| 1 | /* $Id: minixml.c,v 1.12 2017/12/12 11:17:40 nanard Exp $ */ |
| 2 | /* vim: tabstop=4 shiftwidth=4 noexpandtab |
| 3 | * minixml.c : the minimum size a xml parser can be ! */ |
| 4 | /* Project : miniupnp |
| 5 | * webpage: http://miniupnp.free.fr/ or http://miniupnp.tuxfamily.org/ |
| 6 | * Author : Thomas Bernard |
| 7 | |
| 8 | Copyright (c) 2005-2017, Thomas BERNARD |
| 9 | All rights reserved. |
| 10 | |
| 11 | Redistribution and use in source and binary forms, with or without |
| 12 | modification, are permitted provided that the following conditions are met: |
| 13 | |
| 14 | * Redistributions of source code must retain the above copyright notice, |
| 15 | this list of conditions and the following disclaimer. |
| 16 | * Redistributions in binary form must reproduce the above copyright notice, |
| 17 | this list of conditions and the following disclaimer in the documentation |
| 18 | and/or other materials provided with the distribution. |
| 19 | * The name of the author may not be used to endorse or promote products |
| 20 | derived from this software without specific prior written permission. |
| 21 | |
| 22 | THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" |
| 23 | AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE |
| 24 | IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE |
| 25 | ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE |
| 26 | LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR |
| 27 | CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF |
| 28 | SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS |
| 29 | INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN |
| 30 | CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) |
| 31 | ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE |
| 32 | POSSIBILITY OF SUCH DAMAGE. |
| 33 | */ |
| 34 | #include <string.h> |
| 35 | #include "minixml.h" |
| 36 | |
| 37 | /* parseatt : used to parse the argument list |
| 38 | * return 0 (false) in case of success and -1 (true) if the end |
| 39 | * of the xmlbuffer is reached. */ |
| 40 | static int parseatt(struct xmlparser * p) |
| 41 | { |
| 42 | const char * attname; |
| 43 | int attnamelen; |
| 44 | const char * attvalue; |
| 45 | int attvaluelen; |
| 46 | while(p->xml < p->xmlend) |
| 47 | { |
| 48 | if(*p->xml=='/' || *p->xml=='>') |
| 49 | return 0; |
| 50 | if( !IS_WHITE_SPACE(*p->xml) ) |
| 51 | { |
| 52 | char sep; |
| 53 | attname = p->xml; |
| 54 | attnamelen = 0; |
| 55 | while(*p->xml!='=' && !IS_WHITE_SPACE(*p->xml) ) |
| 56 | { |
| 57 | attnamelen++; p->xml++; |
| 58 | if(p->xml >= p->xmlend) |
| 59 | return -1; |
| 60 | } |
| 61 | while(*(p->xml++) != '=') |
| 62 | { |
| 63 | if(p->xml >= p->xmlend) |
| 64 | return -1; |
| 65 | } |
| 66 | while(IS_WHITE_SPACE(*p->xml)) |
| 67 | { |
| 68 | p->xml++; |
| 69 | if(p->xml >= p->xmlend) |
| 70 | return -1; |
| 71 | } |
| 72 | sep = *p->xml; |
| 73 | if(sep=='\'' || sep=='\"') |
| 74 | { |
| 75 | p->xml++; |
| 76 | if(p->xml >= p->xmlend) |
| 77 | return -1; |
| 78 | attvalue = p->xml; |
| 79 | attvaluelen = 0; |
| 80 | while(*p->xml != sep) |
| 81 | { |
| 82 | attvaluelen++; p->xml++; |
| 83 | if(p->xml >= p->xmlend) |
| 84 | return -1; |
| 85 | } |
| 86 | } |
| 87 | else |
| 88 | { |
| 89 | attvalue = p->xml; |
| 90 | attvaluelen = 0; |
| 91 | while( !IS_WHITE_SPACE(*p->xml) |
| 92 | && *p->xml != '>' && *p->xml != '/') |
| 93 | { |
| 94 | attvaluelen++; p->xml++; |
| 95 | if(p->xml >= p->xmlend) |
| 96 | return -1; |
| 97 | } |
| 98 | } |
