lzip/zutils
1
0
Fork 0
Code Issues Activity

Adding upstream version 0.8.

Browse source 
Signed-off-by: Daniel Baumann <daniel@debian.org>
This commit is contained in:
Daniel Baumann 2025-02-24 05:01:08 +01:00
parent 7877117516
commit 056171c0b2
Signed by: daniel
GPG key ID: FBB4F0E80A80222F
32 changed files with 3798 additions and 1551 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

23
ChangeLog
View file

@ -1,6 +1,19 @@
2009-12-01 Antonio Diaz Diaz <ant_diaz@teleline.es>
2010-11-15 Antonio Diaz Diaz <ant_diaz@teleline.es>
* Version 0.8-rc1 released.
* Version 0.8 released.
* main.cc: Added new options "--zcat", "--zgrep" and "--ztest".
* zcat.cc: New file implementing zcat+cat functionality in C++.
* zcmp.cc: New file implementing zcmp+cmp functionality in C++.
* doc/zcmp.1: New file.
* zcmp.in: Removed.
* zdiff.cc: New file implementing zdiff functionality in C++.
* zdiff.in: Removed.
* zgrep.cc: New file implementing zgrep functionality in C++.
* All mentions to zegrep and zfgrep have been removed from the
documentation because egrep and fgrep are deprecated.
* ztest.cc: New file implementing ztest functionality in C++.
* Makefile.in: Added quotes to directory names.
* testsuite/check.sh: Use "test.txt" instead of "COPYING" for testing.
* Removed environment safeguards from configure as requested by
Richard Stallman. Now environment variables affect configure.
@ -46,8 +59,8 @@
* Version 0.1 released.
Copyright (C) 2009 Antonio Diaz Diaz.
Copyright (C) 2009, 2010 Antonio Diaz Diaz.
This file is a collection of facts, and thus it is not copyrightable,
but just in case, I give you unlimited permission to copy, distribute
and modify it.
but just in case, you have unlimited permission to copy, distribute and
modify it.

2
INSTALL
View file

@ -55,7 +55,7 @@ After running `configure', you can run `make' and `make install' as
explained above.
Copyright (C) 2009 Antonio Diaz Diaz.
Copyright (C) 2009, 2010 Antonio Diaz Diaz.
This file is free documentation: you have unlimited permission to copy,
distribute and modify it.

159
Makefile.in
View file

@ -1,5 +1,5 @@
DISTNAME = $(progname)-$(progversion)
DISTNAME = $(pkgname)-$(pkgversion)
INSTALL = install
INSTALL_PROGRAM = $(INSTALL) -p -m 755
INSTALL_SCRIPT = $(INSTALL) -p -m 755
@ -7,33 +7,33 @@ INSTALL_DATA = $(INSTALL) -p -m 644
INSTALL_DIR = $(INSTALL) -d -m 755
SHELL = /bin/sh
objs = arg_parser.o main.o
scripts = zcat zcmp zdiff zegrep zfgrep zgrep ztest
objs = arg_parser.o zutils.o main.o
zcmp_objs = arg_parser.o zutils.o zcmp.o
zdiff_objs = arg_parser.o zutils.o zdiff.o
scripts = zcat zegrep zfgrep zgrep ztest
.PHONY : all install install-info install-man install-strip \
uninstall uninstall-info uninstall-man \
doc info man check dist clean distclean
all : $(progname) $(scripts)
all : $(progname) zcmp zdiff $(scripts)
$(progname) : $(objs)
$(CXX) $(LDFLAGS) -o $(progname) $(objs)
$(CXX) $(LDFLAGS) -o $@ $(objs)
$(progname)_profiled : $(objs)
$(CXX) $(LDFLAGS) -pg -o $(progname)_profiled $(objs)
$(CXX) $(LDFLAGS) -pg -o $@ $(objs)
zcat : zcat.in
sed -e 's,VERSION,$(progversion),g' $(VPATH)/zcat.in > zcat
cat $(VPATH)/zcat.in > zcat
chmod a+x zcat
zcmp : zcmp.in
cat $(VPATH)/zcmp.in > zcmp
chmod a+x zcmp
zcmp : $(zcmp_objs)
$(CXX) $(LDFLAGS) -o $@ $(zcmp_objs)
zdiff : zdiff.in
sed -e 's,VERSION,$(progversion),g' $(VPATH)/zdiff.in > zdiff
chmod a+x zdiff
zdiff : $(zdiff_objs)
$(CXX) $(LDFLAGS) -o $@ $(zdiff_objs)
zegrep : zegrep.in
cat $(VPATH)/zegrep.in > zegrep
@ -44,15 +44,15 @@ zfgrep : zfgrep.in
chmod a+x zfgrep
zgrep : zgrep.in
sed -e 's,VERSION,$(progversion),g' $(VPATH)/zgrep.in > zgrep
cat $(VPATH)/zgrep.in > zgrep
chmod a+x zgrep
ztest : ztest.in
sed -e 's,VERSION,$(progversion),g' $(VPATH)/ztest.in > ztest
cat $(VPATH)/ztest.in > ztest
chmod a+x ztest
main.o : main.cc
$(CXX) $(CPPFLAGS) $(CXXFLAGS) -DPROGVERSION=\"$(progversion)\" -c -o $@ $<
zutils.o : zutils.cc
$(CXX) $(CPPFLAGS) $(CXXFLAGS) -DPROGVERSION=\"$(pkgversion)\" -c -o $@ $<
%.o : %.cc
$(CXX) $(CPPFLAGS) $(CXXFLAGS) -c -o $@ $<
@ -60,96 +60,100 @@ main.o : main.cc
$(objs) : Makefile
$(scripts) : Makefile
arg_parser.o : arg_parser.h
main.o : arg_parser.h
main.o : arg_parser.h zutils.h zcat.cc zgrep.cc ztest.cc
zcmp.o : arg_parser.h zutils.h Makefile
zdiff.o : arg_parser.h zutils.h Makefile
zutils.o : zutils.h
doc : info man
info : $(VPATH)/doc/$(progname).info
info : $(VPATH)/doc/$(pkgname).info
$(VPATH)/doc/$(progname).info : $(VPATH)/doc/$(progname).texinfo
cd $(VPATH)/doc && makeinfo $(progname).texinfo
$(VPATH)/doc/$(pkgname).info : $(VPATH)/doc/$(pkgname).texinfo
cd $(VPATH)/doc && makeinfo $(pkgname).texinfo
man : $(VPATH)/doc/zcat.1 $(VPATH)/doc/zdiff.1 \
man : $(VPATH)/doc/zcat.1 $(VPATH)/doc/zcmp.1 $(VPATH)/doc/zdiff.1 \
$(VPATH)/doc/zgrep.1 $(VPATH)/doc/ztest.1
$(VPATH)/doc/zcat.1 : zcat
help2man -n 'concatenate compressed files to stdout' \
-o $(VPATH)/doc/zcat.1 --no-info ./zcat
$(VPATH)/doc/zcat.1 : $(progname) zcat
help2man -n 'decompress and concatenate files to standard output' \
-o $@ --no-info ./zcat
$(VPATH)/doc/zcmp.1 : zcmp
help2man -n 'decompress and compare two files byte by byte' \
-o $@ --no-info ./zcmp
$(VPATH)/doc/zdiff.1 : zdiff
help2man -n 'compare compressed files' \
-o $(VPATH)/doc/zdiff.1 --no-info ./zdiff
help2man -n 'decompress and compare two files line by line' \
-o $@ --no-info ./zdiff
$(VPATH)/doc/zgrep.1 : zgrep
$(VPATH)/doc/zgrep.1 : $(progname) zgrep
help2man -n 'search compressed files for a regular expression' \
-o $(VPATH)/doc/zgrep.1 --no-info ./zgrep
-o $@ --no-info ./zgrep
$(VPATH)/doc/ztest.1 : ztest
$(VPATH)/doc/ztest.1 : $(progname) ztest
help2man -n 'verify integrity of compressed files' \
-o $(VPATH)/doc/ztest.1 --no-info ./ztest
-o $@ --no-info ./ztest
Makefile : $(VPATH)/configure $(VPATH)/Makefile.in
./config.status
check : all $(VPATH)/testsuite/check.sh
@$(VPATH)/testsuite/check.sh $(VPATH)/testsuite
check : all
@$(VPATH)/testsuite/check.sh $(VPATH)/testsuite $(pkgversion)
install : all install-info install-man
if [ ! -d $(DESTDIR)$(bindir) ] ; then $(INSTALL_DIR) $(DESTDIR)$(bindir) ; fi
$(INSTALL_PROGRAM) ./$(progname) $(DESTDIR)$(bindir)/$(progname)
$(INSTALL_SCRIPT) zcat $(DESTDIR)$(bindir)/zcat
$(INSTALL_SCRIPT) zcmp $(DESTDIR)$(bindir)/zcmp
$(INSTALL_SCRIPT) zdiff $(DESTDIR)$(bindir)/zdiff
$(INSTALL_SCRIPT) zegrep $(DESTDIR)$(bindir)/zegrep
$(INSTALL_SCRIPT) zfgrep $(DESTDIR)$(bindir)/zfgrep
$(INSTALL_SCRIPT) zgrep $(DESTDIR)$(bindir)/zgrep
$(INSTALL_SCRIPT) ztest $(DESTDIR)$(bindir)/ztest
if [ ! -d "$(DESTDIR)$(bindir)" ] ; then $(INSTALL_DIR) "$(DESTDIR)$(bindir)" ; fi
$(INSTALL_PROGRAM) ./$(progname) "$(DESTDIR)$(bindir)/$(progname)"
$(INSTALL_SCRIPT) ./zcat "$(DESTDIR)$(bindir)/zcat"
$(INSTALL_PROGRAM) ./zcmp "$(DESTDIR)$(bindir)/zcmp"
$(INSTALL_PROGRAM) ./zdiff "$(DESTDIR)$(bindir)/zdiff"
$(INSTALL_SCRIPT) ./zegrep "$(DESTDIR)$(bindir)/zegrep"
$(INSTALL_SCRIPT) ./zfgrep "$(DESTDIR)$(bindir)/zfgrep"
$(INSTALL_SCRIPT) ./zgrep "$(DESTDIR)$(bindir)/zgrep"
$(INSTALL_SCRIPT) ./ztest "$(DESTDIR)$(bindir)/ztest"
install-info :
if [ ! -d $(DESTDIR)$(infodir) ] ; then $(INSTALL_DIR) $(DESTDIR)$(infodir) ; fi
$(INSTALL_DATA) $(VPATH)/doc/$(progname).info $(DESTDIR)$(infodir)/$(progname).info
-install-info --info-dir=$(DESTDIR)$(infodir) $(DESTDIR)$(infodir)/$(progname).info
if [ ! -d "$(DESTDIR)$(infodir)" ] ; then $(INSTALL_DIR) "$(DESTDIR)$(infodir)" ; fi
$(INSTALL_DATA) $(VPATH)/doc/$(pkgname).info "$(DESTDIR)$(infodir)/$(pkgname).info"
-install-info --info-dir="$(DESTDIR)$(infodir)" $(DESTDIR)$(infodir)/$(pkgname).info
install-man :
if [ ! -d $(DESTDIR)$(mandir)/man1 ] ; then $(INSTALL_DIR) $(DESTDIR)$(mandir)/man1 ; fi
$(INSTALL_DATA) $(VPATH)/doc/zcat.1 $(DESTDIR)$(mandir)/man1/zcat.1
-rm -f $(DESTDIR)$(mandir)/man1/zcmp.1
cd $(DESTDIR)$(mandir)/man1 && ln -s zdiff.1 zcmp.1
$(INSTALL_DATA) $(VPATH)/doc/zdiff.1 $(DESTDIR)$(mandir)/man1/zdiff.1
$(INSTALL_DATA) $(VPATH)/doc/zgrep.1 $(DESTDIR)$(mandir)/man1/zgrep.1
-rm -f $(DESTDIR)$(mandir)/man1/zegrep.1
-rm -f $(DESTDIR)$(mandir)/man1/zfgrep.1
cd $(DESTDIR)$(mandir)/man1 && ln -s zgrep.1 zegrep.1
cd $(DESTDIR)$(mandir)/man1 && ln -s zgrep.1 zfgrep.1
$(INSTALL_DATA) $(VPATH)/doc/ztest.1 $(DESTDIR)$(mandir)/man1/ztest.1
if [ ! -d "$(DESTDIR)$(mandir)/man1" ] ; then $(INSTALL_DIR) "$(DESTDIR)$(mandir)/man1" ; fi
$(INSTALL_DATA) $(VPATH)/doc/zcat.1 "$(DESTDIR)$(mandir)/man1/zcat.1"
$(INSTALL_DATA) $(VPATH)/doc/zcmp.1 "$(DESTDIR)$(mandir)/man1/zcmp.1"
$(INSTALL_DATA) $(VPATH)/doc/zdiff.1 "$(DESTDIR)$(mandir)/man1/zdiff.1"
$(INSTALL_DATA) $(VPATH)/doc/zgrep.1 "$(DESTDIR)$(mandir)/man1/zgrep.1"
-rm -f "$(DESTDIR)$(mandir)/man1/zegrep.1"
-rm -f "$(DESTDIR)$(mandir)/man1/zfgrep.1"
$(INSTALL_DATA) $(VPATH)/doc/ztest.1 "$(DESTDIR)$(mandir)/man1/ztest.1"
install-strip : all
$(MAKE) INSTALL_PROGRAM='$(INSTALL_PROGRAM) -s' install
uninstall : uninstall-info uninstall-man
-rm -f $(DESTDIR)$(bindir)/$(progname)
-rm -f $(DESTDIR)$(bindir)/zcat
-rm -f $(DESTDIR)$(bindir)/zcmp
-rm -f $(DESTDIR)$(bindir)/zdiff
-rm -f $(DESTDIR)$(bindir)/zegrep
-rm -f $(DESTDIR)$(bindir)/zfgrep
-rm -f $(DESTDIR)$(bindir)/zgrep
-rm -f $(DESTDIR)$(bindir)/ztest
-rm -f "$(DESTDIR)$(bindir)/$(progname)"
-rm -f "$(DESTDIR)$(bindir)/zcat"
-rm -f "$(DESTDIR)$(bindir)/zcmp"
-rm -f "$(DESTDIR)$(bindir)/zdiff"
-rm -f "$(DESTDIR)$(bindir)/zegrep"
-rm -f "$(DESTDIR)$(bindir)/zfgrep"
-rm -f "$(DESTDIR)$(bindir)/zgrep"
-rm -f "$(DESTDIR)$(bindir)/ztest"
uninstall-info :
-install-info --info-dir=$(DESTDIR)$(infodir) --remove $(DESTDIR)$(infodir)/$(progname).info
-rm -f $(DESTDIR)$(infodir)/$(progname).info
-install-info --info-dir="$(DESTDIR)$(infodir)" --remove "$(DESTDIR)$(infodir)/$(pkgname).info"
-rm -f "$(DESTDIR)$(infodir)/$(pkgname).info"
uninstall-man :
-rm -f $(DESTDIR)$(mandir)/man1/zcat.1
-rm -f $(DESTDIR)$(mandir)/man1/zcmp.1
-rm -f $(DESTDIR)$(mandir)/man1/zdiff.1
-rm -f $(DESTDIR)$(mandir)/man1/zegrep.1
-rm -f $(DESTDIR)$(mandir)/man1/zfgrep.1
-rm -f $(DESTDIR)$(mandir)/man1/zgrep.1
-rm -f $(DESTDIR)$(mandir)/man1/ztest.1
-rm -f "$(DESTDIR)$(mandir)/man1/zcat.1"
-rm -f "$(DESTDIR)$(mandir)/man1/zcmp.1"
-rm -f "$(DESTDIR)$(mandir)/man1/zdiff.1"
-rm -f "$(DESTDIR)$(mandir)/man1/zegrep.1"
-rm -f "$(DESTDIR)$(mandir)/man1/zfgrep.1"
-rm -f "$(DESTDIR)$(mandir)/man1/zgrep.1"
-rm -f "$(DESTDIR)$(mandir)/man1/ztest.1"
dist :
dist : doc
ln -sf $(VPATH) $(DISTNAME)
tar -cvf $(DISTNAME).tar \
$(DISTNAME)/AUTHORS \
@ -161,9 +165,10 @@ dist :
$(DISTNAME)/README \
$(DISTNAME)/configure \
$(DISTNAME)/doc/*.1 \
$(DISTNAME)/doc/$(progname).info \
$(DISTNAME)/doc/$(progname).texinfo \
$(DISTNAME)/doc/$(pkgname).info \
$(DISTNAME)/doc/$(pkgname).texinfo \
$(DISTNAME)/testsuite/check.sh \
$(DISTNAME)/testsuite/test.txt \
$(DISTNAME)/*.h \
$(DISTNAME)/*.cc \
$(DISTNAME)/z*.in
@ -172,7 +177,7 @@ dist :
clean :
-rm -f $(progname) $(progname)_profiled $(objs)
-rm -f $(scripts)
-rm -f zcmp zcmp.o zdiff zdiff.o $(scripts)
distclean : clean
-rm -f Makefile config.status *.tar *.tar.lz

11
NEWS
View file

@ -1,4 +1,15 @@
Changes in version 0.8:
The option "--recursive" has been added to zgrep.
All the utilities have been rewritten in C++, making them safer and more
efficient.
Zcat and zcmp implement the functionality of cat and cmp respectively.
Cat and cmp are not needed at runtime.
All mentions to zegrep and zfgrep have been removed from the
documentation because egrep and fgrep are deprecated.
Environment safeguards from configure have been removed. This allows
environment variables to affect configuration.

20
README
View file

@ -1,18 +1,22 @@
Description
Zutils is a collection of utilities for dealing with any combination of
compressed and non-compressed files transparently. The supported
compressors are bzip2, gzip, lzip and xz.
Zutils is a collection of utilities able to deal with any combination of
compressed and non-compressed files transparently. If any given file,
including standard input, is compressed, its uncompressed content is
used. Compressed files are decompressed on the fly; no temporary files
are created. These utilities are not wrapper scripts but safer and more
efficient C++ programs. In particular the "--recursive" option is very
efficient in those utilities supporting it.
The currently provided utilities are zcat, zcmp, zdiff, zegrep, zfgrep,
zgrep and ztest.
The provided utilities are zcat, zcmp, zdiff, zgrep and ztest.
The supported compressors are bzip2, gzip, lzip and xz.
Copyright (C) 2009 Antonio Diaz Diaz.
Copyright (C) 2009, 2010 Antonio Diaz Diaz.
This file is free documentation: you have unlimited permission to copy,
distribute and modify it.
The file Makefile.in is a data file used by configure to produce the
Makefile. It has the same copyright owner and permissions that this
file.
Makefile. It has the same copyright owner and permissions that configure
itself.

