Minix/minix
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

Importing usr.bin/tr

Browse Source 
Change-Id: I4563198f111f2ec3687f6a5084edd05f243c2263
This commit is contained in:
Lionel Sambuc
2013-08-24 22:11:19 +02:00
parent 00785f561f
commit d5c6c6a51b
11 changed files with 494 additions and 231 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
usr.bin/Makefile
View File

@@ -26,7 +26,7 @@ SUBDIR= \
shuffle sed seq \
sort stat su \
tic tput \
tsort unexpand \
tr tsort unexpand \
toproto \
uniq \
\

11
usr.bin/tr/Makefile Normal file
View File

@@ -0,0 +1,11 @@
# $NetBSD: Makefile,v 1.8 2012/08/10 12:10:28 joerg Exp $
# @(#)Makefile 8.1 (Berkeley) 6/6/93
PROG= tr
SRCS= str.c tr.c
.for f in str tr
COPTS.${f}.c+= -Wno-pointer-sign
.endfor
.include <bsd.prog.mk>

48
usr.bin/tr/extern.h Normal file
View File

@@ -0,0 +1,48 @@
/* $NetBSD: extern.h,v 1.7 2011/09/06 18:33:46 joerg Exp $ */
/*-
* Copyright (c) 1991, 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.
*
* @(#)extern.h 8.1 (Berkeley) 6/6/93
*/
typedef struct {
enum { STRING1, STRING2 } which;
enum { EOS, INFINITE, NORMAL, RANGE, SEQUENCE, SET } state;
int cnt; /* character count */
int lastch; /* last character */
int equiv[2]; /* equivalence set */
int *set; /* set of characters */
unsigned char *str; /* user's string */
} STR;
#include <limits.h>
#define NCHARS (UCHAR_MAX + 1) /* Number of possible characters. */
#define OOBCH (UCHAR_MAX + 1) /* Out of band character value. */
int next(STR *);

