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
|
# coding: utf-8
from __future__ import with_statement
import pytest
from whoosh import analysis, highlight, fields, qparser, query
from whoosh.compat import u
from whoosh.filedb.filestore import RamStorage
from whoosh.util.testing import TempIndex
_doc = u("alfa bravo charlie delta echo foxtrot golf hotel india juliet " +
"kilo lima")
def test_null_fragment():
terms = frozenset(("bravo", "india"))
sa = analysis.StandardAnalyzer()
nf = highlight.WholeFragmenter()
uc = highlight.UppercaseFormatter()
htext = highlight.highlight(_doc, terms, sa, nf, uc)
assert htext == "alfa BRAVO charlie delta echo foxtrot golf hotel INDIA juliet kilo lima"
def test_sentence_fragment():
text = u("This is the first sentence. This one doesn't have the word. " +
"This sentence is the second. Third sentence here.")
terms = ("sentence",)
sa = analysis.StandardAnalyzer(stoplist=None)
sf = highlight.SentenceFragmenter()
uc = highlight.UppercaseFormatter()
htext = highlight.highlight(text, terms, sa, sf, uc)
assert htext == "This is the first SENTENCE...This SENTENCE is the second...Third SENTENCE here"
def test_context_fragment():
terms = frozenset(("bravo", "india"))
sa = analysis.StandardAnalyzer()
cf = highlight.ContextFragmenter(surround=6)
uc = highlight.UppercaseFormatter()
htext = highlight.highlight(_doc, terms, sa, cf, uc)
assert htext == "alfa BRAVO charlie...hotel INDIA juliet"
def test_context_at_start():
terms = frozenset(["alfa"])
sa = analysis.StandardAnalyzer()
cf = highlight.ContextFragmenter(surround=15)
uc = highlight.UppercaseFormatter()
htext = highlight.highlight(_doc, terms, sa, cf, uc)
assert htext == "ALFA bravo charlie delta echo foxtrot"
def test_html_format():
terms = frozenset(("bravo", "india"))
sa = analysis.StandardAnalyzer()
cf = highlight.ContextFragmenter(surround=6)
hf = highlight.HtmlFormatter()
htext = highlight.highlight(_doc, terms, sa, cf, hf)
assert htext == 'alfa <strong class="match term0">bravo</strong> charlie...hotel <strong class="match term1">india</strong> juliet'
def test_html_escape():
terms = frozenset(["bravo"])
sa = analysis.StandardAnalyzer()
wf = highlight.WholeFragmenter()
hf = highlight.HtmlFormatter()
htext = highlight.highlight(u('alfa <bravo "charlie"> delta'), terms, sa,
wf, hf)
assert htext == 'alfa <<strong class="match term0">bravo</strong> "charlie"> delta'
def test_maxclasses():
terms = frozenset(("alfa", "bravo", "charlie", "delta", "echo"))
sa = analysis.StandardAnalyzer()
cf = highlight.ContextFragmenter(surround=6)
hf = highlight.HtmlFormatter(tagname="b", termclass="t", maxclasses=2)
htext = highlight.highlight(_doc, terms, sa, cf, hf)
assert htext == '<b class="match t0">alfa</b> <b class="match t1">bravo</b> <b class="match t0">charlie</b>...<b class="match t1">delta</b> <b class="match t0">echo</b> foxtrot'
def test_workflow_easy():
schema = fields.Schema(id=fields.ID(stored=True),
title=fields.TEXT(stored=True))
ix = RamStorage().create_index(schema)
w = ix.writer()
w.add_document(id=u("1"), title=u("The man who wasn't there"))
w.add_document(id=u("2"), title=u("The dog who barked at midnight"))
w.add_document(id=u("3"), title=u("The invisible man"))
w.add_document(id=u("4"), title=u("The girl with the dragon tattoo"))
w.add_document(id=u("5"), title=u("The woman who disappeared"))
w.commit()
with ix.searcher() as s:
# Parse the user query
parser = qparser.QueryParser("title", schema=ix.schema)
q = parser.parse(u("man"))
r = s.search(q, terms=True)
assert len(r) == 2
r.fragmenter = highlight.WholeFragmenter()
r.formatter = highlight.UppercaseFormatter()
outputs = [hit.highlights("title") for hit in r]
assert outputs == ["The invisible MAN", "The MAN who wasn't there"]
def test_workflow_manual():
schema = fields.Schema(id=fields.ID(stored=True),
title=fields.TEXT(stored=True))
ix = RamStorage().create_index(schema)
w = ix.writer()
w.add_document(id=u("1"), title=u("The man who wasn't there"))
w.add_document(id=u("2"), title=u("The dog who barked at midnight"))
w.add_document(id=u("3"), title=u("The invisible man"))
w.add_document(id=u("4"), title=u("The girl with the dragon tattoo"))
w.add_document(id=u("5"), title=u("The woman who disappeared"))
w.commit()
with ix.searcher() as s:
# Parse the user query
parser = qparser.QueryParser("title", schema=ix.schema)
q = parser.parse(u("man"))
# Extract the terms the user used in the field we're interested in
terms = [text for fieldname, text in q.all_terms()
if fieldname == "title"]
# Perform the search
r = s.search(q)
