2004-11-03 13:51:07 +00:00
|
|
|
.\" Copyright (C) Markus Kuhn, 1996, 2001
|
|
|
|
.\"
|
getent.1, _syscall.2, acct.2, adjtimex.2, bdflush.2, brk.2, cacheflush.2, getsid.2, getxattr.2, inotify_add_watch.2, inotify_init.2, inotify_rm_watch.2, ioperm.2, ipc.2, listxattr.2, mlock.2, modify_ldt.2, mremap.2, nanosleep.2, outb.2, perf_event_open.2, ptrace.2, removexattr.2, s390_runtime_instr.2, sched_get_priority_max.2, sched_rr_get_interval.2, sched_setaffinity.2, sched_setparam.2, sched_setscheduler.2, sched_yield.2, setsid.2, setxattr.2, socketcall.2, unimplemented.2, aio_cancel.3, aio_error.3, aio_fsync.3, aio_read.3, aio_return.3, aio_suspend.3, aio_write.3, cfree.3, crypt.3, dlopen.3, encrypt.3, errno.3, fenv.3, ftime.3, ftw.3, getgrent_r.3, getpass.3, getpwent_r.3, getutent.3, hsearch.3, lio_listio.3, lockf.3, login.3, longjmp.3, perror.3, printf.3, scandirat.3, setjmp.3, strfmon.3, strtoimax.3, termios.3, ttyname.3, ualarm.3, updwtmp.3, wcstoimax.3, wordexp.3, console_ioctl.4, dsp56k.4, fd.4, hd.4, intro.4, lp.4, mem.4, null.4, ram.4, rtc.4, sk98lin.4, tty.4, ttyS.4, vcs.4, filesystems.5, group.5, host.conf.5, hosts.5, intro.5, issue.5, motd.5, networks.5, nologin.5, nsswitch.conf.5, passwd.5, proc.5, protocols.5, securetty.5, shells.5, termcap.5, ttytype.5, utmp.5, intro.6, armscii-8.7, ascii.7, bootparam.7, cp1251.7, environ.7, glob.7, intro.7, iso_8859-1.7, iso_8859-10.7, iso_8859-11.7, iso_8859-13.7, iso_8859-14.7, iso_8859-15.7, iso_8859-16.7, iso_8859-2.7, iso_8859-3.7, iso_8859-4.7, iso_8859-5.7, iso_8859-6.7, iso_8859-7.7, iso_8859-8.7, iso_8859-9.7, koi8-r.7, koi8-u.7, posixoptions.7, standards.7, unicode.7, utf-8.7, intro.8: s/GPLv2+_doc_full/GPLv2+_DOC_FULL/
Signed-off-by: Michael Kerrisk <mtk.manpages@gmail.com>
2013-03-10 09:29:46 +00:00
|
|
|
.\" %%%LICENSE_START(GPLv2+_DOC_FULL)
|
2004-11-03 13:51:07 +00:00
|
|
|
.\" This is free documentation; you can redistribute it and/or
|
|
|
|
.\" modify it under the terms of the GNU General Public License as
|
|
|
|
.\" published by the Free Software Foundation; either version 2 of
|
|
|
|
.\" the License, or (at your option) any later version.
|
|
|
|
.\"
|
|
|
|
.\" The GNU General Public License's references to "object code"
|
|
|
|
.\" and "executables" are to be interpreted as the output of any
|
|
|
|
.\" document formatting or typesetting system, including
|
|
|
|
.\" intermediate and printed output.
|
|
|
|
.\"
|
|
|
|
.\" This manual is distributed in the hope that it will be useful,
|
|
|
|
.\" but WITHOUT ANY WARRANTY; without even the implied warranty of
|
|
|
|
.\" MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
|
|
|
|
.\" GNU General Public License for more details.
|
|
|
|
.\"
|
|
|
|
.\" You should have received a copy of the GNU General Public
|
getent.1, _syscall.2, acct.2, adjtimex.2, bdflush.2, brk.2, cacheflush.2, getsid.2, getxattr.2, inotify_add_watch.2, inotify_init.2, inotify_rm_watch.2, ioperm.2, ipc.2, listxattr.2, mlock.2, modify_ldt.2, mremap.2, nanosleep.2, outb.2, ptrace.2, removexattr.2, sched_get_priority_max.2, sched_rr_get_interval.2, sched_setaffinity.2, sched_setparam.2, sched_setscheduler.2, sched_yield.2, setsid.2, setxattr.2, socketcall.2, unimplemented.2, aio_cancel.3, aio_error.3, aio_fsync.3, aio_read.3, aio_return.3, aio_suspend.3, aio_write.3, cfree.3, crypt.3, dlopen.3, errno.3, fenv.3, ftime.3, ftw.3, getgrent_r.3, getpass.3, getpwent_r.3, getutent.3, hsearch.3, lio_listio.3, login.3, longjmp.3, perror.3, printf.3, scandirat.3, setjmp.3, strfmon.3, strtoimax.3, termios.3, ttyname.3, ualarm.3, wcstoimax.3, wordexp.3, console_ioctl.4, dsp56k.4, fd.4, hd.4, intro.4, lp.4, mem.4, null.4, ram.4, rtc.4, sk98lin.4, tty.4, ttyS.4, vcs.4, charmap.5, filesystems.5, ftpusers.5, gai.conf.5, group.5, host.conf.5, hosts.5, intro.5, issue.5, locale.5, motd.5, networks.5, nologin.5, nscd.conf.5, nss.5, nsswitch.conf.5, passwd.5, proc.5, protocols.5, securetty.5, shells.5, termcap.5, ttytype.5, utmp.5, intro.6, armscii-8.7, ascii.7, bootparam.7, cp1251.7, cpuset.7, environ.7, glob.7, intro.7, iso_8859-1.7, iso_8859-10.7, iso_8859-11.7, iso_8859-13.7, iso_8859-14.7, iso_8859-15.7, iso_8859-16.7, iso_8859-2.7, iso_8859-3.7, iso_8859-4.7, iso_8859-5.7, iso_8859-6.7, iso_8859-7.7, iso_8859-8.7, iso_8859-9.7, koi8-r.7, koi8-u.7, posixoptions.7, standards.7, unicode.7, utf-8.7, intro.8, ldconfig.8, nscd.8: Global fix: Update info in source comments on where to get a copy of the GPL
Signed-off-by: Michael Kerrisk <mtk.manpages@gmail.com>
2013-03-10 09:28:43 +00:00
|
|
|
.\" License along with this manual; if not, see
|
|
|
|
.\" <http://www.gnu.org/licenses/>.
|
getent.1, _syscall.2, acct.2, adjtimex.2, bdflush.2, brk.2, cacheflush.2, getsid.2, getxattr.2, inotify_add_watch.2, inotify_init.2, inotify_rm_watch.2, ioperm.2, ipc.2, listxattr.2, mlock.2, modify_ldt.2, mremap.2, nanosleep.2, outb.2, perf_event_open.2, ptrace.2, removexattr.2, s390_runtime_instr.2, sched_get_priority_max.2, sched_rr_get_interval.2, sched_setaffinity.2, sched_setparam.2, sched_setscheduler.2, sched_yield.2, setsid.2, setxattr.2, socketcall.2, unimplemented.2, aio_cancel.3, aio_error.3, aio_fsync.3, aio_read.3, aio_return.3, aio_suspend.3, aio_write.3, cfree.3, crypt.3, dlopen.3, encrypt.3, errno.3, fenv.3, ftime.3, ftw.3, getgrent_r.3, getpass.3, getpwent_r.3, getutent.3, hsearch.3, lio_listio.3, lockf.3, login.3, longjmp.3, perror.3, printf.3, scandirat.3, setjmp.3, strfmon.3, strtoimax.3, termios.3, ttyname.3, ualarm.3, updwtmp.3, wcstoimax.3, wordexp.3, console_ioctl.4, dsp56k.4, fd.4, hd.4, intro.4, lp.4, mem.4, null.4, ram.4, rtc.4, sk98lin.4, tty.4, ttyS.4, vcs.4, filesystems.5, group.5, host.conf.5, hosts.5, intro.5, issue.5, motd.5, networks.5, nologin.5, nsswitch.conf.5, passwd.5, proc.5, protocols.5, securetty.5, shells.5, termcap.5, ttytype.5, utmp.5, intro.6, armscii-8.7, ascii.7, bootparam.7, cp1251.7, environ.7, glob.7, intro.7, iso_8859-1.7, iso_8859-10.7, iso_8859-11.7, iso_8859-13.7, iso_8859-14.7, iso_8859-15.7, iso_8859-16.7, iso_8859-2.7, iso_8859-3.7, iso_8859-4.7, iso_8859-5.7, iso_8859-6.7, iso_8859-7.7, iso_8859-8.7, iso_8859-9.7, koi8-r.7, koi8-u.7, posixoptions.7, standards.7, unicode.7, utf-8.7, intro.8: Global fix: Add LICENSE_START(GPLv2+_doc_full)