20
arg_parser.cc
View file

@ -1,18 +1,28 @@
/* Arg_parser - A POSIX/GNU command line argument parser.
Copyright (C) 2006, 2007, 2008, 2009 Antonio Diaz Diaz.
/* Arg_parser - A POSIX/GNU command line argument parser. (C++ version)
Copyright (C) 2006, 2007, 2008, 2009, 2010 Antonio Diaz Diaz.
This program is free software: you can redistribute it and/or modify
This library is free software: you can redistribute it and/or modify
it under the terms of the GNU General Public License as published by
the Free Software Foundation, either version 3 of the License, or
(at your option) any later version.
This program is distributed in the hope that it will be useful,
This library is distributed in the hope that it will be useful,
but WITHOUT ANY WARRANTY; without even the implied warranty of
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
GNU General Public License for more details.
You should have received a copy of the GNU General Public License
along with this program. If not, see <http://www.gnu.org/licenses/>.
along with this library. If not, see <http://www.gnu.org/licenses/>.
As a special exception, you may use this file as part of a free
software library without restriction. Specifically, if other files
instantiate templates or use macros or inline functions from this
file, or you compile this file and link it with other files to
produce an executable, this file does not by itself cause the
resulting executable to be covered by the GNU General Public
License. This exception does not however invalidate any other
reasons why the executable file might be covered by the GNU General
Public License.
*/
#include <cstring>

20
arg_parser.h
View file

@ -1,18 +1,28 @@
/* Arg_parser - A POSIX/GNU command line argument parser.
Copyright (C) 2006, 2007, 2008, 2009 Antonio Diaz Diaz.
/* Arg_parser - A POSIX/GNU command line argument parser. (C++ version)
Copyright (C) 2006, 2007, 2008, 2009, 2010 Antonio Diaz Diaz.
This program is free software: you can redistribute it and/or modify
This library is free software: you can redistribute it and/or modify
it under the terms of the GNU General Public License as published by
the Free Software Foundation, either version 3 of the License, or
(at your option) any later version.
This program is distributed in the hope that it will be useful,
This library is distributed in the hope that it will be useful,
but WITHOUT ANY WARRANTY; without even the implied warranty of
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
GNU General Public License for more details.
You should have received a copy of the GNU General Public License
along with this program. If not, see <http://www.gnu.org/licenses/>.
along with this library. If not, see <http://www.gnu.org/licenses/>.
As a special exception, you may use this file as part of a free
software library without restriction. Specifically, if other files
instantiate templates or use macros or inline functions from this
file, or you compile this file and link it with other files to
produce an executable, this file does not by itself cause the
resulting executable to be covered by the GNU General Public
License. This exception does not however invalidate any other
reasons why the executable file might be covered by the GNU General
Public License.
*/
/* Arg_parser reads the arguments in `argv' and creates a number of

20
configure vendored
View file

@ -1,17 +1,18 @@
#! /bin/sh
# configure script for Zutils - Utilities dealing with compressed files
# Copyright (C) 2009 Antonio Diaz Diaz.
# Copyright (C) 2009, 2010 Antonio Diaz Diaz.
#
# This configure script is free software: you have unlimited permission
# to copy, distribute and modify it.
#
# Date of this version: 2009-12-01
# Date of this version: 2010-11-15
args=
no_create=
pkgname=zutils
pkgversion=0.8
progname=zutils
progversion=0.8-rc1
srctrigger=zdiff.in
srctrigger=zutils.h
# clear some things potentially inherited from environment.
LC_ALL=C
@ -69,7 +70,7 @@ while [ -n "$1" ] ; do
echo
exit 0 ;;
--version | --ve* | -V)
echo "Configure script for ${progname} version ${progversion}"
echo "Configure script for ${pkgname} version ${pkgversion}"
exit 0 ;;
--srcdir* | --sr*)
srcdir=`echo ${optarg} | sed -e 's,/$,,'` ;;
@ -81,7 +82,7 @@ while [ -n "$1" ] ; do
bindir=`echo ${optarg} | sed -e 's,/$,,'` ;;
--datadir* | --da*)
datadir=`echo ${optarg} | sed -e 's,/$,,'` ;;
--infodir* | --in*)
--infodir* | --inf*)
infodir=`echo ${optarg} | sed -e 's,/$,,'` ;;
--mandir* | --ma*)
mandir=`echo ${optarg} | sed -e 's,/$,,'` ;;
@ -136,7 +137,7 @@ if [ -z "${CXX}" ] ; then # Let the user override the test.
fi
echo
if [ x${no_create} = x ] ; then
if [ -z "${no_create}" ] ; then
echo "creating config.status"
rm -f config.status
cat > config.status << EOF
@ -168,14 +169,15 @@ echo "LDFLAGS = ${LDFLAGS}"
rm -f Makefile
cat > Makefile << EOF
# Makefile for Zutils - Utilities dealing with compressed files
# Copyright (C) 2009 Antonio Diaz Diaz.
# Copyright (C) 2009, 2010 Antonio Diaz Diaz.
# This file was generated automatically by configure. Do not edit.
#
# This Makefile is free software: you have unlimited permission
# to copy, distribute and modify it.
pkgname = ${pkgname}
pkgversion = ${pkgversion}
progname = ${progname}
progversion = ${progversion}
VPATH = ${srcdir}
prefix = ${prefix}
exec_prefix = ${exec_prefix}

67
doc/zcat.1
View file

@ -1,25 +1,22 @@
.\" DO NOT MODIFY THIS FILE! It was generated by help2man 1.36.
.TH ZCAT "1" "December 2009" "Zcat (zutils) 0.8-rc1" "User Commands"
.\" DO NOT MODIFY THIS FILE! It was generated by help2man 1.37.1.
.TH ZCAT "1" "November 2010" "Zcat (zutils) 0.8" "User Commands"
.SH NAME
Zcat \- concatenate compressed files to stdout
Zcat \- decompress and concatenate files to standard output
.SH SYNOPSIS
.B zcat
[\fIOPTIONS\fR] [\fICAT_OPTIONS\fR] [\fIFILES\fR]
[\fIoptions\fR] [\fIfiles\fR]
.SH DESCRIPTION
Zcat \- Cat wrapper for compressed files.
.PP
Zcat is a wrapper script around the cat command that allows transparent
concatenation of any combination of compressed and non\-compressed files.
If any given file is compressed, its uncompressed content is used. If a
given file does not exist, zcat tries the compressed file names
Zcat copies each given file ("\-" means standard input), to standard
output. If any given file is compressed, its uncompressed content is
used. If a given file does not exist, and its name does not end with one
of the known extensions, zcat tries the compressed file names
corresponding to the supported compressors. If no files are specified,
data is read from standard input, decompressed if needed, and sent to
stdout. Data read from standard input must be of the same type; all
uncompressed or all compressed with the same compressor.
standard output. Data read from standard input must be of the same type;
all uncompressed or all compressed with the same compressor.
The supported compressors are bzip2, gzip, lzip and xz.
.PP
CAT_OPTIONS are passed directly to cat.
The exit status from cat is preserved.
Exit status is 0 if no errors occurred, 1 otherwise.
.SH OPTIONS
.TP
\fB\-h\fR, \fB\-\-help\fR
@ -28,12 +25,48 @@ display this help and exit
\fB\-V\fR, \fB\-\-version\fR
output version information and exit
.TP
\fB\-A\fR, \fB\-\-show\-all\fR
equivalent to `\-vET'
.TP
\fB\-b\fR, \fB\-\-number\-nonblank\fR
number nonblank output lines
.TP
\fB\-e\fR
equivalent to `\-vE'
.TP
\fB\-E\fR, \fB\-\-show\-ends\fR
display `$' at end of each line
.TP
\fB\-n\fR, \fB\-\-number\fR
number all output lines
.TP
\fB\-q\fR, \fB\-\-quiet\fR
suppress all messages
.TP
\fB\-r\fR, \fB\-\-recursive\fR
operate recursively on directories
.TP
\fB\-s\fR, \fB\-\-squeeze\-blank\fR
never more than one single blank line
.TP
\fB\-t\fR
equivalent to `\-vT'
.TP
\fB\-T\fR, \fB\-\-show\-tabs\fR
display TAB characters as `^I'
.TP
\fB\-v\fR, \fB\-\-show\-nonprinting\fR
use `^' and `M\-' notation, except for LF and TAB
.TP
\fB\-\-verbose\fR
verbose mode (show error messages)
.SH "REPORTING BUGS"
Report bugs to zutils\-bug@nongnu.org
.br
Zutils home page: http://www.nongnu.org/zutils/zutils.html
.SH COPYRIGHT
Copyright \(co 2009 Antonio Diaz Diaz.
This script is free software: you have unlimited permission
to copy, distribute and modify it.
Copyright \(co 2010 Antonio Diaz Diaz.
License GPLv3+: GNU GPL version 3 or later <http://gnu.org/licenses/gpl.html>
.br
This is free software: you are free to change and redistribute it.
There is NO WARRANTY, to the extent permitted by law.

67
doc/zcmp.1 Normal file
View file

@ -0,0 +1,67 @@
.\" DO NOT MODIFY THIS FILE! It was generated by help2man 1.37.1.
.TH ZCMP "1" "November 2010" "Zcmp (zutils) 0.8" "User Commands"
.SH NAME
Zcmp \- decompress and compare two files byte by byte
.SH SYNOPSIS
.B zcmp
[\fIoptions\fR] \fIfile1 \fR[\fIfile2\fR]
.SH DESCRIPTION
Zcmp compares two files ("\-" means standard input), and if they
differ, tells the first byte and line number where they differ. Bytes
and lines are numbered starting with 1. If any given file is compressed,
its uncompressed content is used. Compressed files are uncompressed on
the fly; no temporary files are created.
The supported compressors are bzip2, gzip, lzip and xz.
.PP
Compares <file1> to <file2>. If <file2> is omitted zcmp tries the
following:
If <file1> is compressed, compares <file1> to the file with the
corresponding decompressed file name (removes the extension from
<file1>).
If <file1> is not compressed, compares <file1> to the uncompressed
contents of <file1>.[bz2|gz|lz|xz] (the first one that is found).
If no suitable file is found, compares <file1> to data read from
standard input.
.PP
Exit status is 0 if inputs are identical, 1 if different, 2 if trouble.
.SH OPTIONS
.TP
\fB\-h\fR, \fB\-\-help\fR
display this help and exit
.TP
\fB\-V\fR, \fB\-\-version\fR
output version information and exit
.TP
\fB\-b\fR, \fB\-\-print\-bytes\fR
print differing bytes
.TP
\fB\-i\fR, \fB\-\-ignore\-initial=\fR<n>[,<n2>]
ignore differences in the first <n> bytes
.TP
\fB\-l\fR, \fB\-\-list\fR
list position, value of all differing bytes
.TP
\fB\-n\fR, \fB\-\-bytes=\fR<n>
compare at most <n> bytes
.TP
\fB\-q\fR, \fB\-\-quiet\fR
suppress all messages
.TP
\fB\-s\fR, \fB\-\-silent\fR
(same as \fB\-\-quiet\fR)
.TP
\fB\-v\fR, \fB\-\-verbose\fR
verbose mode (same as \fB\-\-list\fR)
.PP
Numbers may be followed by a multiplier: k = kB = 10^3 = 1000,
Ki = KiB = 2^10 = 1024, M = 10^6, Mi = 2^20, G = 10^9, Gi = 2^30, etc...
.SH "REPORTING BUGS"
Report bugs to zutils\-bug@nongnu.org
.br
Zutils home page: http://www.nongnu.org/zutils/zutils.html
.SH COPYRIGHT
Copyright \(co 2010 Antonio Diaz Diaz.
License GPLv3+: GNU GPL version 3 or later <http://gnu.org/licenses/gpl.html>
.br
This is free software: you are free to change and redistribute it.
There is NO WARRANTY, to the extent permitted by law.

100
doc/zdiff.1
View file

@ -1,27 +1,29 @@
.\" DO NOT MODIFY THIS FILE! It was generated by help2man 1.36.
.TH ZDIFF "1" "December 2009" "Zdiff (zutils) 0.8-rc1" "User Commands"
.\" DO NOT MODIFY THIS FILE! It was generated by help2man 1.37.1.
.TH ZDIFF "1" "November 2010" "Zdiff (zutils) 0.8" "User Commands"
.SH NAME
Zdiff \- compare compressed files
Zdiff \- decompress and compare two files line by line
.SH SYNOPSIS
.B zdiff
[\fIOPTIONS\fR] [\fIDIFF_OPTIONS\fR] \fIFILE1 \fR[\fIFILE2\fR]
[\fIoptions\fR] \fIfile1 \fR[\fIfile2\fR]
.SH DESCRIPTION
Zdiff \- Diff/cmp wrapper for compressed files.
Zdiff compares two files ("\-" means standard input), and if they
differ, shows the differences line by line. If any given file is
compressed, its uncompressed content is used. Zdiff is a front end to
the diff program and has the limitation that messages from diff refer to
temporary filenames instead of those specified.
The supported compressors are bzip2, gzip, lzip and xz.
.PP
Zdiff is a wrapper script around the diff and cmp commands that allows
transparent comparison of any combination of compressed and
non\-compressed files. If any given file is compressed, its uncompressed
content is used. The supported compressors are bzip2, gzip, lzip and xz.
Compares <file1> to <file2>. If <file2> is omitted zdiff tries the
following:
If <file1> is compressed, compares <file1> to the file with the
corresponding decompressed file name (removes the extension from
<file1>).
If <file1> is not compressed, compares <file1> to the uncompressed
contents of <file1>.[bz2|gz|lz|xz] (the first one that is found).
If no suitable file is found, compares <file1> to data read from
standard input.
.PP
Zcmp is a shortcut for "zdiff \fB\-\-cmp\fR"
.PP
Compares FILE1 to FILE2. If FILE2 is omitted and FILE1 is compressed,
compares FILE1 to the file with the corresponding decompressed file
name (removes the extension from FILE1). If FILE2 is omitted and FILE1
is not compressed, compares FILE1 to the uncompressed contents of
FILE1.[bz2|gz|lz|xz] (the first one that is found).
DIFF_OPTIONS are passed directly to diff or cmp.
The exit status from diff or cmp is preserved.
Exit status is 0 if inputs are identical, 1 if different, 2 if trouble.
.SH OPTIONS
.TP
\fB\-h\fR, \fB\-\-help\fR
@ -30,15 +32,63 @@ display this help and exit
\fB\-V\fR, \fB\-\-version\fR
output version information and exit
.TP
\fB\-\-diff\fR
use diff to compare files (default)
\fB\-a\fR, \fB\-\-text\fR
treat all files as text
.TP
\fB\-\-cmp\fR
use cmp to compare files
\fB\-b\fR, \fB\-\-ignore\-space\-change\fR
ignore changes in the amount of white space
.TP
\fB\-B\fR, \fB\-\-ignore\-blank\-lines\fR
ignore changes whose lines are all blank
.TP
\fB\-c\fR
use the context output format
.TP
\fB\-C\fR, \fB\-\-context=\fR<n>
same as \fB\-c\fR but use <n> lines of context
.TP
\fB\-d\fR, \fB\-\-minimal\fR
try hard to find a smaller set of changes
.TP
\fB\-E\fR, \fB\-\-ignore\-tab\-expansion\fR
ignore changes due to tab expansion
.TP
\fB\-i\fR, \fB\-\-ignore\-case\fR
ignore case differences in file contents
.TP
\fB\-p\fR, \fB\-\-show\-c\-function\fR
show which C function each change is in
.TP
\fB\-q\fR, \fB\-\-brief\fR
output only whether files differ
.TP
\fB\-s\fR, \fB\-\-report\-identical\-files\fR
report when two files are identical
.TP
\fB\-t\fR, \fB\-\-expand\-tabs\fR
expand tabs to spaces in output
.TP
\fB\-T\fR, \fB\-\-initial\-tab\fR
make tabs line up by prepending a tab
.TP
\fB\-u\fR
use the unified output format
.TP
\fB\-U\fR, \fB\-\-unified=\fR<n>
same as \fB\-u\fR but use <n> lines of context
.TP
\fB\-w\fR, \fB\-\-ignore\-all\-space\fR
ignore all white space
.PP
Numbers may be followed by a multiplier: k = kB = 10^3 = 1000,
Ki = KiB = 2^10 = 1024, M = 10^6, Mi = 2^20, G = 10^9, Gi = 2^30, etc...
.SH "REPORTING BUGS"
Report bugs to zutils\-bug@nongnu.org
.br
Zutils home page: http://www.nongnu.org/zutils/zutils.html
.SH COPYRIGHT
Copyright \(co 2009 Antonio Diaz Diaz.
This script is free software: you have unlimited permission
to copy, distribute and modify it.
Copyright \(co 2010 Antonio Diaz Diaz.
License GPLv3+: GNU GPL version 3 or later <http://gnu.org/licenses/gpl.html>
.br
This is free software: you are free to change and redistribute it.
There is NO WARRANTY, to the extent permitted by law.

120
doc/zgrep.1
View file

@ -1,39 +1,115 @@
.\" DO NOT MODIFY THIS FILE! It was generated by help2man 1.36.
.TH ZGREP "1" "December 2009" "Zgrep (zutils) 0.8-rc1" "User Commands"
.\" DO NOT MODIFY THIS FILE! It was generated by help2man 1.37.1.
.TH ZGREP "1" "November 2010" "Zgrep (zutils) 0.8" "User Commands"
.SH NAME
Zgrep \- search compressed files for a regular expression
.SH SYNOPSIS
.B zgrep
[\fIOPTIONS\fR] [\fIGREP_OPTIONS\fR] \fIPATTERN \fR[\fIFILES\fR]
[\fIoptions\fR] \fI<pattern> \fR[\fIfiles\fR]
.SH DESCRIPTION
Zgrep \- Grep wrapper for compressed files.
.PP
Zgrep is a wrapper script around the grep command that allows
transparent search on any combination of compressed and non\-compressed
files. If any given file is compressed, its uncompressed content is
used. If a given file does not exist, zgrep tries the compressed file
names corresponding to the supported compressors. If no files are
specified, data is read from standard input, decompressed if needed, and
fed to grep. Data read from standard input must be of the same type; all
uncompressed or all compressed with the same compressor.
Zgrep is a front end to the grep program that allows transparent search
on any combination of compressed and non\-compressed files. If any given
file is compressed, its uncompressed content is used. If a given file
does not exist, and its name does not end with one of the known
extensions, zgrep tries the compressed file names corresponding to the
supported compressors. If no files are specified, data is read from
standard input, decompressed if needed, and fed to grep. Data read from
standard input must be of the same type; all uncompressed or all
compressed with the same compressor.
The supported compressors are bzip2, gzip, lzip and xz.
.PP
Zegrep is a shortcut for "zgrep \fB\-E\fR"
Zfgrep is a shortcut for "zgrep \fB\-F\fR"
.PP
GREP_OPTIONS are passed directly to grep.
The exit status from grep is preserved.
Exit status is 0 if match, 1 if no match, 2 if trouble.
.SH OPTIONS
.TP
\fB\-h\fR, \fB\-\-help\fR
\fB\-\-help\fR
display this help and exit
.TP
\fB\-V\fR, \fB\-\-version\fR
output version information and exit
.TP
\fB\-a\fR, \fB\-\-text\fR
treat all files as text
.TP
\fB\-A\fR, \fB\-\-after\-context=\fR<n>
print <n> lines of trailing context
.TP
\fB\-b\fR, \fB\-\-byte\-offset\fR
print the byte offset of each line
.TP
\fB\-B\fR, \fB\-\-before\-context=\fR<n>
print <n> lines of leading context
.TP
\fB\-c\fR, \fB\-\-count\fR
only print a count of matching lines per file
.TP
\fB\-C\fR, \fB\-\-context=\fR<n>
print <n> lines of output context
.TP
\fB\-e\fR, \fB\-\-regexp=\fR<pattern>
use <pattern> as the pattern to match
.TP
\fB\-E\fR, \fB\-\-extended\-regexp\fR
<pattern> is an extended regular expression
.TP
\fB\-f\fR, \fB\-\-file=\fR<file>
obtain patterns from <file>
.TP
\fB\-F\fR, \fB\-\-fixed\-strings\fR
<pattern> is a set of newline\-separated strings
.TP
\fB\-h\fR, \fB\-\-no\-filename\fR
suppress the prefixing filename on output
.TP
\fB\-H\fR, \fB\-\-with\-filename\fR
print the filename for each match
.TP
\fB\-i\fR, \fB\-\-ignore\-case\fR
ignore case distinctions
.TP
\fB\-I\fR
ignore binary files
.TP
\fB\-l\fR, \fB\-\-files\-with\-matches\fR
only print names of files containing matches
.TP
\fB\-L\fR, \fB\-\-files\-without\-match\fR
only print names of files containing no matches
.TP
\fB\-m\fR, \fB\-\-max\-count=\fR<n>
stop after <n> matches
.TP
\fB\-n\fR, \fB\-\-line\-number\fR
print the line number of each line
.TP
\fB\-o\fR, \fB\-\-only\-matching\fR
show only the part of a line matching <pattern>
.TP
\fB\-q\fR, \fB\-\-quiet\fR
suppress all messages
.TP
\fB\-r\fR, \fB\-\-recursive\fR
operate recursively on directories
.TP
\fB\-s\fR, \fB\-\-no\-messages\fR
suppress error messages
.TP
\fB\-v\fR, \fB\-\-invert\-match\fR
select non\-matching lines
.TP
\fB\-\-verbose\fR
verbose mode (show error messages)
.TP
\fB\-w\fR, \fB\-\-word\-regexp\fR
match only whole words
.TP
\fB\-x\fR, \fB\-\-line\-regexp\fR
match only whole lines
.SH "REPORTING BUGS"
Report bugs to zutils\-bug@nongnu.org
.br
Zutils home page: http://www.nongnu.org/zutils/zutils.html
.SH COPYRIGHT
Copyright \(co 2009 Antonio Diaz Diaz.
This script is free software: you have unlimited permission
to copy, distribute and modify it.
Copyright \(co 2010 Antonio Diaz Diaz.
License GPLv3+: GNU GPL version 3 or later <http://gnu.org/licenses/gpl.html>
.br
This is free software: you are free to change and redistribute it.
There is NO WARRANTY, to the extent permitted by law.

