/usr/share/gocode/src/gopkg.in/gcfg.v1/scanner/scanner.go is in golang-gopkg-gcfg.v1-dev 0.0~git20150907.0.0ef1a85-1.
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 | // Copyright 2009 The Go Authors. All rights reserved.
// Use of this source code is governed by a BSD-style
// license that can be found in the LICENSE file.
// Package scanner implements a scanner for gcfg configuration text.
// It takes a []byte as source which can then be tokenized
// through repeated calls to the Scan method.
//
// Note that the API for the scanner package may change to accommodate new
// features or implementation changes in gcfg.
//
package scanner
import (
"fmt"
"path/filepath"
"unicode"
"unicode/utf8"
)
import (
"gopkg.in/gcfg.v1/token"
)
// An ErrorHandler may be provided to Scanner.Init. If a syntax error is
// encountered and a handler was installed, the handler is called with a
// position and an error message. The position points to the beginning of
// the offending token.
//
type ErrorHandler func(pos token.Position, msg string)
// A Scanner holds the scanner's internal state while processing
// a given text. It can be allocated as part of another data
// structure but must be initialized via Init before use.
//
type Scanner struct {
// immutable state
file *token.File // source file handle
dir string // directory portion of file.Name()
src []byte // source
err ErrorHandler // error reporting; or nil
mode Mode // scanning mode
// scanning state
ch rune // current character
offset int // character offset
rdOffset int // reading offset (position after current character)
lineOffset int // current line offset
nextVal bool // next token is expected to be a value
// public state - ok to modify
ErrorCount int // number of errors encountered
}
// Read the next Unicode char into s.ch.
// s.ch < 0 means end-of-file.
//
func (s *Scanner) next() {
if s.rdOffset < len(s.src) {
s.offset = s.rdOffset
if s.ch == '\n' {
s.lineOffset = s.offset
s.file.AddLine(s.offset)
}
r, w := rune(s.src[s.rdOffset]), 1
switch {
case r == 0:
s.error(s.offset, "illegal character NUL")
case r >= 0x80:
// not ASCII
r, w = utf8.DecodeRune(s.src[s.rdOffset:])
if r == utf8.RuneError && w == 1 {
s.error(s.offset, "illegal UTF-8 encoding")
}
}
s.rdOffset += w
s.ch = r
} else {
s.offset = len(s.src)
if s.ch == '\n' {
s.lineOffset = s.offset
s.file.AddLine(s.offset)
}
s.ch = -1 // eof
}
}
// A mode value is a set of flags (or 0).
// They control scanner behavior.
//
type Mode uint
const (
ScanComments Mode = 1 << iota // return comments as COMMENT tokens
)
// Init prepares the scanner s to tokenize the text src by setting the
// scanner at the beginning of src. The scanner uses the file set file
// for position information and it adds line information for each line.
// It is ok to re-use the same file when re-scanning the same file as
// line information which is already present is ignored. Init causes a
// panic if the file size does not match the src size.
//
// Calls to Scan will invoke the error handler err if they encounter a
// syntax error and err is not nil. Also, for each error encountered,
// the Scanner field ErrorCount is incremented by one. The mode parameter
// determines how comments are handled.
//
// Note that Init may call err if there is an error in the first character
// of the file.
//
func (s *Scanner) Init(file *token.File, src []byte, err ErrorHandler, mode Mode) {
// Explicitly initialize all fields since a scanner may be reused.
