6 Commits

Author SHA1 Message Date
amery ff03ee922d lexer: introduce Error{}
Signed-off-by: Alejandro Mery <amery@jpi.io>
2023-08-29 02:41:48 +00:00
amery 868786cb9f lexer: introduce a Position (Line, Column) handler
Signed-off-by: Alejandro Mery <amery@jpi.io>
2023-08-29 02:10:46 +00:00
amery 3e964d1455 lexer: introduce StateFn and the basic state machine loop
Signed-off-by: Alejandro Mery <amery@jpi.io>
2023-08-29 02:10:03 +00:00
amery 530eff87e9 lexer: introduce Reader.Accept()/AcceptAll()
Signed-off-by: Alejandro Mery <amery@jpi.io>
2023-08-29 02:10:03 +00:00
amery c3339a2cdb build-sys: import build system from darvaza.org/core
Signed-off-by: Alejandro Mery <amery@jpi.io>
2023-08-29 02:03:53 +00:00
amery 5e3171d891 Merge branch 'pr-amery-reader' 2023-08-29 02:03:36 +00:00
7 changed files with 28 additions and 215 deletions
-77
View File
@@ -1,78 +1 @@
# asciigoat's core library
[![Go Reference][godoc-badge]][godoc]
[![Go Report Card][goreport-badge]][goreport]
This package contains the basics for writing simple parsers of
text languages heavily inspired by
[Rob Pike](https://en.wikipedia.org/wiki/Rob_Pike)'s talk on
[Lexical Scanning in Go](https://go.dev/talks/2011/lex.slide#1) in 2011 which
you can [watch online](https://www.youtube.com/watch?v=HxaD_trXwRE) to get
better understanding of the ideas behind **asciigoat**.
**asciigoat** is [MIT](https://opensource.org/license/mit/) licensed.
[godoc]: https://pkg.go.dev/asciigoat.org/core
[godoc-badge]: https://pkg.go.dev/badge/asciigoat.org/core.svg
[goreport]: https://goreportcard.com/report/asciigoat.org/core
[goreport-badge]: https://goreportcard.com/badge/asciigoat.org/core
[godoc-lexer-reader]: https://pkg.go.dev/asciigoat.org/core/lexer#Reader
[godoc-readcloser]: https://pkg.go.dev/asciigoat.org/core#ReadCloser
## Lexer
### lexer.Reader
The lexer package provides [`lexer.Reader`][godoc-lexer-reader] which is
actually an [`io.RuneScanner`](https://pkg.go.dev/io#RuneScanner)
that buffers accepted runes until you are ready to
[emit](https://pkg.go.dev/asciigoat.org/core/lexer#Reader.Emit) or
[discard](https://pkg.go.dev/asciigoat.org/core/lexer#Reader.Discard).
### lexer.Position
[`lexer.Position`](https://pkg.go.dev/asciigoat.org/core/lexer#Position)
is a `(Line, Column)` pair with methods to facilitate tracking
your position on the source [Reader](https://pkg.go.dev/io#Reader).
### lexer.Error
[`lexer.Error`](https://pkg.go.dev/asciigoat.org/core/lexer#Error)
is an [unwrappable](https://pkg.go.dev/errors#Unwrap) error with a
token position and hint attached.
### lexer.StateFn
At the heart of **asciigoat** we have _state functions_ as proposed on [Rob Pike's famous talk](https://www.youtube.com/watch?v=HxaD_trXwRE) which return the next _state function_ parsing is done.
Additionally there is a [`Run()`](https://pkg.go.dev/asciigoat.org/lexer#Run) helper that implements the loop.
### rune checkers
_Rune checkers_ are simple functions that tell if a rune is of a class or it's not.
Fundamental checkers are provided by the [`unicode` package](https://pkg.go.dev/unicode).
Our [`lexer.Reader`][godoc-lexer-reader] uses them on its `Accept()` and `AcceptAll()` methods to
make it easier to consume the _source_ document.
