1 /*
2  * Summary: interface for an HTML 4.0 non-verifying parser
3  * Description: this module implements an HTML 4.0 non-verifying parser
4  *              with API compatible with the XML parser ones. It should
5  *              be able to parse "real world" HTML, even if severely
6  *              broken from a specification point of view.
7  *
8  * Copy: See Copyright for the status of this software.
9  *
10  * Author: Daniel Veillard
11  */
12 
13 #ifndef __HTML_PARSER_H__
14 #define __HTML_PARSER_H__
15 #include <libxml/xmlversion.h>
16 #include <libxml/parser.h>
17 
18 #ifdef LIBXML_HTML_ENABLED
19 
20 #ifdef __cplusplus
21 extern "C" {
22 #endif
23 
24 /*
25  * Most of the back-end structures from XML and HTML are shared.
26  */
27 typedef xmlParserCtxt htmlParserCtxt;
28 typedef xmlParserCtxtPtr htmlParserCtxtPtr;
29 typedef xmlParserNodeInfo htmlParserNodeInfo;
30 typedef xmlSAXHandler htmlSAXHandler;
31 typedef xmlSAXHandlerPtr htmlSAXHandlerPtr;
32 typedef xmlParserInput htmlParserInput;
33 typedef xmlParserInputPtr htmlParserInputPtr;
34 typedef xmlDocPtr htmlDocPtr;
35 typedef xmlNodePtr htmlNodePtr;
36 
37 /*
38  * Internal description of an HTML element, representing HTML 4.01
39  * and XHTML 1.0 (which share the same structure).
40  */
41 typedef struct _htmlElemDesc htmlElemDesc;
42 typedef htmlElemDesc *htmlElemDescPtr;
43 struct _htmlElemDesc {
44     const char *name;	/* The tag name */
45     char startTag;      /* Whether the start tag can be implied */
46     char endTag;        /* Whether the end tag can be implied */
47     char saveEndTag;    /* Whether the end tag should be saved */
48     char empty;         /* Is this an empty element ? */
49     char depr;          /* Is this a deprecated element ? */
50     char dtd;           /* 1: only in Loose DTD, 2: only Frameset one */
51     char isinline;      /* is this a block 0 or inline 1 element */
52     const char *desc;   /* the description */
53 
54 /* NRK Jan.2003
55  * New fields encapsulating HTML structure
56  *
57  * Bugs:
58  *	This is a very limited representation.  It fails to tell us when
59  *	an element *requires* subelements (we only have whether they're
60  *	allowed or not), and it doesn't tell us where CDATA and PCDATA
61  *	are allowed.  Some element relationships are not fully represented:
62  *	these are flagged with the word MODIFIER
63  */
64     const char** subelts;		/* allowed sub-elements of this element */
65     const char* defaultsubelt;	/* subelement for suggested auto-repair
66 					   if necessary or NULL */
67     const char** attrs_opt;		/* Optional Attributes */
68     const char** attrs_depr;		/* Additional deprecated attributes */
69     const char** attrs_req;		/* Required attributes */
70 };
71 
72 /*
73  * Internal description of an HTML entity.
74  */
75 typedef struct _htmlEntityDesc htmlEntityDesc;
76 typedef htmlEntityDesc *htmlEntityDescPtr;
77 struct _htmlEntityDesc {
78     unsigned int value;	/* the UNICODE value for the character */
79     const char *name;	/* The entity name */
80     const char *desc;   /* the description */
81 };
82 
83 /*
84  * There is only few public functions.
