sbase/util.h

/* See LICENSE file for copyright and license details. */
#include <sys/types.h>

#include <regex.h>
#include <stddef.h>
#include <stdio.h>

#include "arg.h"
#include "compat.h"

#define UTF8_POINT(c) (((c) & 0xc0) != 0x80)

#undef MIN
#define MIN(x,y)  ((x) < (y) ? (x) : (y))
#undef MAX
#define MAX(x,y)  ((x) > (y) ? (x) : (y))
#undef LIMIT
#define LIMIT(x, a, b)  (x) = (x) < (a) ? (a) : (x) > (b) ? (b) : (x)

#define LEN(x) (sizeof (x) / sizeof *(x))

extern char *argv0;

void *ecalloc(size_t, size_t);
void *emalloc(size_t);
void *erealloc(void *, size_t);
#undef reallocarray
void *reallocarray(void *, size_t, size_t);
void *ereallocarray(void *, size_t, size_t);
char *estrdup(const char *);
char *estrndup(const char *, size_t);
void *encalloc(int, size_t, size_t);
void *enmalloc(int, size_t);
void *enrealloc(int, void *, size_t);
char *enstrdup(int, const char *);
char *enstrndup(int, const char *, size_t);

void enfshut(int, FILE *, const char *);
void efshut(FILE *, const char *);
int  fshut(FILE *, const char *);

void enprintf(int, const char *, ...);
void eprintf(const char *, ...);
void weprintf(const char *, ...);

double estrtod(const char *);

#undef strcasestr
char *strcasestr(const char *, const char *);

#undef strlcat
size_t strlcat(char *, const char *, size_t);
size_t estrlcat(char *, const char *, size_t);
#undef strlcpy
size_t strlcpy(char *, const char *, size_t);
size_t estrlcpy(char *, const char *, size_t);

#undef strsep
char *strsep(char **, const char *);

/* regex */
int enregcomp(int, regex_t *, const char *, int);
int eregcomp(regex_t *, const char *, int);

/* io */
ssize_t writeall(int, const void *, size_t);
int concat(int, const char *, int, const char *);

