quick_xml/reader/mod.rs
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921
//! Contains high-level interface for a pull-based XML parser.
#[cfg(feature = "encoding")]
use encoding_rs::Encoding;
use std::io;
use std::ops::Range;
use crate::encoding::Decoder;
use crate::errors::{Error, SyntaxError};
use crate::events::Event;
use crate::parser::{ElementParser, Parser, PiParser};
use crate::reader::state::ReaderState;
/// A struct that holds a parser configuration.
///
/// Current parser configuration can be retrieved by calling [`Reader::config()`]
/// and changed by changing properties of the object returned by a call to
/// [`Reader::config_mut()`].
///
/// [`Reader::config()`]: crate::reader::Reader::config
/// [`Reader::config_mut()`]: crate::reader::Reader::config_mut
#[derive(Debug, Clone, PartialEq, Eq)]
#[cfg_attr(feature = "arbitrary", derive(arbitrary::Arbitrary))]
#[cfg_attr(feature = "serde-types", derive(serde::Deserialize, serde::Serialize))]
#[non_exhaustive]
pub struct Config {
/// Whether unmatched closing tag names should be allowed. Unless enabled,
/// in case of a dangling end tag, the [`Error::IllFormed(UnmatchedEndTag)`]
/// is returned from read methods.
///
/// When set to `true`, it won't check if a closing tag has a corresponding
/// opening tag at all. For example, `<a></a></b>` will be permitted.
///
/// Note that the emitted [`End`] event will not be modified if this is enabled,
/// ie. it will contain the data of the unmatched end tag.
///
/// Note, that setting this to `true` will lead to additional allocates that
/// needed to store tag name for an [`End`] event.
///
/// Default: `false`
///
/// [`Error::IllFormed(UnmatchedEndTag)`]: crate::errors::IllFormedError::UnmatchedEndTag
/// [`End`]: crate::events::Event::End
pub allow_unmatched_ends: bool,
/// Whether comments should be validated. If enabled, in case of invalid comment
/// [`Error::IllFormed(DoubleHyphenInComment)`] is returned from read methods.
///
/// When set to `true`, every [`Comment`] event will be checked for not
/// containing `--`, which [is not allowed] in XML comments. Most of the time
/// we don't want comments at all so we don't really care about comment
/// correctness, thus the default value is `false` to improve performance.
///
/// Default: `false`
///
/// [`Error::IllFormed(DoubleHyphenInComment)`]: crate::errors::IllFormedError::DoubleHyphenInComment
/// [`Comment`]: crate::events::Event::Comment
/// [is not allowed]: https://www.w3.org/TR/xml11/#sec-comments
pub check_comments: bool,
/// Whether mismatched closing tag names should be detected. If enabled, in
/// case of mismatch the [`Error::IllFormed(MismatchedEndTag)`] is returned from
/// read methods.
///
/// Note, that start and end tags [should match literally][spec], they cannot
/// have different prefixes even if both prefixes resolve to the same namespace.
/// The XML
///
/// ```xml
/// <outer xmlns="namespace" xmlns:p="namespace">
/// </p:outer>
/// ```
///
/// is not valid, even though semantically the start tag is the same as the
/// end tag. The reason is that namespaces are an extension of the original
/// XML specification (without namespaces) and it should be backward-compatible.
///
/// When set to `false`, it won't check if a closing tag matches the corresponding
/// opening tag. For example, `<mytag></different_tag>` will be permitted.
///
/// If the XML is known to be sane (already processed, etc.) this saves extra time.
///
/// Note that the emitted [`End`] event will not be modified if this is disabled,
/// ie. it will contain the data of the mismatched end tag.
///
/// Note, that setting this to `true` will lead to additional allocates that
/// needed to store tag name for an [`End`] event. However if [`expand_empty_elements`]
/// is also set, only one additional allocation will be performed that support
/// both these options.
///
/// Default: `true`
///
/// [`Error::IllFormed(MismatchedEndTag)`]: crate::errors::IllFormedError::MismatchedEndTag
/// [spec]: https://www.w3.org/TR/xml11/#dt-etag
/// [`End`]: crate::events::Event::End
/// [`expand_empty_elements`]: Self::expand_empty_elements
pub check_end_names: bool,
/// Whether empty elements should be split into an `Open` and a `Close` event.
///
/// When set to `true`, all [`Empty`] events produced by a self-closing tag
/// like `<tag/>` are expanded into a [`Start`] event followed by an [`End`]
/// event. When set to `false` (the default), those tags are represented by
/// an [`Empty`] event instead.
///
/// Note, that setting this to `true` will lead to additional allocates that
/// needed to store tag name for an [`End`] event. However if [`check_end_names`]
/// is also set, only one additional allocation will be performed that support
/// both these options.
///
/// Default: `false`
///
/// [`Empty`]: crate::events::Event::Empty
/// [`Start`]: crate::events::Event::Start
/// [`End`]: crate::events::Event::End
/// [`check_end_names`]: Self::check_end_names
pub expand_empty_elements: bool,
/// Whether trailing whitespace after the markup name are trimmed in closing
/// tags `</a >`.
///
/// If `true` the emitted [`End`] event is stripped of trailing whitespace
/// after the markup name.
///
/// Note that if set to `false` and [`check_end_names`] is `true` the comparison
/// of markup names is going to fail erroneously if a closing tag contains
/// trailing whitespace.
///
/// Default: `true`
///
/// [`End`]: crate::events::Event::End
/// [`check_end_names`]: Self::check_end_names
pub trim_markup_names_in_closing_tags: bool,
/// Whether whitespace before character data should be removed.
///
/// When set to `true`, leading whitespace is trimmed in [`Text`] events.
/// If after that the event is empty it will not be pushed.
///
/// Default: `false`
///
/// <div style="background:rgba(80, 240, 100, 0.20);padding:0.75em;">
///
/// WARNING: With this option every text events will be trimmed which is
/// incorrect behavior when text events delimited by comments, processing
/// instructions or CDATA sections. To correctly trim data manually apply
/// [`BytesText::inplace_trim_start`] and [`BytesText::inplace_trim_end`]
/// only to necessary events.
/// </div>
///
/// [`Text`]: crate::events::Event::Text
/// [`BytesText::inplace_trim_start`]: crate::events::BytesText::inplace_trim_start
/// [`BytesText::inplace_trim_end`]: crate::events::BytesText::inplace_trim_end
pub trim_text_start: bool,
/// Whether whitespace after character data should be removed.
///
/// When set to `true`, trailing whitespace is trimmed in [`Text`] events.
/// If after that the event is empty it will not be pushed.
///
/// Default: `false`
///
/// <div style="background:rgba(80, 240, 100, 0.20);padding:0.75em;">
///
/// WARNING: With this option every text events will be trimmed which is
/// incorrect behavior when text events delimited by comments, processing
/// instructions or CDATA sections. To correctly trim data manually apply
/// [`BytesText::inplace_trim_start`] and [`BytesText::inplace_trim_end`]
/// only to necessary events.
/// </div>
///
/// [`Text`]: crate::events::Event::Text
/// [`BytesText::inplace_trim_start`]: crate::events::BytesText::inplace_trim_start
/// [`BytesText::inplace_trim_end`]: crate::events::BytesText::inplace_trim_end
pub trim_text_end: bool,
}
impl Config {
/// Set both [`trim_text_start`] and [`trim_text_end`] to the same value.
///
/// <div style="background:rgba(80, 240, 100, 0.20);padding:0.75em;">
///
/// WARNING: With this option every text events will be trimmed which is
/// incorrect behavior when text events delimited by comments, processing
/// instructions or CDATA sections. To correctly trim data manually apply
/// [`BytesText::inplace_trim_start`] and [`BytesText::inplace_trim_end`]
/// only to necessary events.