Signed-off-by: Michael Kerrisk <mtk.manpages@gmail.com>
2013-03-10 09:28:44 +00:00
|
|
|
.\" %%%LICENSE_END
|
2004-11-03 13:51:07 +00:00
|
|
|
.\"
|
|
|
|
.\" 1995-11-26 Markus Kuhn <mskuhn@cip.informatik.uni-erlangen.de>
|
|
|
|
.\" First version written
|
|
|
|
.\" 2001-05-11 Markus Kuhn <mgk25@cl.cam.ac.uk>
|
|
|
|
.\" Update
|
|
|
|
.\"
|
getent.1, iconv.1, ldd.1, locale.1, localedef.1, memusage.1, memusagestat.1, pldd.1, sprof.1, time.1, _syscall.2, accept.2, add_key.2, adjtimex.2, bind.2, bpf.2, capget.2, chown.2, chroot.2, clock_getres.2, clone.2, connect.2, copy_file_range.2, epoll_ctl.2, epoll_wait.2, eventfd.2, fanotify_init.2, fanotify_mark.2, fcntl.2, fsync.2, futex.2, getcpu.2, getdents.2, getgid.2, getgroups.2, getpid.2, gettid.2, gettimeofday.2, getuid.2, getxattr.2, inotify_add_watch.2, inotify_init.2, ioctl_fat.2, ioctl_ns.2, ioctl_userfaultfd.2, ioprio_set.2, kcmp.2, kexec_load.2, keyctl.2, listxattr.2, lseek.2, madvise.2, memfd_create.2, migrate_pages.2, mount.2, mprotect.2, mremap.2, msgctl.2, msgop.2, nfsservctl.2, open_by_handle_at.2, perf_event_open.2, pipe.2, pivot_root.2, pkey_alloc.2, poll.2, posix_fadvise.2, prctl.2, readahead.2, readdir.2, readlink.2, reboot.2, recvmmsg.2, removexattr.2, rename.2, request_key.2, s390_guarded_storage.2, s390_runtime_instr.2, s390_sthyi.2, sched_setaffinity.2, sched_setattr.2, sched_setparam.2, seccomp.2, select.2, select_tut.2, semctl.2, sendmmsg.2, set_thread_area.2, setgid.2, setns.2, setuid.2, setxattr.2, shmctl.2, sigaction.2, signalfd.2, sigsuspend.2, socket.2, socketpair.2, spu_run.2, stat.2, statx.2, subpage_prot.2, syscalls.2, sysctl.2, tee.2, timer_create.2, timerfd_create.2, truncate.2, uname.2, unshare.2, userfaultfd.2, ustat.2, vmsplice.2, write.2, CPU_SET.3, __ppc_get_timebase.3, alloca.3, argz_add.3, asprintf.3, backtrace.3, basename.3, bsd_signal.3, bstring.3, bswap.3, bzero.3, cacos.3, cacosh.3, catan.3, catanh.3, catgets.3, clock_getcpuclockid.3, cmsg.3, confstr.3, ctermid.3, ctime.3, des_crypt.3, dl_iterate_phdr.3, dlinfo.3, dlsym.3, duplocale.3, end.3, endian.3, errno.3, exec.3, exit.3, ferror.3, fgetws.3, fmemopen.3, fnmatch.3, fopencookie.3, fputws.3, frexp.3, ftw.3, get_nprocs_conf.3, get_phys_pages.3, getaddrinfo.3, getaddrinfo_a.3, getdate.3, getgrouplist.3, getifaddrs.3, getline.3, getlogin.3, getmntent.3, getnameinfo.3, getopt.3, getpass.3, getprotoent_r.3, getpwnam.3, getservent_r.3, getsubopt.3, glob.3, gnu_get_libc_version.3, hsearch.3, if_nameindex.3, index.3, inet.3, inet_net_pton.3, inet_pton.3, insque.3, isatty.3, iswblank.3, iswspace.3, lockf.3, makecontext.3, mallinfo.3, malloc.3, malloc_hook.3, malloc_info.3, mallopt.3, matherr.3, mbrtowc.3, mbsnrtowcs.3, mbsrtowcs.3, mbstowcs.3, mbtowc.3, mcheck.3, memchr.3, mq_getattr.3, mq_notify.3, newlocale.3, nl_langinfo.3, offsetof.3, perror.3, posix_spawn.3, printf.3, pthread_attr_init.3, pthread_cancel.3, pthread_cleanup_push.3, pthread_getattr_default_np.3, pthread_getattr_np.3, pthread_getcpuclockid.3, pthread_mutexattr_setrobust.3, pthread_rwlockattr_setkind_np.3, pthread_setaffinity_np.3, pthread_setname_np.3, pthread_setschedparam.3, pthread_sigmask.3, putenv.3, qsort.3, rand.3, random.3, readdir.3, regex.3, resolver.3, rpmatch.3, rtime.3, scanf.3, sem_wait.3, setaliasent.3, setbuf.3, stpcpy.3, stpncpy.3, strcat.3, strchr.3, strcmp.3, strcpy.3, strdup.3, strerror.3, strfromd.3, strfry.3, strftime.3, string.3, strlen.3, strnlen.3, strsep.3, strstr.3, strtok.3, strtol.3, strtoul.3, strverscmp.3, strxfrm.3, system.3, termios.3, trunc.3, wcpcpy.3, wcpncpy.3, wcrtomb.3, wcscat.3, wcscpy.3, wcslen.3, wcsncat.3, wcsncmp.3, wcsncpy.3, wcsnlen.3, wcsnrtombs.3, wcsrtombs.3, wcsstr.3, wcstok.3, wcstombs.3, wcwidth.3, wprintf.3, xcrypt.3, console_codes.4, dsp56k.4, full.4, initrd.4, lirc.4, loop.4, st.4, tty.4, vcs.4, charmap.5, core.5, host.conf.5, locale.5, proc.5, repertoiremap.5, resolv.conf.5, termcap.5, tmpfs.5, tzfile.5, aio.7, capabilities.7, cgroup_namespaces.7, cgroups.7, charsets.7, complex.7, epoll.7, fanotify.7, feature_test_macros.7, inotify.7, ip.7, locale.7, man-pages.7, man.7, namespaces.7, pid_namespaces.7, pkeys.7, pthreads.7, rtld-audit.7, sched.7, signal.7, sock_diag.7, socket.7, tcp.7, udp.7, unicode.7, user_namespaces.7, utf-8.7, zdump.8, zic.8: tstamp
Signed-off-by: Michael Kerrisk <mtk.manpages@gmail.com>
2019-03-06 14:11:03 +00:00
|
|
|
.TH UTF-8 7 2019-03-06 "GNU" "Linux Programmer's Manual"
|
2004-11-03 13:51:07 +00:00
|
|
|
.SH NAME
|
getaddrinfo.3, setlocale.3, strchr.3, wctob.3, st.4, glob.7, locale.7, regex.7, standards.7, unicode.7, utf-8.7: Global fix: s/multi-/multi/
The tendency in English, as prescribed in style guides like
Chicago MoS, is towards removing hyphens after prefixes
like "multi-" etc.
Signed-off-by: Michael Kerrisk <mtk.manpages@gmail.com>
2010-01-16 17:47:55 +00:00
|
|
|
UTF-8 \- an ASCII compatible multibyte Unicode encoding
|
2004-11-03 13:51:07 +00:00
|
|
|
.SH DESCRIPTION
|
2014-06-24 10:08:09 +00:00
|
|
|
The Unicode 3.0 character set occupies a 16-bit code space.
|
2007-04-12 22:42:49 +00:00
|
|
|
The most obvious
|
2014-06-24 10:08:09 +00:00
|
|
|
Unicode encoding (known as UCS-2)
|
2007-04-12 22:42:49 +00:00
|
|
|
consists of a sequence of 16-bit words.