To facilitate the declaration of _rune classes_ in the context of **asciigoat** powered parsers we include
a series of rune checker factories.
* `NewIsIn(string)`
* `NewIsInRunes(...rune)`
* `NewIsNot(checker)`
* `NewIsOneOf(...checker)`
## Others
### ReadCloser
[ReadCloser][godoc-readcloser] assists in providing a
[io.Closer](https://pkg.go.dev/io#Closer) to Readers or buffers without on,
or unearthing one if available so
[io.ReadCloser](https://pkg.go.dev/io#ReadCloser) can be fulfilled.
## See also
* [asciigoat.org/ini](https://asciigoat.org/ini)
* [oss.jpi.io](https://oss.jpi.io)
+3 -4
View File
@@ -6,17 +6,16 @@ require github.com/mgechev/revive v1.3.3
require (
github.com/BurntSushi/toml v1.3.2 // indirect
github.com/chavacava/garif v0.1.0 // indirect
github.com/chavacava/garif v0.0.0-20230608123814-4bd63c2919ab // indirect
github.com/fatih/color v1.15.0 // indirect
github.com/fatih/structtag v1.2.0 // indirect
github.com/mattn/go-colorable v0.1.13 // indirect
github.com/mattn/go-isatty v0.0.19 // indirect
github.com/mattn/go-runewidth v0.0.15 // indirect
github.com/mattn/go-isatty v0.0.17 // indirect
github.com/mattn/go-runewidth v0.0.9 // indirect
github.com/mgechev/dots v0.0.0-20210922191527-e955255bf517 // indirect
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
github.com/rivo/uniseg v0.4.4 // indirect
golang.org/x/sys v0.11.0 // indirect
golang.org/x/tools v0.12.0 // indirect
)
+5 -10
View File
@@ -1,7 +1,7 @@
github.com/BurntSushi/toml v1.3.2 h1:o7IhLm0Msx3BaB+n3Ag7L8EVlByGnpq14C4YWiu/gL8=
github.com/BurntSushi/toml v1.3.2/go.mod h1:CxXYINrC8qIiEnFrOxCa7Jy5BFHlXnUU2pbicEuybxQ=
github.com/chavacava/garif v0.1.0 h1:2JHa3hbYf5D9dsgseMKAmc/MZ109otzgNFk5s87H9Pc=
github.com/chavacava/garif v0.1.0/go.mod h1:XMyYCkEL58DF0oyW4qDjjnPWONs2HBqYKI+UIPD+Gww=
github.com/chavacava/garif v0.0.0-20230608123814-4bd63c2919ab h1:5JxePczlyGAtj6R1MUEFZ/UFud6FfsOejq7xLC2ZIb0=
github.com/chavacava/garif v0.0.0-20230608123814-4bd63c2919ab/go.mod h1:XMyYCkEL58DF0oyW4qDjjnPWONs2HBqYKI+UIPD+Gww=
github.com/davecgh/go-spew v1.1.0/go.mod h1:J7Y8YcW2NihsgmVo/mv3lAwl/skON4iLHjSsI+c5H38=
github.com/davecgh/go-spew v1.1.1 h1:vj9j/u1bqnvCEfJOwUhtlOARqs3+rkHYY13jYWTU97c=
github.com/davecgh/go-spew v1.1.1/go.mod h1:J7Y8YcW2NihsgmVo/mv3lAwl/skON4iLHjSsI+c5H38=
@@ -12,11 +12,10 @@ github.com/fatih/structtag v1.2.0/go.mod h1:mBJUNpUnHmRKrKlQQlmCrh5PuhftFbNv8Ys4
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 v0.0.19 h1:JITubQf0MOLdlGRuRq+jtsDlekdYPia9ZFsB8h/APPA=
github.com/mattn/go-isatty v0.0.19/go.mod h1:W+V8PltTTMOvKvAeJH7IuucS94S2C6jfK/D7dTCTo3Y=
github.com/mattn/go-isatty v0.0.17 h1:BTarxUcIeDqL27Mc+vyvdWYSL28zpIhv3RoTdsLMPng=
github.com/mattn/go-isatty v0.0.17/go.mod h1:kYGgaQfpe5nmfYZH+SKPsOc2e4SrIfOl2e/yFXSvRLM=
