diff --git a/usr.bin/split/split.1 b/usr.bin/split/split.1 index 6dba7489a83d..67e3c0cd448b 100644 --- a/usr.bin/split/split.1 +++ b/usr.bin/split/split.1 @@ -1,218 +1,234 @@ .\" 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. 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 .\" -.Dd April 18, 2023 +.Dd May 26, 2023 .Dt SPLIT 1 .Os .Sh NAME .Nm split .Nd split a file into pieces .Sh SYNOPSIS .Nm -.Op Fl d +.Op Fl cd .Op Fl l Ar line_count .Op Fl a Ar suffix_length .Op Ar file Op Ar prefix .Nm -.Op Fl d +.Op Fl cd .Fl b Ar byte_count Ns .Oo .Sm off .Cm K | k | M | m | G | g .Sm on .Oc .Op Fl a Ar suffix_length .Op Ar file Op Ar prefix .Nm -.Op Fl d +.Op Fl cd .Fl n Ar chunk_count .Op Fl a Ar suffix_length .Op Ar file Op Ar prefix .Nm -.Op Fl d +.Op Fl cd .Fl p Ar pattern .Op Fl a Ar suffix_length .Op Ar file Op Ar prefix .Sh DESCRIPTION The .Nm utility reads the given .Ar file and breaks it up into files of 1000 lines each (if no options are specified), leaving the .Ar file unchanged. 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 indent .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 Ns Oo .Sm off .Cm K | k | M | m | G | g .Sm on .Oc Create split files .Ar byte_count bytes in length. If .Cm k or .Cm K is appended to the number, the file is split into .Ar byte_count kilobyte pieces. If .Cm m or .Cm M is appended to the number, the file is split into .Ar byte_count megabyte pieces. If .Cm g or .Cm G is appended to the number, the file is split into .Ar byte_count gigabyte pieces. +.It Fl c +Continue creating files and do not overwrite existing +output files. .It Fl d Use a numeric suffix instead of a alphabetic suffix. .It Fl l Ar line_count Create split files .Ar line_count lines in length. .It Fl n Ar chunk_count Split file into .Ar chunk_count smaller files. The first n - 1 files will be of size (size of .Ar file / .Ar chunk_count ) and the last file will contain the remaining bytes. .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 Ns - Ns Li z . If .Fl a -is not specified, two letters are used as the suffix. +is not specified, two letters are used as the initial suffix. +If the output does not fit into the resulting number of files and the +.Fl d +flag is not specified, then the suffix length is automatically extended as +needed such that all output files continue to sort in lexical order. .Pp If the .Ar prefix argument is not specified, the file is split into lexically ordered files named with the prefix .Dq Li x and with suffixes as above. +.Pp +By default, +.Nm +will overwrite any existing output files. +If the +.Fl c +flag is specified, +.Nm +will instead create files with names that do not already exist. .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 EXAMPLES Split input into as many files as needed, so that each file contains at most 2 lines: .Bd -literal -offset indent $ echo -e "first line\\nsecond line\\nthird line\\nforth line" | split -l2 .Ed .Pp Split input in chunks of 10 bytes using numeric prefixes for file names. This generates two files of 10 bytes (x00 and x01) and a third file (x02) with the remaining 2 bytes: .Bd -literal -offset indent $ echo -e "This is 22 bytes long" | split -d -b10 .Ed .Pp Split input generating 6 files: .Bd -literal -offset indent $ echo -e "This is 22 bytes long" | split -n 6 .Ed .Pp Split input creating a new file every time a line matches the regular expression for a .Dq t followed by either .Dq a or .Dq u thus creating two files: .Bd -literal -offset indent $ echo -e "stack\\nstock\\nstuck\\nanother line" | split -p 't[au]' .Ed .