|
2014-02-26 09:55:52 +00:00
|
|
|
Such strings can contain\(emas part of many 16-bit characters\(embytes
|
locale.1, memusage.1, pldd.1, _syscall.2, add_key.2, bind.2, bpf.2, chown.2, clone.2, copy_file_range.2, eventfd.2, execve.2, futex.2, getdents.2, getrlimit.2, ioctl_fat.2, ioctl_ns.2, kcmp.2, kexec_load.2, keyctl.2, listxattr.2, lseek.2, membarrier.2, memfd_create.2, mmap.2, mprotect.2, msgop.2, open_by_handle_at.2, perf_event_open.2, pipe.2, readdir.2, readlink.2, readv.2, recvmmsg.2, request_key.2, sched_setaffinity.2, seccomp.2, select.2, select_tut.2, sendmmsg.2, setns.2, signalfd.2, spu_run.2, stat.2, sysctl.2, tee.2, timer_create.2, timerfd_create.2, truncate.2, uname.2, unshare.2, userfaultfd.2, ustat.2, wait.2, CPU_SET.3, __ppc_get_timebase.3, argz_add.3, asprintf.3, backtrace.3, basename.3, bswap.3, bzero.3, cacos.3, cacosh.3, catan.3, catanh.3, catgets.3, clock_getcpuclockid.3, confstr.3, ctime.3, dl_iterate_phdr.3, dlinfo.3, duplocale.3, encrypt.3, end.3, endian.3, fgetws.3, fmemopen.3, fopencookie.3, fputws.3, frexp.3, ftw.3, get_nprocs_conf.3, get_phys_pages.3, getaddrinfo.3, getaddrinfo_a.3, getdate.3, getgrouplist.3, getifaddrs.3, getline.3, getlogin.3, getopt.3, getpass.3, getprotoent_r.3, getpwnam.3, getservent_r.3, getsubopt.3, glob.3, gnu_get_libc_version.3, hsearch.3, if_nameindex.3, index.3, inet.3, inet_net_pton.3, inet_pton.3, insque.3, iswblank.3, iswspace.3, makecontext.3, mallinfo.3, malloc_hook.3, malloc_info.3, mallopt.3, matherr.3, mbrtowc.3, mbsnrtowcs.3, mbsrtowcs.3, mbstowcs.3, mbtowc.3, mcheck.3, memchr.3, mq_getattr.3, mq_notify.3, newlocale.3, nl_langinfo.3, offsetof.3, perror.3, posix_spawn.3, printf.3, pthread_attr_init.3, pthread_cancel.3, pthread_cleanup_push.3, pthread_create.3, pthread_getattr_default_np.3, pthread_getattr_np.3, pthread_getcpuclockid.3, pthread_mutexattr_setrobust.3, pthread_setaffinity_np.3, pthread_setname_np.3, pthread_setschedparam.3, pthread_sigmask.3, qsort.3, rand.3, readdir.3, regex.3, rpmatch.3, rtime.3, scanf.3, sem_wait.3, setaliasent.3, setbuf.3, stpcpy.3, stpncpy.3, strcat.3, strchr.3, strcpy.3, strdup.3, strerror.3, strfromd.3, strftime.3, strlen.3, strnlen.3, strsep.3, strstr.3, strtok.3, strtol.3, strtoul.3, strverscmp.3, strxfrm.3, termios.3, tsearch.3, wcpcpy.3, wcpncpy.3, wcrtomb.3, wcscat.3, wcscpy.3, wcslen.3, wcsncat.3, wcsncmp.3, wcsncpy.3, wcsnlen.3, wcsnrtombs.3, wcsrtombs.3, wcsstr.3, wcstok.3, wcstombs.3, wcwidth.3, wprintf.3, console_codes.4, dsp56k.4, full.4, initrd.4, loop.4, vcs.4, charmap.5, core.5, elf.5, locale.5, proc.5, repertoiremap.5, sysfs.5, termcap.5, aio.7, bpf-helpers.7, cgroups.7, charsets.7, complex.7, fanotify.7, feature_test_macros.7, inotify.7, locale.7, man-pages.7, man.7, pkeys.7, pthreads.7, rtld-audit.7, sock_diag.7, unix.7, user_namespaces.7, utf-8.7: Use '\e' rather than '\\' to get a backslash
Quoting Branden:
*roff escape sequences may sometimes look like C escapes, but that
is misleading. *roff is in part a macro language and that means
recursive expansion to arbitrary depths.
You can get away with "\\" in a context where no macro expansion
is taking place, but try to spell a literal backslash this way in
the argument to a macro and you will likely be unhappy with
results.
Try viewing the attached file with "man -l".
"\e" is the preferred and portable way to get a portable "escape
literal" going back to CSTR #54, the original Bell Labs troff
paper.
groff(7) discusses the issue:
\\ reduces to a single backslash; useful to delay its
interpretation as escape character in copy mode. For a
printable backslash, use \e, or even better \[rs], to be
independent from the current escape character.
As of groff 1.22.4, groff_man(7) does as well:
\e Widely used in man pages to represent a backslash output
glyph. It works reliably as long as the .ec request is
not used, which should never happen in man pages, and it
is slightly more portable than the more exact ‘\(rs’
(“reverse solidus”) escape sequence.
People not concerned with portability to extremely old troffs should
probably just use \(rs (or \[rs]), as it means "the backslash
glyph", not "the glyph corresponding to whatever the current escape
character is".
Signed-off-by: Michael Kerrisk <mtk.manpages@gmail.com>
2019-02-27 11:57:17 +00:00
|
|
|
such as \(aq\e0\(aq or \(aq/\(aq, which have a
|
2008-07-10 20:53:08 +00:00
|
|
|
special meaning in filenames and other C library function arguments.
|
2014-02-26 09:55:52 +00:00
|
|
|
In addition, the majority of UNIX tools expect ASCII files and can't
|
2007-04-12 22:42:49 +00:00
|
|
|
read 16-bit words as characters without major modifications.
|
|
|
|
For these reasons,
|
2014-06-24 10:08:09 +00:00
|
|
|
UCS-2 is not a suitable external encoding of Unicode
|
2012-05-06 20:16:42 +00:00
|
|
|
in filenames, text files, environment variables, and so on.
|
2014-06-24 10:08:09 +00:00
|
|
|
The ISO 10646 Universal Character Set (UCS),
|
2014-02-26 09:55:52 +00:00
|
|
|
a superset of Unicode, occupies an even larger code
|
|
|
|
space\(em31\ bits\(emand the obvious
|
2014-06-24 10:08:09 +00:00
|
|
|
UCS-4 encoding for it (a sequence of 32-bit words) has the same problems.
|
aio.7, arp.7, attributes.7, boot.7, cgroups.7, cpuset.7, credentials.7, fanotify.7, fifo.7, glob.7, hier.7, hostname.7, icmp.7, inode.7, inotify.7, keyrings.7, libc.7, mailaddr.7, mount_namespaces.7, mq_overview.7, nptl.7, numa.7, path_resolution.7, persistent-keyring.7, pid_namespaces.7, pipe.7, pkeys.7, process-keyring.7, pthreads.7, pty.7, random.7, sched.7, sem_overview.7, session-keyring.7, shm_overview.7, signal-safety.7, signal.7, spufs.7, standards.7, symlink.7, termio.7, thread-keyring.7, time.7, unicode.7, user-keyring.7, user-session-keyring.7, user_namespaces.7, utf-8.7, xattr.7: ffix
Signed-off-by: Michael Kerrisk <mtk.manpages@gmail.com>
2017-08-17 22:59:04 +00:00
|
|
|
.PP
|
2014-06-24 10:08:09 +00:00
|
|
|
The UTF-8 encoding of Unicode and UCS
|
2004-11-03 13:51:07 +00:00
|
|
|
does not have these problems and is the common way in which
|
2014-06-24 10:08:09 +00:00
|
|
|
Unicode is used on UNIX-style operating systems.
|
2007-06-15 20:16:04 +00:00
|
|
|
.SS Properties
|
2014-06-24 10:08:09 +00:00
|
|
|
The UTF-8 encoding has the following nice properties:
|
2004-11-03 13:51:07 +00:00
|
|
|
.TP 0.2i
|
|
|
|
*
|
2014-06-24 10:08:09 +00:00
|
|
|
UCS
|
|
|
|
characters 0x00000000 to 0x0000007f (the classic US-ASCII
|
2004-11-03 13:51:07 +00:00
|
|
|
characters) are encoded simply as bytes 0x00 to 0x7f (ASCII
|
2007-04-12 22:42:49 +00:00
|
|
|
compatibility).
|
|
|
|
This means that files and strings which contain only
|
|
|
|
7-bit ASCII characters have the same encoding under both
|
2014-06-24 10:08:09 +00:00
|
|
|
ASCII
|
2004-11-03 13:51:07 +00:00
|
|
|
and
|
2014-06-24 10:08:09 +00:00
|
|
|
UTF-8 .
|
2004-11-03 13:51:07 +00:00
|
|
|
.TP
|
|
|
|
*
|
2014-06-24 10:08:09 +00:00
|
|
|
All UCS characters greater than 0x7f are encoded as a multibyte sequence
|
2004-11-03 13:51:07 +00:00
|
|
|
consisting only of bytes in the range 0x80 to 0xfd, so no ASCII
|
|
|
|
byte can appear as part of another character and there are no
|
locale.1, memusage.1, pldd.1, _syscall.2, add_key.2, bind.2, bpf.2, chown.2, clone.2, copy_file_range.2, eventfd.2, execve.2, futex.2, getdents.2, getrlimit.2, ioctl_fat.2, ioctl_ns.2, kcmp.2, kexec_load.2, keyctl.2, listxattr.2, lseek.2, membarrier.2, memfd_create.2, mmap.2, mprotect.2, msgop.2, open_by_handle_at.2, perf_event_open.2, pipe.2, readdir.2, readlink.2, readv.2, recvmmsg.2, request_key.2, sched_setaffinity.2, seccomp.2, select.2, select_tut.2, sendmmsg.2, setns.2, signalfd.2, spu_run.2, stat.2, sysctl.2, tee.2, timer_create.2, timerfd_create.2, truncate.2, uname.2, unshare.2, userfaultfd.2, ustat.2, wait.2, CPU_SET.3, __ppc_get_timebase.3, argz_add.3, asprintf.3, backtrace.3, basename.3, bswap.3, bzero.3, cacos.3, cacosh.3, catan.3, catanh.3, catgets.3, clock_getcpuclockid.3, confstr.3, ctime.3, dl_iterate_phdr.3, dlinfo.3, duplocale.3, encrypt.3, end.3, endian.3, fgetws.3, fmemopen.3, fopencookie.3, fputws.3, frexp.3, ftw.3, get_nprocs_conf.3, get_phys_pages.3, getaddrinfo.3, getaddrinfo_a.3, getdate.3, getgrouplist.3, getifaddrs.3, getline.3, getlogin.3, getopt.3, getpass.3, getprotoent_r.3, getpwnam.3, getservent_r.3, getsubopt.3, glob.3, gnu_get_libc_version.3, hsearch.3, if_nameindex.3, index.3, inet.3, inet_net_pton.3, inet_pton.3, insque.3, iswblank.3, iswspace.3, makecontext.3, mallinfo.3, malloc_hook.3, malloc_info.3, mallopt.3, matherr.3, mbrtowc.3, mbsnrtowcs.3, mbsrtowcs.3, mbstowcs.3, mbtowc.3, mcheck.3, memchr.3, mq_getattr.3, mq_notify.3, newlocale.3, nl_langinfo.3, offsetof.3, perror.3, posix_spawn.3, printf.3, pthread_attr_init.3, pthread_cancel.3, pthread_cleanup_push.3, pthread_create.3, pthread_getattr_default_np.3, pthread_getattr_np.3, pthread_getcpuclockid.3, pthread_mutexattr_setrobust.3, pthread_setaffinity_np.3, pthread_setname_np.3, pthread_setschedparam.3, pthread_sigmask.3, qsort.3, rand.3, readdir.3, regex.3, rpmatch.3, rtime.3, scanf.3, sem_wait.3, setaliasent.3, setbuf.3, stpcpy.3, stpncpy.3, strcat.3, strchr.3, strcpy.3, strdup.3, strerror.3, strfromd.3, strftime.3, strlen.3, strnlen.3, strsep.3, strstr.3, strtok.3, strtol.3, strtoul.3, strverscmp.3, strxfrm.3, termios.3, tsearch.3, wcpcpy.3, wcpncpy.3, wcrtomb.3, wcscat.3, wcscpy.3, wcslen.3, wcsncat.3, wcsncmp.3, wcsncpy.3, wcsnlen.3, wcsnrtombs.3, wcsrtombs.3, wcsstr.3, wcstok.3, wcstombs.3, wcwidth.3, wprintf.3, console_codes.4, dsp56k.4, full.4, initrd.4, loop.4, vcs.4, charmap.5, core.5, elf.5, locale.5, proc.5, repertoiremap.5, sysfs.5, termcap.5, aio.7, bpf-helpers.7, cgroups.7, charsets.7, complex.7, fanotify.7, feature_test_macros.7, inotify.7, locale.7, man-pages.7, man.7, pkeys.7, pthreads.7, rtld-audit.7, sock_diag.7, unix.7, user_namespaces.7, utf-8.7: Use '\e' rather than '\\' to get a backslash
Quoting Branden:
*roff escape sequences may sometimes look like C escapes, but that
is misleading. *roff is in part a macro language and that means
recursive expansion to arbitrary depths.