324
usr.bin/tr/str.c Normal file
View File

@@ -0,0 +1,324 @@
/* $NetBSD: str.c,v 1.19 2011/09/08 12:00:26 christos Exp $ */
/*-
* Copyright (c) 1991, 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.
*/
#include <sys/cdefs.h>
#ifndef lint
#if 0
static char sccsid[] = "@(#)str.c 8.2 (Berkeley) 4/28/95";
#endif
__RCSID("$NetBSD: str.c,v 1.19 2011/09/08 12:00:26 christos Exp $");
#endif /* not lint */
#include <sys/types.h>
#include <err.h>
#include <errno.h>
#include <stddef.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <ctype.h>
#include "extern.h"
static int backslash(STR *);
static int bracket(STR *);
static int c_class(const void *, const void *);
static void genclass(STR *);
static void genequiv(STR *);
static int genrange(STR *);
static void genseq(STR *);
int
next(STR *s)
{
int ch;
switch (s->state) {
case EOS:
return 0;
case INFINITE:
return 1;
case NORMAL:
switch (ch = *s->str) {
case '\0':
s->state = EOS;
return 0;
case '\\':
s->lastch = backslash(s);
break;
case '[':
if (bracket(s))
return next(s);
/* FALLTHROUGH */
default:
++s->str;
s->lastch = ch;
break;
}
/* We can start a range at any time. */
if (s->str[0] == '-' && genrange(s))
return next(s);
return 1;
case RANGE:
if (s->cnt-- == 0) {
s->state = NORMAL;
return next(s);
}
++s->lastch;
return 1;
case SEQUENCE:
if (s->cnt-- == 0) {
s->state = NORMAL;
return next(s);
}
return 1;
case SET:
if ((s->lastch = s->set[s->cnt++]) == OOBCH) {
s->state = NORMAL;
return next(s);
}
return 1;
}
/* NOTREACHED */
return 0;
}
static int
bracket(STR *s)
{
char *p;
switch (s->str[1]) {
case ':': /* "[:class:]" */
if ((p = strstr(s->str + 2, ":]")) == NULL)
return 0;
*p = '\0';
s->str += 2;
genclass(s);
s->str = p + 2;
return 1;
case '=': /* "[=equiv=]" */
if ((p = strstr(s->str + 2, "=]")) == NULL)
return 0;
s->str += 2;
genequiv(s);
return 1;
default: /* "[\###*n]" or "[#*n]" */
if ((p = strpbrk(s->str + 2, "*]")) == NULL)
return 0;
if (p[0] != '*' || strchr(p, ']') == NULL)
return 0;
s->str += 1;
genseq(s);
return 1;
}
/* NOTREACHED */
}
typedef struct {
const char *name;
int (*func)(int);
} CLASS;
static const CLASS classes[] = {
{ "alnum", isalnum },
{ "alpha", isalpha },
{ "blank", isblank },
{ "cntrl", iscntrl },
{ "digit", isdigit },
{ "graph", isgraph },
{ "lower", islower },
{ "print", isprint },
{ "punct", ispunct },
{ "space", isspace },
{ "upper", isupper },
{ "xdigit", isxdigit },
};
static void
genclass(STR *s)
{
int cnt;
const CLASS *cp;
CLASS tmp;
int *p;
tmp.name = s->str;
if ((cp = bsearch(&tmp, classes, sizeof(classes) /
sizeof(*cp), sizeof(*cp), c_class)) == NULL)
errx(1, "unknown class %s", s->str);
if ((s->set = p = malloc((NCHARS + 1) * sizeof(*p))) == NULL)
err(1, "malloc");
for (cnt = 0; cnt < NCHARS; ++cnt)
if ((*cp->func)(cnt))
*p++ = cnt;
*p++ = OOBCH;
memset(p, 0, NCHARS + 1 - (p - s->set));
s->cnt = 0;
s->state = SET;
}
static int
c_class(const void *a, const void *b)
{
return strcmp(((const CLASS *)a)->name, ((const CLASS *)b)->name);
}
/*
* English doesn't have any equivalence classes, so for now
* we just syntax check and grab the character.
*/
static void
genequiv(STR *s)
{
if (*s->str == '\\') {
s->equiv[0] = backslash(s);
if (*s->str != '=')
errx(1, "misplaced equivalence equals sign");
} else {
s->equiv[0] = s->str[0];
if (s->str[1] != '=')
errx(1, "misplaced equivalence equals sign");
}
s->str += 2;
s->cnt = 0;
s->state = SET;
s->set = s->equiv;
}
static int
genrange(STR *s)
{
int stopval;
char *savestart;
savestart = s->str;
stopval = *++s->str == '\\' ? backslash(s) : *s->str++;
if (stopval < (u_char)s->lastch) {
s->str = savestart;
return 0;
}
s->cnt = stopval - s->lastch + 1;
s->state = RANGE;
--s->lastch;
return 1;
}
static void
genseq(STR *s)
{
char *ep;
if (s->which == STRING1)
errx(1, "sequences only valid in string2");
if (*s->str == '\\')
s->lastch = backslash(s);
else
s->lastch = *s->str++;
if (*s->str != '*')
errx(1, "misplaced sequence asterisk");
switch (*++s->str) {
case '\\':
s->cnt = backslash(s);
break;
case ']':
s->cnt = 0;
++s->str;
break;
default:
if (isdigit(*s->str)) {
s->cnt = strtol(s->str, &ep, 0);
if (*ep == ']') {
s->str = ep + 1;
break;
}
}
errx(1, "illegal sequence count");
/* NOTREACHED */
}
s->state = s->cnt ? SEQUENCE : INFINITE;
}
/*
* Translate \??? into a character. Up to 3 octal digits, if no digits either
* an escape code or a literal character.
*/
static int
backslash(STR *s)
{
int ch, cnt, val;
for (cnt = val = 0;;) {
ch = *++s->str;
if (!isascii(ch) || !isdigit(ch))
break;
val = val * 8 + ch - '0';
if (++cnt == 3) {
++s->str;
break;
}
}
if (cnt)
return val;
if (ch != '\0')
++s->str;
switch (ch) {
case 'a': /* escape characters */
return '\7';
case 'b':
return '\b';
case 'e':
return '\033';
case 'f':
return '\f';
case 'n':
return '\n';
case 'r':
return '\r';
case 't':
return '\t';
case 'v':
return '\13';
case '\0': /* \" -> \ */
s->state = EOS;
return '\\';
default: /* \x" -> x */
return ch;
}
}

