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
/*!
Represent an [XML 1.0](https://www.w3.org/TR/xml/) document as a read-only tree.
The root point of the documentations is [`Document::parse`].
You can find more details in the [README] and the [parsing doc].
The tree structure itself is a heavily modified <https://github.com/causal-agent/ego-tree>
License: ISC.
[`Document::parse`]: struct.Document.html#method.parse
[README]: https://github.com/RazrFalcon/roxmltree/blob/master/README.md
[parsing doc]: https://github.com/RazrFalcon/roxmltree/blob/master/docs/parsing.md
*/
#![no_std]
#![forbid(unsafe_code)]
#![warn(missing_docs)]
#![warn(missing_copy_implementations)]
#![warn(missing_debug_implementations)]
// `matches!` available since 1.42, but we target 1.36 for now.
#![allow(clippy::match_like_matches_macro)]
extern crate alloc;
#[cfg(feature = "std")]
extern crate std;
use core::cmp::Ordering;
use core::fmt;
use core::hash::{Hash, Hasher};
use core::num::NonZeroU32;
use core::ops::Range;
use alloc::vec::Vec;
pub use xmlparser::TextPos;
mod parse;
pub use crate::parse::*;
/// The <http://www.w3.org/XML/1998/namespace> URI.
pub const NS_XML_URI: &str = "http://www.w3.org/XML/1998/namespace";
/// The prefix 'xml', which is by definition bound to NS_XML_URI
const NS_XML_PREFIX: &str = "xml";
/// The <http://www.w3.org/2000/xmlns/> URI.
pub const NS_XMLNS_URI: &str = "http://www.w3.org/2000/xmlns/";
/// The string 'xmlns', which is used to declare new namespaces
const XMLNS: &str = "xmlns";
/// An XML tree container.
///
/// A tree consists of [`Nodes`].
/// There are no separate structs for each node type.
/// So you should check the current node type yourself via [`Node::node_type()`].
/// There are only [5 types](enum.NodeType.html):
/// Root, Element, PI, Comment and Text.
///
/// As you can see there are no XML declaration and CDATA types.
/// The XML declaration is basically skipped, since it doesn't contain any
/// valuable information (we support only UTF-8 anyway).
/// And CDATA will be converted into a Text node as is, without
/// any preprocessing (you can read more about it
/// [here](https://github.com/RazrFalcon/roxmltree/blob/master/docs/parsing.md)).
///
/// Also, the Text node data can be accessed from the text node itself or from
/// the parent element via [`Node::text()`] or [`Node::tail()`].
///
/// [`Nodes`]: struct.Node.html
/// [`Node::node_type()`]: struct.Node.html#method.node_type
/// [`Node::text()`]: struct.Node.html#method.text
/// [`Node::tail()`]: struct.Node.html#method.tail
pub struct Document<'input> {
/// An original data.
///
/// Required for `text_pos_at` methods.
text: &'input str,
nodes: Vec<NodeData<'input>>,
attributes: Vec<AttributeData<'input>>,
namespaces: Namespaces<'input>,
}
impl<'input> Document<'input> {
/// Returns the root node.
///
/// # Examples
///
/// ```
/// let doc = roxmltree::Document::parse("<e/>").unwrap();
/// assert!(doc.root().is_root());
/// assert!(doc.root().first_child().unwrap().has_tag_name("e"));
/// ```
#[inline]
pub fn root<'a>(&'a self) -> Node<'a, 'input> {
Node {
id: NodeId::new(0),
d: &self.nodes[0],
doc: self,
}
}
/// Returns the node of the tree with the given NodeId.
///
/// Note: NodeId::new(0) represents the root node
///
/// # Examples
///
/// ```
/// let doc = roxmltree::Document::parse("\
/// <p>
/// text
/// </p>
/// ").unwrap();
///
/// use roxmltree::NodeId;
/// assert_eq!(doc.get_node(NodeId::new(0)).unwrap(), doc.root());
/// assert_eq!(doc.get_node(NodeId::new(1)), doc.descendants().find(|n| n.has_tag_name("p")));
/// assert_eq!(doc.get_node(NodeId::new(2)), doc.descendants().find(|n| n.is_text()));
/// assert_eq!(doc.get_node(NodeId::new(3)), None);
/// ```
#[inline]
pub fn get_node<'a>(&'a self, id: NodeId) -> Option<Node<'a, 'input>> {
self.nodes.get(id.get_usize()).map(|data| Node {
id,
d: data,
doc: self,
})
}
/// Returns the root element of the document.
///
/// Unlike `root`, will return a first element node.
///
/// The root element always exists.
///
/// # Examples
///
/// ```
/// let doc = roxmltree::Document::parse("<!-- comment --><e/>").unwrap();
/// assert!(doc.root_element().has_tag_name("e"));
/// ```
#[inline]
pub fn root_element<'a>(&'a self) -> Node<'a, 'input> {
// `expect` is safe, because the `Document` is guarantee to have at least one element.
self.root()
.first_element_child()
.expect("XML documents must contain a root element")
}
/// Returns an iterator over document's descendant nodes.
///
/// Shorthand for `doc.root().descendants()`.
#[inline]
pub fn descendants(&self) -> Descendants<'_, 'input> {
self.root().descendants()
}
/// Calculates `TextPos` in the original document from position in bytes.
///
/// **Note:** this operation is expensive.
///
/// # Examples
///
/// ```
/// use roxmltree::*;
///
/// let doc = Document::parse("\
/// <!-- comment -->
/// <e/>"
/// ).unwrap();
///
/// assert_eq!(doc.text_pos_at(10), TextPos::new(1, 11));
/// assert_eq!(doc.text_pos_at(9999), TextPos::new(2, 5));
/// ```
#[inline]
pub fn text_pos_at(&self, pos: usize) -> TextPos {
xmlparser::Stream::from(self.text).gen_text_pos_from(pos)
}
/// Returns the input text of the original document.
