rs-20140609/Makefile010064400000000000000000000001401020120127100107510ustar00# $OpenBSD: Makefile,v 1.2 1996/06/26 05:38:46 deraadt Exp $ PROG= rs .include rs-20140609/rs.1010064400000000000000000000232141234540002600100400ustar00.\" $MirOS: src/usr.bin/rs/rs.1,v 1.4 2014/06/09 18:41:40 tg Exp $ .\" $OpenBSD: rs.1,v 1.16 2014/01/20 05:07:48 schwarze Exp $ .\" $FreeBSD: src/usr.bin/rs/rs.1,v 1.4 1999/08/28 01:05:21 peter Exp $ .\"- .\" Copyright (c) 1993 .\" The Regents of the University of California. All rights reserved. .\" Copyright (c) 2008, 2009, 2010, 2012 .\" Thorsten “mirabilos” Glaser .\" .\" 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. .\" .\" @(#)rs.1 8.2 (Berkeley) 12/30/93 .\" .\"- .\" Try to make GNU groff and AT&T nroff more compatible .\" * ` generates ‘ in gnroff, so use \` .\" * ' generates ’ in gnroff, \' generates ´, so use \*(aq .\" * - generates ‐ in gnroff, \- generates −, so .tr it to - .\" thus use - for hyphens and \- for minus signs and option dashes .\" * ~ is size-reduced and placed atop in groff, so use \*(TI .\" * ^ is size-reduced and placed atop in groff, so use \*(ha .\" * \(en does not work in nroff, so use \*(en .\" * <>| are problematic, so redefine and use \*(Lt\*(Gt\*(Ba .\" Also make sure to use \& especially with two-letter words. .\" The section after the "doc" macropackage has been loaded contains .\" additional code to convene between the UCB mdoc macropackage (and .\" its variant as BSD mdoc in groff) and the GNU mdoc macropackage. .\" .ie \n(.g \{\ . if \*[.T]ascii .tr \-\N'45' . if \*[.T]latin1 .tr \-\N'45' . if \*[.T]utf8 .tr \-\N'45' . ds <= \[<=] . ds >= \[>=] . ds Rq \[rq] . ds Lq \[lq] . ds sL \(aq . ds sR \(aq . if \*[.T]utf8 .ds sL ` . if \*[.T]ps .ds sL ` . if \*[.T]utf8 .ds sR ' . if \*[.T]ps .ds sR ' . ds aq \(aq . ds TI \(ti . ds ha \(ha . ds en \(en .\} .el \{\ . ds aq ' . ds TI ~ . ds ha ^ . ds en \(em .\} .\" .\" Implement .Dd with the Mdocdate RCS keyword .\" .rn Dd xD .de Dd .ie \\$1$Mdocdate: \{\ . xD \\$2 \\$3, \\$4 .\} .el .xD \\$1 \\$2 \\$3 \\$4 \\$5 \\$6 \\$7 \\$8 .. .\" .\" .Dd must come before definition of .Mx, because when called .\" with -mandoc, it might implement .Mx itself, but we want to .\" use our own definition. And .Dd must come *first*, always. .\" .Dd $Mdocdate: June 9 2014 $ .\" .\" Check which macro package we use, and do other -mdoc setup. .\" .ie \n(.g \{\ . if \*[.T]utf8 .tr \[la]\*(Lt . if \*[.T]utf8 .tr \[ra]\*(Gt . ie d volume-ds-1 .ds tT gnu . el .ds tT bsd .\} .el .ds tT ucb .\" .\" Implement .Mx (MirBSD) .\" .ie "\*(tT"gnu" \{\ . eo . de Mx . nr curr-font \n[.f] . nr curr-size \n[.ps] . ds str-Mx \f[\n[curr-font]]\s[\n[curr-size]u] . ds str-Mx1 \*[Tn-font-size]\%MirOS\*[str-Mx] . if !\n[arg-limit] \ . if \n[.$] \{\ . ds macro-name Mx . parse-args \$@ . \} . if (\n[arg-limit] > \n[arg-ptr]) \{\ . nr arg-ptr +1 . ie (\n[type\n[arg-ptr]] == 2) \ . as str-Mx1 \~\*[arg\n[arg-ptr]] . el \ . nr arg-ptr -1 . \} . ds arg\n[arg-ptr] "\*[str-Mx1] . nr type\n[arg-ptr] 2 . ds space\n[arg-ptr] "\*[space] . nr num-args (\n[arg-limit] - \n[arg-ptr]) . nr arg-limit \n[arg-ptr] . if \n[num-args] \ . parse-space-vector . print-recursive .. . ec . ds sP \s0 . ds tN \*[Tn-font-size] .\} .el \{\ . de Mx . nr cF \\n(.f . nr cZ \\n(.s . ds aa \&\f\\n(cF\s\\n(cZ . if \\n(aC==0 \{\ . ie \\n(.$==0 \&MirOS\\*(aa . el .aV \\$1 \\$2 \\$3 \\$4 \\$5 \\$6 \\$7 \\$8 \\$9 . \} . if \\n(aC>\\n(aP \{\ . nr aP \\n(aP+1 . ie \\n(C\\n(aP==2 \{\ . as b1 \&MirOS\ #\&\\*(A\\n(aP\\*(aa . ie \\n(aC>\\n(aP \{\ . nr aP \\n(aP+1 . nR . \} . el .aZ . \} . el \{\ . as b1 \&MirOS\\*(aa . nR . \} . \} .. .