350
usr.bin/tr/tr.1 Normal file
View File

@@ -0,0 +1,350 @@
.\" $NetBSD: tr.1,v 1.18 2009/11/12 00:43:53 joerg Exp $
.\"
.\" Copyright (c) 1991, 1993
.\" The Regents of the University of California. All rights reserved.
.\"
.\" This code is derived from software contributed to Berkeley by
.\" the Institute of Electrical and Electronics Engineers, Inc.
.\"
.\" 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.
.\"
.\" @(#)tr.1 8.1 (Berkeley) 6/6/93
.\"
.Dd March 23, 2004
.Dt TR 1
.Os
.Sh NAME
.Nm tr
.Nd translate characters
.Sh SYNOPSIS
.Nm
.Op Fl cs
.Ar string1 string2
.Nm
.Op Fl c
.Fl d
.Ar string1
.Nm
.Op Fl c
.Fl s
.Ar string1
.Nm
.Op Fl c
.Fl ds
.Ar string1 string2
.Sh DESCRIPTION
The
.Nm
utility copies the standard input to the standard output with substitution
or deletion of selected characters.
.Pp
The following options are available:
.Bl -tag -width Ds
.It Fl c
Complements the set of characters in
.Ar string1 ,
that is
.Fl c Ar \&ab
includes every character except for
.Sq a
and
.Sq b .
.It Fl d
The
.Fl d
option causes characters to be deleted from the input.
.It Fl s
The
.Fl s
option squeezes multiple occurrences of the characters listed in the last
operand (either
.Ar string1
or
.Ar string2 )
in the input into a single instance of the character.
This occurs after all deletion and translation is completed.
.El
.Pp
In the first synopsis form, the characters in
.Ar string1
are translated into the characters in
.Ar string2
where the first character in
.Ar string1
is translated into the first character in
.Ar string2
and so on.
If
.Ar string1
is longer than
.Ar string2 ,
the last character found in
.Ar string2
is duplicated until
.Ar string1
is exhausted.
.Pp
In the second synopsis form, the characters in
.Ar string1
are deleted from the input.
.Pp
In the third synopsis form, the characters in
.Ar string1
are compressed as described for the
.Fl s
option.
.Pp
In the fourth synopsis form, the characters in
.Ar string1
are deleted from the input, and the characters in
.Ar string2
are compressed as described for the
.Fl s
option.
.Pp
The following conventions can be used in
.Ar string1
and
.Ar string2
to specify sets of characters:
.Bl -tag -width [:equiv:]
.It character
Any character not described by one of the following conventions
represents itself.
.It \eoctal
A backslash followed by 1, 2 or 3 octal digits represents a character
with that encoded value.
To follow an octal sequence with a digit as a character, left zero-pad
the octal sequence to the full 3 octal digits.
.It \echaracter
A backslash followed by certain special characters maps to special
values.
.sp
.Bl -column cc
.It \ea \*[Lt]alert character\*[Gt]
.It \eb \*[Lt]backspace\*[Gt]
.It \ef \*[Lt]form-feed\*[Gt]
.It \en \*[Lt]newline\*[Gt]
.It \er \*[Lt]carriage return\*[Gt]
.It \et \*[Lt]tab\*[Gt]
.It \ev \*[Lt]vertical tab\*[Gt]
.El
.sp
A backslash followed by any other character maps to that character.
.It c-c
Represents the range of characters between the range endpoints, inclusively.
.It [:class:]
Represents all characters belonging to the defined character class.
Class names are:
.sp
.Bl -column xdigit
.It alnum \*[Lt]alphanumeric characters\*[Gt]
.It alpha \*[Lt]alphabetic characters\*[Gt]
.It blank \*[Lt]blank characters\*[Gt]
.It cntrl \*[Lt]control characters\*[Gt]
.It digit \*[Lt]numeric characters\*[Gt]
.It graph \*[Lt]graphic characters\*[Gt]
.It lower \*[Lt]lower-case alphabetic characters\*[Gt]
.It print \*[Lt]printable characters\*[Gt]
.It punct \*[Lt]punctuation characters\*[Gt]
.It space \*[Lt]space characters\*[Gt]
.It upper \*[Lt]upper-case characters\*[Gt]
.It xdigit \*[Lt]hexadecimal characters\*[Gt]
.El
.Pp
.\" All classes may be used in
.\" .Ar string1 ,
.\" and in
.\" .Ar string2
.\" when both the
.\" .Fl d
.\" and
.\" .Fl s
.\" options are specified.
.\" Otherwise, only the classes ``upper'' and ``lower'' may be used in