/// </div>
///
/// [`trim_text_start`]: Self::trim_text_start
/// [`trim_text_end`]: Self::trim_text_end
/// [`BytesText::inplace_trim_start`]: crate::events::BytesText::inplace_trim_start
/// [`BytesText::inplace_trim_end`]: crate::events::BytesText::inplace_trim_end
#[inline]
pub fn trim_text(&mut self, trim: bool) {
self.trim_text_start = trim;
self.trim_text_end = trim;
}
/// Turn on or off all checks for well-formedness. Currently it is that settings:
/// - [`check_comments`](Self::check_comments)
/// - [`check_end_names`](Self::check_end_names)
#[inline]
pub fn enable_all_checks(&mut self, enable: bool) {
self.check_comments = enable;
self.check_end_names = enable;
}
}
impl Default for Config {
fn default() -> Self {
Self {
allow_unmatched_ends: false,
check_comments: false,
check_end_names: true,
expand_empty_elements: false,
trim_markup_names_in_closing_tags: true,
trim_text_start: false,
trim_text_end: false,
}
}
}
////////////////////////////////////////////////////////////////////////////////////////////////////
macro_rules! read_event_impl {
(
$self:ident, $buf:ident,
$reader:expr,
$read_until_close:ident
$(, $await:ident)?
) => {{
let event = loop {
break match $self.state.state {
ParseState::Init => { // Go to InsideMarkup state
// If encoding set explicitly, we not need to detect it. For example,
// explicit UTF-8 set automatically if Reader was created using `from_str`.
// But we still need to remove BOM for consistency with no encoding
// feature enabled path
#[cfg(feature = "encoding")]
if let Some(encoding) = $reader.detect_encoding() $(.$await)? ? {
if $self.state.encoding.can_be_refined() {
$self.state.encoding = crate::reader::EncodingRef::BomDetected(encoding);
}
}
// Removes UTF-8 BOM if it is present
#[cfg(not(feature = "encoding"))]
$reader.remove_utf8_bom() $(.$await)? ?;
$self.state.state = ParseState::InsideText;
continue;
},
ParseState::InsideText => { // Go to InsideMarkup or Done state
if $self.state.config.trim_text_start {
$reader.skip_whitespace(&mut $self.state.offset) $(.$await)? ?;
}
match $reader.read_text($buf, &mut $self.state.offset) $(.$await)? {
ReadTextResult::Markup(buf) => {
$self.state.state = ParseState::InsideMarkup;
// Pass `buf` to the next next iteration of parsing loop
$buf = buf;
continue;
}
ReadTextResult::UpToMarkup(bytes) => {
$self.state.state = ParseState::InsideMarkup;
// FIXME: Can produce an empty event if:
// - event contains only spaces
// - trim_text_start = false
// - trim_text_end = true
Ok(Event::Text($self.state.emit_text(bytes)))
}
ReadTextResult::UpToEof(bytes) => {
$self.state.state = ParseState::Done;
// Trim bytes from end if required
let event = $self.state.emit_text(bytes);
if event.is_empty() {
Ok(Event::Eof)
} else {
Ok(Event::Text(event))
}
}
ReadTextResult::Err(e) => Err(Error::Io(e.into())),
}
},
// Go to InsideText state in next two arms
ParseState::InsideMarkup => $self.$read_until_close($buf) $(.$await)?,
ParseState::InsideEmpty => Ok(Event::End($self.state.close_expanded_empty())),
ParseState::Done => Ok(Event::Eof),
};
};
match event {
// #513: In case of ill-formed errors we already consume the wrong data
// and change the state. We can continue parsing if we wish
Err(Error::IllFormed(_)) => {}
Err(_) | Ok(Event::Eof) => $self.state.state = ParseState::Done,
_ => {}
}
event
}};
}
/// Read bytes up to the `>` and skip it. This method is expected to be called
/// after seeing the `<` symbol and skipping it. Inspects the next (current)
/// symbol and returns an appropriate [`Event`]:
///
/// |Symbol |Event
/// |-------|-------------------------------------
/// |`!` |[`Comment`], [`CData`] or [`DocType`]
/// |`/` |[`End`]
/// |`?` |[`PI`]
/// |_other_|[`Start`] or [`Empty`]
///
/// Moves parser to the `InsideText` state.
///
/// [`Comment`]: Event::Comment
/// [`CData`]: Event::CData
/// [`DocType`]: Event::DocType
/// [`End`]: Event::End
/// [`PI`]: Event::PI
/// [`Start`]: Event::Start
/// [`Empty`]: Event::Empty
macro_rules! read_until_close {
(
$self:ident, $buf:ident,
$reader:expr
$(, $await:ident)?
) => {{
$self.state.state = ParseState::InsideText;
let start = $self.state.offset;
match $reader.peek_one() $(.$await)? {
// `<!` - comment, CDATA or DOCTYPE declaration
Ok(Some(b'!')) => match $reader
.read_bang_element($buf, &mut $self.state.offset)
$(.$await)?
{
Ok((bang_type, bytes)) => $self.state.emit_bang(bang_type, bytes),
Err(e) => {
// We want to report error at `<`, but offset was increased,
// so return it back (-1 for `<`)
$self.state.last_error_offset = start - 1;
Err(e)
}
},
// `</` - closing tag
// #776: We parse using ElementParser which allows us to have attributes
// in close tags. While such tags are not allowed by the specification,
// we anyway allow to parse them because:
// - we do not check constraints during parsing. This is performed by the
// optional validate step which user should call manually
// - if we just look for `>` we will parse `</tag attr=">" >` as end tag
// `</tag attr=">` and text `" >` which probably no one existing parser
// does. This is malformed XML, however it is tolerated by some parsers
// (e.g. the one used by Adobe Flash) and such documents do exist in the wild.
Ok(Some(b'/')) => match $reader
.read_with(ElementParser::Outside, $buf, &mut $self.state.offset)
$(.$await)?
{
Ok(bytes) => $self.state.emit_end(bytes),
Err(e) => {
// We want to report error at `<`, but offset was increased,
// so return it back (-1 for `<`)
$self.state.last_error_offset = start - 1;
Err(e)
}
},
// `<?` - processing instruction
Ok(Some(b'?')) => match $reader
.read_with(PiParser(false), $buf, &mut $self.state.offset)
$(.$await)?
{
Ok(bytes) => $self.state.emit_question_mark(bytes),
Err(e) => {
// We want to report error at `<`, but offset was increased,
// so return it back (-1 for `<`)
$self.state.last_error_offset = start - 1;
Err(e)
}
},
// `<...` - opening or self-closed tag
Ok(Some(_)) => match $reader
.read_with(ElementParser::Outside, $buf, &mut $self.state.offset)
$(.$await)?
{
Ok(bytes) => Ok($self.state.emit_start(bytes)),
Err(e) => {
// We want to report error at `<`, but offset was increased,
// so return it back (-1 for `<`)
$self.state.last_error_offset = start - 1;
Err(e)
}
},
// `<` - syntax error, tag not closed
Ok(None) => {
// We want to report error at `<`, but offset was increased,
// so return it back (-1 for `<`)
$self.state.last_error_offset = start - 1;
Err(Error::Syntax(SyntaxError::UnclosedTag))
}
Err(e) => Err(Error::Io(e.into())),
}
}};
}
/// Generalization of `read_to_end` method for buffered and borrowed readers
macro_rules! read_to_end {
(
// $self: &mut Reader
$self:expr, $end:expr, $buf:expr,
$read_event:ident,
// Code block that performs clearing of internal buffer after read of each event
$clear:block
$(, $await:ident)?
