/usr/share/gocode/src/github.com/alecthomas/chroma/regexp.go is in golang-github-alecthomas-chroma-dev 0.4.0+git20180402.51d250f-1.
This file is owned by root:root, with mode 0o644.
The actual contents of the file can be viewed below.
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 | package chroma
import (
"fmt"
"os"
"regexp"
"strings"
"sync"
"unicode/utf8"
"github.com/dlclark/regexp2"
)
type Rule struct {
Pattern string
Type Emitter
Mutator Mutator
}
// An Emitter takes group matches and returns tokens.
type Emitter interface {
// Emit tokens for the given regex groups.
Emit(groups []string, lexer Lexer) Iterator
}
// EmitterFunc is a function that is an Emitter.
type EmitterFunc func(groups []string, lexer Lexer) Iterator
// Emit tokens for groups.
func (e EmitterFunc) Emit(groups []string, lexer Lexer) Iterator { return e(groups, lexer) }
// ByGroups emits a token for each matching group in the rule's regex.
func ByGroups(emitters ...Emitter) Emitter {
return EmitterFunc(func(groups []string, lexer Lexer) Iterator {
iterators := make([]Iterator, 0, len(groups)-1)
// NOTE: If this panics, there is a mismatch with groups. Uncomment the following line to debug.
for i, group := range groups[1:] {
iterators = append(iterators, emitters[i].Emit([]string{group}, lexer))
}
return Concaterator(iterators...)
})
}
// Using returns an Emitter that uses a given Lexer for parsing and emitting.
func Using(lexer Lexer) Emitter {
return EmitterFunc(func(groups []string, _ Lexer) Iterator {
it, err := lexer.Tokenise(&TokeniseOptions{State: "root", Nested: true}, groups[0])
if err != nil {
panic(err)
}
return it
})
}
// UsingSelf is like Using, but uses the current Lexer.
func UsingSelf(state string) Emitter {
return EmitterFunc(func(groups []string, lexer Lexer) Iterator {
it, err := lexer.Tokenise(&TokeniseOptions{State: state, Nested: true}, groups[0])
if err != nil {
panic(err)
}
return it
})
}
// Words creates a regex that matches any of the given literal words.
func Words(prefix, suffix string, words ...string) string {
for i, word := range words {
words[i] = regexp.QuoteMeta(word)
}
return prefix + `(` + strings.Join(words, `|`) + `)` + suffix
}
// Tokenise text using lexer, returning tokens as a slice.
func Tokenise(lexer Lexer, options *TokeniseOptions, text string) ([]*Token, error) {
out := []*Token{}
it, err := lexer.Tokenise(options, text)
if err != nil {
return nil, err
}
for t := it(); t != nil; t = it() {
out = append(out, t)
}
return out, nil
}
// Rules maps from state to a sequence of Rules.
type Rules map[string][]Rule
func (r Rules) Clone() Rules {
out := map[string][]Rule{}
for key, rules := range r {
out[key] = make([]Rule, len(rules))
copy(out[key], rules)
}
return out
}
// MustNewLexer creates a new Lexer or panics.
func MustNewLexer(config *Config, rules Rules) *RegexLexer {
lexer, err := NewLexer(config, rules)
if err != nil {
panic(err)
}
return lexer
}
// NewLexer creates a new regex-based Lexer.
//
// "rules" is a state machine transitition map. Each key is a state. Values are sets of rules
// that match input, optionally modify lexer state, and output tokens.
func NewLexer(config *Config, rules Rules) (*RegexLexer, error) {
if config == nil {
config = &Config{}
}
if _, ok := rules["root"]; !ok {
return nil, fmt.Errorf("no \"root\" state")
}
compiledRules := map[string][]*CompiledRule{}
for state, rules := range rules {
compiledRules[state] = nil
for _, rule := range rules {
flags := ""
if !config.NotMultiline {
flags += "m"
}
if config.CaseInsensitive {
flags += "i"
}
if config.DotAll {
flags += "s"
}
compiledRules[state] = append(compiledRules[state], &CompiledRule{Rule: rule, flags: flags})
}
}
return &RegexLexer{
config: config,
rules: compiledRules,
}, nil
}
func (r *RegexLexer) Trace(trace bool) *RegexLexer {
r.trace = trace
return r
}
// A CompiledRule is a Rule with a pre-compiled regex.
//
// Note that regular expressions are lazily compiled on first use of the lexer.
type CompiledRule struct {
Rule
Regexp *regexp2.Regexp
flags string
}
type CompiledRules map[string][]*CompiledRule
type LexerState struct {
Lexer *RegexLexer
Text []rune
Pos int
Rules CompiledRules
Stack []string
State string
Rule int
// Group matches.
Groups []string
// Custum context for mutators.
