1 | /* |
---|
2 | * |
---|
3 | * Copyright (c) 2002 |
---|
4 | * John Maddock |
---|
5 | * |
---|
6 | * Use, modification and distribution are subject to the |
---|
7 | * Boost Software License, Version 1.0. (See accompanying file |
---|
8 | * LICENSE_1_0.txt or copy at http://www.boost.org/LICENSE_1_0.txt) |
---|
9 | * |
---|
10 | */ |
---|
11 | |
---|
12 | #include <iostream> |
---|
13 | #include <fstream> |
---|
14 | #include <iterator> |
---|
15 | #include <cassert> |
---|
16 | #include <boost/test/execution_monitor.hpp> |
---|
17 | #include "./regex_comparison.hpp" |
---|
18 | |
---|
19 | void test_match(const std::string& re, const std::string& text, const std::string& description) |
---|
20 | { |
---|
21 | double time; |
---|
22 | results r(re, description); |
---|
23 | |
---|
24 | std::cout << "Testing: \"" << re << "\" against \"" << description << "\"" << std::endl; |
---|
25 | if(time_greta == true) |
---|
26 | { |
---|
27 | // time = g::time_match(re, text); |
---|
28 | // r.greta_time = time; |
---|
29 | // std::cout << "\tGRETA regex: " << time << "s\n"; |
---|
30 | } |
---|
31 | if(time_safe_greta == true) |
---|
32 | { |
---|
33 | // time = gs::time_match(re, text); |
---|
34 | // r.safe_greta_time = time; |
---|
35 | // std::cout << "\tSafe GRETA regex: " << time << "s\n"; |
---|
36 | } |
---|
37 | if(time_dynamic_xpressive == true) |
---|
38 | { |
---|
39 | time = dxpr::time_match(re, text); |
---|
40 | r.dynamic_xpressive_time = time; |
---|
41 | std::cout << "\tdynamic xpressive regex: " << time << "s\n"; |
---|
42 | } |
---|
43 | if(time_static_xpressive == true) |
---|
44 | { |
---|
45 | time = sxpr::time_match(re, text); |
---|
46 | r.static_xpressive_time = time; |
---|
47 | std::cout << "\tstatic xpressive regex: " << time << "s\n"; |
---|
48 | } |
---|
49 | if(time_boost == true) |
---|
50 | { |
---|
51 | time = b::time_match(re, text); |
---|
52 | r.boost_time = time; |
---|
53 | std::cout << "\tBoost regex: " << time << "s\n"; |
---|
54 | } |
---|
55 | //if(time_posix == true) |
---|
56 | //{ |
---|
57 | // time = posix::time_match(re, text); |
---|
58 | // r.posix_time = time; |
---|
59 | // std::cout << "\tPOSIX regex: " << time << "s\n"; |
---|
60 | //} |
---|
61 | //if(time_pcre == true) |
---|
62 | //{ |
---|
63 | // time = pcr::time_match(re, text); |
---|
64 | // r.pcre_time = time; |
---|
65 | // std::cout << "\tPCRE regex: " << time << "s\n"; |
---|
66 | //} |
---|
67 | r.finalise(); |
---|
68 | result_list.push_back(r); |
---|
69 | } |
---|
70 | |
---|
71 | void test_find_all(const std::string& re, const std::string& text, const std::string& description) |
---|
72 | { |
---|
73 | std::cout << "Testing: " << re << std::endl; |
---|
74 | |
---|
75 | double time; |
---|
76 | results r(re, description); |
---|
77 | |
---|
78 | #if defined(_MSC_VER) && (_MSC_VER >= 1300) |
---|
79 | if(time_greta == true) |
---|
80 | { |
---|
81 | // time = g::time_find_all(re, text); |
---|
82 | // r.greta_time = time; |
---|
83 | // std::cout << "\tGRETA regex: " << time << "s\n"; |
---|
84 | } |
---|
85 | if(time_safe_greta == true) |
---|
86 | { |
---|
87 | // time = gs::time_find_all(re, text); |
---|
88 | // r.safe_greta_time = time; |
---|
89 | // std::cout << "\tSafe GRETA regex: " << time << "s\n"; |
---|
90 | } |
---|
91 | #endif |
---|
92 | if(time_dynamic_xpressive == true) |
---|
93 | { |
---|
94 | time = dxpr::time_find_all(re, text); |
---|
95 | r.dynamic_xpressive_time = time; |
---|
96 | std::cout << "\tdynamic xpressive regex: " << time << "s\n"; |
---|
97 | } |
---|
98 | if(time_static_xpressive == true) |
---|
99 | { |
---|
100 | time = sxpr::time_find_all(re, text); |
---|
101 | r.static_xpressive_time = time; |
---|
102 | std::cout << "\tstatic xpressive regex: " << time << "s\n"; |
---|
103 | } |
---|
104 | if(time_boost == true) |
---|
105 | { |
---|
106 | time = b::time_find_all(re, text); |
---|
107 | r.boost_time = time; |
---|
108 | std::cout << "\tBoost regex: " << time << "s\n"; |
---|
109 | } |
---|
110 | //if(time_posix == true) |
---|
