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
|
// |reftest| random -- bogus perf test (bug 467263)
/* -*- Mode: C++; tab-width: 2; indent-tabs-mode: nil; c-basic-offset: 2 -*- */
/* This Source Code Form is subject to the terms of the Mozilla Public
* License, v. 2.0. If a copy of the MPL was not distributed with this
* file, You can obtain one at http://mozilla.org/MPL/2.0/. */
/*
*
* Date: 14 Feb 2002
* SUMMARY: Performance: Regexp performance degraded from 4.7
* See http://bugzilla.mozilla.org/show_bug.cgi?id=85721
*
* Adjust this testcase if necessary. The FAST constant defines
* an upper bound in milliseconds for any execution to take.
*
*/
//-----------------------------------------------------------------------------
var BUGNUMBER = 85721;
var summary = 'Performance: execution of regular expression';
var FAST = 100; // execution should be 100 ms or less to pass the test
var MSG_FAST = 'Execution took less than ' + FAST + ' ms';
var MSG_SLOW = 'Execution took ';
var MSG_MS = ' ms';
var str = '';
var re = '';
var status = '';
var actual = '';
var expect= '';
printBugNumber(BUGNUMBER);
printStatus (summary);
function elapsedTime(startTime)
{
return new Date() - startTime;
}
function isThisFast(ms)
{
if (ms <= FAST)
return MSG_FAST;
return MSG_SLOW + ms + MSG_MS;
}
/*
* The first regexp. We'll test for performance (Section 1) and accuracy (Section 2).
*/
str='<sql:connection id="conn1"> <sql:url>www.m.com</sql:url> <sql:driver>drive.class</sql:driver>\n<sql:userId>foo</sql:userId> <sql:password>goo</sql:password> </sql:connection>';
re = /<sql:connection id="([^\r\n]*?)">\s*<sql:url>\s*([^\r\n]*?)\s*<\/sql:url>\s*<sql:driver>\s*([^\r\n]*?)\s*<\/sql:driver>\s*(\s*<sql:userId>\s*([^\r\n]*?)\s*<\/sql:userId>\s*)?\s*(\s*<sql:password>\s*([^\r\n]*?)\s*<\/sql:password>\s*)?\s*<\/sql:connection>/;
expect = Array("<sql:connection id=\"conn1\"> <sql:url>www.m.com</sql:url> <sql:driver>drive.class</sql:driver>\n<sql:userId>foo</sql:userId> <sql:password>goo</sql:password> </sql:connection>","conn1","www.m.com","drive.class","<sql:userId>foo</sql:userId> ","foo","<sql:password>goo</sql:password> ","goo");
/*
* Check performance -
*/
status = inSection(1);
var start = new Date();
var result = re.exec(str);
actual = elapsedTime(start);
reportCompare(isThisFast(FAST), isThisFast(actual), status);
/*
* Check accuracy -
*/
status = inSection(2);
testRegExp([status], [re], [str], [result], [expect]);
/*
* The second regexp (HUGE!). We'll test for performance (Section 3) and accuracy (Section 4).
* It comes from the O'Reilly book "Mastering Regular Expressions" by Jeffrey Friedl, Appendix B
*/
//# Some things for avoiding backslashitis later on.
$esc = '\\\\';
$Period = '\.';
$space = '\040'; $tab = '\t';
$OpenBR = '\\['; $CloseBR = '\\]';
$OpenParen = '\\('; $CloseParen = '\\)';
$NonASCII = '\x80-\xff'; $ctrl = '\000-\037';
$CRlist = '\n\015'; //# note: this should really be only \015.
// Items 19, 20, 21
$qtext = '[^' + $esc + $NonASCII + $CRlist + '\"]'; // # for within "..."
$dtext = '[^' + $esc + $NonASCII + $CRlist + $OpenBR + $CloseBR + ']'; // # for within [...]
$quoted_pair = $esc + '[^' + $NonASCII + ']'; // # an escaped character
//##############################################################################
//# Items 22 and 23, comment.
//# Impossible to do properly with a regex, I make do by allowing at most one level of nesting.
$ctext = '[^' + $esc + $NonASCII + $CRlist + '()]';
//# $Cnested matches one non-nested comment.
//# It is unrolled, with normal of $ctext, special of $quoted_pair.