You can get away with "\\" in a context where no macro expansion
is taking place, but try to spell a literal backslash this way in
the argument to a macro and you will likely be unhappy with
results.
Try viewing the attached file with "man -l".
"\e" is the preferred and portable way to get a portable "escape
literal" going back to CSTR #54, the original Bell Labs troff
paper.
groff(7) discusses the issue:
\\ reduces to a single backslash; useful to delay its
interpretation as escape character in copy mode. For a
printable backslash, use \e, or even better \[rs], to be
independent from the current escape character.
As of groff 1.22.4, groff_man(7) does as well:
\e Widely used in man pages to represent a backslash output
glyph. It works reliably as long as the .ec request is
not used, which should never happen in man pages, and it
is slightly more portable than the more exact ‘\(rs’
(“reverse solidus”) escape sequence.
People not concerned with portability to extremely old troffs should
probably just use \(rs (or \[rs]), as it means "the backslash
glyph", not "the glyph corresponding to whatever the current escape
character is".
Signed-off-by: Michael Kerrisk <mtk.manpages@gmail.com>
2019-02-27 11:57:17 +00:00
|
|
|
problems with, for example, \(aq\e0\(aq or \(aq/\(aq.
|
2004-11-03 13:51:07 +00:00
|
|
|
.TP
|
|
|
|
*
|
2014-06-24 10:08:09 +00:00
|
|
|
The lexicographic sorting order of UCS-4 strings is preserved.
|
2004-11-03 13:51:07 +00:00
|
|
|
.TP
|
|
|
|
*
|
2014-06-24 10:08:09 +00:00
|
|
|
All possible 2^31 UCS codes can be encoded using UTF-8.
|
2004-11-03 13:51:07 +00:00
|
|
|
.TP
|
|
|
|
*
|
2014-06-24 10:08:09 +00:00
|
|
|
The bytes 0xc0, 0xc1, 0xfe, and 0xff are never used in the UTF-8 encoding.
|
2004-11-03 13:51:07 +00:00
|
|
|
.TP
|
2007-04-12 22:42:49 +00:00
|
|
|
*
|
getaddrinfo.3, setlocale.3, strchr.3, wctob.3, st.4, glob.7, locale.7, regex.7, standards.7, unicode.7, utf-8.7: Global fix: s/multi-/multi/
The tendency in English, as prescribed in style guides like
Chicago MoS, is towards removing hyphens after prefixes
like "multi-" etc.
Signed-off-by: Michael Kerrisk <mtk.manpages@gmail.com>
2010-01-16 17:47:55 +00:00
|
|
|
The first byte of a multibyte sequence which represents a single non-ASCII
|
2014-06-24 10:08:09 +00:00
|
|
|
UCS character is always in the range 0xc2 to 0xfd and indicates how long
|
getaddrinfo.3, setlocale.3, strchr.3, wctob.3, st.4, glob.7, locale.7, regex.7, standards.7, unicode.7, utf-8.7: Global fix: s/multi-/multi/
The tendency in English, as prescribed in style guides like
Chicago MoS, is towards removing hyphens after prefixes
like "multi-" etc.
Signed-off-by: Michael Kerrisk <mtk.manpages@gmail.com>
2010-01-16 17:47:55 +00:00
|
|
|
this multibyte sequence is.
|
|
|
|
All further bytes in a multibyte sequence
|
2007-04-12 22:42:49 +00:00
|
|
|
are in the range 0x80 to 0xbf.
|
|
|
|
This allows easy resynchronization and
|
2004-11-03 13:51:07 +00:00
|
|
|
makes the encoding stateless and robust against missing bytes.
|
|
|
|
.TP
|
|
|
|
*
|
2014-06-24 10:08:09 +00:00
|
|
|
UTF-8 encoded UCS characters may be up to six bytes long, however the
|
|
|
|
Unicode standard specifies no characters above 0x10ffff, so Unicode characters
|
intro.1, _syscall.2, access.2, arch_prctl.2, cacheflush.2, chown.2, clock_getres.2, clone.2, create_module.2, fcntl.2, flock.2, get_kernel_syms.2, get_robust_list.2, get_thread_area.2, getcpu.2, getpriority.2, getrlimit.2, getrusage.2, ioprio_set.2, kexec_load.2, madvise.2, mbind.2, migrate_pages.2, mknod.2, mmap.2, mount.2, move_pages.2, mprotect.2, open.2, pause.2, pciconfig_read.2, perf_event_open.2, prctl.2, ptrace.2, query_module.2, read.2, reboot.2, recv.2, s390_runtime_instr.2, sched_setscheduler.2, select_tut.2, send.2, set_mempolicy.2, setfsgid.2, setfsuid.2, sigaction.2, spu_create.2, spu_run.2, stime.2, swapon.2, syslog.2, timer_create.2, timer_getoverrun.2, times.2, tkill.2, umount.2, unimplemented.2, ustat.2, vm86.2, wait.2, abs.3, aio_read.3, aio_write.3, bsd_signal.3, catgets.3, clearenv.3, cmsg.3, dbopen.3, dirfd.3, dlopen.3, exec.3, fenv.3, ferror.3, fmemopen.3, fnmatch.3, fopen.3, futimes.3, getaddrinfo.3, getifaddrs.3, getipnodebyname.3, hsearch.3, if_nameindex.3, inet_pton.3, mblen.3, mbrlen.3, mbsrtowcs.3, mbtowc.3, mcheck.3, memfrob.3, mq_notify.3, netlink.3, posix_memalign.3, printf.3, pthread_attr_setscope.3, pthread_cleanup_push.3, pthread_kill_other_threads_np.3, pthread_self.3, pthread_setcancelstate.3, pthread_setconcurrency.3, raise.3, resolver.3, rpc.3, rtime.3, rtnetlink.3, scanf.3, setbuf.3, setnetgrent.3, shm_open.3, sigpause.3, sigset.3, sigwait.3, sockatmark.3, strcasecmp.3, strcmp.3, strdup.3, strftime.3, strptime.3, strsignal.3, strverscmp.3, sysv_signal.3, termios.3, wcrtomb.3, wcsnlen.3, wcsnrtombs.3, wcsrtombs.3, wctomb.3, wprintf.3, console_codes.4, cpuid.4, msr.4, rtc.4, sk98lin.4, st.4, tty.4, charmap.5, core.5, elf.5, hosts.equiv.5, proc.5, resolv.conf.5, services.5, slabinfo.5, arp.7, bootparam.7, capabilities.7, charsets.7, cpuset.7, ddp.7, epoll.7, feature_test_macros.7, futex.7, hier.7, icmp.7, inotify.7, ip.7, ipv6.7, man-pages.7, mdoc.7, mdoc.samples.7, netdevice.7, netlink.7, numa.7, packet.7, path_resolution.7, posixoptions.7, pthreads.7, raw.7, rtld-audit.7, rtnetlink.7, sem_overview.7, sigevent.7, socket.7, spufs.7, tcp.7, udp.7, unicode.7, uri.7, utf-8.7, intro.8, ldconfig.8, sync.8: Global fix: fix placement of word "only"
Signed-off-by: Michael Kerrisk <mtk.manpages@gmail.com>
2013-03-31 08:53:00 +00:00
|
|
|
can be only up to four bytes long in
|
2014-06-24 10:08:09 +00:00
|
|
|
UTF-8.