19
doc/ztest.1
View file

@ -1,20 +1,18 @@
.\" DO NOT MODIFY THIS FILE! It was generated by help2man 1.36.
.TH ZTEST "1" "December 2009" "Ztest (zutils) 0.8-rc1" "User Commands"
.\" DO NOT MODIFY THIS FILE! It was generated by help2man 1.37.1.
.TH ZTEST "1" "November 2010" "Ztest (zutils) 0.8" "User Commands"
.SH NAME
Ztest \- verify integrity of compressed files
.SH SYNOPSIS
.B ztest
[\fIOPTIONS\fR] [\fIFILES\fR]
[\fIoptions\fR] [\fIfiles\fR]
.SH DESCRIPTION
Ztest \- Test integrity of compressed files.
.PP
Ztest verifies the integrity of the specified compressed files.
Non\-compressed files are ignored. If no files are specified, the
integrity of compressed data read from standard input is verified. Data
read from standard input must be all compressed with the same compressor.
The supported compressors are bzip2, gzip, lzip and xz.
.PP
The exit status is 1 if any compressed file is corrupt, 0 otherwise.
Exit status is 2 if any compressed file is corrupt, 0 otherwise.
.SH OPTIONS
.TP
\fB\-h\fR, \fB\-\-help\fR
@ -33,8 +31,11 @@ operate recursively on directories
be verbose (a 2nd \fB\-v\fR gives more)
.SH "REPORTING BUGS"
Report bugs to zutils\-bug@nongnu.org
.br
Zutils home page: http://www.nongnu.org/zutils/zutils.html
.SH COPYRIGHT
Copyright \(co 2009 Antonio Diaz Diaz.
This script is free software: you have unlimited permission
to copy, distribute and modify it.
Copyright \(co 2010 Antonio Diaz Diaz.
License GPLv3+: GNU GPL version 3 or later <http://gnu.org/licenses/gpl.html>
.br
This is free software: you are free to change and redistribute it.
There is NO WARRANTY, to the extent permitted by law.

BIN
doc/zutils.info
View file

Binary file not shown.

468
doc/zutils.texinfo
View file

@ -5,8 +5,8 @@
@finalout
@c %**end of header
@set UPDATED 1 December 2009
@set VERSION 0.8-rc1
@set UPDATED 15 November 2010
@set VERSION 0.8
@dircategory Data Compression
@direntry
@ -24,7 +24,9 @@
@vskip 0pt plus 1filll
@end titlepage
@ifnothtml
@contents
@end ifnothtml
@node Top
@top
@ -34,7 +36,8 @@ This manual is for Zutils (version @value{VERSION}, @value{UPDATED}).
@menu
* Introduction:: Purpose and features of zutils
* Zcat:: Concatenating compressed files
* Zcmp/Zdiff:: Comparing compressed files
* Zcmp:: Comparing compressed files byte by byte
* Zdiff:: Comparing compressed files line by line
* Zgrep:: Searching inside compressed files
* Ztest:: Testing integrity of compressed files
* Problems:: Reporting bugs
@ -42,7 +45,7 @@ This manual is for Zutils (version @value{VERSION}, @value{UPDATED}).
@end menu
@sp 1
Copyright @copyright{} 2008, 2009 Antonio Diaz Diaz.
Copyright @copyright{} 2008, 2009, 2010 Antonio Diaz Diaz.
This manual is free documentation: you have unlimited permission
to copy, distribute and modify it.
@ -52,148 +55,443 @@ to copy, distribute and modify it.
@chapter Introduction
@cindex introduction
Zutils is a collection of utilities for dealing with any combination of
compressed and non-compressed files transparently. The supported
compressors are bzip2, gzip, lzip and xz.
Zutils is a collection of utilities able to deal with any combination of
compressed and non-compressed files transparently. If any given file,
including standard input, is compressed, its uncompressed content is
used. Compressed files are decompressed on the fly; no temporary files
are created. These utilities are not wrapper scripts but safer and more
efficient C++ programs. In particular the @samp{--recursive} option is
very efficient in those utilities supporting it.
The currently provided utilities are zcat, zcmp, zdiff, zegrep, zfgrep,
zgrep and ztest.
@noindent
The provided utilities are zcat, zcmp, zdiff, zgrep and ztest.@*
The supported compressors are bzip2, gzip, lzip and xz.
@sp 1
Numbers given as arguments to options (positions, sizes) may be followed
by a multiplier and an optional @samp{B} for "byte".
Table of SI and binary prefixes (unit multipliers):
@multitable {Prefix} {kilobyte (10^3 = 1000)} {|} {Prefix} {kibibyte (2^10 = 1024)}
@item Prefix @tab Value @tab | @tab Prefix @tab Value
@item k @tab kilobyte (10^3 = 1000) @tab | @tab Ki @tab kibibyte (2^10 = 1024)
@item M @tab megabyte (10^6) @tab | @tab Mi @tab mebibyte (2^20)
@item G @tab gigabyte (10^9) @tab | @tab Gi @tab gibibyte (2^30)
@item T @tab terabyte (10^12) @tab | @tab Ti @tab tebibyte (2^40)
@item P @tab petabyte (10^15) @tab | @tab Pi @tab pebibyte (2^50)
@item E @tab exabyte (10^18) @tab | @tab Ei @tab exbibyte (2^60)
@item Z @tab zettabyte (10^21) @tab | @tab Zi @tab zebibyte (2^70)
@item Y @tab yottabyte (10^24) @tab | @tab Yi @tab yobibyte (2^80)
@end multitable
@node Zcat
@chapter Zcat
@cindex zcat
Zcat is a wrapper script around the cat command that allows transparent
concatenation of any combination of compressed and non-compressed files.
If any given file is compressed, its uncompressed content is used. If a
given file does not exist, zcat tries the compressed file names
Zcat copies each given file (@samp{-} means standard input), to standard
output. If any given file is compressed, its uncompressed content is
used. If a given file does not exist, and its name does not end with one
of the known extensions, zcat tries the compressed file names
corresponding to the supported compressors. If no files are specified,
data is read from standard input, decompressed if needed, and sent to
stdout. Data read from standard input must be of the same type; all
uncompressed or all compressed with the same compressor.
standard output. Data read from standard input must be of the same type;
all uncompressed or all compressed with the same compressor.
The format for running zcat is:
@example
zcat [@var{options}] [@var{cat_options}] [@var{files}]
zcat [@var{options}] [@var{files}]
@end example
@noindent
@var{cat_options} are passed directly to cat. The exit status from cat
is preserved.
Exit status is 0 if no errors occurred, 1 otherwise.
Zcat supports the following options:
@table @samp
@item --help
@itemx -h
@item -h
@itemx --help
Print an informative help message describing the options and exit.
@item --version
@itemx -V
@item -V
@itemx --version
Print the version number of zcat on the standard output and exit.
@item --recursive
@itemx -r
@item -A
@itemx --show-all
Equivalent to @samp{-vET}.
@item -b
@itemx --number-nonblank
Number all nonblank output lines, starting with 1. The line count is
unlimited.
@item -e
Equivalent to @samp{-vE}.
@item -E
@itemx --show-ends
Print a @samp{$} after the end of each line.
@item -n
@itemx --number
Number all output lines, starting with 1. The line count is unlimited.
@item -q
@itemx --quiet
Quiet operation. Suppress all messages.
@item -r
@itemx --recursive
Operate recursively on directories.
@item -s
@itemx --squeeze-blank
Replace multiple adjacent blank lines with a single blank line.
@item -t
Equivalent to @samp{-vT}.
@item -T
@itemx --show-tabs
Print TAB characters as @samp{^I}.
@item -v
@itemx --show-nonprinting
Print control characters except for LF (newline) and TAB using @samp{^}
notation and precede characters larger than 127 with @samp{M-} (which
stands for "meta").
@item --verbose
Verbose mode. Show error messages.
@end table
@node Zcmp/Zdiff
@chapter Zcmp/Zdiff
@node Zcmp
@chapter Zcmp
@cindex zcmp
@cindex zdiff
Zdiff is a wrapper script around the diff and cmp commands that allows
transparent comparison of any combination of compressed and
non-compressed files. If any given file is compressed, its uncompressed
content is used.
Zcmp compares two files (@samp{-} means standard input), and if they
differ, tells the first byte and line number where they differ. Bytes
and lines are numbered starting with 1. If any given file is compressed,
its uncompressed content is used. Compressed files are decompressed on
the fly; no temporary files are created.
The format for running zcmp is:
@example
zcmp [@var{options}] @var{file1} [@var{file2}]
@end example
@noindent
Zcmp is a shortcut for @samp{zdiff --cmp}
Compares @var{file1} to @var{file2}. If @var{file2} is omitted zcmp
tries the following:@*
If @var{file1} is compressed, compares @var{file1} to the file with the
corresponding decompressed file name (removes the extension from
@var{file1}).@*
If @var{file1} is not compressed, compares @var{file1} to the
uncompressed contents of @var{file1}.[bz2|gz|lz|xz] (the first one that
is found).@*
If no suitable file is found, compares @var{file1} to data read from
standard input.
@noindent
An exit status of 0 means no differences were found, 1 means some
differences were found, and 2 means trouble.
Zcmp supports the following options:
@table @samp
@item -h
@itemx --help
Print an informative help message describing the options and exit.
@item -V
@itemx --version
Print the version number of zcmp on the standard output and exit.
@item -b
@itemx --print-bytes
Print the differing bytes. Print control bytes as a @samp{^} followed by
a letter, and precede bytes larger than 127 with @samp{M-} (which stands
for "meta").
@item -i @var{size}
@itemx --ignore-initial=@var{size}
Ignore any differences in the first @var{size} bytes of the input files.
Treat files with fewer than @var{size} bytes as if they were empty. If
@var{size} is in the form @samp{@var{size1},@var{size2}}, ignore the
first @var{size1} bytes of the first input file and the first
@var{size2} bytes of the second input file.
@item -l
@itemx -v
@itemx --list
@itemx --verbose
Print the byte numbers (in decimal) and values (in octal) of all
differing bytes.
@item -n @var{count}
@itemx --bytes=@var{count}
Compare at most @var{count} input bytes.
@item -q
@itemx -s
@itemx --quiet
@itemx --silent
Do not print anything; only return an exit status indicating whether the
files differ.
@end table
@node Zdiff
@chapter Zdiff
@cindex zdiff
Zdiff compares two files (@samp{-} means standard input), and if they
differ, shows the differences line by line. If any given file is
compressed, its uncompressed content is used. Zdiff is a front end to
the diff program and has the limitation that messages from diff refer to
temporary filenames instead of those specified.
The format for running zdiff is:
@example
zdiff [@var{options}] [@var{diff_options}] @var{file1} [@var{file2}]
zdiff [@var{options}] @var{file1} [@var{file2}]
@end example
@noindent
Compares @var{file1} to @var{file2}. If @var{file2} is omitted and
@var{file1} is compressed, compares @var{file1} to the file with the
Compares @var{file1} to @var{file2}. If @var{file2} is omitted zdiff
tries the following:@*
If @var{file1} is compressed, compares @var{file1} to the file with the
corresponding decompressed file name (removes the extension from
@var{file1}). If @var{file2} is omitted and @var{file1} is not
compressed, compares @var{file1} to the uncompressed contents of
@var{file1}.[bz2|gz|lz|xz] (the first one that is found).
@var{diff_options} are passed directly to diff or cmp. The exit status
from diff or cmp is preserved.
@var{file1}).@*
If @var{file1} is not compressed, compares @var{file1} to the
uncompressed contents of @var{file1}.[bz2|gz|lz|xz] (the first one that
is found).@*
If no suitable file is found, compares @var{file1} to data read from
standard input.
@noindent
An exit status of 0 means no differences were found, 1 means some
differences were found, and 2 means trouble.
Zdiff supports the following options:
@table @samp
@item --help
@itemx -h
@item -h
@itemx --help
Print an informative help message describing the options and exit.
@item --version
@itemx -V
@item -V
@itemx --version
Print the version number of zdiff on the standard output and exit.
@item --diff
Use diff to compare files (default).
@item -a
@itemx --text
Treat all files as text.
@item --cmp
Use cmp to compare files.
@item -b
@itemx --ignore-space-change
Ignore changes in the amount of white space.
@item -B
@itemx --ignore-blank-lines
Ignore changes whose lines are all blank.
@itemx -c
Use the context output format.
@item -C @var{n}
@itemx --context=@var{n}
Same as -c but use @var{n} lines of context.
@item -d
@itemx --minimal
Try hard to find a smaller set of changes.
@item -E
@itemx --ignore-tab-expansion
Ignore changes due to tab expansion.
@item -i
@itemx --ignore-case
Ignore case differences in file contents.
@item -p
@itemx --show-c-function
Show which C function each change is in.
@item -q
@itemx --brief
Output only whether files differ.
@item -s
@itemx --report-identical-files
Report when two files are identical.
@item -t
@itemx --expand-tabs
Expand tabs to spaces in output.
@item -T
@itemx --initial-tab
Make tabs line up by prepending a tab.
@item -u
Use the unified output format.
@item -U @var{n}
@itemx --unified=@var{n}
Same as -u but use @var{n} lines of context.
@item -w
@itemx --ignore-all-space
Ignore all white space.
@end table
Zdiff has the limitation that messages from the diff or cmp programs
refer to temporary filenames instead of those specified.
@node Zgrep
@chapter Zgrep
@cindex zegrep
@cindex zfgrep
@cindex zgrep
Zgrep is a wrapper script around the grep command that allows
transparent search on any combination of compressed and non-compressed
files. If any given file is compressed, its uncompressed content is
used. If a given file does not exist, zgrep tries the compressed file
names corresponding to the supported compressors. If no files are
specified, data is read from standard input, decompressed if needed, and
fed to grep. Data read from standard input must be of the same type; all
uncompressed or all compressed with the same compressor.
@noindent
Zegrep is a shortcut for @samp{zgrep -E}@*
Zfgrep is a shortcut for @samp{zgrep -F}
Zgrep is a front end to the grep program that allows transparent search
on any combination of compressed and non-compressed files. If any given
file is compressed, its uncompressed content is used. If a given file
does not exist, and its name does not end with one of the known
extensions, zgrep tries the compressed file names corresponding to the
supported compressors. If no files are specified, data is read from
standard input, decompressed if needed, and fed to grep. Data read from
standard input must be of the same type; all uncompressed or all
compressed with the same compressor.
The format for running zgrep is:
@example
zgrep [@var{options}] [@var{grep_options}] @var{pattern} [@var{files}]
zgrep [@var{options}] @var{pattern} [@var{files}]
@end example
@noindent
@var{grep_options} are passed directly to grep. The exit status from
grep is preserved.
An exit status of 0 means at least one match was found, 1 means no
matches were found, and 2 means trouble.
Zgrep supports the following options:
@table @samp
@item --help
@itemx -h
Print an informative help message describing the options and exit.
@item --version
@itemx -V
@item -V
@itemx --version
Print the version number of zgrep on the standard output and exit.
@item -a
@itemx --text
Treat all files as text.
@item -A @var{n}
@itemx --after-context=@var{n}
Print @var{n} lines of trailing context.
@item -b
@itemx --byte-offset
Print the byte offset of each line.
@item -B @var{n}
@itemx --before-context=@var{n}
Print @var{n} lines of leading context.
@item -c
@itemx --count
Only print a count of matching lines per file.
@item -C @var{n}
@itemx --context=@var{n}
Print @var{n} lines of output context.
@item -e @var{pattern}
@itemx --regexp=@var{pattern}
Use @var{pattern} as the pattern to match.
@item -E
@itemx --extended-regexp
Treat @var{pattern} as an extended regular expression.
@item -f @var{file}
@itemx --file=@var{file}
Obtain patterns from @var{file}, one per line.
@item -F
@itemx --fixed-strings
Treat @var{pattern} as a set of newline-separated strings.
@item -h
@itemx --no-filename
Suppress the prefixing filename on output.
@item -H
@itemx --with-filename
Print the filename for each match.
@item -i
@itemx --ignore-case
Ignore case distinctions.
@item -I
Ignore binary files.
@item -l
@itemx --files-with-matches
Only print names of files containing at least one match.
@item -L
@itemx --files-without-match
Only print names of files not containing any matches.
@item -m @var{n}
@itemx --max-count=@var{n}
Stop after @var{n} matches.
@item -n
@itemx --line-number
Prefix each matched line with its line number in the input file.
@item -o
@itemx --only-matching
Show only the part of matching lines that actually matches @var{pattern}.
@item -q
@itemx --quiet
Suppress all messages.
@item -r
@itemx --recursive
Operate recursively on directories.
@item -s
@itemx --no-messages
Suppress error messages.
@item -v
@itemx --invert-match
Select non-matching lines.
@item --verbose
Verbose mode. Show error messages.
@item -w
@itemx --word-regexp
Match only whole words.
@item -x
@itemx --line-regexp
Match only whole lines.
@end table
@ -213,29 +511,31 @@ ztest [@var{options}] [@var{files}]
@end example
@noindent
The exit status is 0 if all files verify OK, 1 otherwise.
The exit status is 0 if all files verify OK, 1 for environmental
problems (file not found, invalid flags, I/O errors, etc), 2 to indicate
a corrupt or invalid input file.
Ztest supports the following options:
@table @samp
@item --help
@itemx -h
@item -h
@itemx --help
Print an informative help message describing the options and exit.
@item --version
@itemx -V
@item -V
@itemx --version
Print the version number of ztest on the standard output and exit.
@item --quiet
@itemx -q
@item -q
@itemx --quiet
Quiet operation. Suppress all messages.
@item --recursive
@itemx -r
@item -r
@itemx --recursive
Operate recursively on directories.
@item --verbose
@itemx -v
@item -v
@itemx --verbose
Verbose mode. Show the verify status for each file processed.
Further -v's increase the verbosity level.
@ -254,7 +554,7 @@ for all eternity, if not longer.
If you find a bug in zutils, please send electronic mail to
@email{zutils-bug@@nongnu.org}. Include the version number, which you can
find by running @w{@samp{zdiff --version}}.
find by running @w{@samp{zutils --version}}.
@node Concept Index