///
/// # Examples
///
/// ```
/// use roxmltree::*;
///
/// let doc = Document::parse("<e/>").unwrap();
///
/// assert_eq!(doc.input_text(), "<e/>");
/// ```
#[inline]
pub fn input_text(&self) -> &'input str {
self.text
}
}
impl<'input> fmt::Debug for Document<'input> {
fn fmt(&self, f: &mut fmt::Formatter) -> Result<(), fmt::Error> {
if !self.root().has_children() {
return write!(f, "Document []");
}
macro_rules! writeln_indented {
($depth:expr, $f:expr, $fmt:expr) => {
for _ in 0..$depth { write!($f, " ")?; }
writeln!($f, $fmt)?;
};
($depth:expr, $f:expr, $fmt:expr, $($arg:tt)*) => {
for _ in 0..$depth { write!($f, " ")?; }
writeln!($f, $fmt, $($arg)*)?;
};
}
fn print_into_iter<
T: fmt::Debug,
E: ExactSizeIterator<Item = T>,
I: IntoIterator<Item = T, IntoIter = E>,
>(
prefix: &str,
data: I,
depth: usize,
f: &mut fmt::Formatter,
) -> Result<(), fmt::Error> {
let data = data.into_iter();
if data.len() == 0 {
return Ok(());
}
writeln_indented!(depth, f, "{}: [", prefix);
for v in data {
writeln_indented!(depth + 1, f, "{:?}", v);
}
writeln_indented!(depth, f, "]");
Ok(())
}
fn print_children(
parent: Node,
depth: usize,
f: &mut fmt::Formatter,
) -> Result<(), fmt::Error> {
for child in parent.children() {
if child.is_element() {
writeln_indented!(depth, f, "Element {{");
writeln_indented!(depth, f, " tag_name: {:?}", child.tag_name());
print_into_iter("attributes", child.attributes(), depth + 1, f)?;
print_into_iter("namespaces", child.namespaces(), depth + 1, f)?;
if child.has_children() {
writeln_indented!(depth, f, " children: [");
print_children(child, depth + 2, f)?;
writeln_indented!(depth, f, " ]");
}
writeln_indented!(depth, f, "}}");
} else {
writeln_indented!(depth, f, "{:?}", child);
}
}
Ok(())
}
writeln!(f, "Document [")?;
print_children(self.root(), 1, f)?;
writeln!(f, "]")?;
Ok(())
}
}
/// A list of supported node types.
#[derive(Clone, Copy, PartialEq, Eq, Debug)]
pub enum NodeType {
/// The root node of the `Document`.
Root,
/// An element node.
///
/// Only an element can have a tag name and attributes.
Element,
/// A processing instruction.
PI,
/// A comment node.
Comment,
/// A text node.
Text,
}
/// A processing instruction.
#[derive(Clone, Copy, PartialEq, Eq, Debug)]
#[allow(missing_docs)]
pub struct PI<'input> {
pub target: &'input str,
pub value: Option<&'input str>,
}
/// A short range.
///
/// Just like Range, but only for `u32` and copyable.
#[derive(Clone, Copy, Debug)]
struct ShortRange {
start: u32,
end: u32,
}
impl From<Range<usize>> for ShortRange {
#[inline]
fn from(range: Range<usize>) -> Self {
debug_assert!(range.start <= core::u32::MAX as usize);
debug_assert!(range.end <= core::u32::MAX as usize);
ShortRange::new(range.start as u32, range.end as u32)
}
}
impl ShortRange {
#[inline]
fn new(start: u32, end: u32) -> Self {
ShortRange { start, end }
}
#[inline]
fn to_urange(self) -> Range<usize> {
self.start as usize..self.end as usize
}
}
/// A node ID stored as `u32`.
///
/// An index into a `Tree`-internal `Vec`.
///
/// Note that this value should be used with care since `roxmltree` doesn't
/// check that `NodeId` actually belongs to a selected `Document`.
/// So you can end up in a situation, when `NodeId` produced by one `Document`
/// is used to select a node in another `Document`.
#[derive(Clone, Copy, PartialEq, Eq, Hash, Debug)]
pub struct NodeId(NonZeroU32);
impl NodeId {
/// Construct a new `NodeId` from a `u32`.
#[inline]
pub fn new(id: u32) -> Self {
debug_assert!(id < core::u32::MAX);
// We are using `NonZeroU32` to reduce overhead of `Option<NodeId>`.
NodeId(NonZeroU32::new(id + 1).unwrap())
}
/// Returns the `u32` representation of the `NodeId`.
#[inline]
pub fn get(self) -> u32 {
self.0.get() - 1
}
/// Returns the `usize` representation of the `NodeId`.
#[inline]
pub fn get_usize(self) -> usize {
self.get() as usize
}
}
impl From<u32> for NodeId {
#[inline]
fn from(id: u32) -> Self {
NodeId::new(id)
}
}
impl From<usize> for NodeId {
#[inline]
fn from(id: usize) -> Self {
// We already checked that `id` is limited by u32::MAX.
debug_assert!(id <= core::u32::MAX as usize);
NodeId::new(id as u32)
}
}
#[derive(Debug)]
enum NodeKind<'input> {
Root,
Element {
tag_name: ExpandedNameIndexed<'input>,
attributes: ShortRange,
namespaces: ShortRange,
},
PI(PI<'input>),
Comment(StringStorage<'input>),
Text(StringStorage<'input>),
}
#[derive(Debug)]
struct NodeData<'input> {
parent: Option<NodeId>,
prev_sibling: Option<NodeId>,
next_subtree: Option<NodeId>,
last_child: Option<NodeId>,
kind: NodeKind<'input>,
#[cfg(feature = "positions")]
range: Range<usize>,
}
/// A string storage.
///
/// Used by text nodes and attributes values.
///
/// We try our best to keep parsed strings as `&str`, but in some cases post-processing
/// is necessary and we have to allocates them.
///
/// All owned, allocated strings are stored as `Arc<str>`.
