New returns a Lexer which will read tokens from the given source.
func New(r io.Reader) *Lexer {
return &Lexer{
in: bufio.NewReader(r),
out: new(bytes.Buffer),
cur: lex,
row: -1,
col: -1,
}
}
func (l *Lexer) emit(t TokenType) {
str := l.out.String()
if str == "" {
panic("cannot emit empty token")
}
l.out.Reset()
l.emitTok(Token{
TokenType: t,
Val: str,
Row: l.row,
Col: l.col,
})
}
func (l *Lexer) emitErr(err error) {
tok := Token{
TokenType: Err,
Val: err.Error(),
Row: l.absRow,
Col: l.absCol,
}
if errors.Is(err, io.EOF) {
tok.TokenType = EOF
}
l.emitTok(tok)
}
func (l *Lexer) emitTok(tok Token) {
l.next = append(l.next, tok)
l.row = -1
l.col = -1
}
func (l *Lexer) readRune() (rune, error) {
r, _, err := l.in.ReadRune()
if err != nil {
return r, err
}
if r == '\n' {
l.absRow++
l.absCol = 0
} else {
l.absCol++
}
return r, err
}
func (l *Lexer) peekRune() (rune, error) {
r, _, err := l.in.ReadRune()
if err != nil {
return r, err
}
if err := l.in.UnreadRune(); err != nil {
return r, err
}
return r, nil
}
func (l *Lexer) readAndPeek() (rune, rune, error) {
r, err := l.readRune()
if err != nil {
return r, 0, err
}
n, err := l.peekRune()
return r, n, err
}
func (l *Lexer) bufferRune(r rune) {
l.out.WriteRune(r)
if l.row < 0 && l.col < 0 {
l.row, l.col = l.absRow, l.absCol
}
}
// HasNext returns true if Next should be called, and false if it should not be
// called and Err should be called instead. When HasNext returns false the Lexer
// is considered to be done
func (l *Lexer) HasNext() bool {
for {
if len(l.next) > 0 {
return true
} else if l.cur == nil {
return false
}
l.cur = l.cur(l)
}
}
// Next returns the next available token. HasNext must be called before every
// call to Next
func (l *Lexer) Next() Token {
t := l.next[0]
l.next = l.next[1:]
if len(l.next) == 0 {
l.next = nil
}
return t
}
////////////////////////////////////////////////////////////////////////////////
// the actual fsm
var whitespaceSet = " \n\r\t\v\f"
var punctuationSet = ",>"
var wrapperSet = "{}()"
var identifierSepSet = whitespaceSet + punctuationSet + wrapperSet
func lex(l *Lexer) lexerFn {
r, err := l.readRune()
if err != nil {
l.emitErr(err)
return nil
}
// handle comments first, cause we have to peek for those. We ignore errors,
// and assume that any error that would happen here will happen again the
// next read
if n, _ := l.peekRune(); r == '/' && n == '/' {
return lexLineComment
} else if r == '/' && n == '*' {
return lexBlockComment
}
return lexSingleRune(l, r)
}
func lexSingleRune(l *Lexer, r rune) lexerFn {
switch {
case strings.ContainsRune(whitespaceSet, r):
return lex
case strings.ContainsRune(punctuationSet, r):
l.bufferRune(r)
l.emit(Punctuation)
return lex
case strings.ContainsRune(wrapperSet, r):
l.bufferRune(r)
l.emit(Wrapper)
return lex
case r == '"' || r == '\'' || r == '`':
canEscape := r != '`'
return lexStrStart(l, r, makeLexStr(r, canEscape))
default:
l.bufferRune(r)
return lexIdentifier
}
}
func lexIdentifier(l *Lexer) lexerFn {
r, err := l.readRune()
if err != nil {
l.emit(Identifier)
l.emitErr(err)
return nil
}
if strings.ContainsRune(identifierSepSet, r) {