1014
main.cc
View file

File diff suppressed because it is too large Load diff

185
testsuite/check.sh
View file

@ -1,6 +1,6 @@
#! /bin/sh
# check script for Zutils - Utilities dealing with compressed files
# Copyright (C) 2009 Antonio Diaz Diaz.
# Copyright (C) 2009, 2010 Antonio Diaz Diaz.
#
# This script is free software: you have unlimited permission
# to copy, distribute and modify it.
@ -16,10 +16,9 @@ ZGREP="${objdir}"/zgrep
ZEGREP="${objdir}"/zegrep
ZFGREP="${objdir}"/zfgrep
ZTEST="${objdir}"/ztest
ZUTILS="${objdir}"/zutils
compressors="bzip2 gzip lzip"
extensions="bz2 gz lz"
framework_failure() { echo 'failure in testing framework'; exit 1; }
framework_failure() { echo "failure in testing framework" ; exit 1 ; }
compressor_needed() { echo "${compressors} are needed to run tests" ; exit 1 ; }
if [ ! -x "${ZCAT}" ] ; then
@ -32,123 +31,181 @@ mkdir tmp
cd "${objdir}"/tmp
for i in ${compressors}; do
cat "${testdir}"/../COPYING > in || framework_failure
cat "${testdir}"/test.txt > in || framework_failure
$i in || compressor_needed
done
echo -n "testing zutils..."
cat "${testdir}"/../COPYING > in || framework_failure
printf "testing zutils-%s..." "$2"
cat "${testdir}"/test.txt > in || framework_failure
cat in > -in- || framework_failure
cat in.lz > -in-.lz || framework_failure
cat in in in in in > in5 || framework_failure
cat in.lz > lz_only.lz || framework_failure
cat in in in in in in > in6 || framework_failure
fail=0
printf "\ntesting zcat-%s..." "$2"
for i in ${extensions}; do
"${ZCAT}" in.$i > copy || fail=1
cmp in copy || fail=1
echo -n .
printf .
done
"${ZCAT}" < in > copy || fail=1
cmp in copy || fail=1
echo -n .
printf .
"${ZCAT}" < in.gz > copy || fail=1
cmp in copy || fail=1
echo -n .
printf .
"${ZCAT}" < in.bz2 > copy || fail=1
cmp in copy || fail=1
echo -n .
printf .
"${ZCAT}" < in.lz > copy || fail=1
cmp in copy || fail=1
echo -n .
printf .
"${ZCAT}" in > copy || fail=1
cmp in copy || fail=1
echo -n .
"${ZCAT}" in in.gz in.bz2 in.lz -- -in- > copy5 || fail=1
cmp in5 copy5 || fail=1
echo -n .
printf .
"${ZCAT}" lz_only > copy || fail=1
cmp in copy || fail=1
printf .
"${ZCAT}" in in.gz in.bz2 in.lz -- -in- -in-.lz > copy6 || fail=1
cmp in6 copy6 || fail=1
printf .
printf "\ntesting zcmp-%s..." "$2"
for i in ${extensions}; do
"${ZCMP}" in.$i || fail=1
echo -n .
printf .
"${ZCMP}" in in.$i || fail=1
echo -n .
printf .
"${ZCMP}" in.$i in || fail=1
echo -n .
printf .
done
"${ZCMP}" - || fail=1
printf .
"${ZCMP}" in in || fail=1
printf .
"${ZCMP}" in || fail=1
printf .
"${ZCMP}" in.lz in.gz || fail=1
printf .
"${ZCMP}" in.gz -- -in-.lz || fail=1
printf .
"${ZCMP}" -- -in-.lz in.gz || fail=1
printf .
"${ZCMP}" in -- -in-.lz || fail=1
printf .
"${ZCMP}" -- -in- in.lz || fail=1
printf .
"${ZCMP}" in.lz -- -in- || fail=1
printf .
"${ZCMP}" -- -in-.lz in || fail=1
printf .
"${ZCMP}" -- -in- in || fail=1
printf .
"${ZCMP}" in -- -in- || fail=1
printf .
"${ZCMP}" lz_only.lz < in || fail=1
printf .
"${ZCMP}" in.lz - < in || fail=1
printf .
"${ZCMP}" - in.lz < in || fail=1
printf .
"${ZCMP}" in - < in.lz || fail=1
printf .
"${ZCMP}" - in < in.lz || fail=1
printf .
printf "\ntesting zdiff-%s..." "$2"
for i in ${extensions}; do
"${ZDIFF}" in.$i || fail=1
echo -n .
printf .
"${ZDIFF}" in in.$i || fail=1
echo -n .
printf .
"${ZDIFF}" in.$i in || fail=1
echo -n .
printf .
done
"${ZDIFF}" - || fail=1
printf .
"${ZDIFF}" in in || fail=1
printf .
"${ZDIFF}" in || fail=1
echo -n .
printf .
"${ZDIFF}" in.lz in.gz || fail=1
echo -n .
printf .
"${ZDIFF}" in.gz -- -in-.lz || fail=1
echo -n .
printf .
"${ZDIFF}" -- -in-.lz in.gz || fail=1
echo -n .
printf .
"${ZDIFF}" in -- -in-.lz || fail=1
echo -n .
printf .
"${ZDIFF}" -- -in- in.lz || fail=1
echo -n .
printf .
"${ZDIFF}" in.lz -- -in- || fail=1
echo -n .
printf .
"${ZDIFF}" -- -in-.lz in || fail=1
echo -n .
printf .
"${ZDIFF}" -- -in- in || fail=1
echo -n .
printf .
"${ZDIFF}" in -- -in- || fail=1
echo -n .
printf .
"${ZDIFF}" lz_only.lz < in || fail=1
printf .
"${ZDIFF}" in.lz - < in || fail=1
printf .
"${ZDIFF}" - in.lz < in || fail=1
printf .
"${ZDIFF}" in - < in.lz || fail=1
printf .
"${ZDIFF}" - in < in.lz || fail=1
printf .
printf "\ntesting zgrep-%s..." "$2"
for i in ${extensions}; do
"${ZGREP}" License in.$i 2>&1 > /dev/null || fail=1
echo -n .
"${ZGREP}" License in.$i > /dev/null || fail=1
"${ZGREP}" nx_pattern in.$i > /dev/null && fail=1
printf .
done
"${ZGREP}" License < in 2>&1 > /dev/null || fail=1
echo -n .
"${ZGREP}" License < in.gz 2>&1 > /dev/null || fail=1
echo -n .
"${ZGREP}" License < in.bz2 2>&1 > /dev/null || fail=1
echo -n .
"${ZGREP}" License < in.lz 2>&1 > /dev/null || fail=1
echo -n .
"${ZGREP}" License in 2>&1 > /dev/null || fail=1
echo -n .
"${ZGREP}" License -- -in- 2>&1 > /dev/null || fail=1
echo -n .
"${ZGREP}" License -- -in-.lz 2>&1 > /dev/null || fail=1
echo -n .
"${ZGREP}" License in in.gz in.bz2 in.lz -- -in- 2>&1 > /dev/null || fail=1
echo -n .
"${ZEGREP}" License in 2>&1 > /dev/null || fail=1
echo -n .
"${ZFGREP}" License in 2>&1 > /dev/null || fail=1
echo -n .
"${ZGREP}" -r License . > /dev/null || fail=1
printf .
"${ZGREP}" nx_pattern -r . in > /dev/null && fail=1
printf .
"${ZGREP}" License < in > /dev/null || fail=1
printf .
"${ZGREP}" License < in.gz > /dev/null || fail=1
printf .
"${ZGREP}" License < in.bz2 > /dev/null || fail=1
printf .
"${ZGREP}" License < in.lz > /dev/null || fail=1
printf .
"${ZGREP}" License in > /dev/null || fail=1
printf .
"${ZGREP}" License -- -in- > /dev/null || fail=1
printf .
"${ZGREP}" License -- -in-.lz > /dev/null || fail=1
printf .
"${ZGREP}" License in in.gz in.bz2 in.lz -- -in- > /dev/null || fail=1
printf .
"${ZEGREP}" License in > /dev/null || fail=1
printf .
"${ZFGREP}" License in > /dev/null || fail=1
printf .
printf "\ntesting ztest-%s..." "$2"
"${ZTEST}" in in.gz in.bz2 in.lz -- -in- || fail=1
echo -n .
printf .
"${ZTEST}" -r . || fail=1
echo -n .
if [ "bzip2" != `"${ZUTILS}" -t in.bz2` ] ; then fail=1 ; fi
echo -n .
if [ "gzip" != `"${ZUTILS}" -t in.gz` ] ; then fail=1 ; fi
echo -n .
if [ "lzip" != `"${ZUTILS}" -t in.lz` ] ; then fail=1 ; fi
echo -n .
printf .
printf "LZIPvs0000000000000000000000" | "${ZTEST}" 2>/dev/null && fail=1
printf .
echo
if [ ${fail} = 0 ] ; then

