Jarkko Poyry | 3c82736 | 2014-09-02 11:48:52 +0300 | [diff] [blame] | 1 | #ifndef _XEXMLPARSER_HPP |
| 2 | #define _XEXMLPARSER_HPP |
| 3 | /*------------------------------------------------------------------------- |
| 4 | * drawElements Quality Program Test Executor |
| 5 | * ------------------------------------------ |
| 6 | * |
| 7 | * Copyright 2014 The Android Open Source Project |
| 8 | * |
| 9 | * Licensed under the Apache License, Version 2.0 (the "License"); |
| 10 | * you may not use this file except in compliance with the License. |
| 11 | * You may obtain a copy of the License at |
| 12 | * |
| 13 | * http://www.apache.org/licenses/LICENSE-2.0 |
| 14 | * |
| 15 | * Unless required by applicable law or agreed to in writing, software |
| 16 | * distributed under the License is distributed on an "AS IS" BASIS, |
| 17 | * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. |
| 18 | * See the License for the specific language governing permissions and |
| 19 | * limitations under the License. |
| 20 | * |
| 21 | *//*! |
| 22 | * \file |
| 23 | * \brief XML Parser. |
| 24 | * |
| 25 | * \todo [2012-06-07 pyry] Not supported / handled properly: |
| 26 | * - xml namespaces (<ns:Element>) |
| 27 | * - backslash escapes in strings |
| 28 | * - " -style escapes |
| 29 | * - utf-8 |
| 30 | *//*--------------------------------------------------------------------*/ |
| 31 | |
| 32 | #include "xeDefs.hpp" |
| 33 | #include "deRingBuffer.hpp" |
| 34 | |
| 35 | #include <string> |
| 36 | #include <map> |
| 37 | |
| 38 | namespace xe |
| 39 | { |
| 40 | namespace xml |
| 41 | { |
| 42 | |
| 43 | enum Token |
| 44 | { |
| 45 | TOKEN_INCOMPLETE = 0, //!< Not enough data to determine token. |
| 46 | TOKEN_END_OF_STRING, //!< End of document string. |
| 47 | TOKEN_DATA, //!< Block of data (anything outside tags). |
| 48 | TOKEN_COMMENT, //!< <!-- comment --> |
| 49 | TOKEN_IDENTIFIER, //!< Identifier (in tags). |
| 50 | TOKEN_STRING, //!< String (in tags). |
| 51 | TOKEN_TAG_START, //!< < |
| 52 | TOKEN_TAG_END, //!< > |
| 53 | TOKEN_END_TAG_START, //!< </ |
| 54 | TOKEN_EMPTY_ELEMENT_END, //!< /> |
| 55 | TOKEN_PROCESSING_INSTRUCTION_START, //!< <? |
| 56 | TOKEN_PROCESSING_INSTRUCTION_END, //!< ?> |
| 57 | TOKEN_EQUAL, //!< = |
| 58 | TOKEN_ENTITY, //!< Entity reference, such as & |
| 59 | |
| 60 | TOKEN_LAST |
| 61 | }; |
| 62 | |
| 63 | enum Element |
| 64 | { |
| 65 | ELEMENT_INCOMPLETE = 0, //!< Incomplete element. |
| 66 | ELEMENT_START, //!< Element start. |
| 67 | ELEMENT_END, //!< Element end. |
| 68 | ELEMENT_DATA, //!< Data element. |
| 69 | ELEMENT_END_OF_STRING, //!< End of document string. |
| 70 | |
| 71 | ELEMENT_LAST |
| 72 | }; |
| 73 | |
| 74 | const char* getTokenName (Token token); |
| 75 | |
| 76 | // \todo [2012-10-17 pyry] Add line number etc. |
| 77 | class ParseError : public xe::ParseError |
| 78 | { |
| 79 | public: |
| 80 | ParseError (const std::string& message) : xe::ParseError(message) {} |
| 81 | }; |
| 82 | |
| 83 | class Tokenizer |
