libxml 0.3.15

A Rust wrapper for libxml2 - the XML C parser and toolkit developed for the Gnome project
Documentation 
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

//! xpath module tests
//!

use libxml::parser::Parser;
use libxml::xpath::Context;

#[test]
/// Test the evaluation of an xpath expression yields the correct number of nodes
fn xpath_result_number_correct() {
  let parser = Parser::default();
  let doc_result = parser.parse_file("tests/resources/file01.xml");
  assert!(doc_result.is_ok());
  let doc = doc_result.unwrap();
  let context = Context::new(&doc).unwrap();

  let result1 = context.evaluate("//child").unwrap();
  assert_eq!(result1.get_number_of_nodes(), 2);
  assert_eq!(result1.get_nodes_as_vec().len(), 2);

  let result2 = context.evaluate("//nonexistent").unwrap();
  assert_eq!(result2.get_number_of_nodes(), 0);
  assert_eq!(result2.get_nodes_as_vec().len(), 0);
}

#[test]
/// Test xpath with namespaces
fn xpath_with_namespaces() {
  let parser = Parser::default();
  let doc_result = parser.parse_file("tests/resources/simple_namespaces.xml");
  assert!(doc_result.is_ok());

  let doc = doc_result.unwrap();
  let context = Context::new(&doc).unwrap();
  assert!(
    context
      .register_namespace("h", "http://example.com/ns/hello")
      .is_ok()
  );
  assert!(
    context
      .register_namespace("f", "http://example.com/ns/farewell")
      .is_ok()
  );
  assert!(
    context
      .register_namespace("r", "http://example.com/ns/root")
      .is_ok()
  );
  let result_h_td = context.evaluate("//h:td").unwrap();
  assert_eq!(result_h_td.get_number_of_nodes(), 3);
  assert_eq!(result_h_td.get_nodes_as_vec().len(), 3);

  let result_h_table = context.evaluate("//h:table").unwrap();
  assert_eq!(result_h_table.get_number_of_nodes(), 2);
  assert_eq!(result_h_table.get_nodes_as_vec().len(), 2);

  let result_f_footer = context.evaluate("//f:footer").unwrap();
  assert_eq!(result_f_footer.get_number_of_nodes(), 2);
  assert_eq!(result_f_footer.get_nodes_as_vec().len(), 2);

  let result_r = context.evaluate("//r:*").unwrap();
  assert_eq!(result_r.get_number_of_nodes(), 1);
  assert_eq!(result_r.get_nodes_as_vec().len(), 1);

  let result_h = context.evaluate("//h:*").unwrap();
  assert_eq!(result_h.get_number_of_nodes(), 7);
  assert_eq!(result_h.get_nodes_as_vec().len(), 7);

  let result_f = context.evaluate("//f:*").unwrap();
  assert_eq!(result_f.get_number_of_nodes(), 4);
  assert_eq!(result_f.get_nodes_as_vec().len(), 4);

  let result_all = context.evaluate("//*").unwrap();
  assert_eq!(result_all.get_number_of_nodes(), 12);
  assert_eq!(result_all.get_nodes_as_vec().len(), 12);

  let result_h_table = context.evaluate("//table").unwrap();
  assert_eq!(result_h_table.get_number_of_nodes(), 0);
  assert_eq!(result_h_table.get_nodes_as_vec().len(), 0);

  assert!(doc.as_node().recursively_remove_namespaces().is_ok());
  let result_h_table = context.evaluate("//table").unwrap();
  assert_eq!(result_h_table.get_number_of_nodes(), 2);
  assert_eq!(result_h_table.get_nodes_as_vec().len(), 2);
}

#[test]
/// Test that an xpath expression finds the correct node and
/// that the class names are interpreted correctly.
fn class_names() {
  let parser = Parser::default_html();
  let doc_result = parser.parse_file("tests/resources/file02.xml");
  assert!(doc_result.is_ok());
  let doc = doc_result.unwrap();
  let context = Context::new(&doc).unwrap();

  let p_result = context.evaluate("/html/body/p");
  assert!(p_result.is_ok());
  let p = p_result.unwrap();
  assert_eq!(p.get_number_of_nodes(), 1);

  let node = &p.get_nodes_as_vec()[0];
  let names = node.get_class_names();
  assert_eq!(names.len(), 2);
  assert!(names.contains("paragraph"));
  assert!(names.contains("important"));
  assert!(!names.contains("nonsense"));
}