) => {{
// Because we take position after the event before the End event,
// it is important that this position indicates beginning of the End event.
// If between last event and the End event would be only spaces, then we
// take position before the spaces, but spaces would be skipped without
// generating event if `trim_text_start` is set to `true`. To prevent that
// we temporary disable start text trimming.
//
// We also cannot take position after getting End event, because if
// `trim_markup_names_in_closing_tags` is set to `true` (which is the default),
// we do not known the real size of the End event that it is occupies in
// the source and cannot correct the position after the End event.
// So, we in any case should tweak parser configuration.
let config = $self.config_mut();
let trim = config.trim_text_start;
config.trim_text_start = false;
let start = $self.buffer_position();
let mut depth = 0;
loop {
$clear
let end = $self.buffer_position();
match $self.$read_event($buf) $(.$await)? {
Err(e) => {
$self.config_mut().trim_text_start = trim;
return Err(e);
}
Ok(Event::Start(e)) if e.name() == $end => depth += 1,
Ok(Event::End(e)) if e.name() == $end => {
if depth == 0 {
$self.config_mut().trim_text_start = trim;
break start..end;
}
depth -= 1;
}
Ok(Event::Eof) => {
$self.config_mut().trim_text_start = trim;
return Err(Error::missed_end($end, $self.decoder()));
}
_ => (),
}
}
}};
}
#[cfg(feature = "async-tokio")]
mod async_tokio;
mod buffered_reader;
mod ns_reader;
mod slice_reader;
mod state;
pub use ns_reader::NsReader;
/// Range of input in bytes, that corresponds to some piece of XML
pub type Span = Range<u64>;
////////////////////////////////////////////////////////////////////////////////////////////////////
/// Possible reader states. The state transition diagram (`true` and `false` shows
/// value of [`Config::expand_empty_elements`] option):
///
/// ```mermaid
/// flowchart LR
/// subgraph _
/// direction LR
///
/// Init -- "(no event)"\n --> InsideMarkup
/// InsideMarkup -- Decl, DocType, PI\nComment, CData\nStart, Empty, End --> InsideText
/// InsideText -- "#lt;false#gt;\n(no event)"\nText --> InsideMarkup
/// end
/// InsideText -- "#lt;true#gt;"\nStart --> InsideEmpty
/// InsideEmpty -- End --> InsideText
/// _ -. Eof .-> Done
/// ```
#[derive(Clone, Debug)]
enum ParseState {
/// Initial state in which reader stay after creation. Transition from that
/// state could produce a `Text`, `Decl`, `Comment` or `Start` event. The next
/// state is always `InsideMarkup`. The reader will never return to this state. The
/// event emitted during transition to `InsideMarkup` is a `StartEvent` if the
/// first symbol not `<`, otherwise no event are emitted.
Init,
/// State after seeing the `<` symbol. Depending on the next symbol all other
/// events could be generated.
///
/// After generating one event the reader moves to the `InsideText` state.
InsideMarkup,
/// State in which reader searches the `<` symbol of a markup. All bytes before
/// that symbol will be returned in the [`Event::Text`] event. After that
/// the reader moves to the `InsideMarkup` state.
InsideText,
/// This state is used only if option [`expand_empty_elements`] is set to `true`.
/// Reader enters to this state when it is in a `InsideText` state and emits an
/// [`Event::Start`] event. The next event emitted will be an [`Event::End`],
/// after which reader returned to the `InsideText` state.
///
/// [`expand_empty_elements`]: Config::expand_empty_elements
InsideEmpty,
/// Reader enters this state when `Eof` event generated or an error occurred.
/// This is the last state, the reader stay in it forever.
Done,
}
/// A reference to an encoding together with information about how it was retrieved.
///
/// The state transition diagram:
///
/// ```mermaid
/// flowchart LR
/// Implicit -- from_str --> Explicit
/// Implicit -- BOM --> BomDetected
/// Implicit -- "encoding=..." --> XmlDetected
/// BomDetected -- "encoding=..." --> XmlDetected
/// ```
#[cfg(feature = "encoding")]
#[derive(Clone, Copy, Debug)]
enum EncodingRef {
/// Encoding was implicitly assumed to have a specified value. It can be refined
/// using BOM or by the XML declaration event (`<?xml encoding=... ?>`)
Implicit(&'static Encoding),
/// Encoding was explicitly set to the desired value. It cannot be changed
/// nor by BOM, nor by parsing XML declaration (`<?xml encoding=... ?>`)
Explicit(&'static Encoding),
/// Encoding was detected from a byte order mark (BOM) or by the first bytes
/// of the content. It can be refined by the XML declaration event (`<?xml encoding=... ?>`)
BomDetected(&'static Encoding),
/// Encoding was detected using XML declaration event (`<?xml encoding=... ?>`).
/// It can no longer change
XmlDetected(&'static Encoding),
}
#[cfg(feature = "encoding")]
impl EncodingRef {
#[inline]
const fn encoding(&self) -> &'static Encoding {
match self {
Self::Implicit(e) => e,
Self::Explicit(e) => e,
Self::BomDetected(e) => e,
Self::XmlDetected(e) => e,
}
}
#[inline]
const fn can_be_refined(&self) -> bool {
match self {
Self::Implicit(_) | Self::BomDetected(_) => true,
Self::Explicit(_) | Self::XmlDetected(_) => false,
}
}
}
////////////////////////////////////////////////////////////////////////////////////////////////////
/// A direct stream to the underlying [`Reader`]s reader which updates
/// [`Reader::buffer_position()`] when read from it.
#[derive(Debug)]
#[must_use = "streams do nothing unless read or polled"]
pub struct BinaryStream<'r, R> {
inner: &'r mut R,
offset: &'r mut u64,
}
impl<'r, R> BinaryStream<'r, R> {
/// Returns current position in bytes in the original source.
#[inline]
pub const fn offset(&self) -> u64 {
*self.offset
}
/// Gets a reference to the underlying reader.
#[inline]
pub const fn get_ref(&self) -> &R {
self.inner
}
/// Gets a mutable reference to the underlying reader.
///
/// Avoid read from this reader because this will not update reader's position
/// and will lead to incorrect positions of errors. Read from this stream instead.
#[inline]
pub fn get_mut(&mut self) -> &mut R {
self.inner
}
}
impl<'r, R> io::Read for BinaryStream<'r, R>
where
R: io::Read,
{
#[inline]
fn read(&mut self, buf: &mut [u8]) -> io::Result<usize> {
let amt = self.inner.read(buf)?;
*self.offset += amt as u64;
Ok(amt)
}
}
impl<'r, R> io::BufRead for BinaryStream<'r, R>
where
R: io::BufRead,
{
#[inline]
fn fill_buf(&mut self) -> io::Result<&[u8]> {
self.inner.fill_buf()
}
#[inline]
fn consume(&mut self, amt: usize) {
self.inner.consume(amt);
*self.offset += amt as u64;
}
}
////////////////////////////////////////////////////////////////////////////////////////////////////
/// A low level encoding-agnostic XML event reader.
///
/// Consumes bytes and streams XML [`Event`]s.
///
/// This reader does not manage namespace declarations and not able to resolve
/// prefixes. If you want these features, use the [`NsReader`].
///
/// # Examples
///
/// ```
/// use quick_xml::events::Event;
/// use quick_xml::reader::Reader;
///
/// let xml = r#"<tag1 att1 = "test">
/// <tag2><!--Test comment-->Test</tag2>
/// <tag2>Test 2</tag2>
/// </tag1>"#;
/// let mut reader = Reader::from_str(xml);
/// reader.config_mut().trim_text(true);
///
/// let mut count = 0;
/// let mut txt = Vec::new();
/// let mut buf = Vec::new();
///
/// // The `Reader` does not implement `Iterator` because it outputs borrowed data (`Cow`s)
/// loop {
/// // NOTE: this is the generic case when we don't know about the input BufRead.
