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
|
// Copyright 2015-2019 Brett Vickers.
// Use of this source code is governed by a BSD-style
// license that can be found in the LICENSE file.
package etree
import (
"io"
"strings"
"unicode/utf8"
)
type stack[E any] struct {
data []E
}
func (s *stack[E]) empty() bool {
return len(s.data) == 0
}
func (s *stack[E]) push(value E) {
s.data = append(s.data, value)
}
func (s *stack[E]) pop() E {
value := s.data[len(s.data)-1]
var empty E
s.data[len(s.data)-1] = empty
s.data = s.data[:len(s.data)-1]
return value
}
func (s *stack[E]) peek() E {
return s.data[len(s.data)-1]
}
type queue[E any] struct {
data []E
head, tail int
}
func (f *queue[E]) add(value E) {
if f.len()+1 >= len(f.data) {
f.grow()
}
f.data[f.tail] = value
if f.tail++; f.tail == len(f.data) {
f.tail = 0
}
}
func (f *queue[E]) remove() E {
value := f.data[f.head]
var empty E
f.data[f.head] = empty
if f.head++; f.head == len(f.data) {
f.head = 0
}
return value
}
func (f *queue[E]) len() int {
if f.tail >= f.head {
return f.tail - f.head
}
return len(f.data) - f.head + f.tail
}
func (f *queue[E]) grow() {
c := len(f.data) * 2
if c == 0 {
c = 4
}
buf, count := make([]E, c), f.len()
if f.tail >= f.head {
copy(buf[:count], f.data[f.head:f.tail])
} else {
hindex := len(f.data) - f.head
copy(buf[:hindex], f.data[f.head:])
copy(buf[hindex:count], f.data[:f.tail])
}
f.data, f.head, f.tail = buf, 0, count
}
// xmlReader provides the interface by which an XML byte stream is
// processed and decoded.
type xmlReader interface {
Bytes() int64
Read(p []byte) (n int, err error)
}
// xmlSimpleReader implements a proxy reader that counts the number of
// bytes read from its encapsulated reader.
type xmlSimpleReader struct {
r io.Reader
bytes int64
}
func newXmlSimpleReader(r io.Reader) xmlReader {
return &xmlSimpleReader{r, 0}
}
func (xr *xmlSimpleReader) Bytes() int64 {
return xr.bytes
}
func (xr *xmlSimpleReader) Read(p []byte) (n int, err error) {
n, err = xr.r.Read(p)
xr.bytes += int64(n)
return n, err
}
// xmlPeekReader implements a proxy reader that counts the number of
// bytes read from its encapsulated reader. It also allows the caller to
// "peek" at the previous portions of the buffer after they have been
// parsed.
type xmlPeekReader struct {
r io.Reader
bytes int64 // total bytes read by the Read function
buf []byte // internal read buffer
bufSize int // total bytes used in the read buffer
bufOffset int64 // total bytes read when buf was last filled
window []byte // current read buffer window
peekBuf []byte // buffer used to store data to be peeked at later
peekOffset int64 // total read offset of the start of the peek buffer
}
func newXmlPeekReader(r io.Reader) *xmlPeekReader {
buf := make([]byte, 4096)
return &xmlPeekReader{
r: r,
bytes: 0,
buf: buf,
bufSize: 0,
bufOffset: 0,
window: buf[0:0],
peekBuf: make([]byte, 0),
peekOffset: -1,
}
}
func (xr *xmlPeekReader) Bytes() int64 {
return xr.bytes
}
func (xr *xmlPeekReader) Read(p []byte) (n int, err error) {
if len(xr.window) == 0 {
err = xr.fill()
if err != nil {
return 0, err
}
if len(xr.window) == 0 {
return 0, nil
}
}
if len(xr.window) < len(p) {
n = len(xr.window)
} else {
n = len(p)
}
copy(p, xr.window)
xr.window = xr.window[n:]
xr.bytes += int64(n)
return n, err
}
func (xr *xmlPeekReader) PeekPrepare(offset int64, maxLen int) {
if maxLen > cap(xr.peekBuf) {
xr.peekBuf = make([]byte, 0, maxLen)
}
xr.peekBuf = xr.peekBuf[0:0]
xr.peekOffset = offset
xr.updatePeekBuf()
}
func (xr *xmlPeekReader) PeekFinalize() []byte {
xr.updatePeekBuf()
return xr.peekBuf
}
func (xr *xmlPeekReader) fill() error {
xr.bufOffset = xr.bytes
xr.bufSize = 0
n, err := xr.r.Read(xr.buf)
if err != nil {
xr.window, xr.bufSize = xr.buf[0:0], 0
return err
}
xr.window, xr.bufSize = xr.buf[:n], n
xr.updatePeekBuf()
return nil
}
func (xr *xmlPeekReader) updatePeekBuf() {
peekRemain := cap(xr.peekBuf) - len(xr.peekBuf)
if xr.peekOffset >= 0 && peekRemain > 0 {
rangeMin := xr.peekOffset
rangeMax := xr.peekOffset + int64(cap(xr.peekBuf))
bufMin := xr.bufOffset
bufMax := xr.bufOffset + int64(xr.bufSize)
if rangeMin < bufMin {
rangeMin = bufMin
}
if rangeMax > bufMax {
rangeMax = bufMax
}
if rangeMax > rangeMin {
rangeMin -= xr.bufOffset
rangeMax -= xr.bufOffset
if int(rangeMax-rangeMin) > peekRemain {
rangeMax = rangeMin + int64(peekRemain)
}
xr.peekBuf = append(xr.peekBuf, xr.buf[rangeMin:rangeMax]...)