/* misc */
void enmasse(int, char **, int (*)(const char *, const char *, int));
void fnck(const char *, const char *, int (*)(const char *, const char *, int), int);
mode_t getumask(void);
char *humansize(off_t);
mode_t parsemode(const char *, mode_t, mode_t);
off_t parseoffset(const char *);
void putword(FILE *, const char *);
#undef strtonum
long long strtonum(const char *, long long, long long, const char **);
long long enstrtonum(int, const char *, long long, long long);
long long estrtonum(const char *, long long, long long);
size_t unescape(char *);
int mkdirp(const char *, mode_t, mode_t);
#undef memmem
void *memmem(const void *, size_t, const void *, size_t);
initial commit 2011-05-22 21:36:34 -04:00			`/* See LICENSE file for copyright and license details. */`
Define HOST_NAME_MAX if necessary Some systems do not provide this, namely FreeBSD and NetBSD. 2014-11-17 09:50:12 -05:00			`#include <sys/types.h>`
Add compat.h 2014-11-17 10:45:09 -05:00
util: add eregcomp: show descriptive error message on regcomp error 2014-11-16 09:16:14 -05:00			`#include <regex.h>`
Add strlcpy()/strlcat() Refactor recurse() routine in preparation to moving tar(1) over to use it instead of the ftw() interface. 2014-01-30 07:37:35 -05:00			`#include <stddef.h>`
Add *fshut() functions to properly flush file streams This has been a known issue for a long time. Example: printf "word" > /dev/full wouldn't report there's not enough space on the device. This is due to the fact that every libc has internal buffers for stdout which store fragments of written data until they reach a certain size or on some callback to flush them all at once to the kernel. You can force the libc to flush them with fflush(). In case flushing fails, you can check the return value of fflush() and report an error. However, previously, sbase didn't have such checks and without fflush(), the libc silently flushes the buffers on exit without checking the errors. No offense, but there's no way for the libc to report errors in the exit- condition. GNU coreutils solve this by having onexit-callbacks to handle the flushing and report issues, but they have obvious deficiencies. After long discussions on IRC, we came to the conclusion that checking the return value of every io-function would be a bit too much, and having a general-purpose fclose-wrapper would be the best way to go. It turned out that fclose() alone is not enough to detect errors. The right way to do it is to fflush() + check ferror on the fp and then to a fclose(). This is what fshut does and that's how it's done before each return. The return value is obviously affected, reporting an error in case a flush or close failed, but also when reading failed for some reason, the error- state is caught. the !!( ... + ...) construction is used to call all functions inside the brackets and not "terminating" on the first. We want errors to be reported, but there's no reason to stop flushing buffers when one other file buffer has issues. Obviously, functionales come before the flush and ret-logic comes after to prevent early exits as well without reporting warnings if there are any. One more advantage of fshut() is that it is even able to report errors on obscure NFS-setups which the other coreutils are unable to detect, because they only check the return-value of fflush() and fclose(), not ferror() as well. 2015-04-04 15:25:17 -04:00			`#include <stdio.h>`
Fixing the ARG macros and adding nice. Thanks "Galos, David" <galosd83@students.rowan.edu>! 2013-05-29 14:52:39 -04:00
Add compat.h 2014-11-17 10:45:09 -05:00			`#include "arg.h"`
			`#include "compat.h"`
Define HOST_NAME_MAX if necessary Some systems do not provide this, namely FreeBSD and NetBSD. 2014-11-17 09:50:12 -05:00
add fold 2011-06-08 16:30:33 -04:00			`#define UTF8_POINT(c) (((c) & 0xc0) != 0x80)`

Undef MIN/MAX in case they are defined somewhere else 2014-11-13 10:27:54 -05:00			`#undef MIN`
seq: some cleanup 2012-05-10 14:20:16 -04:00			`#define MIN(x,y) ((x) < (y) ? (x) : (y))`
Undef MIN/MAX in case they are defined somewhere else 2014-11-13 10:27:54 -05:00			`#undef MAX`
seq: some cleanup 2012-05-10 14:20:16 -04:00			`#define MAX(x,y) ((x) > (y) ? (x) : (y))`
Audit nice(1) 1) val is sufficient as "int" (read the standard) 2) BUGFIX: If getpriority fails, it returns -1 and sets errno. Previously, it would correctly catch the errno but not take care of the fact that by then val has been decremented by 1. Only change val if the getpriority-call has been successful. 3) Add LIMIT()-macro from st to increase readability. 4) setpriority returns < 0 on failure 5) Remove bikeshedding-comment. Read the standard if you wonder. 6) return-value trick from env(1) 2015-03-02 10:53:13 -05:00			`#undef LIMIT`
			`#define LIMIT(x, a, b) (x) = (x) < (a) ? (a) : (x) > (b) ? (b) : (x)`
seq: some cleanup 2012-05-10 14:20:16 -04:00
new ARGBEGIN & usage() function 2012-05-14 16:28:41 -04:00			`#define LEN(x) (sizeof (x) / sizeof *(x))`

