domq 0.5.0

Tiny, zero-dependency, forgiving HTML parser: turn messy real-world HTML into a clean DOM tree (and JSON). WASM-first, no_std-friendly.
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

//! URL reference resolution (`resolve_url`, RFC 3986 §5) and `srcset`
//! handling (`resolve_srcset`).

use domq::{resolve_srcset, resolve_url};

/// The normal and abnormal examples from RFC 3986 §5.4.
#[test]
fn rfc3986_examples() {
    let base = "http://a/b/c/d;p?q";
    let cases = [
        // §5.4.1 normal examples
        ("g:h", "g:h"),
        ("g", "http://a/b/c/g"),
        ("./g", "http://a/b/c/g"),
        ("g/", "http://a/b/c/g/"),
        ("/g", "http://a/g"),
        ("//g", "http://g"),
        ("?y", "http://a/b/c/d;p?y"),
        ("g?y", "http://a/b/c/g?y"),
        ("#s", "http://a/b/c/d;p?q#s"),
        ("g#s", "http://a/b/c/g#s"),
        ("g?y#s", "http://a/b/c/g?y#s"),
        (";x", "http://a/b/c/;x"),
        ("g;x", "http://a/b/c/g;x"),
        ("g;x?y#s", "http://a/b/c/g;x?y#s"),
        ("", "http://a/b/c/d;p?q"),
        (".", "http://a/b/c/"),
        ("./", "http://a/b/c/"),
        ("..", "http://a/b/"),
        ("../", "http://a/b/"),
        ("../g", "http://a/b/g"),
        ("../..", "http://a/"),
        ("../../", "http://a/"),
        ("../../g", "http://a/g"),
        // §5.4.2 abnormal examples
        ("../../../g", "http://a/g"),
        ("../../../../g", "http://a/g"),
        ("/./g", "http://a/g"),
        ("/../g", "http://a/g"),
        ("g.", "http://a/b/c/g."),
        (".g", "http://a/b/c/.g"),
        ("g..", "http://a/b/c/g.."),
        ("..g", "http://a/b/c/..g"),
        ("./../g", "http://a/b/g"),
        ("./g/.", "http://a/b/c/g/"),
        ("g/./h", "http://a/b/c/g/h"),
        ("g/../h", "http://a/b/c/h"),
        ("g;x=1/./y", "http://a/b/c/g;x=1/y"),
        ("g;x=1/../y", "http://a/b/c/y"),
        ("g?y/./x", "http://a/b/c/g?y/./x"),
        ("g?y/../x", "http://a/b/c/g?y/../x"),
        ("g#s/./x", "http://a/b/c/g#s/./x"),
        ("g#s/../x", "http://a/b/c/g#s/../x"),
        ("http:g", "http:g"), // strict parsers
    ];
    for (reference, want) in cases {
        assert_eq!(
            resolve_url(base, reference),
            want,
            "resolving {reference:?}"
        );
    }
}

#[test]
fn host_only_base() {
    assert_eq!(resolve_url("https://x.dev", "a/b"), "https://x.dev/a/b");
    assert_eq!(resolve_url("https://x.dev", "/a"), "https://x.dev/a");
    assert_eq!(resolve_url("https://x.dev", "?q"), "https://x.dev?q");
}

#[test]
fn schemeless_base_leaves_reference_alone() {
    assert_eq!(resolve_url("/docs/", "a.html"), "a.html");
    assert_eq!(resolve_url("", " ../x "), "../x");
}

#[test]
fn whitespace_is_cleaned_like_a_browser() {
    let base = "https://x.dev/a/";
    assert_eq!(resolve_url(base, "  b.html\n"), "https://x.dev/a/b.html");
    // Tabs and line breaks inside a URL are dropped.
    assert_eq!(resolve_url(base, "b\n.ht\tml"), "https://x.dev/a/b.html");
    assert_eq!(resolve_url(" https://x.dev/a/ ", "c"), "https://x.dev/a/c");
}

#[test]
fn base_fragment_is_ignored() {
    assert_eq!(resolve_url("https://x.dev/p#frag", "q"), "https://x.dev/q");
    assert_eq!(
        resolve_url("https://x.dev/p?a#frag", ""),
        "https://x.dev/p?a"
    );
}

#[test]
fn other_schemes_pass_through() {
    let base = "https://x.dev/";
    assert_eq!(resolve_url(base, "mailto:a@b.c"), "mailto:a@b.c");
    assert_eq!(
        resolve_url(base, "javascript:void(0)"),
        "javascript:void(0)"
    );
    assert_eq!(
        resolve_url(base, "data:text/plain,hi"),
        "data:text/plain,hi"
    );
    // Not a scheme: `/` before the colon.
    assert_eq!(resolve_url(base, "a/b:c"), "https://x.dev/a/b:c");
}

