b6b9d458 |
1 | .\" -*-nroff-*- |
2 | .de VS |
3 | .sp 1 |
d66d7727 |
4 | .RS |
b6b9d458 |
5 | .nf |
6 | .ft B |
7 | .. |
8 | .de VE |
9 | .ft R |
10 | .fi |
11 | .RE |
12 | .sp 1 |
13 | .. |
fbf20b5b |
14 | .TH sym 3 "8 May 1999" "Straylight/Edgeware" "mLib utilities library" |
b6b9d458 |
15 | .SH NAME |
16 | sym \- symbol table manager |
08da152e |
17 | .\" @sym_create |
18 | .\" @sym_destroy |
19 | .\" @sym_find |
20 | .\" @sym_remove |
21 | .\" @sym_mkiter |
22 | .\" @sym_next |
23 | .\" |
24 | .\" @SYM_NAME |
0c404077 |
25 | .\" @SYM_LEN |
26 | .\" @SYM_HASH |
08da152e |
27 | .\" |
b6b9d458 |
28 | .SH SYNOPSIS |
29 | .nf |
30 | .B "#include <mLib/sym.h>" |
31 | |
32 | .BI "void sym_create(sym_table *" t ); |
33 | .BI "void sym_destroy(sym_table *" t ); |
34 | |
b6b9d458 |
35 | .BI "void *sym_find(sym_table *" t , |
36 | .BI " const char *" n ", long " l , |
37 | .BI " size_t " sz ", unsigned *" f ); |
38 | .BI "void sym_remove(sym_table *" t ", void *" b ); |
39 | |
0c404077 |
40 | .BI "const char *SYM_NAME(const void *" p ); |
41 | .BI "size_t SYM_LEN(const void *" p ); |
42 | .BI "uint32 SYM_HASH(const void *" p ); |
43 | |
b6b9d458 |
44 | .BI "void sym_mkiter(sym_iter *" i ", sym_table *" t ); |
45 | .BI "void *sym_next(sym_iter *" i ); |
46 | .fi |
0c404077 |
47 | .SH "DESCRIPTION" |
b6b9d458 |
48 | The |
49 | .B sym |
50 | functions implement a data structure often described as a dictionary, a |
51 | finite map, an associative array, or a symbol table. It associates |
52 | .I values |
53 | with |
54 | .I keys |
55 | such that the value corresponding to a given key can be found quickly. |
56 | Additionally, all stored associations can be enumerated. |
57 | .PP |
58 | The interface provides an |
59 | .I intrusive |
60 | symbol table. The data objects stored in the table must include a small |
61 | header used by the symbol table manager. This reduces the amount of |
62 | pointer fiddling that needs to be done, and in practice doesn't seem to |
63 | be much of a problem. It's also fairly easy to construct a |
64 | non-intrusive interface if you really want one. |
65 | .PP |
66 | There are three main data structures involved in the interface: |
67 | .TP |
68 | .B sym_table |
69 | Keeps track of the information associated with a particular table. |
70 | .TP |
71 | .B sym_base |
72 | The header which must be attached to the front of all the value |
73 | objects. |
74 | .TP |
75 | .B sym_iter |
76 | An iterator object, used for enumerating all of the associations stored |
77 | in a symbol table. |
78 | .PP |
79 | All of the above data structures should be considered |
80 | .IR opaque : |
81 | don't try looking inside. Representations have changed in the past, and |
82 | they may change again in the future. |
0c404077 |
83 | .SS "Creation and destruction" |
b6b9d458 |
84 | The |
85 | .B sym_table |
86 | object itself needs to be allocated by the caller. It is initialized by |
87 | passing it to the function |
88 | .BR sym_create . |
89 | After initialization, the table contains no entries. |
90 | .PP |
91 | Initializing a symbol table involves allocating some memory. If this |
d2a91066 |
92 | allocation fails, an |
b6b9d458 |
93 | .B EXC_NOMEM |
94 | exception is raised. |
95 | .PP |
96 | When a symbol table is no longer needed, the memory occupied by the |
97 | values and other maintenance structures can be reclaimed by calling |
98 | .BR sym_destroy . |
0c404077 |
99 | Any bits of user data attached to values should previously have been |
100 | destroyed. |
101 | .SS "Adding, searching and removing" |
b6b9d458 |
102 | Most of the actual work is done by the function |
103 | .BR sym_find . |
104 | It does both lookup and creation, depending on its arguments. To do its |
105 | job, it needs to know the following bits of information: |
106 | .TP |
ff76c38f |
107 | .BI "sym_table *" t |
b6b9d458 |
108 | A pointer to a symbol table to manipulate. |
109 | .TP |
ff76c38f |
110 | .BI "const char *" n |
b6b9d458 |
111 | The address of the |
112 | .I key |
113 | to look up or create. Usually this will be a simple text string, |
114 | although it can actually be any arbitrary binary data. |
115 | .TP |
ff76c38f |
116 | .BI "long " l |
b6b9d458 |
117 | The length of the key. If this is \-1, |
118 | .B sym_find |
119 | assumes that the key is a null-terminated string, and calculates its |
0c404077 |
120 | length itself. This is entirely equivalent to passing |
121 | .BI strlen( n )\fR. |
b6b9d458 |
122 | .TP |
ff76c38f |
123 | .BI "size_t " sz |
b6b9d458 |
124 | The size of the value block to allocate if the key could not be found. |