.\" .Ar string2
.\" and then only when the corresponding class (``upper'' for ``lower''
.\" and vice-versa) is specified in the same relative position in
.\" .Ar string1 .
.\" .Pp
With the exception of the
.Dq upper
and
.Dq lower
classes, characters in the classes are in unspecified order.
In the
.Dq upper
and
.Dq lower
classes, characters are entered in ascending order.
.Pp
For specific information as to which ASCII characters are included
in these classes, see
.Xr ctype 3
and related manual pages.
.It [=equiv=]
Represents all characters or collating (sorting) elements belonging to
the same equivalence class as
.Ar equiv .
If there is a secondary ordering within the equivalence class, the
characters are ordered in ascending sequence.
Otherwise, they are ordered after their encoded values.
An example of an equivalence class might be
.Dq \&c
and
.Dq \&ch
in Spanish;
English has no equivalence classes.
.It [#*n]
Represents
.Ar n
repeated occurrences of the character represented by
.Ar # .
This
expression is only valid when it occurs in
.Ar string2 .
If
.Ar n
is omitted or is zero, it is interpreted as large enough to extend
.Ar string2
sequence to the length of
.Ar string1 .
If
.Ar n
has a leading zero, it is interpreted as an octal value, otherwise,
it's interpreted as a decimal value.
.El
.Sh EXIT STATUS
.Nm
exits 0 on success, and \*[Gt]0 if an error occurs.
.Sh EXAMPLES
The following examples are shown as given to the shell:
.Pp
Create a list of the words in
.Ar file1 ,
one per line, where a word is taken to be a maximal string of letters:
.sp
.D1 Li "tr -cs \*q[:alpha:]\*q \*q\en\*q \*[Lt] file1"
.sp
Translate the contents of
.Ar file1
to upper-case:
.sp
.D1 Li "tr \*q[:lower:]\*q \*q[:upper:]\*q \*[Lt] file1"
.sp
Strip out non-printable characters from
.Ar file1 :
.sp
.D1 Li "tr -cd \*q[:print:]\*q \*[Lt] file1"
.Sh COMPATIBILITY
.At V
has historically implemented character ranges using the syntax
.Dq [c-c]
instead of the
.Dq c-c
used by historic
.Bx
implementations and standardized by POSIX.
.At V
shell scripts should work under this implementation as long as
the range is intended to map in another range, i.e. the command
.Pp
.Ic "tr [a-z] [A-Z]"
.Pp
will work as it will map the
.Sq \&[
character in
.Ar string1
to the
.Sq \&[
character in
.Ar string2 .
However, if the shell script is deleting or squeezing characters as in
the command
.Pp
.Ic "tr -d [a-z]"
.Pp
the characters
.Sq \&[
and
.Sq \&]
will be included in the deletion or compression list which would
not have happened under an historic
.At V
implementation.
Additionally, any scripts that depended on the sequence
.Dq a-z
to represent the three characters
.Sq \&a ,
.Sq \&- ,
and
.Sq \&z
will have to be rewritten as
.Dq a\e-z .
.Pp
The
.Nm
utility has historically not permitted the manipulation of NUL bytes in
its input and, additionally, stripped NUL's from its input stream.
This implementation has removed this behavior as a bug.
.Pp
The
.Nm
utility has historically been extremely forgiving of syntax errors,
for example, the
.Fl c
and
.Fl s
options were ignored unless two strings were specified.
This implementation will not permit illegal syntax.
.Sh STANDARDS
The
.Nm
utility is expected to be
.St -p1003.2
compatible.
It should be noted that the feature wherein the last character of
.Ar string2
is duplicated if
.Ar string2
has less characters than
.Ar string1
is permitted by POSIX but is not required.
Shell scripts attempting to be portable to other POSIX systems should use
the
.Dq [#*]
convention instead of relying on this behavior.
.Sh BUGS
.Nm
was originally designed to work with
.Tn US-ASCII .
Its use with character sets that do not share all the properties of
.Tn US-ASCII ,
e.g., a symmetric set of upper and lower case characters
that can be algorithmically converted one to the other,
may yield unpredictable results.
.Pp
.Nm
should be internationalized.