l.emit(Identifier)
return lexSingleRune(l, r)
}
l.bufferRune(r)
return lexIdentifier
}
func lexLineComment(l *Lexer) lexerFn {
r, err := l.readRune()
if err != nil {
l.emitErr(err)
return nil
}
if r == '\n' {
return lex
}
return lexLineComment
}
// assumes the starting / has been read already
func lexBlockComment(l *Lexer) lexerFn {
depth := 1
var recurse lexerFn
recurse = func(l *Lexer) lexerFn {
r, err := l.readRune()
if err != nil {
l.emitErr(err)
return nil
}
n, _ := l.peekRune()
if r == '/' && n == '*' {
depth++
} else if r == '*' && n == '/' {
depth--
}
if depth == 0 {
return lexSkipThen(lex)
}
return recurse
}
return recurse
}
func lexStrStart(lexer *Lexer, r rune, then lexerFn) lexerFn {
lexer.bufferRune(r)
return then
}
func makeLexStr(quoteC rune, canEscape bool) lexerFn {
var fn lexerFn
fn = func(l *Lexer) lexerFn {
r, n, err := l.readAndPeek()
if err != nil {
if err == io.EOF {
if r == quoteC {
l.bufferRune(r)
l.emit(String)
l.emitErr(err)
return nil
}
l.emitErr(errors.New("expected end of string, got end of file"))
return nil
}
}
if canEscape && r == '\\' && n == quoteC {
l.bufferRune(r)
l.bufferRune(n)
return lexSkipThen(fn)
}
l.bufferRune(r)
if r == quoteC {
l.emit(String)
return lex
}
return fn
}
return fn
}
func lexSkipThen(then lexerFn) lexerFn {
return func(l *Lexer) lexerFn {
if _, err := l.readRune(); err != nil {
l.emitErr(err)
return nil
}
return then
}
}

View File

@ -1,82 +0,0 @@
package lexer
import (
"bytes"
. "testing"
"github.com/stretchr/testify/assert"
"github.com/stretchr/testify/require"
)
var lexTestSrc = `
// this is a comment
// // this is also a comment
a
anIdentifier
1
100
1.5
1.5e9
/*
some stuff
*/
/* this should actually work */
/*/
/*
nested!
/*
wtf this is crazy
*/
*/
(punctuation,is{cool}> )
-tab
"this is a string", "and so is this one"
"\"foo"
"bar\"baz\""
"buz\0"
`
func TestLex(t *T) {
l := New(bytes.NewBufferString(lexTestSrc))
assertNext := func(typ TokenType, val string, row, col int) {
t.Logf("asserting %s %q [row:%d col:%d]", typ, val, row, col)
require.True(t, l.HasNext())
tok := l.Next()
assert.Equal(t, typ, tok.TokenType)
assert.Equal(t, val, tok.Val)
assert.Equal(t, row, tok.Row)
assert.Equal(t, col, tok.Col)
}
assertNext(Identifier, "a", 3, 2)
assertNext(Identifier, "anIdentifier", 4, 2)
assertNext(Identifier, "1", 5, 2)
assertNext(Identifier, "100", 6, 2)
assertNext(Identifier, "1.5", 7, 2)
assertNext(Identifier, "1.5e9", 8, 2)
assertNext(Wrapper, "(", 24, 2)
assertNext(Identifier, "punctuation", 24, 3)
assertNext(Punctuation, ",", 24, 14)
assertNext(Identifier, "is", 24, 15)
assertNext(Wrapper, "{", 24, 17)
assertNext(Identifier, "cool", 24, 18)
assertNext(Wrapper, "}", 24, 22)
assertNext(Punctuation, ">", 24, 23)
assertNext(Wrapper, ")", 24, 25)
assertNext(Identifier, "-tab", 25, 2)
assertNext(String, `"this is a string"`, 27, 2)
assertNext(Punctuation, ",", 27, 20)
assertNext(String, `"and so is this one"`, 27, 22)
assertNext(String, `"\"foo"`, 28, 2)
assertNext(String, `"bar\"baz\""`, 29, 2)
assertNext(String, `"buz\0"`, 30, 2)
assertNext(EOF, "EOF", 31, 0)
assert.False(t, l.HasNext())
}