676
testsuite/test.txt Normal file
View file

@ -0,0 +1,676 @@
GNU GENERAL PUBLIC LICENSE
Version 3, 29 June 2007
Copyright (C) 2007 Free Software Foundation, Inc. <http://fsf.org/>
Everyone is permitted to copy and distribute verbatim copies
of this license document, but changing it is not allowed.
Preamble
The GNU General Public License is a free, copyleft license for
software and other kinds of works.
The licenses for most software and other practical works are designed
to take away your freedom to share and change the works. By contrast,
the GNU General Public License is intended to guarantee your freedom to
share and change all versions of a program--to make sure it remains free
software for all its users. We, the Free Software Foundation, use the
GNU General Public License for most of our software; it applies also to
any other work released this way by its authors. You can apply it to
your programs, too.
When we speak of free software, we are referring to freedom, not
price. Our General Public Licenses are designed to make sure that you
have the freedom to distribute copies of free software (and charge for
them if you wish), that you receive source code or can get it if you
want it, that you can change the software or use pieces of it in new
free programs, and that you know you can do these things.
To protect your rights, we need to prevent others from denying you
these rights or asking you to surrender the rights. Therefore, you have
certain responsibilities if you distribute copies of the software, or if
you modify it: responsibilities to respect the freedom of others.
For example, if you distribute copies of such a program, whether
gratis or for a fee, you must pass on to the recipients the same
freedoms that you received. You must make sure that they, too, receive
or can get the source code. And you must show them these terms so they
know their rights.
Developers that use the GNU GPL protect your rights with two steps:
(1) assert copyright on the software, and (2) offer you this License
giving you legal permission to copy, distribute and/or modify it.
For the developers' and authors' protection, the GPL clearly explains
that there is no warranty for this free software. For both users' and
authors' sake, the GPL requires that modified versions be marked as
changed, so that their problems will not be attributed erroneously to
authors of previous versions.
Some devices are designed to deny users access to install or run
modified versions of the software inside them, although the manufacturer
can do so. This is fundamentally incompatible with the aim of
protecting users' freedom to change the software. The systematic
pattern of such abuse occurs in the area of products for individuals to
use, which is precisely where it is most unacceptable. Therefore, we
have designed this version of the GPL to prohibit the practice for those
products. If such problems arise substantially in other domains, we
stand ready to extend this provision to those domains in future versions
of the GPL, as needed to protect the freedom of users.
Finally, every program is threatened constantly by software patents.
States should not allow patents to restrict development and use of
software on general-purpose computers, but in those that do, we wish to
avoid the special danger that patents applied to a free program could
make it effectively proprietary. To prevent this, the GPL assures that
patents cannot be used to render the program non-free.
The precise terms and conditions for copying, distribution and
modification follow.
TERMS AND CONDITIONS
0. Definitions.
"This License" refers to version 3 of the GNU General Public License.
"Copyright" also means copyright-like laws that apply to other kinds of
works, such as semiconductor masks.
"The Program" refers to any copyrightable work licensed under this
License. Each licensee is addressed as "you". "Licensees" and
"recipients" may be individuals or organizations.
To "modify" a work means to copy from or adapt all or part of the work
in a fashion requiring copyright permission, other than the making of an
exact copy. The resulting work is called a "modified version" of the
earlier work or a work "based on" the earlier work.
A "covered work" means either the unmodified Program or a work based
on the Program.
To "propagate" a work means to do anything with it that, without
permission, would make you directly or secondarily liable for
infringement under applicable copyright law, except executing it on a
computer or modifying a private copy. Propagation includes copying,
distribution (with or without modification), making available to the
public, and in some countries other activities as well.
To "convey" a work means any kind of propagation that enables other
parties to make or receive copies. Mere interaction with a user through
a computer network, with no transfer of a copy, is not conveying.
An interactive user interface displays "Appropriate Legal Notices"
to the extent that it includes a convenient and prominently visible
feature that (1) displays an appropriate copyright notice, and (2)
tells the user that there is no warranty for the work (except to the
extent that warranties are provided), that licensees may convey the
work under this License, and how to view a copy of this License. If
the interface presents a list of user commands or options, such as a
menu, a prominent item in the list meets this criterion.
1. Source Code.
The "source code" for a work means the preferred form of the work
for making modifications to it. "Object code" means any non-source
form of a work.
A "Standard Interface" means an interface that either is an official
standard defined by a recognized standards body, or, in the case of
interfaces specified for a particular programming language, one that
is widely used among developers working in that language.
The "System Libraries" of an executable work include anything, other
than the work as a whole, that (a) is included in the normal form of
packaging a Major Component, but which is not part of that Major
Component, and (b) serves only to enable use of the work with that
Major Component, or to implement a Standard Interface for which an
implementation is available to the public in source code form. A
"Major Component", in this context, means a major essential component
(kernel, window system, and so on) of the specific operating system
(if any) on which the executable work runs, or a compiler used to
produce the work, or an object code interpreter used to run it.
The "Corresponding Source" for a work in object code form means all
the source code needed to generate, install, and (for an executable
work) run the object code and to modify the work, including scripts to
control those activities. However, it does not include the work's
System Libraries, or general-purpose tools or generally available free
programs which are used unmodified in performing those activities but
which are not part of the work. For example, Corresponding Source
includes interface definition files associated with source files for
the work, and the source code for shared libraries and dynamically
linked subprograms that the work is specifically designed to require,
such as by intimate data communication or control flow between those
subprograms and other parts of the work.
The Corresponding Source need not include anything that users
can regenerate automatically from other parts of the Corresponding
Source.
The Corresponding Source for a work in source code form is that
same work.
2. Basic Permissions.
All rights granted under this License are granted for the term of
copyright on the Program, and are irrevocable provided the stated
conditions are met. This License explicitly affirms your unlimited
permission to run the unmodified Program. The output from running a
covered work is covered by this License only if the output, given its
content, constitutes a covered work. This License acknowledges your
rights of fair use or other equivalent, as provided by copyright law.
You may make, run and propagate covered works that you do not
convey, without conditions so long as your license otherwise remains
in force. You may convey covered works to others for the sole purpose
of having them make modifications exclusively for you, or provide you
with facilities for running those works, provided that you comply with
the terms of this License in conveying all material for which you do
not control copyright. Those thus making or running the covered works
for you must do so exclusively on your behalf, under your direction
and control, on terms that prohibit them from making any copies of
your copyrighted material outside their relationship with you.
Conveying under any other circumstances is permitted solely under
the conditions stated below. Sublicensing is not allowed; section 10
makes it unnecessary.
3. Protecting Users' Legal Rights From Anti-Circumvention Law.
No covered work shall be deemed part of an effective technological
measure under any applicable law fulfilling obligations under article
11 of the WIPO copyright treaty adopted on 20 December 1996, or
similar laws prohibiting or restricting circumvention of such
measures.
When you convey a covered work, you waive any legal power to forbid
circumvention of technological measures to the extent such circumvention
is effected by exercising rights under this License with respect to
the covered work, and you disclaim any intention to limit operation or
modification of the work as a means of enforcing, against the work's
users, your or third parties' legal rights to forbid circumvention of
technological measures.
4. Conveying Verbatim Copies.
You may convey verbatim copies of the Program's source code as you
receive it, in any medium, provided that you conspicuously and
appropriately publish on each copy an appropriate copyright notice;
keep intact all notices stating that this License and any
non-permissive terms added in accord with section 7 apply to the code;
keep intact all notices of the absence of any warranty; and give all
recipients a copy of this License along with the Program.
You may charge any price or no price for each copy that you convey,
and you may offer support or warranty protection for a fee.
5. Conveying Modified Source Versions.
You may convey a work based on the Program, or the modifications to
produce it from the Program, in the form of source code under the
terms of section 4, provided that you also meet all of these conditions:
a) The work must carry prominent notices stating that you modified
it, and giving a relevant date.
b) The work must carry prominent notices stating that it is
released under this License and any conditions added under section
7. This requirement modifies the requirement in section 4 to
"keep intact all notices".
c) You must license the entire work, as a whole, under this
License to anyone who comes into possession of a copy. This
License will therefore apply, along with any applicable section 7
additional terms, to the whole of the work, and all its parts,
regardless of how they are packaged. This License gives no
permission to license the work in any other way, but it does not
invalidate such permission if you have separately received it.
d) If the work has interactive user interfaces, each must display
Appropriate Legal Notices; however, if the Program has interactive
interfaces that do not display Appropriate Legal Notices, your
work need not make them do so.
A compilation of a covered work with other separate and independent
works, which are not by their nature extensions of the covered work,
and which are not combined with it such as to form a larger program,
in or on a volume of a storage or distribution medium, is called an
"aggregate" if the compilation and its resulting copyright are not
used to limit the access or legal rights of the compilation's users
beyond what the individual works permit. Inclusion of a covered work
in an aggregate does not cause this License to apply to the other
parts of the aggregate.
6. Conveying Non-Source Forms.
You may convey a covered work in object code form under the terms
of sections 4 and 5, provided that you also convey the
machine-readable Corresponding Source under the terms of this License,
in one of these ways:
a) Convey the object code in, or embodied in, a physical product
(including a physical distribution medium), accompanied by the
Corresponding Source fixed on a durable physical medium
customarily used for software interchange.
b) Convey the object code in, or embodied in, a physical product
(including a physical distribution medium), accompanied by a
written offer, valid for at least three years and valid for as
long as you offer spare parts or customer support for that product
model, to give anyone who possesses the object code either (1) a
copy of the Corresponding Source for all the software in the
product that is covered by this License, on a durable physical
medium customarily used for software interchange, for a price no
more than your reasonable cost of physically performing this
conveying of source, or (2) access to copy the
Corresponding Source from a network server at no charge.
c) Convey individual copies of the object code with a copy of the
written offer to provide the Corresponding Source. This
alternative is allowed only occasionally and noncommercially, and
only if you received the object code with such an offer, in accord
with subsection 6b.
d) Convey the object code by offering access from a designated
place (gratis or for a charge), and offer equivalent access to the
Corresponding Source in the same way through the same place at no
further charge. You need not require recipients to copy the
Corresponding Source along with the object code. If the place to
copy the object code is a network server, the Corresponding Source
may be on a different server (operated by you or a third party)
that supports equivalent copying facilities, provided you maintain
clear directions next to the object code saying where to find the
Corresponding Source. Regardless of what server hosts the
Corresponding Source, you remain obligated to ensure that it is
available for as long as needed to satisfy these requirements.
e) Convey the object code using peer-to-peer transmission, provided
you inform other peers where the object code and Corresponding
Source of the work are being offered to the general public at no
charge under subsection 6d.
A separable portion of the object code, whose source code is excluded
from the Corresponding Source as a System Library, need not be
included in conveying the object code work.
A "User Product" is either (1) a "consumer product", which means any
tangible personal property which is normally used for personal, family,
or household purposes, or (2) anything designed or sold for incorporation
into a dwelling. In determining whether a product is a consumer product,
doubtful cases shall be resolved in favor of coverage. For a particular
product received by a particular user, "normally used" refers to a
typical or common use of that class of product, regardless of the status
of the particular user or of the way in which the particular user
actually uses, or expects or is expected to use, the product. A product
is a consumer product regardless of whether the product has substantial
commercial, industrial or non-consumer uses, unless such uses represent
the only significant mode of use of the product.
"Installation Information" for a User Product means any methods,
procedures, authorization keys, or other information required to install
and execute modified versions of a covered work in that User Product from
a modified version of its Corresponding Source. The information must
suffice to ensure that the continued functioning of the modified object
code is in no case prevented or interfered with solely because
modification has been made.
If you convey an object code work under this section in, or with, or
specifically for use in, a User Product, and the conveying occurs as
part of a transaction in which the right of possession and use of the
User Product is transferred to the recipient in perpetuity or for a
fixed term (regardless of how the transaction is characterized), the
Corresponding Source conveyed under this section must be accompanied
by the Installation Information. But this requirement does not apply
if neither you nor any third party retains the ability to install
modified object code on the User Product (for example, the work has
been installed in ROM).
The requirement to provide Installation Information does not include a
requirement to continue to provide support service, warranty, or updates
for a work that has been modified or installed by the recipient, or for
the User Product in which it has been modified or installed. Access to a
network may be denied when the modification itself materially and
adversely affects the operation of the network or violates the rules and
protocols for communication across the network.
Corresponding Source conveyed, and Installation Information provided,
in accord with this section must be in a format that is publicly
documented (and with an implementation available to the public in
source code form), and must require no special password or key for
unpacking, reading or copying.
7. Additional Terms.
"Additional permissions" are terms that supplement the terms of this
License by making exceptions from one or more of its conditions.
Additional permissions that are applicable to the entire Program shall
be treated as though they were included in this License, to the extent
that they are valid under applicable law. If additional permissions
apply only to part of the Program, that part may be used separately
under those permissions, but the entire Program remains governed by
this License without regard to the additional permissions.
When you convey a copy of a covered work, you may at your option
remove any additional permissions from that copy, or from any part of
it. (Additional permissions may be written to require their own
removal in certain cases when you modify the work.) You may place
additional permissions on material, added by you to a covered work,
for which you have or can give appropriate copyright permission.
Notwithstanding any other provision of this License, for material you
add to a covered work, you may (if authorized by the copyright holders of
that material) supplement the terms of this License with terms:
a) Disclaiming warranty or limiting liability differently from the
terms of sections 15 and 16 of this License; or
b) Requiring preservation of specified reasonable legal notices or
author attributions in that material or in the Appropriate Legal
Notices displayed by works containing it; or
c) Prohibiting misrepresentation of the origin of that material, or
requiring that modified versions of such material be marked in
reasonable ways as different from the original version; or
d) Limiting the use for publicity purposes of names of licensors or
authors of the material; or
e) Declining to grant rights under trademark law for use of some
trade names, trademarks, or service marks; or
f) Requiring indemnification of licensors and authors of that
material by anyone who conveys the material (or modified versions of
it) with contractual assumptions of liability to the recipient, for
any liability that these contractual assumptions directly impose on
those licensors and authors.
All other non-permissive additional terms are considered "further
restrictions" within the meaning of section 10. If the Program as you
received it, or any part of it, contains a notice stating that it is
governed by this License along with a term that is a further
restriction, you may remove that term. If a license document contains
a further restriction but permits relicensing or conveying under this
License, you may add to a covered work material governed by the terms
of that license document, provided that the further restriction does
not survive such relicensing or conveying.
If you add terms to a covered work in accord with this section, you
must place, in the relevant source files, a statement of the
additional terms that apply to those files, or a notice indicating
where to find the applicable terms.
Additional terms, permissive or non-permissive, may be stated in the
form of a separately written license, or stated as exceptions;
the above requirements apply either way.
8. Termination.
You may not propagate or modify a covered work except as expressly
provided under this License. Any attempt otherwise to propagate or
modify it is void, and will automatically terminate your rights under
this License (including any patent licenses granted under the third
paragraph of section 11).
However, if you cease all violation of this License, then your
license from a particular copyright holder is reinstated (a)
provisionally, unless and until the copyright holder explicitly and
finally terminates your license, and (b) permanently, if the copyright
holder fails to notify you of the violation by some reasonable means
prior to 60 days after the cessation.
Moreover, your license from a particular copyright holder is
reinstated permanently if the copyright holder notifies you of the
violation by some reasonable means, this is the first time you have
received notice of violation of this License (for any work) from that
copyright holder, and you cure the violation prior to 30 days after
your receipt of the notice.
Termination of your rights under this section does not terminate the
licenses of parties who have received copies or rights from you under
this License. If your rights have been terminated and not permanently
reinstated, you do not qualify to receive new licenses for the same
material under section 10.
9. Acceptance Not Required for Having Copies.
You are not required to accept this License in order to receive or
run a copy of the Program. Ancillary propagation of a covered work
occurring solely as a consequence of using peer-to-peer transmission
to receive a copy likewise does not require acceptance. However,
nothing other than this License grants you permission to propagate or
modify any covered work. These actions infringe copyright if you do
not accept this License. Therefore, by modifying or propagating a
covered work, you indicate your acceptance of this License to do so.
10. Automatic Licensing of Downstream Recipients.
Each time you convey a covered work, the recipient automatically
receives a license from the original licensors, to run, modify and
propagate that work, subject to this License. You are not responsible
for enforcing compliance by third parties with this License.
An "entity transaction" is a transaction transferring control of an
organization, or substantially all assets of one, or subdividing an
organization, or merging organizations. If propagation of a covered
work results from an entity transaction, each party to that
transaction who receives a copy of the work also receives whatever
licenses to the work the party's predecessor in interest had or could
give under the previous paragraph, plus a right to possession of the
Corresponding Source of the work from the predecessor in interest, if
the predecessor has it or can get it with reasonable efforts.
You may not impose any further restrictions on the exercise of the
rights granted or affirmed under this License. For example, you may
not impose a license fee, royalty, or other charge for exercise of
rights granted under this License, and you may not initiate litigation
(including a cross-claim or counterclaim in a lawsuit) alleging that
any patent claim is infringed by making, using, selling, offering for
sale, or importing the Program or any portion of it.
11. Patents.
A "contributor" is a copyright holder who authorizes use under this
License of the Program or a work on which the Program is based. The
work thus licensed is called the contributor's "contributor version".
A contributor's "essential patent claims" are all patent claims
owned or controlled by the contributor, whether already acquired or
hereafter acquired, that would be infringed by some manner, permitted
by this License, of making, using, or selling its contributor version,
but do not include claims that would be infringed only as a
consequence of further modification of the contributor version. For
purposes of this definition, "control" includes the right to grant
patent sublicenses in a manner consistent with the requirements of
this License.
Each contributor grants you a non-exclusive, worldwide, royalty-free
patent license under the contributor's essential patent claims, to
make, use, sell, offer for sale, import and otherwise run, modify and
propagate the contents of its contributor version.
In the following three paragraphs, a "patent license" is any express
agreement or commitment, however denominated, not to enforce a patent
(such as an express permission to practice a patent or covenant not to
sue for patent infringement). To "grant" such a patent license to a
party means to make such an agreement or commitment not to enforce a
patent against the party.
If you convey a covered work, knowingly relying on a patent license,
and the Corresponding Source of the work is not available for anyone
to copy, free of charge and under the terms of this License, through a
publicly available network server or other readily accessible means,
then you must either (1) cause the Corresponding Source to be so
available, or (2) arrange to deprive yourself of the benefit of the
patent license for this particular work, or (3) arrange, in a manner
consistent with the requirements of this License, to extend the patent
license to downstream recipients. "Knowingly relying" means you have
actual knowledge that, but for the patent license, your conveying the
covered work in a country, or your recipient's use of the covered work
in a country, would infringe one or more identifiable patents in that
country that you have reason to believe are valid.
If, pursuant to or in connection with a single transaction or
arrangement, you convey, or propagate by procuring conveyance of, a
covered work, and grant a patent license to some of the parties
receiving the covered work authorizing them to use, propagate, modify
or convey a specific copy of the covered work, then the patent license
you grant is automatically extended to all recipients of the covered
work and works based on it.
A patent license is "discriminatory" if it does not include within
the scope of its coverage, prohibits the exercise of, or is
conditioned on the non-exercise of one or more of the rights that are
specifically granted under this License. You may not convey a covered
work if you are a party to an arrangement with a third party that is
in the business of distributing software, under which you make payment
to the third party based on the extent of your activity of conveying
the work, and under which the third party grants, to any of the
parties who would receive the covered work from you, a discriminatory
patent license (a) in connection with copies of the covered work
conveyed by you (or copies made from those copies), or (b) primarily
for and in connection with specific products or compilations that
contain the covered work, unless you entered into that arrangement,
or that patent license was granted, prior to 28 March 2007.
Nothing in this License shall be construed as excluding or limiting
any implied license or other defenses to infringement that may
otherwise be available to you under applicable patent law.
12. No Surrender of Others' Freedom.
If conditions are imposed on you (whether by court order, agreement or
otherwise) that contradict the conditions of this License, they do not
excuse you from the conditions of this License. If you cannot convey a
covered work so as to satisfy simultaneously your obligations under this
License and any other pertinent obligations, then as a consequence you may
not convey it at all. For example, if you agree to terms that obligate you
to collect a royalty for further conveying from those to whom you convey
the Program, the only way you could satisfy both those terms and this
License would be to refrain entirely from conveying the Program.
13. Use with the GNU Affero General Public License.
Notwithstanding any other provision of this License, you have
permission to link or combine any covered work with a work licensed
under version 3 of the GNU Affero General Public License into a single
combined work, and to convey the resulting work. The terms of this
License will continue to apply to the part which is the covered work,
but the special requirements of the GNU Affero General Public License,
section 13, concerning interaction through a network will apply to the
combination as such.
14. Revised Versions of this License.
The Free Software Foundation may publish revised and/or new versions of
the GNU General Public License from time to time. Such new versions will
be similar in spirit to the present version, but may differ in detail to
address new problems or concerns.
Each version is given a distinguishing version number. If the
Program specifies that a certain numbered version of the GNU General
Public License "or any later version" applies to it, you have the
option of following the terms and conditions either of that numbered
version or of any later version published by the Free Software
Foundation. If the Program does not specify a version number of the
GNU General Public License, you may choose any version ever published
by the Free Software Foundation.
If the Program specifies that a proxy can decide which future
versions of the GNU General Public License can be used, that proxy's
public statement of acceptance of a version permanently authorizes you
to choose that version for the Program.
Later license versions may give you additional or different
permissions. However, no additional obligations are imposed on any
author or copyright holder as a result of your choosing to follow a
later version.
15. Disclaimer of Warranty.
THERE IS NO WARRANTY FOR THE PROGRAM, TO THE EXTENT PERMITTED BY
APPLICABLE LAW. EXCEPT WHEN OTHERWISE STATED IN WRITING THE COPYRIGHT
HOLDERS AND/OR OTHER PARTIES PROVIDE THE PROGRAM "AS IS" WITHOUT WARRANTY
OF ANY KIND, EITHER EXPRESSED OR IMPLIED, INCLUDING, BUT NOT LIMITED TO,
THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR
PURPOSE. THE ENTIRE RISK AS TO THE QUALITY AND PERFORMANCE OF THE PROGRAM
IS WITH YOU. SHOULD THE PROGRAM PROVE DEFECTIVE, YOU ASSUME THE COST OF
ALL NECESSARY SERVICING, REPAIR OR CORRECTION.
16. Limitation of Liability.
IN NO EVENT UNLESS REQUIRED BY APPLICABLE LAW OR AGREED TO IN WRITING
WILL ANY COPYRIGHT HOLDER, OR ANY OTHER PARTY WHO MODIFIES AND/OR CONVEYS
THE PROGRAM AS PERMITTED ABOVE, BE LIABLE TO YOU FOR DAMAGES, INCLUDING ANY
GENERAL, SPECIAL, INCIDENTAL OR CONSEQUENTIAL DAMAGES ARISING OUT OF THE
USE OR INABILITY TO USE THE PROGRAM (INCLUDING BUT NOT LIMITED TO LOSS OF
DATA OR DATA BEING RENDERED INACCURATE OR LOSSES SUSTAINED BY YOU OR THIRD
PARTIES OR A FAILURE OF THE PROGRAM TO OPERATE WITH ANY OTHER PROGRAMS),
EVEN IF SUCH HOLDER OR OTHER PARTY HAS BEEN ADVISED OF THE POSSIBILITY OF
SUCH DAMAGES.
17. Interpretation of Sections 15 and 16.
If the disclaimer of warranty and limitation of liability provided
above cannot be given local legal effect according to their terms,
reviewing courts shall apply local law that most closely approximates
an absolute waiver of all civil liability in connection with the
Program, unless a warranty or assumption of liability accompanies a
copy of the Program in return for a fee.
END OF TERMS AND CONDITIONS
How to Apply These Terms to Your New Programs
If you develop a new program, and you want it to be of the greatest
possible use to the public, the best way to achieve this is to make it
free software which everyone can redistribute and change under these terms.
To do so, attach the following notices to the program. It is safest
to attach them to the start of each source file to most effectively
state the exclusion of warranty; and each file should have at least
the "copyright" line and a pointer to where the full notice is found.
<one line to give the program's name and a brief idea of what it does.>
Copyright (C) <year> <name of author>
This program is free software: you can redistribute it and/or modify
it under the terms of the GNU General Public License as published by
the Free Software Foundation, either version 3 of the License, or
(at your option) any later version.
This program is distributed in the hope that it will be useful,
but WITHOUT ANY WARRANTY; without even the implied warranty of
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
GNU General Public License for more details.
You should have received a copy of the GNU General Public License
along with this program. If not, see <http://www.gnu.org/licenses/>.
Also add information on how to contact you by electronic and paper mail.
If the program does terminal interaction, make it output a short
notice like this when it starts in an interactive mode:
<program> Copyright (C) <year> <name of author>
This program comes with ABSOLUTELY NO WARRANTY; for details type `show w'.
This is free software, and you are welcome to redistribute it
under certain conditions; type `show c' for details.
The hypothetical commands `show w' and `show c' should show the appropriate
parts of the General Public License. Of course, your program's commands
might be different; for a GUI interface, you would use an "about box".
You should also get your employer (if you work as a programmer) or school,
if any, to sign a "copyright disclaimer" for the program, if necessary.
For more information on this, and how to apply and follow the GNU GPL, see
<http://www.gnu.org/licenses/>.
The GNU General Public License does not permit incorporating your program
into proprietary programs. If your program is a subroutine library, you
may consider it more useful to permit linking proprietary applications with
the library. If this is what you want to do, use the GNU Lesser General
Public License instead of this License. But first, please read
<http://www.gnu.org/philosophy/why-not-lgpl.html>.

213
zcat.cc Normal file
View file

@ -0,0 +1,213 @@
/* Zcat - decompress and concatenate files to standard output
Copyright (C) 2010 Antonio Diaz Diaz.
This program is free software: you can redistribute it and/or modify
it under the terms of the GNU General Public License as published by
the Free Software Foundation, either version 3 of the License, or
(at your option) any later version.
This program is distributed in the hope that it will be useful,
but WITHOUT ANY WARRANTY; without even the implied warranty of
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
GNU General Public License for more details.
You should have received a copy of the GNU General Public License
along with this program. If not, see <http://www.gnu.org/licenses/>.
*/
struct Cat_options
{
int number_lines; // 0 = no, 1 = nonblank, 2 = all
bool show_ends;
bool show_nonprinting;
bool show_tabs;
bool squeeze_blank;
Cat_options() throw()
: number_lines( 0 ), show_ends( false ), show_nonprinting( false ),
show_tabs( false ), squeeze_blank( false ) {}
};
class Line_number // unlimited size line counter
{
std::string str;
int first_digit_pos;
public:
Line_number() : str( " 0\t" ), first_digit_pos( 5 ) {}
void next()
{
for( int i = str.size() - 2; i >= first_digit_pos; --i )
{
if( str[i] < '9' ) { ++str[i]; return; }
str[i] = '0';
}
if( first_digit_pos > 0 ) str[--first_digit_pos] = '1';
else str.insert( 0, 1, '1' );
}
int sprint( uint8_t * const buf )
{
std::memcpy( buf, str.c_str(), str.size() );
return str.size();
}
};
Line_number line_number;
void show_zcat_help() throw()
{
std::printf( "Zcat copies each given file (\"-\" means standard input), to standard\n" );
std::printf( "output. If any given file is compressed, its uncompressed content is\n" );
std::printf( "used. If a given file does not exist, and its name does not end with one\n" );
std::printf( "of the known extensions, zcat tries the compressed file names\n" );
std::printf( "corresponding to the supported compressors. If no files are specified,\n" );
std::printf( "data is read from standard input, decompressed if needed, and sent to\n" );
std::printf( "standard output. Data read from standard input must be of the same type;\n" );
std::printf( "all uncompressed or all compressed with the same compressor.\n" );
std::printf( "The supported compressors are bzip2, gzip, lzip and xz.\n" );
std::printf( "\nUsage: zcat [options] [files]\n" );
std::printf( "\nExit status is 0 if no errors occurred, 1 otherwise.\n" );
std::printf( "\nOptions:\n" );
std::printf( " -h, --help display this help and exit\n" );
std::printf( " -V, --version output version information and exit\n" );
std::printf( " -A, --show-all equivalent to `-vET'\n" );
std::printf( " -b, --number-nonblank number nonblank output lines\n" );
std::printf( " -e equivalent to `-vE'\n" );
std::printf( " -E, --show-ends display `$' at end of each line\n" );
std::printf( " -n, --number number all output lines\n" );
std::printf( " -q, --quiet suppress all messages\n" );
std::printf( " -r, --recursive operate recursively on directories\n" );
std::printf( " -s, --squeeze-blank never more than one single blank line\n" );
std::printf( " -t equivalent to `-vT'\n" );
std::printf( " -T, --show-tabs display TAB characters as `^I'\n" );
std::printf( " -v, --show-nonprinting use `^' and `M-' notation, except for LF and TAB\n" );
std::printf( " --verbose verbose mode (show error messages)\n" );
show_help_addr();
}
int do_cat( const int infd, const int buffer_size,
uint8_t * const inbuf, uint8_t * const outbuf,
const std::string & input_filename,
const Cat_options & cat_options )
{
static int at_bol = 1; // at begin of line. 0 = false, 1 = true,
// 2 = at begin of second blank line.
int inpos = 0; // positions in buffers
int outpos = 0;
int rd = -1; // bytes read by the last readblock
unsigned char c;
while( true )
{
do {
if( outpos >= buffer_size )
{
if( writeblock( STDOUT_FILENO, outbuf, outpos ) != outpos )
{ show_error( "Write error", errno ); return 1; }
outpos = 0;
}
if( inpos > rd ) // inbuf is empty
{
rd = readblock( infd, inbuf, buffer_size );
if( rd != buffer_size && errno )
{
if( verbosity >= 0 )
std::fprintf( stderr, "%s: Error reading file `%s': %s.\n",
util_name, input_filename.c_str(),
std::strerror( errno ) );
return 1;
}
if( rd == 0 )
{
if( writeblock( STDOUT_FILENO, outbuf, outpos ) != outpos )
{ show_error( "Write error", errno ); return 1; }
outpos = 0;
return 0;
}
inpos = 0;
inbuf[rd] = '\n'; // sentinel newline
}
else // a real newline was found
{
if( at_bol > 1 )
{
if( cat_options.squeeze_blank ) { c = inbuf[inpos++]; continue; }
}
else ++at_bol;
if( at_bol > 1 && cat_options.number_lines == 2 )
{
line_number.next();
outpos += line_number.sprint( &outbuf[outpos] );
}
if( cat_options.show_ends ) outbuf[outpos++] = '$';
outbuf[outpos++] = '\n'; // output the newline
}
c = inbuf[inpos++];
}
while( c == '\n' );
if( at_bol > 0 && cat_options.number_lines )
{
line_number.next();
outpos += line_number.sprint( &outbuf[outpos] );
}
at_bol = 0;
// the loops below continue until a newline (real or sentinel) is found
if( cat_options.show_nonprinting )
while( true )
{
if( c < 32 || c >= 127 )
{
if( c == '\n' ) break;
if( c != '\t' || cat_options.show_tabs )
{
if( c >= 128 )
{ c -= 128; outbuf[outpos++] = 'M'; outbuf[outpos++] = '-'; }
if( c < 32 ) { c += 64; outbuf[outpos++] = '^'; }
else if( c == 127 ) { c = '?'; outbuf[outpos++] = '^'; }
}
}
outbuf[outpos++] = c;
c = inbuf[inpos++];
}
else // not quoting
while( c != '\n' )
{
if( c == '\t' && cat_options.show_tabs )
{ c += 64; outbuf[outpos++] = '^'; }
outbuf[outpos++] = c;
c = inbuf[inpos++];
}
}
}
int cat( int infd, const std::string & input_filename,
const Cat_options & cat_options )
{
enum { buffer_size = 4096 };
// buffer with space for sentinel newline at the end
uint8_t * const inbuf = new uint8_t[buffer_size+1];
// buffer with space for character quoting and 255-digit line number
uint8_t * const outbuf = new uint8_t[(4*buffer_size)+256];
pid_t pid = 0;
int retval = 0;
if( !set_data_feeder( &infd, &pid ) ) retval = 1;
else
{
retval = do_cat( infd, buffer_size, inbuf, outbuf,
input_filename, cat_options );
if( pid && wait_for_child( pid, "data feeder" ) != 0 ) retval = 1;
if( close( infd ) != 0 )
{ show_error( "Can't close output of data feeder", errno ); retval = 1; }
}
delete[] inbuf; delete[] outbuf;
return retval;
}