github.com/mattn/go-runewidth v0.0.9 h1:Lm995f3rfxdpd6TSmuVCHVb/QhupuXlYr8sCI/QdE+0=
github.com/mattn/go-runewidth v0.0.9/go.mod h1:H031xJmbD/WCDINGzjvQ9THkh0rPKHF+m2gUSrubnMI=
github.com/mattn/go-runewidth v0.0.15 h1:UNAjwbU9l54TA3KzvqLGxwWjHmMgBUVhBiTjelZgg3U=
github.com/mattn/go-runewidth v0.0.15/go.mod h1:Jdepj2loyihRzMpdS35Xk/zdY8IAYHsh153qUoGf23w=
github.com/mgechev/dots v0.0.0-20210922191527-e955255bf517 h1:zpIH83+oKzcpryru8ceC6BxnoG8TBrhgAvRg8obzup0=
github.com/mgechev/dots v0.0.0-20210922191527-e955255bf517/go.mod h1:KQ7+USdGKfpPjXk4Ga+5XxQM4Lm4e3gAogrreFAYpOg=
github.com/mgechev/revive v1.3.3 h1:GUWzV3g185agbHN4ZdaQvR6zrLVYTUSA2ktvIinivK0=
@@ -29,9 +28,6 @@ github.com/pkg/errors v0.9.1 h1:FEBLx1zS214owpjy7qsBeixbURkuhQAwrK5UwLGTwt4=
github.com/pkg/errors v0.9.1/go.mod h1:bwawxfHBFNV+L2hUp1rHADufV3IMtnDRdf1r5NINEl0=
github.com/pmezard/go-difflib v1.0.0 h1:4DBwDE0NGyQoBHbLQYPwSUPoCMWR5BEzIk/f1lZbAQM=
github.com/pmezard/go-difflib v1.0.0/go.mod h1:iKH77koFhYxTK1pcRnkKkqfTogsbg7gZNVY4sRDYZ/4=
github.com/rivo/uniseg v0.2.0/go.mod h1:J6wj4VEh+S6ZtnVlnTBMWIodfgj8LQOQFoIToxlJtxc=
github.com/rivo/uniseg v0.4.4 h1:8TfxU8dW6PdqD27gjM8MVNuicgxIjxpm4K7x4jp8sis=
github.com/rivo/uniseg v0.4.4/go.mod h1:FN3SvrM+Zdj16jyLfmOkMNblXMcoc8DfTHruCPUcx88=
github.com/stretchr/objx v0.1.0/go.mod h1:HFkY916IF+rwdDfMAkV7OtwuqBVzrE8GR6GFx+wExME=
github.com/stretchr/objx v0.4.0/go.mod h1:YvHI0jy2hoMjB+UWwv71VJQ9isScKT/TqJzVSSt89Yw=
github.com/stretchr/objx v0.5.0/go.mod h1:Yh+to48EsGEfYuaHDzXPcE3xhTkx73EhmCGUpEOglKo=
@@ -41,7 +37,6 @@ github.com/stretchr/testify v1.8.4 h1:CcVxjf3Q8PM0mHUKJCdn+eZZtm5yQwehR5yeSVQQcU
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/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=
golang.org/x/sys v0.11.0/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
golang.org/x/tools v0.12.0 h1:YW6HUoUmYBpwSgyaGaZq1fHjrBjX1rlpZ54T6mu2kss=
+5 -30
View File
@@ -1,7 +1,6 @@
package lexer
import (
"errors"
"fmt"
"strings"
)
@@ -10,14 +9,6 @@ var (
_ error = (*Error)(nil)
)
var (
// ErrUnacceptableRune indicates the read rune isn't acceptable in the context
ErrUnacceptableRune = errors.New("rune not acceptable in context")
// ErrNotImplemented indicates something hasn't been implemented yet
ErrNotImplemented = errors.New("not implemented")
)
// Error represents a generic parsing error
type Error struct {
Filename string
@@ -25,29 +16,17 @@ type Error struct {
Column int
Content string
Hint string
Err error
}
func (err Error) prefix() string {
switch {
case err.Line > 0 || err.Column > 0:
if err.Filename != "" {
return fmt.Sprintf("%s:%v:%v", err.Filename, err.Line, err.Column)
}
return fmt.Sprintf("%v:%v", err.Line, err.Column)
default:
return err.Filename
}
}
func (err Error) Error() string {
var s []string
prefix := err.prefix()
if prefix != "" {