#[derive(Clone, Eq, Debug)]
pub enum StringStorage<'input> {
/// A raw slice of the input string.
Borrowed(&'input str),
/// A reference-counted string.
Owned(alloc::sync::Arc<str>),
}
impl StringStorage<'_> {
/// Creates a new owned string from `&str` or `String`.
pub fn new_owned<T: Into<alloc::sync::Arc<str>>>(s: T) -> Self {
StringStorage::Owned(s.into())
}
/// Returns a string slice.
pub fn as_str(&self) -> &str {
match self {
StringStorage::Borrowed(s) => s,
StringStorage::Owned(s) => s,
}
}
}
impl PartialEq for StringStorage<'_> {
fn eq(&self, other: &Self) -> bool {
self.as_str() == other.as_str()
}
}
impl core::fmt::Display for StringStorage<'_> {
fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
write!(f, "{}", self.as_str())
}
}
impl core::ops::Deref for StringStorage<'_> {
type Target = str;
fn deref(&self) -> &Self::Target {
self.as_str()
}
}
#[derive(Clone, Debug)]
struct AttributeData<'input> {
name: ExpandedNameIndexed<'input>,
value: StringStorage<'input>,
#[cfg(feature = "positions")]
pos: usize,
}
/// An attribute.
#[derive(Copy, Clone)]
pub struct Attribute<'a, 'input: 'a> {
doc: &'a Document<'input>,
data: &'a AttributeData<'input>,
}
impl<'a, 'input> Attribute<'a, 'input> {
/// Returns attribute's namespace URI.
///
/// # Examples
///
/// ```
/// let doc = roxmltree::Document::parse(
/// "<e xmlns:n='http://www.w3.org' a='b' n:a='c'/>"
/// ).unwrap();
///
/// assert_eq!(doc.root_element().attributes().nth(0).unwrap().namespace(), None);
/// assert_eq!(doc.root_element().attributes().nth(1).unwrap().namespace(), Some("http://www.w3.org"));
/// ```
#[inline]
pub fn namespace(&self) -> Option<&'a str> {
self.data.name.namespace(self.doc).map(Namespace::uri)
}
/// Returns attribute's name.
///
/// # Examples
///
/// ```
/// let doc = roxmltree::Document::parse(
/// "<e xmlns:n='http://www.w3.org' a='b' n:a='c'/>"
/// ).unwrap();
///
/// assert_eq!(doc.root_element().attributes().nth(0).unwrap().name(), "a");
/// assert_eq!(doc.root_element().attributes().nth(1).unwrap().name(), "a");
/// ```
#[inline]
pub fn name(&self) -> &'input str {
self.data.name.local_name
}
/// Returns attribute's value.
///
/// # Examples
///
/// ```
/// let doc = roxmltree::Document::parse(
/// "<e xmlns:n='http://www.w3.org' a='b' n:a='c'/>"
/// ).unwrap();
///
/// assert_eq!(doc.root_element().attributes().nth(0).unwrap().value(), "b");
/// assert_eq!(doc.root_element().attributes().nth(1).unwrap().value(), "c");
/// ```
#[inline]
pub fn value(&self) -> &'a str {
&self.data.value
}
/// Returns attribute's value storage.
///
/// Useful when you need a more low-level access to an allocated string.
#[inline]
pub fn value_storage(&self) -> &StringStorage<'input> {
&self.data.value
}
/// Returns attribute's position in bytes in the original document.
///
/// You can calculate a human-readable text position via [Document::text_pos_at].
///
/// ```text
/// <e attr='value'/>
/// ^
/// ```
///
/// [Document::text_pos_at]: struct.Document.html#method.text_pos_at
#[cfg(feature = "positions")]
#[inline]
pub fn position(&self) -> usize {
self.data.pos
}
}
impl PartialEq for Attribute<'_, '_> {
#[inline]
fn eq(&self, other: &Attribute<'_, '_>) -> bool {
self.data.name.as_expanded_name(self.doc) == other.data.name.as_expanded_name(other.doc)
&& self.data.value == other.data.value
}
}
impl fmt::Debug for Attribute<'_, '_> {
fn fmt(&self, f: &mut fmt::Formatter) -> Result<(), fmt::Error> {
write!(
f,
"Attribute {{ name: {:?}, value: {:?} }}",
self.data.name.as_expanded_name(self.doc),
self.data.value
)
}
}
/// A namespace.
///
/// Contains URI and *prefix* pair.
#[derive(Clone, PartialEq, Eq, Debug)]
pub struct Namespace<'input> {
name: Option<&'input str>,
uri: StringStorage<'input>,
}
impl<'input> Namespace<'input> {
/// Returns namespace name/prefix.
///
/// # Examples
///
/// ```
/// let doc = roxmltree::Document::parse(
/// "<e xmlns:n='http://www.w3.org'/>"
/// ).unwrap();
///
/// assert_eq!(doc.root_element().namespaces().nth(0).unwrap().name(), Some("n"));
/// ```
///
/// ```
/// let doc = roxmltree::Document::parse(
/// "<e xmlns='http://www.w3.org'/>"
/// ).unwrap();
///
/// assert_eq!(doc.root_element().namespaces().nth(0).unwrap().name(), None);
/// ```
#[inline]
pub fn name(&self) -> Option<&'input str> {
self.name
}
/// Returns namespace URI.
