| 1 | .\" -*-nroff-*- |
| 2 | .de VS |
| 3 | .sp 1 |
| 4 | .in +5n |
| 5 | .ft B |
| 6 | .nf |
| 7 | .. |
| 8 | .de VE |
| 9 | .ft R |
| 10 | .in -5n |
| 11 | .sp 1 |
| 12 | .fi |
| 13 | .. |
| 14 | .TH str 3 "20 June 1999" "Straylight/Edgeware" "mLib utilities library" |
| 15 | .SH NAME |
| 16 | str \- small string utilities |
| 17 | .\" @str_qword |
| 18 | .\" @str_qsplit |
| 19 | .\" @str_getword |
| 20 | .\" @str_split |
| 21 | .\" @str_match |
| 22 | .\" @str_sanitize |
| 23 | .SH SYNOPSIS |
| 24 | .nf |
| 25 | .B "#include <mLib/str.h>" |
| 26 | |
| 27 | .BI "char *str_qword(char **" pp ", unsigned " f ); |
| 28 | .BI "size_t str_qsplit(char *" p ", char *" v "[], size_t " c , |
| 29 | .BI " char **" rest ", unsigned " f ); |
| 30 | .BI "char *str_getword(char **" pp ); |
| 31 | .BI "size_t str_split(char *" p ", char *" v "[], size_t " c ", char **" rest ); |
| 32 | .BI "int str_match(const char *" p ", const char *" s ); |
| 33 | .BI "void str_sanitize(char *" d ", const char *" p ", size_t " sz ); |
| 34 | .fi |
| 35 | .SH DESCRIPTION |
| 36 | The header file |
| 37 | .B <mLib/str.h> |
| 38 | contains a few small utility functions for manipulating null-terminated |
| 39 | strings. |
| 40 | .PP |
| 41 | The function |
| 42 | .B str_qword |
| 43 | extracts the next whitespace-delimited word from a string. The |
| 44 | function's argument, |
| 45 | .IR pp , |
| 46 | is the address of a pointer into the string: this pointer is updated by |
| 47 | .B str_qword |
| 48 | so that it can extract the following word on the next call and so on. |
| 49 | The return value is the address of the next word, appropriately null |
| 50 | terminated. A null pointer is returned if the entire remainder of the |
| 51 | string is whitespace. Note that |
| 52 | .B str_qword |
| 53 | modifies the string as it goes, to null-terminate the individual words. |
| 54 | If the flag |
| 55 | .B STRF_QUOTE |
| 56 | is passed, the single- and double-quote characters may be used to quote |
| 57 | whitespace within words, and the backslash can escape quote characters |
| 58 | and whitespace. |
| 59 | .PP |
| 60 | The function |
| 61 | .B str_qsplit |
| 62 | divides a string into whitespace-separated words. The arguments are as |
| 63 | follows: |
| 64 | .TP |
| 65 | .BI "char *" p |
| 66 | The address of the string to split. The string is modified by having |
| 67 | null terminators written after each word extracted. |
| 68 | .TP |
| 69 | .BI "char *" v [] |
| 70 | The address of an array of pointers to characters. This array will be |
| 71 | filled in by |
| 72 | .BR str_split : |
| 73 | the first entry will point to the first word extracted from the string, |
| 74 | and so on. If there aren't enough words in the string, the remaining |
| 75 | array elements are filled with null pointers. |
| 76 | .TP |
| 77 | .BI "size_t " c |
| 78 | The maximum number of words to extract; also, the number of elements in |
| 79 | the array |
| 80 | .IR v . |
| 81 | .TP |
| 82 | .BI "char **" rest |
| 83 | The address of a pointer in which to store the address of the remainder |
| 84 | of the string. Leading whitespace is removed from the remainder before |
| 85 | storing. If the remainder string is empty, a null pointer is stored |