if file.Size() != len(src) {
panic(fmt.Sprintf("file size (%d) does not match src len (%d)", file.Size(), len(src)))
}
s.file = file
s.dir, _ = filepath.Split(file.Name())
s.src = src
s.err = err
s.mode = mode
s.ch = ' '
s.offset = 0
s.rdOffset = 0
s.lineOffset = 0
s.ErrorCount = 0
s.nextVal = false
s.next()
}
func (s *Scanner) error(offs int, msg string) {
if s.err != nil {
s.err(s.file.Position(s.file.Pos(offs)), msg)
}
s.ErrorCount++
}
func (s *Scanner) scanComment() string {
// initial [;#] already consumed
offs := s.offset - 1 // position of initial [;#]
for s.ch != '\n' && s.ch >= 0 {
s.next()
}
return string(s.src[offs:s.offset])
}
func isLetter(ch rune) bool {
return 'a' <= ch && ch <= 'z' || 'A' <= ch && ch <= 'Z' || ch >= 0x80 && unicode.IsLetter(ch)
}
func isDigit(ch rune) bool {
return '0' <= ch && ch <= '9' || ch >= 0x80 && unicode.IsDigit(ch)
}
func (s *Scanner) scanIdentifier() string {
offs := s.offset
for isLetter(s.ch) || isDigit(s.ch) || s.ch == '-' {
s.next()
}
return string(s.src[offs:s.offset])
}
func (s *Scanner) scanEscape(val bool) {
offs := s.offset
ch := s.ch
s.next() // always make progress
switch ch {
case '\\', '"':
// ok
case 'n', 't':
if val {
break // ok
}
fallthrough
default:
s.error(offs, "unknown escape sequence")
}
}
func (s *Scanner) scanString() string {
// '"' opening already consumed
offs := s.offset - 1
for s.ch != '"' {
ch := s.ch
s.next()
if ch == '\n' || ch < 0 {
s.error(offs, "string not terminated")
break
}
if ch == '\\' {
s.scanEscape(false)
}
}
s.next()
return string(s.src[offs:s.offset])
}
func stripCR(b []byte) []byte {
c := make([]byte, len(b))
i := 0
for _, ch := range b {
if ch != '\r' {
c[i] = ch
i++
}
}
return c[:i]
}
func (s *Scanner) scanValString() string {
offs := s.offset
hasCR := false
end := offs
inQuote := false
loop:
for inQuote || s.ch >= 0 && s.ch != '\n' && s.ch != ';' && s.ch != '#' {
ch := s.ch
s.next()
switch {
case inQuote && ch == '\\':
s.scanEscape(true)
case !inQuote && ch == '\\':
if s.ch == '\r' {
hasCR = true
s.next()
}
if s.ch != '\n' {
s.error(offs, "unquoted '\\' must be followed by new line")
break loop
}
s.next()
case ch == '"':
inQuote = !inQuote
case ch == '\r':
hasCR = true
case ch < 0 || inQuote && ch == '\n':
s.error(offs, "string not terminated")
break loop
}
if inQuote || !isWhiteSpace(ch) {
end = s.offset
}
}
lit := s.src[offs:end]
if hasCR {
lit = stripCR(lit)
}
return string(lit)
}
func isWhiteSpace(ch rune) bool {
return ch == ' ' || ch == '\t' || ch == '\r'
}
func (s *Scanner) skipWhitespace() {
for isWhiteSpace(s.ch) {
s.next()
}
}
// Scan scans the next token and returns the token position, the token,
// and its literal string if applicable. The source end is indicated by
// token.EOF.
//
// If the returned token is a literal (token.IDENT, token.STRING) or
// token.COMMENT, the literal string has the corresponding value.
//
// If the returned token is token.ILLEGAL, the literal string is the
// offending character.
//
// In all other cases, Scan returns an empty literal string.
//
// For more tolerant parsing, Scan will return a valid token if
// possible even if a syntax error was encountered. Thus, even
// if the resulting token sequence contains no illegal tokens,
// a client may not assume that no error occurred. Instead it
// must check the scanner's ErrorCount or the number of calls
// of the error handler, if there was one installed.
//
// Scan adds line information to the file added to the file
// set with Init. Token positions are relative to that file
// and thus relative to the file set.
//
func (s *Scanner) Scan() (pos token.Pos, tok token.Token, lit string) {
scanAgain:
s.skipWhitespace()
// current token start
pos = s.file.Pos(s.offset)
// determine token value
switch ch := s.ch; {
case s.nextVal:
lit = s.scanValString()
tok = token.STRING
s.nextVal = false
case isLetter(ch):
lit = s.scanIdentifier()
tok = token.IDENT
default:
s.next() // always make progress
switch ch {
case -1:
tok = token.EOF
case '\n':
tok = token.EOL
case '"':
tok = token.STRING
lit = s.scanString()
case '[':
tok = token.LBRACK
case ']':
tok = token.RBRACK
case ';', '#':
// comment
lit = s.scanComment()
if s.mode&ScanComments == 0 {
// skip comment
goto scanAgain
}
tok = token.COMMENT
case '=':
tok = token.ASSIGN
s.nextVal = true
default:
s.error(s.file.Offset(pos), fmt.Sprintf("illegal character %#U", ch))
tok = token.ILLEGAL
lit = string(ch)
}
}
return
}
|