|
2007-06-15 20:16:04 +00:00
|
|
|
.SS Encoding
|
2007-04-12 22:42:49 +00:00
|
|
|
The following byte sequences are used to represent a character.
|
|
|
|
The sequence to be used depends on the UCS code number of the character:
|
2004-11-03 13:51:07 +00:00
|
|
|
.TP 0.4i
|
2005-07-06 07:41:37 +00:00
|
|
|
0x00000000 \- 0x0000007F:
|
2004-11-03 13:51:07 +00:00
|
|
|
.RI 0 xxxxxxx
|
|
|
|
.TP
|
2005-07-06 07:41:37 +00:00
|
|
|
0x00000080 \- 0x000007FF:
|
2007-04-12 22:42:49 +00:00
|
|
|
.RI 110 xxxxx
|
2004-11-03 13:51:07 +00:00
|
|
|
.RI 10 xxxxxx
|
|
|
|
.TP
|
2005-07-06 07:41:37 +00:00
|
|
|
0x00000800 \- 0x0000FFFF:
|
2004-11-03 13:51:07 +00:00
|
|
|
.RI 1110 xxxx
|
|
|
|
.RI 10 xxxxxx
|
|
|
|
.RI 10 xxxxxx
|
|
|
|
.TP
|
2005-07-06 07:41:37 +00:00
|
|
|
0x00010000 \- 0x001FFFFF:
|
2004-11-03 13:51:07 +00:00
|
|
|
.RI 11110 xxx
|
|
|
|
.RI 10 xxxxxx
|
|
|
|
.RI 10 xxxxxx
|
|
|
|
.RI 10 xxxxxx
|
|
|
|
.TP
|
2005-07-06 07:41:37 +00:00
|
|
|
0x00200000 \- 0x03FFFFFF:
|
2004-11-03 13:51:07 +00:00
|
|
|
.RI 111110 xx
|
|
|
|
.RI 10 xxxxxx
|
|
|
|
.RI 10 xxxxxx
|
|
|
|
.RI 10 xxxxxx
|
|
|
|
.RI 10 xxxxxx
|
|
|
|
.TP
|
2005-07-06 07:41:37 +00:00
|
|
|
0x04000000 \- 0x7FFFFFFF:
|
2004-11-03 13:51:07 +00:00
|
|
|
.RI 1111110 x
|
|
|
|
.RI 10 xxxxxx
|
|
|
|
.RI 10 xxxxxx
|
|
|
|
.RI 10 xxxxxx
|
|
|
|
.RI 10 xxxxxx
|
|
|
|
.RI 10 xxxxxx
|
|
|
|
.PP
|
|
|
|
The
|
|
|
|
.I xxx
|
|
|
|
bit positions are filled with the bits of the character code number in
|
2015-05-26 06:53:06 +00:00
|
|
|
binary representation, most significant bit first (big-endian).
|
getaddrinfo.3, setlocale.3, strchr.3, wctob.3, st.4, glob.7, locale.7, regex.7, standards.7, unicode.7, utf-8.7: Global fix: s/multi-/multi/
The tendency in English, as prescribed in style guides like
Chicago MoS, is towards removing hyphens after prefixes
like "multi-" etc.
Signed-off-by: Michael Kerrisk <mtk.manpages@gmail.com>
2010-01-16 17:47:55 +00:00
|
|
|
Only the shortest possible multibyte sequence
|
2004-11-03 13:51:07 +00:00
|
|
|
which can represent the code number of the character can be used.
|
|
|
|
.PP
|
2014-06-24 10:08:09 +00:00
|
|
|
The UCS code values 0xd800\(en0xdfff (UTF-16 surrogates) as well as 0xfffe and
|
2015-05-26 06:53:06 +00:00
|
|
|
0xffff (UCS noncharacters) should not appear in conforming UTF-8 streams. According
|
|
|
|
to RFC 3629 no point above U+10FFFF should be used, which limits characters to four
|
|
|
|
bytes.
|
2007-06-15 20:16:04 +00:00
|
|
|
.SS Example
|
2014-06-24 10:08:09 +00:00
|
|
|
The Unicode character 0xa9 = 1010 1001 (the copyright sign) is encoded
|
2004-11-03 13:51:07 +00:00
|
|
|
in UTF-8 as
|
|
|
|
.PP
|
|
|
|
.RS
|
|
|
|
11000010 10101001 = 0xc2 0xa9
|
|
|
|
.RE
|
|
|
|
.PP
|
|
|
|
and character 0x2260 = 0010 0010 0110 0000 (the "not equal" symbol) is
|
|
|
|
encoded as:
|
|
|
|
.PP
|
|
|
|
.RS
|
|
|
|
11100010 10001001 10100000 = 0xe2 0x89 0xa0
|
|
|
|
.RE
|
intro.1, time.1, _syscall.2, accept.2, capget.2, clone.2, execve.2, fcntl.2, intro.2, ioctl_list.2, ioprio_set.2, kill.2, mlock.2, nanosleep.2, perf_event_open.2, select.2, stat.2, times.2, ustat.2, vfork.2, wait.2, cfree.3, dbopen.3, dlopen.3, fenv.3, fmtmsg.3, gamma.3, getaddrinfo.3, gethostbyname.3, getnameinfo.3, getspnam.3, login.3, printf.3, regex.3, stdio.3, sysconf.3, termios.3, ttyslot.3, undocumented.3, wordexp.3, console_codes.4, initrd.4, mouse.4, random.4, st.4, tty_ioctl.4, wavelan.4, charmap.5, dir_colors.5, hosts.5, termcap.5, armscii-8.7, boot.7, bootparam.7, capabilities.7, charsets.7, ddp.7, futex.7, glob.7, ipv6.7, iso_8859-1.7, iso_8859-10.7, iso_8859-11.7, iso_8859-13.7, iso_8859-14.7, iso_8859-15.7, iso_8859-16.7, iso_8859-2.7, iso_8859-3.7, iso_8859-4.7, iso_8859-5.7, iso_8859-6.7, iso_8859-7.7, iso_8859-8.7, iso_8859-9.7, koi8-r.7, koi8-u.7, man.7, numa.7, path_resolution.7, pipe.7, posixoptions.7, pthreads.7, pty.7, rtnetlink.7, signal.7, time.7, udp.7, udplite.7, unicode.7, uri.7, utf-8.7: G;lobal fix: remove unneeded double quotes in .SS headings
Signed-off-by: Michael Kerrisk <mtk.manpages@gmail.com>
2013-02-24 18:02:18 +00:00
|
|
|
.SS Application notes
|
2014-06-24 10:08:09 +00:00
|
|
|
Users have to select a UTF-8 locale, for example with
|
2004-11-03 13:51:07 +00:00
|
|
|
.PP
|
|
|
|
.RS
|
|
|
|
export LANG=en_GB.UTF-8
|
|
|
|
.RE
|
|
|
|
.PP
|
2014-06-24 10:08:09 +00:00
|
|
|
in order to activate the UTF-8 support in applications.
|
2004-11-03 13:51:07 +00:00
|
|
|
.PP
|
|
|
|
Application software that has to be aware of the used character
|
|
|
|
encoding should always set the locale with for example
|
|
|
|
.PP
|
|
|
|
.RS
|
|
|
|
setlocale(LC_CTYPE, "")
|
|
|
|
.RE
|
|
|
|
.PP
|
|
|
|
and programmers can then test the expression
|
|
|
|
.PP
|
|
|
|
.RS
|
|
|
|
strcmp(nl_langinfo(CODESET), "UTF-8") == 0
|
|
|
|
.RE
|
|
|
|
.PP
|
2014-06-24 10:08:09 +00:00
|
|
|
to determine whether a UTF-8 locale has been selected and whether
|
2004-11-03 13:51:07 +00:00
|
|
|
therefore all plaintext standard input and output, terminal
|
|
|
|
communication, plaintext file content, filenames and environment
|
2014-06-24 10:08:09 +00:00
|
|
|
variables are encoded in UTF-8.
|
2004-11-03 13:51:07 +00:00
|
|
|
.PP
|
2014-06-24 10:08:09 +00:00
|
|
|
Programmers accustomed to single-byte encodings such as US-ASCII or ISO 8859
|
2004-11-03 13:51:07 +00:00
|
|
|
have to be aware that two assumptions made so far are no longer valid
|
2014-06-24 10:08:09 +00:00
|
|
|
in UTF-8 locales.
|
2007-04-12 22:42:49 +00:00
|
|
|
Firstly, a single byte does not necessarily correspond any
|
|
|
|
more to a single character.
|
2014-06-24 10:08:09 +00:00
|
|
|
Secondly, since modern terminal emulators in UTF-8
|
2004-11-03 13:51:07 +00:00
|
|
|
mode also support Chinese, Japanese, and Korean
|
2014-06-24 10:08:09 +00:00
|
|
|
double-width characters as well as nonspacing combining characters,
|
2004-11-03 13:51:07 +00:00
|
|
|
outputting a single character does not necessarily advance the cursor
|
2014-06-24 10:08:09 +00:00
|
|
|
by one position as it did in ASCII.
|
2004-11-03 13:51:07 +00:00
|
|
|
Library functions such as
|
|
|
|
.BR mbsrtowcs (3)
|
|
|
|
and
|
|
|
|
.BR wcswidth (3)
|
|
|
|
should be used today to count characters and cursor positions.
