1 #ifndef __PEDRODOM_H__
2 #define __PEDRODOM_H__
3 /*
4 * API for the Pedro mini-DOM parser and tree
5 *
6 * Authors:
7 * Bob Jamison
8 *
9 * Copyright (C) 2005-2008 Bob Jamison
10 *
11 * This library is free software; you can redistribute it and/or
12 * modify it under the terms of the GNU Lesser General Public
13 * License as published by the Free Software Foundation; either
14 * version 2.1 of the License, or (at your option) any later version.
15 *
16 * This library is distributed in the hope that it will be useful,
17 * but WITHOUT ANY WARRANTY; without even the implied warranty of
18 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
19 * Lesser General Public License for more details.
20 *
21 * You should have received a copy of the GNU Lesser General Public
22 * License along with this library; if not, write to the Free Software
23 * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
24 */
26 #include <glib.h>
28 #include <string>
29 #include <vector>
32 namespace Pedro
33 {
35 typedef std::string DOMString;
36 typedef unsigned int XMLCh;
39 class Namespace
40 {
41 public:
42 Namespace()
43 {}
45 Namespace(const DOMString &prefixArg, const DOMString &namespaceURIArg)
46 {
47 prefix = prefixArg;
48 namespaceURI = namespaceURIArg;
49 }
51 Namespace(const Namespace &other)
52 {
53 assign(other);
54 }
56 Namespace &operator=(const Namespace &other)
57 {
58 assign(other);
59 return *this;
60 }
62 virtual ~Namespace()
63 {}
65 virtual DOMString getPrefix()
66 { return prefix; }
68 virtual DOMString getNamespaceURI()
69 { return namespaceURI; }
71 protected:
73 void assign(const Namespace &other)
74 {
75 prefix = other.prefix;
76 namespaceURI = other.namespaceURI;
77 }
79 DOMString prefix;
80 DOMString namespaceURI;
82 };
84 class Attribute
85 {
86 public:
87 Attribute()
88 {}
90 Attribute(const DOMString &nameArg, const DOMString &valueArg)
91 {
92 name = nameArg;
93 value = valueArg;
94 }
96 Attribute(const Attribute &other)
97 {
98 assign(other);
99 }
101 Attribute &operator=(const Attribute &other)
102 {
103 assign(other);
104 return *this;
105 }
107 virtual ~Attribute()
108 {}
110 virtual DOMString getName()
111 { return name; }
113 virtual DOMString getValue()
114 { return value; }
116 protected:
118 void assign(const Attribute &other)
119 {
120 name = other.name;
121 value = other.value;
122 }
124 DOMString name;
125 DOMString value;
127 };
130 //#Define a list of elements. (Children, search results, etc)
131 class Element;
132 typedef std::vector<Element *> ElementList;
136 class Element
137 {
138 friend class Parser;
140 public:
141 Element()
142 {
143 parent = NULL;
144 }
146 Element(const DOMString &nameArg)
147 {
148 parent = NULL;
149 name = nameArg;
150 }
152 Element(const DOMString &nameArg, const DOMString &valueArg)
153 {
154 parent = NULL;
155 name = nameArg;
156 value = valueArg;
157 }
159 Element(const Element &other)
160 {
161 assign(other);
162 }
164 Element &operator=(const Element &other)
165 {
166 assign(other);
167 return *this;
168 }
170 virtual Element *clone();
172 virtual ~Element()
173 {
174 for (unsigned int i=0 ; i<children.size() ; i++)
175 delete children[i];
176 }
178 virtual DOMString getName()
179 { return name; }
181 virtual DOMString getValue()
182 { return value; }
184 Element *getParent()
185 { return parent; }
187 Element *getFirstChild()
188 { return (children.size() == 0) ? NULL : children[0]; }
190 ElementList getChildren()
191 { return children; }
193 ElementList findElements(const DOMString &name);
195 DOMString getAttribute(const DOMString &name);
197 std::vector<Attribute> &getAttributes()
198 { return attributes; }
200 DOMString getTagAttribute(const DOMString &tagName, const DOMString &attrName);
202 DOMString getTagValue(const DOMString &tagName);
204 void addChild(Element *child);
206 void addAttribute(const DOMString &name, const DOMString &value);
208 void addNamespace(const DOMString &prefix, const DOMString &namespaceURI);
210 bool exists(const DOMString &name)
211 { return (findElements(name).size() > 0); }
213 /**
214 * Prettyprint an XML tree to an output stream. Elements are indented
215 * according to element hierarchy.