/// // when the input is a &str or a &[u8], we don't actually need to use another
/// // buffer, we could directly call `reader.read_event()`
/// match reader.read_event_into(&mut buf) {
/// Err(e) => panic!("Error at position {}: {:?}", reader.error_position(), e),
/// // exits the loop when reaching end of file
/// Ok(Event::Eof) => break,
///
/// Ok(Event::Start(e)) => {
/// match e.name().as_ref() {
/// b"tag1" => println!("attributes values: {:?}",
/// e.attributes().map(|a| a.unwrap().value)
/// .collect::<Vec<_>>()),
/// b"tag2" => count += 1,
/// _ => (),
/// }
/// }
/// Ok(Event::Text(e)) => txt.push(e.unescape().unwrap().into_owned()),
///
/// // There are several other `Event`s we do not consider here
/// _ => (),
/// }
/// // if we don't keep a borrow elsewhere, we can clear the buffer to keep memory usage low
/// buf.clear();
/// }
/// ```
///
/// [`NsReader`]: crate::reader::NsReader
#[derive(Clone)]
pub struct Reader<R> {
/// Source of data for parse
reader: R,
/// Configuration and current parse state
state: ReaderState,
}
/// Builder methods
impl<R> Reader<R> {
/// Creates a `Reader` that reads from a given reader.
pub fn from_reader(reader: R) -> Self {
Self {
reader,
state: ReaderState::default(),
}
}
/// Returns reference to the parser configuration
pub const fn config(&self) -> &Config {
&self.state.config
}
/// Returns mutable reference to the parser configuration
pub fn config_mut(&mut self) -> &mut Config {
&mut self.state.config
}
}
/// Getters
impl<R> Reader<R> {
/// Consumes `Reader` returning the underlying reader
///
/// Can be used to compute line and column of a parsing error position
///
/// # Examples
///
/// ```
/// # use pretty_assertions::assert_eq;
/// use std::{str, io::Cursor};
/// use quick_xml::events::Event;
/// use quick_xml::reader::Reader;
///
/// let xml = r#"<tag1 att1 = "test">
/// <tag2><!--Test comment-->Test</tag2>
/// <tag3>Test 2</tag3>
/// </tag1>"#;
/// let mut reader = Reader::from_reader(Cursor::new(xml.as_bytes()));
/// let mut buf = Vec::new();
///
/// fn into_line_and_column(reader: Reader<Cursor<&[u8]>>) -> (usize, usize) {
/// // We known that size cannot exceed usize::MAX because we created parser from single &[u8]
/// let end_pos = reader.buffer_position() as usize;
/// let mut cursor = reader.into_inner();
/// let s = String::from_utf8(cursor.into_inner()[0..end_pos].to_owned())
/// .expect("can't make a string");
/// let mut line = 1;
/// let mut column = 0;
/// for c in s.chars() {
/// if c == '\n' {
/// line += 1;
/// column = 0;
/// } else {
/// column += 1;
/// }
/// }
/// (line, column)
/// }
///
/// loop {
/// match reader.read_event_into(&mut buf) {
/// Ok(Event::Start(ref e)) => match e.name().as_ref() {
/// b"tag1" | b"tag2" => (),
/// tag => {
/// assert_eq!(b"tag3", tag);
/// assert_eq!((3, 22), into_line_and_column(reader));
/// break;
/// }
/// },
/// Ok(Event::Eof) => unreachable!(),
/// _ => (),
/// }
/// buf.clear();
/// }
/// ```
pub fn into_inner(self) -> R {
self.reader
}
/// Gets a reference to the underlying reader.
pub const fn get_ref(&self) -> &R {
&self.reader
}
/// Gets a mutable reference to the underlying reader.
///
/// Avoid read from this reader because this will not update reader's position
/// and will lead to incorrect positions of errors. If you want to read, use
/// [`stream()`] instead.
///
/// [`stream()`]: Self::stream
pub fn get_mut(&mut self) -> &mut R {
&mut self.reader
}
/// Gets the current byte position in the input data.
pub const fn buffer_position(&self) -> u64 {
// when internal state is InsideMarkup, we have actually read until '<',
// which we don't want to show
if let ParseState::InsideMarkup = self.state.state {
self.state.offset - 1
} else {
self.state.offset
}
}
/// Gets the last error byte position in the input data. If there is no errors
/// yet, returns `0`.
///
/// Unlike `buffer_position` it will point to the place where it is rational
/// to report error to the end user. For example, all [`SyntaxError`]s are
/// reported when the parser sees EOF inside of some kind of markup. The
/// `buffer_position()` will point to the last byte of input which is not
/// very useful. `error_position()` will point to the start of corresponding
/// markup element (i. e. to the `<` character).
///
/// This position is always `<= buffer_position()`.
pub const fn error_position(&self) -> u64 {
self.state.last_error_offset
}
/// Get the decoder, used to decode bytes, read by this reader, to the strings.
///
/// If [`encoding`] feature is enabled, the used encoding may change after
/// parsing the XML declaration, otherwise encoding is fixed to UTF-8.
///
/// If [`encoding`] feature is enabled and no encoding is specified in declaration,
/// defaults to UTF-8.
///
/// [`encoding`]: ../index.html#encoding
#[inline]
pub const fn decoder(&self) -> Decoder {
self.state.decoder()
}
/// Get the direct access to the underlying reader, but tracks the amount of
/// read data and update [`Reader::buffer_position()`] accordingly.
///
/// Note, that this method gives you access to the internal reader and read
/// data will not be returned in any subsequent events read by `read_event`
/// family of methods.
///
/// # Example
///
/// This example demonstrates how to read stream raw bytes from an XML document.
/// This could be used to implement streaming read of text, or to read raw binary
/// bytes embedded in an XML document. (Documents with embedded raw bytes are not
/// valid XML, but XML-derived file formats exist where such documents are valid).
///
/// ```
/// # use pretty_assertions::assert_eq;
/// use std::io::{BufRead, Read};
/// use quick_xml::events::{BytesEnd, BytesStart, Event};
/// use quick_xml::reader::Reader;
///
/// let mut reader = Reader::from_str("<tag>binary << data&></tag>");
/// // ^ ^ ^ ^
/// // 0 5 21 27
///
/// assert_eq!(
/// (reader.read_event().unwrap(), reader.buffer_position()),
/// // 5 - end of the `<tag>`
/// (Event::Start(BytesStart::new("tag")), 5)
/// );
///
/// // Reading directly from underlying reader will not update position
/// // let mut inner = reader.get_mut();
///
/// // Reading from the stream() advances position
/// let mut inner = reader.stream();
///
/// // Read binary data. We must know its size
/// let mut binary = [0u8; 16];
/// inner.read_exact(&mut binary).unwrap();
/// assert_eq!(&binary, b"binary << data&>");
/// // 21 - end of the `binary << data&>`
/// assert_eq!(inner.offset(), 21);
/// assert_eq!(reader.buffer_position(), 21);
///
/// assert_eq!(
/// (reader.read_event().unwrap(), reader.buffer_position()),
/// // 27 - end of the `</tag>`
/// (Event::End(BytesEnd::new("tag")), 27)
/// );
///
/// assert_eq!(reader.read_event().unwrap(), Event::Eof);
/// ```
#[inline]
pub fn stream(&mut self) -> BinaryStream<R> {
BinaryStream {
inner: &mut self.reader,
offset: &mut self.state.offset,
}
}
}
/// Private sync reading methods
impl<R> Reader<R> {
/// Read text into the given buffer, and return an event that borrows from
/// either that buffer or from the input itself, based on the type of the
/// reader.
fn read_event_impl<'i, B>(&mut self, mut buf: B) -> Result<Event<'i>, Error>
where
R: XmlSource<'i, B>,
{
read_event_impl!(self, buf, self.reader, read_until_close)
}
/// Private function to read until `>` is found. This function expects that
/// it was called just after encounter a `<` symbol.
fn read_until_close<'i, B>(&mut self, buf: B) -> Result<Event<'i>, Error>
where
R: XmlSource<'i, B>,
{
read_until_close!(self, buf, self.reader)
}
}
////////////////////////////////////////////////////////////////////////////////////////////////////
/// Result of an attempt to read XML textual data from the reader.
enum ReadTextResult<'r, B> {
/// Start of markup (`<` character) was found in the first byte.