\} .\"- .Dt RS 1 .Os .Sh NAME .Nm rs .Nd reshape a data array .Sh SYNOPSIS .Nm rs .Op Fl CcSs Ns Op Ar x .Op Fl GgKkw Ar N .Op Fl EeHhjmnTtyz .Op Ar rows Op Ar cols .Sh DESCRIPTION .Nm reads the standard input, interpreting each line as a row of blank-separated entries in an array, transforms the array according to the options, and writes it on the standard output. With no arguments it transforms stream input into a columnar format convenient for terminal viewing. .Pp The shape of the input array is deduced from the number of lines and the number of columns on the first line. If that shape is inconvenient, a more useful one might be obtained by skipping some of the input with the .Fl k option. Other options control interpretation of the input columns. .Pp The shape of the output array is influenced by the .Ar rows and .Ar cols specifications, which should be positive integers. If only one of them is a positive integer, .Nm computes a value for the other which will accommodate all of the data. When necessary, missing data are supplied in a manner specified by the options and surplus data are deleted. There are options to control presentation of the output columns, including transposition of the rows and columns. .Pp The options are as follows: .Bl -tag -width Ds .It Fl C Ns Op Ar x Output columns are delimited by the single character .Ar x . A missing .Ar x is taken to be .Ql \*(haI . .It Fl c Ns Op Ar x Input columns are delimited by the single character .Ar x . A missing .Ar x is taken to be .Ql \*(haI . .It Fl E Consider each character of input as an array entry. .It Fl e Consider each line of input as an array entry. .It Fl G Ns Ar N The gutter width has .Ar N percent of the maximum column width added to it. .It Fl g Ns Ar N The gutter width (inter-column space), normally 2, is taken to be .Ar N . .It Fl H Like .Fl h , but also print the length of each line. .It Fl h Print the shape of the input array and do nothing else. The shape is just the number of lines and the number of entries on the first line. .It Fl j Right adjust entries within columns. .It Fl K Ns Ar N Like .Fl k , but print the ignored lines. .It Fl k Ns Ar N Ignore the first .Ar N lines of input. .It Fl m Do not trim excess delimiters from the ends of the output array. .It Fl n On lines having fewer entries than the first line, use null entries to pad out the line. Normally, missing entries are taken from the next line of input. .It Fl S Ns Op Ar x Like .Fl C , but padded strings of .Ar x are delimiters. .It Fl s Ns Op Ar x Like .Fl c , but maximal strings of .Ar x are delimiters. .It Fl T Print the pure transpose of the input, ignoring any .Ar rows or .Ar cols specification. .It Fl t Fill in the rows of the output array using the columns of the input array, that is, transpose the input while honoring any .Ar rows and .Ar cols specifications. .It Fl w Ns Ar N The width of the display, normally 80, is taken to be the positive integer .Ar N . .It Fl y If there are too few entries to make up the output dimensions, pad the output by recycling the input from the beginning. Normally, the output is padded with blanks. .It Fl z Shrink column widths to fit the largest entries appearing in them. .El .Pp With no arguments, .Nm transposes its input, and assumes one array entry per input line unless the first non-ignored line is longer than the display width. Option letters which take numerical