source: icGREP/icgrep-devel/QA/greptest.xml @ 4120

Last change on this file since 4120 was 4120, checked in by cameron, 5 years ago

Check in IP tests for fixed bound repetition

File size: 7.0 KB
Line 
1
2<greptest>
3<datafile id="simple1">
4A few lines of input
5in this simple test file
6provide fodder for some simple
7regexp tests.
8</datafile>
9
10<grepcase regexp="in" datafile="simple1" grepcount="2"/>
11<grepcase regexp="[A-Z]" datafile="simple1" grepcount="1"/>
12<grepcase regexp="fodder|simple" datafile="simple1" grepcount="2"/>
13
14<datafile id="bounded_charclass">
15=a;
16=bb;
17=ccc;
18=dddd;
19=eeeee;
20=ffffff;
21=ggggggg;
22=hhhhhhhh;
23=iiiiiiiii;
24=jjjjjjjjjj;
25=kkkkkkkkkkk;
26=llllllllllll;
27=mmmmmmmmmmmmm;
28=nnnnnnnnnnnnnn;
29=ooooooooooooooo;
30=pppppppppppppppp;
31=qqqqqqqqqqqqqqqqq;
32=rrrrrrrrrrrrrrrrrr;
33=sssssssssssssssssss;
34=tttttttttttttttttttt;
35=uuuuuuuuuuuuuuuuuuuuu;
36=vvvvvvvvvvvvvvvvvvvvvv;
37=wwwwwwwwwwwwwwwwwwwwwww;
38=xxxxxxxxxxxxxxxxxxxxxxxx;
39=yyyyyyyyyyyyyyyyyyyyyyyyy;
40=zzzzzzzzzzzzzzzzzzzzzzzzzz;
41</datafile>
42<grepcase regexp="[cde]{3}" datafile="bounded_charclass" grepcount="3"/>
43<grepcase regexp="[f-h]{5}" datafile="bounded_charclass" grepcount="3"/>
44<grepcase regexp="[a-z]{5}" datafile="bounded_charclass" grepcount="22"/>
45<grepcase regexp="[a-z]{5,15}" datafile="bounded_charclass" grepcount="22"/>
46<grepcase regexp="=[a-z]{7,}" datafile="bounded_charclass" grepcount="20"/>
47<grepcase regexp="=[a-z]{5,15};" datafile="bounded_charclass" grepcount="11"/>
48<grepcase regexp="[wxy]{2}{3}{2}" datafile="bounded_charclass" grepcount="3"/>
49<grepcase regexp="=([a-z][c-z])*;" datafile="bounded_charclass" grepcount="12"/>
50
51<datafile id="RangeAltSeqMatchStarKplusWhileNotOptAny">
52Dogbe hat ,/R Cat dt bt bt bt bt bat MzzzzzzzzT MaT MT McT MdT MeT M0T M1T M2T M3T M4T
53Dogbe hit foffasm zza " Dog Cat 1, 4= Dog ['zxcvbnm,./R Dog MT
54Dogbe hot foffasm czzb " MazazazTDogogogogog Cat 1, 4= Dog [;'zxcvbnm,./R Dogtp
55Dogbe foffasm dooooc MazT" Dog Cat 1, 4= Dog [Sqwertyuiopasdfghjkl;'zxcvbnm,./R Dog Cat
56Dogbe foffasm ezzzzzzzzzzzzzzt "tp Dog Cat 12, ktp 4= Dog [jkl;'zxcvbnm,./R Dogtp
57Dogbe foffasm zze " Dog CatMjT , = Dog [;'zxcvbzzznm,./R Dog MazazT cat
58zzcztpDogbe fofasm zazazz4z Doggg Cat 6, azzzzz= Dog [;'zxcvbonm,.R Dog TUT Dog
59Natatatats Nats T M0T ed bazbzczdzt et
60Dfg dc fog Nt ezt
61MazazazazazazazT
62</datafile>
63
64<grepcase regexp="^D[zabcdefoy]g" datafile="RangeAltSeqMatchStarKplusWhileNotOptAny" grepcount="7"/>
65<grepcase regexp="do*c|ez*t" datafile="RangeAltSeqMatchStarKplusWhileNotOptAny" grepcount="4"/>
66<grepcase regexp="M(az)*T" datafile="RangeAltSeqMatchStarKplusWhileNotOptAny" grepcount="6"/>         
67<grepcase regexp="ez+t" datafile="RangeAltSeqMatchStarKplusWhileNotOptAny" grepcount="2" />
68<grepcase regexp="b([a-d]z)*t" datafile="RangeAltSeqMatchStarKplusWhileNotOptAny" grepcount="2"/>
69<grepcase regexp="[^D]og" datafile="RangeAltSeqMatchStarKplusWhileNotOptAny" grepcount="2"/>
70<grepcase regexp="Na?t" datafile="RangeAltSeqMatchStarKplusWhileNotOptAny" grepcount="2"/>
71<grepcase regexp="h.t" datafile="RangeAltSeqMatchStarKplusWhileNotOptAny" grepcount="3" />
72
73<datafile id="StartEndAlt">
74The ever-growing social networks and social media provide invaluable
75sources of information for modeling the behavior of users. High-quality
76user models enable superior services and functions for end users. In this
77talk, I will present several examples of user modeling based on social
78networks and social media. I will first describe our research in modeling
79users' information preferences on Microblogs using a novel user message
80model. I will then discuss our work on extracting users' daily activities,
81such as dining and shopping, that inherently reflect their habits, intents and preferences.
82I explain our novel transfer learning solution via a collaborative boosting
