| .\" Copyright (C) 2005, 2013 Michael Kerrisk <mtk.manpages@gmail.com> |
| .\" a few fragments from an earlier (1996) version by |
| .\" Andries Brouwer (aeb@cwi.nl) remain. |
| .\" |
| .\" %%%LICENSE_START(VERBATIM) |
| .\" Permission is granted to make and distribute verbatim copies of this |
| .\" manual provided the copyright notice and this permission notice are |
| .\" preserved on all copies. |
| .\" |
| .\" Permission is granted to copy and distribute modified versions of this |
| .\" manual under the conditions for verbatim copying, provided that the |
| .\" entire resulting derived work is distributed under the terms of a |
| .\" permission notice identical to this one. |
| .\" |
| .\" Since the Linux kernel and libraries are constantly changing, this |
| .\" manual page may be incorrect or out-of-date. The author(s) assume no |
| .\" responsibility for errors or omissions, or for damages resulting from |
| .\" the use of the information contained herein. The author(s) may not |
| .\" have taken the same level of care in the production of this manual, |
| .\" which is licensed free of charge, as they might when working |
| .\" professionally. |
| .\" |
| .\" Formatted or processed versions of this manual, if unaccompanied by |
| .\" the source, must acknowledge the copyright and authors of this work. |
| .\" %%%LICENSE_END |
| .\" |
| .\" Rewritten old page, 960210, aeb@cwi.nl |
| .\" Updated, added strtok_r. 2000-02-13 Nicolรกs Lichtmaier <nick@debian.org> |
| .\" 2005-11-17, mtk: Substantial parts rewritten |
| .\" 2013-05-19, mtk: added much further detail on the operation of strtok() |
| .\" |
| .TH STRTOK 3 2021-03-22 "GNU" "Linux Programmer's Manual" |
| .SH NAME |
| strtok, strtok_r \- extract tokens from strings |
| .SH SYNOPSIS |
| .nf |
| .B #include <string.h> |
| .PP |
| .BI "char *strtok(char *restrict " str ", const char *restrict " delim ); |
| .BI "char *strtok_r(char *restrict " str ", const char *restrict " delim , |
| .BI " char **restrict " saveptr ); |
| .fi |
| .PP |
| .RS -4 |
| Feature Test Macro Requirements for glibc (see |
| .BR feature_test_macros (7)): |
| .RE |
| .PP |
| .BR strtok_r (): |
| .nf |
| _POSIX_C_SOURCE |
| || /* Glibc <= 2.19: */ _BSD_SOURCE || _SVID_SOURCE |
| .fi |
| .SH DESCRIPTION |
| The |
| .BR strtok () |
| function breaks a string into a sequence of zero or more nonempty tokens. |
| On the first call to |
| .BR strtok (), |
| the string to be parsed should be |
| specified in |
| .IR str . |
| In each subsequent call that should parse the same string, |
| .I str |
| must be NULL. |
| .PP |
| The |
| .I delim |
| argument specifies a set of bytes that |
| delimit the tokens in the parsed string. |
| The caller may specify different strings in |
| .I delim |
| in successive |
| calls that parse the same string. |
| .PP |
| Each call to |
| .BR strtok () |
| returns a pointer to a |
| null-terminated string containing the next token. |
| This string does not include the delimiting byte. |
| If no more tokens are found, |
| .BR strtok () |
| returns NULL. |
| .PP |
| A sequence of calls to |
| .BR strtok () |
| that operate on the same string maintains a pointer |
| that determines the point from which to start searching for the next token. |
| The first call to |
| .BR strtok () |
| sets this pointer to point to the first byte of the string. |
| The start of the next token is determined by scanning forward |
| for the next nondelimiter byte in |
| .IR str . |
| If such a byte is found, it is taken as the start of the next token. |
| If no such byte is found, |
| then there are no more tokens, and |
| .BR strtok () |
| returns NULL. |
| (A string that is empty or that contains only delimiters |
| will thus cause |
| .BR strtok () |
| to return NULL on the first call.) |
| .PP |
| The end of each token is found by scanning forward until either |
| the next delimiter byte is found or until the |
| terminating null byte (\(aq\e0\(aq) is encountered. |
| If a delimiter byte is found, it is overwritten with |
| a null byte to terminate the current token, and |
| .BR strtok () |
| saves a pointer to the following byte; |
| that pointer will be used as the starting point |
| when searching for the next token. |
| In this case, |
| .BR strtok () |
| returns a pointer to the start of the found token. |
| .PP |
| From the above description, |
| it follows that a sequence of two or more contiguous delimiter bytes in |