			`extern char *argv0;`

Import ealloc.c from ubase 2014-11-14 13:09:48 -05:00			`void *ecalloc(size_t, size_t);`
add en*alloc functions 2015-02-10 19:40:52 -05:00			`void *emalloc(size_t);`
Import ealloc.c from ubase 2014-11-14 13:09:48 -05:00			`void erealloc(void , size_t);`
Undef reallocarray in util.h before declaration In case we link against the OpenBSD-libc, we want to avoid collisions. 2015-03-11 12:06:52 -04:00			`#undef reallocarray`
Implement reallocarray() Stateless and I stumbled upon this issue while discussing the semantics of read, accepting a size_t but only being able to return ssize_t, effectively lacking the ability to report successful reads > SSIZE_MAX. The discussion went along and we came to the topic of input-based memory allocations. Basically, it was possible for the argument to a memory-allocation-function to overflow, leading to a segfault later. The OpenBSD-guys came up with the ingenious reallocarray-function, and I implemented it as ereallocarray, which automatically returns on error. Read more about it here[0]. A simple testcase is this (courtesy to stateless): $ sbase-strings -n (2^(32\|64) / 4) This will segfault before this patch and properly return an OOM- situation afterwards (thanks to the overflow-check in reallocarray). [0]: http://www.openbsd.org/cgi-bin/man.cgi/OpenBSD-current/man3/calloc.3 2015-03-10 16:16:21 -04:00			`void reallocarray(void , size_t, size_t);`
			`void ereallocarray(void , size_t, size_t);`
Import ealloc.c from ubase 2014-11-14 13:09:48 -05:00			`char estrdup(const char );`
add estrndup 2015-02-10 19:59:04 -05:00			`char estrndup(const char , size_t);`
add en*alloc functions 2015-02-10 19:40:52 -05:00			`void *encalloc(int, size_t, size_t);`
			`void *enmalloc(int, size_t);`
			`void enrealloc(int, void , size_t);`
			`char enstrdup(int, const char );`
add estrndup 2015-02-10 19:59:04 -05:00			`char enstrndup(int, const char , size_t);`
Group related decls together in util.h 2014-11-14 13:13:14 -05:00
Add *fshut() functions to properly flush file streams This has been a known issue for a long time. Example: printf "word" > /dev/full wouldn't report there's not enough space on the device. This is due to the fact that every libc has internal buffers for stdout which store fragments of written data until they reach a certain size or on some callback to flush them all at once to the kernel. You can force the libc to flush them with fflush(). In case flushing fails, you can check the return value of fflush() and report an error. However, previously, sbase didn't have such checks and without fflush(), the libc silently flushes the buffers on exit without checking the errors. No offense, but there's no way for the libc to report errors in the exit- condition. GNU coreutils solve this by having onexit-callbacks to handle the flushing and report issues, but they have obvious deficiencies. After long discussions on IRC, we came to the conclusion that checking the return value of every io-function would be a bit too much, and having a general-purpose fclose-wrapper would be the best way to go. It turned out that fclose() alone is not enough to detect errors. The right way to do it is to fflush() + check ferror on the fp and then to a fclose(). This is what fshut does and that's how it's done before each return. The return value is obviously affected, reporting an error in case a flush or close failed, but also when reading failed for some reason, the error- state is caught. the !!( ... + ...) construction is used to call all functions inside the brackets and not "terminating" on the first. We want errors to be reported, but there's no reason to stop flushing buffers when one other file buffer has issues. Obviously, functionales come before the flush and ret-logic comes after to prevent early exits as well without reporting warnings if there are any. One more advantage of fshut() is that it is even able to report errors on obscure NFS-setups which the other coreutils are unable to detect, because they only check the return-value of fflush() and fclose(), not ferror() as well. 2015-04-04 15:25:17 -04:00			`void enfshut(int, FILE , const char );`
			`void efshut(FILE , const char );`
			`int fshut(FILE , const char );`

Group related decls together in util.h 2014-11-14 13:13:14 -05:00			`void enprintf(int, const char *, ...);`
			`void eprintf(const char *, ...);`
			`void weprintf(const char *, ...);`

add agetline, separate estrtod to util Signed-off-by: Hiltjo Posthuma <hiltjo@codemadness.org> 2014-06-01 07:57:22 -04:00			`double estrtod(const char *);`
Import ealloc.c from ubase 2014-11-14 13:09:48 -05:00
Import strcasestr() from musl and remove -D_GNU_SOURCE 2014-11-20 18:43:08 -05:00			`#undef strcasestr`
			`char strcasestr(const char , const char *);`

