5 Commits

Author SHA1 Message Date
amery 4d0d4ffb4f build-sys: import build system from darvaza.org/core
Signed-off-by: Alejandro Mery <amery@jpi.io>
2023-08-28 23:03:04 +00:00
amery be11c6985d Merge branch 'pr-amery-lexer' into next-amery 2023-08-28 23:02:54 +00:00
amery 48b75ec3c3 lexer: introduce a Position (Line, Column) handler
Signed-off-by: Alejandro Mery <amery@jpi.io>
2023-08-28 23:02:37 +00:00
amery a4124fb3e1 lexer: introduce Accept()/AcceptAll() helpers
Signed-off-by: Alejandro Mery <amery@jpi.io>
2023-08-28 22:36:29 +00:00
amery d760902dce lexer: introduce StateFn and the basic state machine loop
Signed-off-by: Alejandro Mery <amery@jpi.io>
2023-08-28 22:36:26 +00:00
5 changed files with 69 additions and 100 deletions
-45
View File
@@ -1,45 +0,0 @@
package lexer
import (
"fmt"
"strings"
)
var (
_ error = (*Error)(nil)
)
// Error represents a generic parsing error
type Error struct {
Filename string
Line int
Column int
Content string
Err error
}
func (err Error) Error() string {
var s []string
switch {
case err.Line > 0 || err.Column > 0:
s = append(s, fmt.Sprintf("%s:%v:%v", err.Filename, err.Line, err.Column))
case err.Filename != "":
s = append(s, err.Filename)
}
if err.Err != nil {
s = append(s, err.Err.Error())
}
if err.Content != "" {
s = append(s, fmt.Sprintf("%q", err.Content))
}
return strings.Join(s, ": ")
}
func (err Error) Unwrap() error {
return err.Err
}
+52
View File
@@ -1,2 +1,54 @@
// Package lexer provides basic helpers to implement parsers // Package lexer provides basic helpers to implement parsers
package lexer package lexer
import "io"
// StateFn is a State Function of the parser
type StateFn func() (StateFn, error)
// Run runs a state machine until the state function either
// returns nil or an error
func Run(fn StateFn) error {
var err error
for fn != nil && err == nil {
fn, err = fn()
}
return err
}
// Accept consumes a rune from the source if it meets the condition.
// it returns true if the condition was met and false if it wasn't.
func Accept(src io.RuneScanner, cond func(r rune) bool) bool {
r, _, err := src.ReadRune()
switch {
case err != nil:
return false
case cond(r):
return true
default:
_ = src.UnreadRune()
return false
}
}
// AcceptAll consumes runes from the source as long as they meet the
// condition. it returns true if the condition was met for at least one rune,
// and false if it wasn't.
func AcceptAll(src io.RuneScanner, cond func(r rune) bool) bool {
var accepted bool
for {
r, _, err := src.ReadRune()
switch {
case err != nil:
return accepted
case cond(r):
accepted = true
default:
_ = src.UnreadRune()
return accepted
}
}
}
+13 -11
View File
@@ -41,26 +41,28 @@ func (p *Position) Step() {
p.Column++ p.Column++
} }
// StepN moves the column N places forward // Next returns a new Position one rune forward
func (p *Position) StepN(n int) { // on the line
func (p Position) Next() Position {
if p.Line == 0 { if p.Line == 0 {
p.Reset() p.Reset()
} }
switch { return Position{
case n > 0: Line: p.Line,
p.Column += n Column: p.Column + 1,
default:
panic(fmt.Errorf("invalid %v increment", n))
} }
} }
// StepLine moves position to the start of the next line // NextLine returns a new Position at the begining of the next
func (p *Position) StepLine() { // line.
func (p Position) NextLine() Position {
if p.Line == 0 { if p.Line == 0 {
p.Reset() p.Reset()
} }
p.Line++ return Position{
p.Column = 1 Line: p.Line + 1,
Column: 1,
}
} }
+2
View File
@@ -0,0 +1,2 @@
// Package runes helps us work with runes
package runes
+2 -44
View File
@@ -1,8 +1,7 @@
package lexer package runes
import ( import (
"bytes" "bytes"
"errors"
"io" "io"
"strings" "strings"
"unicode/utf8" "unicode/utf8"
@@ -19,14 +18,7 @@ const (
// implemented interfaces // implemented interfaces
var ( var (
_ io.RuneReader = (*Reader)(nil) _ io.RuneReader = (*Reader)(nil)
_ io.RuneScanner = (*Reader)(nil)
)
var (
// ErrInvalidUnreadRune indicates UnreadRune() was calls after an
// action other than a successful ReadRune()
ErrInvalidUnreadRune = errors.New("invalid UnreadRune() call")
) )
// Reader is a RuneReader aimed at implementing text parsers // Reader is a RuneReader aimed at implementing text parsers
@@ -36,8 +28,6 @@ type Reader struct {
buf []byte buf []byte
off int off int
cursor int cursor int
lastRuneSize int
} }
// String returns what's already Read but not yet emitted or discarded // String returns what's already Read but not yet emitted or discarded
@@ -64,9 +54,6 @@ func (b *Reader) Discard() {
// step // step
b.off = b.cursor b.off = b.cursor
} }
// and prevent UnreadRune()
b.lastRuneSize = -1
} }
// ready tells how many bytes are ready to decode // ready tells how many bytes are ready to decode
@@ -152,8 +139,6 @@ func (b *Reader) ReadRune() (rune, int, error) {
for { for {
err := b.needsBytes(count) err := b.needsBytes(count)
if err != nil { if err != nil {
b.lastRuneSize = -1
return 0, 0, err return 0, 0, err
} }
@@ -168,36 +153,9 @@ func (b *Reader) ReadRune() (rune, int, error) {
// decode rune // decode rune
r, l := utf8.DecodeRune(b.buf[b.cursor:]) r, l := utf8.DecodeRune(b.buf[b.cursor:])
// step over
b.cursor += l
// and remember for UnreadRune()
b.lastRuneSize = l
return r, l, nil return r, l, nil
} }
// UnreadRune moves the cursor where it was before the last call to ReadRune
func (b *Reader) UnreadRune() error {
if b.lastRuneSize > 0 {
b.cursor -= b.lastRuneSize
b.lastRuneSize = -1
return nil
}
return ErrInvalidUnreadRune
}
// PeekRune returns information about the next rune without moving the
// cursor
func (b *Reader) PeekRune() (rune, int, error) {
r, l, err := b.ReadRune()
if err != nil {
return r, l, err
}
err = b.UnreadRune()
return r, l, err
}
// NewReader creates a new runes [Reader] using the given [io.Reader] // NewReader creates a new runes [Reader] using the given [io.Reader]
func NewReader(r io.Reader) *Reader { func NewReader(r io.Reader) *Reader {
if r == nil { if r == nil {