/// Contains buffer that should be returned back to the next iteration cycle
/// to satisfy borrow checker requirements.
Markup(B),
/// Contains text block up to start of markup (`<` character).
UpToMarkup(&'r [u8]),
/// Contains text block up to EOF, start of markup (`<` character) was not found.
UpToEof(&'r [u8]),
/// IO error occurred.
Err(io::Error),
}
/// Represents an input for a reader that can return borrowed data.
///
/// There are two implementors of this trait: generic one that read data from
/// `Self`, copies some part of it into a provided buffer of type `B` and then
/// returns data that borrow from that buffer.
///
/// The other implementor is for `&[u8]` and instead of copying data returns
/// borrowed data from `Self` instead. This implementation allows zero-copy
/// deserialization.
///
/// # Parameters
/// - `'r`: lifetime of a buffer from which events will borrow
/// - `B`: a type of a buffer that can be used to store data read from `Self` and
/// from which events can borrow
trait XmlSource<'r, B> {
/// Removes UTF-8 BOM if it is present
#[cfg(not(feature = "encoding"))]
fn remove_utf8_bom(&mut self) -> io::Result<()>;
/// Determines encoding from the start of input and removes BOM if it is present
#[cfg(feature = "encoding")]
fn detect_encoding(&mut self) -> io::Result<Option<&'static Encoding>>;
/// Read input until start of markup (the `<`) is found or end of input is reached.
///
/// # Parameters
/// - `buf`: Buffer that could be filled from an input (`Self`) and
/// from which [events] could borrow their data
/// - `position`: Will be increased by amount of bytes consumed
///
/// [events]: crate::events::Event
fn read_text(&mut self, buf: B, position: &mut u64) -> ReadTextResult<'r, B>;
/// Read input until processing instruction is finished.
///
/// This method expect that start sequence of a parser already was read.
///
/// Returns a slice of data read up to the end of the thing being parsed.
/// The end of thing and the returned content is determined by the used parser.
///
/// If input (`Self`) is exhausted and no bytes was read, or if the specified
/// parser could not find the ending sequence of the thing, returns `SyntaxError`.
///
/// # Parameters
/// - `buf`: Buffer that could be filled from an input (`Self`) and
/// from which [events] could borrow their data
/// - `position`: Will be increased by amount of bytes consumed
///
/// A `P` type parameter is used to preserve state between calls to the underlying
/// reader which provides bytes fed into the parser.
///
/// [events]: crate::events::Event
fn read_with<P>(&mut self, parser: P, buf: B, position: &mut u64) -> Result<&'r [u8], Error>
where
P: Parser;
/// Read input until comment or CDATA is finished.
///
/// This method expect that `<` already was read.
///
/// Returns a slice of data read up to end of comment or CDATA (`>`),
/// which does not include into result.
///
/// If input (`Self`) is exhausted and nothing was read, returns `None`.
///
/// # Parameters
/// - `buf`: Buffer that could be filled from an input (`Self`) and
/// from which [events] could borrow their data
/// - `position`: Will be increased by amount of bytes consumed
///
/// [events]: crate::events::Event
fn read_bang_element(
&mut self,
buf: B,
position: &mut u64,
) -> Result<(BangType, &'r [u8]), Error>;
/// Consume and discard all the whitespace until the next non-whitespace
/// character or EOF.
///
/// # Parameters
/// - `position`: Will be increased by amount of bytes consumed
fn skip_whitespace(&mut self, position: &mut u64) -> io::Result<()>;
/// Return one character without consuming it, so that future `read_*` calls
/// will still include it. On EOF, return `None`.
fn peek_one(&mut self) -> io::Result<Option<u8>>;
}
/// Possible elements started with `<!`
#[derive(Debug, PartialEq)]
enum BangType {
/// <![CDATA[...]]>
CData,
/// <!--...-->
Comment,
/// <!DOCTYPE...>. Contains balance of '<' (+1) and '>' (-1)
DocType(i32),
}
impl BangType {
#[inline(always)]
const fn new(byte: Option<u8>) -> Result<Self, SyntaxError> {
Ok(match byte {
Some(b'[') => Self::CData,
Some(b'-') => Self::Comment,
Some(b'D') | Some(b'd') => Self::DocType(0),
_ => return Err(SyntaxError::InvalidBangMarkup),
})
}
/// If element is finished, returns its content up to `>` symbol and
/// an index of this symbol, otherwise returns `None`
///
/// # Parameters
/// - `buf`: buffer with data consumed on previous iterations
/// - `chunk`: data read on current iteration and not yet consumed from reader
#[inline(always)]
fn parse<'b>(&mut self, buf: &[u8], chunk: &'b [u8]) -> Option<(&'b [u8], usize)> {
match self {
Self::Comment => {
for i in memchr::memchr_iter(b'>', chunk) {
// Need to read at least 6 symbols (`!---->`) for properly finished comment
// <!----> - XML comment
// 012345 - i
if buf.len() + i > 4 {
if chunk[..i].ends_with(b"--") {
// We cannot strip last `--` from the buffer because we need it in case of
// check_comments enabled option. XML standard requires that comment
// will not end with `--->` sequence because this is a special case of
// `--` in the comment (https://www.w3.org/TR/xml11/#sec-comments)
return Some((&chunk[..i], i + 1)); // +1 for `>`
}
// End sequence `-|->` was splitted at |
// buf --/ \-- chunk
if i == 1 && buf.ends_with(b"-") && chunk[0] == b'-' {
return Some((&chunk[..i], i + 1)); // +1 for `>`
}
// End sequence `--|>` was splitted at |
// buf --/ \-- chunk
if i == 0 && buf.ends_with(b"--") {
return Some((&[], i + 1)); // +1 for `>`
}
}
}
}
Self::CData => {
for i in memchr::memchr_iter(b'>', chunk) {
if chunk[..i].ends_with(b"]]") {
return Some((&chunk[..i], i + 1)); // +1 for `>`
}
// End sequence `]|]>` was splitted at |
// buf --/ \-- chunk
if i == 1 && buf.ends_with(b"]") && chunk[0] == b']' {
return Some((&chunk[..i], i + 1)); // +1 for `>`
}
// End sequence `]]|>` was splitted at |
// buf --/ \-- chunk
if i == 0 && buf.ends_with(b"]]") {
return Some((&[], i + 1)); // +1 for `>`
}
}
}
Self::DocType(ref mut balance) => {
for i in memchr::memchr2_iter(b'<', b'>', chunk) {
if chunk[i] == b'<' {
*balance += 1;
} else {
if *balance == 0 {
return Some((&chunk[..i], i + 1)); // +1 for `>`
}
*balance -= 1;
}
}
}
}
None
}
#[inline]
const fn to_err(&self) -> SyntaxError {
match self {
Self::CData => SyntaxError::UnclosedCData,
Self::Comment => SyntaxError::UnclosedComment,
Self::DocType(_) => SyntaxError::UnclosedDoctype,
}
}
}
////////////////////////////////////////////////////////////////////////////////////////////////////
#[cfg(test)]
mod test {
/// Checks the internal implementation of the various reader methods
macro_rules! check {
(
#[$test:meta]
$read_event:ident,
$read_until_close:ident,
// constructor of the XML source on which internal functions will be called
$source:path,
// constructor of the buffer to which read data will stored
$buf:expr
$(, $async:ident, $await:ident)?