}
}
}
// xmlWriter implements a proxy writer that counts the number of
// bytes written by its encapsulated writer.
type xmlWriter struct {
w io.Writer
bytes int64
}
func newXmlWriter(w io.Writer) *xmlWriter {
return &xmlWriter{w: w}
}
func (xw *xmlWriter) Write(p []byte) (n int, err error) {
n, err = xw.w.Write(p)
xw.bytes += int64(n)
return n, err
}
// isWhitespace returns true if the byte slice contains only
// whitespace characters.
func isWhitespace(s string) bool {
for i := 0; i < len(s); i++ {
if c := s[i]; c != ' ' && c != '\t' && c != '\n' && c != '\r' {
return false
}
}
return true
}
// spaceMatch returns true if namespace a is the empty string
// or if namespace a equals namespace b.
func spaceMatch(a, b string) bool {
switch {
case a == "":
return true
default:
return a == b
}
}
// spaceDecompose breaks a namespace:tag identifier at the ':'
// and returns the two parts.
func spaceDecompose(str string) (space, key string) {
colon := strings.IndexByte(str, ':')
if colon == -1 {
return "", str
}
return str[:colon], str[colon+1:]
}
// Strings used by indentCRLF and indentLF
const (
indentSpaces = "\r\n "
indentTabs = "\r\n\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t"
)
// indentCRLF returns a CRLF newline followed by n copies of the first
// non-CRLF character in the source string.
func indentCRLF(n int, source string) string {
switch {
case n < 0:
return source[:2]
case n < len(source)-1:
return source[:n+2]
default:
return source + strings.Repeat(source[2:3], n-len(source)+2)
}
}
// indentLF returns a LF newline followed by n copies of the first non-LF
// character in the source string.
func indentLF(n int, source string) string {
switch {
case n < 0:
return source[1:2]
case n < len(source)-1:
return source[1 : n+2]
default:
return source[1:] + strings.Repeat(source[2:3], n-len(source)+2)
}
}
// nextIndex returns the index of the next occurrence of byte ch in s,
// starting from offset. It returns -1 if the byte is not found.
func nextIndex(s string, ch byte, offset int) int {
switch i := strings.IndexByte(s[offset:], ch); i {
case -1:
return -1
default:
return offset + i
}
}
// isInteger returns true if the string s contains an integer.
func isInteger(s string) bool {
for i := 0; i < len(s); i++ {
if (s[i] < '0' || s[i] > '9') && !(i == 0 && s[i] == '-') {
return false
}
}
return true
}
type escapeMode byte
const (
escapeNormal escapeMode = iota
escapeCanonicalText
escapeCanonicalAttr
)
// escapeString writes an escaped version of a string to the writer.
func escapeString(w Writer, s string, m escapeMode) {
var esc []byte
last := 0
for i := 0; i < len(s); {
r, width := utf8.DecodeRuneInString(s[i:])
i += width
switch r {
case '&':
esc = []byte("&")
case '<':
esc = []byte("<")
case '>':
if m == escapeCanonicalAttr {
continue
}
esc = []byte(">")
case '\'':
if m != escapeNormal {
continue
}
esc = []byte("'")
case '"':
if m == escapeCanonicalText {
continue
}
esc = []byte(""")
case '\t':
if m != escapeCanonicalAttr {
continue
}
esc = []byte("	")
case '\n':
if m != escapeCanonicalAttr {
continue
}
esc = []byte("
")
case '\r':
if m == escapeNormal {
continue
}
esc = []byte("
")
default:
if !isInCharacterRange(r) || (r == 0xFFFD && width == 1) {
esc = []byte("\uFFFD")
break
}
continue
}
w.WriteString(s[last : i-width])
w.Write(esc)
last = i
}
w.WriteString(s[last:])
}
func isInCharacterRange(r rune) bool {
return r == 0x09 ||
r == 0x0A ||
r == 0x0D ||
r >= 0x20 && r <= 0xD7FF ||
r >= 0xE000 && r <= 0xFFFD ||
r >= 0x10000 && r <= 0x10FFFF
}
|