Remove compression support from bsdgrep
Compression support is now handled by an external script, remove it from the bsdgrep(1) utility. This removes the support for -Z -J -X and -M Note: that it matches the changes in newer GNU grep Reviewed by: kevans Approved by: kevans MFC after: 1 week Differential Revision: https://reviews.freebsd.org/D15197
This commit is contained in:
parent
19c5cea336
commit
4a5b420738
@ -69,20 +69,6 @@ MLINKS+= grep.1 egrep.1 \
|
||||
grep.1 rgrep.1
|
||||
.endif
|
||||
|
||||
LIBADD= z
|
||||
|
||||
.if ${MK_LZMA_SUPPORT} != "no"
|
||||
LIBADD+= lzma
|
||||
.else
|
||||
CFLAGS+= -DWITHOUT_LZMA
|
||||
.endif
|
||||
|
||||
.if ${MK_BZIP2_SUPPORT} != "no"
|
||||
LIBADD+= bz2
|
||||
.else
|
||||
CFLAGS+= -DWITHOUT_BZIP2
|
||||
.endif
|
||||
|
||||
.if ${MK_GNU_GREP_COMPAT} != "no"
|
||||
CFLAGS+= -I${SYSROOT:U${DESTDIR}}/usr/include/gnu -DWITH_GNU
|
||||
LIBADD+= gnuregex
|
||||
|
@ -49,31 +49,12 @@ __FBSDID("$FreeBSD$");
|
||||
#include <unistd.h>
|
||||
#include <wchar.h>
|
||||
#include <wctype.h>
|
||||
#include <zlib.h>
|
||||
|
||||
#ifndef WITHOUT_LZMA
|
||||
#include <lzma.h>
|
||||
#endif
|
||||
|
||||
#ifndef WITHOUT_BZIP2
|
||||
#include <bzlib.h>
|
||||
#endif
|
||||
|
||||
#include "grep.h"
|
||||
|
||||
#define MAXBUFSIZ (32 * 1024)
|
||||
#define LNBUFBUMP 80
|
||||
|
||||
static gzFile gzbufdesc;
|
||||
#ifndef WITHOUT_LZMA
|
||||
static lzma_stream lstrm = LZMA_STREAM_INIT;
|
||||
static lzma_action laction;
|
||||
static uint8_t lin_buf[MAXBUFSIZ];
|
||||
#endif
|
||||
#ifndef WITHOUT_BZIP2
|
||||
static BZFILE* bzbufdesc;
|
||||
#endif
|
||||
|
||||
static unsigned char *buffer;
|
||||
static unsigned char *bufpos;
|
||||
static size_t bufrem;
|
||||
@ -86,9 +67,6 @@ static inline int
|
||||
grep_refill(struct file *f)
|
||||
{
|
||||
ssize_t nr;
|
||||
#ifndef WITHOUT_LZMA
|
||||
lzma_ret lzmaret;
|
||||
#endif
|
||||
|
||||
if (filebehave == FILE_MMAP)
|
||||
return (0);
|
||||
@ -96,84 +74,7 @@ grep_refill(struct file *f)
|
||||
bufpos = buffer;
|
||||
bufrem = 0;
|
||||
|
||||
switch (filebehave) {
|
||||
case FILE_GZIP:
|
||||
nr = gzread(gzbufdesc, buffer, MAXBUFSIZ);
|
||||
break;
|
||||
#ifndef WITHOUT_BZIP2
|
||||
case FILE_BZIP:
|
||||
if (bzbufdesc != NULL) {
|
||||
int bzerr;
|
||||
|
||||
nr = BZ2_bzRead(&bzerr, bzbufdesc, buffer, MAXBUFSIZ);
|
||||
switch (bzerr) {
|
||||
case BZ_OK:
|
||||
case BZ_STREAM_END:
|
||||
/* No problem, nr will be okay */
|
||||
break;
|
||||
case BZ_DATA_ERROR_MAGIC:
|
||||
/*
|
||||
* As opposed to gzread(), which simply returns the
|
||||
* plain file data, if it is not in the correct
|
||||
* compressed format, BZ2_bzRead() instead aborts.
|
||||
*
|
||||
* So, just restart at the beginning of the file again,
|
||||
* and use plain reads from now on.