arguments interpret a missing number as zero unless otherwise indicated. .Sh EXAMPLES .Nm can be used as a filter to convert the stream output of certain programs (e.g., .Xr spell 1 , .Xr du 1 , .Xr file 1 , .Xr look 1 , .Xr nm 1 , .Xr who 1 , and .Xr wc 1 ) into a convenient .Dq window format, as in .Bd -literal -offset indent $ who \*(Ba rs .Ed .Pp This function has been incorporated into the .Xr ls 1 program, though for most programs with similar output .Nm suffices. .Pp To convert stream input into vector output and back again, use .Bd -literal -offset indent $ rs 1 0 \*(Ba rs 0 1 .Ed .Pp A 10 by 10 array of random numbers from 1 to 100 and its transpose can be generated with .Bd -literal -offset indent $ jot \-r 100 \*(Ba rs 10 10 \*(Ba tee array \*(Ba rs \-T \*(Gttarray .Ed .Pp In the editor .Xr vi 1 , a file consisting of a multi-line vector with 9 elements per line can undergo insertions and deletions, and then be neatly reshaped into 9 columns with .Bd -literal -offset indent :1,$!rs 0 9 .Ed .Pp Finally, to sort a database by the first line of each 4-line field, try .Bd -literal -offset indent $ rs \-eC 0 4 \*(Ba sort \*(Ba rs \-c 0 1 .Ed .Sh SEE ALSO .Xr jot 1 , .Xr pr 1 , .Xr sort 1 , .Xr vi 1 .Sh BUGS Handles only two dimensional arrays. .Pp The algorithm currently reads the whole file into memory, so files that do not fit in memory will not be reshaped. .Pp Fields cannot be defined yet on character positions. .Pp Re-ordering of columns is not yet possible. .Pp There are too many options. rs-20140609/rs.c010064400000000000000000000262761234540422300101400ustar00/* $OpenBSD: rs.c,v 1.23 2013/11/15 15:47:53 millert Exp $ */ /*- * Copyright (c) 2014 * Thorsten Glaser * Copyright (c) 1993 * 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. */ /* * rs - reshape a data array * Author: John Kunze, Office of Comp. Affairs, UCB * BEWARE: lots of unfinished edges */ #include #include #include #include #include #include #include #include #ifdef USE_LIBBSD #ifndef __RCSID #define __RCSID(x) static const char rcsid[] __attribute__((__used__)) = x #endif #ifndef __dead #define __dead __attribute__((__noreturn__)) #endif extern long long strtonum(const char *, long long, long long, const char **); #endif __RCSID("$MirOS: src/usr.bin/rs/rs.c,v 1.11 2014/06/09 19:17:53 tg Exp $"); long flags; #define TRANSPOSE 000001 #define MTRANSPOSE 000002 #define ONEPERLINE 000004 #define ONEISEPONLY 000010 #define ONEOSEPONLY 000020 #define NOTRIMENDCOL 000040 #define SQUEEZE 000100 #define SHAPEONLY 000200 #define DETAILSHAPE 000400 #define RIGHTADJUST 001000 #define NULLPAD 002000 #define RECYCLE 004000 #define SKIPPRINT 010000 #define ONEPERCHAR 0100000 #define NOARGS 0200000 short *colwidths; int nelem; const char **elem; const char **endelem; char *curline; size_t allocsize = BUFSIZ; int curlen; int irows, icols; int orows, ocols; int maxlen; int skip; int propgutter; char isep = ' ', osep = ' '; int owidth = 80, gutter = 2; void usage(void) __dead; void getargs(int, char *[]); void getfile(void); int get_line(void); const char **getptrs(const char **); void prepfile(void); void prints(const char *, int); void putfile(void); #define INCR(ep) do { \ if (++ep >= endelem) \ ep = getptrs(ep); \ } while(0) int main(int argc, char *argv[]) { getargs(argc, argv); getfile(); if (flags & SHAPEONLY) { printf("%d %d\n", irows, icols); exit(0); } prepfile(); putfile(); exit(0); } void getfile(void) { char *p; char *endp; const char **ep = NULL; int multisep = (flags & ONEISEPONLY ? 