| 1 | //===----------------------------------------------------------------------===// |
| 2 | // |
| 3 | // Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions. |
| 4 | // See https://llvm.org/LICENSE.txt for license information. |
| 5 | // SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception |
| 6 | // |
| 7 | //===----------------------------------------------------------------------===// |
| 8 | |
| 9 | // <regex> |
| 10 | |
| 11 | // class regex_iterator<BidirectionalIterator, charT, traits> |
| 12 | |
| 13 | // regex_iterator operator++(int); |
| 14 | |
| 15 | #include <regex> |
| 16 | #include <cassert> |
| 17 | #include <iterator> |
| 18 | #include "test_macros.h" |
| 19 | |
| 20 | void validate_prefixes(const std::regex& empty_matching_pattern) { |
| 21 | const char source[] = "abc" ; |
| 22 | |
| 23 | std::cregex_iterator i(source, source + 3, empty_matching_pattern); |
| 24 | assert(!i->prefix().matched); |
| 25 | assert(i->prefix().length() == 0); |
| 26 | assert(i->prefix().first == source); |
| 27 | assert(i->prefix().second == source); |
| 28 | |
| 29 | ++i; |
| 30 | assert(i->prefix().matched); |
| 31 | assert(i->prefix().length() == 1); |
| 32 | assert(i->prefix().first == source); |
| 33 | assert(i->prefix().second == source + 1); |
| 34 | assert(i->prefix().str() == "a" ); |
| 35 | |
| 36 | ++i; |
| 37 | assert(i->prefix().matched); |
| 38 | assert(i->prefix().length() == 1); |
| 39 | assert(i->prefix().first == source + 1); |
| 40 | assert(i->prefix().second == source + 2); |
| 41 | assert(i->prefix().str() == "b" ); |
| 42 | |
| 43 | ++i; |
| 44 | assert(i->prefix().matched); |
| 45 | assert(i->prefix().length() == 1); |
| 46 | assert(i->prefix().first == source + 2); |
| 47 | assert(i->prefix().second == source + 3); |
| 48 | assert(i->prefix().str() == "c" ); |
| 49 | |
| 50 | ++i; |
| 51 | assert(i == std::cregex_iterator()); |
| 52 | } |
| 53 | |
| 54 | void test_prefix_adjustment() { |
| 55 | // Check that we correctly adjust the match prefix when dealing with zero-length matches -- this is explicitly |
| 56 | // required by the Standard ([re.regiter.incr]: "In all cases in which the call to `regex_search` returns true, |
| 57 | // `match.prefix().first` shall be equal to the previous value of `match[0].second`"). For a pattern that matches |
| 58 | // empty sequences, there is an implicit zero-length match between every character in a string -- make sure the |
| 59 | // prefix of each of these matches (except the first one) is the preceding character. |
| 60 | |
| 61 | // An empty pattern produces zero-length matches. |
| 62 | validate_prefixes(empty_matching_pattern: std::regex("" )); |
| 63 | // Any character repeated zero or more times can produce zero-length matches. |
| 64 | validate_prefixes(empty_matching_pattern: std::regex("X*" )); |
| 65 | validate_prefixes(empty_matching_pattern: std::regex("X{0,3}" )); |
| 66 | } |
| 67 | |
| 68 | int main(int, char**) { |
| 69 | { |
| 70 | std::regex phone_numbers("\\d{3}-\\d{4}" ); |
| 71 | const char phone_book[] = "555-1234, 555-2345, 555-3456" ; |
| 72 | std::cregex_iterator i(std::begin(arr: phone_book), std::end(arr: phone_book), phone_numbers); |
| 73 | std::cregex_iterator i2 = i; |
| 74 | assert(i != std::cregex_iterator()); |
| 75 | assert(i2 != std::cregex_iterator()); |
| 76 | assert((*i).size() == 1); |
| 77 | assert((*i).position() == 0); |