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 . .Pp Before .Fx 14 , pattern and line matching only operated on lines shorter than 65,536 bytes. diff --git a/usr.bin/split/split.c b/usr.bin/split/split.c index 29ee0581d071..eeb7d663ecb1 100644 --- a/usr.bin/split/split.c +++ b/usr.bin/split/split.c @@ -1,401 +1,444 @@ /*- * SPDX-License-Identifier: BSD-3-Clause * * 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. 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 #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 #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #define DEFLINE 1000 /* Default num lines per file. */ static off_t bytecnt; /* Byte count to split on. */ static off_t chunks = 0; /* Chunks count to split into. */ +static bool clobber = true; /* Whether to overwrite existing output files. */ static long numlines; /* Line count to split on. */ static int file_open; /* If a file open. */ static int ifd = -1, ofd = -1; /* Input/output file descriptors. */ static char fname[MAXPATHLEN]; /* File name prefix. */ static regex_t rgx; static int pflag; static bool dflag; static long sufflen = 2; /* File name suffix length. */ +static int autosfx = 1; /* Whether to auto-extend the suffix length. */ static void newfile(void); static void split1(void); static void split2(void); static void split3(void); static void usage(void); int main(int argc, char **argv) { int ch; int error; char *ep, *p; setlocale(LC_ALL, ""); dflag = false; - while ((ch = getopt(argc, argv, "0123456789a:b:dl:n:p:")) != -1) + while ((ch = getopt(argc, argv, "0123456789a:b:cdl:n: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); + autosfx = 0; break; case 'b': /* Byte count. */ errno = 0; error = expand_number(optarg, &bytecnt); if (error == -1) errx(EX_USAGE, "%s: offset too large", optarg); break; + case 'c': /* Continue, don't overwrite output files. */ + clobber = false; + break; case 'd': /* Decimal suffix */ dflag = true; 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; case 'n': /* Chunks. */ if (!isdigit((unsigned char)optarg[0]) || (chunks = (size_t)strtoul(optarg, &ep, 10)) == 0 || *ep != '\0') { errx(EX_USAGE, "%s: illegal number of chunks", optarg); } break; case 'p': /* pattern matching. */ if (regcomp(&rgx, optarg, REG_EXTENDED|REG_NOSUB) != 0) errx(EX_USAGE, "%s: illegal regexp", optarg); pflag = 1; 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 || chunks != 0)) usage(); if (numlines == 0) numlines = DEFLINE; else if (bytecnt != 0 || chunks != 0) usage(); if (bytecnt && chunks) usage(); if (ifd == -1) /* Stdin by default. */ ifd = 0; if (bytecnt) { split1(); exit (0); } else if (chunks) { split3(); exit (0); } split2(); if (pflag) regfree(&rgx); exit(0); } /* * split1 -- * Split the input by bytes. */ static void split1(void) { static char bfr[MAXBSIZE]; off_t bcnt; char *C; ssize_t dist, len; int nfiles; nfiles = 0; for (bcnt = 0;;) switch ((len = read(ifd, bfr, sizeof(bfr)))) { case 0: exit(0); case -1: err(EX_IOERR, "read"); /* NOTREACHED */ default: if (!file_open) { if (!chunks || (nfiles < chunks)) { newfile(); nfiles++; } } 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) { if (!chunks || (nfiles < chunks)) { newfile(); nfiles++; } if (write(ofd, C, bytecnt) != bytecnt) err(EX_IOERR, "write"); } if (len != 0) { if (!chunks || (nfiles < chunks)) { newfile(); nfiles++; } 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. */ static void split2(void) { char *buf; size_t bufsize; ssize_t len; long lcnt = 0; FILE *infp; buf = NULL; bufsize = 0; /* 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 ((errno = 0, len = getline(&buf, &bufsize, infp)) > 0) { /* 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, buf, 0, &pmatch, REG_STARTEND) == 0) newfile(); } else if (lcnt++ == numlines) { newfile(); lcnt = 1; } /* Open output file if needed */ if (!file_open) newfile(); /* Write out line */ if (write(ofd, buf, len) != len) err(EX_IOERR, "write"); } /* EOF or error? */ if ((len == -1 && errno != 0) || ferror(infp)) err(EX_IOERR, "read"); else exit(0); } /* * split3 -- * Split the input into specified number of chunks */ static void split3(void) { struct stat sb; if (fstat(ifd, &sb) == -1) { err(1, "stat"); /* NOTREACHED */ } if (chunks > sb.st_size) { errx(1, "can't split into more than %d files", (int)sb.st_size); /* NOTREACHED */ } bytecnt = sb.st_size / chunks; split1(); } /* * newfile -- * Open a new output file. */ static void newfile(void) { long i, maxfiles, tfnum; static long fnum; static char *fpnt; char beg, end; int pattlen; + int flags = O_WRONLY | O_CREAT | O_TRUNC; + + if (!clobber) + flags |= O_EXCL; if (ofd == -1) { if (fname[0] == '\0') { fname[0] = 'x'; fpnt = fname + 1; } else { fpnt = fname + strlen(fname); } - ofd = fileno(stdout); - } + } else if (close(ofd) != 0) + err(1, "%s", fname); + again: if (dflag) { beg = '0'; end = '9'; } else { beg = 'a'; end = 'z'; } pattlen = end - beg + 1; + /* + * If '-a' is not specified, then we automatically expand the + * suffix length to accomodate splitting all input. We do this + * by moving the suffix pointer (fpnt) forward and incrementing + * sufflen by one, thereby yielding an additional two characters + * and allowing all output files to sort such that 'cat *' yields + * the input in order. I.e., the order is '... xyy xyz xzaaa + * xzaab ... xzyzy, xzyzz, xzzaaaa, xzzaaab' and so on. + */ + if (!dflag && autosfx && (fpnt[0] == 'y') && + strspn(fpnt+1, "z") == strlen(fpnt+1)) { + fpnt = fname + strlen(fname) - sufflen; + fpnt[sufflen + 2] = '\0'; + fpnt[0] = end; + fpnt[1] = beg; + + /* Basename | Suffix + * before: + * x | yz + * after: + * xz | a.. */ + fpnt++; + sufflen++; + + /* Reset so we start back at all 'a's in our extended suffix. */ + tfnum = 0; + fnum = 0; + } + /* maxfiles = pattlen^sufflen, but don't use libm. */ for (maxfiles = 1, i = 0; i < sufflen; i++) if (LONG_MAX / pattlen < maxfiles) errx(EX_USAGE, "suffix is too long (max %ld)", i); else maxfiles *= pattlen; if (fnum == maxfiles) errx(EX_DATAERR, "too many files"); /* Generate suffix of sufflen letters */ tfnum = fnum; i = sufflen - 1; do { fpnt[i] = tfnum % pattlen + beg; tfnum /= pattlen; } while (i-- > 0); fpnt[sufflen] = '\0'; ++fnum; - if (!freopen(fname, "w", stdout)) + if ((ofd = open(fname, flags, DEFFILEMODE)) < 0) { + if (!clobber && errno == EEXIST) + goto again; err(EX_IOERR, "%s", fname); + } file_open = 1; } static void usage(void) { (void)fprintf(stderr, -"usage: split [-d] [-l line_count] [-a suffix_length] [file [prefix]]\n" -" split [-d] -b byte_count[K|k|M|m|G|g] [-a suffix_length] [file [prefix]]\n" -" split [-d] -n chunk_count [-a suffix_length] [file [prefix]]\n" -" split [-d] -p pattern [-a suffix_length] [file [prefix]]\n"); +"usage: split [-cd] [-l line_count] [-a suffix_length] [file [prefix]]\n" +" split [-cd] -b byte_count[K|k|M|m|G|g] [-a suffix_length] [file [prefix]]\n" +" split [-cd] -n chunk_count [-a suffix_length] [file [prefix]]\n" +" split [-cd] -p pattern [-a suffix_length] [file [prefix]]\n"); exit(EX_USAGE); }