) => {
mod read_bang_element {
use super::*;
use crate::errors::{Error, SyntaxError};
use crate::reader::BangType;
use crate::utils::Bytes;
/// Checks that reading CDATA content works correctly
mod cdata {
use super::*;
use pretty_assertions::assert_eq;
/// Checks that if input begins like CDATA element, but CDATA start sequence
/// is not finished, parsing ends with an error
#[$test]
#[ignore = "start CDATA sequence fully checked outside of `read_bang_element`"]
$($async)? fn not_properly_start() {
let buf = $buf;
let mut position = 1;
let mut input = b"![]]>other content".as_ref();
// ^= 1
match $source(&mut input).read_bang_element(buf, &mut position) $(.$await)? {
Err(Error::Syntax(cause)) => assert_eq!(cause, SyntaxError::UnclosedCData),
x => panic!(
"Expected `Err(Syntax(_))`, but got `{:?}`",
x
),
}
assert_eq!(position, 1);
}
/// Checks that if CDATA startup sequence was matched, but an end sequence
/// is not found, parsing ends with an error
#[$test]
$($async)? fn not_closed() {
let buf = $buf;
let mut position = 1;
let mut input = b"![CDATA[other content".as_ref();
// ^= 1 ^= 22
match $source(&mut input).read_bang_element(buf, &mut position) $(.$await)? {
Err(Error::Syntax(cause)) => assert_eq!(cause, SyntaxError::UnclosedCData),
x => panic!(
"Expected `Err(Syntax(_))`, but got `{:?}`",
x
),
}
assert_eq!(position, 22);
}
/// Checks that CDATA element without content inside parsed successfully
#[$test]
$($async)? fn empty() {
let buf = $buf;
let mut position = 1;
let mut input = b"![CDATA[]]>other content".as_ref();
// ^= 1 ^= 12
let (ty, bytes) = $source(&mut input)
.read_bang_element(buf, &mut position)
$(.$await)?
.unwrap();
assert_eq!(
(ty, Bytes(bytes)),
(BangType::CData, Bytes(b"![CDATA[]]"))
);
assert_eq!(position, 12);
}
/// Checks that CDATA element with content parsed successfully.
/// Additionally checks that sequences inside CDATA that may look like
/// a CDATA end sequence do not interrupt CDATA parsing
#[$test]
$($async)? fn with_content() {
let buf = $buf;
let mut position = 1;
let mut input = b"![CDATA[cdata]] ]>content]]>other content]]>".as_ref();
// ^= 1 ^= 29
let (ty, bytes) = $source(&mut input)
.read_bang_element(buf, &mut position)
$(.$await)?
.unwrap();
assert_eq!(
(ty, Bytes(bytes)),
(BangType::CData, Bytes(b"![CDATA[cdata]] ]>content]]"))
);
assert_eq!(position, 29);
}
}
/// Checks that reading XML comments works correctly. According to the [specification],
/// comment data can contain any sequence except `--`:
///
/// ```peg
/// comment = '<--' (!'--' char)* '-->';
/// char = [#x1-#x2C]
/// / [#x2E-#xD7FF]
/// / [#xE000-#xFFFD]
/// / [#x10000-#x10FFFF]
/// ```
///
/// The presence of this limitation, however, is simply a poorly designed specification
/// (maybe for purpose of building of LL(1) XML parser) and quick-xml does not check for
/// presence of these sequences by default. This tests allow such content.
///
/// [specification]: https://www.w3.org/TR/xml11/#dt-comment
mod comment {
use super::*;
use pretty_assertions::assert_eq;
#[$test]
#[ignore = "start comment sequence fully checked outside of `read_bang_element`"]
$($async)? fn not_properly_start() {
let buf = $buf;
let mut position = 1;
let mut input = b"!- -->other content".as_ref();
// ^= 1
match $source(&mut input).read_bang_element(buf, &mut position) $(.$await)? {
Err(Error::Syntax(cause)) => assert_eq!(cause, SyntaxError::UnclosedComment),
x => panic!(
"Expected `Err(Syntax(_))`, but got `{:?}`",
x
),
}
assert_eq!(position, 1);
}
#[$test]
$($async)? fn not_properly_end() {
let buf = $buf;
let mut position = 1;
let mut input = b"!->other content".as_ref();
// ^= 1 ^= 17
match $source(&mut input).read_bang_element(buf, &mut position) $(.$await)? {
Err(Error::Syntax(cause)) => assert_eq!(cause, SyntaxError::UnclosedComment),
x => panic!(
"Expected `Err(Syntax(_))`, but got `{:?}`",
x
),
}
assert_eq!(position, 17);
}
#[$test]
$($async)? fn not_closed1() {
let buf = $buf;
let mut position = 1;
let mut input = b"!--other content".as_ref();
// ^= 1 ^= 17
match $source(&mut input).read_bang_element(buf, &mut position) $(.$await)? {
Err(Error::Syntax(cause)) => assert_eq!(cause, SyntaxError::UnclosedComment),
x => panic!(
"Expected `Err(Syntax(_))`, but got `{:?}`",
x
),
}
assert_eq!(position, 17);
}
#[$test]
$($async)? fn not_closed2() {
let buf = $buf;
let mut position = 1;
let mut input = b"!-->other content".as_ref();
// ^= 1 ^= 18
match $source(&mut input).read_bang_element(buf, &mut position) $(.$await)? {
Err(Error::Syntax(cause)) => assert_eq!(cause, SyntaxError::UnclosedComment),
x => panic!(
"Expected `Err(Syntax(_))`, but got `{:?}`",
x
),
}
assert_eq!(position, 18);
}
#[$test]
$($async)? fn not_closed3() {
let buf = $buf;
let mut position = 1;
let mut input = b"!--->other content".as_ref();
// ^= 1 ^= 19
match $source(&mut input).read_bang_element(buf, &mut position) $(.$await)? {
Err(Error::Syntax(cause)) => assert_eq!(cause, SyntaxError::UnclosedComment),
x => panic!(
"Expected `Err(Syntax(_))`, but got `{:?}`",
x
),
}
assert_eq!(position, 19);
}
#[$test]
$($async)? fn empty() {
let buf = $buf;
let mut position = 1;
let mut input = b"!---->other content".as_ref();
// ^= 1 ^= 7
let (ty, bytes) = $source(&mut input)
.read_bang_element(buf, &mut position)
$(.$await)?
.unwrap();
assert_eq!(
(ty, Bytes(bytes)),
(BangType::Comment, Bytes(b"!----"))
);
assert_eq!(position, 7);
}
#[$test]
$($async)? fn with_content() {
let buf = $buf;
let mut position = 1;
let mut input = b"!--->comment<--->other content".as_ref();
// ^= 1 ^= 18
let (ty, bytes) = $source(&mut input)
.read_bang_element(buf, &mut position)
$(.$await)?