| 78 | assert((*i).str() == "555-1234" ); |
| 79 | assert((*i2).size() == 1); |
| 80 | assert((*i2).position() == 0); |
| 81 | assert((*i2).str() == "555-1234" ); |
| 82 | i++; |
| 83 | assert(i != std::cregex_iterator()); |
| 84 | assert(i2 != std::cregex_iterator()); |
| 85 | assert((*i).size() == 1); |
| 86 | assert((*i).position() == 10); |
| 87 | assert((*i).str() == "555-2345" ); |
| 88 | assert((*i2).size() == 1); |
| 89 | assert((*i2).position() == 0); |
| 90 | assert((*i2).str() == "555-1234" ); |
| 91 | i++; |
| 92 | assert(i != std::cregex_iterator()); |
| 93 | assert(i2 != std::cregex_iterator()); |
| 94 | assert((*i).size() == 1); |
| 95 | assert((*i).position() == 20); |
| 96 | assert((*i).str() == "555-3456" ); |
| 97 | assert((*i2).size() == 1); |
| 98 | assert((*i2).position() == 0); |
| 99 | assert((*i2).str() == "555-1234" ); |
| 100 | i++; |
| 101 | assert(i == std::cregex_iterator()); |
| 102 | assert(i2 != std::cregex_iterator()); |
| 103 | assert((*i2).size() == 1); |
| 104 | assert((*i2).position() == 0); |
| 105 | assert((*i2).str() == "555-1234" ); |
| 106 | } |
| 107 | { |
| 108 | std::regex phone_numbers("\\d{3}-\\d{4}" ); |
| 109 | const char phone_book[] = "555-1234, 555-2345, 555-3456" ; |
| 110 | std::cregex_iterator i(std::begin(arr: phone_book), std::end(arr: phone_book), phone_numbers); |
| 111 | std::cregex_iterator i2 = i; |
| 112 | assert(i != std::cregex_iterator()); |
| 113 | assert(i2 != std::cregex_iterator()); |
| 114 | assert((*i).size() == 1); |
| 115 | assert((*i).position() == 0); |
| 116 | assert((*i).str() == "555-1234" ); |
| 117 | assert((*i2).size() == 1); |
| 118 | assert((*i2).position() == 0); |
| 119 | assert((*i2).str() == "555-1234" ); |
| 120 | ++i; |
| 121 | assert(i != std::cregex_iterator()); |
| 122 | assert(i2 != std::cregex_iterator()); |
| 123 | assert((*i).size() == 1); |
| 124 | assert((*i).position() == 10); |
| 125 | assert((*i).str() == "555-2345" ); |
| 126 | assert((*i2).size() == 1); |
| 127 | assert((*i2).position() == 0); |
| 128 | assert((*i2).str() == "555-1234" ); |
| 129 | ++i; |
| 130 | assert(i != std::cregex_iterator()); |
| 131 | assert(i2 != std::cregex_iterator()); |
| 132 | assert((*i).size() == 1); |
| 133 | assert((*i).position() == 20); |
| 134 | assert((*i).str() == "555-3456" ); |
| 135 | assert((*i2).size() == 1); |
| 136 | assert((*i2).position() == 0); |
| 137 | assert((*i2).str() == "555-1234" ); |
| 138 | ++i; |
| 139 | assert(i == std::cregex_iterator()); |
| 140 | assert(i2 != std::cregex_iterator()); |
| 141 | assert((*i2).size() == 1); |
| 142 | assert((*i2).position() == 0); |
| 143 | assert((*i2).str() == "555-1234" ); |
| 144 | } |
| 145 | { // https://llvm.org/PR33681 |
| 146 | std::regex rex(".*" ); |
| 147 | const char foo[] = "foo" ; |
| 148 | // The -1 is because we don't want the implicit null from the array. |
| 149 | std::cregex_iterator i(std::begin(arr: foo), std::end(arr: foo) - 1, rex); |
| 150 | std::cregex_iterator e; |
| 151 | assert(i != e); |
| 152 | assert((*i).size() == 1); |
| 153 | assert((*i).str() == "foo" ); |
| 154 | |
| 155 | ++i; |
| 156 | assert(i != e); |
| 157 | assert((*i).size() == 1); |
| 158 | assert((*i).str() == "" ); |
| 159 | |
| 160 | ++i; |
| 161 | assert(i == e); |
| 162 | } |
| 163 | |
| 164 | test_prefix_adjustment(); |
| 165 | |
| 166 | return 0; |
| 167 | } |
| 168 | |