0 : 1); int nullpad = flags & NULLPAD; const char **padto; while (skip--) { get_line(); if (flags & SKIPPRINT) puts(curline); } get_line(); if (flags & NOARGS && curlen < owidth) flags |= ONEPERLINE; if (flags & ONEPERLINE) icols = 1; else /* count cols on first line */ for (p = curline, endp = curline + curlen; p < endp; p++) { if (*p == isep && multisep) continue; icols++; while (*p && *p != isep) p++; } ep = getptrs(elem); p = curline; do { if (flags & ONEPERLINE) { *ep = curline; INCR(ep); /* prepare for next entry */ if (maxlen < curlen) maxlen = curlen; irows++; continue; } for (p = curline, endp = curline + curlen; p < endp; p++) { if (*p == isep) { if (multisep) /* eat up column separators */ goto handle_last_field; /* must be an empty column */ *ep = ""; } else { /* store column entry */ *ep = p; /* find end of entry */ while (p < endp && *p != isep) p++; /* update maxlen */ if (maxlen < p - *ep) maxlen = p - *ep; } /* mark end of entry */ *p = '\0'; /* prepare for next entry */ INCR(ep); /* handle empty last field */ handle_last_field: if ((p + 1) == endp) { /* insert empty entry iff checked */ *ep = ""; INCR(ep); /* the loop will end immediately */ } } irows++; /* update row count */ if (nullpad) { /* pad missing entries */ padto = elem + irows * icols; while (ep < padto) { *ep = ""; INCR(ep); } } } while (get_line() != EOF); *ep = NULL; /* mark end of pointers */ nelem = ep - elem; } void putfile(void) { const char **ep; int i, j, n; ep = elem; if (flags & TRANSPOSE) { for (i = 0; i < orows; i++) { for (j = i; j < nelem; j += orows) prints(ep[j], (j - i) / orows); putchar('\n'); } } else { for (n = 0, i = 0; i < orows && n < nelem; i++) { for (j = 0; j < ocols; j++) { if (n++ >= nelem) break; prints(*ep++, j); } putchar('\n'); } } } void prints(const char *s, int col) { int n; const char *p = s; while (*p) p++; n = (flags & ONEOSEPONLY ? 1 : colwidths[col] - (p - s)); if (flags & RIGHTADJUST) while (n-- > 0) putchar(osep); for (p = s; *p; p++) putchar(*p); while (n-- > 0) putchar(osep); } void usage(void) { extern char *__progname; fprintf(stderr, "usage: %s [-CcSs[x]] [-GgKkw N] [-EeHhjmnTtyz] [rows [cols]]\n", __progname); exit(1); } void prepfile(void) { int i, j, colw, max, n; const char **ep, **lp; if (!nelem) exit(0); gutter += maxlen * propgutter / 100.0; colw = maxlen + gutter; if (flags & MTRANSPOSE) { orows = icols; ocols = irows; } else if (orows == 0 && ocols == 0) { /* decide rows and cols */ ocols = owidth / colw; if (ocols == 0) { warnx("Display width %d is less than column width %d", owidth, colw); ocols = 1; } if (ocols > nelem) ocols = nelem; orows = nelem / ocols + (nelem % ocols ? 1 : 0); } else if (orows == 0) /* decide on rows */ orows = nelem / ocols + (nelem % ocols ? 1 : 0); else if (ocols == 0) /* decide on cols */ ocols = nelem / orows + (nelem % orows ? 1 : 0); lp = elem + orows * ocols; while (lp > endelem) { getptrs(elem + nelem); lp = elem + orows * ocols; } if (flags & RECYCLE) { for (ep = elem + nelem; ep < lp; ep++) *ep = *(ep - nelem); nelem = lp - elem; } if (!(colwidths = (short *) calloc(ocols, sizeof(short)))) errx(1, "malloc: No gutter space"); if (flags & SQUEEZE) { if (flags & TRANSPOSE) for (ep = elem, i = 0; i < ocols; i++) { max = 0; for (j = 0; j < orows; j++) if ((n = strlen(*ep++)) > max) max = n; colwidths[i] = max + gutter; } else for (ep = elem, i = 0; i < ocols; i++) { max = 0; for (j = i; j < nelem; j += ocols) if ((n = strlen(ep[j])) > max) max = n; colwidths[i] = max + gutter; } } else { for (i = 0; i < ocols; i++) colwidths[i] = colw; } if (!