s = append(s, prefix)
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 {
@@ -58,10 +37,6 @@ func (err Error) Error() string {
s = append(s, fmt.Sprintf("%q", err.Content))
}
if err.Hint != "" {
s = append(s, err.Hint)
}
return strings.Join(s, ": ")
}
+3 -17
View File
@@ -1,31 +1,17 @@
// Package lexer provides basic helpers to implement parsers
package lexer
import (
"errors"
"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 {
for fn != nil {
var err error
var err error
for fn != nil && err == nil {
fn, err = fn()
switch {
case errors.Is(err, io.EOF):
// EOF
return nil
case err != nil:
// failed
return err
}
}
// ended
return nil
return err
}
+12 -30
View File
@@ -41,46 +41,28 @@ func (p *Position) Step() {
p.Column++
}
// StepN moves the column N places forward
func (p *Position) StepN(n int) {
// Next returns a new Position one rune forward
// on the line
func (p Position) Next() Position {
if p.Line == 0 {
p.Reset()
}
switch {
case n > 0:
p.Column += n
default:
panic(fmt.Errorf("invalid %v increment", n))
return Position{
Line: p.Line,
Column: p.Column + 1,
}
}
// StepLine moves position to the start of the next line
func (p *Position) StepLine() {
// NextLine returns a new Position at the begining of the next
// line.
func (p Position) NextLine() Position {
if p.Line == 0 {
p.Reset()
}
p.Line++
p.Column = 1
}
// Add adds a relative position considering
// potential new lines
func (p *Position) Add(rel Position) {
if p.Line == 0 {
p.Reset()
}
switch {
case rel.Line == 0:
// nothing
case rel.Line > 1:
// includes new lines
p.Line += rel.Line - 1
p.Column = rel.Column
default:
// same line
p.Column += rel.Column - 1
return Position{
Line: p.Line + 1,
Column: 1,
}
}
-47
View File
@@ -1,47 +0,0 @@
package lexer
import (
"strings"
"unicode"
)
// NewIsNot generates a rune condition checker that reverses the
// decision of the given checker.
func NewIsNot(cond func(rune) bool) func(rune) bool {
return func(r rune) bool {
return !cond(r)
}
}
// NewIsIn generates a rune condition checker that accepts runes
// contained on the provided string
func NewIsIn(s string) func(rune) bool {
return func(r rune) bool {
return strings.ContainsRune(s, r)
}
}
// NewIsInRunes generates a rune condition checker that accepts
// the runes specified
func NewIsInRunes(s ...rune) func(rune) bool {
return NewIsIn(string(s))
}
// NewIsOneOf generates a run condition checker that accepts runes
// accepted by any of the given checkers
func NewIsOneOf(s ...func(rune) bool) func(rune) bool {
return func(r rune) bool {
for _, cond := range s {
if cond(r) {
return true
}
}
return false
}
}
// IsSpace reports whether the rune is a space character as
// defined by Unicode's White Space property
func IsSpace(r rune) bool {
return unicode.IsSpace(r)
}