| the parsed string is considered to be a single delimiter, and that |
| delimiter bytes at the start or end of the string are ignored. |
| Put another way: the tokens returned by |
| .BR strtok () |
| are always nonempty strings. |
| Thus, for example, given the string "\fIaaa;;bbb,\fP", |
| successive calls to |
| .BR strtok () |
| that specify the delimiter string "\fI;,\fP" |
| would return the strings "\fIaaa\fP" and "\fIbbb\fP", |
| and then a null pointer. |
| .PP |
| The |
| .BR strtok_r () |
| function is a reentrant version of |
| .BR strtok (). |
| The |
| .I saveptr |
| argument is a pointer to a |
| .IR "char\ *" |
| variable that is used internally by |
| .BR strtok_r () |
| in order to maintain context between successive calls that parse the |
| same string. |
| .PP |
| On the first call to |
| .BR strtok_r (), |
| .I str |
| should point to the string to be parsed, and the value of |
| .I *saveptr |
| is ignored (but see NOTES). |
| In subsequent calls, |
| .I str |
| should be NULL, and |
| .I saveptr |
| (and the buffer that it points to) |
| should be unchanged since the previous call. |
| .PP |
| Different strings may be parsed concurrently using sequences of calls to |
| .BR strtok_r () |
| that specify different |
| .I saveptr |
| arguments. |
| .SH RETURN VALUE |
| The |
| .BR strtok () |
| and |
| .BR strtok_r () |
| functions return a pointer to |
| the next token, or NULL if there are no more tokens. |
| .SH ATTRIBUTES |
| For an explanation of the terms used in this section, see |
| .BR attributes (7). |
| .ad l |
| .nh |
| .TS |
| allbox; |
| lbx lb lb |
| l l l. |
| Interface Attribute Value |
| T{ |
| .BR strtok () |
| T} Thread safety MT-Unsafe race:strtok |
| T{ |
| .BR strtok_r () |
| T} Thread safety MT-Safe |
| .TE |
| .hy |
| .ad |
| .sp 1 |
| .SH CONFORMING TO |
| .TP |
| .BR strtok () |
| POSIX.1-2001, POSIX.1-2008, C89, C99, SVr4, 4.3BSD. |
| .TP |
| .BR strtok_r () |
| POSIX.1-2001, POSIX.1-2008. |
| .SH NOTES |
| On some implementations, |
| .\" Tru64, according to its manual page |
| .I *saveptr |
| is required to be NULL on the first call to |
| .BR strtok_r () |
| that is being used to parse |
| .IR str . |
| .SH BUGS |
| Be cautious when using these functions. |
| If you do use them, note that: |
| .IP * 2 |
| These functions modify their first argument. |
| .IP * |
| These functions cannot be used on constant strings. |
| .IP * |
| The identity of the delimiting byte is lost. |
| .IP * |
| The |
| .BR strtok () |
| function uses a static buffer while parsing, so it's not thread safe. |
| Use |
| .BR strtok_r () |
| if this matters to you. |
| .SH EXAMPLES |
| The program below uses nested loops that employ |
| .BR strtok_r () |
| to break a string into a two-level hierarchy of tokens. |
| The first command-line argument specifies the string to be parsed. |
| The second argument specifies the delimiter byte(s) |
| to be used to separate that string into "major" tokens. |
| The third argument specifies the delimiter byte(s) |
| to be used to separate the "major" tokens into subtokens. |
| .PP |
| An example of the output produced by this program is the following: |
| .PP |
| .in +4n |
| .EX |
| .RB "$" " ./a.out \(aqa/bbb///cc;xxx:yyy:\(aq \(aq:;\(aq \(aq/\(aq" |
| 1: a/bbb///cc |
| \-\-> a |
| \-\-> bbb |
| \-\-> cc |
| 2: xxx |
| \-\-> xxx |
| 3: yyy |
| \-\-> yyy |
| .EE |
| .in |
| .SS Program source |
| \& |
| .EX |
| #include <stdio.h> |
| #include <stdlib.h> |
| #include <string.h> |
| |
| int |
| main(int argc, char *argv[]) |
| { |
| char *str1, *str2, *token, *subtoken; |
| char *saveptr1, *saveptr2; |
| |
| if (argc != 4) { |
| fprintf(stderr, "Usage: %s string delim subdelim\en", |
| argv[0]); |
| exit(EXIT_FAILURE); |
| } |
| |
| for (int j = 1, str1 = argv[1]; ; j++, str1 = NULL) { |
| token = strtok_r(str1, argv[2], &saveptr1); |
| if (token == NULL) |
| break; |
| printf("%d: %s\en", j, token); |
| |
| for (str2 = token; ; str2 = NULL) { |
| subtoken = strtok_r(str2, argv[3], &saveptr2); |
| if (subtoken == NULL) |
| break; |
| printf("\t \-\-> %s\en", subtoken); |
| } |
| } |
| |
| exit(EXIT_SUCCESS); |
| } |
| .EE |
| .PP |
| Another example program using |
| .BR strtok () |
| can be found in |
| .BR getaddrinfo_a (3). |
| .SH SEE ALSO |
| .BR index (3), |
| .BR memchr (3), |
| .BR rindex (3), |
| .BR strchr (3), |
| .BR string (3), |
| .BR strpbrk (3), |
| .BR strsep (3), |
| .BR strspn (3), |
| .BR strstr (3), |
| .BR wcstok (3) |