83framework comprising a text-to-activity classifier for socially connected users.
84I will also describe our research on user modeling in multiple, overlapping
85social networks in a 'composite social network' setting. I will show the benefits of
86modeling the dynamics of composite networks, where the evolution processes
87of different networks are jointly considered. Finally, I will explain our
88research on finding social spammers in large social networks.
89</datafile>
90
91<grepcase regexp="^user|^I|our$" datafile="StartEndAlt" grepcount="5"/>
92
93<datafile id="special_characters">
94The ] character may appear as the first character inside character class
95expressions such as []>)].
96In this case, the ] character does not terminate the character class, but
97stands for itself.
98Similarly, the - character may appear as the first or last character
99in a character class expression, such as [-] or []-].  Occurring as the
100first or last character in a class means that it is a member of the
101class, instead of being interpreted as a range metacharacter.
102For both ] and -, occurrence as the first character could mean after
103an opening [^ mark for negated character class.   That is [^]] is the
104class that matches everything but ], while [^-] is the class that matches
105anything but -.
106----------
107The above line does not match [^-].
108----------
109]]]]]]]]]]
110</datafile>
111<grepcase regexp="[]]" datafile="special_characters" grepcount="9"/>
112<grepcase regexp="[-]" datafile="special_characters" grepcount="8"/>
113<grepcase regexp="[^]]" datafile="special_characters" grepcount="15"/>
114<grepcase regexp="[^-]" datafile="special_characters" grepcount="14"/>
115<grepcase regexp="[^]-]" datafile="special_characters" grepcount="13"/>
116
117
118<datafile id="ips"> 
119201.250.180.213
120236.4.20.176
121137.96.194.126
122245.16.96.112
123245.19.58.43
124131.176.131.248
125248.160.22.214
126156.179.88.103
127174.13.62.156
128256.122.123.5
12916.81.78.152
130177.17.24.167
13132.120.25.23
132138.82.66.15
1334.196.8.251
134101.30.211.3
135209.44.105.129
13656.166.31.72
137247.108.224.170
138124.248.83.156
139113.107.178.250
140189.243.10.192
141184.18.189.31
14248.145.33.2
143188.137.131.244
14449.161.61.42
14514.31.211.138
14624.39.39.136
147146.217.131.80
148205.141.18.135
149159.207.166.206
15096.211.62.20
15123.148.44.140
152109.159.129.161
153183.230.172.129
15448.178.63.192
155224.41.190.207
156144.114.56.31
157151.205.132.247
158161.194.12.184
15987.55.69.195
160214.198.102.143
161173.19.17.220
162197.80.158.167
163121.94.119.11
164208.174.42.104
165124.173.96.31
166112.107.215.199
167162.30.140.121
168227.241.9.145
1696.26.111.203
170106.14.115.226
171107.233.237.60
172153.24.163.23
173197.4.54.55
174111.14.253.18
17543.138.139.15
176125.148.160.131
177173.16.80.24
17830.194.250.136
179173.233.196.71
180</datafile>
181
182<grepcase regexp="^((([2][5][0-5]|([2][0-4]|[1][0-9]|[0-9])?[0-9])[.]){3})([2][5][0-5]|([2][0-4]|[1][0-9]|[0-9])?[0-9])$" datafile="ips" grepcount="60"/>
183
184<datafile id = "CRLF">line with CRLF &#13;&#10;two lines with LFCR &#10;&#13;final line
185</datafile>
186 <grepcase regexp="^$" datafile="CRLF" grepcount="1"/>
187 <grepcase regexp="^.*$" datafile="CRLF" grepcount="4"/>
188
189 <datafile id = "LU_test">
190The following line has LATIN CAPITAL LETTER G WITH MACRON in single quotes.
191'&#x1E20;'
192</datafile>
193<!-- . should match a unique character, even if it is 3 bytes. -->
194<grepcase regexp="'.'" datafile="LU_test" grepcount="1"/>
195<grepcase regexp="'...'" datafile="LU_test" grepcount="0"/>
196<grepcase regexp="\u{1e20}" datafile="LU_test" grepcount="1"/>
197<grepcase regexp="\u{1e21}" datafile="LU_test" grepcount="0"/>
198<grepcase regexp="\p{Lu}" datafile="LU_test" grepcount="2"/>
199<grepcase regexp="'\p{Lu}'" datafile="LU_test" grepcount="1"/>
200<grepcase regexp="\p{Ll}" datafile="LU_test" grepcount="1"/>
201</greptest>
Note: See TracBrowser for help on using the repository browser.