///
/// # Examples
///
/// ```
/// let doc = roxmltree::Document::parse(
/// "<e xmlns:n='http://www.w3.org'/>"
/// ).unwrap();
///
/// assert_eq!(doc.root_element().namespaces().nth(0).unwrap().uri(), "http://www.w3.org");
/// ```
#[inline]
pub fn uri(&self) -> &str {
self.uri.as_ref()
}
}
#[derive(Default)]
struct Namespaces<'input> {
// Deduplicated namespace values used throughout the document
values: Vec<Namespace<'input>>,
// Indices into the above in tree order as the document is parsed
tree_order: Vec<NamespaceIdx>,
// Indices into the above sorted by value used for deduplication
sorted_order: Vec<NamespaceIdx>,
}
impl<'input> Namespaces<'input> {
fn push_ns<'temp>(
&mut self,
name: Option<&'input str>,
uri: BorrowedText<'input, 'temp>,
) -> Result<(), Error> {
debug_assert_ne!(name, Some(""));
let idx = match self.sorted_order.binary_search_by(|idx| {
let value = &self.values[idx.0 as usize];
(value.name, value.uri.as_ref()).cmp(&(name, uri.as_str()))
}) {
Ok(sorted_idx) => self.sorted_order[sorted_idx],
Err(sorted_idx) => {
if self.values.len() > core::u16::MAX as usize {
return Err(Error::NamespacesLimitReached);
}
let idx = NamespaceIdx(self.values.len() as u16);
self.values.push(Namespace {
name,
uri: uri.to_storage(),
});
self.sorted_order.insert(sorted_idx, idx);
idx
}
};
self.tree_order.push(idx);
Ok(())
}
#[inline]
fn push_ref(&mut self, tree_idx: usize) {
let idx = self.tree_order[tree_idx];
self.tree_order.push(idx);
}
#[inline]
fn exists(&self, start: usize, prefix: Option<&str>) -> bool {
self.tree_order[start..]
.iter()
.any(|idx| self.values[idx.0 as usize].name == prefix)
}
fn shrink_to_fit(&mut self) {
self.values.shrink_to_fit();
self.tree_order.shrink_to_fit();
self.sorted_order.shrink_to_fit();
}
#[inline]
fn get(&self, idx: NamespaceIdx) -> &Namespace<'input> {
&self.values[idx.0 as usize]
}
}
#[derive(Clone, Copy, Debug)]
#[repr(transparent)]
struct NamespaceIdx(u16);
#[derive(Clone, Copy, Debug)]
struct ExpandedNameIndexed<'input> {
namespace_idx: Option<NamespaceIdx>,
local_name: &'input str,
}
impl<'input> ExpandedNameIndexed<'input> {
#[inline]
fn namespace<'a>(&self, doc: &'a Document<'input>) -> Option<&'a Namespace<'input>> {
self.namespace_idx.map(|idx| doc.namespaces.get(idx))
}
#[inline]
fn as_expanded_name<'a>(&self, doc: &'a Document<'input>) -> ExpandedName<'a, 'input> {
ExpandedName {
uri: self.namespace(doc).map(Namespace::uri),
name: self.local_name,
}
}
}
/// An expanded name.
///
/// Contains an namespace URI and name pair.
#[derive(Clone, Copy, PartialEq, Eq)]
pub struct ExpandedName<'a, 'b> {
uri: Option<&'a str>,
name: &'b str,
}
impl<'a, 'b> ExpandedName<'a, 'b> {
/// Returns a namespace URI.
///
/// # Examples
///
/// ```
/// let doc = roxmltree::Document::parse("<e xmlns='http://www.w3.org'/>").unwrap();
///
/// assert_eq!(doc.root_element().tag_name().namespace(), Some("http://www.w3.org"));
/// ```
#[inline]
pub fn namespace(&self) -> Option<&'a str> {
self.uri
}
/// Returns a local name.
///
/// # Examples
///
/// ```
/// let doc = roxmltree::Document::parse("<e/>").unwrap();
///
/// assert_eq!(doc.root_element().tag_name().name(), "e");
/// ```
#[inline]
pub fn name(&self) -> &'b str {
self.name
}
}
impl ExpandedName<'static, 'static> {
/// Create a new instance from static data.
///
/// # Example
///
/// ```rust
/// use roxmltree::ExpandedName;
/// const DAV_HREF: ExpandedName =
/// ExpandedName::from_static("urn:ietf:params:xml:ns:caldav:", "calendar-data");
/// ```
pub const fn from_static(uri: &'static str, name: &'static str) -> Self {
Self {
uri: Some(uri),
name,
}
}
}
impl fmt::Debug for ExpandedName<'_, '_> {
fn fmt(&self, f: &mut fmt::Formatter) -> Result<(), fmt::Error> {
match self.namespace() {
Some(ns) => write!(f, "{{{}}}{}", ns, self.name),
None => write!(f, "{}", self.name),
}
}
}
impl<'a, 'b> From<&'b str> for ExpandedName<'a, 'b> {
#[inline]
fn from(v: &'b str) -> Self {
ExpandedName { uri: None, name: v }
}
}
impl<'a, 'b> From<(&'a str, &'b str)> for ExpandedName<'a, 'b> {
#[inline]
fn from(v: (&'a str, &'b str)) -> Self {
ExpandedName {
uri: Some(v.0),
name: v.1,
}
}
}
/// A node in a document.
///
/// # Document Order
///
/// The implementation of the `Ord` traits for `Node` is based on the concept of *document-order*.
/// In layman's terms, document-order is the order in which one would see each element if
/// one opened a document in a text editor or web browser and scrolled down.
/// Document-order convention is followed in XPath, CSS Counters, and DOM selectors API
/// to ensure consistent results from selection.
/// One difference in `roxmltree` is that there is the notion of more than one document
/// in existence at a time. While Nodes within the same document are in document-order,
/// Nodes in different documents will be grouped together, but not in any particular
/// order.
///
/// As an example, if we have a Document `a` with Nodes `[a0, a1, a2]` and a
/// Document `b` with Nodes `[b0, b1]`, these Nodes in order could be either
/// `[a0, a1, a2, b0, b1]` or `[b0, b1, a0, a1, a2]` and roxmltree makes no
/// guarantee which it will be.