114
zcat.in
View file

@ -1,115 +1,3 @@
#! /bin/sh
# Zcat - Cat wrapper for compressed files.
# Copyright (C) 2009 Antonio Diaz Diaz.
#
# This script is free software: you have unlimited permission
# to copy, distribute and modify it.
LC_ALL=C
export LC_ALL
args=
gz_args=
xz_args=
recursive=0
two_hyphens=0
# Loop over args until a filename is found
while [ -n "$1" ] ; do
case "$1" in
--help | --he* | -h)
echo "Zcat - Cat wrapper for compressed files."
echo
echo "Zcat is a wrapper script around the cat command that allows transparent"
echo "concatenation of any combination of compressed and non-compressed files."
echo "If any given file is compressed, its uncompressed content is used. If a"
echo "given file does not exist, zcat tries the compressed file names"
echo "corresponding to the supported compressors. If no files are specified,"
echo "data is read from standard input, decompressed if needed, and sent to"
echo "stdout. Data read from standard input must be of the same type; all"
echo "uncompressed or all compressed with the same compressor."
echo "The supported compressors are bzip2, gzip, lzip and xz."
echo
echo "Usage: $0 [OPTIONS] [CAT_OPTIONS] [FILES]"
echo
echo "CAT_OPTIONS are passed directly to cat."
echo "The exit status from cat is preserved."
echo
echo "Options:"
echo " -h, --help display this help and exit"
echo " -V, --version output version information and exit"
echo " -r, --recursive operate recursively on directories"
echo
echo "Report bugs to zutils-bug@nongnu.org"
echo "Zutils home page: http://www.nongnu.org/zutils/zutils.html"
exit 0 ;;
--version | --ve* | -V)
echo "Zcat (zutils) VERSION"
echo "Copyright (C) 2009 Antonio Diaz Diaz."
echo "This script is free software: you have unlimited permission"
echo "to copy, distribute and modify it."
exit 0 ;;
- | -c | --st* | -d | --de* | -f | --fo* | -q | --qu* | -L | --lic* )
;;
-l | --lis*)
gz_args="${gz_args} $1"; xz_args="${xz_args} $1" ;;
-r | --re*)
recursive=1 ;;
--)
shift ; two_hyphens=1 ; break ;;
-?*)
args="${args} $1" ;;
*)
break ;;
esac
shift
done
if [ $# = 0 ] ; then
bindir=`echo "$0" | sed -e 's,[^/]*$,,'`
prog_name=`"${bindir}"zutils -t`
case "${prog_name}" in
bzip2) prog="bzip2 -cdfq" ;;
gzip) prog="gzip -cdfq ${gz_args}" ;;
lzip) prog="lzip -cdfq" ;;
xz) prog="xz -cdfq ${xz_args}" ;;
*) prog=cat ;;
esac
{ "${bindir}"zutils -m ${prog_name} ; cat ; } | ${prog} | cat ${args}
exit $?
fi
retval=0
for i in "$@" ; do
if [ "$i" = "--" ] && [ ${two_hyphens} = 0 ] ; then two_hyphens=1
else
if [ ! -f "$i" ] ; then
if [ -f "$i.gz" ] ; then i="$i.gz"
elif [ -f "$i.bz2" ] ; then i="$i.bz2"
elif [ -f "$i.lz" ] ; then i="$i.lz"
elif [ -f "$i.xz" ] ; then i="$i.xz"
elif [ ${recursive} = 1 ] && [ -d "$i" ] ; then
find "$i" -type f -exec "$0" '{}' ';'
continue
else
echo "$0: File \"$i\" not found or not a regular file" 1>&2
if [ ${retval} = 0 ] ; then retval=1 ; fi
continue
fi
fi
bindir=`echo "$0" | sed -e 's,[^/]*$,,'`
prog_name=`"${bindir}"zutils -t -- "$i"`
case "${prog_name}" in
bzip2) prog="bzip2 -cdfq" ;;
gzip) prog="gzip -cdfq ${gz_args}" ;;
lzip) prog="lzip -cdfq" ;;
xz) prog="xz -cdfq ${xz_args}" ;;
*) prog=cat ;;
esac
${prog} -- "$i" | cat ${args}
r=$?
if [ $r != 0 ] ; then retval=$r ; fi
fi
done
exit ${retval}
exec "${bindir}"zutils --zcat "$@"

502
zcmp.cc Normal file
View file

@ -0,0 +1,502 @@
/* Zcmp - decompress and compare two files byte by byte
Copyright (C) 2010 Antonio Diaz Diaz.
This program is free software: you can redistribute it and/or modify
it under the terms of the GNU General Public License as published by
the Free Software Foundation, either version 3 of the License, or
(at your option) any later version.
This program is distributed in the hope that it will be useful,
but WITHOUT ANY WARRANTY; without even the implied warranty of
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
GNU General Public License for more details.
You should have received a copy of the GNU General Public License
along with this program. If not, see <http://www.gnu.org/licenses/>.
*/
#define _FILE_OFFSET_BITS 64
#include <cctype>
#include <cerrno>
#include <climits>
#include <csignal>
#include <cstdio>
#include <cstdlib>
#include <cstring>
#include <string>
#include <vector>
#include <fcntl.h>
#include <stdint.h>
#include <unistd.h>
#include <sys/stat.h>
#if defined(__MSVCRT__) || defined(__OS2__)
#include <io.h>
#endif
#include "arg_parser.h"
#include "zutils.h"
#if CHAR_BIT != 8
#error "Environments where CHAR_BIT != 8 are not supported."
#endif
#ifndef LLONG_MAX
#define LLONG_MAX 0x7FFFFFFFFFFFFFFFLL
#endif
#ifndef LLONG_MIN
#define LLONG_MIN (-LLONG_MAX - 1LL)
#endif
#ifndef ULLONG_MAX
#define ULLONG_MAX 0xFFFFFFFFFFFFFFFFULL
#endif
namespace {
#ifdef O_BINARY
const int o_binary = O_BINARY;
#else
const int o_binary = 0;
#endif
struct { const char * from; const char * to; } const known_extensions[] = {
{ ".bz2", "" },
{ ".tbz", ".tar" },
{ ".tbz2", ".tar" },
{ ".gz", "" },
{ ".tgz", ".tar" },
{ ".lz", "" },
{ ".tlz", ".tar" },
{ ".xz", "" },
{ ".txz", ".tar" },
{ 0, 0 } };
void show_help() throw()
{
std::printf( "Zcmp compares two files (\"-\" means standard input), and if they\n" );
std::printf( "differ, tells the first byte and line number where they differ. Bytes\n" );
std::printf( "and lines are numbered starting with 1. If any given file is compressed,\n" );
std::printf( "its uncompressed content is used. Compressed files are uncompressed on\n" );
std::printf( "the fly; no temporary files are created.\n" );
std::printf( "The supported compressors are bzip2, gzip, lzip and xz.\n" );
std::printf( "\nUsage: zcmp [options] file1 [file2]\n" );
std::printf( "\nCompares <file1> to <file2>. If <file2> is omitted zcmp tries the\n" );
std::printf( "following:\n" );
std::printf( "If <file1> is compressed, compares <file1> to the file with the\n" );
std::printf( "corresponding decompressed file name (removes the extension from\n" );
std::printf( "<file1>).\n" );
std::printf( "If <file1> is not compressed, compares <file1> to the uncompressed\n" );
std::printf( "contents of <file1>.[bz2|gz|lz|xz] (the first one that is found).\n" );
std::printf( "If no suitable file is found, compares <file1> to data read from\n" );
std::printf( "standard input.\n" );
std::printf( "\nExit status is 0 if inputs are identical, 1 if different, 2 if trouble.\n" );
std::printf( "\nOptions:\n" );
std::printf( " -h, --help display this help and exit\n" );
std::printf( " -V, --version output version information and exit\n" );
std::printf( " -b, --print-bytes print differing bytes\n" );
std::printf( " -i, --ignore-initial=<n>[,<n2>] ignore differences in the first <n> bytes\n" );
std::printf( " -l, --list list position, value of all differing bytes\n" );
std::printf( " -n, --bytes=<n> compare at most <n> bytes\n" );
std::printf( " -q, --quiet suppress all messages\n" );
std::printf( " -s, --silent (same as --quiet)\n" );
std::printf( " -v, --verbose verbose mode (same as --list)\n" );
std::printf( "Numbers may be followed by a multiplier: k = kB = 10^3 = 1000,\n" );
std::printf( "Ki = KiB = 2^10 = 1024, M = 10^6, Mi = 2^20, G = 10^9, Gi = 2^30, etc...\n" );
show_help_addr();
}
long long getnum( const char * const ptr, const char ** const tailp = 0,
const long long llimit = LLONG_MIN + 1,
const long long ulimit = LLONG_MAX ) throw()
{
errno = 0;
char * tail;
long long result = strtoll( ptr, &tail, 0 );
if( tail == ptr )
{
show_error( "Bad or missing numerical argument.", 0, true );
std::exit( 2 );
}
if( !errno && tail[0] && std::isalpha( tail[0] ) )
{
int factor = ( tail[1] == 'i' ) ? 1024 : 1000;
int exponent = 0;
bool bad_multiplier = false;
switch( tail[0] )
{
case 'Y': exponent = 8; break;
case 'Z': exponent = 7; break;
case 'E': exponent = 6; break;
case 'P': exponent = 5; break;
case 'T': exponent = 4; break;
case 'G': exponent = 3; break;
case 'M': exponent = 2; break;
case 'K': if( factor == 1024 ) exponent = 1; else bad_multiplier = true;
break;
case 'k': if( factor == 1000 ) exponent = 1; else bad_multiplier = true;
break;
default : bad_multiplier = true;
}
if( bad_multiplier )
{
show_error( "Bad multiplier in numerical argument.", 0, true );
std::exit( 2 );
}
for( int i = 0; i < exponent; ++i )
{
if( LLONG_MAX / factor >= llabs( result ) ) result *= factor;
else { errno = ERANGE; break; }
}
}
if( !errno && ( result < llimit || result > ulimit ) ) errno = ERANGE;
if( errno )
{
show_error( "Numerical argument out of limits." );
std::exit( 2 );
}
if( tailp ) *tailp = tail;
return result;
}
int open_instream( const std::string & input_filename ) throw()
{
int infd = open( input_filename.c_str(), O_RDONLY | o_binary );
if( infd < 0 && verbosity >= 0 )
std::fprintf( stderr, "%s: Can't open input file `%s': %s.\n",
util_name, input_filename.c_str(), std::strerror( errno ) );
return infd;
}
int open_other_instream( std::string & name ) throw()
{
for( int i = 0; known_extensions[i].from; ++i )
{ // search uncompressed version
const std::string from( known_extensions[i].from );
if( name.size() > from.size() &&
name.compare( name.size() - from.size(), from.size(), from ) == 0 )
{
name.resize( name.size() - from.size() );
name += known_extensions[i].to;
return open( name.c_str(), O_RDONLY | o_binary );
}
}
for( int i = 0; simple_extensions[i]; ++i )
{ // search compressed version
const std::string s( name + simple_extensions[i] );
const int infd = open( s.c_str(), O_RDONLY | o_binary );
if( infd >= 0 ) { name = s; return infd; }
}
return -1;
}
bool check_identical( const char * const name1, const char * const name2 ) throw()
{
if( !std::strcmp( name1, name2 ) ) return true;
struct stat stat1, stat2;
if( stat( name1, &stat1 ) || stat( name2, &stat2 ) ) return false;
return ( stat1.st_ino == stat2.st_ino && stat1.st_dev == stat2.st_dev );
}
void parse_ignore_initial( const char * const arg, long long ignore_initial[2] )
{
const char * tail;
ignore_initial[0] = getnum( arg, &tail, 0 );
if( *tail == ',' || *tail == ':' )
ignore_initial[1] = getnum( ++tail, 0, 0 );
else ignore_initial[1] = ignore_initial[0];
}
bool skip_ignore_initial( const long long ignore_initial, const int infd )
{
if( ignore_initial > 0 )
{
enum { buffer_size = 4096 };
long long rest = ignore_initial;
uint8_t buffer[buffer_size];
while( rest > 0 )
{
const int size = std::min( rest, (long long)buffer_size );
const int rd = readblock( infd, buffer, size );
if( rd != size && errno ) return false;
if( rd < size ) break;
rest -= rd;
}
}
return true;
}
// Put into buf the unsigned char c, making unprintable bytes
// visible by quoting like cat -t does.
void sprintc( char * const buf, unsigned char c )
{
int i = 0;
if( c < 32 || c >= 127 )
{
if( c >= 128 ) { c -= 128; buf[i++] = 'M'; buf[i++] = '-'; }
if( c < 32 ) { c += 64; buf[i++] = '^'; }
else if( c == 127 ) { c = '?'; buf[i++] = '^'; }
}
buf[i++] = c;
buf[i++] = 0;
}
int block_compare( const uint8_t * const buffer0,
const uint8_t * const buffer1,
long long * line_numberp )
{
const uint8_t * p0 = buffer0;
const uint8_t * p1 = buffer1;
if( verbosity == 0 )
{
int nl_count = 0;
while( *p0 == *p1 )
{ if( *p0 == '\n' ) { ++nl_count; } ++p0; ++p1; }
*line_numberp += nl_count;
}
else while( *p0 == *p1 ) { ++p0; ++p1; }
return p0 - buffer0;
}
int cmp( const long long max_size, const int infd[2],
const std::string filenames[2], const bool print_bytes )
{
enum { buffer_size = 4096 };
long long byte_number = 1;
long long line_number = 1;
long long rest = max_size; // remaining number of bytes to compare
// buffers with space for sentinels at the end
uint8_t * const buffer0 = new uint8_t[2*(buffer_size+1)];
uint8_t * const buffer1 = buffer0 + buffer_size + 1;
uint8_t * buffer[2];
buffer[0] = buffer0; buffer[1] = buffer1;
int different = 0;
while( rest > 0 )
{
const int size = std::min( rest, (long long)buffer_size );
int rd[2]; // number of bytes read from each file
for( int i = 0; i < 2; ++i )
{
rd[i] = readblock( infd[i], buffer[i], size );
if( rd[i] != size && errno )
{
if( verbosity >= 0 )
std::fprintf( stderr, "%s: Error reading file `%s': %s.\n",
util_name, filenames[i].c_str(), std::strerror( errno ) );
return 2;
}
}
rest -= size;
buffer0[rd[0]] = ~buffer1[rd[0]]; // sentinels for the block compare
buffer1[rd[1]] = ~buffer0[rd[1]];
int first_diff = block_compare( buffer0, buffer1, &line_number );
byte_number += first_diff;
const int min_rd = std::min( rd[0], rd[1] );
if( first_diff < min_rd )
{
if( verbosity < 0 ) return 1; // return status only
if( verbosity == 0 ) // show first difference
{
if( !print_bytes )
std::printf( "%s %s differ: byte %lld, line %lld\n",
filenames[0].c_str(), filenames[1].c_str(),
byte_number, line_number );
else
{
const unsigned char c0 = buffer0[first_diff];
const unsigned char c1 = buffer1[first_diff];
char buf0[5], buf1[5];
sprintc( buf0, c0 ); sprintc( buf1, c1 );
std::printf( "%s %s differ: byte %lld, line %lld is %3o %s %3o %s\n",
filenames[0].c_str(), filenames[1].c_str(),
byte_number, line_number, c0, buf0, c1, buf1 );
}
return 1;
}
else // verbosity > 0 ; show all differences
{
different = 1;
for( ; first_diff < min_rd; ++byte_number, ++first_diff )
{
const unsigned char c0 = buffer0[first_diff];
const unsigned char c1 = buffer1[first_diff];
if( c0 != c1 )
{
if( !print_bytes )
std::printf( "%lld %3o %3o\n", byte_number, c0, c1 );
else
{
char buf0[5], buf1[5];
sprintc( buf0, c0 ); sprintc( buf1, c1 );
std::printf( "%lld %3o %-4s %3o %s\n",
byte_number, c0, buf0, c1, buf1 );
}
}
}
}
}
if( rd[0] != rd[1] )
{
if( verbosity >= 0 )
std::fprintf( stderr, "%s: EOF on %s\n",
util_name, filenames[rd[1]<rd[0]].c_str() );
return 1;
}
if( min_rd != buffer_size ) break;
}
delete[] buffer0;
return different;
}
} // end namespace
int main( const int argc, const char * const argv[] )
{
// number of initial bytes ignored for each file
long long ignore_initial[2] = { 0, 0 };
long long max_size = LLONG_MAX;
bool print_bytes = false;
invocation_name = argv[0];
util_name = "zcmp";
const Arg_parser::Option options[] =
{
{ 'b', "print-bytes", Arg_parser::no },
{ 'h', "help", Arg_parser::no },
{ 'i', "ignore-initial", Arg_parser::yes },
{ 'l', "list", Arg_parser::no },
{ 'n', "bytes", Arg_parser::yes },
{ 'q', "quiet", Arg_parser::no },
{ 's', "silent", Arg_parser::no },
{ 'v', "verbose", Arg_parser::no },
{ 'V', "version", Arg_parser::no },
{ 0 , 0, Arg_parser::no } };
const Arg_parser parser( argc, argv, options );
if( parser.error().size() ) // bad option
{ show_error( parser.error().c_str(), 0, true ); return 2; }
int argind = 0;
for( ; argind < parser.arguments(); ++argind )
{
const int code = parser.code( argind );
if( !code ) break; // no more options
const char * const arg = parser.argument( argind ).c_str();
switch( code )
{
case 'b': print_bytes = true; break;
case 'h': show_help(); return 0;
case 'i': parse_ignore_initial( arg, ignore_initial ); break;
case 'l': verbosity = 1; break;
case 'n': max_size = getnum( arg, 0, 0 ); break;
case 'q':
case 's': verbosity = -1; break;
case 'v': verbosity = 1; break;
case 'V': show_version( "Zcmp" ); return 0;
default : internal_error( "uncaught option" );
}
} // end process options
#if defined(__MSVCRT__) || defined(__OS2__)
_setmode( STDIN_FILENO, O_BINARY );
_setmode( STDOUT_FILENO, O_BINARY );
#endif
if( argind >= parser.arguments() )
{ show_error( "No files given.", 0, true ); return 2; }
if( argind + 2 < parser.arguments() )
{ show_error( "Too many files.", 0, true ); return 2; }
const int files = parser.arguments() - argind;
std::string filenames[2]; // file names of the two input files
filenames[0] = parser.argument( argind );
if( files == 2 ) filenames[1] = parser.argument( argind + 1 );
int infd[2]; // file descriptors of the two files
infd[0] = ( filenames[0] == "-" ) ?
STDIN_FILENO : open_instream( filenames[0] );
if( infd[0] < 0 ) return 2;
if( ( files == 1 && filenames[0] == "-" ) ||
( files == 2 && check_identical( filenames[0].c_str(),
filenames[1].c_str() ) ) )
{
if( ignore_initial[0] == ignore_initial[1] ) return 0;
else { show_error( "Can't compare parts of same file." ); return 2; }
}
if( files == 2 )
{
infd[1] = ( filenames[1] == "-" ) ?
STDIN_FILENO : open_instream( filenames[1] );
if( infd[1] < 0 ) return 2;
}
else
{
filenames[1] = filenames[0];
infd[1] = open_other_instream( filenames[1] );
if( infd[1] < 0 ) { infd[1] = STDIN_FILENO; filenames[1] = "-"; }
}
int old_infd[2]; // copy of file descriptors of the two files
old_infd[0] = infd[0]; old_infd[1] = infd[1];
pid_t pid[2];
if( !set_data_feeder( &infd[0], &pid[0] ) ||
!set_data_feeder( &infd[1], &pid[1] ) )
return 2;
for( int i = 0; i < 2; ++i )
if( !skip_ignore_initial( ignore_initial[i], infd[i] ) )
{
if( verbosity >= 0 )
std::fprintf( stderr, "%s: Can't skip initial bytes from file `%s': %s.\n",
util_name, filenames[i].c_str(), std::strerror( errno ) );
return 2;
}
int retval = cmp( max_size, infd, filenames, print_bytes );
if( ( ( pid[0] && wait_for_child( pid[0], "data feeder" ) != 0 ) ||
( pid[1] && wait_for_child( pid[1], "data feeder" ) != 0 ) ) &&
retval == 0 )
retval = 2;
for( int i = 0; i < 2; ++i )
{
if( close( infd[i] ) != 0 )
{ show_error( "Can't close output of data feeder", errno ); retval = 2; }
if( filenames[i] != "-" && close( old_infd[i] ) != 0 )
{
if( verbosity >= 0 )
std::fprintf( stderr, "%s: Can't close input file `%s': %s.\n",
util_name, filenames[i].c_str(), std::strerror( errno ) );
retval = 2;
}
}
if( std::fclose( stdout ) != 0 )
{
show_error( "Can't close stdout", errno );
retval = 2;
}
return retval;
}