| 84 | { |
| 85 | public: |
| 86 | Tokenizer (void); |
| 87 | ~Tokenizer (void); |
| 88 | |
| 89 | void clear (void); //!< Resets tokenizer to initial state. |
| 90 | |
| 91 | void feed (const deUint8* bytes, int numBytes); |
| 92 | void advance (void); |
| 93 | |
| 94 | Token getToken (void) const { return m_curToken; } |
| 95 | int getTokenLen (void) const { return m_curTokenLen; } |
| 96 | deUint8 getTokenByte (int offset) const { DE_ASSERT(m_curToken != TOKEN_INCOMPLETE && m_curToken != TOKEN_END_OF_STRING); return m_buf.peekBack(offset); } |
| 97 | void getTokenStr (std::string& dst) const; |
| 98 | void appendTokenStr (std::string& dst) const; |
| 99 | |
| 100 | void getString (std::string& dst) const; |
| 101 | |
| 102 | private: |
| 103 | Tokenizer (const Tokenizer& other); |
| 104 | Tokenizer& operator= (const Tokenizer& other); |
| 105 | |
| 106 | int getChar (int offset) const; |
| 107 | |
| 108 | void error (const std::string& what); |
| 109 | |
| 110 | enum State |
| 111 | { |
| 112 | STATE_DATA = 0, |
| 113 | STATE_TAG, |
| 114 | STATE_IDENTIFIER, |
| 115 | STATE_VALUE, |
| 116 | STATE_COMMENT, |
| 117 | STATE_ENTITY, |
| 118 | |
| 119 | STATE_LAST |
| 120 | }; |
| 121 | |
| 122 | enum |
| 123 | { |
| 124 | END_OF_STRING = 0, //!< End of string (0). |
| 125 | END_OF_BUFFER = 0xffffffff //!< End of current data buffer. |
| 126 | }; |
| 127 | |
| 128 | Token m_curToken; //!< Current token. |
| 129 | int m_curTokenLen; //!< Length of current token. |
| 130 | |
| 131 | State m_state; //!< Tokenization state. |
| 132 | |
| 133 | de::RingBuffer<deUint8> m_buf; |
| 134 | }; |
| 135 | |
| 136 | class Parser |
| 137 | { |
| 138 | public: |
| 139 | typedef std::map<std::string, std::string> AttributeMap; |
| 140 | typedef AttributeMap::const_iterator AttributeIter; |
| 141 | |
| 142 | Parser (void); |
| 143 | ~Parser (void); |
| 144 | |
| 145 | void clear (void); //!< Resets parser to initial state. |
| 146 | |
| 147 | void feed (const deUint8* bytes, int numBytes); |
| 148 | void advance (void); |
| 149 | |
| 150 | Element getElement (void) const { return m_element; } |
| 151 | |
| 152 | // For ELEMENT_START / ELEMENT_END. |
| 153 | const char* getElementName (void) const { return m_elementName.c_str(); } |
| 154 | |
| 155 | // For ELEMENT_START. |
| 156 | bool hasAttribute (const char* name) const { return m_attributes.find(name) != m_attributes.end(); } |
| 157 | const char* getAttribute (const char* name) const { return m_attributes.find(name)->second.c_str(); } |
| 158 | const AttributeMap& attributes (void) const { return m_attributes; } |
| 159 | |
| 160 | // For ELEMENT_DATA. |
| 161 | int getDataSize (void) const; |
| 162 | deUint8 getDataByte (int offset) const; |
| 163 | void getDataStr (std::string& dst) const; |
| 164 | void appendDataStr (std::string& dst) const; |
| 165 | |
| 166 | private: |
| 167 | Parser (const Parser& other); |
| 168 | Parser& operator= (const Parser& other); |
| 169 | |
| 170 | void parseEntityValue (void); |