125 | If this is zero, no value is allocated, and a null pointer is returned |
126 | to indicate an unsuccessful lookup. |
127 | .TP |
ff76c38f |
128 | .BI "unsigned *" f |
b6b9d458 |
129 | The address of a `found' flag to set. This is an output parameter. On |
130 | exit, |
131 | .B sym_find |
132 | will set the value of |
133 | .BI * f |
134 | to zero if the key could not be found, or nonzero if it was found. This |
135 | can be used to tell whether the value returned has been newly allocated, |
136 | or whether it was already in the table. |
137 | .PP |
0c404077 |
138 | A terminating null byte is appended to the copy of the symbol's name in |
139 | memory. This is not considered to be a part of the symbol's name, and |
140 | does not contribute to the name's length as reported by the |
141 | .B SYM_LEN |
142 | macro. |
b6b9d458 |
143 | .PP |
144 | A symbol can be removed from the table by calling |
145 | .BR sym_remove , |
146 | passing the symbol table itself, and the value block that needs |
147 | removing. |
0c404077 |
148 | .SS "Enquiries about symbols" |
149 | Three macros are provided to enable simple enquiries about a symbol. |
150 | Given a pointer |
151 | .I s |
152 | to a symbol table entry, |
153 | .BI SYM_LEN( s ) |
154 | returns the length of the symbol's name (excluding any terminating null |
d4efbcd9 |
155 | byte); |
0c404077 |
156 | .BI SYM_NAME( s ) |
157 | returns a pointer to the symbol's name; and |
158 | .BI SYM_HASH( s ) |
159 | returns the symbol's hash value. |
160 | .SS "Enumerating symbols" |
b6b9d458 |
161 | Enumerating the values in a symbol table is fairly simple. Allocate a |
162 | .B sym_iter |
163 | object from somewhere. Attach it to a symbol table by calling |
164 | .BR sym_mkiter , |
165 | and passing in the addresses of the iterator and the symbol table. |
166 | Then, each call to |
167 | .B sym_next |
168 | will return a different value from the symbol table, until all of them |
169 | have been enumerated, at which point, |
170 | .B sym_next |
171 | returns a null pointer. |
172 | .PP |
173 | It's safe to remove the symbol you've just been returned by |
174 | .BR sym_next . |
175 | However, it's not safe to remove any other symbol. So don't do that. |
176 | .PP |
177 | When you've finished with an iterator, it's safe to just throw it away. |
178 | You don't need to call any functions beforehand. |
0c404077 |
179 | .SS "Use in practice" |
b6b9d458 |
180 | In normal use, the keys are simple strings (usually identifiers from |
181 | some language), and the values are nontrivial structures providing |
182 | information about types and values. |
183 | .PP |
184 | In this case, you'd define something like the following structure for |
185 | your values: |
186 | .VS |
187 | typedef struct val { |
188 | sym_base _base; /* Symbol header */ |
189 | unsigned type; /* Type of this symbol */ |
190 | int dispoff; /* Which display variable is in */ |
191 | size_t frameoff; /* Offset of variable in frame */ |
192 | } val; |
193 | .VE |
194 | Given a pointer |
195 | .I v |
196 | to a |
197 | .BR val , |
198 | you can find the variable's name by calling |
199 | .BI SYM_NAME( v )\fR. |
200 | .PP |
201 | You can look up a name in the table by saying something like: |
202 | .VS |
203 | val *v = sym_find(t, name, -1, 0, 0); |
204 | if (!v) |
205 | error("unknown variable `%s'", name); |
206 | .VE |
207 | You can add in a new variable by saying something like |
208 | .VS |
209 | unsigned f; |
210 | val *v = sym_find(t, name, -1, sizeof(val), &f); |
211 | if (f) |
212 | error("variable `%s' already exists", name); |
213 | /* fill in v */ |
214 | .VE |
215 | You can examine all the variables in your symbol table by saying |
216 | something like: |
217 | .VS |
218 | sym_iter i; |
219 | val *v; |
220 | |
221 | for (sym_mkiter(&i, t); (v = sym_next(&i)) != 0; ) { |
222 | /* ... */ |
223 | } |
224 | .VE |
225 | That ought to be enough examples to be getting on with. |
0c404077 |
226 | .SS Implementation |
6f444bda |
227 | The symbol table is an extensible hashtable, using the universal hash |
228 | function described in |
229 | .BR unihash (3) |
230 | and the global hashing key. The hash chains are kept very short |
231 | (probably too short, actually). Every time a symbol is found, its block |
232 | is promoted to the front of its bin chain so it gets found faster next |
233 | time. |
b6b9d458 |
234 | .SH SEE ALSO |
0c404077 |
235 | .BR hash (3), |
08da152e |
236 | .BR mLib (3). |
b6b9d458 |
237 | .SH AUTHOR |
9b5ac6ff |
238 | Mark Wooding, <mdw@distorted.org.uk> |