3
zcmp.in
View file

@ -1,3 +0,0 @@
#! /bin/sh
bindir=`echo "$0" | sed -e 's,[^/]*$,,'`
exec "${bindir}"zdiff --cmp "$@"

476
zdiff.cc Normal file
View file

@ -0,0 +1,476 @@
/* Zdiff - decompress and compare two files line by line
Copyright (C) 2010 Antonio Diaz Diaz.
This program is free software: you can redistribute it and/or modify
it under the terms of the GNU General Public License as published by
the Free Software Foundation, either version 3 of the License, or
(at your option) any later version.
This program is distributed in the hope that it will be useful,
but WITHOUT ANY WARRANTY; without even the implied warranty of
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
GNU General Public License for more details.
You should have received a copy of the GNU General Public License
along with this program. If not, see <http://www.gnu.org/licenses/>.
*/
#define _FILE_OFFSET_BITS 64
#include <cctype>
#include <cerrno>
#include <climits>
#include <csignal>
#include <cstdio>
#include <cstdlib>
#include <cstring>
#include <string>
#include <vector>
#include <fcntl.h>
#include <stdint.h>
#include <unistd.h>
#include <sys/stat.h>
#if defined(__MSVCRT__) || defined(__OS2__)
#include <io.h>
#endif
#include "arg_parser.h"
#include "zutils.h"
#if CHAR_BIT != 8
#error "Environments where CHAR_BIT != 8 are not supported."
#endif
#ifndef LLONG_MAX
#define LLONG_MAX 0x7FFFFFFFFFFFFFFFLL
#endif
#ifndef LLONG_MIN
#define LLONG_MIN (-LLONG_MAX - 1LL)
#endif
#ifndef ULLONG_MAX
#define ULLONG_MAX 0xFFFFFFFFFFFFFFFFULL
#endif
namespace {
std::string fifonames[2]; // names of the two fifos passed to diff
#ifdef O_BINARY
const int o_binary = O_BINARY;
#else
const int o_binary = 0;
#endif
struct { const char * from; const char * to; } const known_extensions[] = {
{ ".bz2", "" },
{ ".tbz", ".tar" },
{ ".tbz2", ".tar" },
{ ".gz", "" },
{ ".tgz", ".tar" },
{ ".lz", "" },
{ ".tlz", ".tar" },
{ ".xz", "" },
{ ".txz", ".tar" },
{ 0, 0 } };
void show_help() throw()
{
std::printf( "Zdiff compares two files (\"-\" means standard input), and if they\n" );
std::printf( "differ, shows the differences line by line. If any given file is\n" );
std::printf( "compressed, its uncompressed content is used. Zdiff is a front end to\n" );
std::printf( "the diff program and has the limitation that messages from diff refer to\n" );
std::printf( "temporary filenames instead of those specified.\n" );
std::printf( "The supported compressors are bzip2, gzip, lzip and xz.\n" );
std::printf( "\nUsage: zdiff [options] file1 [file2]\n" );
std::printf( "\nCompares <file1> to <file2>. If <file2> is omitted zdiff tries the\n" );
std::printf( "following:\n" );
std::printf( "If <file1> is compressed, compares <file1> to the file with the\n" );
std::printf( "corresponding decompressed file name (removes the extension from\n" );
std::printf( "<file1>).\n" );
std::printf( "If <file1> is not compressed, compares <file1> to the uncompressed\n" );
std::printf( "contents of <file1>.[bz2|gz|lz|xz] (the first one that is found).\n" );
std::printf( "If no suitable file is found, compares <file1> to data read from\n" );
std::printf( "standard input.\n" );
std::printf( "\nExit status is 0 if inputs are identical, 1 if different, 2 if trouble.\n" );
std::printf( "\nOptions:\n" );
std::printf( " -h, --help display this help and exit\n" );
std::printf( " -V, --version output version information and exit\n" );
std::printf( " -a, --text treat all files as text\n" );
std::printf( " -b, --ignore-space-change ignore changes in the amount of white space\n" );
std::printf( " -B, --ignore-blank-lines ignore changes whose lines are all blank\n" );
std::printf( " -c use the context output format\n" );
std::printf( " -C, --context=<n> same as -c but use <n> lines of context\n" );
std::printf( " -d, --minimal try hard to find a smaller set of changes\n" );
std::printf( " -E, --ignore-tab-expansion ignore changes due to tab expansion\n" );
std::printf( " -i, --ignore-case ignore case differences in file contents\n" );
std::printf( " -p, --show-c-function show which C function each change is in\n" );
std::printf( " -q, --brief output only whether files differ\n" );
std::printf( " -s, --report-identical-files report when two files are identical\n" );
std::printf( " -t, --expand-tabs expand tabs to spaces in output\n" );
std::printf( " -T, --initial-tab make tabs line up by prepending a tab\n" );
std::printf( " -u use the unified output format\n" );
std::printf( " -U, --unified=<n> same as -u but use <n> lines of context\n" );
std::printf( " -w, --ignore-all-space ignore all white space\n" );
std::printf( "Numbers may be followed by a multiplier: k = kB = 10^3 = 1000,\n" );
std::printf( "Ki = KiB = 2^10 = 1024, M = 10^6, Mi = 2^20, G = 10^9, Gi = 2^30, etc...\n" );
show_help_addr();
}
int open_instream( const std::string & input_filename ) throw()
{
int infd = open( input_filename.c_str(), O_RDONLY | o_binary );
if( infd < 0 && verbosity >= 0 )
std::fprintf( stderr, "%s: Can't open input file `%s': %s.\n",
util_name, input_filename.c_str(), std::strerror( errno ) );
return infd;
}
int open_other_instream( std::string & name ) throw()
{
for( int i = 0; known_extensions[i].from; ++i )
{ // search uncompressed version
const std::string from( known_extensions[i].from );
if( name.size() > from.size() &&
name.compare( name.size() - from.size(), from.size(), from ) == 0 )
{
name.resize( name.size() - from.size() );
name += known_extensions[i].to;
return open( name.c_str(), O_RDONLY | o_binary );
}
}
for( int i = 0; simple_extensions[i]; ++i )
{ // search compressed version
const std::string s( name + simple_extensions[i] );
const int infd = open( s.c_str(), O_RDONLY | o_binary );
if( infd >= 0 ) { name = s; return infd; }
}
return -1;
}
bool check_identical( const char * const name1, const char * const name2 ) throw()
{
if( !std::strcmp( name1, name2 ) ) return true;
struct stat stat1, stat2;
if( stat( name1, &stat1 ) || stat( name2, &stat2 ) ) return false;
return ( stat1.st_ino == stat2.st_ino && stat1.st_dev == stat2.st_dev );
}
const char * my_basename( const char * filename ) throw()
{
const char * c = filename;
while( *c ) { if( *c == '/' ) { filename = c + 1; } ++c; }
return filename;
}
void remove_fifos() throw()
{
if( fifonames[0].size() )
{ std::remove( fifonames[0].c_str() ); fifonames[0].clear(); }
if( fifonames[1].size() )
{ std::remove( fifonames[1].c_str() ); fifonames[1].clear(); }
}
// Set fifonames[i] to "${TMPDIR}/<coded_pid><i>_<basename(filenames[i])>"
// and create FIFOs.
bool set_fifonames( const std::string filenames[2] )
{
enum { num_codes = 36 };
const char * const codes = "0123456789abcdefghijklmnopqrstuvwxyz";
const char * p = std::getenv( "TMPDIR" );
const int pid = getpid();
for( int i = 0; i < 2; ++i )
{
if( p ) fifonames[i] = p; else fifonames[i] = "/tmp";
fifonames[i] += '/';
int n = ( 2 * pid ) + i;
const unsigned int pos = fifonames[i].size();
do { fifonames[i].insert( pos, 1, codes[n % num_codes] );
n /= num_codes; }
while( n );
fifonames[i] += '_';
fifonames[i] += my_basename( filenames[i].c_str() );
}
for( int i = 0; i < 2; ++i )
if( mkfifo( fifonames[i].c_str(), S_IRUSR | S_IWUSR ) != 0 )
{
if( errno == EEXIST )
{
std::remove( fifonames[i].c_str() );
if( mkfifo( fifonames[i].c_str(), S_IRUSR | S_IWUSR ) == 0 )
continue;
}
if( verbosity >= 0 )
std::fprintf( stderr, "%s: Can't create FIFO `%s': %s.\n",
util_name, fifonames[i].c_str(), std::strerror( errno ) );
return false;
}
return true;
}
bool set_data_feeder( const std::string & fifoname, const int infd,
pid_t * const pidp )
{
std::string file_type;
const uint8_t * magic_data;
int magic_size;
const bool compressed =
test_format( infd, file_type, &magic_data, &magic_size );
if( compressed ) // compressed with `file_type'
{
int fda[2]; // pipe from feeder to decompressor
if( pipe( fda ) < 0 )
{ show_error( "Can't create pipe", errno ); return false; }
const pid_t pid = fork();
if( pid == 0 ) // child (decompressor feeder)
{
const pid_t pid2 = fork();
if( pid2 == 0 ) // grandchild (decompressor)
{
const int outfd = open( fifoname.c_str(), O_WRONLY | o_binary );
if( outfd < 0 )
{
if( verbosity >= 0 )
std::fprintf( stderr, "%s: Can't open FIFO `%s' for writing: %s.\n",
util_name, fifoname.c_str(), std::strerror( errno ) );
_exit( 2 );
}
if( dup2( fda[0], STDIN_FILENO ) >= 0 &&
dup2( outfd, STDOUT_FILENO ) >= 0 &&
close( fda[0] ) == 0 && close( fda[1] ) == 0 &&
close( outfd ) == 0 )
execlp( file_type.c_str(), file_type.c_str(), "-cdfq", (char *)0 );
if( verbosity >= 0 )
std::fprintf( stderr, "%s: Can't exec `%s': %s.\n",
util_name, file_type.c_str(), std::strerror( errno ) );
_exit( 2 );
}
if( pid2 < 0 )
{
if( verbosity >= 0 )
std::fprintf( stderr, "%s: Can't fork `%s': %s.\n",
util_name, file_type.c_str(), std::strerror( errno ) );
_exit( 2 );
}
if( close( fda[0] ) != 0 ||
!feed_data( infd, fda[1], magic_data, magic_size ) )
_exit( 2 );
if( close( fda[1] ) != 0 )
{ show_error( "Can't close output of feeder", errno ); _exit( 2 ); }
_exit( wait_for_child( pid2, file_type.c_str() ) );
}
// parent
close( fda[0] ); close( fda[1] );
if( pid < 0 )
{ show_error( "Can't fork decompressor feeder", errno ); return false; }
*pidp = pid;
}
else // not compressed
{
const pid_t pid = fork();
if( pid == 0 ) // child (feeder)
{
const int outfd = open( fifoname.c_str(), O_WRONLY | o_binary );
if( outfd < 0 )
{
if( verbosity >= 0 )
std::fprintf( stderr, "%s: Can't open FIFO `%s' for writing: %s.\n",
util_name, fifoname.c_str(), std::strerror( errno ) );
_exit( 2 );
}
if( !feed_data( infd, outfd, magic_data, magic_size ) )
_exit( 2 );
if( close( outfd ) != 0 )
{ show_error( "Can't close output of feeder", errno ); _exit( 2 ); }
_exit( 0 );
}
// parent
if( pid < 0 )
{ show_error( "Can't fork data feeder", errno ); return false; }
*pidp = pid;
}
return true;
}
extern "C" void signal_handler( int sig ) throw()
{
remove_fifos();
std::signal( sig, SIG_DFL );
std::raise( sig );
}
void set_signals() throw()
{
std::signal( SIGHUP, signal_handler );
std::signal( SIGINT, signal_handler );
std::signal( SIGTERM, signal_handler );
}
} // end namespace
int main( const int argc, const char * const argv[] )
{
std::vector< const char * > diff_args; // args to diff, maybe empty
invocation_name = argv[0];
util_name = "zdiff";
const Arg_parser::Option options[] =
{
{ 'a', "text", Arg_parser::no },
{ 'b', "ignore-space-change", Arg_parser::no },
{ 'B', "ignore-blank-lines", Arg_parser::no },
{ 'c', 0, Arg_parser::no },
{ 'C', "context", Arg_parser::yes },
{ 'd', "minimal", Arg_parser::no },
{ 'E', "ignore-tab-expansion", Arg_parser::no },
{ 'h', "help", Arg_parser::no },
{ 'i', "ignore-case", Arg_parser::no },
{ 'p', "show-c-function", Arg_parser::no },
{ 'q', "brief", Arg_parser::no },
{ 's', "report-identical-files", Arg_parser::no },
{ 't', "expand-tabs", Arg_parser::no },
{ 'T', "initial-tab", Arg_parser::no },
{ 'u', 0, Arg_parser::no },
{ 'U', "unified", Arg_parser::yes },
{ 'V', "version", Arg_parser::no },
{ 'w', "ignore-all-space", Arg_parser::no },
{ 0 , 0, Arg_parser::no } };
const Arg_parser parser( argc, argv, options );
if( parser.error().size() ) // bad option
{ show_error( parser.error().c_str(), 0, true ); return 2; }
int argind = 0;
for( ; argind < parser.arguments(); ++argind )
{
const int code = parser.code( argind );
if( !code ) break; // no more options
const char * const arg = parser.argument( argind ).c_str();
switch( code )
{
case 'a': diff_args.push_back( "-a" ); break;
case 'b': diff_args.push_back( "-b" ); break;
case 'B': diff_args.push_back( "-B" ); break;
case 'c': diff_args.push_back( "-c" ); break;
case 'C': diff_args.push_back( "-C" ); diff_args.push_back( arg ); break;
case 'd': diff_args.push_back( "-d" ); break;
case 'E': diff_args.push_back( "-E" ); break;
case 'h': show_help(); return 0;
case 'i': diff_args.push_back( "-i" ); break;
case 'p': diff_args.push_back( "-p" ); break;
case 'q': diff_args.push_back( "-q" ); break;
case 's': diff_args.push_back( "-s" ); break;
case 't': diff_args.push_back( "-t" ); break;
case 'T': diff_args.push_back( "-T" ); break;
case 'u': diff_args.push_back( "-u" ); break;
case 'U': diff_args.push_back( "-U" ); diff_args.push_back( arg ); break;
case 'V': show_version( "Zdiff" ); return 0;
case 'w': diff_args.push_back( "-w" ); break;
default : internal_error( "uncaught option" );
}
} // end process options
#if defined(__MSVCRT__) || defined(__OS2__)
_setmode( STDIN_FILENO, O_BINARY );
_setmode( STDOUT_FILENO, O_BINARY );
#endif
if( argind >= parser.arguments() )
{ show_error( "No files given.", 0, true ); return 2; }
if( argind + 2 < parser.arguments() )
{ show_error( "Too many files.", 0, true ); return 2; }
const int files = parser.arguments() - argind;
std::string filenames[2]; // file names of the two input files
filenames[0] = parser.argument( argind );
if( files == 2 ) filenames[1] = parser.argument( argind + 1 );
int infd[2]; // file descriptors of the two files
infd[0] = ( filenames[0] == "-" ) ?
STDIN_FILENO : open_instream( filenames[0] );
if( infd[0] < 0 ) return 2;
if( ( files == 1 && filenames[0] == "-" ) ||
( files == 2 && check_identical( filenames[0].c_str(),
filenames[1].c_str() ) ) )
return 0;
if( files == 2 )
{
infd[1] = ( filenames[1] == "-" ) ?
STDIN_FILENO : open_instream( filenames[1] );
if( infd[1] < 0 ) return 2;
}
else
{
filenames[1] = filenames[0];
infd[1] = open_other_instream( filenames[1] );
if( infd[1] < 0 ) { infd[1] = STDIN_FILENO; filenames[1] = "-"; }
}
std::atexit( remove_fifos );
set_signals();
if( !set_fifonames( filenames ) ) return 2;
const pid_t diff_pid = fork();
if( diff_pid == 0 ) // child (diff)
{
const char ** const argv = new const char *[diff_args.size()+5];
argv[0] = "diff";
for( unsigned int i = 0; i < diff_args.size(); ++i )
argv[i+1] = diff_args[i];
argv[diff_args.size()+1] = "--";
argv[diff_args.size()+2] = fifonames[0].c_str();
argv[diff_args.size()+3] = fifonames[1].c_str();
argv[diff_args.size()+4] = 0;
execvp( argv[0], (char **)argv );
show_error( "Can't exec `diff'." );
_exit( 2 );
}
// parent
if( diff_pid < 0 )
{ show_error( "Can't fork `diff'", errno ); return 2; }
pid_t pid[2];
if( !set_data_feeder( fifonames[0], infd[0], &pid[0] ) ||
!set_data_feeder( fifonames[1], infd[1], &pid[1] ) )
return 2;
int retval = wait_for_child( diff_pid, "diff" );
if( retval != 0 )
{
if( pid[0] ) kill( pid[0], SIGTERM );
if( pid[1] ) kill( pid[1], SIGTERM );
}
else
if( ( pid[0] && wait_for_child( pid[0], "data feeder" ) != 0 ) ||
( pid[1] && wait_for_child( pid[1], "data feeder" ) != 0 ) )
retval = 2;
for( int i = 0; i < 2; ++i )
if( filenames[i] != "-" && close( infd[i] ) != 0 )
{
if( verbosity >= 0 )
std::fprintf( stderr, "%s: Can't close input file `%s': %s.\n",
util_name, filenames[i].c_str(), std::strerror( errno ) );
retval = 2;
}
return retval;
}

