1 /* Copyright (c) 2013-2014 Yoran Heling 2 3 Permission is hereby granted, free of charge, to any person obtaining 4 a copy of this software and associated documentation files (the 5 "Software"), to deal in the Software without restriction, including 6 without limitation the rights to use, copy, modify, merge, publish, 7 distribute, sublicense, and/or sell copies of the Software, and to 8 permit persons to whom the Software is furnished to do so, subject to 9 the following conditions: 10 11 The above copyright notice and this permission notice shall be included 12 in all copies or substantial portions of the Software. 13 14 THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, 15 EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF 16 MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. 17 IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY 18 CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, 19 TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE 20 SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE. 21 */ 22 23 #ifndef YXML_H 24 #define YXML_H 25 26 #include <stdint.h> 27 #include <stddef.h> 28 29 #if defined(_MSC_VER) && !defined(__cplusplus) && !defined(inline) 30 #define inline __inline 31 #endif 32 33 /* Full API documentation for this library can be found in the "yxml.pod" file 34 * in the yxml git repository, or online at http://dev.yorhel.nl/yxml/man */ 35 36 typedef enum { 37 YXML_EEOF = -5, /* Unexpected EOF */ 38 YXML_EREF = -4, /* Invalid character or entity reference (&whatever;) */ 39 YXML_ECLOSE = -3, /* Close tag does not match open tag (<Tag> .. </OtherTag>) */ 40 YXML_ESTACK = -2, /* Stack overflow (too deeply nested tags or too long element/attribute name) */ 41 YXML_ESYN = -1, /* Syntax error (unexpected byte) */ 42 YXML_OK = 0, /* Character consumed, no new token present */ 43 YXML_ELEMSTART = 1, /* Start of an element: '<Tag ..' */ 44 YXML_CONTENT = 2, /* Element content */ 45 YXML_ELEMEND = 3, /* End of an element: '.. />' or '</Tag>' */ 46 YXML_ATTRSTART = 4, /* Attribute: 'Name=..' */ 47 YXML_ATTRVAL = 5, /* Attribute value */ 48 YXML_ATTREND = 6, /* End of attribute '.."' */ 49 YXML_PISTART = 7, /* Start of a processing instruction */ 50 YXML_PICONTENT = 8, /* Content of a PI */ 51 YXML_PIEND = 9 /* End of a processing instruction */ 52 } yxml_ret_t; 53 54 /* When, exactly, are tokens returned? 55 * 56 * <TagName 57 * '>' ELEMSTART 58 * '/' ELEMSTART, '>' ELEMEND 59 * ' ' ELEMSTART 60 * '>' 61 * '/', '>' ELEMEND 62 * Attr 63 * '=' ATTRSTART 64 * "X ATTRVAL 65 * 'Y' ATTRVAL 66 * 'Z' ATTRVAL 67 * '"' ATTREND 68 * '>' 69 * '/', '>' ELEMEND 70 * 71 * </TagName 72 * '>' ELEMEND 73 */ 74 75 76 typedef struct { 77 /* PUBLIC (read-only) */ 78 79 /* Name of the current element, zero-length if not in any element. Changed 80 * after YXML_ELEMSTART. The pointer will remain valid up to and including 81 * the next non-YXML_ATTR* token, the pointed-to buffer will remain valid 82 * up to and including the YXML_ELEMEND for the corresponding element. */ 83 char *elem; 84 85 /* The last read character(s) of an attribute value (YXML_ATTRVAL), element 86 * data (YXML_CONTENT), or processing instruction (YXML_PICONTENT). Changed 87 * after one of the respective YXML_ values is returned, and only valid 88 * until the next yxml_parse() call. Usually, this string only consists of 89 * a single byte, but multiple bytes are returned in the following cases: 90 * - "<?SomePI ?x ?>": The two characters "?x" 91 * - "<![CDATA[ ]x ]]>": The two characters "]x" 92 * - "<![CDATA[ ]]x ]]>": The three characters "]]x" 93 * - "&#N;" and "&#xN;", where dec(n) > 127. The referenced Unicode 94 * character is then encoded in multiple UTF-8 bytes. 95 */ 96 char data[8]; 97 98 /* Name of the current attribute. Changed after YXML_ATTRSTART, valid up to 99 * and including the next YXML_ATTREND. */ 100 char *attr; 101 102 /* Name/target of the current processing instruction, zero-length if not in 103 * a PI. Changed after YXML_PISTART, valid up to (but excluding) 104 * the next YXML_PIEND. */ 105 char *pi; 106 107 /* Line number, byte offset within that line, and total bytes read. These 108 * values refer to the position _after_ the last byte given to 109 * yxml_parse(). These are useful for debugging and error reporting. */ 110 uint64_t byte; 111 uint64_t total; 112 uint32_t line; 113 114 115 /* PRIVATE */ 116 int state; 117 unsigned char *stack; /* Stack of element names + attribute/PI name, separated by \0. Also starts with a \0. */ 118 size_t stacksize, stacklen; 119 unsigned reflen; 120 unsigned quote; 121 int nextstate; /* Used for '@' state remembering and for the "string" consuming state */ 122 unsigned ignore; 123 unsigned char *string; 124 } yxml_t; 125 126 127 #ifdef __cplusplus 128 extern "C" { 129 #endif 130 131 void yxml_init(yxml_t *, void *, size_t); 132 133 134 yxml_ret_t yxml_parse(yxml_t *, int); 135 136 137 /* May be called after the last character has been given to yxml_parse(). 138 * Returns YXML_OK if the XML document is valid, YXML_EEOF otherwise. Using 139 * this function isn't really necessary, but can be used to detect documents 140 * that don't end correctly. In particular, an error is returned when the XML 141 * document did not contain a (complete) root element, or when the document 142 * ended while in a comment or processing instruction. */ 143 yxml_ret_t yxml_eof(yxml_t *); 144 145 #ifdef __cplusplus 146 } 147 #endif 148 149 150 /* Returns the length of the element name (x->elem), attribute name (x->attr), 151 * or PI name (x->pi). This function should ONLY be used directly after the 152 * YXML_ELEMSTART, YXML_ATTRSTART or YXML_PISTART (respectively) tokens have 153 * been returned by yxml_parse(), calling this at any other time may not give 154 * the correct results. This function should also NOT be used on strings other 155 * than x->elem, x->attr or x->pi. */ 156 static inline size_t yxml_symlen(yxml_t *x, const char *s) { 157 return (x->stack + x->stacklen) - (const unsigned char*)s; 158 } 159 160 #endif 161 162 /* vim: set noet sw=4 ts=4: */ 163