/usr/share/gocode/src/github.com/ChrisTrenkamp/goxpath/internal/lexer/lexer.go is in golang-github-christrenkamp-goxpath-dev 1.0~alpha3-1.
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 | package lexer
import (
"fmt"
"strings"
"unicode"
"unicode/utf8"
)
const (
//XItemError is an error with the parser input
XItemError XItemType = "Error"
//XItemAbsLocPath is an absolute path
XItemAbsLocPath = "Absolute path"
//XItemAbbrAbsLocPath represents an abbreviated absolute path
XItemAbbrAbsLocPath = "Abbreviated absolute path"
//XItemAbbrRelLocPath marks the start of a path expression
XItemAbbrRelLocPath = "Abbreviated relative path"
//XItemRelLocPath represents a relative location path
XItemRelLocPath = "Relative path"
//XItemEndPath marks the end of a path
XItemEndPath = "End path instruction"
//XItemAxis marks an axis specifier of a path
XItemAxis = "Axis"
//XItemAbbrAxis marks an abbreviated axis specifier (just @ at this point)
XItemAbbrAxis = "Abbreviated attribute axis"
//XItemNCName marks a namespace name in a node test
XItemNCName = "Namespace"
//XItemQName marks the local name in an a node test
XItemQName = "Local name"
//XItemNodeType marks a node type in a node test
XItemNodeType = "Node type"
//XItemProcLit marks a processing-instruction literal
XItemProcLit = "processing-instruction"
//XItemFunction marks a function call
XItemFunction = "function"
//XItemArgument marks a function argument
XItemArgument = "function argument"
//XItemEndFunction marks the end of a function
XItemEndFunction = "end of function"
//XItemPredicate marks a predicate in an axis
XItemPredicate = "predicate"
//XItemEndPredicate marks a predicate in an axis
XItemEndPredicate = "end of predicate"
//XItemStrLit marks a string literal
XItemStrLit = "string literal"
//XItemNumLit marks a numeric literal
XItemNumLit = "numeric literal"
//XItemOperator marks an operator
XItemOperator = "operator"
//XItemVariable marks a variable reference
XItemVariable = "variable"
)
const (
eof = -(iota + 1)
)
//XItemType is the parser token types
type XItemType string
//XItem is the token emitted from the parser
type XItem struct {
Typ XItemType
Val string
}
type stateFn func(*Lexer) stateFn
//Lexer lexes out XPath expressions
type Lexer struct {
input string
start int
pos int
width int
items chan XItem
}
//Lex an XPath expresion on the io.Reader
func Lex(xpath string) chan XItem {
l := &Lexer{
input: xpath,
items: make(chan XItem),
}
go l.run()
return l.items
}
func (l *Lexer) run() {
for state := startState; state != nil; {
state = state(l)
}
if l.peek() != eof {
l.errorf("Malformed XPath expression")
}
close(l.items)
}
func (l *Lexer) emit(t XItemType) {
l.items <- XItem{t, l.input[l.start:l.pos]}
l.start = l.pos
}
func (l *Lexer) emitVal(t XItemType, val string) {
l.items <- XItem{t, val}
l.start = l.pos
}
func (l *Lexer) next() (r rune) {
if l.pos >= len(l.input) {
l.width = 0
return eof
}
r, l.width = utf8.DecodeRuneInString(l.input[l.pos:])
l.pos += l.width
return r
}
func (l *Lexer) ignore() {
l.start = l.pos
}
func (l *Lexer) backup() {
l.pos -= l.width
}
func (l *Lexer) peek() rune {
r := l.next()
l.backup()
return r
}
func (l *Lexer) peekAt(n int) rune {
if n <= 1 {
return l.peek()
}
width := 0
var ret rune
for count := 0; count < n; count++ {
r, s := utf8.DecodeRuneInString(l.input[l.pos+width:])
width += s
if l.pos+width > len(l.input) {
return eof
}
ret = r
}
return ret
}
func (l *Lexer) accept(valid string) bool {