///
/// Document-order is defined here in the
/// [W3C XPath Recommendation](https://www.w3.org/TR/xpath-3/#id-document-order)
/// The use of document-order in DOM Selectors is described here in the
/// [W3C Selectors API Level 1](https://www.w3.org/TR/selectors-api/#the-apis)
#[derive(Clone, Copy)]
pub struct Node<'a, 'input: 'a> {
/// Node's ID.
id: NodeId,
/// The tree containing the node.
doc: &'a Document<'input>,
/// Node's data.
d: &'a NodeData<'input>,
}
impl Eq for Node<'_, '_> {}
impl PartialEq for Node<'_, '_> {
#[inline]
fn eq(&self, other: &Self) -> bool {
(self.id, self.doc as *const _) == (other.id, other.doc as *const _)
}
}
impl PartialOrd for Node<'_, '_> {
fn partial_cmp(&self, other: &Self) -> Option<Ordering> {
Some(self.cmp(other))
}
}
impl Ord for Node<'_, '_> {
fn cmp(&self, other: &Self) -> Ordering {
(self.id.0, self.doc as *const _).cmp(&(other.id.0, other.doc as *const _))
}
}
impl Hash for Node<'_, '_> {
fn hash<H: Hasher>(&self, state: &mut H) {
self.id.0.hash(state);
(self.doc as *const Document).hash(state);
(self.d as *const NodeData).hash(state);
}
}
impl<'a, 'input: 'a> Node<'a, 'input> {
/// Returns node's type.
#[inline]
pub fn node_type(&self) -> NodeType {
match self.d.kind {
NodeKind::Root => NodeType::Root,
NodeKind::Element { .. } => NodeType::Element,
NodeKind::PI { .. } => NodeType::PI,
NodeKind::Comment(_) => NodeType::Comment,
NodeKind::Text(_) => NodeType::Text,
}
}
/// Checks that node is a root node.
#[inline]
pub fn is_root(&self) -> bool {
self.node_type() == NodeType::Root
}
/// Checks that node is an element node.
#[inline]
pub fn is_element(&self) -> bool {
self.node_type() == NodeType::Element
}
/// Checks that node is a processing instruction node.
#[inline]
pub fn is_pi(&self) -> bool {
self.node_type() == NodeType::PI
}
/// Checks that node is a comment node.
#[inline]
pub fn is_comment(&self) -> bool {
self.node_type() == NodeType::Comment
}
/// Checks that node is a text node.
#[inline]
pub fn is_text(&self) -> bool {
self.node_type() == NodeType::Text
}
/// Returns node's document.
#[inline]
pub fn document(&self) -> &'a Document<'input> {
self.doc
}
/// Returns node's tag name.
///
/// Returns an empty name with no namespace if the current node is not an element.
///
/// # Examples
///
/// ```
/// let doc = roxmltree::Document::parse("<e xmlns='http://www.w3.org'/>").unwrap();
///
/// assert_eq!(doc.root_element().tag_name().namespace(), Some("http://www.w3.org"));
/// assert_eq!(doc.root_element().tag_name().name(), "e");
/// ```
#[inline]
pub fn tag_name(&self) -> ExpandedName<'a, 'input> {
match self.d.kind {
NodeKind::Element { ref tag_name, .. } => tag_name.as_expanded_name(self.doc),
_ => "".into(),
}
}
/// Checks that node has a specified tag name.
///
/// # Examples
///
/// ```
/// let doc = roxmltree::Document::parse("<e xmlns='http://www.w3.org'/>").unwrap();
///
/// assert!(doc.root_element().has_tag_name("e"));
/// assert!(doc.root_element().has_tag_name(("http://www.w3.org", "e")));
///
/// assert!(!doc.root_element().has_tag_name("b"));
/// assert!(!doc.root_element().has_tag_name(("http://www.w4.org", "e")));
/// ```
pub fn has_tag_name<'n, 'm, N>(&self, name: N) -> bool
where
N: Into<ExpandedName<'n, 'm>>,
{
let name = name.into();
match self.d.kind {
NodeKind::Element { ref tag_name, .. } => match name.namespace() {
Some(_) => tag_name.as_expanded_name(self.doc) == name,
None => tag_name.local_name == name.name,
},
_ => false,
}
}
/// Returns node's default namespace URI.
///
/// # Examples
///
/// ```
/// let doc = roxmltree::Document::parse("<e xmlns='http://www.w3.org'/>").unwrap();
///
/// assert_eq!(doc.root_element().default_namespace(), Some("http://www.w3.org"));
/// ```
///
/// ```
/// let doc = roxmltree::Document::parse("<e xmlns:n='http://www.w3.org'/>").unwrap();
///
/// assert_eq!(doc.root_element().default_namespace(), None);
/// ```
pub fn default_namespace(&self) -> Option<&'a str> {
self.namespaces()
.find(|ns| ns.name.is_none())
.map(|v| v.uri.as_ref())
}
/// Returns a prefix for a given namespace URI.
///
/// # Examples
///
/// ```
/// let doc = roxmltree::Document::parse("<e xmlns:n='http://www.w3.org'/>").unwrap();
///
/// assert_eq!(doc.root_element().lookup_prefix("http://www.w3.org"), Some("n"));
/// ```
///
/// ```
/// let doc = roxmltree::Document::parse("<e xmlns:n=''/>").unwrap();
///
/// assert_eq!(doc.root_element().lookup_prefix(""), Some("n"));
/// ```
pub fn lookup_prefix(&self, uri: &str) -> Option<&'input str> {
if uri == NS_XML_URI {
return Some(NS_XML_PREFIX);
}
self.namespaces()
.find(|ns| &*ns.uri == uri)
.map(|v| v.name)
.unwrap_or(None)
}
/// Returns an URI for a given prefix.
///
/// # Examples
///
/// ```
/// let doc = roxmltree::Document::parse("<e xmlns:n='http://www.w3.org'/>").unwrap();
///
/// assert_eq!(doc.root_element().lookup_namespace_uri(Some("n")), Some("http://www.w3.org"));
/// ```
///
/// ```
/// let doc = roxmltree::Document::parse("<e xmlns='http://www.w3.org'/>").unwrap();
///
/// assert_eq!(doc.root_element().lookup_namespace_uri(None), Some("http://www.w3.org"));
/// ```
pub fn lookup_namespace_uri(&self, prefix: Option<&str>) -> Option<&'a str> {
self.namespaces()
.find(|ns| ns.name == prefix)
.map(|v| v.uri.as_ref())
}
/// Returns element's attribute value.
