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
|
describe('Basic html theme search', function() {
function loadFixture(name) {
req = new XMLHttpRequest();
req.open("GET", `base/tests/js/fixtures/${name}`, false);
req.send(null);
return req.responseText;
}
function checkRanking(expectedRanking, results) {
let [nextExpected, ...remainingItems] = expectedRanking;
for (result of results.reverse()) {
if (!nextExpected) break;
let [expectedPage, expectedTitle, expectedTarget] = nextExpected;
let [page, title, target] = result;
if (page == expectedPage && title == expectedTitle && target == expectedTarget) {
[nextExpected, ...remainingItems] = remainingItems;
}
}
expect(remainingItems.length).toEqual(0);
expect(nextExpected).toEqual(undefined);
}
describe('terms search', function() {
it('should find "C++" when in index', function() {
eval(loadFixture("cpp/searchindex.js"));
[_searchQuery, searchterms, excluded, ..._remainingItems] = Search._parseQuery('C++');
terms = Search._index.terms;
titleterms = Search._index.titleterms;
hits = [[
"index",
"<no title>",
"",
null,
5,
"index.rst"
]];
expect(Search.performTermsSearch(searchterms, excluded, terms, titleterms)).toEqual(hits);
});
it('should be able to search for multiple terms', function() {
eval(loadFixture("multiterm/searchindex.js"));
[_searchQuery, searchterms, excluded, ..._remainingItems] = Search._parseQuery('main page');
terms = Search._index.terms;
titleterms = Search._index.titleterms;
hits = [[
'index',
'Main Page',
'',
null,
15,
'index.rst']];
expect(Search.performTermsSearch(searchterms, excluded, terms, titleterms)).toEqual(hits);
});
it('should partially-match "sphinx" when in title index', function() {
eval(loadFixture("partial/searchindex.js"));
[_searchQuery, searchterms, excluded, ..._remainingItems] = Search._parseQuery('sphinx');
terms = Search._index.terms;
titleterms = Search._index.titleterms;
hits = [[
"index",
"sphinx_utils module",
"",
null,
7,
"index.rst"
]];
expect(Search.performTermsSearch(searchterms, excluded, terms, titleterms)).toEqual(hits);
});
});
describe('aggregation of search results', function() {
it('should combine document title and document term matches', function() {
eval(loadFixture("multiterm/searchindex.js"));
searchParameters = Search._parseQuery('main page');
hits = [
[
'index',
'Main Page',
'',
null,
16,
'index.rst'
]
];
expect(Search._performSearch(...searchParameters)).toEqual(hits);
});
});
describe('search result ranking', function() {
/*
* These tests should not proscribe precise expected ordering of search
* results; instead each test case should describe a single relevance rule
* that helps users to locate relevant information efficiently.
*
* If you think that one of the rules seems to be poorly-defined or is
* limiting the potential for search algorithm improvements, please check
* for existing discussion/bugreports related to it on GitHub[1] before
* creating one yourself. Suggestions for possible improvements are also
* welcome.
*
* [1] - https://github.com/sphinx-doc/sphinx.git/
*/
it('should score a code module match above a page-title match', function() {
eval(loadFixture("titles/searchindex.js"));
expectedRanking = [
['index', 'relevance', '#module-relevance'], /* py:module documentation */
['relevance', 'Relevance', ''], /* main title */
];
searchParameters = Search._parseQuery('relevance');
results = Search._performSearch(...searchParameters);
checkRanking(expectedRanking, results);
});
it('should score a main-title match above an object member match', function() {
eval(loadFixture("titles/searchindex.js"));
expectedRanking = [
['relevance', 'Relevance', ''], /* main title */
['index', 'relevance.Example.relevance', '#relevance.Example.relevance'], /* py:class attribute */
];
searchParameters = Search._parseQuery('relevance');
results = Search._performSearch(...searchParameters);
checkRanking(expectedRanking, results);
});
it('should score a main-title match above a subheading-title match', function() {
eval(loadFixture("titles/searchindex.js"));
expectedRanking = [
['relevance', 'Relevance', ''], /* main title */
['index', 'Main Page > Relevance', '#relevance'], /* subsection heading title */
];
searchParameters = Search._parseQuery('relevance');
results = Search._performSearch(...searchParameters);
checkRanking(expectedRanking, results);
});
});
});
describe("htmlToText", function() {
const testHTML = `<html>
<body>
<script src="directory/filename.js"></script>
<div class="body" role="main">
<script>
console.log('dynamic');
</script>
<style>
div.body p.centered {
text-align: center;
margin-top: 25px;
}
</style>
<!-- main content -->
<section id="getting-started">
<h1>Getting Started <a class="headerlink" href="#getting-started" title="Link to this heading">¶</a></h1>
<p>Some text</p>
</section>
<section id="other-section">
<h1>Other Section <a class="headerlink" href="#other-section" title="Link to this heading">¶</a></h1>
<p>Other text</p>
</section>
<section id="yet-another-section">
<h1>Yet Another Section <a class="headerlink" href="#yet-another-section" title="Link to this heading">¶</a></h1>
<p>More text</p>
</section>
</div>
</body>
</html>`;
it("basic case", () => {
expect(Search.htmlToText(testHTML).trim().split(/\s+/)).toEqual([
'Getting', 'Started', 'Some', 'text',
'Other', 'Section', 'Other', 'text',
'Yet', 'Another', 'Section', 'More', 'text'
]);
});
it("will start reading from the anchor", () => {
expect(Search.htmlToText(testHTML, '#other-section').trim().split(/\s+/)).toEqual(['Other', 'Section', 'Other', 'text']);
});
});
// This is regression test for https://github.com/sphinx-doc/sphinx/issues/3150
describe('splitQuery regression tests', () => {
it('can split English words', () => {
const parts = splitQuery(' Hello World ')
expect(parts).toEqual(['Hello', 'World'])
})
it('can split special characters', () => {
const parts = splitQuery('Pin-Code')
expect(parts).toEqual(['Pin', 'Code'])
})
it('can split Chinese characters', () => {
const parts = splitQuery('Hello from 中国 上海')
expect(parts).toEqual(['Hello', 'from', '中国', '上海'])
})
it('can split Emoji (surrogate pair) characters. It should keep emojis.', () => {
const parts = splitQuery('😁😁')
expect(parts).toEqual(['😁😁'])
})
it('can split umlauts. It should keep umlauts.', () => {
const parts = splitQuery('Löschen Prüfung Abändern ærlig spørsmål')
expect(parts).toEqual(['Löschen', 'Prüfung', 'Abändern', 'ærlig', 'spørsmål'])
})
})
|