.unwrap();
assert_eq!(
(ty, Bytes(bytes)),
(BangType::Comment, Bytes(b"!--->comment<---"))
);
assert_eq!(position, 18);
}
}
/// Checks that reading DOCTYPE definition works correctly
mod doctype {
use super::*;
mod uppercase {
use super::*;
use pretty_assertions::assert_eq;
#[$test]
$($async)? fn not_properly_start() {
let buf = $buf;
let mut position = 1;
let mut input = b"!D other content".as_ref();
// ^= 1 ^= 17
match $source(&mut input).read_bang_element(buf, &mut position) $(.$await)? {
Err(Error::Syntax(cause)) => assert_eq!(cause, SyntaxError::UnclosedDoctype),
x => panic!(
"Expected `Err(Syntax(_))`, but got `{:?}`",
x
),
}
assert_eq!(position, 17);
}
#[$test]
$($async)? fn without_space() {
let buf = $buf;
let mut position = 1;
let mut input = b"!DOCTYPEother content".as_ref();
// ^= 1 ^= 22
match $source(&mut input).read_bang_element(buf, &mut position) $(.$await)? {
Err(Error::Syntax(cause)) => assert_eq!(cause, SyntaxError::UnclosedDoctype),
x => panic!(
"Expected `Err(Syntax(_))`, but got `{:?}`",
x
),
}
assert_eq!(position, 22);
}
#[$test]
$($async)? fn empty() {
let buf = $buf;
let mut position = 1;
let mut input = b"!DOCTYPE>other content".as_ref();
// ^= 1 ^= 10
let (ty, bytes) = $source(&mut input)
.read_bang_element(buf, &mut position)
$(.$await)?
.unwrap();
assert_eq!(
(ty, Bytes(bytes)),
(BangType::DocType(0), Bytes(b"!DOCTYPE"))
);
assert_eq!(position, 10);
}
#[$test]
$($async)? fn not_closed() {
let buf = $buf;
let mut position = 1;
let mut input = b"!DOCTYPE other content".as_ref();
// ^= 1 ^23
match $source(&mut input).read_bang_element(buf, &mut position) $(.$await)? {
Err(Error::Syntax(cause)) => assert_eq!(cause, SyntaxError::UnclosedDoctype),
x => panic!(
"Expected `Err(Syntax(_))`, but got `{:?}`",
x
),
}
assert_eq!(position, 23);
}
}
mod lowercase {
use super::*;
use pretty_assertions::assert_eq;
#[$test]
$($async)? fn not_properly_start() {
let buf = $buf;
let mut position = 1;
let mut input = b"!d other content".as_ref();
// ^= 1 ^= 17
match $source(&mut input).read_bang_element(buf, &mut position) $(.$await)? {
Err(Error::Syntax(cause)) => assert_eq!(cause, SyntaxError::UnclosedDoctype),
x => panic!(
"Expected `Err(Syntax(_))`, but got `{:?}`",
x
),
}
assert_eq!(position, 17);
}
#[$test]
$($async)? fn without_space() {
let buf = $buf;
let mut position = 1;
let mut input = b"!doctypeother content".as_ref();
// ^= 1 ^= 22
match $source(&mut input).read_bang_element(buf, &mut position) $(.$await)? {
Err(Error::Syntax(cause)) => assert_eq!(cause, SyntaxError::UnclosedDoctype),
x => panic!(
"Expected `Err(Syntax(_))`, but got `{:?}`",
x
),
}
assert_eq!(position, 22);
}
#[$test]
$($async)? fn empty() {
let buf = $buf;
let mut position = 1;
let mut input = b"!doctype>other content".as_ref();
// ^= 1 ^= 10
let (ty, bytes) = $source(&mut input)
.read_bang_element(buf, &mut position)
$(.$await)?
.unwrap();
assert_eq!(
(ty, Bytes(bytes)),
(BangType::DocType(0), Bytes(b"!doctype"))
);
assert_eq!(position, 10);
}
#[$test]
$($async)? fn not_closed() {
let buf = $buf;
let mut position = 1;
let mut input = b"!doctype other content".as_ref();
// ^= 1 ^= 23
match $source(&mut input).read_bang_element(buf, &mut position) $(.$await)? {
Err(Error::Syntax(cause)) => assert_eq!(cause, SyntaxError::UnclosedDoctype),
x => panic!(
"Expected `Err(Syntax(_))`, but got `{:?}`",
x
),
}
assert_eq!(position, 23);
}
}
}
}
mod read_element {
use super::*;
use crate::errors::{Error, SyntaxError};
use crate::parser::ElementParser;
use crate::utils::Bytes;
use pretty_assertions::assert_eq;
/// Checks that nothing was read from empty buffer
#[$test]
$($async)? fn empty() {
let buf = $buf;
let mut position = 1;
let mut input = b"".as_ref();
// ^= 1
match $source(&mut input).read_with(ElementParser::default(), buf, &mut position) $(.$await)? {
Err(Error::Syntax(cause)) => assert_eq!(cause, SyntaxError::UnclosedTag),
x => panic!(
"Expected `Err(Syntax(_))`, but got `{:?}`",
x
),
}
assert_eq!(position, 1);
}
mod open {
use super::*;
use pretty_assertions::assert_eq;
#[$test]
$($async)? fn empty_tag() {
let buf = $buf;
let mut position = 1;
let mut input = b">".as_ref();
// ^= 2
assert_eq!(
Bytes($source(&mut input).read_with(ElementParser::default(), buf, &mut position) $(.$await)? .unwrap()),
Bytes(b"")
);
assert_eq!(position, 2);
}
#[$test]
$($async)? fn normal() {
let buf = $buf;
let mut position = 1;
let mut input = b"tag>".as_ref();
// ^= 5
assert_eq!(
Bytes($source(&mut input).read_with(ElementParser::default(), buf, &mut position) $(.$await)? .unwrap()),
Bytes(b"tag")
);
assert_eq!(position, 5);
}
#[$test]
$($async)? fn empty_ns_empty_tag() {
let buf = $buf;
let mut position = 1;
let mut input = b":>".as_ref();
// ^= 3
assert_eq!(
Bytes($source(&mut input).read_with(ElementParser::default(), buf, &mut position) $(.$await)? .unwrap()),
Bytes(b":")
);
assert_eq!(position, 3);
}
#[$test]
$($async)? fn empty_ns() {
let buf = $buf;
let mut position = 1;
let mut input = b":tag>".as_ref();
// ^= 6
assert_eq!(
Bytes($source(&mut input).read_with(ElementParser::default(), buf, &mut position) $(.$await)? .unwrap()),
Bytes(b":tag")
);
assert_eq!(position, 6);
}
#[$test]
$($async)? fn with_attributes() {
let buf = $buf;
let mut position = 1;
let mut input = br#"tag attr-1=">" attr2 = '>' 3attr>"#.as_ref();
// ^= 39
assert_eq!(
Bytes($source(&mut input).read_with(ElementParser::default(), buf, &mut position) $(.$await)? .unwrap()),
Bytes(br#"tag attr-1=">" attr2 = '>' 3attr"#)
);
assert_eq!(position, 39);
}
}
mod self_closed {
use super::*;
use pretty_assertions::assert_eq;
#[$test]
$($async)? fn empty_tag() {
let buf = $buf;
let mut position = 1;
let mut input = b"/>".as_ref();
// ^= 3
assert_eq!(
Bytes($source(&mut input).read_with(ElementParser::default(), buf, &mut position) $(.$await)? .unwrap()),
Bytes(b"/")
);
assert_eq!(position, 3);
}
#[$test]
$($async)? fn normal() {
let buf = $buf;
let mut position = 1;
let mut input = b"tag/>".as_ref();
// ^= 6