(flags & NOTRIMENDCOL)) { if (flags & RIGHTADJUST) colwidths[0] -= gutter; else colwidths[ocols - 1] = 0; } n = orows * ocols; if (n > nelem && (flags & RECYCLE)) nelem = n; } #define BSIZE 2048 char ibuf[BSIZE]; /* two screenfuls should do */ int get_line(void) /* get line; maintain curline, curlen; manage storage */ { static int putlength; static char *endblock = ibuf + BSIZE; char *p; int c, i; if (!irows) { curline = ibuf; putlength = flags & DETAILSHAPE; } else if (skip <= 0) { /* don't waste storage */ curline += curlen + 1; if (putlength) /* print length, recycle storage */ printf(" %d line %d\n", curlen, irows); } if (!putlength && endblock - curline < BUFSIZ) { /* need storage */ if (!(curline = (char *) malloc(BSIZE))) errx(1, "File too large"); endblock = curline + BSIZE; } for (p = curline, i = 1; i < BUFSIZ; *p++ = c, i++) if ((c = getchar()) == EOF || c == '\n') break; *p = '\0'; curlen = i - 1; return(c); } const char ** getptrs(const char **sp) { const char **p; size_t newsize; newsize = allocsize * 2; p = realloc(elem, newsize * sizeof(char *)); if (p == NULL) err(1, "no memory"); allocsize = newsize; sp += p - elem; elem = p; endelem = elem + allocsize; return(sp); } void getargs(int ac, char *av[]) { int ch; const char *errstr; if (ac == 1) flags |= NOARGS | TRANSPOSE; while ((ch = getopt(ac, av, "c::C::s::S::k:K:g:G:w:tTeEnyjhHmz")) != -1) { switch (ch) { case 'T': flags |= MTRANSPOSE; /* FALLTHROUGH */ case 't': flags |= TRANSPOSE; break; case 'c': /* input col. separator */ flags |= ONEISEPONLY; /* FALLTHROUGH */ case 's': /* one or more allowed */ if (optarg == NULL) isep = '\t'; /* default is ^I */ else if (optarg[1] != '\0') usage(); /* single char only */ else isep = *optarg; break; case 'C': flags |= ONEOSEPONLY; /* FALLTHROUGH */ case 'S': if (optarg == NULL) osep = '\t'; /* default is ^I */ else if (optarg[1] != '\0') usage(); /* single char only */ else osep = *optarg; break; case 'w': /* window width, default 80 */ owidth = strtonum(optarg, 1, INT_MAX, &errstr); if (errstr) { warnx("width %s", errstr); usage(); } break; case 'K': /* skip N lines */ flags |= SKIPPRINT; /* FALLTHROUGH */ case 'k': /* skip, do not print */ skip = strtonum(optarg, 0, INT_MAX, &errstr); if (errstr) { warnx("skip value %s", errstr); usage(); } if (skip == 0) skip = 1; break; case 'm': flags |= NOTRIMENDCOL; break; case 'g': /* gutter width */ gutter = strtonum(optarg, 0, INT_MAX, &errstr); if (errstr) { warnx("gutter width %s", errstr); usage(); } break; case 'G': propgutter = strtonum(optarg, 0, INT_MAX, &errstr); if (errstr) { warnx("gutter proportion %s", errstr); usage(); } break; case 'e': /* each line is an entry */ flags |= ONEPERLINE; break; case 'E': flags |= ONEPERCHAR; break; case 'j': /* right adjust */ flags |= RIGHTADJUST; break; case 'n': /* null padding for missing values */ flags |= NULLPAD; break; case 'y': flags |= RECYCLE; break; case 'H': /* print shape only */ flags |= DETAILSHAPE; /* FALLTHROUGH */ case 'h': flags |= SHAPEONLY; break; case 'z': /* squeeze col width */ flags |= SQUEEZE; break; default: usage(); } } ac -= optind; av += optind; switch (ac) { case 2: ocols = strtonum(av[1], 0, INT_MAX, &errstr); if (errstr) { warnx("columns value %s", errstr); usage(); } /* FALLTHROUGH */ case 1: orows = strtonum(av[0], 0, INT_MAX, &errstr); if (errstr) { warnx("columns value %s", errstr); usage(); } /* FALLTHROUGH */ case 0: break; default: usage(); } }