#[test]
/// Test that an xpath string() function processed correctly
fn xpath_string_function() {
  let parser = Parser::default_html();
  let doc_result = parser.parse_file("tests/resources/file01.xml");
  assert!(doc_result.is_ok());
  let doc = doc_result.unwrap();
  let context = Context::new(&doc).unwrap();

  let p_result = context.evaluate("string(//root//child[1]/@attribute)");
  assert!(p_result.is_ok());
  let p = p_result.unwrap();
  // Not a node really
  assert_eq!(p.get_number_of_nodes(), 0);
  let content = p.to_string();
  assert_eq!(content, "value");
}

#[test]
/// Test that the dual findnodes interfaces are operational
fn findnodes_interfaces() {
  let parser = Parser::default_html();
  let doc_result = parser.parse_file("tests/resources/file02.xml");
  assert!(doc_result.is_ok());
  let doc = doc_result.unwrap();

  // Xpath interface
  let mut context = Context::new(&doc).unwrap();
  let body = context.evaluate("/html/body").unwrap().get_nodes_as_vec();
  let p_result = context.findnodes("p", body.first());
  assert!(p_result.is_ok());
  let p = p_result.unwrap();
  assert_eq!(p.len(), 1);

  // Node interface
  let body_node = body.first().unwrap();
  let p2_result = body_node.findnodes("p");
  assert!(p2_result.is_ok());
  let p2 = p2_result.unwrap();
  assert_eq!(p2.len(), 1);
}

#[test]
/// Clone is safe on Context objects
fn safe_context_clone() {
  let parser = Parser::default_html();
  let doc_result = parser.parse_file("tests/resources/file02.xml");
  assert!(doc_result.is_ok());
  let doc = doc_result.unwrap();

  // Xpath interface
  let context = Context::new(&doc).unwrap();
  let body = context.evaluate("/html/body").unwrap().get_nodes_as_vec();
  assert_eq!(body.len(), 1);
  let context2 = context.clone();
  let body2 = context2.evaluate("/html/body").unwrap().get_nodes_as_vec();
  assert_eq!(body2.len(), 1);
}

#[test]
fn cleanup_safely_unlinked_xpath_nodes() {
  let p = Parser::default();
  let doc_result = p.parse_string(r##"<?xml version="1.0" standalone="no"?> <!DOCTYPE svg PUBLIC "-//W3C//DTD SVG 1.0//EN" "http://www.w3.org/TR/2001/REC-SVG-20010904/DTD/svg10.dtd" > <svg xmlns="http://www.w3.org/2000/svg" width="100%" height="100%">
<defs >
<font horiz-adv-x="874" ><font-face
    font-family="Luxi Serif"
    units-per-em="2048"
    panose-1="2 2 7 3 7 0 0 0 0 4"
    ascent="2073"
    descent="-432"
    alphabetic="0" />
<missing-glyph horiz-adv-x="512" d="M51 0V1480H461V0H51ZM410 51V1429H102V51H410Z" />
<glyph unicode=" " glyph-name="space" horiz-adv-x="512" />
<c g1="one" g2="X" k="32" />
</font>
</defs>
</svg>
"##);
  assert!(doc_result.is_ok(), "successfully parsed SVG snippet");
  let doc = doc_result.unwrap();
  let mut xpath = libxml::xpath::Context::new(&doc).unwrap();
  xpath
    .register_namespace("svg", "http://www.w3.org/2000/svg")
    .unwrap();
  for mut k in xpath.findnodes("//svg:c", None).unwrap() {
    k.unlink_node();
  }
  drop(xpath);
  drop(doc);
  // No assertion — reaching this point means the drops did not crash.
}