257
usr.bin/tr/tr.c Normal file
View File

@@ -0,0 +1,257 @@
/* $NetBSD: tr.c,v 1.9 2011/09/06 18:33:46 joerg Exp $ */
/*
* Copyright (c) 1988, 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.
*/
#include <sys/cdefs.h>
#ifndef lint
__COPYRIGHT("@(#) Copyright (c) 1988, 1993\
The Regents of the University of California. All rights reserved.");
#endif /* not lint */
#ifndef lint
#if 0
static char sccsid[] = "@(#)tr.c 8.2 (Berkeley) 5/4/95";
#endif
__RCSID("$NetBSD: tr.c,v 1.9 2011/09/06 18:33:46 joerg Exp $");
#endif /* not lint */
#include <sys/types.h>
#include <err.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <unistd.h>
#include "extern.h"
static int string1[NCHARS] = {
0x00, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07, /* ASCII */
0x08, 0x09, 0x0a, 0x0b, 0x0c, 0x0d, 0x0e, 0x0f,
0x10, 0x11, 0x12, 0x13, 0x14, 0x15, 0x16, 0x17,
0x18, 0x19, 0x1a, 0x1b, 0x1c, 0x1d, 0x1e, 0x1f,
0x20, 0x21, 0x22, 0x23, 0x24, 0x25, 0x26, 0x27,
0x28, 0x29, 0x2a, 0x2b, 0x2c, 0x2d, 0x2e, 0x2f,
0x30, 0x31, 0x32, 0x33, 0x34, 0x35, 0x36, 0x37,
0x38, 0x39, 0x3a, 0x3b, 0x3c, 0x3d, 0x3e, 0x3f,
0x40, 0x41, 0x42, 0x43, 0x44, 0x45, 0x46, 0x47,
0x48, 0x49, 0x4a, 0x4b, 0x4c, 0x4d, 0x4e, 0x4f,
0x50, 0x51, 0x52, 0x53, 0x54, 0x55, 0x56, 0x57,
0x58, 0x59, 0x5a, 0x5b, 0x5c, 0x5d, 0x5e, 0x5f,
0x60, 0x61, 0x62, 0x63, 0x64, 0x65, 0x66, 0x67,
0x68, 0x69, 0x6a, 0x6b, 0x6c, 0x6d, 0x6e, 0x6f,
0x70, 0x71, 0x72, 0x73, 0x74, 0x75, 0x76, 0x77,
0x78, 0x79, 0x7a, 0x7b, 0x7c, 0x7d, 0x7e, 0x7f,
0x80, 0x81, 0x82, 0x83, 0x84, 0x85, 0x86, 0x87,
0x88, 0x89, 0x8a, 0x8b, 0x8c, 0x8d, 0x8e, 0x8f,
0x90, 0x91, 0x92, 0x93, 0x94, 0x95, 0x96, 0x97,
0x98, 0x99, 0x9a, 0x9b, 0x9c, 0x9d, 0x9e, 0x9f,
0xa0, 0xa1, 0xa2, 0xa3, 0xa4, 0xa5, 0xa6, 0xa7,
0xa8, 0xa9, 0xaa, 0xab, 0xac, 0xad, 0xae, 0xaf,
0xb0, 0xb1, 0xb2, 0xb3, 0xb4, 0xb5, 0xb6, 0xb7,
0xb8, 0xb9, 0xba, 0xbb, 0xbc, 0xbd, 0xbe, 0xbf,
0xc0, 0xc1, 0xc2, 0xc3, 0xc4, 0xc5, 0xc6, 0xc7,
0xc8, 0xc9, 0xca, 0xcb, 0xcc, 0xcd, 0xce, 0xcf,
0xd0, 0xd1, 0xd2, 0xd3, 0xd4, 0xd5, 0xd6, 0xd7,
0xd8, 0xd9, 0xda, 0xdb, 0xdc, 0xdd, 0xde, 0xdf,
0xe0, 0xe1, 0xe2, 0xe3, 0xe4, 0xe5, 0xe6, 0xe7,
0xe8, 0xe9, 0xea, 0xeb, 0xec, 0xed, 0xee, 0xef,
0xf0, 0xf1, 0xf2, 0xf3, 0xf4, 0xf5, 0xf6, 0xf7,
0xf8, 0xf9, 0xfa, 0xfb, 0xfc, 0xfd, 0xfe, 0xff,
}, string2[NCHARS];
STR s1 = { STRING1, NORMAL, 0, OOBCH, { 0, OOBCH }, NULL, NULL };
STR s2 = { STRING2, NORMAL, 0, OOBCH, { 0, OOBCH }, NULL, NULL };
static void setup(int *, char *, STR *, int);
__dead static void usage(void);
int
main(int argc, char **argv)
{
int ch, cnt, lastch, *p;
int cflag, dflag, sflag, isstring2;
cflag = dflag = sflag = 0;
while ((ch = getopt(argc, argv, "cds")) != -1)
switch((char)ch) {
