diff options
author | Cameron Katri <me@cameronkatri.com> | 2021-05-09 14:20:58 -0400 |
---|---|---|
committer | Cameron Katri <me@cameronkatri.com> | 2021-05-09 14:20:58 -0400 |
commit | 5fd83771641d15c418f747bd343ba6738d3875f7 (patch) | |
tree | 5abf0f78f680d9837dbd93d4d4c3933bb7509599 /text_cmds/split | |
download | apple_cmds-5fd83771641d15c418f747bd343ba6738d3875f7.tar.gz apple_cmds-5fd83771641d15c418f747bd343ba6738d3875f7.tar.zst apple_cmds-5fd83771641d15c418f747bd343ba6738d3875f7.zip |
Import macOS userland
adv_cmds-176
basic_cmds-55
bootstrap_cmds-116.100.1
developer_cmds-66
diskdev_cmds-667.40.1
doc_cmds-53.60.1
file_cmds-321.40.3
mail_cmds-35
misc_cmds-34
network_cmds-606.40.1
patch_cmds-17
remote_cmds-63
shell_cmds-216.60.1
system_cmds-880.60.2
text_cmds-106
Diffstat (limited to 'text_cmds/split')
-rw-r--r-- | text_cmds/split/split.1 | 142 | ||||
-rw-r--r-- | text_cmds/split/split.c | 342 |
2 files changed, 484 insertions, 0 deletions
diff --git a/text_cmds/split/split.1 b/text_cmds/split/split.1 new file mode 100644 index 0000000..39818e0 --- /dev/null +++ b/text_cmds/split/split.1 @@ -0,0 +1,142 @@ +.\" Copyright (c) 1990, 1991, 1993, 1994 +.\" The Regents of the University of California. All rights reserved. +.\" +.\" Redistribution and use in source and binary forms, with or without +.\" modification, are permitted provided that the following conditions +.\" are met: +.\" 1. Redistributions of source code must retain the above copyright +.\" notice, this list of conditions and the following disclaimer. +.\" 2. Redistributions in binary form must reproduce the above copyright +.\" notice, this list of conditions and the following disclaimer in the +.\" documentation and/or other materials provided with the distribution. +.\" 3. All advertising materials mentioning features or use of this software +.\" must display the following acknowledgement: +.\" This product includes software developed by the University of +.\" California, Berkeley and its contributors. +.\" 4. Neither the name of the University nor the names of its contributors +.\" may be used to endorse or promote products derived from this software +.\" without specific prior written permission. +.\" +.\" THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND +.\" ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE +.\" IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE +.\" ARE DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE +.\" FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL +.\" DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS +.\" OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) +.\" HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT +.\" LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY +.\" OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF +.\" SUCH DAMAGE. +.\" +.\" @(#)split.1 8.3 (Berkeley) 4/16/94 +.\" $FreeBSD: src/usr.bin/split/split.1,v 1.17 2005/08/30 12:48:28 tjr Exp $ +.\" +.Dd August 21, 2005 +.Dt SPLIT 1 +.Os +.Sh NAME +.Nm split +.Nd split a file into pieces +.Sh SYNOPSIS +.Nm +.Op Fl a Ar suffix_length +.Op Fl b Ar byte_count[k|m] +.Op Fl l Ar line_count +.Op Fl p Ar pattern +.Op Ar file Op Ar name +.Sh DESCRIPTION +The +.Nm +utility reads the given +.Ar file +and breaks it up into files of 1000 lines each. +If +.Ar file +is a single dash +.Pq Sq Fl +or absent, +.Nm +reads from the standard input. +.Pp +The options are as follows: +.Bl -tag -width Ds +.It Fl a Ar suffix_length +Use +.Ar suffix_length +letters to form the suffix of the file name. +.It Fl b Ar byte_count[k|m] +Create smaller files +.Ar byte_count +bytes in length. +If +.Dq Li k +is appended to the number, the file is split into +.Ar byte_count +kilobyte pieces. +If +.Dq Li m +is appended to the number, the file is split into +.Ar byte_count +megabyte pieces. +.It Fl l Ar line_count +Create smaller files +.Ar n +lines in length. +.It Fl p Ar pattern +The file is split whenever an input line matches +.Ar pattern , +which is interpreted as an extended regular expression. +The matching line will be the first line of the next output file. +This option is incompatible with the +.Fl b +and +.Fl l +options. +.El +.Pp +If additional arguments are specified, the first is used as the name +of the input file which is to be split. +If a second additional argument is specified, it is used as a prefix +for the names of the files into which the file is split. +In this case, each file into