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
|
/* Split source by line breaks, and calculate a simplistic checksum. */
/*
* Copyright (c) 2020 Neels Hofmeyr <neels@hofmeyr.de>
*
* Permission to use, copy, modify, and distribute this software for any
* purpose with or without fee is hereby granted, provided that the above
* copyright notice and this permission notice appear in all copies.
*
* THE SOFTWARE IS PROVIDED "AS IS" AND THE AUTHOR DISCLAIMS ALL WARRANTIES
* WITH REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES OF
* MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR
* ANY SPECIAL, DIRECT, INDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES
* WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN
* ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF
* OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
*/
#include <errno.h>
#include <stdbool.h>
#include <stdint.h>
#include <stdio.h>
#include <stdlib.h>
#include <unistd.h>
#include <ctype.h>
#include <arraylist.h>
#include <diff_main.h>
#include "diff_internal.h"
#include "diff_debug.h"
unsigned int
diff_atom_hash_update(unsigned int hash, unsigned char atom_byte)
{
return hash * 23 + atom_byte;
}
static int
diff_data_atomize_text_lines_fd(struct diff_data *d)
{
off_t pos = 0;
const off_t end = pos + d->len;
unsigned int array_size_estimate = d->len / 50;
unsigned int pow2 = 1;
bool ignore_whitespace = (d->diff_flags & DIFF_FLAG_IGNORE_WHITESPACE);
bool isbinary = false;
while (array_size_estimate >>= 1)
pow2++;
ARRAYLIST_INIT(d->atoms, 1 << pow2);
if (fseek(d->root->f, 0L, SEEK_SET) == -1)
return errno;
while (pos < end) {
off_t line_end = pos;
unsigned int hash = 0;
unsigned char buf[512];
size_t r, i;
struct diff_atom *atom;
int eol = 0;
while (eol == 0 && line_end < end) {
r = fread(buf, sizeof(char), sizeof(buf), d->root->f);
if (r == 0 && ferror(d->root->f))
return EIO;
i = 0;
while (eol == 0 && i < r) {
if (buf[i] != '\r' && buf[i] != '\n') {
if (!ignore_whitespace
|| !isspace((unsigned char)buf[i]))
hash = diff_atom_hash_update(
hash, buf[i]);
if (iscntrl((unsigned char)buf[i]) &&
!isspace((unsigned char)buf[i]))
isbinary = true;
line_end++;
} else
eol = buf[i];
i++;
}
}
/* When not at the end of data, the line ending char ('\r' or
* '\n') must follow */
if (line_end < end)
line_end++;
/* If that was an '\r', also pull in any following '\n' */
if (line_end < end && eol == '\r') {
if (fseeko(d->root->f, line_end, SEEK_SET) == -1)
return errno;
r = fread(buf, sizeof(char), sizeof(buf), d->root->f);
if (r == 0 && ferror(d->root->f))
return EIO;
if (r > 0 && buf[0] == '\n')
line_end++;
}
/* Record the found line as diff atom */
ARRAYLIST_ADD(atom, d->atoms);
if (!atom)
return ENOMEM;
*atom = (struct diff_atom){
.root = d,
.pos = pos,
.at = NULL, /* atom data is not memory-mapped */
.len = line_end - pos,
.hash = hash,
};
/* Starting point for next line: */
pos = line_end;
if (fseeko(d->root->f, pos, SEEK_SET) == -1)
return errno;
}
/* File are considered binary if they contain control bytes. */
if (isbinary)
d->atomizer_flags |= DIFF_ATOMIZER_FOUND_BINARY_DATA;
return DIFF_RC_OK;
}
static int
diff_data_atomize_text_lines_mmap(struct diff_data *d)
{
const uint8_t *pos = d->data;
const uint8_t *end = pos + d->len;
bool ignore_whitespace = (d->diff_flags & DIFF_FLAG_IGNORE_WHITESPACE);
bool isbinary = false;
unsigned int array_size_estimate = d->len / 50;
unsigned int pow2 = 1;
while (array_size_estimate >>= 1)
pow2++;
ARRAYLIST_INIT(d->atoms, 1 << pow2);
while (pos < end) {
const uint8_t *line_end = pos;
unsigned int hash = 0;
while (line_end < end && *line_end != '\r' && *line_end != '\n') {
if (!ignore_whitespace
|| !isspace((unsigned char)*line_end))
hash = diff_atom_hash_update(hash, *line_end);
if (iscntrl((unsigned char)*line_end) &&
!isspace((unsigned char)*line_end))
isbinary = true;
line_end++;
}
/* When not at the end of data, the line ending char ('\r' or
* '\n') must follow */
if (line_end < end && *line_end == '\r')
line_end++;
if (line_end < end && *line_end == '\n')
line_end++;
/* Record the found line as diff atom */
struct diff_atom *atom;
ARRAYLIST_ADD(atom, d->atoms);
if (!atom)
return ENOMEM;
*atom = (struct diff_atom){
.root = d,
.pos = (off_t)(pos - d->data),
.at = pos,
.len = line_end - pos,
.hash = hash,
};
/* Starting point for next line: */
pos = line_end;
}
/* File are considered binary if they contain embedded control bytes. */
if (isbinary)
d->atomizer_flags |= DIFF_ATOMIZER_FOUND_BINARY_DATA;
return DIFF_RC_OK;
}
static int
diff_data_atomize_text_lines(struct diff_data *d)
{
if (d->data == NULL)
return diff_data_atomize_text_lines_fd(d);
else
return diff_data_atomize_text_lines_mmap(d);
}
int
diff_atomize_text_by_line(void *func_data, struct diff_data *d)
{
return diff_data_atomize_text_lines(d);
}
|
