1 /**
2 * Copyright (c) 2019, Timothy Stack
3 *
4 * All rights reserved.
5 *
6 * Redistribution and use in source and binary forms, with or without
7 * modification, are permitted provided that the following conditions are met:
8 *
9 * * Redistributions of source code must retain the above copyright notice, this
10 * list of conditions and the following disclaimer.
11 * * Redistributions in binary form must reproduce the above copyright notice,
12 * this list of conditions and the following disclaimer in the documentation
13 * and/or other materials provided with the distribution.
14 * * Neither the name of Timothy Stack nor the names of its contributors
15 * may be used to endorse or promote products derived from this software
16 * without specific prior written permission.
17 *
18 * THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ''AS IS'' AND ANY
19 * EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
20 * WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
21 * DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE FOR ANY
22 * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
23 * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
24 * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON
25 * ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
26 * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
27 * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
28 */
29
30 #ifndef lnav_string_util_hh
31 #define lnav_string_util_hh
32
33 #include <string.h>
34 #include <string>
35 #include <vector>
36
37 #include "ww898/cp_utf8.hpp"
38
39 void scrub_to_utf8(char *buffer, size_t length);
40
is_line_ending(char ch)41 inline bool is_line_ending(char ch) {
42 return ch == '\r' || ch == '\n';
43 }
44
45 size_t unquote(char *dst, const char *str, size_t len);
46
47 size_t unquote_w3c(char *dst, const char *str, size_t len);
48
startswith(const char * str,const char * prefix)49 inline bool startswith(const char *str, const char *prefix)
50 {
51 return strncmp(str, prefix, strlen(prefix)) == 0;
52 }
53
startswith(const std::string & str,const char * prefix)54 inline bool startswith(const std::string &str, const char *prefix)
55 {
56 return startswith(str.c_str(), prefix);
57 }
58
startswith(const std::string & str,const std::string & prefix)59 inline bool startswith(const std::string &str, const std::string& prefix)
60 {
61 return startswith(str.c_str(), prefix.c_str());
62 }
63
endswith(const char * str,const char * suffix)64 inline bool endswith(const char *str, const char *suffix)
65 {
66 size_t len = strlen(str), suffix_len = strlen(suffix);
67
68 if (suffix_len > len) {
69 return false;
70 }
71
72 return strcmp(&str[len - suffix_len], suffix) == 0;
73 }
74
75 template<int N>
endswith(const std::string & str,const char (& suffix)[N])76 inline bool endswith(const std::string& str, const char (&suffix) [N])
77 {
78 if (N - 1 > str.length()) {
79 return false;
80 }
81
82 return strcmp(&str[str.size() - (N - 1)], suffix) == 0;
83 }
84
85 void truncate_to(std::string &str, size_t max_char_len);
86
trim(const std::string & str)87 inline std::string trim(const std::string &str)
88 {
89 std::string::size_type start, end;
90
91 for (start = 0; start < str.size() && isspace(str[start]); start++);
92 for (end = str.size(); end > 0 && isspace(str[end - 1]); end--);
93
94 return str.substr(start, end - start);
95 }
96
tolower(const char * str)97 inline std::string tolower(const char *str)
98 {
99 std::string retval;
100
101 for (int lpc = 0; str[lpc]; lpc++) {
102 retval.push_back(::tolower(str[lpc]));
103 }
104
105 return retval;
106 }
107
tolower(const std::string & str)108 inline std::string tolower(const std::string &str)
109 {
110 return tolower(str.c_str());
111 }
112
toupper(const char * str)113 inline std::string toupper(const char *str)
114 {
115 std::string retval;
116
117 for (int lpc = 0; str[lpc]; lpc++) {
118 retval.push_back(::toupper(str[lpc]));
119 }
120
121 return retval;
122 }
123
toupper(const std::string & str)124 inline std::string toupper(const std::string &str)
125 {
126 return toupper(str.c_str());
127 }
128
utf8_char_to_byte_index(const std::string & str,ssize_t ch_index)129 inline ssize_t utf8_char_to_byte_index(const std::string &str, ssize_t ch_index)
130 {
131 ssize_t retval = 0;
132
133 while (ch_index > 0) {
134 auto ch_len = ww898::utf::utf8::char_size([&str, retval]() {
135 return std::make_pair(str[retval], str.length() - retval - 1);
136 }).unwrapOr(1);
137
138 retval += ch_len;
139 ch_index -= 1;
140 }
141
142 return retval;
143 }
144
utf8_string_length(const char * str,ssize_t len=-1)145 inline Result<size_t, const char *> utf8_string_length(const char *str, ssize_t len = -1)
146 {
147 size_t retval = 0;
148
149 if (len == -1) {
150 len = strlen(str);
151 }
152
153 for (ssize_t byte_index = 0; byte_index < len;) {
154 auto ch_size = TRY(ww898::utf::utf8::char_size([str, len, byte_index]() {
155 return std::make_pair(str[byte_index], len - byte_index);
156 }));
157 byte_index += ch_size;
158 retval += 1;
159 }
160
161 return Ok(retval);
162 }
163
utf8_string_length(const std::string & str)164 inline Result<size_t, const char *> utf8_string_length(const std::string& str)
165 {
166 return utf8_string_length(str.c_str(), str.length());
167 }
168
169 bool is_url(const char *fn);
170
171 size_t abbreviate_str(char *str, size_t len, size_t max_len);
172
173 void split_ws(const std::string &str, std::vector<std::string> &toks_out);
174
175 std::string repeat(const std::string& input, size_t num);
176
177 std::string center_str(const std::string& subject, size_t width);
178
179 template<typename T>
180 size_t strtonum(T &num_out, const char *data, size_t len);
181
182 #endif
183