-
Notifications
You must be signed in to change notification settings - Fork 41
Expand file tree
/
Copy pathlib.rs
More file actions
1745 lines (1555 loc) · 48.7 KB
/
Copy pathlib.rs
File metadata and controls
1745 lines (1555 loc) · 48.7 KB
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
/*!
Represent an [XML](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)]
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;
mod parse;
mod tokenizer;
#[cfg(test)]
mod tokenizer_tests;
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";
/// Position in text.
///
/// Position indicates a row/line and a column in the original text. Starting from 1:1.
#[allow(missing_docs)]
#[derive(Clone, Copy, PartialEq, Eq, Hash, Debug)]
pub struct TextPos {
pub row: u32,
pub col: u32,
}
impl TextPos {
/// Constructs a new `TextPos`.
pub fn new(row: u32, col: u32) -> TextPos {
TextPos { row, col }
}
}
impl fmt::Display for TextPos {
fn fmt(&self, f: &mut fmt::Formatter) -> fmt::Result {
write!(f, "{}:{}", self.row, self.col)
}
}
/// 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 {
tokenizer::Stream::new(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 <= u32::MAX as usize);
debug_assert!(range.end <= 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 < 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 <= 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>,
}
#[cfg(target_has_atomic = "ptr")]
type OwnedSharedString = alloc::sync::Arc<str>;
#[cfg(not(target_has_atomic = "ptr"))]
type OwnedSharedString = alloc::rc::Rc<str>;
/// A string storage.
///
/// Used by text nodes and attributes values.
///
/// We try our best not to allocate strings, referencing the input string as much as possible.
/// But in some cases post-processing is necessary and we have to allocate them.
///
/// All owned, allocated strings are stored as `Arc<str>` or as `Rc<str>` on targets
/// were `Arc` isn't available.
/// And unlike `Cow<&str>`, `StringStorage` is immutable and can be cheaply cloned.
#[derive(Clone, Eq, Debug)]
pub enum StringStorage<'input> {
/// A raw slice of the input string.
Borrowed(&'input str),
/// A reference-counted string.
Owned(OwnedSharedString),
}
impl StringStorage<'_> {
/// Creates a new owned string copied from a `&str`.
pub fn new_owned(s: &str) -> 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")]
range: Range<usize>,
#[cfg(feature = "positions")]
qname_len: u16,
#[cfg(feature = "positions")]
eq_len: u8, // includes any surrounding spaces
}
/// 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
#[deprecated(note="replaced by `range`")]
#[cfg(feature = "positions")]
#[inline]
pub fn position(&self) -> usize {
self.data.range.start
}
/// Returns attribute's range in bytes in the original document.
///
/// ```text
/// <e n:attr='value'/>
/// ^^^^^^^^^^^^^^
/// ```
#[cfg(feature = "positions")]
#[inline]
pub fn range(&self) -> Range<usize> {
self.data.range.clone()
}
/// Returns attribute's qname's range in bytes in the original document.
///
/// ```text
/// <e n:attr='value'/>
/// ^^^^^^
/// ```
///
/// To reduce memory usage the qname length is limited by u16::MAX.
/// If the attribute exceeds that limit then the end of the returned range will be incorrect.
#[cfg(feature = "positions")]
#[inline]
pub fn range_qname(&self) -> Range<usize> {
let end = self.data.range.start + usize::from(self.data.qname_len);
self.data.range.start..end
}
/// Returns attribute's value's range in bytes in the original document, excluding the surrounding quotes.
///
/// If the attribute's value is an empty string then the `start` and `end` of this `Range` are equal, and indicate the closing quote.
///
/// ```text
/// <e n:attr='value'/>
/// ^^^^^
/// ```
///
/// To reduce memory usage the qname length is limited by u16::MAX,
/// and the number of spaces around the equal sign is limited by u8::MAX.
/// If the attribute exceeds those limits then the start of the returned range will be incorrect.
#[cfg(feature = "positions")]
#[inline]
pub fn range_value(&self) -> Range<usize> {
// +1 on start and -1 on end are to exclude the quotes around the value (all valid quotes are 1 byte)
let start = self.data.range.start + usize::from(self.data.qname_len) + usize::from(self.data.eq_len) + 1;
let end = self.data.range.end - 1;
start..end
}
}
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(
&mut self,
name: Option<&'input str>,
uri: StringStorage<'input>,
) -> 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() > u16::MAX as usize {
return Err(Error::NamespacesLimitReached);
}
let idx = NamespaceIdx(self.values.len() as u16);
self.values.push(Namespace { name, uri });
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();
// Only needed to deduplicate namespaces during parsing.
self.sorted_order = Vec::new();
}
#[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");