///
/// # Examples
///
/// ```
/// let doc = roxmltree::Document::parse("<e a='b'/>").unwrap();
///
/// assert_eq!(doc.root_element().attribute("a"), Some("b"));
/// ```
///
/// ```
/// let doc = roxmltree::Document::parse(
/// "<e xmlns:n='http://www.w3.org' a='b' n:a='c'/>"
/// ).unwrap();
///
/// assert_eq!(doc.root_element().attribute("a"), Some("b"));
/// assert_eq!(doc.root_element().attribute(("http://www.w3.org", "a")), Some("c"));
/// ```
pub fn attribute<'n, 'm, N>(&self, name: N) -> Option<&'a str>
where
N: Into<ExpandedName<'n, 'm>>,
{
let name = name.into();
self.attributes()
.find(|a| a.data.name.as_expanded_name(self.doc) == name)
.map(|a| a.value())
}
/// Returns element's attribute object.
///
/// The same as [`attribute()`], but returns the `Attribute` itself instead of a value string.
///
/// [`attribute()`]: struct.Node.html#method.attribute
pub fn attribute_node<'n, 'm, N>(&self, name: N) -> Option<Attribute<'a, 'input>>
where
N: Into<ExpandedName<'n, 'm>>,
{
let name = name.into();
self.attributes()
.find(|a| a.data.name.as_expanded_name(self.doc) == name)
}
/// Checks that element has a specified attribute.
///
/// # Examples
///
/// ```
/// let doc = roxmltree::Document::parse(
/// "<e xmlns:n='http://www.w3.org' a='b' n:a='c'/>"
/// ).unwrap();
///
/// assert!(doc.root_element().has_attribute("a"));
/// assert!(doc.root_element().has_attribute(("http://www.w3.org", "a")));
///
/// assert!(!doc.root_element().has_attribute("b"));
/// assert!(!doc.root_element().has_attribute(("http://www.w4.org", "a")));
/// ```
pub fn has_attribute<'n, 'm, N>(&self, name: N) -> bool
where
N: Into<ExpandedName<'n, 'm>>,
{
let name = name.into();
self.attributes()
.any(|a| a.data.name.as_expanded_name(self.doc) == name)
}
/// Returns element's attributes.
///
/// # Examples
///
/// ```
/// let doc = roxmltree::Document::parse(
/// "<e xmlns:n='http://www.w3.org' a='b' n:a='c'/>"
/// ).unwrap();
///
/// assert_eq!(doc.root_element().attributes().len(), 2);
/// ```
#[inline]
pub fn attributes(&self) -> Attributes<'a, 'input> {
Attributes::new(self)
}
/// Returns element's namespaces.
///
/// # Examples
///
/// ```
/// let doc = roxmltree::Document::parse(
/// "<e xmlns:n='http://www.w3.org'/>"
/// ).unwrap();
///
/// assert_eq!(doc.root_element().namespaces().len(), 1);
/// ```
#[inline]
pub fn namespaces(&self) -> NamespaceIter<'a, 'input> {
let namespaces = match self.d.kind {
NodeKind::Element { ref namespaces, .. } => {
&self.doc.namespaces.tree_order[namespaces.to_urange()]
}
_ => &[],
};
NamespaceIter {
doc: self.doc,
namespaces: namespaces.iter(),
}
}
/// Returns node's text.
///
/// - for an element will return a first text child
/// - for a comment will return a self text
/// - for a text node will return a self text
///
/// # Examples
///
/// ```
/// let doc = roxmltree::Document::parse("\
/// <p>
/// text
/// </p>
/// ").unwrap();
///
/// assert_eq!(doc.root_element().text(),
/// Some("\n text\n"));
/// assert_eq!(doc.root_element().first_child().unwrap().text(),
/// Some("\n text\n"));
/// ```
///
/// ```
/// let doc = roxmltree::Document::parse("<!-- comment --><e/>").unwrap();
///
/// assert_eq!(doc.root().first_child().unwrap().text(), Some(" comment "));
/// ```
#[inline]
pub fn text(&self) -> Option<&'a str> {
self.text_storage().map(|s| s.as_str())
}
/// Returns node's text storage.
///
/// Useful when you need a more low-level access to an allocated string.
pub fn text_storage(&self) -> Option<&'a StringStorage<'input>> {
match self.d.kind {
NodeKind::Element { .. } => match self.first_child() {
Some(child) if child.is_text() => match self.doc.nodes[child.id.get_usize()].kind {
NodeKind::Text(ref text) => Some(text),
_ => None,
},
_ => None,
},
NodeKind::Comment(ref text) => Some(text),
NodeKind::Text(ref text) => Some(text),
_ => None,
}
}
/// Returns element's tail text.
///
/// # Examples
///
/// ```
/// let doc = roxmltree::Document::parse("\
/// <root>
/// text1
/// <p/>
/// text2
/// </root>
/// ").unwrap();
///
/// let p = doc.descendants().find(|n| n.has_tag_name("p")).unwrap();
/// assert_eq!(p.tail(), Some("\n text2\n"));
/// ```
#[inline]
pub fn tail(&self) -> Option<&'a str> {
self.tail_storage().map(|s| s.as_str())
}
/// Returns element's tail text storage.
///
/// Useful when you need a more low-level access to an allocated string.
pub fn tail_storage(&self) -> Option<&'a StringStorage<'input>> {
if !self.is_element() {
return None;
}
match self.next_sibling().map(|n| n.id) {
Some(id) => match self.doc.nodes[id.get_usize()].kind {
NodeKind::Text(ref text) => Some(text),
_ => None,
},
None => None,
}
}
/// Returns node as Processing Instruction.
#[inline]
pub fn pi(&self) -> Option<PI<'input>> {
match self.d.kind {
NodeKind::PI(pi) => Some(pi),
_ => None,
}
}
/// Returns the parent of this node.