|
||||
*/
|
||||
BZ2_bzReadClose(&bzerr, bzbufdesc);
|
||||
bzbufdesc = NULL;
|
||||
if (lseek(f->fd, 0, SEEK_SET) == -1)
|
||||
return (-1);
|
||||
nr = read(f->fd, buffer, MAXBUFSIZ);
|
||||
break;
|
||||
default:
|
||||
/* Make sure we exit with an error */
|
||||
nr = -1;
|
||||
}
|
||||
} else
|
||||
/*
|
||||
* Also an error case; we should never have a scenario
|
||||
* where we have an open file but no bzip descriptor
|
||||
* at this point. See: grep_open
|
||||
*/
|
||||
nr = -1;
|
||||
break;
|
||||
#endif
|
||||
#ifndef WITHOUT_LZMA
|
||||
case FILE_XZ:
|
||||
case FILE_LZMA:
|
||||
lstrm.next_out = buffer;
|
||||
|
||||
do {
|
||||
if (lstrm.avail_in == 0) {
|
||||
lstrm.next_in = lin_buf;
|
||||
nr = read(f->fd, lin_buf, MAXBUFSIZ);
|
||||
|
||||
if (nr < 0)
|
||||
return (-1);
|
||||
else if (nr == 0)
|
||||
laction = LZMA_FINISH;
|
||||
|
||||
lstrm.avail_in = nr;
|
||||
}
|
||||
|
||||
lzmaret = lzma_code(&lstrm, laction);
|
||||
|
||||
if (lzmaret != LZMA_OK && lzmaret != LZMA_STREAM_END)
|
||||
return (-1);
|
||||
|
||||
if (lstrm.avail_out == 0 || lzmaret == LZMA_STREAM_END) {
|
||||
bufrem = MAXBUFSIZ - lstrm.avail_out;
|
||||
lstrm.next_out = buffer;
|
||||
lstrm.avail_out = MAXBUFSIZ;
|
||||
}
|
||||
} while (bufrem == 0 && lzmaret != LZMA_STREAM_END);
|
||||
|
||||
return (0);
|
||||
#endif /* WITHOUT_LZMA */
|
||||
default:
|
||||
nr = read(f->fd, buffer, MAXBUFSIZ);
|
||||
}
|
||||
nr = read(f->fd, buffer, MAXBUFSIZ);
|
||||
if (nr < 0)
|
||||
return (-1);
|
||||
|
||||
@ -269,9 +170,6 @@ struct file *
|
||||
grep_open(const char *path)
|
||||
{
|
||||
struct file *f;
|
||||
#ifndef WITHOUT_LZMA
|
||||
lzma_ret lzmaret;
|
||||
#endif
|
||||
|
||||
f = grep_malloc(sizeof *f);
|
||||
memset(f, 0, sizeof *f);
|
||||
@ -309,37 +207,6 @@ grep_open(const char *path)
|
||||
if ((buffer == NULL) || (buffer == MAP_FAILED))
|
||||
buffer = grep_malloc(MAXBUFSIZ);
|
||||
|
||||
switch (filebehave) {
|
||||
case FILE_GZIP:
|
||||
if ((gzbufdesc = gzdopen(f->fd, "r")) == NULL)
|
||||
goto error2;
|
||||
break;
|
||||
#ifndef WITHOUT_BZIP2
|
||||
case FILE_BZIP:
|
||||
if ((bzbufdesc = BZ2_bzdopen(f->fd, "r")) == NULL)
|
||||
goto error2;
|
||||
break;
|
||||
#endif
|
||||
#ifndef WITHOUT_LZMA
|
||||
case FILE_XZ:
|
||||
case FILE_LZMA:
|
||||
|
||||
if (filebehave == FILE_XZ)
|
||||
lzmaret = lzma_stream_decoder(&lstrm, UINT64_MAX,
|
||||
LZMA_CONCATENATED);
