File: matcher.cpp

package info (click to toggle)
packagekit 1.1.5-2%2Bdeb9u1
  • links: PTS, VCS
  • area: main
  • in suites: stretch
  • size: 15,464 kB
  • sloc: ansic: 56,926; cpp: 8,658; python: 7,641; xml: 6,388; sh: 4,517; perl: 1,738; makefile: 1,437; ruby: 1,341
file content (202 lines) | stat: -rw-r--r-- 5,423 bytes parent folder | download
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
/* matcher.cpp
 *
 * Copyright (c) 1999-2008 Daniel Burrows
 * Copyright (c) 2009-2016 Daniel Nicoletti <dantti12@gmail.com>
 *               2012 Matthias Klumpp <matthias@tenstral.net>
 *
 * 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; see the file COPYING.  If not, write to
 * the Free Software Foundation, Inc., 59 Temple Place - Suite 330,
 * Boston, MA 02111-1307, USA.
 */

#include "matcher.h"
#include <stdio.h>
#include <iostream>

Matcher::Matcher(const string &matchers) :
    m_hasError(false)
{
    string::const_iterator start = matchers.begin();
    parse_pattern(start, matchers.end());
    if (m_hasError) {
        cerr << "ERROR: " << m_error << endl;
    }
}

Matcher::~Matcher()
{
    for (regex_t &rx : m_matches) {
        regfree(&rx);
    }
}

bool do_compile(const string &_pattern,
                regex_t &pattern,
                int cflags)
{
    return !regcomp(&pattern, _pattern.c_str(), cflags);
}

bool string_matches(const char *s, regex_t &pattern_nogroup)
{
    return !regexec(&pattern_nogroup, s, 0, NULL, 0);
}

bool Matcher::matches(const string &s)
{
    int matchesCount = 0;
    for (regex_t &rx : m_matches) {
        if (string_matches(s.c_str(), rx)) {
            matchesCount++;
        }
    }

    return m_matches.size() == matchesCount;
}

bool Matcher::parse_pattern(string::const_iterator &start,
                            const std::string::const_iterator &end)
{
    // Just filter blank strings out immediately.
    while (start != end && isspace(*start)) {
        ++start;
    }

    if (start == end) {
        return false;
    }

    while (start != end && *start != '|' && *start != ')') {
        string subString = parse_substr(start, end);

        if (subString.empty()) {
            continue;
        }

        regex_t pattern_nogroup;
        if (do_compile(subString, pattern_nogroup, REG_ICASE|REG_EXTENDED|REG_NOSUB)) {
            m_matches.push_back(pattern_nogroup);
        } else {
            regfree(&pattern_nogroup);
            m_error = string("Regex compilation error");
            m_hasError = true;
            return false;
        }
    }

    return true;
}

string Matcher::parse_literal_string_tail(string::const_iterator &start,
                                          const string::const_iterator end)
{
    std::string rval;

    while (start != end && *start != '"') {
        if (*start == '\\') {
            ++start;
            if (start != end) {
                switch (*start) {
                case 'n':
                    rval += '\n';
                    break;
                case 't':
                    rval += '\t';
                    break;
                default:
                    rval += *start;
                    break;
                }
                ++start;
            }
        } else {
            rval += *start;
            ++start;
        }
    }

    if (start == end || *start != '"') {
        m_error = string("Unterminated literal string after " + rval);
        m_hasError = true;
        return string();
    }

    ++start;

    return rval;
}

// Returns a substring up to the first metacharacter, including escaped
// metacharacters (parentheses, ~, |, and !)
//
// Advances loc to the first character of 's' following the escaped string.
string Matcher::parse_substr(string::const_iterator &start,
                             const string::const_iterator &end)
{
    std::string rval;
    bool done=false;

    // Strip leading whitespace.
    while (start != end && isspace(*start))
        ++start;

    do {
        while (start != end &&
               *start != '(' &&
               *start != ')' &&
               *start != '!' &&
               *start != '~' &&
               *start != '|' &&
               *start != '"' &&
               !isspace(*start)) {
            rval += *start;
            ++start;
        }

        if (start != end && *start == '"') {
            ++start;

            rval += parse_literal_string_tail(start, end);
            if (m_hasError) {
                return string();
            }
        }

        // We quit because we ran off the end of the string or saw a
        // metacharacter.  If the latter case and it was a tilde-escape,
        // add the escaped character to the string and continue.
        if (start != end && start+1 != end && *start == '~') {
            const char next = *(start+1);

            if (next == '(' || next == ')' ||
                    next == '!' || next == '~' ||
                    next == '|' || next == '"' ||
                    isspace(next)) {
                rval += next;
                start += 2;
            } else {
                done = true;
            }
        } else {
            done = true;
        }
    } while(!done);

    return rval;
}

bool Matcher::hasError() const
{
    return m_hasError;
}