| 99 | /*printf("%.*s='%.*s'\n", |
| 100 | attnamelen, attname, attvaluelen, attvalue);*/ |
| 101 | if(p->attfunc) |
| 102 | p->attfunc(p->data, attname, attnamelen, attvalue, attvaluelen); |
| 103 | } |
| 104 | p->xml++; |
| 105 | } |
| 106 | return -1; |
| 107 | } |
| 108 | |
| 109 | /* parseelt parse the xml stream and |
| 110 | * call the callback functions when needed... */ |
| 111 | static void parseelt(struct xmlparser * p) |
| 112 | { |
| 113 | int i; |
| 114 | const char * elementname; |
| 115 | while(p->xml < (p->xmlend - 1)) |
| 116 | { |
| 117 | if((p->xml + 4) <= p->xmlend && (0 == memcmp(p->xml, "<!--" , 4))) |
| 118 | { |
| 119 | p->xml += 3; |
| 120 | /* ignore comments */ |
| 121 | do |
| 122 | { |
| 123 | p->xml++; |
| 124 | if ((p->xml + 3) >= p->xmlend) |
| 125 | return; |
| 126 | } |
| 127 | while(memcmp(p->xml, "-->" , 3) != 0); |
| 128 | p->xml += 3; |
| 129 | } |
| 130 | else if((p->xml)[0]=='<' && (p->xml)[1]!='?') |
| 131 | { |
| 132 | i = 0; elementname = ++p->xml; |
| 133 | while( !IS_WHITE_SPACE(*p->xml) |
| 134 | && (*p->xml!='>') && (*p->xml!='/') |
| 135 | ) |
| 136 | { |
| 137 | i++; p->xml++; |
| 138 | if (p->xml >= p->xmlend) |
| 139 | return; |
| 140 | /* to ignore namespace : */ |
| 141 | if(*p->xml==':') |
| 142 | { |
| 143 | i = 0; |
| 144 | elementname = ++p->xml; |
| 145 | } |
| 146 | } |
| 147 | if(i>0) |
| 148 | { |
| 149 | if(p->starteltfunc) |
| 150 | p->starteltfunc(p->data, elementname, i); |
| 151 | if(parseatt(p)) |
| 152 | return; |
| 153 | if(*p->xml!='/') |
| 154 | { |
| 155 | const char * data; |
| 156 | i = 0; data = ++p->xml; |
| 157 | if (p->xml >= p->xmlend) |
| 158 | return; |
| 159 | while( IS_WHITE_SPACE(*p->xml) ) |
| 160 | { |
| 161 | i++; p->xml++; |
| 162 | if (p->xml >= p->xmlend) |
| 163 | return; |
| 164 | } |
| 165 | /* CDATA are at least 9 + 3 characters long : <![CDATA[ ]]> */ |
| 166 | if((p->xmlend >= (p->xml + (9 + 3))) && (memcmp(p->xml, "<![CDATA[" , 9) == 0)) |
| 167 | { |
| 168 | /* CDATA handling */ |
| 169 | p->xml += 9; |
| 170 | data = p->xml; |
| 171 | i = 0; |
| 172 | while(memcmp(p->xml, "]]>" , 3) != 0) |
| 173 | { |
| 174 | i++; p->xml++; |
| 175 | if ((p->xml + 3) >= p->xmlend) |
| 176 | return; |
| 177 | } |
| 178 | if(i>0 && p->datafunc) |
| 179 | p->datafunc(p->data, data, i); |
| 180 | while(*p->xml!='<') |
| 181 | { |
| 182 | p->xml++; |
| 183 | if (p->xml >= p->xmlend) |
| 184 | return; |
| 185 | } |
| 186 | } |
| 187 | else |
| 188 | { |
| 189 | while(*p->xml!='<') |
| 190 | { |
| 191 | i++; p->xml++; |
| 192 | if ((p->xml + 1) >= p->xmlend) |
| 193 | return; |
| 194 | } |
| 195 | if(i>0 && p->datafunc && *(p->xml + 1) == '/') |
| 196 | p->datafunc(p->data, data, i); |
| 197 | } |
| 198 | } |
| 199 | } |
| 200 | else if(*p->xml == '/') |
| 201 | { |
| 202 | i = 0; elementname = ++p->xml; |
| 203 | if (p->xml >= p->xmlend) |
| 204 | return; |
| 205 | while((*p->xml != '>')) |
| 206 | { |
| 207 | i++; p->xml++; |
| 208 | if (p->xml >= p->xmlend) |
| 209 | return; |
| 210 | } |
| 211 | if(p->endeltfunc) |
| 212 | p->endeltfunc(p->data, elementname, i); |
| 213 | p->xml++; |
| 214 | } |
| 215 | } |
| 216 | else |
| 217 | { |
| 218 | p->xml++; |
| 219 | } |
| 220 | } |
| 221 | } |
| 222 | |
| 223 | /* the parser must be initialized before calling this function */ |
| 224 | void parsexml(struct xmlparser * parser) |
| 225 | { |
| 226 | parser->xml = parser->xmlstart; |
| 227 | parser->xmlend = parser->xmlstart + parser->xmlsize; |
| 228 | parseelt(parser); |
| 229 | } |
| 230 | |
| 231 | |
| 232 | |