assert_eq!(
Bytes($source(&mut input).read_with(ElementParser::default(), buf, &mut position) $(.$await)? .unwrap()),
Bytes(b"tag/")
);
assert_eq!(position, 6);
}
#[$test]
$($async)? fn empty_ns_empty_tag() {
let buf = $buf;
let mut position = 1;
let mut input = b":/>".as_ref();
// ^= 4
assert_eq!(
Bytes($source(&mut input).read_with(ElementParser::default(), buf, &mut position) $(.$await)? .unwrap()),
Bytes(b":/")
);
assert_eq!(position, 4);
}
#[$test]
$($async)? fn empty_ns() {
let buf = $buf;
let mut position = 1;
let mut input = b":tag/>".as_ref();
// ^= 7
assert_eq!(
Bytes($source(&mut input).read_with(ElementParser::default(), buf, &mut position) $(.$await)? .unwrap()),
Bytes(b":tag/")
);
assert_eq!(position, 7);
}
#[$test]
$($async)? fn with_attributes() {
let buf = $buf;
let mut position = 1;
let mut input = br#"tag attr-1="/>" attr2 = '/>' 3attr/>"#.as_ref();
// ^= 42
assert_eq!(
Bytes($source(&mut input).read_with(ElementParser::default(), buf, &mut position) $(.$await)? .unwrap()),
Bytes(br#"tag attr-1="/>" attr2 = '/>' 3attr/"#)
);
assert_eq!(position, 42);
}
}
mod close {
use super::*;
use pretty_assertions::assert_eq;
#[$test]
$($async)? fn empty_tag() {
let buf = $buf;
let mut position = 1;
let mut input = b"/ >".as_ref();
// ^= 4
assert_eq!(
Bytes($source(&mut input).read_with(ElementParser::default(), buf, &mut position) $(.$await)? .unwrap()),
Bytes(b"/ ")
);
assert_eq!(position, 4);
}
#[$test]
$($async)? fn normal() {
let buf = $buf;
let mut position = 1;
let mut input = b"/tag>".as_ref();
// ^= 6
assert_eq!(
Bytes($source(&mut input).read_with(ElementParser::default(), buf, &mut position) $(.$await)? .unwrap()),
Bytes(b"/tag")
);
assert_eq!(position, 6);
}
#[$test]
$($async)? fn empty_ns_empty_tag() {
let buf = $buf;
let mut position = 1;
let mut input = b"/:>".as_ref();
// ^= 4
assert_eq!(
Bytes($source(&mut input).read_with(ElementParser::default(), buf, &mut position) $(.$await)? .unwrap()),
Bytes(b"/:")
);
assert_eq!(position, 4);
}
#[$test]
$($async)? fn empty_ns() {
let buf = $buf;
let mut position = 1;
let mut input = b"/:tag>".as_ref();
// ^= 7
assert_eq!(
Bytes($source(&mut input).read_with(ElementParser::default(), buf, &mut position) $(.$await)? .unwrap()),
Bytes(b"/:tag")
);
assert_eq!(position, 7);
}
#[$test]
$($async)? fn with_attributes() {
let buf = $buf;
let mut position = 1;
let mut input = br#"/tag attr-1=">" attr2 = '>' 3attr>"#.as_ref();
// ^= 40
assert_eq!(
Bytes($source(&mut input).read_with(ElementParser::default(), buf, &mut position) $(.$await)? .unwrap()),
Bytes(br#"/tag attr-1=">" attr2 = '>' 3attr"#)
);
assert_eq!(position, 40);
}
}
}
/// Ensures, that no empty `Text` events are generated
mod $read_event {
use crate::events::{BytesCData, BytesDecl, BytesEnd, BytesPI, BytesStart, BytesText, Event};
use crate::reader::Reader;
use pretty_assertions::assert_eq;
/// When `encoding` feature is enabled, encoding should be detected
/// from BOM (UTF-8) and BOM should be stripped.
///
/// When `encoding` feature is disabled, UTF-8 is assumed and BOM
/// character should be stripped for consistency
#[$test]
$($async)? fn bom_from_reader() {
let mut reader = Reader::from_reader("\u{feff}\u{feff}".as_bytes());
assert_eq!(
reader.$read_event($buf) $(.$await)? .unwrap(),
Event::Text(BytesText::from_escaped("\u{feff}"))
);
assert_eq!(
reader.$read_event($buf) $(.$await)? .unwrap(),
Event::Eof
);
}
/// When parsing from &str, encoding is fixed (UTF-8), so
/// - when `encoding` feature is disabled, the behavior the
/// same as in `bom_from_reader` text
/// - when `encoding` feature is enabled, the behavior should
/// stay consistent, so the first BOM character is stripped
#[$test]
$($async)? fn bom_from_str() {
let mut reader = Reader::from_str("\u{feff}\u{feff}");
assert_eq!(
reader.$read_event($buf) $(.$await)? .unwrap(),
Event::Text(BytesText::from_escaped("\u{feff}"))
);
assert_eq!(
reader.$read_event($buf) $(.$await)? .unwrap(),
Event::Eof
);
}
#[$test]
$($async)? fn declaration() {
let mut reader = Reader::from_str("<?xml ?>");
assert_eq!(
reader.$read_event($buf) $(.$await)? .unwrap(),
Event::Decl(BytesDecl::from_start(BytesStart::from_content("xml ", 3)))
);
}
#[$test]
$($async)? fn doctype() {
let mut reader = Reader::from_str("<!DOCTYPE x>");
assert_eq!(
reader.$read_event($buf) $(.$await)? .unwrap(),
Event::DocType(BytesText::from_escaped("x"))
);
}
#[$test]
$($async)? fn processing_instruction() {
let mut reader = Reader::from_str("<?xml-stylesheet '? >\" ?>");
assert_eq!(
reader.$read_event($buf) $(.$await)? .unwrap(),
Event::PI(BytesPI::new("xml-stylesheet '? >\" "))
);
}
/// Lone closing tags are not allowed, so testing it together with start tag
#[$test]
$($async)? fn start_and_end() {
let mut reader = Reader::from_str("<tag></tag>");
assert_eq!(
reader.$read_event($buf) $(.$await)? .unwrap(),
Event::Start(BytesStart::new("tag"))
);
assert_eq!(
reader.$read_event($buf) $(.$await)? .unwrap(),
Event::End(BytesEnd::new("tag"))
);
}
#[$test]
$($async)? fn empty() {
let mut reader = Reader::from_str("<tag/>");
assert_eq!(
reader.$read_event($buf) $(.$await)? .unwrap(),
Event::Empty(BytesStart::new("tag"))
);
}
#[$test]
$($async)? fn text() {
let mut reader = Reader::from_str("text");
assert_eq!(
reader.$read_event($buf) $(.$await)? .unwrap(),
Event::Text(BytesText::from_escaped("text"))
);
}
#[$test]
$($async)? fn cdata() {
let mut reader = Reader::from_str("<![CDATA[]]>");
assert_eq!(
reader.$read_event($buf) $(.$await)? .unwrap(),
Event::CData(BytesCData::new(""))
);
}
#[$test]
$($async)? fn comment() {
let mut reader = Reader::from_str("<!---->");
assert_eq!(
reader.$read_event($buf) $(.$await)? .unwrap(),
Event::Comment(BytesText::from_escaped(""))
);
}
#[$test]
$($async)? fn eof() {
let mut reader = Reader::from_str("");
assert_eq!(
reader.$read_event($buf) $(.$await)? .unwrap(),
Event::Eof
);
}
}
};
}
// Export macros for the child modules:
// - buffered_reader
// - slice_reader
pub(super) use check;
}