|
|
|
|
.PP
|
2014-06-24 10:08:09 +00:00
|
|
|
The official ESC sequence to switch from an ISO 2022
|
2004-11-03 13:51:07 +00:00
|
|
|
encoding scheme (as used for instance by VT100 terminals) to
|
2014-06-24 10:08:09 +00:00
|
|
|
UTF-8 is ESC % G
|
locale.1, memusage.1, pldd.1, _syscall.2, add_key.2, bind.2, bpf.2, chown.2, clone.2, copy_file_range.2, eventfd.2, execve.2, futex.2, getdents.2, getrlimit.2, ioctl_fat.2, ioctl_ns.2, kcmp.2, kexec_load.2, keyctl.2, listxattr.2, lseek.2, membarrier.2, memfd_create.2, mmap.2, mprotect.2, msgop.2, open_by_handle_at.2, perf_event_open.2, pipe.2, readdir.2, readlink.2, readv.2, recvmmsg.2, request_key.2, sched_setaffinity.2, seccomp.2, select.2, select_tut.2, sendmmsg.2, setns.2, signalfd.2, spu_run.2, stat.2, sysctl.2, tee.2, timer_create.2, timerfd_create.2, truncate.2, uname.2, unshare.2, userfaultfd.2, ustat.2, wait.2, CPU_SET.3, __ppc_get_timebase.3, argz_add.3, asprintf.3, backtrace.3, basename.3, bswap.3, bzero.3, cacos.3, cacosh.3, catan.3, catanh.3, catgets.3, clock_getcpuclockid.3, confstr.3, ctime.3, dl_iterate_phdr.3, dlinfo.3, duplocale.3, encrypt.3, end.3, endian.3, fgetws.3, fmemopen.3, fopencookie.3, fputws.3, frexp.3, ftw.3, get_nprocs_conf.3, get_phys_pages.3, getaddrinfo.3, getaddrinfo_a.3, getdate.3, getgrouplist.3, getifaddrs.3, getline.3, getlogin.3, getopt.3, getpass.3, getprotoent_r.3, getpwnam.3, getservent_r.3, getsubopt.3, glob.3, gnu_get_libc_version.3, hsearch.3, if_nameindex.3, index.3, inet.3, inet_net_pton.3, inet_pton.3, insque.3, iswblank.3, iswspace.3, makecontext.3, mallinfo.3, malloc_hook.3, malloc_info.3, mallopt.3, matherr.3, mbrtowc.3, mbsnrtowcs.3, mbsrtowcs.3, mbstowcs.3, mbtowc.3, mcheck.3, memchr.3, mq_getattr.3, mq_notify.3, newlocale.3, nl_langinfo.3, offsetof.3, perror.3, posix_spawn.3, printf.3, pthread_attr_init.3, pthread_cancel.3, pthread_cleanup_push.3, pthread_create.3, pthread_getattr_default_np.3, pthread_getattr_np.3, pthread_getcpuclockid.3, pthread_mutexattr_setrobust.3, pthread_setaffinity_np.3, pthread_setname_np.3, pthread_setschedparam.3, pthread_sigmask.3, qsort.3, rand.3, readdir.3, regex.3, rpmatch.3, rtime.3, scanf.3, sem_wait.3, setaliasent.3, setbuf.3, stpcpy.3, stpncpy.3, strcat.3, strchr.3, strcpy.3, strdup.3, strerror.3, strfromd.3, strftime.3, strlen.3, strnlen.3, strsep.3, strstr.3, strtok.3, strtol.3, strtoul.3, strverscmp.3, strxfrm.3, termios.3, tsearch.3, wcpcpy.3, wcpncpy.3, wcrtomb.3, wcscat.3, wcscpy.3, wcslen.3, wcsncat.3, wcsncmp.3, wcsncpy.3, wcsnlen.3, wcsnrtombs.3, wcsrtombs.3, wcsstr.3, wcstok.3, wcstombs.3, wcwidth.3, wprintf.3, console_codes.4, dsp56k.4, full.4, initrd.4, loop.4, vcs.4, charmap.5, core.5, elf.5, locale.5, proc.5, repertoiremap.5, sysfs.5, termcap.5, aio.7, bpf-helpers.7, cgroups.7, charsets.7, complex.7, fanotify.7, feature_test_macros.7, inotify.7, locale.7, man-pages.7, man.7, pkeys.7, pthreads.7, rtld-audit.7, sock_diag.7, unix.7, user_namespaces.7, utf-8.7: Use '\e' rather than '\\' to get a backslash
Quoting Branden:
*roff escape sequences may sometimes look like C escapes, but that
is misleading. *roff is in part a macro language and that means
recursive expansion to arbitrary depths.
You can get away with "\\" in a context where no macro expansion
is taking place, but try to spell a literal backslash this way in
the argument to a macro and you will likely be unhappy with
results.
Try viewing the attached file with "man -l".
"\e" is the preferred and portable way to get a portable "escape
literal" going back to CSTR #54, the original Bell Labs troff
paper.
groff(7) discusses the issue:
\\ reduces to a single backslash; useful to delay its
interpretation as escape character in copy mode. For a
printable backslash, use \e, or even better \[rs], to be
independent from the current escape character.
As of groff 1.22.4, groff_man(7) does as well:
\e Widely used in man pages to represent a backslash output
glyph. It works reliably as long as the .ec request is
not used, which should never happen in man pages, and it
is slightly more portable than the more exact ‘\(rs’
(“reverse solidus”) escape sequence.
People not concerned with portability to extremely old troffs should
probably just use \(rs (or \[rs]), as it means "the backslash
glyph", not "the glyph corresponding to whatever the current escape
character is".
Signed-off-by: Michael Kerrisk <mtk.manpages@gmail.com>
2019-02-27 11:57:17 +00:00
|
|
|
("\ex1b%G").
|
2007-04-12 22:42:49 +00:00
|
|
|
The corresponding return sequence from
|
locale.1, memusage.1, pldd.1, _syscall.2, add_key.2, bind.2, bpf.2, chown.2, clone.2, copy_file_range.2, eventfd.2, execve.2, futex.2, getdents.2, getrlimit.2, ioctl_fat.2, ioctl_ns.2, kcmp.2, kexec_load.2, keyctl.2, listxattr.2, lseek.2, membarrier.2, memfd_create.2, mmap.2, mprotect.2, msgop.2, open_by_handle_at.2, perf_event_open.2, pipe.2, readdir.2, readlink.2, readv.2, recvmmsg.2, request_key.2, sched_setaffinity.2, seccomp.2, select.2, select_tut.2, sendmmsg.2, setns.2, signalfd.2, spu_run.2, stat.2, sysctl.2, tee.2, timer_create.2, timerfd_create.2, truncate.2, uname.2, unshare.2, userfaultfd.2, ustat.2, wait.2, CPU_SET.3, __ppc_get_timebase.3, argz_add.3, asprintf.3, backtrace.3, basename.3, bswap.3, bzero.3, cacos.3, cacosh.3, catan.3, catanh.3, catgets.3, clock_getcpuclockid.3, confstr.3, ctime.3, dl_iterate_phdr.3, dlinfo.3, duplocale.3, encrypt.3, end.3, endian.3, fgetws.3, fmemopen.3, fopencookie.3, fputws.3, frexp.3, ftw.3, get_nprocs_conf.3, get_phys_pages.3, getaddrinfo.3, getaddrinfo_a.3, getdate.3, getgrouplist.3, getifaddrs.3, getline.3, getlogin.3, getopt.3, getpass.3, getprotoent_r.3, getpwnam.3, getservent_r.3, getsubopt.3, glob.3, gnu_get_libc_version.3, hsearch.3, if_nameindex.3, index.3, inet.3, inet_net_pton.3, inet_pton.3, insque.3, iswblank.3, iswspace.3, makecontext.3, mallinfo.3, malloc_hook.3, malloc_info.3, mallopt.3, matherr.3, mbrtowc.3, mbsnrtowcs.3, mbsrtowcs.3, mbstowcs.3, mbtowc.3, mcheck.3, memchr.3, mq_getattr.3, mq_notify.3, newlocale.3, nl_langinfo.3, offsetof.3, perror.3, posix_spawn.3, printf.3, pthread_attr_init.3, pthread_cancel.3, pthread_cleanup_push.3, pthread_create.3, pthread_getattr_default_np.3, pthread_getattr_np.3, pthread_getcpuclockid.3, pthread_mutexattr_setrobust.3, pthread_setaffinity_np.3, pthread_setname_np.3, pthread_setschedparam.3, pthread_sigmask.3, qsort.3, rand.3, readdir.3, regex.3, rpmatch.3, rtime.3, scanf.3, sem_wait.3, setaliasent.3, setbuf.3, stpcpy.3, stpncpy.3, strcat.3, strchr.3, strcpy.3, strdup.3, strerror.3, strfromd.3, strftime.3, strlen.3, strnlen.3, strsep.3, strstr.3, strtok.3, strtol.3, strtoul.3, strverscmp.3, strxfrm.3, termios.3, tsearch.3, wcpcpy.3, wcpncpy.3, wcrtomb.3, wcscat.3, wcscpy.3, wcslen.3, wcsncat.3, wcsncmp.3, wcsncpy.3, wcsnlen.3, wcsnrtombs.3, wcsrtombs.3, wcsstr.3, wcstok.3, wcstombs.3, wcwidth.3, wprintf.3, console_codes.4, dsp56k.4, full.4, initrd.4, loop.4, vcs.4, charmap.5, core.5, elf.5, locale.5, proc.5, repertoiremap.5, sysfs.5, termcap.5, aio.7, bpf-helpers.7, cgroups.7, charsets.7, complex.7, fanotify.7, feature_test_macros.7, inotify.7, locale.7, man-pages.7, man.7, pkeys.7, pthreads.7, rtld-audit.7, sock_diag.7, unix.7, user_namespaces.7, utf-8.7: Use '\e' rather than '\\' to get a backslash
Quoting Branden:
*roff escape sequences may sometimes look like C escapes, but that
is misleading. *roff is in part a macro language and that means
recursive expansion to arbitrary depths.
