1
0
mirror of https://github.com/alecthomas/chroma.git synced 2025-01-28 03:29:41 +02:00
chroma/mutators.go
Alec Thomas cc2dd5b8ad Version 2 of Chroma
This cleans up the API in general, removing a bunch of deprecated stuff,
cleaning up circular imports, etc.

But the biggest change is switching to an optional XML format for the
regex lexer.

Having lexers defined only in Go is not ideal for a couple of reasons.
Firstly, it impedes a significant portion of contributors who use Chroma
in Hugo, but don't know Go. Secondly, it bloats the binary size of any
project that imports Chroma.

Why XML? YAML is an abomination and JSON is not human editable. XML
also compresses very well (eg. Go template lexer XML compresses from
3239 bytes to 718).

Why a new syntax format? All major existing formats rely on the
Oniguruma regex engine, which is extremely complex and for which there
is no Go port.

Why not earlier? Prior to the existence of fs.FS this was not a viable
option.

Benchmarks:

    $ hyperfine --warmup 3 \
        './chroma.master --version' \
        './chroma.xml-pre-opt --version' \
        './chroma.xml --version'
    Benchmark 1: ./chroma.master --version
      Time (mean ± σ):       5.3 ms ±   0.5 ms    [User: 3.6 ms, System: 1.4 ms]
      Range (min … max):     4.2 ms …   6.6 ms    233 runs

    Benchmark 2: ./chroma.xml-pre-opt --version
      Time (mean ± σ):      50.6 ms ±   0.5 ms    [User: 52.4 ms, System: 3.6 ms]
      Range (min … max):    49.2 ms …  51.5 ms    51 runs

    Benchmark 3: ./chroma.xml --version
      Time (mean ± σ):       6.9 ms ±   1.1 ms    [User: 5.1 ms, System: 1.5 ms]
      Range (min … max):     5.7 ms …  19.9 ms    196 runs

    Summary
      './chroma.master --version' ran
        1.30 ± 0.23 times faster than './chroma.xml --version'
        9.56 ± 0.83 times faster than './chroma.xml-pre-opt --version'

A slight increase in init time, but I think this is okay given the
increase in flexibility.

And binary size difference:

    $ du -h lexers.test*
    $ du -sh chroma*                                                                                                                                                                                                                                                                                                                                                                                                                                                             951371ms
    8.8M	chroma.master
    7.8M	chroma.xml
    7.8M	chroma.xml-pre-opt

Benchmarks:

    $ hyperfine --warmup 3 \
        './chroma.master --version' \
        './chroma.xml-pre-opt --version' \
        './chroma.xml --version'
    Benchmark 1: ./chroma.master --version
      Time (mean ± σ):       5.3 ms ±   0.5 ms    [User: 3.6 ms, System: 1.4 ms]
      Range (min … max):     4.2 ms …   6.6 ms    233 runs

    Benchmark 2: ./chroma.xml-pre-opt --version
      Time (mean ± σ):      50.6 ms ±   0.5 ms    [User: 52.4 ms, System: 3.6 ms]
      Range (min … max):    49.2 ms …  51.5 ms    51 runs

    Benchmark 3: ./chroma.xml --version
      Time (mean ± σ):       6.9 ms ±   1.1 ms    [User: 5.1 ms, System: 1.5 ms]
      Range (min … max):     5.7 ms …  19.9 ms    196 runs

    Summary
      './chroma.master --version' ran
        1.30 ± 0.23 times faster than './chroma.xml --version'
        9.56 ± 0.83 times faster than './chroma.xml-pre-opt --version'

Incompatible changes:

- (*RegexLexer).SetAnalyser: changed from func(func(text string) float32) *RegexLexer to func(func(text string) float32) Lexer
- (*TokenType).UnmarshalJSON: removed
- Lexer.AnalyseText: added
- Lexer.SetAnalyser: added
- Lexer.SetRegistry: added
- MustNewLazyLexer: removed
- MustNewLexer: changed from func(*Config, Rules) *RegexLexer to func(*Config, func() Rules) *RegexLexer
- Mutators: changed from func(...Mutator) MutatorFunc to func(...Mutator) Mutator
- NewLazyLexer: removed
- NewLexer: changed from func(*Config, Rules) (*RegexLexer, error) to func(*Config, func() Rules) (*RegexLexer, error)
- Pop: changed from func(int) MutatorFunc to func(int) Mutator
- Push: changed from func(...string) MutatorFunc to func(...string) Mutator
- TokenType.MarshalJSON: removed
- Using: changed from func(Lexer) Emitter to func(string) Emitter
- UsingByGroup: changed from func(func(string) Lexer, int, int, ...Emitter) Emitter to func(int, int, ...Emitter) Emitter
2022-01-27 15:22:00 +11:00

