Qiuhan Ding | 699725d | 2015-05-24 01:41:09 -0700 | [diff] [blame^] | 1 | /* -*- Mode:C++; c-file-style:"gnu"; indent-tabs-mode:nil; -*- */ |
| 2 | /** |
| 3 | * Copyright (c) 2013-2015 Regents of the University of California. |
| 4 | * |
| 5 | * This file is part of ndn-cxx library (NDN C++ library with eXperimental eXtensions). |
| 6 | * |
| 7 | * ndn-cxx library is free software: you can redistribute it and/or modify it under the |
| 8 | * terms of the GNU Lesser General Public License as published by the Free Software |
| 9 | * Foundation, either version 3 of the License, or (at your option) any later version. |
| 10 | * |
| 11 | * ndn-cxx library is distributed in the hope that it will be useful, but WITHOUT ANY |
| 12 | * WARRANTY; without even the implied warranty of MERCHANTABILITY or FITNESS FOR A |
| 13 | * PARTICULAR PURPOSE. See the GNU Lesser General Public License for more details. |
| 14 | * |
| 15 | * You should have received copies of the GNU General Public License and GNU Lesser |
| 16 | * General Public License along with ndn-cxx, e.g., in COPYING.md file. If not, see |
| 17 | * <http://www.gnu.org/licenses/>. |
| 18 | * |
| 19 | * See AUTHORS.md for complete list of ndn-cxx authors and contributors. |
| 20 | */ |
| 21 | |
| 22 | #include "regex-pattern-list-matcher.hpp" |
| 23 | |
| 24 | #include "regex-repeat-matcher.hpp" |
| 25 | #include "regex-backref-matcher.hpp" |
| 26 | |
| 27 | namespace ndn { |
| 28 | |
| 29 | RegexPatternListMatcher::RegexPatternListMatcher(const std::string& expr, |
| 30 | shared_ptr<RegexBackrefManager> backrefManager) |
| 31 | : RegexMatcher(expr, EXPR_PATTERN_LIST, backrefManager) |
| 32 | { |
| 33 | compile(); |
| 34 | } |
| 35 | |
| 36 | RegexPatternListMatcher::~RegexPatternListMatcher() |
| 37 | { |
| 38 | } |
| 39 | |
| 40 | void |
| 41 | RegexPatternListMatcher::compile() |
| 42 | { |
| 43 | size_t len = m_expr.size(); |
| 44 | size_t index = 0; |
| 45 | size_t subHead = index; |
| 46 | |
| 47 | while (index < len) { |
| 48 | subHead = index; |
| 49 | |
| 50 | if (!extractPattern(subHead, &index)) |
| 51 | throw Error("Compile error"); |
| 52 | } |
| 53 | } |
| 54 | |
| 55 | bool |
| 56 | RegexPatternListMatcher::extractPattern(size_t index, size_t* next) |
| 57 | { |
| 58 | size_t start = index; |
| 59 | size_t end = index; |
| 60 | size_t indicator = index; |
| 61 | |
| 62 | switch (m_expr[index]) { |
| 63 | case '(': |
| 64 | index++; |
| 65 | index = extractSubPattern('(', ')', index); |
| 66 | indicator = index; |
| 67 | end = extractRepetition(index); |
| 68 | if (indicator == end) { |
| 69 | auto matcher = make_shared<RegexBackrefMatcher>(m_expr.substr(start, end - start), |
| 70 | m_backrefManager); |
| 71 | m_backrefManager->pushRef(matcher); |
| 72 | dynamic_pointer_cast<RegexBackrefMatcher>(matcher)->lateCompile(); |
| 73 | |
| 74 | m_matchers.push_back(matcher); |
| 75 | } |
| 76 | else |
| 77 | m_matchers.push_back(make_shared<RegexRepeatMatcher>(m_expr.substr(start, end - start), |
| 78 | m_backrefManager, indicator - start)); |
| 79 | break; |
| 80 | |
| 81 | case '<': |
| 82 | index++; |
| 83 | index = extractSubPattern('<', '>', index); |
| 84 | indicator = index; |
| 85 | end = extractRepetition(index); |
| 86 | m_matchers.push_back(make_shared<RegexRepeatMatcher>(m_expr.substr(start, end - start), |
| 87 | m_backrefManager, indicator - start)); |
| 88 | break; |
| 89 | |
| 90 | case '[': |
| 91 | index++; |
| 92 | index = extractSubPattern('[', ']', index); |
| 93 | indicator = index; |
| 94 | end = extractRepetition(index); |
| 95 | m_matchers.push_back(make_shared<RegexRepeatMatcher>(m_expr.substr(start, end - start), |
| 96 | m_backrefManager, indicator - start)); |
| 97 | break; |
| 98 | |
| 99 | default: |
| 100 | throw Error("Unexpected syntax"); |
| 101 | } |
| 102 | |
| 103 | *next = end; |
| 104 | |
| 105 | return true; |
| 106 | } |
| 107 | |
| 108 | int |
| 109 | RegexPatternListMatcher::extractSubPattern(const char left, const char right, size_t index) |
| 110 | { |
| 111 | size_t lcount = 1; |
| 112 | size_t rcount = 0; |
| 113 | |
| 114 | while (lcount > rcount) { |
| 115 | |
| 116 | if (index >= m_expr.size()) |
| 117 | throw Error("Parenthesis mismatch"); |
| 118 | |
| 119 | if (left == m_expr[index]) |
| 120 | lcount++; |
| 121 | |
| 122 | if (right == m_expr[index]) |
| 123 | rcount++; |
| 124 | |
| 125 | index++; |
| 126 | } |
| 127 | return index; |
| 128 | } |
| 129 | |
| 130 | int |
| 131 | RegexPatternListMatcher::extractRepetition(size_t index) |
| 132 | { |
| 133 | size_t exprSize = m_expr.size(); |
| 134 | |
| 135 | if (index == exprSize) |
| 136 | return index; |
| 137 | |
| 138 | if (('+' == m_expr[index] || '?' == m_expr[index] || '*' == m_expr[index])) { |
| 139 | return ++index; |
| 140 | } |
| 141 | |
| 142 | if ('{' == m_expr[index]) { |
| 143 | while ('}' != m_expr[index]) { |
| 144 | index++; |
| 145 | if (index == exprSize) |
| 146 | break; |
| 147 | } |
| 148 | if (index == exprSize) |
| 149 | throw Error("Missing right brace bracket"); |
| 150 | else |
| 151 | return ++index; |
| 152 | } |
| 153 | else { |
| 154 | return index; |
| 155 | } |
| 156 | } |
| 157 | |
| 158 | } // namespace ndn |
| 159 | |