assert len(r) == 2
# Use the same analyzer as the field uses. To be sure, you can
# do schema[fieldname].analyzer. Be careful not to do this
# on non-text field types such as DATETIME.
analyzer = schema["title"].analyzer
# Since we want to highlight the full title, not extract fragments,
# we'll use WholeFragmenter.
nf = highlight.WholeFragmenter()
# In this example we'll simply uppercase the matched terms
fmt = highlight.UppercaseFormatter()
outputs = []
for d in r:
text = d["title"]
outputs.append(highlight.highlight(text, terms, analyzer, nf, fmt))
assert outputs == ["The invisible MAN", "The MAN who wasn't there"]
def test_unstored():
schema = fields.Schema(text=fields.TEXT, tags=fields.KEYWORD)
ix = RamStorage().create_index(schema)
w = ix.writer()
w.add_document(text=u("alfa bravo charlie"), tags=u("delta echo"))
w.commit()
hit = ix.searcher().search(query.Term("text", "bravo"))[0]
with pytest.raises(KeyError):
hit.highlights("tags")
def test_multifilter():
iwf_for_index = analysis.IntraWordFilter(mergewords=True, mergenums=False)
iwf_for_query = analysis.IntraWordFilter(mergewords=False, mergenums=False)
mf = analysis.MultiFilter(index=iwf_for_index, query=iwf_for_query)
ana = analysis.RegexTokenizer() | mf | analysis.LowercaseFilter()
schema = fields.Schema(text=fields.TEXT(analyzer=ana, stored=True))
with TempIndex(schema) as ix:
w = ix.writer()
w.add_document(text=u("Our BabbleTron5000 is great"))
w.commit()
with ix.searcher() as s:
assert ("text", "5000") in s.reader()
hit = s.search(query.Term("text", "5000"))[0]
assert (hit.highlights("text")
== 'Our BabbleTron<b class="match term0">5000</b> is great')
def test_pinpoint():
domain = u("alfa bravo charlie delta echo foxtrot golf hotel india juliet "
"kilo lima mike november oskar papa quebec romeo sierra tango")
schema = fields.Schema(text=fields.TEXT(stored=True, chars=True))
ix = RamStorage().create_index(schema)
w = ix.writer()
w.add_document(text=domain)
w.commit()
assert ix.schema["text"].supports("characters")
with ix.searcher() as s:
r = s.search(query.Term("text", "juliet"), terms=True)
hit = r[0]
hi = highlight.Highlighter()
hi.formatter = highlight.UppercaseFormatter()
assert not hi.can_load_chars(r, "text")
assert (hi.highlight_hit(hit, "text")
== "golf hotel india JULIET kilo lima mike november")
hi.fragmenter = highlight.PinpointFragmenter()
assert hi.can_load_chars(r, "text")
assert (hi.highlight_hit(hit, "text")
== "ot golf hotel india JULIET kilo lima mike nove")
hi.fragmenter.autotrim = True
assert (hi.highlight_hit(hit, "text")
== "golf hotel india JULIET kilo lima mike")
def test_highlight_wildcards():
schema = fields.Schema(text=fields.TEXT(stored=True))
ix = RamStorage().create_index(schema)
with ix.writer() as w:
w.add_document(text=u("alfa bravo charlie delta cookie echo"))
with ix.searcher() as s:
qp = qparser.QueryParser("text", ix.schema)
q = qp.parse(u("c*"))
r = s.search(q)
assert r.scored_length() == 1
r.formatter = highlight.UppercaseFormatter()
hit = r[0]
assert hit.highlights("text") == "alfa bravo CHARLIE delta COOKIE echo"
def test_highlight_ngrams():
schema = fields.Schema(text=fields.NGRAMWORDS(stored=True))
ix = RamStorage().create_index(schema)
with ix.writer() as w:
w.add_document(text=u("Multiplication and subtraction are good"))
with ix.searcher() as s:
qp = qparser.QueryParser("text", ix.schema)
q = qp.parse(u("multiplication"))
r = s.search(q)
assert r.scored_length() == 1
r.fragmenter = highlight.SentenceFragmenter()
r.formatter = highlight.UppercaseFormatter()
snippet = r[0].highlights("text")
assert snippet == "MULTIPLICATIon and subtracTION are good"
def test_issue324():
sa = analysis.StemmingAnalyzer()
result = highlight.highlight(u("Indexed!\n1"), [u("index")], sa,
fragmenter=highlight.ContextFragmenter(),
formatter=highlight.UppercaseFormatter())
assert result == "INDEXED!\n1"
def test_whole_noterms():
schema = fields.Schema(text=fields.TEXT(stored=True), tag=fields.KEYWORD)
ix = RamStorage().create_index(schema)
with ix.writer() as w:
w.add_document(text=u("alfa bravo charlie delta echo foxtrot golf"),
tag=u("foo"))
with ix.searcher() as s:
r = s.search(query.Term("text", u("delta")))
assert len(r) == 1
r.fragmenter = highlight.WholeFragmenter()
r.formatter = highlight.UppercaseFormatter()
hi = r[0].highlights("text")
assert hi == u("alfa bravo charlie DELTA echo foxtrot golf")
r = s.search(query.Term("tag", u("foo")))
assert len(r) == 1
r.fragmenter = highlight.WholeFragmenter()
r.formatter = highlight.UppercaseFormatter()
hi = r[0].highlights("text")
assert hi == u("")
hi = r[0].highlights("text", minscore=0)
assert hi == u("alfa bravo charlie delta echo foxtrot golf")
|