MutatorContext map[interface{}]interface{}
iteratorStack []Iterator
}
func (l *LexerState) Set(key interface{}, value interface{}) {
l.MutatorContext[key] = value
}
func (l *LexerState) Get(key interface{}) interface{} {
return l.MutatorContext[key]
}
func (l *LexerState) Iterator() *Token {
for l.Pos < len(l.Text) && len(l.Stack) > 0 {
// Exhaust the iterator stack, if any.
for len(l.iteratorStack) > 0 {
n := len(l.iteratorStack) - 1
t := l.iteratorStack[n]()
if t == nil {
l.iteratorStack = l.iteratorStack[:n]
continue
}
return t
}
l.State = l.Stack[len(l.Stack)-1]
if l.Lexer.trace {
fmt.Fprintf(os.Stderr, "%s: pos=%d, text=%q\n", l.State, l.Pos, string(l.Text[l.Pos:]))
}
selectedRule, ok := l.Rules[l.State]
if !ok {
panic("unknown state " + l.State)
}
ruleIndex, rule, groups := matchRules(l.Text[l.Pos:], selectedRule)
// No match.
if groups == nil {
l.Pos++
return &Token{Error, string(l.Text[l.Pos-1 : l.Pos])}
}
l.Rule = ruleIndex
l.Groups = groups
l.Pos += utf8.RuneCountInString(groups[0])
if rule.Mutator != nil {
if err := rule.Mutator.Mutate(l); err != nil {
panic(err)
}
}
if rule.Type != nil {
l.iteratorStack = append(l.iteratorStack, rule.Type.Emit(l.Groups, l.Lexer))
}
}
// Exhaust the IteratorStack, if any.
// Duplicate code, but eh.
for len(l.iteratorStack) > 0 {
n := len(l.iteratorStack) - 1
t := l.iteratorStack[n]()
if t == nil {
l.iteratorStack = l.iteratorStack[:n]
continue
}
return t
}
// If we get to here and we still have text, return it as an error.
if l.Pos != len(l.Text) && len(l.Stack) == 0 {
value := string(l.Text[l.Pos:])
l.Pos = len(l.Text)
return &Token{Type: Error, Value: value}
}
return nil
}
type RegexLexer struct {
config *Config
analyser func(text string) float32
trace bool
mu sync.Mutex
compiled bool
rules map[string][]*CompiledRule
}
// SetAnalyser sets the analyser function used to perform content inspection.
func (r *RegexLexer) SetAnalyser(analyser func(text string) float32) *RegexLexer {
r.analyser = analyser
return r
}
func (r *RegexLexer) AnalyseText(text string) float32 {
if r.analyser != nil {
return r.analyser(text)
}
return 0.0
}
func (r *RegexLexer) Config() *Config {
return r.config
}
// Regex compilation is deferred until the lexer is used. This is to avoid significant init() time costs.
func (r *RegexLexer) maybeCompile() (err error) {
r.mu.Lock()
defer r.mu.Unlock()
if r.compiled {
return nil
}
for state, rules := range r.rules {
for i, rule := range rules {
if rule.Regexp == nil {
rule.Regexp, err = regexp2.Compile("^(?"+rule.flags+")(?:"+rule.Pattern+")", 0)
if err != nil {
return fmt.Errorf("failed to compile rule %s.%d: %s", state, i, err)
}
}
}
}
restart:
seen := map[LexerMutator]bool{}
for state := range r.rules {
for i := 0; i < len(r.rules[state]); i++ {
rule := r.rules[state][i]
if compile, ok := rule.Mutator.(LexerMutator); ok {
if seen[compile] {
return fmt.Errorf("saw mutator %T twice; this should not happen", compile)
}
seen[compile] = true
if err := compile.MutateLexer(r.rules, state, i); err != nil {
return err
}
// Process the rules again in case the mutator added/removed rules.
//
// This sounds bad, but shouldn't be significant in practice.
goto restart
}
}
}
r.compiled = true
return nil
}
func (r *RegexLexer) Tokenise(options *TokeniseOptions, text string) (Iterator, error) {
if err := r.maybeCompile(); err != nil {
return nil, err
}
if options == nil {
options = defaultOptions
}
if !options.Nested && r.config.EnsureNL && !strings.HasSuffix(text, "\n") {
text += "\n"
}
state := &LexerState{
Lexer: r,
Text: []rune(text),
Stack: []string{options.State},
Rules: r.rules,
MutatorContext: map[interface{}]interface{}{},
}
return state.Iterator, nil
}
func matchRules(text []rune, rules []*CompiledRule) (int, *CompiledRule, []string) {
for i, rule := range rules {
match, err := rule.Regexp.FindRunesMatch(text)
if match != nil && err == nil {
groups := []string{}
for _, g := range match.Groups() {
groups = append(groups, g.String())
}
return i, rule, groups
}
}
return 0, &CompiledRule{}, nil
}
|