|
||||
else
|
||||
lzmaret = lzma_alone_decoder(&lstrm, UINT64_MAX);
|
||||
|
||||
if (lzmaret != LZMA_OK)
|
||||
goto error2;
|
||||
|
||||
lstrm.avail_in = 0;
|
||||
lstrm.avail_out = MAXBUFSIZ;
|
||||
laction = LZMA_RUN;
|
||||
break;
|
||||
#endif
|
||||
}
|
||||
|
||||
/* Fill read buffer, also catches errors early */
|
||||
if (bufrem == 0 && grep_refill(f) != 0)
|
||||
goto error2;
|
||||
|
@ -30,17 +30,16 @@
|
||||
.\"
|
||||
.\" @(#)grep.1 8.3 (Berkeley) 4/18/94
|
||||
.\"
|
||||
.Dd April 17, 2017
|
||||
.Dd April 25, 2018
|
||||
.Dt GREP 1
|
||||
.Os
|
||||
.Sh NAME
|
||||
.Nm grep , egrep , fgrep , rgrep ,
|
||||
.Nm zgrep , zegrep , zfgrep
|
||||
.Nd file pattern searcher
|
||||
.Sh SYNOPSIS
|
||||
.Nm grep
|
||||
.Bk -words
|
||||
.Op Fl abcdDEFGHhIiJLlmnOopqRSsUVvwxZz
|
||||
.Op Fl abcdDEFGHhIiLlmnOopqRSsUVvwxz
|
||||
.Op Fl A Ar num
|
||||
.Op Fl B Ar num
|
||||
.Op Fl C Ns Op Ar num
|
||||
@ -88,21 +87,6 @@ but can only handle fixed patterns
|
||||
Patterns may consist of one or more lines,
|
||||
allowing any of the pattern lines to match a portion of the input.
|
||||
.Pp
|
||||
.Nm zgrep ,
|
||||
.Nm zegrep ,
|
||||
and
|
||||
.Nm zfgrep
|
||||
act like
|
||||
.Nm grep ,
|
||||
.Nm egrep ,
|
||||
and
|
||||
.Nm fgrep ,
|
||||
respectively, but accept input files compressed with the
|
||||
.Xr compress 1
|
||||
or
|
||||
.Xr gzip 1
|
||||
compression utilities.
|
||||
.Pp
|
||||
The following options are available:
|
||||
.Bl -tag -width indent
|
||||
.It Fl A Ar num , Fl Fl after-context Ns = Ns Ar num
|
||||
@ -274,10 +258,6 @@ Note that
|
||||
patterns take priority over
|
||||
.Fl Fl include-dir
|
||||
patterns.
|
||||
.It Fl J, Fl Fl bz2decompress
|
||||
Decompress the
|
||||
.Xr bzip2 1
|
||||
compressed file before looking for the text.
|
||||
.It Fl L , Fl Fl files-without-match
|
||||
Only the names of files not containing selected lines are written to
|
||||
standard output.
|
||||
@ -381,11 +361,6 @@ Obsoleted.
|
||||
.It Fl z , Fl Fl null-data
|
||||
Treat input and output data as sequences of lines terminated by a
|
||||
zero-byte instead of a newline.
|
||||
.It Fl Z , Fl Fl decompress
|
||||
Force
|
||||
.Nm grep
|
||||
to behave as
|
||||
.Nm zgrep .
|
||||
.It Fl Fl binary-files Ns = Ns Ar value
|
||||
Controls searching and printing of binary files.
|
||||
Options are
|
||||
@ -465,7 +440,6 @@ looking for either 19, 20, or 25.