85  */
86 XMLPUBFUN const htmlElemDesc * XMLCALL
87 			htmlTagLookup	(const xmlChar *tag);
88 XMLPUBFUN const htmlEntityDesc * XMLCALL
89 			htmlEntityLookup(const xmlChar *name);
90 XMLPUBFUN const htmlEntityDesc * XMLCALL
91 			htmlEntityValueLookup(unsigned int value);
92 
93 XMLPUBFUN int XMLCALL
94 			htmlIsAutoClosed(htmlDocPtr doc,
95 					 htmlNodePtr elem);
96 XMLPUBFUN int XMLCALL
97 			htmlAutoCloseTag(htmlDocPtr doc,
98 					 const xmlChar *name,
99 					 htmlNodePtr elem);
100 XMLPUBFUN const htmlEntityDesc * XMLCALL
101 			htmlParseEntityRef(htmlParserCtxtPtr ctxt,
102 					 const xmlChar **str);
103 XMLPUBFUN int XMLCALL
104 			htmlParseCharRef(htmlParserCtxtPtr ctxt);
105 XMLPUBFUN void XMLCALL
106 			htmlParseElement(htmlParserCtxtPtr ctxt);
107 
108 XMLPUBFUN htmlParserCtxtPtr XMLCALL
109 			htmlNewParserCtxt(void);
110 
111 XMLPUBFUN htmlParserCtxtPtr XMLCALL
112 			htmlCreateMemoryParserCtxt(const char *buffer,
113 						   int size);
114 
115 XMLPUBFUN int XMLCALL
116 			htmlParseDocument(htmlParserCtxtPtr ctxt);
117 XMLPUBFUN htmlDocPtr XMLCALL
118 			htmlSAXParseDoc	(xmlChar *cur,
119 					 const char *encoding,
120 					 htmlSAXHandlerPtr sax,
121 					 void *userData);
122 XMLPUBFUN htmlDocPtr XMLCALL
123 			htmlParseDoc	(xmlChar *cur,
124 					 const char *encoding);
125 XMLPUBFUN htmlDocPtr XMLCALL
126 			htmlSAXParseFile(const char *filename,
127 					 const char *encoding,
128 					 htmlSAXHandlerPtr sax,
129 					 void *userData);
130 XMLPUBFUN htmlDocPtr XMLCALL
131 			htmlParseFile	(const char *filename,
132 					 const char *encoding);
133 XMLPUBFUN int XMLCALL
134 			UTF8ToHtml	(unsigned char *out,
135 					 int *outlen,
136 					 const unsigned char *in,
137 					 int *inlen);
138 XMLPUBFUN int XMLCALL
139 			htmlEncodeEntities(unsigned char *out,
140 					 int *outlen,
141 					 const unsigned char *in,
142 					 int *inlen, int quoteChar);
143 XMLPUBFUN int XMLCALL
144 			htmlIsScriptAttribute(const xmlChar *name);
145 XMLPUBFUN int XMLCALL
146 			htmlHandleOmittedElem(int val);
147 
148 #ifdef LIBXML_PUSH_ENABLED
149 /**
150  * Interfaces for the Push mode.
151  */
152 XMLPUBFUN htmlParserCtxtPtr XMLCALL
153 			htmlCreatePushParserCtxt(htmlSAXHandlerPtr sax,
154 						 void *user_data,
155 						 const char *chunk,
156 						 int size,
157 						 const char *filename,
158 						 xmlCharEncoding enc);
159 XMLPUBFUN int XMLCALL
160 			htmlParseChunk		(htmlParserCtxtPtr ctxt,
161 						 const char *chunk,
162 						 int size,
163 						 int terminate);
164 #endif /* LIBXML_PUSH_ENABLED */
165 
166 XMLPUBFUN void XMLCALL
167 			htmlFreeParserCtxt	(htmlParserCtxtPtr ctxt);
168 
169 /*
170  * New set of simpler/more flexible APIs
171  */
172 /**
173  * xmlParserOption:
174  *
175  * This is the set of XML parser options that can be passed down
176  * to the xmlReadDoc() and similar calls.