| 86 | instead. If |
| 87 | .I rest |
| 88 | is null, the remainder pointer is discarded. |
| 89 | .TP |
| 90 | .BI "unsigned " f |
| 91 | Flags, as for |
| 92 | .BR str_qsplit . |
| 93 | .PP |
| 94 | The return value of |
| 95 | .B str_qsplit |
| 96 | is the number of words extracted from the input string. |
| 97 | .PP |
| 98 | The functions |
| 99 | .B str_getword |
| 100 | and |
| 101 | .B str_split |
| 102 | are veneers over |
| 103 | .B str_qword |
| 104 | and |
| 105 | .B str_qsplit |
| 106 | respectively; they are equivalent to calls to the latter functions with |
| 107 | flags words of zero. |
| 108 | .PP |
| 109 | The |
| 110 | .B str_match |
| 111 | function does simple wildcard matching. The first argument is a |
| 112 | pattern, which may contain metacharacters: |
| 113 | .RB ` * ' |
| 114 | matches zero or more arbitrary characters; |
| 115 | .RB ` ? ' |
| 116 | matches exactly one arbitrary characters; and |
| 117 | .RB ` [ ... ] ' |
| 118 | matches one of the characters listed. The backslash |
| 119 | .RB ` \e ' |
| 120 | escapes the following character. Within square brackets, the |
| 121 | hyphen |
| 122 | .RB ` \- ' |
| 123 | may be used to designate ranges of characters. If the initial character |
| 124 | is |
| 125 | .RB ` ! ' |
| 126 | or |
| 127 | .RB ` ^ ' |
| 128 | then the sense of the match is reversed. To literally match a |
| 129 | .RB ` ] ' |
| 130 | character, list it first; to literally match a |
| 131 | .RB ` \- ' |
| 132 | character, list it immediately after a range, or at the beginning or end |
| 133 | of the set. The return value is nonzero if the pattern |
| 134 | .I p |
| 135 | matches the given string |
| 136 | .IR s , |
| 137 | or zero if the pattern doesn't match. |
| 138 | .PP |
| 139 | The function |
| 140 | .B str_sanitize |
| 141 | copies at most |
| 142 | .I sz \- 1 |
| 143 | characters from the string |
| 144 | .I p |
| 145 | to |
| 146 | .IR d . |
| 147 | The result string is null terminated. Any nonprinting characters in |
| 148 | .I p |
| 149 | are replaced by an underscore |
| 150 | .RB ` _ ' |
| 151 | when written to |
| 152 | .IR d . |
| 153 | .SH EXAMPLES |
| 154 | Given the code |
| 155 | .VS |
| 156 | char p[] = " alpha beta gamma delta "; |
| 157 | char *v[3]; |
| 158 | size_t n; |
| 159 | char *q; |
| 160 | |
| 161 | n = str_split(p, v, 3, &q); |
| 162 | .VE |
| 163 | following the call to |
| 164 | .BR str_split , |
| 165 | .B n |
| 166 | will have the value 3, |
| 167 | .B v[0] |
| 168 | will point to |
| 169 | .RB ` alpha ', |
| 170 | .B v[1] |
| 171 | will point to |
| 172 | .RB ` beta ', |
| 173 | .B v[2] |
| 174 | will point to |
| 175 | .RB ` gamma ' |
| 176 | and |
| 177 | .B rest |
| 178 | will point to |
| 179 | .RB ` delta\ ' |
| 180 | (note the trailing space). |
| 181 | .PP |
| 182 | Similarly, given the string |
| 183 | .B """\ alpha\ \ beta\ """ |
| 184 | instead, |
| 185 | .B n |
| 186 | will be assigned the value 2, |
| 187 | .B v[0] |
| 188 | and |
| 189 | .B v[1] |
| 190 | will have the same values as last time, and |
| 191 | .B v[2] |
| 192 | and |
| 193 | .B rest |
| 194 | will be null. |
| 195 | .SH "SEE ALSO" |
| 196 | .BR mLib (3). |
| 197 | .SH AUTHOR |
| 198 | Mark Wooding, <mdw@distorted.org.uk> |