#[test]
fn xpath_find_string_values() {
  let parser = Parser::default();
  let doc_result = parser.parse_file("tests/resources/ids.xml");
  assert!(doc_result.is_ok());
  let doc = doc_result.unwrap();
  let mut xpath = libxml::xpath::Context::new(&doc).unwrap();
  match doc.get_root_element() {
    Some(root) => {
      let tests = root.get_child_elements();
      let empty_test = &tests[0];
      let ids_test = &tests[1];
      let empty_values = xpath.findvalues(".//@xml:id", Some(empty_test));
      assert_eq!(empty_values, Ok(Vec::new()));
      let ids_values = xpath.findvalues(".//@xml:id", Some(ids_test));
      let expected_ids = Ok(vec![
        String::from("start"),
        String::from("mid"),
        String::from("end"),
      ]);
      assert_eq!(ids_values, expected_ids);
      let node_ids_values = ids_test.findvalues(".//@xml:id");
      assert_eq!(node_ids_values, expected_ids);
    }
    _ => {
      panic!("Document fails to obtain root!");
    }
  }
}

/// Tests for checking xpath well-formedness
mod compile_tests {
  use libxml::xpath::is_well_formed_xpath;

  #[test]
  fn can_compile_an_xpath() {
    let compiles = is_well_formed_xpath("//a");
    assert!(compiles);
  }

  #[test]
  fn invalid_xpath_does_not_compile() {
    let compiles = is_well_formed_xpath("//a[but invalid]");
    assert!(!compiles);
  }
}

/// Coverage for the `*_checked` evaluators and `XPathError` — the error-surfacing
/// API added for very large documents. The `Ok` path is exercised throughout the
/// tests above (the thin `evaluate`/`node_evaluate` wrappers delegate to their
/// `_checked` variant); these pin the previously-untested `Err`/classification path.
mod checked_evaluators {
  use libxml::parser::Parser;
  use libxml::xpath::{Context, XPathError};

  /// An invalid expression makes libxml2 return NULL; `evaluate_checked` turns
  /// that into a populated `XPathError` (message + non-zero code), while the thin
  /// `evaluate` still collapses it to `Err(())`.
  #[test]
  fn evaluate_checked_surfaces_invalid_expression() {
    let doc = Parser::default().parse_string("<r><c/></r>").unwrap();
    let ctx = Context::new(&doc).unwrap();

    let err = ctx
      .evaluate_checked("///")
      .expect_err("`///` is not a valid XPath expression");
    assert!(err.message.is_some(), "expected a libxml2 error message");
    assert_ne!(err.code, 0, "expected a non-zero libxml2 error code");
    assert!(
      !err.is_nodeset_limit(),
      "a syntax error is not the nodeset ceiling"
    );

    assert!(ctx.evaluate("///").is_err(), "thin wrapper still errors");
    // A valid expression still succeeds through the checked path.
    assert_eq!(
      ctx.evaluate_checked("//c").unwrap().get_number_of_nodes(),
      1
    );
  }

  /// `is_nodeset_limit` recognizes exactly libxml2's growing-nodeset / OOM
  /// messages and nothing else. Constructed directly (the fields are public)
  /// because materializing a real >10M node-set in a unit test is impractical.
  #[test]
  fn is_nodeset_limit_classifies_libxml2_messages() {
    let mk = |m: Option<&str>| XPathError {
      message: m.map(str::to_string),
      code: 0,
      domain: 0,
    };
    assert!(mk(Some("XPath error : growing nodeset hit limit")).is_nodeset_limit());
    assert!(mk(Some("Memory allocation failed : growing nodeset")).is_nodeset_limit());
    assert!(!mk(Some("Invalid expression\n")).is_nodeset_limit());
    assert!(!mk(None).is_nodeset_limit());
  }

  /// The node-relative checked evaluators resolve against the given context node
  /// (both the `&Node` and `RoNode` entry points) and surface errors the same way.
  #[test]
  fn node_checked_evaluators_ok_and_err() {
    let doc = Parser::default()
      .parse_file("tests/resources/file01.xml")
      .unwrap();
    let ctx = Context::new(&doc).unwrap();

    let root = doc.get_root_element().unwrap();
    assert_eq!(
      ctx
        .node_evaluate_checked("child", &root)
        .unwrap()
        .get_number_of_nodes(),
      2,
      "two <child> nodes are reachable from the root"
    );
    assert!(ctx.node_evaluate_checked("///", &root).is_err());

    let ro_root = doc.get_root_readonly().unwrap();
    assert_eq!(
      ctx
        .node_evaluate_readonly_checked("child", ro_root)
        .unwrap()
        .get_number_of_nodes(),
      2
    );
    assert!(ctx.node_evaluate_readonly_checked("///", ro_root).is_err());
  }
}