|
||||
.Sh SEE ALSO
|
||||
.Xr ed 1 ,
|
||||
.Xr ex 1 ,
|
||||
.Xr gzip 1 ,
|
||||
.Xr sed 1 ,
|
||||
.Xr re_format 7
|
||||
.Sh STANDARDS
|
||||
|
@ -68,9 +68,8 @@ nl_catd catalog;
|
||||
const char *errstr[] = {
|
||||
"",
|
||||
/* 1*/ "(standard input)",
|
||||
/* 2*/ "cannot read bzip2 compressed file",
|
||||
/* 3*/ "unknown %s option",
|
||||
/* 4*/ "usage: %s [-abcDEFGHhIiJLlmnOoPqRSsUVvwxZz] [-A num] [-B num] [-C[num]]\n",
|
||||
/* 4*/ "usage: %s [-abcDEFGHhIiLlmnOoPqRSsUVvwxz] [-A num] [-B num] [-C[num]]\n",
|
||||
/* 5*/ "\t[-e pattern] [-f file] [--binary-files=value] [--color=when]\n",
|
||||
/* 6*/ "\t[--context[=num]] [--directories=action] [--label] [--line-buffered]\n",
|
||||
/* 7*/ "\t[--null] [pattern] [file ...]\n",
|
||||
@ -136,7 +135,7 @@ char *label; /* --label */
|
||||
const char *color; /* --color */
|
||||
int grepbehave = GREP_BASIC; /* -EFGP: type of the regex */
|
||||
int binbehave = BINFILE_BIN; /* -aIU: handling of binary files */
|
||||
int filebehave = FILE_STDIO; /* -JZ: normal, gzip or bzip2 file */
|
||||
int filebehave = FILE_STDIO;
|
||||
int devbehave = DEV_READ; /* -D: handling of devices */
|
||||
int dirbehave = DIR_READ; /* -dRr: handling of directories */
|
||||
int linkbehave = LINK_READ; /* -OpS: handling of symlinks */
|
||||
@ -169,14 +168,14 @@ bool file_err; /* file reading error */
|
||||
static void
|
||||
usage(void)
|
||||
{
|
||||
fprintf(stderr, getstr(4), getprogname());
|
||||
fprintf(stderr, getstr(3), getprogname());
|
||||
fprintf(stderr, "%s", getstr(4));
|
||||
fprintf(stderr, "%s", getstr(5));
|
||||
fprintf(stderr, "%s", getstr(6));
|
||||
fprintf(stderr, "%s", getstr(7));
|
||||
exit(2);
|
||||
}
|
||||
|
||||
static const char *optstr = "0123456789A:B:C:D:EFGHIJMLOPSRUVZabcd:e:f:hilm:nopqrsuvwxXyz";
|
||||
static const char *optstr = "0123456789A:B:C:D:EFGHILOPSRUVabcd:e:f:hilm:nopqrsuvwxyz";
|
||||
|
||||
static const struct option long_options[] =
|
||||
{
|
||||
@ -208,11 +207,9 @@ static const struct option long_options[] =
|
||||
{"no-filename", no_argument, NULL, 'h'},
|
||||
{"with-filename", no_argument, NULL, 'H'},
|
||||
{"ignore-case", no_argument, NULL, 'i'},
|
||||
{"bz2decompress", no_argument, NULL, 'J'},
|
||||
{"files-with-matches", no_argument, NULL, 'l'},
|
||||
{"files-without-match", no_argument, NULL, 'L'},
|
||||
{"max-count", required_argument, NULL, 'm'},
|
||||
{"lzma", no_argument, NULL, 'M'},
|
||||
{"line-number", no_argument, NULL, 'n'},
|
||||
{"only-matching", no_argument, NULL, 'o'},
|
||||
{"quiet", no_argument, NULL, 'q'},
|
||||
@ -225,9 +222,7 @@ static const struct option long_options[] =
|
||||
{"version", no_argument, NULL, 'V'},
|
||||
{"word-regexp", no_argument, NULL, 'w'},
|
||||
{"line-regexp", no_argument, NULL, 'x'},
|
||||
{"xz", no_argument, NULL, 'X'},
|
||||
{"null-data", no_argument, NULL, 'z'},
|
||||
{"decompress", no_argument, NULL, 'Z'},
|
||||
{NULL, no_argument, NULL, 0}
|
||||
};
|
||||
|
||||
@ -367,21 +362,9 @@ main(int argc, char *argv[])
|
||||
way we can have all the funcionalities in one binary
|
||||
without the need of scripting and using ugly hacks. */
|
||||
pn = getprogname();
|
||||
if (pn[0] == 'b' && pn[1] == 'z') {
|
||||
filebehave = FILE_BZIP;
|
||||
pn += 2;
|
||||