#[inline]
pub fn parent(&self) -> Option<Self> {
self.d.parent.map(|id| self.doc.get_node(id).unwrap())
}
/// Returns the parent element of this node.
pub fn parent_element(&self) -> Option<Self> {
self.ancestors().skip(1).find(|n| n.is_element())
}
/// Returns the previous sibling of this node.
#[inline]
pub fn prev_sibling(&self) -> Option<Self> {
self.d.prev_sibling.map(|id| self.doc.get_node(id).unwrap())
}
/// Returns the previous sibling element of this node.
pub fn prev_sibling_element(&self) -> Option<Self> {
self.prev_siblings().skip(1).find(|n| n.is_element())
}
/// Returns the next sibling of this node.
#[inline]
pub fn next_sibling(&self) -> Option<Self> {
self.d
.next_subtree
.map(|id| self.doc.get_node(id).unwrap())
.and_then(|node| {
let possibly_self = node
.d
.prev_sibling
.expect("next_subtree will always have a previous sibling");
if possibly_self == self.id {
Some(node)
} else {
None
}
})
}
/// Returns the next sibling element of this node.
pub fn next_sibling_element(&self) -> Option<Self> {
self.next_siblings().skip(1).find(|n| n.is_element())
}
/// Returns the first child of this node.
#[inline]
pub fn first_child(&self) -> Option<Self> {
self.d
.last_child
.map(|_| self.doc.get_node(NodeId::new(self.id.get() + 1)).unwrap())
}
/// Returns the first element child of this node.
pub fn first_element_child(&self) -> Option<Self> {
self.children().find(|n| n.is_element())
}
/// Returns the last child of this node.
#[inline]
pub fn last_child(&self) -> Option<Self> {
self.d.last_child.map(|id| self.doc.get_node(id).unwrap())
}
/// Returns the last element child of this node.
pub fn last_element_child(&self) -> Option<Self> {
self.children().filter(|n| n.is_element()).last()
}
/// Returns true if this node has siblings.
#[inline]
pub fn has_siblings(&self) -> bool {
self.d.prev_sibling.is_some() || self.next_sibling().is_some()
}
/// Returns true if this node has children.
#[inline]
pub fn has_children(&self) -> bool {
self.d.last_child.is_some()
}
/// Returns an iterator over ancestor nodes starting at this node.
#[inline]
pub fn ancestors(&self) -> AxisIter<'a, 'input> {
AxisIter {
node: Some(*self),
next: Node::parent,
}
}
/// Returns an iterator over previous sibling nodes starting at this node.
#[inline]
pub fn prev_siblings(&self) -> AxisIter<'a, 'input> {
AxisIter {
node: Some(*self),
next: Node::prev_sibling,
}
}
/// Returns an iterator over next sibling nodes starting at this node.
#[inline]
pub fn next_siblings(&self) -> AxisIter<'a, 'input> {
AxisIter {
node: Some(*self),
next: Node::next_sibling,
}
}
/// Returns an iterator over first children nodes starting at this node.
#[inline]
pub fn first_children(&self) -> AxisIter<'a, 'input> {
AxisIter {
node: Some(*self),
next: Node::first_child,
}
}
/// Returns an iterator over last children nodes starting at this node.
#[inline]
pub fn last_children(&self) -> AxisIter<'a, 'input> {
AxisIter {
node: Some(*self),
next: Node::last_child,
}
}
/// Returns an iterator over children nodes.
#[inline]
pub fn children(&self) -> Children<'a, 'input> {
Children {
front: self.first_child(),
back: self.last_child(),
}
}
/// Returns an iterator over this node and its descendants.
#[inline]
pub fn descendants(&self) -> Descendants<'a, 'input> {
Descendants::new(*self)
}
/// Returns node's range in bytes in the original document.
#[cfg(feature = "positions")]
#[inline]
pub fn range(&self) -> Range<usize> {
self.d.range.clone()
}
/// Returns node's NodeId
#[inline]
pub fn id(&self) -> NodeId {
self.id
}
}
impl<'a, 'input: 'a> fmt::Debug for Node<'a, 'input> {
fn fmt(&self, f: &mut fmt::Formatter) -> Result<(), fmt::Error> {
match self.d.kind {
NodeKind::Root => write!(f, "Root"),
NodeKind::Element { .. } => {
write!(
f,
"Element {{ tag_name: {:?}, attributes: {:?}, namespaces: {:?} }}",
self.tag_name(),
self.attributes(),
self.namespaces()
)
}
NodeKind::PI(pi) => {
write!(f, "PI {{ target: {:?}, value: {:?} }}", pi.target, pi.value)
}
NodeKind::Comment(ref text) => write!(f, "Comment({:?})", text.as_str()),
NodeKind::Text(ref text) => write!(f, "Text({:?})", text.as_str()),
}
}
}
/// Iterator over a node's attributes
#[derive(Clone)]
pub struct Attributes<'a, 'input> {
doc: &'a Document<'input>,
attrs: core::slice::Iter<'a, AttributeData<'input>>,
}
impl<'a, 'input> Attributes<'a, 'input> {
#[inline]
fn new(node: &Node<'a, 'input>) -> Attributes<'a, 'input> {
let attrs = match node.d.kind {
NodeKind::Element { ref attributes, .. } => {
&node.doc.attributes[attributes.to_urange()]
}
_ => &[],
};
Attributes {
doc: node.doc,
attrs: attrs.iter(),
}
}
}
impl<'a, 'input> Iterator for Attributes<'a, 'input> {
type Item = Attribute<'a, 'input>;
#[inline]
fn next(&mut self) -> Option<Self::Item> {
self.attrs.next().map(|attr| Attribute {
doc: self.doc,
data: attr,
})
}
#[inline]
fn nth(&mut self, n: usize) -> Option<Self::Item> {
self.attrs.nth(n).map(|attr| Attribute {
doc: self.doc,
data: attr,
})
}
#[inline]
fn size_hint(&self) -> (usize, Option<usize>) {
self.attrs.size_hint()
}
}
impl<'a, 'input> DoubleEndedIterator for Attributes<'a, 'input> {
#[inline]
fn next_back(&mut self) -> Option<Self::Item> {
self.attrs.next_back().map(|attr| Attribute {
doc: self.doc,
data: attr,
})
}
}
impl ExactSizeIterator for Attributes<'_, '_> {}
impl fmt::Debug for Attributes<'_, '_> {
fn fmt(&self, f: &mut fmt::Formatter) -> Result<(), fmt::Error> {
f.debug_struct("Attributes")
.field("attrs", &self.attrs)
.finish()
}
}
/// Iterator over specified axis.