111 | //{ |
---|
112 | // time = posix::time_find_all(re, text); |
---|
113 | // r.posix_time = time; |
---|
114 | // std::cout << "\tPOSIX regex: " << time << "s\n"; |
---|
115 | //} |
---|
116 | //if(time_pcre == true) |
---|
117 | //{ |
---|
118 | // time = pcr::time_find_all(re, text); |
---|
119 | // r.pcre_time = time; |
---|
120 | // std::cout << "\tPCRE regex: " << time << "s\n"; |
---|
121 | //} |
---|
122 | r.finalise(); |
---|
123 | result_list.push_back(r); |
---|
124 | } |
---|
125 | |
---|
126 | //int cpp_main(int argc, char**const argv) |
---|
127 | int main(int argc, char**const argv) |
---|
128 | { |
---|
129 | // start by processing the command line args: |
---|
130 | if(argc < 2) |
---|
131 | return show_usage(); |
---|
132 | int result = 0; |
---|
133 | for(int c = 1; c < argc; ++c) |
---|
134 | { |
---|
135 | result += handle_argument(argv[c]); |
---|
136 | } |
---|
137 | if(result) |
---|
138 | return result; |
---|
139 | |
---|
140 | if(test_matches) |
---|
141 | { |
---|
142 | // these are from the regex docs: |
---|
143 | test_match("^([0-9]+)(\\-| |$)(.*)$", "100- this is a line of ftp response which contains a message string"); |
---|
144 | test_match("([[:digit:]]{4}[- ]){3}[[:digit:]]{3,4}", "1234-5678-1234-456"); |
---|
145 | // these are from http://www.regxlib.com/ |
---|
146 | test_match("^([a-zA-Z0-9_\\-\\.]+)@((\\[[0-9]{1,3}\\.[0-9]{1,3}\\.[0-9]{1,3}\\.)|(([a-zA-Z0-9\\-]+\\.)+))([a-zA-Z]{2,4}|[0-9]{1,3})(\\]?)$", "john_maddock@compuserve.com"); |
---|
147 | test_match("^([a-zA-Z0-9_\\-\\.]+)@((\\[[0-9]{1,3}\\.[0-9]{1,3}\\.[0-9]{1,3}\\.)|(([a-zA-Z0-9\\-]+\\.)+))([a-zA-Z]{2,4}|[0-9]{1,3})(\\]?)$", "foo12@foo.edu"); |
---|
148 | test_match("^([a-zA-Z0-9_\\-\\.]+)@((\\[[0-9]{1,3}\\.[0-9]{1,3}\\.[0-9]{1,3}\\.)|(([a-zA-Z0-9\\-]+\\.)+))([a-zA-Z]{2,4}|[0-9]{1,3})(\\]?)$", "bob.smith@foo.tv"); |
---|
149 | test_match("^[a-zA-Z]{1,2}[0-9][0-9A-Za-z]{0,1} {0,1}[0-9][A-Za-z]{2}$", "EH10 2QQ"); |
---|
150 | test_match("^[a-zA-Z]{1,2}[0-9][0-9A-Za-z]{0,1} {0,1}[0-9][A-Za-z]{2}$", "G1 1AA"); |
---|
151 | test_match("^[a-zA-Z]{1,2}[0-9][0-9A-Za-z]{0,1} {0,1}[0-9][A-Za-z]{2}$", "SW1 1ZZ"); |
---|
152 | test_match("^[[:digit:]]{1,2}/[[:digit:]]{1,2}/[[:digit:]]{4}$", "4/1/2001"); |
---|
153 | test_match("^[[:digit:]]{1,2}/[[:digit:]]{1,2}/[[:digit:]]{4}$", "12/12/2001"); |
---|
154 | test_match("^[-+]?[[:digit:]]*\\.?[[:digit:]]*$", "123"); |
---|
155 | test_match("^[-+]?[[:digit:]]*\\.?[[:digit:]]*$", "+3.14159"); |
---|
156 | test_match("^[-+]?[[:digit:]]*\\.?[[:digit:]]*$", "-3.14159"); |
---|
157 | |
---|
158 | output_xml_results(true, "Short Matches", "short_matches.xml"); |
---|
159 | } |
---|
160 | std::string twain; |
---|
161 | |
---|
162 | if(test_short_twain) |
---|
163 | { |
---|
164 | load_file(twain, "short_twain.txt"); |
---|
165 | |
---|
166 | test_find_all("Twain", twain); |
---|
167 | test_find_all("Huck[[:alpha:]]+", twain); |
---|
168 | test_find_all("[[:alpha:]]+ing", twain); |
---|
169 | test_find_all("^[^\n]*?Twain", twain); |
---|
170 | test_find_all("Tom|Sawyer|Huckleberry|Finn", twain); |
---|
171 | test_find_all("(Tom|Sawyer|Huckleberry|Finn).{0,30}river|river.{0,30}(Tom|Sawyer|Huckleberry|Finn)", twain); |
---|
172 | |
---|
173 | output_xml_results(false, "Moderate Searches", "short_twain_search.xml"); |
---|
174 | } |
---|
175 | |
---|
176 | if(test_long_twain) |
---|
177 | { |
---|
178 | load_file(twain, "3200.txt"); |
---|
179 | |
---|
180 | test_find_all("Twain", twain); |
---|
181 | test_find_all("Huck[[:alpha:]]+", twain); |
---|
182 | test_find_all("[[:alpha:]]+ing", twain); |
---|
183 | test_find_all("^[^\n]*?Twain", twain); |
---|
184 | test_find_all("Tom|Sawyer|Huckleberry|Finn", twain); |
---|
185 | //time_posix = false; |
---|
186 | test_find_all("(Tom|Sawyer|Huckleberry|Finn).{0,30}river|river.{0,30}(Tom|Sawyer|Huckleberry|Finn)", twain); |
---|
187 | //time_posix = true; |
---|
188 | |
---|
189 | output_xml_results(false, "Long Searches", "long_twain_search.xml"); |
---|
190 | } |
---|
191 | |
---|
192 | return 0; |
---|
193 | } |
---|