Ensure we #undef strlcat and strlcpy These may be implemented as macros so #undef them and use our own implementation. 2014-01-30 16:02:45 -05:00			`#undef strlcat`
Add strlcpy()/strlcat() Refactor recurse() routine in preparation to moving tar(1) over to use it instead of the ftw() interface. 2014-01-30 07:37:35 -05:00			`size_t strlcat(char , const char , size_t);`
Add estrlcat() and estrlcpy() It has become a common idiom in sbase to check strlcat() and strlcpy() using if (strl{cat, cpy}(dst, src, siz) >= siz) eprintf("path too long\n"); However, this was not carried out consistently and to this very day, some tools employed unchecked calls to these functions, effectively allowing silent truncations to happen, which in turn may lead to security issues. To finally put an end to this, the e*-functions detect truncation automatically and the caller can lean back and enjoy coding without trouble. :) 2015-03-17 06:24:49 -04:00			`size_t estrlcat(char , const char , size_t);`
Ensure we #undef strlcat and strlcpy These may be implemented as macros so #undef them and use our own implementation. 2014-01-30 16:02:45 -05:00			`#undef strlcpy`
Add strlcpy()/strlcat() Refactor recurse() routine in preparation to moving tar(1) over to use it instead of the ftw() interface. 2014-01-30 07:37:35 -05:00			`size_t strlcpy(char , const char , size_t);`
Add estrlcat() and estrlcpy() It has become a common idiom in sbase to check strlcat() and strlcpy() using if (strl{cat, cpy}(dst, src, siz) >= siz) eprintf("path too long\n"); However, this was not carried out consistently and to this very day, some tools employed unchecked calls to these functions, effectively allowing silent truncations to happen, which in turn may lead to security issues. To finally put an end to this, the e*-functions detect truncation automatically and the caller can lean back and enjoy coding without trouble. :) 2015-03-17 06:24:49 -04:00			`size_t estrlcpy(char , const char , size_t);`
make parsemode() generic use for uudecode and chmod Signed-off-by: Hiltjo Posthuma <hiltjo@codemadness.org> 2014-04-09 09:17:20 -04:00
Import strsep() from musl libc 2015-01-25 12:48:11 -05:00			`#undef strsep`
			`char strsep(char , const char );`

util: add eregcomp: show descriptive error message on regcomp error 2014-11-16 09:16:14 -05:00			`/* regex */`
			`int enregcomp(int, regex_t , const char , int);`
			`int eregcomp(regex_t , const char , int);`