} else if (pn[0] == 'x' && pn[1] == 'z') {
|
||||
filebehave = FILE_XZ;
|
||||
pn += 2;
|
||||
} else if (pn[0] == 'l' && pn[1] == 'z') {
|
||||
filebehave = FILE_LZMA;
|
||||
pn += 2;
|
||||
} else if (pn[0] == 'r') {
|
||||
if (pn[0] == 'r') {
|
||||
dirbehave = DIR_RECURSE;
|
||||
Hflag = true;
|
||||
} else if (pn[0] == 'z') {
|
||||
filebehave = FILE_GZIP;
|
||||
pn += 1;
|
||||
}
|
||||
switch (pn[0]) {
|
||||
case 'e':
|
||||
@ -490,7 +473,7 @@ main(int argc, char *argv[])
|
||||
else if (strcasecmp(optarg, "read") == 0)
|
||||
devbehave = DEV_READ;
|
||||
else
|
||||
errx(2, getstr(3), "--devices");
|
||||
errx(2, getstr(2), "--devices");
|
||||
break;
|
||||
case 'd':
|
||||
if (strcasecmp("recurse", optarg) == 0) {
|
||||
@ -501,7 +484,7 @@ main(int argc, char *argv[])
|
||||
else if (strcasecmp("read", optarg) == 0)
|
||||
dirbehave = DIR_READ;
|
||||
else
|
||||
errx(2, getstr(3), "--directories");
|
||||
errx(2, getstr(2), "--directories");
|
||||
break;
|
||||
case 'E':
|
||||
grepbehave = GREP_EXTENDED;
|
||||
@ -541,13 +524,6 @@ main(int argc, char *argv[])
|
||||
iflag = true;
|
||||
cflags |= REG_ICASE;
|
||||
break;
|
||||
case 'J':
|
||||
#ifdef WITHOUT_BZIP2
|
||||
errno = EOPNOTSUPP;
|
||||
err(2, "bzip2 support was disabled at compile-time");
|
||||
#endif
|
||||
filebehave = FILE_BZIP;
|
||||
break;
|
||||
case 'L':
|
||||
lflag = false;
|
||||
Lflag = true;
|
||||
@ -568,9 +544,6 @@ main(int argc, char *argv[])
|
||||
err(2, NULL);
|
||||
}
|
||||
break;
|
||||
case 'M':
|
||||
filebehave = FILE_LZMA;
|
||||
break;
|
||||
case 'n':
|
||||
nflag = true;
|
||||
break;
|
||||
@ -607,9 +580,9 @@ main(int argc, char *argv[])
|
||||
break;
|
||||
case 'V':
|
||||
#ifdef WITH_GNU
|
||||
printf(getstr(10), getprogname(), VERSION);
|
||||
#else
|
||||
printf(getstr(9), getprogname(), VERSION);
|
||||
#else
|
||||
printf(getstr(8), getprogname(), VERSION);
|
||||
#endif
|
||||
exit(0);
|
||||
case 'v':
|
||||
@ -623,15 +596,9 @@ main(int argc, char *argv[])
|
||||
xflag = true;
|
||||
cflags &= ~REG_NOSUB;
|
||||
break;
|
||||
case 'X':
|
||||
filebehave = FILE_XZ;
|
||||
break;
|
||||
case 'z':
|
||||
fileeol = '\0';
|
||||
break;
|
||||
case 'Z':
|
||||
filebehave = FILE_GZIP;
|
||||
break;
|
||||
case BIN_OPT:
|
||||
if (strcasecmp("binary", optarg) == 0)
|
||||
binbehave = BINFILE_BIN;
|
||||
@ -640,7 +607,7 @@ main(int argc, char *argv[])
|
||||
else if (strcasecmp("text", optarg) == 0)
|
||||
binbehave = BINFILE_TEXT;
|
||||
else
|
||||
errx(2, getstr(3), "--binary-files");
|
||||
errx(2, getstr(2), "--binary-files");
|
||||
break;
|
||||
case COLOR_OPT:
|
||||
color = NULL;
|
||||
@ -660,7 +627,7 @@ main(int argc, char *argv[])
|
||||
} else if (strcasecmp("never", optarg) != 0 &&
|
||||
strcasecmp("none", optarg) != 0 &&
|
||||
strcasecmp("no", optarg) != 0)
|
||||
errx(2, getstr(3), "--color");
|
||||
errx(2, getstr(2), "--color");
|
||||
cflags &= ~REG_NOSUB;
|
||||
break;
|
||||
case LABEL_OPT:
|
||||
|
@ -69,10 +69,6 @@ extern const char *errstr[];
|
||||
|
||||
#define FILE_STDIO 0
|
||||
#define FILE_MMAP 1
|
||||
#define FILE_GZIP 2
|
||||
#define FILE_BZIP 3
|
||||
#define FILE_XZ 4
|
||||
#define FILE_LZMA 5
|
||||
|
||||
#define DIR_READ 0
|
||||
#define DIR_SKIP 1
|
||||
|
Loading…
Reference in New Issue
Block a user