Lee Campbell | 220ca84 | 2015-07-30 09:27:11 -0700 | [diff] [blame] | 1 | // Copyright (C) 2015 The Android Open Source Project |
| 2 | // |
| 3 | // Licensed under the Apache License, Version 2.0 (the "License"); |
| 4 | // you may not use this file except in compliance with the License. |
| 5 | // You may obtain a copy of the License at |
| 6 | // |
| 7 | // http://www.apache.org/licenses/LICENSE-2.0 |
| 8 | // |
| 9 | // Unless required by applicable law or agreed to in writing, software |
| 10 | // distributed under the License is distributed on an "AS IS" BASIS, |
| 11 | // WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. |
| 12 | // See the License for the specific language governing permissions and |
| 13 | // limitations under the License. |
| 14 | |
| 15 | #include "tokenizer.h" |
| 16 | |
| 17 | namespace init { |
| 18 | |
| 19 | Tokenizer::Tokenizer(const std::string& data) |
| 20 | : data_(data), eof_(false), pos_(0), tok_start_(0) { |
| 21 | current_.type = TOK_START; |
| 22 | |
| 23 | if (data.size() > 0) { |
| 24 | cur_char_ = data[0]; |
| 25 | } else { |
| 26 | eof_ = true; |
| 27 | cur_char_ = '\0'; |
| 28 | } |
| 29 | } |
| 30 | |
| 31 | Tokenizer::~Tokenizer() {} |
| 32 | |
| 33 | const Tokenizer::Token& Tokenizer::current() { |
| 34 | return current_; |
| 35 | } |
| 36 | |
| 37 | bool Tokenizer::Next() { |
| 38 | while (!eof_) { |
| 39 | AdvWhiteSpace(); |
| 40 | |
| 41 | // Check for comments. |
| 42 | if (cur_char_ == '#') { |
| 43 | AdvChar(); |
| 44 | // Skip rest of line |
| 45 | while (!eof_ && cur_char_ != '\n') { |
| 46 | AdvChar(); |
| 47 | } |
| 48 | } |
| 49 | |
| 50 | if (eof_) { |
| 51 | break; |
| 52 | } |
| 53 | |
| 54 | if (cur_char_ == '\0') { |
| 55 | AdvChar(); |
| 56 | } else if (cur_char_ == '\n') { |
| 57 | current_.type = TOK_NEWLINE; |
| 58 | current_.text.clear(); |
| 59 | AdvChar(); |
| 60 | return true; |
| 61 | } else if (cur_char_ == '\\') { |
| 62 | AdvChar(); // skip backslash |
| 63 | // This is line continuation so |
| 64 | // do not generated TOK_NEWLINE at |
| 65 | // the next \n. |
| 66 | AdvUntil('\n'); |
| 67 | AdvChar(); // skip \n |
| 68 | } else if (cur_char_ == '\"') { |
| 69 | AdvChar(); |
| 70 | StartText(); |
| 71 | // Grab everything until the next quote. |
| 72 | AdvUntil('\"'); |
| 73 | EndText(); |
| 74 | AdvChar(); // skip quote. |
| 75 | return true; |
| 76 | } else { |
| 77 | StartText(); |
| 78 | AdvText(); |
| 79 | EndText(); |
| 80 | return true; |
| 81 | } |
| 82 | } |
| 83 | current_.type = TOK_END; |
| 84 | current_.text.clear(); |
| 85 | return false; |
| 86 | } |
| 87 | |
| 88 | void Tokenizer::AdvChar() { |
| 89 | pos_++; |
| 90 | if (pos_ < data_.size()) { |
| 91 | cur_char_ = data_[pos_]; |
| 92 | } else { |
| 93 | eof_ = true; |
| 94 | cur_char_ = '\0'; |
| 95 | } |
| 96 | } |
| 97 | |
| 98 | void Tokenizer::AdvWhiteSpace() { |
| 99 | while (cur_char_ == '\t' || cur_char_ == '\r' || cur_char_ == ' ') { |
| 100 | AdvChar(); |
| 101 | } |
| 102 | } |
| 103 | |
| 104 | void Tokenizer::AdvUntil(char x) { |
| 105 | while (!eof_ && cur_char_ != x) { |
| 106 | AdvChar(); |
| 107 | } |
| 108 | } |
| 109 | |
| 110 | void Tokenizer::AdvText() { |
| 111 | while (cur_char_ != '\t' && cur_char_ != '\r' && cur_char_ != '\0' && |
| 112 | cur_char_ != ' ' && cur_char_ != '\n' && cur_char_ != '#') { |
| 113 | AdvChar(); |
| 114 | } |
| 115 | } |
| 116 | |
| 117 | void Tokenizer::StartText() { |
| 118 | current_.text.clear(); |
| 119 | tok_start_ = pos_; |
| 120 | current_.type = TOK_TEXT; |
| 121 | } |
| 122 | |
| 123 | void Tokenizer::EndText() { |
| 124 | if (pos_ != tok_start_) { |
| 125 | current_.text.append(data_, tok_start_, pos_ - tok_start_); |
| 126 | } |
| 127 | } |
| 128 | |
| 129 | } // namespace init |