Annotation of libwww/Library/src/SGML.html, revision 2.6
2.4 timbl 1: <HTML>
2: <HEAD>
3: <TITLE>SGML parse and stream definition for libwww</TITLE></HEAD>
2.1 timbl 4: <BODY>
5: <H1>SGML and Structured streams</H1>The SGML parser is a state machine.
6: It is called for every character<P>
7: of the input stream. The DTD data
8: structure contains pointers<P>
9: to functions which are called to
10: implement the actual effect of the<P>
11: text read. When these functions are
12: called, the attribute structures
13: pointed to by the DTD are valid,
14: and the function is passed a pointer
15: to the curent tag structure, and
16: an "element stack" which represents
17: the state of nesting within SGML
18: elements.<P>
19: The following aspects are from Dan
20: Connolly's suggestions: Binary search,
21: Strcutured object scheme basically,
22: SGML content enum type.<P>
23: (c) Copyright CERN 1991 - See Copyright.html
24: <PRE>#ifndef SGML_H
25: #define SGML_H
26:
27: #include "HTUtils.h"
28: #include "HTStream.h"
29:
30: </PRE>
31: <H2>SGML content types</H2>
32: <PRE>typedef enum _SGMLContent{
33: SGML_EMPTY, /* no content */
34: SGML_LITTERAL, /* character data. Recognised excat close tag only. litteral
35: Old www server compatibility only! Not SGML */
36: SGML_CDATA, /* character data. recognize </ only */
37: SGML_RCDATA, /* replaceable character data. recognize </ and &ref; */
38: SGML_MIXED, /* elements and parsed character data. recognize all markup */
39: SGML_ELEMENT /* any data found will be returned as an error*/
40: } SGMLContent;
41:
42:
43: typedef struct {
44: char * name; /* The (constant) name of the attribute */
45: /* Could put type info in here */
46: } attr;
47:
48:
49: /* A tag structure describes an SGML element.
50: ** -----------------------------------------
51: **
52: **
53: ** name is the string which comes after the tag opener "<".
54: **
55: ** attributes points to a zero-terminated array
56: ** of attribute names.
57: **
58: ** litteral determines how the SGML engine parses the charaters
59: ** within the element. If set, tag openers are ignored
60: ** except for that which opens a matching closing tag.
61: **
62: */
63: typedef struct _tag HTTag;
64: struct _tag{
65: char * name; /* The name of the tag */
66: attr * attributes; /* The list of acceptable attributes */
67: int number_of_attributes; /* Number of possible attributes */
68: SGMLContent contents; /* End only on end tag @@ */
69: };
70:
71:
72:
73:
74: /* DTD Information
75: ** ---------------
76: **
77: ** Not the whole DTD, but all this parser usues of it.
78: */
79: typedef struct {
2.2 timbl 80: HTTag * tags; /* Must be in strcmp order by name */
81: int number_of_tags;
82: CONST char ** entity_names; /* Must be in strcmp order by name */
83: int number_of_entities;
2.1 timbl 84: } SGML_dtd;
85:
86:
87: /* SGML context passed to parsers
88: */
89: typedef struct _HTSGMLContext *HTSGMLContext; /* Hidden */
90:
91:
92: /*__________________________________________________________________________
93: */
94:
2.6 ! timbl 95: </PRE>
! 96: <H2>Structured Object definition</H2>A structured object is something
! 97: which can reasonably be represented
! 98: in SGML. I'll rephrase that. A
! 99: structured object is am ordered tree-structured
! 100: arrangement of data which is representable
! 101: as text.The SGML parer outputs to
! 102: a Structured object. A Structured
! 103: object can output its contents to
! 104: another Structured Object. It's a
! 105: kind of typed stream. The architecure
! 106: is largely Dan Conolly's. Elements
! 107: and entities are passed to the sob
! 108: by number, implying a knowledge of
! 109: the DTD. Knowledge of the SGML syntax
! 110: is not here, though.<P>
! 111: Superclass: HTStream<P>
! 112: The creation methods will vary on
! 113: the type of Structured Object.Maybe
! 114: the callerData is enough info to
! 115: pass along.
! 116: <PRE>typedef struct _HTStructured HTStructured;
2.1 timbl 117:
118: typedef struct _HTStructuredClass{
119:
120: char* name; /* Just for diagnostics */
121:
122: void (*free) PARAMS((
123: HTStructured* me));
124:
2.4 timbl 125: void (*abort) PARAMS((
2.5 timbl 126: HTStructured* me,
127: HTError e));
2.1 timbl 128:
129: void (*put_character) PARAMS((
130: HTStructured* me,
131: char ch));
132:
133: void (*put_string) PARAMS((
134: HTStructured* me,
135: CONST char * str));
136:
137: void (*write) PARAMS((
2.2 timbl 138: HTStructured* me,
2.1 timbl 139: CONST char * str,
140: int len));
141:
142: void (*start_element) PARAMS((
143: HTStructured* me,
144: int element_number,
2.2 timbl 145: CONST BOOL* attribute_present,
146: CONST char** attribute_value));
2.1 timbl 147:
148: void (*end_element) PARAMS((
149: HTStructured* me,
150: int element_number));
151:
152: void (*put_entity) PARAMS((
153: HTStructured* me,
154: int entity_number));
155:
156: }HTStructuredClass;
157:
2.6 ! timbl 158: </PRE>
! 159: <H2>Find a Tag by Name</H2>Returns a pointer to the tag within
! 160: the DTD.
! 161: <PRE>extern HTTag * SGMLFindTag PARAMS((CONST SGML_dtd* dtd, char * string));
2.1 timbl 162:
163:
2.6 ! timbl 164: </PRE>
! 165: <H2>Create an SGML parser</H2>
! 166: <PRE>/*
2.1 timbl 167: ** On entry,
168: ** dtd must point to a DTD structure as defined above
169: ** callbacks must point to user routines.
170: ** callData is returned in callbacks transparently.
171: ** On exit,
172: ** The default tag starter has been processed.
173: */
174:
175:
176: extern HTStream* SGML_new PARAMS((
177: CONST SGML_dtd * dtd,
178: HTStructured * target));
179:
2.2 timbl 180: extern CONST HTStreamClass SGMLParser;
2.1 timbl 181:
182:
183: #endif /* SGML_H */
184:
2.3 timbl 185:
186:
2.4 timbl 187:
2.6 ! timbl 188:
! 189:
! 190:
! 191:
! 192: </A></PRE></BODY>
2.4 timbl 193: </HTML>
Webmaster