216 * @param f a stream to receive the output
217 * @param elem the element to output
218 */
219 void writeIndented(FILE *f);
221 /**
222 * Prettyprint an XML tree to standard output. This is the equivalent of
223 * writeIndented(stdout).
224 * @param elem the element to output
225 */
226 void print();
228 protected:
230 void assign(const Element &other)
231 {
232 parent = other.parent;
233 children = other.children;
234 attributes = other.attributes;
235 namespaces = other.namespaces;
236 name = other.name;
237 value = other.value;
238 }
240 void findElementsRecursive(std::vector<Element *>&res, const DOMString &name);
242 void writeIndentedRecursive(FILE *f, int indent);
244 Element *parent;
246 ElementList children;
248 std::vector<Attribute> attributes;
249 std::vector<Namespace> namespaces;
251 DOMString name;
252 DOMString value;
254 };
260 class Parser
261 {
262 public:
263 /**
264 * Constructor
265 */
266 Parser()
267 { init(); }
269 virtual ~Parser()
270 {}
272 /**
273 * Parse XML in a char buffer.
274 * @param buf a character buffer to parse
275 * @param pos position to start parsing
276 * @param len number of chars, from pos, to parse.
277 * @return a pointer to the root of the XML document;
278 */
279 Element *parse(const char *buf,int pos,int len);
281 /**
282 * Parse XML in a char buffer.
283 * @param buf a character buffer to parse
284 * @param pos position to start parsing
285 * @param len number of chars, from pos, to parse.
286 * @return a pointer to the root of the XML document;
287 */
288 Element *parse(const DOMString &buf);
290 /**
291 * Parse a named XML file. The file is loaded like a data file;
292 * the original format is not preserved.
293 * @param fileName the name of the file to read
294 * @return a pointer to the root of the XML document;
295 */
296 Element *parseFile(const DOMString &fileName);
298 /**
299 * Utility method to preprocess a string for XML
300 * output, escaping its entities.
301 * @param str the string to encode
302 */
303 static DOMString encode(const DOMString &str);
305 /**
306 * Removes whitespace from beginning and end of a string
307 */
308 DOMString trim(const DOMString &s);
310 private:
312 void init()
313 {
314 keepGoing = true;
315 currentNode = NULL;
316 parselen = 0;
317 parsebuf = NULL;
318 currentPosition = 0;
319 }
321 void getLineAndColumn(long pos, long *lineNr, long *colNr);
323 void error(char const *fmt, ...) G_GNUC_PRINTF(2,3);
325 int peek(long pos);
327 int match(long pos, const char *text);
329 int skipwhite(long p);
331 int getWord(int p0, DOMString &buf);
333 int getQuoted(int p0, DOMString &buf, int do_i_parse);
335 int parseVersion(int p0);
337 int parseDoctype(int p0);
339 int parseElement(int p0, Element *par,int depth);
341 Element *parse(XMLCh *buf,int pos,int len);
343 bool keepGoing;
344 Element *currentNode;
345 long parselen;
346 XMLCh *parsebuf;
347 DOMString cdatabuf;
348 long currentPosition;
349 int colNr;
351 };
355 }//namespace Pedro
358 #endif /* __PEDRODOM_H__ */
360 //########################################################################
361 //# E N D O F F I L E
362 //########################################################################