#[test]
fn backslashes_are_slashes_in_special_schemes() {
    // Browsers read `\` as `/` in http(s), ftp, ws(s) and file URLs, so these
    // leave the page's host.
    let base = "https://a.example/b/c";
    let cases = [
        (r"\\evil.example\x", "https://evil.example/x"),
        (r"/\evil.example/x", "https://evil.example/x"),
        (r"\/evil.example/x", "https://evil.example/x"),
        (r"\x\y", "https://a.example/x/y"),
        (r"a\b", "https://a.example/b/a/b"),
        (r"a\..\b", "https://a.example/b/b"),
        // Ends the authority, so this is evil.example, not a user name.
        (
            r"https://evil.example\@good.example/",
            "https://evil.example/@good.example/",
        ),
        (r"HTTPS:\\X.example\p", "HTTPS://X.example/p"),
        (r"ws:\\h\p", "ws://h/p"),
        (r"file:\\server\share", "file://server/share"),
        // Not in the query or fragment.
        (r"p\q?x\y#z\w", r"https://a.example/b/p/q?x\y#z\w"),
        (r"#f\g", r"https://a.example/b/c#f\g"),
        (r"?\x", r"https://a.example/b/c?\x"),
        // Not in other schemes, whatever the base.
        (r"mailto:a\b", r"mailto:a\b"),
        (r"foo://h/a\b", r"foo://h/a\b"),
        // Not a scheme: `\` before the colon.
        (r"a\b:c", "https://a.example/b/a/b:c"),
    ];
    for (reference, want) in cases {
        assert_eq!(
            resolve_url(base, reference),
            want,
            "resolving {reference:?}"
        );
    }
    for base in ["http://a/b", "ftp://a/b", "wss://a/b", "file:///a/b"] {
        let host = resolve_url(base, r"\\evil\x");
        assert!(host.ends_with("://evil/x"), "{base}: {host}");
    }
    // A special-scheme base with backslashes is read the same way.
    assert_eq!(
        resolve_url(r"https:\\a.example\b\c", "d"),
        "https://a.example/b/d"
    );
    // Relative references against other schemes keep them.
    assert_eq!(resolve_url("foo://h/p/q", r"a\b"), r"foo://h/p/a\b");
    assert_eq!(resolve_url(r"foo://h\p", "x"), r"foo://h\p/x");
    // Without a base scheme, only a reference with a special scheme of its own
    // can be told apart.
    assert_eq!(resolve_url("", r"\\evil\x"), r"\\evil\x");
    assert_eq!(resolve_url("/docs/", r"http:\\evil\x"), "http://evil/x");
}

#[test]
fn never_panics_on_odd_input() {
    for s in [
        "",
        ":",
        "::",
        "//",
        "///",
        "?",
        "#",
        "a:",
        ":a",
        "..",
        "/..",
        "🦀:x",
        "x:🦀",
        "http://",
        "http:///x",
        "\u{0}",
        "%",
        "\\\\x",
    ] {
        let _ = resolve_url(s, s);
        let _ = resolve_url("http://a/b", s);
        let _ = resolve_url(s, "http://a/b");
        let _ = resolve_srcset(s, s);
    }
}

#[test]
fn srcset() {
    assert_eq!(
        resolve_srcset("https://x.dev/p/", "a.png 1x, /b.png 2x"),
        "https://x.dev/p/a.png 1x, https://x.dev/b.png 2x"
    );
}

#[test]
fn srcset_urls_may_contain_commas() {
    // Cloudinary-style URLs: commas are part of the URL, not separators.
    let srcset = "https://c.io/up/c_fill,w_300/a.jpg 300w, https://c.io/up/c_fill,w_600/a.jpg 600w";
    assert_eq!(resolve_srcset("https://x.dev/", srcset), srcset);
    assert_eq!(
        resolve_srcset("https://x.dev/", "/c_fill,w_300/a.jpg 300w,/b.jpg 600w"),
        "https://x.dev/c_fill,w_300/a.jpg 300w, https://x.dev/b.jpg 600w"
    );
    assert_eq!(
        resolve_srcset("https://x.dev/", "data:image/png;base64,AAAA 1x"),
        "data:image/png;base64,AAAA 1x"
    );
}

#[test]
fn srcset_trailing_and_empty_candidates() {
    // A trailing comma ends the URL; it is not an empty candidate that would
    // resolve to the base.
    assert_eq!(
        resolve_srcset("https://x.dev/", "a.png 1x,"),
        "https://x.dev/a.png 1x"
    );
    assert_eq!(
        resolve_srcset("https://x.dev/", "a.png,"),
        "https://x.dev/a.png"
    );
    assert_eq!(
        resolve_srcset("https://x.dev/", " , ,a.png,, b.png 2x ,"),
        "https://x.dev/a.png, https://x.dev/b.png 2x"
    );
    assert_eq!(resolve_srcset("https://x.dev/", " , "), "");
    assert_eq!(resolve_srcset("https://x.dev/", ""), "");
}

#[test]
fn srcset_descriptors_keep_parentheses() {
    // Descriptors run to the next comma outside parentheses.
    assert_eq!(
        resolve_srcset("https://x.dev/", "a.png (x, y) 1x, b.png"),
        "https://x.dev/a.png (x, y) 1x, https://x.dev/b.png"
    );
    assert_eq!(
        resolve_srcset("https://x.dev/", "a.png\t\n 2x"),
        "https://x.dev/a.png 2x"
    );
}