#[derive(Clone)]
pub struct AxisIter<'a, 'input: 'a> {
node: Option<Node<'a, 'input>>,
next: fn(&Node<'a, 'input>) -> Option<Node<'a, 'input>>,
}
impl<'a, 'input: 'a> Iterator for AxisIter<'a, 'input> {
type Item = Node<'a, 'input>;
#[inline]
fn next(&mut self) -> Option<Self::Item> {
let node = self.node.take();
self.node = node.as_ref().and_then(self.next);
node
}
}
impl fmt::Debug for AxisIter<'_, '_> {
fn fmt(&self, f: &mut fmt::Formatter) -> Result<(), fmt::Error> {
f.debug_struct("AxisIter")
.field("node", &self.node)
.field("next", &"fn()")
.finish()
}
}
/// Iterator over children.
#[derive(Clone, Debug)]
pub struct Children<'a, 'input: 'a> {
front: Option<Node<'a, 'input>>,
back: Option<Node<'a, 'input>>,
}
impl<'a, 'input: 'a> Iterator for Children<'a, 'input> {
type Item = Node<'a, 'input>;
#[inline]
fn next(&mut self) -> Option<Self::Item> {
if self.front == self.back {
let node = self.front.take();
self.back = None;
node
} else {
let node = self.front.take();
self.front = node.as_ref().and_then(Node::next_sibling);
node
}
}
}
impl<'a, 'input: 'a> DoubleEndedIterator for Children<'a, 'input> {
#[inline]
fn next_back(&mut self) -> Option<Self::Item> {
if self.back == self.front {
let node = self.back.take();
self.front = None;
node
} else {
let node = self.back.take();
self.back = node.as_ref().and_then(Node::prev_sibling);
node
}
}
}
/// Iterator over a node and its descendants.
#[derive(Clone)]
pub struct Descendants<'a, 'input> {
doc: &'a Document<'input>,
nodes: core::iter::Enumerate<core::slice::Iter<'a, NodeData<'input>>>,
from: usize,
}
impl<'a, 'input> Descendants<'a, 'input> {
#[inline]
fn new(start: Node<'a, 'input>) -> Self {
let from = start.id.get_usize();
let until = start
.d
.next_subtree
.map(NodeId::get_usize)
.unwrap_or(start.doc.nodes.len());
let nodes = start.doc.nodes[from..until].iter().enumerate();
Self {
doc: start.doc,
nodes,
from,
}
}
}
impl<'a, 'input> Iterator for Descendants<'a, 'input> {
type Item = Node<'a, 'input>;
#[inline]
fn next(&mut self) -> Option<Self::Item> {
self.nodes.next().map(|(idx, data)| Node {
id: NodeId::from(self.from + idx),
d: data,
doc: self.doc,
})
}
#[inline]
fn nth(&mut self, n: usize) -> Option<Self::Item> {
self.nodes.nth(n).map(|(idx, data)| Node {
id: NodeId::from(self.from + idx),
d: data,
doc: self.doc,
})
}
#[inline]
fn size_hint(&self) -> (usize, Option<usize>) {
self.nodes.size_hint()
}
}
impl<'a, 'input> DoubleEndedIterator for Descendants<'a, 'input> {
#[inline]
fn next_back(&mut self) -> Option<Self::Item> {
self.nodes.next_back().map(|(idx, data)| Node {
id: NodeId::from(self.from + idx),
d: data,
doc: self.doc,
})
}
}
impl ExactSizeIterator for Descendants<'_, '_> {}
impl fmt::Debug for Descendants<'_, '_> {
fn fmt(&self, f: &mut fmt::Formatter) -> Result<(), fmt::Error> {
f.debug_struct("Descendants")
.field("nodes", &self.nodes)
.field("from", &self.from)
.finish()
}
}
/// Iterator over the namespaces attached to a node.
#[derive(Clone)]
pub struct NamespaceIter<'a, 'input> {
doc: &'a Document<'input>,
namespaces: core::slice::Iter<'a, NamespaceIdx>,
}
impl<'a, 'input> Iterator for NamespaceIter<'a, 'input> {
type Item = &'a Namespace<'input>;
#[inline]
fn next(&mut self) -> Option<Self::Item> {
self.namespaces
.next()
.map(|idx| self.doc.namespaces.get(*idx))
}
#[inline]
fn nth(&mut self, n: usize) -> Option<Self::Item> {
self.namespaces
.nth(n)
.map(|idx| self.doc.namespaces.get(*idx))
}
#[inline]
fn size_hint(&self) -> (usize, Option<usize>) {
self.namespaces.size_hint()
}
}
impl<'a, 'input> DoubleEndedIterator for NamespaceIter<'a, 'input> {
#[inline]
fn next_back(&mut self) -> Option<Self::Item> {
self.namespaces
.next()
.map(|idx| self.doc.namespaces.get(*idx))
}
}
impl ExactSizeIterator for NamespaceIter<'_, '_> {}
impl fmt::Debug for NamespaceIter<'_, '_> {
fn fmt(&self, f: &mut fmt::Formatter) -> Result<(), fmt::Error> {
f.debug_struct("NamespaceIter")
.field("namespaces", &self.namespaces)
.finish()
}
}