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
|
/***************************************************************************
* Copyright (C) 2015-2018 by Hans-Peter Deifel *
* hpd@hpdeifel.de *
* *
* 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., 51 Franklin Street, Fifth Floor, *
* Boston, MA 02110-1301 USA. *
***************************************************************************/
#include "regengine.h"
#include <regex.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <iostream>
#include <iomanip>
#include <string>
#include <sstream>
#include "output.h"
#include "pdfgrep.h"
using namespace std;
bool PatternList::exec(const string &str, size_t offset, struct match &m) const
{
struct match m_copy = m;
for (auto &r : patterns) {
if (r->exec(str, offset, m_copy)) {
m.start = m_copy.start;
m.end = m_copy.end;
return true;
}
}
return false;
}
void PatternList::add_pattern(unique_ptr<Regengine> pattern) {
patterns.push_back(move(pattern));
}
// regex(3)
PosixRegex::PosixRegex(const string &pattern, bool case_insensitive)
{
int regex_flags = REG_EXTENDED | (case_insensitive ? REG_ICASE : 0);
// The regcomp/regexec implementation of OpenBSD doesn't like empty
// patterns. Thus we just replace empty patterns by "()", which does
// have the same semantics.
const char *c_str_pattern;
if (pattern == "") {
c_str_pattern = "()";
} else {
c_str_pattern = pattern.c_str();
}
int ret = regcomp(&this->regex, c_str_pattern, regex_flags);
if(ret) {
char err_msg[256];
regerror(ret, &this->regex, err_msg, 256);
err() << err_msg << endl;
exit(EXIT_ERROR);
}
}
bool PosixRegex::exec(const string &str, size_t offset, struct match &m) const
{
regmatch_t match[] = {{0, 0}};
const int nmatch = 1;
// If we aren't at the beginning of the page, ^ should not match.
int flags = offset == 0 ? 0 : REG_NOTBOL;
int ret = regexec(&this->regex, &str[offset], nmatch, match, flags);
if(ret) {
return false;
}
m.start = offset + match[0].rm_so;
m.end = offset + match[0].rm_eo;
return true;
}
PosixRegex::~PosixRegex()
{
regfree(&this->regex);
}
// pcre(3)
#ifdef HAVE_LIBPCRE
PCRERegex::PCRERegex(const string &pattern, bool case_insensitive)
{
const char *pcre_err;
int pcre_err_ofs;
const int pcre_options = PCRE_UTF8 | (case_insensitive ? PCRE_CASELESS : 0);
this->regex = pcre_compile(pattern.c_str(), pcre_options,
&pcre_err, &pcre_err_ofs, NULL);
if (this->regex == NULL) {
err() << pattern << endl;
err() << setw(pcre_err_ofs+1) << "^" << endl;
err() << "Error compiling PCRE pattern: " << pcre_err << endl;
exit(EXIT_ERROR);
}
}
PCRERegex::~PCRERegex()
{
pcre_free(this->regex);
}
bool PCRERegex::exec(const string &str, size_t offset, struct match &m) const
{
const size_t len = str.size();
int ov[3];
const int ret = pcre_exec(this->regex, NULL, str.c_str(), len, offset, 0, ov, 3);
// TODO: Print human readable error
if(ret < 0)
return false;
m.start = ov[0];
m.end = ov[1];
return true;
}
#endif // HAVE_LIBPCRE
FixedString::FixedString(const string &pattern, bool case_insensitive)
: case_insensitive(case_insensitive)
{
istringstream str { pattern };
string line;
if (pattern.empty()) {
// special case for the empty pattern. In this case we _do_ want
// matches, but getline returns false leaving our patterns array
// empty. Thus we add the whole pattern explicitly.
patterns.push_back(pattern);
return;
}
// split pattern at newlines
while (getline(str, line)) {
patterns.push_back(line);
}
}
bool FixedString::exec(const string &str, size_t offset, struct match &m) const
{
// We use C-style strings here, because of strcasestr
const char *str_begin = &str[offset];
// FIXME Searching for multiple patterns is very inefficient, because we
// search the same thing over and over, until it becomes the next match.
// We should introduce some kind of caching here
const char *min_result = NULL;
const string *min_pattern;
for (const string pattern : patterns) {
const char *result;
if (this->case_insensitive) {
result = strcasestr(str_begin, pattern.c_str());
} else {
result = strstr(str_begin, pattern.c_str());
}
if (result != NULL) {
if (min_result == NULL || result < min_result) {
min_result = result;
min_pattern = &pattern;
}
}
}
if (min_result != NULL) {
m.start = offset + (min_result - str_begin);
m.end = m.start + (*min_pattern).size();
return true;
}
return false;
}
|