177  */
178 typedef enum {
179     HTML_PARSE_RECOVER  = 1<<0, /* Relaxed parsing */
180     HTML_PARSE_NOERROR	= 1<<5,	/* suppress error reports */
181     HTML_PARSE_NOWARNING= 1<<6,	/* suppress warning reports */
182     HTML_PARSE_PEDANTIC	= 1<<7,	/* pedantic error reporting */
183     HTML_PARSE_NOBLANKS	= 1<<8,	/* remove blank nodes */
184     HTML_PARSE_NONET	= 1<<11,/* Forbid network access */
185     HTML_PARSE_COMPACT  = 1<<16 /* compact small text nodes */
186 } htmlParserOption;
187 
188 XMLPUBFUN void XMLCALL
189 		htmlCtxtReset		(htmlParserCtxtPtr ctxt);
190 XMLPUBFUN int XMLCALL
191 		htmlCtxtUseOptions	(htmlParserCtxtPtr ctxt,
192 					 int options);
193 XMLPUBFUN htmlDocPtr XMLCALL
194 		htmlReadDoc		(const xmlChar *cur,
195 					 const char *URL,
196 					 const char *encoding,
197 					 int options);
198 XMLPUBFUN htmlDocPtr XMLCALL
199 		htmlReadFile		(const char *URL,
200 					 const char *encoding,
201 					 int options);
202 XMLPUBFUN htmlDocPtr XMLCALL
203 		htmlReadMemory		(const char *buffer,
204 					 int size,
205 					 const char *URL,
206 					 const char *encoding,
207 					 int options);
208 XMLPUBFUN htmlDocPtr XMLCALL
209 		htmlReadFd		(int fd,
210 					 const char *URL,
211 					 const char *encoding,
212 					 int options);
213 XMLPUBFUN htmlDocPtr XMLCALL
214 		htmlReadIO		(xmlInputReadCallback ioread,
215 					 xmlInputCloseCallback ioclose,
216 					 void *ioctx,
217 					 const char *URL,
218 					 const char *encoding,
219 					 int options);
220 XMLPUBFUN htmlDocPtr XMLCALL
221 		htmlCtxtReadDoc		(xmlParserCtxtPtr ctxt,
222 					 const xmlChar *cur,
223 					 const char *URL,
224 					 const char *encoding,
225 					 int options);
226 XMLPUBFUN htmlDocPtr XMLCALL
227 		htmlCtxtReadFile		(xmlParserCtxtPtr ctxt,
228 					 const char *filename,
229 					 const char *encoding,
230 					 int options);
231 XMLPUBFUN htmlDocPtr XMLCALL
232 		htmlCtxtReadMemory		(xmlParserCtxtPtr ctxt,
233 					 const char *buffer,
234 					 int size,
235 					 const char *URL,
236 					 const char *encoding,
237 					 int options);
238 XMLPUBFUN htmlDocPtr XMLCALL
239 		htmlCtxtReadFd		(xmlParserCtxtPtr ctxt,
240 					 int fd,
241 					 const char *URL,
242 					 const char *encoding,
243 					 int options);
244 XMLPUBFUN htmlDocPtr XMLCALL
245 		htmlCtxtReadIO		(xmlParserCtxtPtr ctxt,
246 					 xmlInputReadCallback ioread,
247 					 xmlInputCloseCallback ioclose,
248 					 void *ioctx,
249 					 const char *URL,
250 					 const char *encoding,
251 					 int options);
252 
253 /* NRK/Jan2003: further knowledge of HTML structure
254  */
255 typedef enum {
256   HTML_NA = 0 ,		/* something we don't check at all */
257   HTML_INVALID = 0x1 ,
258   HTML_DEPRECATED = 0x2 ,
259   HTML_VALID = 0x4 ,
260   HTML_REQUIRED = 0xc /* VALID bit set so ( & HTML_VALID ) is TRUE */
261 } htmlStatus ;
262 
263 /* Using htmlElemDesc rather than name here, to emphasise the fact
264    that otherwise there's a lookup overhead
265 */
266 XMLPUBFUN htmlStatus XMLCALL htmlAttrAllowed(const htmlElemDesc*, const xmlChar*, int) ;
267 XMLPUBFUN int XMLCALL htmlElementAllowedHere(const htmlElemDesc*, const xmlChar*) ;
268 XMLPUBFUN htmlStatus XMLCALL htmlElementStatusHere(const htmlElemDesc*, const htmlElemDesc*) ;
269 XMLPUBFUN htmlStatus XMLCALL htmlNodeStatus(const htmlNodePtr, int) ;
270 /**
271  * htmlDefaultSubelement:
272  * @elt: HTML element
273  *
274  * Returns the default subelement for this element
275  */
276 #define htmlDefaultSubelement(elt) elt->defaultsubelt
277 /**
278  * htmlElementAllowedHereDesc:
279  * @parent: HTML parent element
280  * @elt: HTML element
281  *
282  * Checks whether an HTML element description may be a
283  * direct child of the specified element.
284  *
285  * Returns 1 if allowed; 0 otherwise.
286  */
287 #define htmlElementAllowedHereDesc(parent,elt) \
288 	htmlElementAllowedHere((parent), (elt)->name)
289 /**
290  * htmlRequiredAttrs:
291  * @elt: HTML element
292  *
293  * Returns the attributes required for the specified element.
294  */
295 #define htmlRequiredAttrs(elt) (elt)->attrs_req
296 
297 
298 #ifdef __cplusplus
299 }
300 #endif
301 
302 #endif /* LIBXML_HTML_ENABLED */
303 #endif /* __HTML_PARSER_H__ */
304