| 171 | |
| 172 | void error (const std::string& what); |
| 173 | |
| 174 | enum State |
| 175 | { |
| 176 | STATE_DATA = 0, //!< Initial state - assuming data or tag open. |
| 177 | STATE_ENTITY, //!< Parsed entity is stored - overrides data. |
| 178 | STATE_IN_PROCESSING_INSTRUCTION, //!< In processing instruction. |
| 179 | STATE_START_TAG_OPEN, //!< Start tag open. |
| 180 | STATE_END_TAG_OPEN, //!< End tag open. |
| 181 | STATE_EXPECTING_END_TAG_CLOSE, //!< Expecting end tag close. |
| 182 | STATE_ATTRIBUTE_LIST, //!< Expecting attribute list. |
| 183 | STATE_EXPECTING_ATTRIBUTE_EQ, //!< Got attribute name, expecting =. |
| 184 | STATE_EXPECTING_ATTRIBUTE_VALUE, //!< Expecting attribute value. |
| 185 | STATE_YIELD_EMPTY_ELEMENT_END, //!< Empty element: start has been reported but not end. |
| 186 | |
| 187 | STATE_LAST |
| 188 | }; |
| 189 | |
| 190 | Tokenizer m_tokenizer; |
| 191 | |
| 192 | Element m_element; |
| 193 | std::string m_elementName; |
| 194 | AttributeMap m_attributes; |
| 195 | |
| 196 | State m_state; |
| 197 | std::string m_attribName; |
| 198 | std::string m_entityValue; //!< Data override, such as entity value. |
| 199 | }; |
| 200 | |
| 201 | // Inline implementations |
| 202 | |
| 203 | inline void Tokenizer::getTokenStr (std::string& dst) const |
| 204 | { |
| 205 | DE_ASSERT(m_curToken != TOKEN_INCOMPLETE && m_curToken != TOKEN_END_OF_STRING); |
| 206 | dst.resize(m_curTokenLen); |
| 207 | for (int ndx = 0; ndx < m_curTokenLen; ndx++) |
| 208 | dst[ndx] = m_buf.peekBack(ndx); |
| 209 | } |
| 210 | |
| 211 | inline void Tokenizer::appendTokenStr (std::string& dst) const |
| 212 | { |
| 213 | DE_ASSERT(m_curToken != TOKEN_INCOMPLETE && m_curToken != TOKEN_END_OF_STRING); |
| 214 | |
| 215 | size_t oldLen = dst.size(); |
| 216 | dst.resize(oldLen+m_curTokenLen); |
| 217 | |
| 218 | for (int ndx = 0; ndx < m_curTokenLen; ndx++) |
| 219 | dst[oldLen+ndx] = m_buf.peekBack(ndx); |
| 220 | } |
| 221 | |
| 222 | inline int Parser::getDataSize (void) const |
| 223 | { |
| 224 | if (m_state != STATE_ENTITY) |
| 225 | return m_tokenizer.getTokenLen(); |
| 226 | else |
| 227 | return (int)m_entityValue.size(); |
| 228 | } |
| 229 | |
| 230 | inline deUint8 Parser::getDataByte (int offset) const |
| 231 | { |
| 232 | if (m_state != STATE_ENTITY) |
| 233 | return m_tokenizer.getTokenByte(offset); |
| 234 | else |
| 235 | return (deUint8)m_entityValue[offset]; |
| 236 | } |
| 237 | |
| 238 | inline void Parser::getDataStr (std::string& dst) const |
| 239 | { |
| 240 | if (m_state != STATE_ENTITY) |
| 241 | return m_tokenizer.getTokenStr(dst); |
| 242 | else |
| 243 | dst = m_entityValue; |
| 244 | } |
| 245 | |
| 246 | inline void Parser::appendDataStr (std::string& dst) const |
| 247 | { |
| 248 | if (m_state != STATE_ENTITY) |
| 249 | return m_tokenizer.appendTokenStr(dst); |
| 250 | else |
| 251 | dst += m_entityValue; |
| 252 | } |
| 253 | |
| 254 | } // xml |
| 255 | } // xe |
| 256 | |
| 257 | #endif // _XEXMLPARSER_HPP |