202 lines
4.9 KiB
Go

package chroma
import (
"encoding/xml"
"fmt"
"strings"
)
// A Mutator modifies the behaviour of the lexer.
type Mutator interface {
// Mutate the lexer state machine as it is processing.
Mutate(state *LexerState) error
}
// SerialisableMutator is a Mutator that can be serialised and deserialised.
type SerialisableMutator interface {
Mutator
MutatorKind() string
}
// A LexerMutator is an additional interface that a Mutator can implement
// to modify the lexer when it is compiled.
type LexerMutator interface {
// MutateLexer can be implemented to mutate the lexer itself.
//
// Rules are the lexer rules, state is the state key for the rule the mutator is associated with.
MutateLexer(rules CompiledRules, state string, rule int) error
}
// A MutatorFunc is a Mutator that mutates the lexer state machine as it is processing.
type MutatorFunc func(state *LexerState) error
func (m MutatorFunc) Mutate(state *LexerState) error { return m(state) } // nolint
type multiMutator struct {
Mutators []Mutator `xml:"mutator"`
}
func (m *multiMutator) UnmarshalXML(d *xml.Decoder, start xml.StartElement) error {
for {
token, err := d.Token()
if err != nil {
return err
}
switch token := token.(type) {
case xml.StartElement:
mutator, err := unmarshalMutator(d, token)
if err != nil {
return err
}
m.Mutators = append(m.Mutators, mutator)
case xml.EndElement:
return nil
}
}
}
func (m *multiMutator) MarshalXML(e *xml.Encoder, start xml.StartElement) error {
name := xml.Name{Local: "mutators"}
if err := e.EncodeToken(xml.StartElement{Name: name}); err != nil {
return err
}
for _, m := range m.Mutators {
if err := marshalMutator(e, m); err != nil {
return err
}
}
return e.EncodeToken(xml.EndElement{Name: name})
}
func (m *multiMutator) MutatorKind() string { return "multiple" }
func (m *multiMutator) Mutate(state *LexerState) error {
for _, modifier := range m.Mutators {
if err := modifier.Mutate(state); err != nil {
return err
}
}
return nil
}
// Mutators applies a set of Mutators in order.
func Mutators(modifiers ...Mutator) Mutator {
return &multiMutator{modifiers}
}
type includeMutator struct {
State string `xml:"state,attr"`
}
// Include the given state.
func Include(state string) Rule {
return Rule{Mutator: &includeMutator{state}}
}
func (i *includeMutator) MutatorKind() string { return "include" }
func (i *includeMutator) Mutate(s *LexerState) error {
return fmt.Errorf("should never reach here Include(%q)", i.State)
}
func (i *includeMutator) MutateLexer(rules CompiledRules, state string, rule int) error {
includedRules, ok := rules[i.State]
if !ok {
return fmt.Errorf("invalid include state %q", i.State)
}
rules[state] = append(rules[state][:rule], append(includedRules, rules[state][rule+1:]...)...)
return nil
}
type combinedMutator struct {
States []string `xml:"state,attr"`
}
func (c *combinedMutator) MutatorKind() string { return "combined" }
// Combined creates a new anonymous state from the given states, and pushes that state.
func Combined(states ...string) Mutator {
return &combinedMutator{states}
}
func (c *combinedMutator) Mutate(s *LexerState) error {
return fmt.Errorf("should never reach here Combined(%v)", c.States)
}
func (c *combinedMutator) MutateLexer(rules CompiledRules, state string, rule int) error {
name := "__combined_" + strings.Join(c.States, "__")
if _, ok := rules[name]; !ok {
combined := []*CompiledRule{}
for _, state := range c.States {
rules, ok := rules[state]
if !ok {
return fmt.Errorf("invalid combine state %q", state)
}
combined = append(combined, rules...)
}
rules[name] = combined
}
rules[state][rule].Mutator = Push(name)
return nil
}
type pushMutator struct {
States []string `xml:"state,attr"`
}
func (p *pushMutator) MutatorKind() string { return "push" }
func (p *pushMutator) Mutate(s *LexerState) error {
if len(p.States) == 0 {
s.Stack = append(s.Stack, s.State)
} else {
for _, state := range p.States {
if state == "#pop" {
s.Stack = s.Stack[:len(s.Stack)-1]
} else {
s.Stack = append(s.Stack, state)
}
}
}
return nil
}
// Push states onto the stack.
func Push(states ...string) Mutator {
return &pushMutator{states}
}
type popMutator struct {
Depth int `xml:"depth,attr"`
}
func (p *popMutator) MutatorKind() string { return "pop" }
func (p *popMutator) Mutate(state *LexerState) error {
if len(state.Stack) == 0 {
return fmt.Errorf("nothing to pop")
}
state.Stack = state.Stack[:len(state.Stack)-p.Depth]
return nil
}
// Pop state from the stack when rule matches.
func Pop(n int) Mutator {
return &popMutator{n}
}
// Default returns a Rule that applies a set of Mutators.
func Default(mutators ...Mutator) Rule {
return Rule{Mutator: Mutators(mutators...)}
}
// Stringify returns the raw string for a set of tokens.
func Stringify(tokens ...Token) string {
out := []string{}
for _, t := range tokens {
out = append(out, t.Value)
}
return strings.Join(out, "")
}