You can get away with "\\" in a context where no macro expansion
is taking place, but try to spell a literal backslash this way in
the argument to a macro and you will likely be unhappy with
results.
Try viewing the attached file with "man -l".
"\e" is the preferred and portable way to get a portable "escape
literal" going back to CSTR #54, the original Bell Labs troff
paper.
groff(7) discusses the issue:
\\ reduces to a single backslash; useful to delay its
interpretation as escape character in copy mode. For a
printable backslash, use \e, or even better \[rs], to be
independent from the current escape character.
As of groff 1.22.4, groff_man(7) does as well:
\e Widely used in man pages to represent a backslash output
glyph. It works reliably as long as the .ec request is
not used, which should never happen in man pages, and it
is slightly more portable than the more exact ‘\(rs’
(“reverse solidus”) escape sequence.
People not concerned with portability to extremely old troffs should
probably just use \(rs (or \[rs]), as it means "the backslash
glyph", not "the glyph corresponding to whatever the current escape
character is".
Signed-off-by: Michael Kerrisk <mtk.manpages@gmail.com>
2019-02-27 11:57:17 +00:00
|
|
|
UTF-8 to ISO 2022 is ESC % @ ("\ex1b%@").
|
2007-04-12 22:42:49 +00:00
|
|
|
Other ISO 2022 sequences (such as
|
2004-11-03 13:51:07 +00:00
|
|
|
for switching the G0 and G1 sets) are not applicable in UTF-8 mode.
|
2007-06-15 20:16:04 +00:00
|
|
|
.SS Security
|
2014-06-24 10:08:09 +00:00
|
|
|
The Unicode and UCS standards require that producers of UTF-8
|
2007-06-08 11:56:22 +00:00
|
|
|
shall use the shortest form possible, for example, producing a two-byte
|
2010-01-16 16:48:00 +00:00
|
|
|
sequence with first byte 0xc0 is nonconforming.
|
2014-06-24 10:08:09 +00:00
|
|
|
Unicode 3.1 has added the requirement that conforming programs must not accept
|
2007-04-12 22:42:49 +00:00
|
|
|
non-shortest forms in their input.
|
|
|
|
This is for security reasons: if
|
2004-11-03 13:51:07 +00:00
|
|
|
user input is checked for possible security violations, a program
|
2014-06-24 10:08:09 +00:00
|
|
|
might check only for the ASCII
|
2004-11-03 13:51:07 +00:00
|
|
|
version of "/../" or ";" or NUL and overlook that there are many
|
2014-06-24 10:08:09 +00:00
|
|
|
non-ASCII ways to represent these things in a non-shortest UTF-8
|
2004-11-03 13:51:07 +00:00
|
|
|
encoding.
|
2007-06-15 20:16:04 +00:00
|
|
|
.SS Standards
|
2012-04-29 22:24:06 +00:00
|
|
|
ISO/IEC 10646-1:2000, Unicode 3.1, RFC\ 3629, Plan 9.
|
2007-05-16 03:40:19 +00:00
|
|
|
.\" .SH AUTHOR
|
|
|
|
.\" Markus Kuhn <mgk25@cl.cam.ac.uk>
|
getent.1, intro.1, time.1, _exit.2, _syscall.2, accept.2, access.2, acct.2, adjtimex.2, alarm.2, alloc_hugepages.2, arch_prctl.2, bdflush.2, bind.2, brk.2, cacheflush.2, capget.2, chdir.2, chmod.2, chown.2, chroot.2, clock_getres.2, clock_nanosleep.2, clone.2, close.2, connect.2, create_module.2, delete_module.2, dup.2, epoll_create.2, epoll_ctl.2, epoll_wait.2, eventfd.2, execve.2, exit_group.2, faccessat.2, fchmodat.2, fchownat.2, fcntl.2, flock.2, fork.2, fstatat.2, fsync.2, futex.2, futimesat.2, get_kernel_syms.2, get_robust_list.2, get_thread_area.2, getcpu.2, getdents.2, getdomainname.2, getgid.2, getgroups.2, gethostname.2, getitimer.2, getpagesize.2, getpeername.2, getpid.2, getpriority.2, getresuid.2, getrlimit.2, getrusage.2, getsid.2, getsockname.2, getsockopt.2, gettid.2, gettimeofday.2, getuid.2, getunwind.2, getxattr.2, idle.2, init_module.2, inotify_add_watch.2, inotify_init.2, inotify_rm_watch.2, intro.2, io_cancel.2, io_destroy.2, io_getevents.2, io_setup.2, io_submit.2, ioctl.2, ioctl_list.2, ioperm.2, iopl.2, ioprio_set.2, ipc.2, kcmp.2, kill.2, killpg.2, link.2, linkat.2, listen.2, listxattr.2, llseek.2, lookup_dcookie.2, lseek.2, madvise.2, migrate_pages.2, mincore.2, mkdir.2, mkdirat.2, mknod.2, mknodat.2, mlock.2, mmap.2, mmap2.2, modify_ldt.2, mount.2, move_pages.2, mprotect.2, mq_getsetattr.2, mremap.2, msgctl.2, msgget.2, msgop.2, msync.2, nanosleep.2, nfsservctl.2, nice.2, open.2, openat.2, outb.2, pause.2, pciconfig_read.2, perf_event_open.2, perfmonctl.2, personality.2, pipe.2, pivot_root.2, poll.2, posix_fadvise.2, prctl.2, pread.2, process_vm_readv.2, ptrace.2, query_module.2, quotactl.2, read.2, readahead.2, readdir.2, readlink.2, readlinkat.2, readv.2, reboot.2, recv.2, remap_file_pages.2, removexattr.2, rename.2, renameat.2, rmdir.2, rt_sigqueueinfo.2, sched_get_priority_max.2, sched_rr_get_interval.2, sched_setaffinity.2, sched_setparam.2, sched_setscheduler.2, sched_yield.2, select.2, semctl.2, semget.2, semop.2, send.2, sendfile.2, set_thread_area.2, set_tid_address.2, seteuid.2, setfsgid.2, setfsuid.2, setgid.2, setpgid.2, setresuid.2, setreuid.2, setsid.2, setuid.2, setup.2, setxattr.2, shmctl.2, shmget.2, shmop.2, shutdown.2, sigaction.2, sigaltstack.2, signal.2, signalfd.2, sigpending.2, sigprocmask.2, sigreturn.2, sigsuspend.2, sigwaitinfo.2, socket.2, socketcall.2, socketpair.2, splice.2, stat.2, statfs.2, stime.2, swapon.2, symlink.2, symlinkat.2, sync.2, sync_file_range.2, sysctl.2, sysfs.2, sysinfo.2, syslog.2, tee.2, time.2, timerfd_create.2, times.2, tkill.2, truncate.2, umask.2, umount.2, uname.2, unimplemented.2, unlink.2, unlinkat.2, uselib.2, ustat.2, utime.2, utimensat.2, vfork.2, vhangup.2, vm86.2, vmsplice.2, wait.2, wait4.2, write.2, CPU_SET.3, INFINITY.3, MB_CUR_MAX.3, MB_LEN_MAX.3, __setfpucw.3, a64l.3, abort.3, abs.3, acos.3, acosh.3, addseverity.3, adjtime.3, aio_cancel.3, aio_error.3, aio_fsync.3, aio_read.3, aio_return.3, aio_suspend.3, aio_write.3, alloca.3, argz_add.3, asin.3, asinh.3, asprintf.3, assert.3, assert_perror.3, atan.3, atan2.3, atanh.3, atexit.3, atof.3, atoi.3, backtrace.3, basename.3, bcmp.3, bcopy.3, bindresvport.3, bsd_signal.3, bsearch.3, bstring.3, btowc.3, btree.3, byteorder.3, bzero.3, cabs.3, cacos.3, cacosh.3, canonicalize_file_name.3, carg.3, casin.3, casinh.3, catan.3, catanh.3, catgets.3, catopen.3, cbrt.3, ccos.3, ccosh.3, ceil.3, cerf.3, cexp.3, cexp2.3, cfree.3, cimag.3, clearenv.3, clock.3, clock_getcpuclockid.3, clog.3, clog10.3, clog2.3, closedir.3, cmsg.3, confstr.3, conj.3, copysign.3, cos.3, cosh.3, cpow.3, cproj.3, creal.3, crypt.3, csin.3, csinh.3, csqrt.3, ctan.3, ctanh.3, ctermid.3, ctime.3, daemon.3, dbopen.3, des_crypt.3, difftime.3, dirfd.3, div.3, dl_iterate_phdr.3, dlopen.3, dprintf.3, drand48.3, drand48_r.3, dysize.3, ecvt.3, ecvt_r.3, encrypt.3, end.3, endian.3, envz_add.3, erf.3, erfc.3, err.3, errno.3, error.3, ether_aton.3, euidaccess.3, exec.3, exit.3, exp.3, exp10.3, exp2.3, expm1.3, fabs.3, fclose.3, fcloseall.3, fdim.3, fenv.3, ferror.3, fexecve.3, fflush.3, ffs.3, fgetgrent.3, fgetpwent.3, fgetwc.3, fgetws.3, finite.3, flockfile.3, floor.3, fma.3, fmax.3, fmemopen.3, fmin.3, fmod.3, fmtmsg.3, fnmatch.3, fopen.3, fpathconf.3, fpclassify.3, fpurge.3, fputwc.3, fputws.3, fread.3, frexp.3, fseek.3, fseeko.3, ftime.3, ftok.3, fts.3, ftw.3, futimes.3, fwide.3, gamma.3, gcvt.3, getaddrinfo.3, getaddrinfo_a.3, getauxval.3, getcontext.3, getcwd.3, getdate.3, getdirentries.3, getdtablesize.3, getenv.3, getfsent.3, getgrent.3, getgrent_r.3, getgrnam.3, getgrouplist.3, gethostbyname.3, gethostid.3, getipnodebyname.3, getline.3, getloadavg.3, getlogin.3, getmntent.3, getnameinfo.3, getnetent.3, getnetent_r.3, getopt.3, getpass.3, getprotoent.3, getprotoent_r.3, getpt.3, getpw.3, getpwent.3, getpwent_r.3, getpwnam.3, getrpcent.3, getrpcent_r.3, getrpcport.3, gets.3, getservent.3, getservent_r.3, getspnam.3, getttyent.3, getumask.3, getusershell.3, getutent.3, getw.3, getwchar.3, glob.3, grantpt.3, gsignal.3, hash.3, hsearch.3, hypot.3, iconv.3, iconv_close.3, iconv_open.3, ilogb.3, index.3, inet.3, inet_ntop.3, inet_pton.3, infnan.3, initgroups.3, insque.3, intro.3, isalpha.3, isatty.3, isgreater.3, iswalnum.3, iswalpha.3, iswblank.3, iswcntrl.3, iswctype.3, iswdigit.3, iswgraph.3, iswlower.3, iswprint.3, iswpunct.3, iswspace.3, iswupper.3, iswxdigit.3, j0.3, key_setsecret.3, ldexp.3, lgamma.3, lio_listio.3, localeconv.3, lockf.3, log.3, log10.3, log1p.3, log2.3, logb.3, login.3, longjmp.3, lrint.3, lround.3, lsearch.3, lseek64.3, makecontext.3, makedev.3, malloc.3, malloc_hook.3, mblen.3, mbrlen.3, mbrtowc.3, mbsinit.3, mbsnrtowcs.3, mbsrtowcs.3, mbstowcs.3, mbtowc.3, memccpy.3, memchr.3, memcmp.3, memcpy.3, memfrob.3, memmem.3, memmove.3, mempcpy.3, memset.3, mkdtemp.3, mkfifo.3, mkfifoat.3, mkstemp.3, mktemp.3, modf.3, mpool.3, mq_close.3, mq_getattr.3, mq_notify.3, mq_open.3, mq_receive.3, mq_send.3, mq_unlink.3, mtrace.3, nan.3, netlink.3, nextafter.3, nl_langinfo.3, offsetof.3, on_exit.3, opendir.3, openpty.3, perror.3, popen.3, posix_fallocate.3, posix_memalign.3, posix_openpt.3, pow.3, pow10.3, printf.3, profil.3, program_invocation_name.3, psignal.3, pthread_kill_other_threads_np.3, ptsname.3, putenv.3, putgrent.3, putpwent.3, puts.3, putwchar.3, qecvt.3, qsort.3, queue.3, raise.3, rand.3, random.3, random_r.3, rcmd.3, re_comp.3, readdir.3, realpath.3, recno.3, regex.3, remainder.3, remove.3, remquo.3, resolver.3, rewinddir.3, rexec.3, rint.3, round.3, rpc.3, rpmatch.3, rtime.3, rtnetlink.3, scalb.3, scalbln.3, scandir.3, scandirat.3, scanf.3, seekdir.3, sem_close.3, sem_destroy.3, sem_getvalue.3, sem_init.3, sem_open.3, sem_post.3, sem_unlink.3, sem_wait.3, setaliasent.3, setbuf.3, setenv.3, setjmp.3, setlocale.3, setlogmask.3, setnetgrent.3, shm_open.3, siginterrupt.3, signbit.3, significand.3, sigpause.3, sigqueue.3, sigset.3, sigsetops.3, sigvec.3, sin.3, sincos.3, sinh.3, sleep.3, sockatmark.3, sqrt.3, statvfs.3, stdarg.3, stdin.3, stdio.3, stdio_ext.3, stpcpy.3, stpncpy.3, strcasecmp.3, strcat.3, strchr.3, strcmp.3, strcoll.3, strcpy.3, strdup.3, strerror.3, strfmon.3, strfry.3, strftime.3, string.3, strlen.3, strnlen.3, strpbrk.3, strptime.3, strsep.3, strsignal.3, strspn.3, strstr.3, strtod.3, strtoimax.3, strtok.3, strtol.3, strtoul.3, strverscmp.3, strxfrm.3, swab.3, sysconf.3, syslog.3, system.3, sysv_signal.3, tan.3, tanh.3, tcgetpgrp.3, tcgetsid.3, telldir.3, tempnam.3, termios.3, tgamma.3, timegm.3, timeradd.3, tmpfile.3, tmpnam.3, toascii.3, toupper.3, towctrans.3, towlower.3, towupper.3, trunc.3, tsearch.3, ttyname.3, ttyslot.3, tzset.3, ualarm.3, ulimit.3, ungetwc.3, unlocked_stdio.3, unlockpt.3, updwtmp.3, usleep.3, wcpcpy.3, wcpncpy.3, wcrtomb.3, wcscasecmp.3, wcscat.3, wcschr.3, wcscmp.3, wcscpy.3, wcscspn.3, wcsdup.3, wcslen.3, wcsncasecmp.3, wcsncat.3, wcsncmp.3, wcsncpy.3, wcsnlen.3, wcsnrtombs.3, wcspbrk.3, wcsrchr.3, wcsrtombs.3, wcsspn.3, wcsstr.3, wcstoimax.3, wcstok.3, wcstombs.3, wcswidth.3, wctob.3, wctomb.3, wctrans.3, wctype.3, wcwidth.3, wmemchr.3, wmemcmp.3, wmemcpy.3, wmemmove.3, wmemset.3, wordexp.3, wprintf.3, xcrypt.3, xdr.3, y0.3, cciss.4, console.4, console_codes.4, console_ioctl.4, dsp56k.4, fd.4, full.4, hd.4, hpsa.4, initrd.4, intro.4, lp.4, mem.4, mouse.4, null.4, pts.4, ram.4, random.4, rtc.4, sk98lin.4, st.4, tty.4, ttyS.4, tty_ioctl.4, vcs.4, wavelan.4, acct.5, charmap.5, dir_colors.5, filesystems.5, ftpusers.5, group.5, host.conf.5, hosts.5, hosts.equiv.5, intro.5, issue.5, locale.5, motd.5, networks.5, nologin.5, nscd.conf.5, passwd.5, proc.5, protocols.5, resolv.conf.5, rpc.5, securetty.5, services.5, shells.5, termcap.5, ttytype.5, utmp.5, armscii-8.7, arp.7, ascii.7, bootparam.7, capabilities.7, charsets.7, complex.7, cp1251.7, credentials.7, ddp.7, environ.7, epoll.7, fifo.7, futex.7, glob.7, hier.7, icmp.7, inotify.7, intro.7, ip.7, ipv6.7, iso_8859-1.7, iso_8859-10.7, iso_8859-11.7, iso_8859-13.7, iso_8859-14.7, iso_8859-15.7, iso_8859-16.7, iso_8859-2.7, iso_8859-3.7, iso_8859-4.7, iso_8859-5.7, iso_8859-6.7, iso_8859-7.7, iso_8859-8.7, iso_8859-9.7, koi8-r.7, koi8-u.7, locale.7, mailaddr.7, man.7, mq_overview.7, netdevice.7, netlink.7, numa.7, packet.7, path_resolution.7, pipe.7, posixoptions.7, pthreads.7, pty.7, raw.7, regex.7, rtld-audit.7, rtnetlink.7, sem_overview.7, shm_overview.7, sigevent.7, signal.7, socket.7, standards.7, suffixes.7, svipc.7, tcp.7, termio.7, time.7, udp.7, udplite.7, unicode.7, unix.7, uri.7, utf-8.7, x25.7, nscd.8, sync.8, tzselect.8, zdump.8, zic.8: Global fix: remove unneeded double quotes in .SH headings
Signed-off-by: Michael Kerrisk <mtk.manpages@gmail.com>
2013-02-24 18:01:36 +00:00
|
|
|
.SH SEE ALSO
|
2014-06-10 08:39:37 +00:00
|
|
|
.BR locale (1),
|
2004-11-03 13:51:07 +00:00
|
|
|
.BR nl_langinfo (3),
|
|
|
|
.BR setlocale (3),
|
|
|
|
.BR charsets (7),
|
|
|
|
.BR unicode (7)
|