$Cnested =
$OpenParen + // # (
$ctext + '*' + // # normal*
'(?:' + $quoted_pair + $ctext + '*)*' + // # (special normal*)*
$CloseParen; // # )
//# $comment allows one level of nested parentheses
//# It is unrolled, with normal of $ctext, special of ($quoted_pair|$Cnested)
$comment =
$OpenParen + // # (
$ctext + '*' + // # normal*
'(?:' + // # (
'(?:' + $quoted_pair + '|' + $Cnested + ')' + // # special
$ctext + '*' + // # normal*
')*' + // # )*
$CloseParen; // # )
//##############################################################################
//# $X is optional whitespace/comments.
$X =
'[' + $space + $tab + ']*' + // # Nab whitespace.
'(?:' + $comment + '[' + $space + $tab + ']*)*'; // # If comment found, allow more spaces.
//# Item 10: atom
$atom_char = '[^(' + $space + '<>\@,;:\".' + $esc + $OpenBR + $CloseBR + $ctrl + $NonASCII + ']';
$atom =
$atom_char + '+' + // # some number of atom characters...
'(?!' + $atom_char + ')'; // # ..not followed by something that could be part of an atom
// # Item 11: doublequoted string, unrolled.
$quoted_str =
'\"' + // # "
$qtext + '*' + // # normal
'(?:' + $quoted_pair + $qtext + '*)*' + // # ( special normal* )*
'\"'; // # "
//# Item 7: word is an atom or quoted string
$word =
'(?:' +
$atom + // # Atom
'|' + // # or
$quoted_str + // # Quoted string
')'
//# Item 12: domain-ref is just an atom
$domain_ref = $atom;
//# Item 13: domain-literal is like a quoted string, but [...] instead of "..."
$domain_lit =
$OpenBR + // # [
'(?:' + $dtext + '|' + $quoted_pair + ')*' + // # stuff
$CloseBR; // # ]
// # Item 9: sub-domain is a domain-ref or domain-literal
$sub_domain =
'(?:' +
$domain_ref +
'|' +
$domain_lit +
')' +
$X; // # optional trailing comments
// # Item 6: domain is a list of subdomains separated by dots.
$domain =
$sub_domain +
'(?:' +
$Period + $X + $sub_domain +
')*';
//# Item 8: a route. A bunch of "@ $domain" separated by commas, followed by a colon.
$route =
'\@' + $X + $domain +
'(?:,' + $X + '\@' + $X + $domain + ')*' + // # additional domains
':' +
$X; // # optional trailing comments
//# Item 6: local-part is a bunch of $word separated by periods
$local_part =
$word + $X
'(?:' +
$Period + $X + $word + $X + // # additional words
')*';
// # Item 2: addr-spec is local@domain
$addr_spec =
$local_part + '\@' + $X + $domain;
//# Item 4: route-addr is <route? addr-spec>
$route_addr =
'<' + $X + // # <
'(?:' + $route + ')?' + // # optional route
$addr_spec + // # address spec
'>'; // # >
//# Item 3: phrase........
$phrase_ctrl = '\000-\010\012-\037'; // # like ctrl, but without tab
//# Like atom-char, but without listing space, and uses phrase_ctrl.
//# Since the class is negated, this matches the same as atom-char plus space and tab
$phrase_char =
'[^()<>\@,;:\".' + $esc + $OpenBR + $CloseBR + $NonASCII + $phrase_ctrl + ']';
// # We've worked it so that $word, $comment, and $quoted_str to not consume trailing $X
// # because we take care of it manually.
$phrase =
$word + // # leading word
$phrase_char + '*' + // # "normal" atoms and/or spaces
'(?:' +
'(?:' + $comment + '|' + $quoted_str + ')' + // # "special" comment or quoted string
$phrase_char + '*' + // # more "normal"
')*';
// ## Item #1: mailbox is an addr_spec or a phrase/route_addr
$mailbox =
$X + // # optional leading comment
'(?:' +
$phrase + $route_addr + // # name and address
'|' + // # or
$addr_spec + // # address
')';
//###########################################################################
re = new RegExp($mailbox, "g");
str = 'Jeffy<"That Tall Guy"@ora.com (this address is no longer active)>';
expect = Array('Jeffy<"That Tall Guy"@ora.com (this address is no longer active)>');
/*
* Check performance -
*/
status = inSection(3);
var start = new Date();
var result = re.exec(str);
actual = elapsedTime(start);
reportCompare(isThisFast(FAST), isThisFast(actual), status);
/*
* Check accuracy -
*/
status = inSection(4);
testRegExp([status], [re], [str], [result], [expect]);
|