case 'c':
cflag = 1;
break;
case 'd':
dflag = 1;
break;
case 's':
sflag = 1;
break;
case '?':
default:
usage();
}
argc -= optind;
argv += optind;
switch(argc) {
case 0:
default:
usage();
/* NOTREACHED */
case 1:
isstring2 = 0;
break;
case 2:
isstring2 = 1;
break;
}
/*
* tr -ds [-c] string1 string2
* Delete all characters (or complemented characters) in string1.
* Squeeze all characters in string2.
*/
if (dflag && sflag) {
if (!isstring2)
usage();
setup(string1, argv[0], &s1, cflag);
setup(string2, argv[1], &s2, 0);
for (lastch = OOBCH; (ch = getchar()) != EOF;)
if (!string1[ch] && (!string2[ch] || lastch != ch)) {
lastch = ch;
(void)putchar(ch);
}
exit(0);
}
/*
* tr -d [-c] string1
* Delete all characters (or complemented characters) in string1.
*/
if (dflag) {
if (isstring2)
usage();
setup(string1, argv[0], &s1, cflag);
while ((ch = getchar()) != EOF)
if (!string1[ch])
(void)putchar(ch);
exit(0);
}
/*
* tr -s [-c] string1
* Squeeze all characters (or complemented characters) in string1.
*/
if (sflag && !isstring2) {
setup(string1, argv[0], &s1, cflag);
for (lastch = OOBCH; (ch = getchar()) != EOF;)
if (!string1[ch] || lastch != ch) {
lastch = ch;
(void)putchar(ch);
}
exit(0);
}
/*
* tr [-cs] string1 string2
* Replace all characters (or complemented characters) in string1 with
* the character in the same position in string2. If the -s option is
* specified, squeeze all the characters in string2.
*/
if (!isstring2)
usage();
s1.str = argv[0];
s2.str = argv[1];
if (cflag)
for (cnt = NCHARS, p = string1; cnt--;)
*p++ = OOBCH;
if (!next(&s2))
errx(1, "empty string2");
/* If string2 runs out of characters, use the last one specified. */
if (sflag)
while (next(&s1)) {
string1[s1.lastch] = ch = s2.lastch;
string2[ch] = 1;
(void)next(&s2);
}
else
while (next(&s1)) {
string1[s1.lastch] = ch = s2.lastch;
(void)next(&s2);
}
if (cflag)
for (cnt = 0, p = string1; cnt < NCHARS; ++p, ++cnt)
*p = *p == OOBCH ? ch : cnt;
if (sflag)
for (lastch = OOBCH; (ch = getchar()) != EOF;) {
ch = string1[ch];
if (!string2[ch] || lastch != ch) {
lastch = ch;
(void)putchar(ch);
}
}
else
while ((ch = getchar()) != EOF)
(void)putchar(string1[ch]);
exit (0);
}
static void
setup(int *string, char *arg, STR *str, int cflag)
{
int cnt, *p;
str->str = arg;
memset(string, 0, NCHARS * sizeof(int));
while (next(str))
string[str->lastch] = 1;
if (cflag)
for (p = string, cnt = NCHARS; cnt--; ++p)
*p = !*p;
}
static void
usage(void)
{
(void)fprintf(stderr, "usage: tr [-cs] string1 string2\n");
(void)fprintf(stderr, " tr [-c] -d string1\n");
(void)fprintf(stderr, " tr [-c] -s string1\n");
(void)fprintf(stderr, " tr [-c] -ds string1 string2\n");
exit(1);
}