1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
|
/*=============================================================================
GNU UnRTF, a command-line program to convert RTF documents to other formats.
Copyright (C) 2000,2001 Zachary Thayer Smith
This program is free software; you can redistribute it and/or modify
it under the terms of the GNU General Public License as published by
the Free Software Foundation; either version 2 of the License, or
(at your option) any later version.
This program is distributed in the hope that it will be useful,
but WITHOUT ANY WARRANTY; without even the implied warranty of
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
GNU General Public License for more details.
You should have received a copy of the GNU General Public License
along with this program; if not, write to the Free Software
Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
The author is reachable by electronic mail at tuorfa@yahoo.com.
=============================================================================*/
/*----------------------------------------------------------------------
* Module name: hash
* Author name: Zach Smith
* Create date: 01 Sep 00
* Purpose: Word-hash management. Words are put into a hash and an
* identifier is returned. This is used to save us from
* doing multiple mallocs for recurring strings such as
* 'the' and \par. This is not a big issue under Unix,
* but it is under other OSes and anyway, waste not want not.
*----------------------------------------------------------------------
* Changes:
* 08 Apr 01, tuorfa@yahoo.com: check for out of memory after malloc.
* 21 Apr 01, tuorfa@yahoo.com: signed to conversion unsigned bug
* 03 Aug 01, tuorfa@yahoo.com: fixes for using 16-bit compiler
* 22 Sep 01, tuorfa@yahoo.com: added function-level comment blocks
* 08 Oct 03, daved@physiol.usyd.edu.au: some type fixes
*--------------------------------------------------------------------*/
#include <stdio.h>
#include <string.h>
#include "error.h"
#include "main.h"
#include "malloc.h"
typedef struct _hi {
struct _hi *next;
char *str;
unsigned long value;
}
HashItem;
/* Index by first char of string */
static HashItem *hash[256];
static unsigned long hash_length[256];
static unsigned long hash_value=0;
/*========================================================================
* Name: hash_init
* Purpose: Clear the hash table.
* Args: None.
* Returns: None.
*=======================================================================*/
void
hash_init ()
{
int i;
for (i=0; i<256; i++) {
hash[i]=NULL;
hash_length[i]=0;
}
}
/*========================================================================
* Name: hash_stats
* Purpose: Prints to stderr the number of words stored.
* Args: None.
* Returns: None.
*=======================================================================*/
void
hash_stats ()
{
int i;
unsigned long total=0;
for (i=0; i<256; i++) {
total += hash_length[i];
}
fprintf (stderr,"%lu words were hashed.\n", total);
}
/*========================================================================
* Name: hashitem_new
* Purpose: Creates a new linked list item for the hash table.
* Args: String.
* Returns: HashItem.
*=======================================================================*/
static HashItem *
hashitem_new (char *str)
{
HashItem *hi;
unsigned long i;
hi=(HashItem*) my_malloc(sizeof(HashItem));
if (!hi)
error_handler ("out of memory");
memset ((void*)hi, 0, sizeof (HashItem));
hi->str = my_strdup(str);
i = *str;
if (i=='\\') i=str[1];
i <<= 24;
hi->value = i | (hash_value++ & 0xffffff);
hi->next = NULL;
#if 0
if (debug_mode) {
printf ("<!-- storing val %08lx str %s -->\n",
hi->value, hi->str);
}
#endif
return hi;
}
/*========================================================================
* Name: hash_get_index
* Purpose: Given a string, returns the "index" i.e. the word identifier.
* Args: String.
* Returns: Index.
*=======================================================================*/
unsigned long
hash_get_index (char *str)
{
#if 1 /* daved - 0.19.1 */
unsigned short index;
unsigned char ch;
#else
int index;
char ch;
#endif
HashItem *hi;
#if 1 /* daved - 0.19.1 */
ch = (unsigned char)*str;
#else
ch = *str;
#endif
if (ch=='\\' && *(str+1))
ch = *(str+1);
index = ch;
hi = hash[index];
while (hi) {
if (!strcmp(hi->str,str))
return hi->value;
hi=hi->next;
}
/* not in hash */
hi = hashitem_new (str);
hi->next = hash[index];
hash [index] = hi;
++hash_length [index];
return hi->value;
}
/*========================================================================
* Name: hash_get_string
* Purpose: Given the index (word identifier) returns the word string.
* Args: Index.
* Returns: String, or NULL if not found.
*=======================================================================*/
char*
hash_get_string (unsigned long value)
{
int index;
HashItem *hi;
index = value >> 24;
hi = hash[index];
while (hi) {
if (hi->value == value)
return hi->str;
hi=hi->next;
}
warning_handler ("word not in hash");
return NULL;
}
|