which the file is split is named by the +prefix followed by a lexically ordered suffix using +.Ar suffix_length +characters in the range +.Dq Li a-z . +If +.Fl a +is not specified, two letters are used as the suffix. +.Pp +If the +.Ar name +argument is not specified, the file is split into lexically ordered +files named with the prefix +.Dq Li x +and with suffixes as above. +.Sh ENVIRONMENT +The +.Ev LANG , LC_ALL , LC_CTYPE +and +.Ev LC_COLLATE +environment variables affect the execution of +.Nm +as described in +.Xr environ 7 . +.Sh EXIT STATUS +.Ex -std +.Sh SEE ALSO +.Xr csplit 1 , +.Xr re_format 7 +.Sh STANDARDS +The +.Nm +utility conforms to +.St -p1003.1-2001 . +.Sh HISTORY +A +.Nm +command appeared in +.At v3 . +.Sh BUGS +The maximum line length for matching patterns is 65536. diff --git a/text_cmds/split/split.c b/text_cmds/split/split.c new file mode 100644 index 0000000..3c47a18 --- /dev/null +++ b/text_cmds/split/split.c @@ -0,0 +1,342 @@ +/* + * Copyright (c) 1987, 1993, 1994 + * The Regents of the University of California. All rights reserved. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions + * are met: + * 1. Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * 2. Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in the + * documentation and/or other materials provided with the distribution. + * 3. All advertising materials mentioning features or use of this software + * must display the following acknowledgement: + * This product includes software developed by the University of + * California, Berkeley and its contributors. + * 4. Neither the name of the University nor the names of its contributors + * may be used to endorse or promote products derived from this software + * without specific prior written permission. + * + * THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND + * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE + * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE + * ARE DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE + * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL + * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS + * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) + * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT + * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY + * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF + * SUCH DAMAGE. + */ + +#include <sys/cdefs.h> +__FBSDID("$FreeBSD: src/usr.bin/split/split.c,v 1.17 2005/08/30 12:32:18 tjr Exp $"); + +#ifndef lint +static const char copyright[] = +"@(#) Copyright (c) 1987, 1993, 1994\n\ + The Regents of the University of California. All rights reserved.\n"; +#endif + +#ifndef lint +static const char sccsid[] = "@(#)split.c 8.2 (Berkeley) 4/16/94"; +#endif + +#include <sys/param.h> + +#include <ctype.h> +#include <err.h> +#include <errno.h> +#include <fcntl.h> +#include <inttypes.h> +#include <limits.h> +#include <locale.h> +#include <stdint.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <unistd.h> +#include <regex.h> +#include <sysexits.h> + +#define DEFLINE 1000 /* Default num lines per file. */ + +off_t bytecnt; /* Byte count to split on. */ +long numlines; /* Line count to split on. */ +int file_open; /* If a file open. */ +int ifd = -1, ofd = -1; /* Input/output file descriptors. */ +char bfr[MAXBSIZE]; /* I/O buffer. */ +char fname[MAXPATHLEN]; /* File name prefix. */ +regex_t rgx; +int pflag; +long sufflen = 2; /* File name suffix length. */ + +void newfile(void); +void split1(void); +void split2(void); +static void usage(void); + +int +main(int argc, char **argv) +{ + intmax_t bytecnti; + long scale; + int ch; + char *ep, *p; + + setlocale(LC_ALL, ""); + + while ((ch = getopt(argc, argv, "0123456789a:b:l:p:")) != -1) + switch (ch) { + case '0': case '1': case '2': case '3': case '4': + case '5': case '6': case '7': case '8': case '9': + /* + * Undocumented kludge: split was originally designed + * to take a number after a dash. + */ + if (numlines == 0) { + p = argv[optind - 1]; + if (p[0] == '-' && p[1] == ch && !p[2]) + numlines = strtol(++p, &ep, 10); + else + numlines = + strtol(argv[optind] + 1, &ep, 10); + if (numlines <= 0 || *ep) + errx(EX_USAGE, + "%s: illegal line count", optarg); + } + break; + case 'a': /* Suffix length */ + if ((sufflen = strtol(optarg, &ep, 10)) <= 0 || *ep) + errx(EX_USAGE, + "%s: illegal suffix length", optarg); + break; + case 'b': /* Byte count. */ + errno = 0; + if ((bytecnti = strtoimax(optarg, &ep, 10)) <= 0 || + (*ep != '\0' && *ep != 'k' && *ep != 'm') || + errno != 0) + errx(EX_USAGE, + "%s: illegal byte count", optarg); + if (*ep == 'k') + scale = 1024; + else if (*ep == 'm') + scale = 1024 * 1024; + else + scale = 1; + if (bytecnti > OFF_MAX / scale) + errx(EX_USAGE, "%s: offset too large", optarg); + bytecnt = (off_t)(bytecnti * scale); + break; + case 'p' : /* pattern matching. */ + if (regcomp(&rgx, optarg, REG_EXTENDED|REG_NOSUB) != 0) + errx(EX_USAGE, "%s: illegal regexp", optarg); + pflag = 1; + break; + case 'l': /* Line count. */ + if (numlines != 0) + usage(); + if ((numlines = strtol(optarg, &ep, 10)) <= 0 || *ep) + errx(EX_USAGE, + "%s: illegal line count", optarg); + break; + default: + usage(); + } + argv += optind; + argc -= optind; + + if (*argv != NULL) { /* Input file. */ + if (strcmp(*argv, "-") == 0) + ifd = STDIN_FILENO; + else if ((ifd = open(*argv, O_RDONLY, 0)) < 0) + err(EX_NOINPUT, "%s", *argv); + ++argv; + } + if (*argv != NULL) /* File name prefix. */ + if (strlcpy(fname, *argv++, sizeof(fname)) >= sizeof(fname)) + errx(EX_USAGE, "file name prefix is too long"); + if (*argv != NULL) + usage(); + + if (strlen(fname) + (unsigned long)sufflen >= sizeof(fname)) + errx(EX_USAGE, "suffix is too long"); + if (pflag && (numlines != 0 || bytecnt != 0)) + usage(); + + if (numlines == 0) + numlines = DEFLINE; + else if (bytecnt != 0) + usage(); + + if (ifd == -1) /* Stdin by default. */ + ifd = 0; + + if (bytecnt) { + split1(); + exit (0); + } + split2(); + if (pflag) + regfree(&rgx); + exit(0); +} + +/* + * split1 -- + * Split the input by bytes. + */ +void +split1(void) +{ + off_t bcnt; + char *C; + ssize_t dist, len; + + for (bcnt = 0;;) + switch ((len = read(ifd, bfr, MAXBSIZE))) { + case 0: + exit(0); + case -1: + err(EX_IOERR, "read"); + /* NOTREACHED */ + default: + if (!file_open) + newfile(); + if (bcnt + len >= bytecnt) { + dist = bytecnt - bcnt; + if (write(ofd, bfr, dist) != dist) + err(EX_IOERR, "write"); + len -= dist; + for (C = bfr + dist; len >= bytecnt; + len -= bytecnt, C += bytecnt) { + newfile(); + if (write(ofd, + C, bytecnt) != bytecnt) + err(EX_IOERR, "write"); + } + if (len != 0) { + newfile(); + if (write(ofd, C, len) != len) + err(EX_IOERR, "write"); + } else + file_open = 0; + bcnt = len; + } else { + bcnt += len; + if (write(ofd, bfr, len) != len) + err(EX_IOERR, "write"); + } + } +} + +/* + * split2 -- + * Split the input by lines. + */ +void +split2(void) +{ + long lcnt = 0; + FILE *infp; + + /* Stick a stream on top of input file descriptor */ + if ((infp = fdopen(ifd, "r")) == NULL) + err(EX_NOINPUT, "fdopen"); + + /* Process input one line at a time */ + while (fgets(bfr, sizeof(bfr), infp) != NULL) { + const int len = strlen(bfr); + + /* If line is too long to deal with, just write it out */ + if (bfr[len - 1] != '\n') + goto writeit; + + /* Check if we need to start a new file */ + if (pflag) { + regmatch_t pmatch; + + pmatch.rm_so = 0; + pmatch.rm_eo = len - 1; + if (regexec(&rgx, bfr, 0, &pmatch, REG_STARTEND) == 0) + newfile(); + } else if (lcnt++ == numlines) { + newfile(); + lcnt = 1; + } + +writeit: + /* Open output file if needed */ + if (!file_open) + newfile(); + + /* Write out line */ + if (write(ofd, bfr, len) != len) + err(EX_IOERR, "write"); + } + + /* EOF or error? */ + if (ferror(infp)) + err(EX_IOERR, "read"); + else + exit(0); +} + +/* + * newfile -- + * Open a new output file. + */ +void +newfile(void) +{ + long i, maxfiles, tfnum; + static long fnum; + static int defname; + static char *fpnt; + + if (ofd == -1) { + if (fname[0] == '\0') { + fname[0] = 'x'; + fpnt = fname + 1; + defname = 1; + } else { + fpnt = fname + strlen(fname); + defname = 0; + } + ofd = fileno(stdout); + } + + /* maxfiles = 26^sufflen, but don't use libm. */ + for (maxfiles = 1, i = 0; i < sufflen; i++) + if ((maxfiles *= 26) <= 0) + errx(EX_USAGE, "suffix is too long (max %ld)", i); + + if (fnum == maxfiles) + errx(EX_DATAERR, "too many files"); + + /* Generate suffix of sufflen letters */ + tfnum = fnum; + i = sufflen - 1; + do { + fpnt[i] = tfnum % 26 + 'a'; + tfnum /= 26; + } while (i-- > 0); + fpnt[sufflen] = '\0'; + + ++fnum; + if (!freopen(fname, "w", stdout)) + err(EX_IOERR, "%s", fname); + file_open = 1; +} + +static void +usage(void) +{ + (void)fprintf(stderr, +"usage: split [-a sufflen] [-b byte_count] [-l line_count] [-p pattern]\n"); + (void)fprintf(stderr, +" [file [prefix]]\n"); + exit(EX_USAGE); +} |