libutil: Add writeall utility function writeall makes successive write calls to write an entire buffer to the output file descriptor. It returns the number of bytes written, or -1 on the first error. 2017-01-01 20:00:32 -05:00			`/* io */`
			`ssize_t writeall(int, const void *, size_t);`
concat: Use plain read/write instead of buffered stdio If we are just copying data from one file to another, we don't need to fill a complete buffer, just read a chunk at a time, and write it to the output. 2017-07-03 17:58:49 -04:00			`int concat(int, const char , int, const char );`
libutil: Add writeall utility function writeall makes successive write calls to write an entire buffer to the output file descriptor. It returns the number of bytes written, or -1 on the first error. 2017-01-01 20:00:32 -05:00
Group related decls together in util.h 2014-11-14 13:13:14 -05:00			`/* misc */`
Refactor enmasse() and recurse() to reflect depth The HLP-changes to sbase have been a great addition of functionality, but they kind of "polluted" the enmasse() and recurse() prototypes. As this will come in handy in the future, knowing at which "depth" you are inside a recursing function is an important functionality. Instead of having a special HLP-flag passed to enmasse, each sub- function needs to provide it on its own and can calculate results based on the current depth (for instance, 'H' implies 'P' at depth > 0). A special case is recurse(), because it actually depends on the follow-type. A new flag "recurse_follow" brings consistency into what used to be spread across different naming conventions (fflag, HLP_flag, ...). This also fixes numerous bugs with the behaviour of HLP in the tools using it. 2015-03-02 15:43:56 -05:00			`void enmasse(int, char *, int ()(const char , const char , int));`
			`void fnck(const char , const char , int ()(const char , const char *, int), int);`
parsemode: rework - for octal input: reset mode to 0. - take umask into account. - make '=rwx' etc work. - we wont support crazy but valid modes like "a+rw,g=x,o=g" - uudecode: use parsemode, mask is 0. Signed-off-by: Hiltjo Posthuma <hiltjo@codemadness.org> 2014-04-23 15:28:59 -04:00			`mode_t getumask(void);`
Use off_t in humansize() as it is more descriptive and applicable 2015-04-28 06:48:05 -04:00			`char *humansize(off_t);`
parsemode: rework - for octal input: reset mode to 0. - take umask into account. - make '=rwx' etc work. - we wont support crazy but valid modes like "a+rw,g=x,o=g" - uudecode: use parsemode, mask is 0. Signed-off-by: Hiltjo Posthuma <hiltjo@codemadness.org> 2014-04-23 15:28:59 -04:00			`mode_t parsemode(const char *, mode_t, mode_t);`
Add parseoffset() This is a utility function to allow easy parsing of file or other offsets, automatically taking in regard suffixes, proper bases and so on, for instance used in split(1) -b or od -j, -N(1). Of course, POSIX is very arbitrary when it comes to defining the parsing rules for different tools. The main focus here lies on being as flexible and consistent as possible. One central utility-function handling the parsing makes this stuff a lot more trivial. 2015-09-29 19:19:01 -04:00			`off_t parseoffset(const char *);`
Update putword() to accept a FILE * 2015-04-21 12:40:57 -04:00			`void putword(FILE , const char );`
Remember to undef strtonum in case it is provided also as a macro 2015-01-30 08:52:24 -05:00			`#undef strtonum`
Add strtonum() in preparation to nuking estrtol() and friends 2015-01-30 08:48:33 -05:00			`long long strtonum(const char , long long, long long, const char *);`
Use strtonum and libutf in test(1), refactor code and manpage and mark it as finished in README. 2015-02-09 16:21:23 -05:00			`long long enstrtonum(int, const char *, long long, long long);`
Add estrtonum() as well 2015-01-30 08:56:45 -05:00			`long long estrtonum(const char *, long long, long long);`
Add unescape() to libutil formerly known as resolveescapes(), it is of central use to numerous programs. This drops a lot of LOC. 2015-01-29 15:52:44 -05:00			`size_t unescape(char *);`
mkdir: Fix created directory permissions Previously, with -p, the specified directory and all of its parents would be 0777&~filemask (regardless of the -m flag). POSIX says parent directories must created as (0300\|~filemask)&0777, and of course if -m is set, the specified directory should be created with those permissions. Additionally, POSIX says that for symbolic_mode strings, + and - should be interpretted relative to a default mode of 0777 (not 0). Without -p, previously the directory would be created first with 0777&~filemask (before a chmod), but POSIX says that the directory shall at no point in time have permissions less restrictive than the -m mode argument. Rather than dealing with mkdir removing the filemask bits by calling chmod afterward, just clear the umask and remove the bits manually. 2016-12-14 22:40:06 -05:00			`int mkdirp(const char *, mode_t, mode_t);`
Support NUL-containing lines in sort(1) For sort(1) we need memmem(), which I imported from OpenBSD. Inside sort(1), the changes involved working with the explicit lengths given by getlines() earlier and rewriting some of the functions. Now we can handle NUL-characters in the input just fine. 2016-02-28 18:47:10 -05:00			`#undef memmem`
			`void memmem(const void , size_t, const void *, size_t);`