if strings.ContainsRune(valid, l.next()) {
return true
}
l.backup()
return false
}
func (l *Lexer) acceptRun(valid string) {
for strings.ContainsRune(valid, l.next()) {
}
l.backup()
}
func (l *Lexer) skip(num int) {
for i := 0; i < num; i++ {
l.next()
}
l.ignore()
}
func (l *Lexer) skipWS(ig bool) {
for {
n := l.next()
if n == eof || !unicode.IsSpace(n) {
break
}
}
l.backup()
if ig {
l.ignore()
}
}
func (l *Lexer) errorf(format string, args ...interface{}) stateFn {
l.items <- XItem{
XItemError,
fmt.Sprintf(format, args...),
}
return nil
}
func isElemChar(r rune) bool {
return string(r) != ":" && string(r) != "/" &&
(unicode.Is(first, r) || unicode.Is(second, r) || string(r) == "*") &&
r != eof
}
func startState(l *Lexer) stateFn {
l.skipWS(true)
if string(l.peek()) == "/" {
l.next()
l.ignore()
if string(l.next()) == "/" {
l.ignore()
return abbrAbsLocPathState
}
l.backup()
return absLocPathState
} else if string(l.peek()) == `'` || string(l.peek()) == `"` {
if err := getStrLit(l, XItemStrLit); err != nil {
return l.errorf(err.Error())
}
if l.peek() != eof {
return startState
}
} else if getNumLit(l) {
l.skipWS(true)
if l.peek() != eof {
return startState
}
} else if string(l.peek()) == "$" {
l.next()
l.ignore()
r := l.peek()
for unicode.Is(first, r) || unicode.Is(second, r) {
l.next()
r = l.peek()
}
tok := l.input[l.start:l.pos]
if len(tok) == 0 {
return l.errorf("Empty variable name")
}
l.emit(XItemVariable)
l.skipWS(true)
if l.peek() != eof {
return startState
}
} else if st := findOperatorState(l); st != nil {
return st
} else {
if isElemChar(l.peek()) {
colons := 0
for {
if isElemChar(l.peek()) {
l.next()
} else if string(l.peek()) == ":" {
l.next()
colons++
} else {
break
}
}
if string(l.peek()) == "(" && colons <= 1 {
tok := l.input[l.start:l.pos]
err := procFunc(l, tok)
if err != nil {
return l.errorf(err.Error())
}
return startState
}
l.pos = l.start
return relLocPathState
} else if string(l.peek()) == "@" {
return relLocPathState
}
}
return nil
}
func strPeek(str string, l *Lexer) bool {
for i := 0; i < len(str); i++ {
if string(l.peekAt(i+1)) != string(str[i]) {
return false
}
}
return true
}
func findOperatorState(l *Lexer) stateFn {
l.skipWS(true)
switch string(l.peek()) {
case ">", "<", "!":
l.next()
if string(l.peek()) == "=" {
l.next()
}
l.emit(XItemOperator)
return startState
case "|", "+", "-", "*", "=":
l.next()
l.emit(XItemOperator)
return startState
case "(":
l.next()
l.emit(XItemOperator)
for state := startState; state != nil; {
state = state(l)
}
l.skipWS(true)
if string(l.next()) != ")" {
return l.errorf("Missing end )")
}
l.emit(XItemOperator)
return startState
}
if strPeek("and", l) {
l.next()
l.next()
l.next()
l.emit(XItemOperator)
return startState
}
if strPeek("or", l) {
l.next()
l.next()
l.emit(XItemOperator)
return startState
}
if strPeek("mod", l) {
l.next()
l.next()
l.next()
l.emit(XItemOperator)
return startState
}
if strPeek("div", l) {
l.next()
l.next()
l.next()
l.emit(XItemOperator)
return startState
}
return nil
}
func getStrLit(l *Lexer, tok XItemType) error {
q := l.next()
var r rune
l.ignore()
for r != q {
r = l.next()
if r == eof {
return fmt.Errorf("Unexpected end of string literal.")
}
}
l.backup()
l.emit(tok)
l.next()
l.ignore()
return nil
}
func getNumLit(l *Lexer) bool {
const dig = "0123456789"
l.accept("-")
start := l.pos
l.acceptRun(dig)
if l.pos == start {
return false
}
if l.accept(".") {
l.acceptRun(dig)
}
l.emit(XItemNumLit)
return true
}
|