1 /*
2 * Copyright (c) 2015-2016 Red Hat, Inc.
3 *
4 * All rights reserved.
5 *
6 * Author: Jan Friesse (jfriesse@redhat.com)
7 *
8 * This software licensed under BSD license, the text of which follows:
9 *
10 * Redistribution and use in source and binary forms, with or without
11 * modification, are permitted provided that the following conditions are met:
12 *
13 * - Redistributions of source code must retain the above copyright notice,
14 * this list of conditions and the following disclaimer.
15 * - Redistributions in binary form must reproduce the above copyright notice,
16 * this list of conditions and the following disclaimer in the documentation
17 * and/or other materials provided with the distribution.
18 * - Neither the name of the Red Hat, Inc. nor the names of its
19 * contributors may be used to endorse or promote products derived from this
20 * software without specific prior written permission.
21 *
22 * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
23 * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
24 * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
25 * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
26 * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
27 * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
28 * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
29 * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
30 * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
31 * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF
32 * THE POSSIBILITY OF SUCH DAMAGE.
33 */
34
35 #include <string.h>
36
37 #include "dynar-simple-lex.h"
38
39 /*
40 * Simple_lex is going to be used in protocol and it's not good idea to depend on locale
41 */
42 static int
dynar_simple_lex_is_space(char ch)43 dynar_simple_lex_is_space(char ch)
44 {
45 return (ch == ' ' || ch == '\f' || ch == '\n' || ch == '\r' || ch == '\t' || ch == '\v');
46 }
47
48 void
dynar_simple_lex_init(struct dynar_simple_lex * lex,struct dynar * input,enum dynar_simple_lex_type lex_type)49 dynar_simple_lex_init(struct dynar_simple_lex *lex, struct dynar *input,
50 enum dynar_simple_lex_type lex_type)
51 {
52
53 memset(lex, 0, sizeof(*lex));
54 lex->input = input;
55 lex->lex_type = lex_type;
56 dynar_init(&lex->token, dynar_max_size(input));
57 }
58
59 void
dynar_simple_lex_destroy(struct dynar_simple_lex * lex)60 dynar_simple_lex_destroy(struct dynar_simple_lex *lex)
61 {
62
63 dynar_destroy(&lex->token);
64 memset(lex, 0, sizeof(*lex));
65 }
66
67 struct dynar *
dynar_simple_lex_token_next(struct dynar_simple_lex * lex)68 dynar_simple_lex_token_next(struct dynar_simple_lex *lex)
69 {
70 size_t pos;
71 size_t size;
72 char *str;
73 char ch, ch2;
74 int add_char;
75 int state;
76
77 dynar_clean(&lex->token);
78
79 size = dynar_size(lex->input);
80 str = dynar_data(lex->input);
81
82 state = 1;
83 pos = lex->pos;
84
85 while (state != 0) {
86 if (pos < size) {
87 ch = str[pos];
88 } else {
89 ch = '\0';
90 }
91
92 add_char = 0;
93
94 switch (state) {
95 case 1:
96 /*
97 * Skip spaces. Newline is special and means end of processing
98 */
99 if (pos >= size || ch == '\n' || ch == '\r') {
100 state = 0;
101 } else if (dynar_simple_lex_is_space(ch)) {
102 pos++;
103 } else {
104 state = 2;
105 }
106 break;
107 case 2:
108 /*
109 * Read word
110 */
111 if (pos >= size) {
112 state = 0;
113 } else if ((lex->lex_type == DYNAR_SIMPLE_LEX_TYPE_BACKSLASH ||
114 lex->lex_type == DYNAR_SIMPLE_LEX_TYPE_QUOTE) && ch == '\\') {
115 pos++;
116 state = 3;
117 } else if (lex->lex_type == DYNAR_SIMPLE_LEX_TYPE_QUOTE &&
118 ch == '"') {
119 pos++;
120 state = 4;
121 } else if (dynar_simple_lex_is_space(ch)) {
122 state = 0;
123 } else {
124 pos++;
125 add_char = 1;
126 }
127 break;
128 case 3:
129 /*
130 * Process backslash
131 */
132 if (pos >= size || ch == '\n' || ch == '\r') {
133 /*
134 * End of string. Do not include backslash (it's just ignored)
135 */
136 state = 0;
137 } else {
138 add_char = 1;
139 state = 2;
140 pos++;
141 }
142 break;
143 case 4:
144 /*
145 * Quote word
146 */
147 if (pos >= size) {
148 state = 0;
149 } else if (ch == '\\') {
150 state = 5;
151 pos++;
152 } else if (ch == '"') {
153 state = 2;
154 pos++;
155 } else if (ch == '\n' || ch == '\r') {
156 state = 0;
157 } else {
158 pos++;
159 add_char = 1;
160 }
161 break;
162 case 5:
163 /*
164 * Quote word backslash
165 */
166 if (pos >= size || ch == '\n' || ch == '\r') {
167 /*
168 * End of string. Do not include backslash (it's just ignored)
169 */
170 state = 0;
171 } else if (ch == '\\' || ch == '"') {
172 add_char = 1;
173 state = 4;
174 pos++;
175 } else {
176 ch2 = '\\';
177 if (dynar_cat(&lex->token, &ch2, sizeof(ch2)) != 0) {
178 return (NULL);
179 }
180
181 add_char = 1;
182 state = 4;
183 pos++;
184 }
185 break;
186 }
187
188 if (add_char) {
189 if (dynar_cat(&lex->token, &ch, sizeof(ch)) != 0) {
190 return (NULL);
191 }
192 }
193 }
194
195 ch = '\0';
196 if (dynar_cat(&lex->token, &ch, sizeof(ch)) != 0) {
197 return (NULL);
198 }
199
200 lex->pos = pos;
201
202 return (&lex->token);
203 }
204