mirror of
https://github.com/alecthomas/chroma.git
synced 2025-02-09 13:23:51 +02:00
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
95 lines
2.1 KiB
Go
95 lines
2.1 KiB
Go
package chroma
|
|
|
|
type remappingLexer struct {
|
|
lexer Lexer
|
|
mapper func(Token) []Token
|
|
}
|
|
|
|
// RemappingLexer remaps a token to a set of, potentially empty, tokens.
|
|
func RemappingLexer(lexer Lexer, mapper func(Token) []Token) Lexer {
|
|
return &remappingLexer{lexer, mapper}
|
|
}
|
|
|
|
func (r *remappingLexer) AnalyseText(text string) float32 {
|
|
return r.lexer.AnalyseText(text)
|
|
}
|
|
|
|
func (r *remappingLexer) SetAnalyser(analyser func(text string) float32) Lexer {
|
|
r.lexer.SetAnalyser(analyser)
|
|
return r
|
|
}
|
|
|
|
func (r *remappingLexer) SetRegistry(registry *LexerRegistry) Lexer {
|
|
r.lexer.SetRegistry(registry)
|
|
return r
|
|
}
|
|
|
|
func (r *remappingLexer) Config() *Config {
|
|
return r.lexer.Config()
|
|
}
|
|
|
|
func (r *remappingLexer) Tokenise(options *TokeniseOptions, text string) (Iterator, error) {
|
|
it, err := r.lexer.Tokenise(options, text)
|
|
if err != nil {
|
|
return nil, err
|
|
}
|
|
var buffer []Token
|
|
return func() Token {
|
|
for {
|
|
if len(buffer) > 0 {
|
|
t := buffer[0]
|
|
buffer = buffer[1:]
|
|
return t
|
|
}
|
|
t := it()
|
|
if t == EOF {
|
|
return t
|
|
}
|
|
buffer = r.mapper(t)
|
|
}
|
|
}, nil
|
|
}
|
|
|
|
// TypeMapping defines type maps for the TypeRemappingLexer.
|
|
type TypeMapping []struct {
|
|
From, To TokenType
|
|
Words []string
|
|
}
|
|
|
|
// TypeRemappingLexer remaps types of tokens coming from a parent Lexer.
|
|
//
|
|
// eg. Map "defvaralias" tokens of type NameVariable to NameFunction:
|
|
//
|
|
// mapping := TypeMapping{
|
|
// {NameVariable, NameFunction, []string{"defvaralias"},
|
|
// }
|
|
// lexer = TypeRemappingLexer(lexer, mapping)
|
|
func TypeRemappingLexer(lexer Lexer, mapping TypeMapping) Lexer {
|
|
// Lookup table for fast remapping.
|
|
lut := map[TokenType]map[string]TokenType{}
|
|
for _, rt := range mapping {
|
|
km, ok := lut[rt.From]
|
|
if !ok {
|
|
km = map[string]TokenType{}
|
|
lut[rt.From] = km
|
|
}
|
|
if len(rt.Words) == 0 {
|
|
km[""] = rt.To
|
|
} else {
|
|
for _, k := range rt.Words {
|
|
km[k] = rt.To
|
|
}
|
|
}
|
|
}
|
|
return RemappingLexer(lexer, func(t Token) []Token {
|
|
if k, ok := lut[t.Type]; ok {
|
|
if tt, ok := k[t.Value]; ok {
|
|
t.Type = tt
|
|
} else if tt, ok := k[""]; ok {
|
|
t.Type = tt
|
|
}
|
|
}
|
|
return []Token{t}
|
|
})
|
|
}
|