160
zdiff.in
View file

@ -1,160 +0,0 @@
#! /bin/sh
# Zdiff - Diff/cmp wrapper for compressed files.
# Copyright (C) 2008, 2009 Antonio Diaz Diaz.
#
# This script is free software: you have unlimited permission
# to copy, distribute and modify it.
LC_ALL=C
export LC_ALL
args=
diff_prog=diff
file1=
file2=
two_hyphens=0
# Loop over args
while [ -n "$1" ] ; do
case "$1" in
--help | --he* | -h)
echo "Zdiff - Diff/cmp wrapper for compressed files."
echo
echo "Zdiff is a wrapper script around the diff and cmp commands that allows"
echo "transparent comparison of any combination of compressed and"
echo "non-compressed files. If any given file is compressed, its uncompressed"
echo "content is used. The supported compressors are bzip2, gzip, lzip and xz."
echo
echo "Zcmp is a shortcut for \"zdiff --cmp\""
echo
echo "Usage: $0 [OPTIONS] [DIFF_OPTIONS] FILE1 [FILE2]"
echo
echo "Compares FILE1 to FILE2. If FILE2 is omitted and FILE1 is compressed,"
echo "compares FILE1 to the file with the corresponding decompressed file"
echo "name (removes the extension from FILE1). If FILE2 is omitted and FILE1"
echo "is not compressed, compares FILE1 to the uncompressed contents of"
echo "FILE1.[bz2|gz|lz|xz] (the first one that is found)."
echo "DIFF_OPTIONS are passed directly to diff or cmp."
echo "The exit status from diff or cmp is preserved."
echo
echo "Options:"
echo " -h, --help display this help and exit"
echo " -V, --version output version information and exit"
echo " --diff use diff to compare files (default)"
echo " --cmp use cmp to compare files"
echo
echo "Report bugs to zutils-bug@nongnu.org"
echo "Zutils home page: http://www.nongnu.org/zutils/zutils.html"
exit 0 ;;
--version | --ve* | -V)
echo "Zdiff (zutils) VERSION"
echo "Copyright (C) 2009 Antonio Diaz Diaz."
echo "This script is free software: you have unlimited permission"
echo "to copy, distribute and modify it."
exit 0 ;;
--diff)
diff_prog=diff ;;
--cmp)
diff_prog=cmp ;;
-)
echo "$0: reading from stdin not supported"
exit 1 ;;
--)
shift; two_hyphens=1 ; break ;;
-?*)
args="${args} $1" ;;
*)
break ;;
esac
shift
done
# Loop over files
for i in "$@" ; do
if [ "$i" = "--" ] && [ ${two_hyphens} = 0 ] ; then two_hyphens=1
else
if [ -f "$i" ] ; then
if [ -z "${file1}" ] ; then file1="$i"
else
if [ -z "${file2}" ] ; then file2="$i"
else
echo "$0: Too many files; use --help for usage." 1>&2
fi
fi
else
echo "$0: File \"$i\" not found or not a regular file" 1>&2
exit 1
fi
fi
done
if [ -z "${file1}" ] ; then
echo "$0: No files given; use --help for usage." 1>&2
exit 1
fi
if [ -z "${file2}" ] ; then
case "${file1}" in
*.bz2) file2=`printf "%s" "${file1}" | sed -e 's,.bz2$,,'` ;;
*.tbz) file2=`printf "%s" "${file1}" | sed -e 's,tbz$,tar,'` ;;
*.tbz2) file2=`printf "%s" "${file1}" | sed -e 's,tbz2$,tar,'` ;;
*.gz) file2=`printf "%s" "${file1}" | sed -e 's,.gz$,,'` ;;
*.tgz) file2=`printf "%s" "${file1}" | sed -e 's,tgz$,tar,'` ;;
*.lz) file2=`printf "%s" "${file1}" | sed -e 's,.lz$,,'` ;;
*.tlz) file2=`printf "%s" "${file1}" | sed -e 's,tlz$,tar,'` ;;
*.xz) file2=`printf "%s" "${file1}" | sed -e 's,.xz$,,'` ;;
*.txz) file2=`printf "%s" "${file1}" | sed -e 's,txz$,tar,'` ;;
*)
if [ -f "${file1}.bz2" ] ; then file2="${file1}.bz2"
elif [ -f "${file1}.gz" ] ; then file2="${file1}.gz"
elif [ -f "${file1}.lz" ] ; then file2="${file1}.lz"
elif [ -f "${file1}.xz" ] ; then file2="${file1}.xz"
else
echo "$0: Compressed version of ${file1} not found; use --help for usage." 1>&2
exit 1
fi ;;
esac
fi
prog1=
prog2=
bindir=`echo "$0" | sed -e 's,[^/]*$,,'`
if [ -f "${file1}" ] ; then
prog_name=`"${bindir}"zutils -t -- "${file1}"`
case "${prog_name}" in
bzip2 | gzip | lzip | xz) prog1=${prog_name} ;;
esac
fi
if [ -f "${file2}" ] ; then
prog_name=`"${bindir}"zutils -t -- "${file2}"`
case "${prog_name}" in
bzip2 | gzip | lzip | xz) prog2=${prog_name} ;;
esac
fi
retval=0
if [ -n "${prog1}" ] ; then
if [ -n "${prog2}" ] ; then
tmp_file=`mktemp "${TMPDIR:-/tmp}"/zdiff.XXXXXXXXXX` || {
echo 'cannot create a temporary file' 1>&2
exit 1
}
${prog2} -cdfq -- "${file2}" > "${tmp_file}" || exit 1
${prog1} -cdfq -- "${file1}" | ${diff_prog} ${args} - -- "${tmp_file}"
retval=$?
rm -f "${tmp_file}" || retval=$?
else
${prog1} -cdfq -- "${file1}" | ${diff_prog} ${args} - -- "${file2}"
retval=$?
fi
else
if [ -n "${prog2}" ] ; then
${prog2} -cdfq -- "${file2}" | ${diff_prog} ${args} -- "${file1}" -
retval=$?
else
${diff_prog} ${args} -- "${file1}" "${file2}"
retval=$?
fi
fi
exit ${retval}

2
zegrep.in
View file

@ -1,3 +1,3 @@
#! /bin/sh
bindir=`echo "$0" | sed -e 's,[^/]*$,,'`
exec "${bindir}"zgrep -E "$@"
exec "${bindir}"zutils --zgrep -E "$@"

2
zfgrep.in
View file

@ -1,3 +1,3 @@
#! /bin/sh
bindir=`echo "$0" | sed -e 's,[^/]*$,,'`
exec "${bindir}"zgrep -F "$@"
exec "${bindir}"zutils --zgrep -F "$@"

159
zgrep.cc Normal file
View file

@ -0,0 +1,159 @@
/* Zgrep - search compressed files for a regular expression
Copyright (C) 2010 Antonio Diaz Diaz.
This program is free software: you can redistribute it and/or modify
it under the terms of the GNU General Public License as published by
the Free Software Foundation, either version 3 of the License, or
(at your option) any later version.
This program is distributed in the hope that it will be useful,
but WITHOUT ANY WARRANTY; without even the implied warranty of
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
GNU General Public License for more details.
You should have received a copy of the GNU General Public License
along with this program. If not, see <http://www.gnu.org/licenses/>.
*/
void show_zgrep_help() throw()
{
std::printf( "Zgrep is a front end to the grep program that allows transparent search\n" );
std::printf( "on any combination of compressed and non-compressed files. If any given\n" );
std::printf( "file is compressed, its uncompressed content is used. If a given file\n" );
std::printf( "does not exist, and its name does not end with one of the known\n" );
std::printf( "extensions, zgrep tries the compressed file names corresponding to the\n" );
std::printf( "supported compressors. If no files are specified, data is read from\n" );
std::printf( "standard input, decompressed if needed, and fed to grep. Data read from\n" );
std::printf( "standard input must be of the same type; all uncompressed or all\n" );
std::printf( "compressed with the same compressor.\n" );
std::printf( "The supported compressors are bzip2, gzip, lzip and xz.\n" );
std::printf( "\nUsage: zgrep [options] <pattern> [files]\n" );
std::printf( "\nExit status is 0 if match, 1 if no match, 2 if trouble.\n" );
std::printf( "\nOptions:\n" );
std::printf( " --help display this help and exit\n" );
std::printf( " -V, --version output version information and exit\n" );
std::printf( " -a, --text treat all files as text\n" );
std::printf( " -A, --after-context=<n> print <n> lines of trailing context\n" );
std::printf( " -b, --byte-offset print the byte offset of each line\n" );
std::printf( " -B, --before-context=<n> print <n> lines of leading context\n" );
std::printf( " -c, --count only print a count of matching lines per file\n" );
std::printf( " -C, --context=<n> print <n> lines of output context\n" );
std::printf( " -e, --regexp=<pattern> use <pattern> as the pattern to match\n" );
std::printf( " -E, --extended-regexp <pattern> is an extended regular expression\n" );
std::printf( " -f, --file=<file> obtain patterns from <file>\n" );
std::printf( " -F, --fixed-strings <pattern> is a set of newline-separated strings\n" );
std::printf( " -h, --no-filename suppress the prefixing filename on output\n" );
std::printf( " -H, --with-filename print the filename for each match\n" );
std::printf( " -i, --ignore-case ignore case distinctions\n" );
std::printf( " -I ignore binary files\n" );
std::printf( " -l, --files-with-matches only print names of files containing matches\n" );
std::printf( " -L, --files-without-match only print names of files containing no matches\n" );
std::printf( " -m, --max-count=<n> stop after <n> matches\n" );
std::printf( " -n, --line-number print the line number of each line\n" );
std::printf( " -o, --only-matching show only the part of a line matching <pattern>\n" );
std::printf( " -q, --quiet suppress all messages\n" );
std::printf( " -r, --recursive operate recursively on directories\n" );
std::printf( " -s, --no-messages suppress error messages\n" );
std::printf( " -v, --invert-match select non-matching lines\n" );
std::printf( " --verbose verbose mode (show error messages)\n" );
std::printf( " -w, --word-regexp match only whole words\n" );
std::printf( " -x, --line-regexp match only whole lines\n" );
show_help_addr();
}
int zgrep_stdin( int infd, const std::vector< const char * > & grep_args )
{
pid_t pid;
if( !set_data_feeder( &infd, &pid ) ) return 2;
const pid_t grep_pid = fork();
if( grep_pid == 0 ) // child (grep)
{
if( dup2( infd, STDIN_FILENO ) >= 0 && close( infd ) == 0 )
{
const char ** const argv = new const char *[grep_args.size()+2];
argv[0] = "grep";
for( unsigned int i = 0; i < grep_args.size(); ++i )
argv[i+1] = grep_args[i];
argv[grep_args.size()+1] = 0;
execvp( argv[0], (char **)argv );
}
show_error( "Can't exec `grep'." );
_exit( 2 );
}
// parent
if( grep_pid < 0 )
{ show_error( "Can't fork `grep'", errno ); return 2; }
int retval = 0;
if( pid && wait_for_child( pid, "data feeder" ) != 0 ) retval = 2;
if( wait_for_child( grep_pid, "grep" ) != 0 ) retval = 2;
if( close( infd ) != 0 )
{ show_error( "Can't close output of data feeder", errno ); return 2; }
return retval;
}
int zgrep_file( int infd, const std::string & input_filename,
const std::vector< const char * > & grep_args,
const bool grep_list, const bool grep_show_name )
{
pid_t pid;
if( !set_data_feeder( &infd, &pid ) ) return 2;
int fda[2]; // pipe from grep
if( pipe( fda ) < 0 )
{ show_error( "Can't create pipe", errno ); return 2; }
const pid_t grep_pid = fork();
if( grep_pid == 0 ) // child (grep)
{
if( dup2( infd, STDIN_FILENO ) >= 0 &&
dup2( fda[1], STDOUT_FILENO ) >= 0 &&
close( infd ) == 0 && close( fda[0] ) == 0 && close( fda[1] ) == 0 )
{
const char ** const argv = new const char *[grep_args.size()+2];
argv[0] = "grep";
for( unsigned int i = 0; i < grep_args.size(); ++i )
argv[i+1] = grep_args[i];
argv[grep_args.size()+1] = 0;
execvp( argv[0], (char **)argv );
}
show_error( "Can't exec `grep'." );
_exit( 2 );
}
// parent
close( fda[1] );
if( grep_pid < 0 )
{ show_error( "Can't fork `grep'", errno ); return 2; }
enum { buffer_size = 256 };
uint8_t buffer[buffer_size];
bool line_begin = true;
while( true )
{
const int size = readblock( fda[0], buffer, buffer_size );
if( size != buffer_size && errno )
{ show_error( "Read error", errno ); return 2; }
if( size > 0 && !grep_list )
{
if( grep_show_name )
for( int i = 0; i < size; ++i )
{
if( line_begin )
{ line_begin = false; std::printf( "%s:", input_filename.c_str() ); }
if( buffer[i] == '\n' ) line_begin = true;
putchar( buffer[i] );
}
else if( std::fwrite( buffer, 1, size, stdout ) != (unsigned int)size )
{ show_error( "Write error", errno ); return 2; }
}
if( size < buffer_size ) break;
}
int retval = 0;
if( pid && wait_for_child( pid, "data feeder" ) != 0 ) retval = 2;
if( wait_for_child( grep_pid, "grep" ) != 0 ) retval = 2;
if( grep_list && retval == 0 )
std::printf( "%s\n", input_filename.c_str() );
if( close( infd ) != 0 )
{ show_error( "Can't close output of data feeder", errno ); return 2; }
if( close( fda[0] ) != 0 )
{ show_error( "Can't close output of grep", errno ); return 2; }
return retval;
}

135
zgrep.in
View file

@ -1,136 +1,3 @@
#! /bin/sh
# Zgrep - Grep wrapper for compressed files.
# Copyright (C) 2008, 2009 Antonio Diaz Diaz.
#
# This script is free software: you have unlimited permission
# to copy, distribute and modify it.
LC_ALL=C
export LC_ALL
args=
have_pat=0
list=0
no_name=0
two_hyphens=0
# Loop over args until pattern is found
while [ -n "$1" ] ; do
case "$1" in
--help | --he* | -h)
echo "Zgrep - Grep wrapper for compressed files."
echo
echo "Zgrep is a wrapper script around the grep command that allows"
echo "transparent search on any combination of compressed and non-compressed"
echo "files. If any given file is compressed, its uncompressed content is"
echo "used. If a given file does not exist, zgrep tries the compressed file"
echo "names corresponding to the supported compressors. If no files are"
echo "specified, data is read from standard input, decompressed if needed, and"
echo "fed to grep. Data read from standard input must be of the same type; all"
echo "uncompressed or all compressed with the same compressor."
echo "The supported compressors are bzip2, gzip, lzip and xz."
echo
echo "Zegrep is a shortcut for \"zgrep -E\""
echo "Zfgrep is a shortcut for \"zgrep -F\""
echo
echo "Usage: $0 [OPTIONS] [GREP_OPTIONS] PATTERN [FILES]"
echo
echo "GREP_OPTIONS are passed directly to grep."
echo "The exit status from grep is preserved."
echo
echo "Options:"
echo " -h, --help display this help and exit"
echo " -V, --version output version information and exit"
echo
echo "Report bugs to zutils-bug@nongnu.org"
echo "Zutils home page: http://www.nongnu.org/zutils/zutils.html"
exit 0 ;;
--version | --ve* | -V)
echo "Zgrep (zutils) VERSION"
echo "Copyright (C) 2009 Antonio Diaz Diaz."
echo "This script is free software: you have unlimited permission"
echo "to copy, distribute and modify it."
exit 0 ;;
-[drRzZ] | --di* | --exc* | --inc* | --nu* | --rec*)
echo "$0: option $1 not supported"
exit 1 ;;
-e?* | -f?* | --file=* | --reg*=*)
args="${args} $1"; have_pat=1 ;;
-e | -f | --file | --reg*)
args="${args} $1 $2"; shift; have_pat=1 ;;
--*=*)
args="${args} $1" ;;
-[ABCDm] | --af* | --be* | --binary-* | --con* | --de* | --[lm]a*)
args="${args} $1 $2"; shift ;;
-l | --files-with-*)
args="${args} $1"; list=1 ;;
-h | --no-f*)
args="${args} $1"; no_name=1 ;;
--)
shift ; two_hyphens=1 ; break ;;
-?*)
args="${args} $1" ;;
*)
if [ ${have_pat} = 0 ] ; then args="${args} $1"; have_pat=1
else break
fi ;;
esac
shift
done
if [ ${have_pat} = 0 ] ; then
echo "$0: Pattern not found; use --help for usage." 1>&2
exit 1
fi
if [ $# = 0 ] ; then
bindir=`echo "$0" | sed -e 's,[^/]*$,,'`
prog_name=`"${bindir}"zutils -t`
case "${prog_name}" in
bzip2 | gzip | lzip | xz) prog="${prog_name} -cdfq" ;;
*) prog=cat ;;
esac
{ "${bindir}"zutils -m ${prog_name} ; cat ; } | ${prog} | grep ${args}
exit $?
fi
retval=0
for i in "$@" ; do
if [ "$i" = "--" ] && [ ${two_hyphens} = 0 ] ; then two_hyphens=1
else
if [ ! -f "$i" ] ; then
if [ -f "$i.gz" ] ; then i="$i.gz"
elif [ -f "$i.bz2" ] ; then i="$i.bz2"
elif [ -f "$i.lz" ] ; then i="$i.lz"
elif [ -f "$i.xz" ] ; then i="$i.xz"
else
echo "$0: File \"$i\" not found or not a regular file" 1>&2
if [ ${retval} = 0 ] ; then retval=1 ; fi
continue
fi
fi
bindir=`echo "$0" | sed -e 's,[^/]*$,,'`
prog_name=`"${bindir}"zutils -t -- "$i"`
case "${prog_name}" in
bzip2 | gzip | lzip | xz) prog="${prog_name} -cdfq" ;;
*) prog=cat ;;
esac
if [ ${list} = 1 ] ; then
${prog} -- "$i" | grep ${args} 2>&1 > /dev/null && echo "$i"
r=$?
elif [ $# = 1 ] || [ ${no_name} = 1 ] ; then
${prog} -- "$i" | grep ${args}
r=$?
else
j=`printf "%s" "$i" | sed -e 's,\\\\,\\\\\\\\,g'`
j=`printf "%s" "$j" | sed -e 's,|,\\\\|,g'`
j=`printf "%s" "$j" | sed -e 's,&,\\\\&,g'`
j=`printf "%s" "$j" | tr '\n' ' '`
${prog} -- "$i" | grep ${args} | sed -e "s,^,${j}:,"
r=$?
fi
[ $r != 0 ] && retval="$r"
fi
done
exit ${retval}
exec "${bindir}"zutils --zgrep "$@"

119
ztest.cc Normal file
View file

@ -0,0 +1,119 @@
/* Ztest - verify integrity of compressed files
Copyright (C) 2010 Antonio Diaz Diaz.
This program is free software: you can redistribute it and/or modify
it under the terms of the GNU General Public License as published by
the Free Software Foundation, either version 3 of the License, or
(at your option) any later version.
This program is distributed in the hope that it will be useful,
but WITHOUT ANY WARRANTY; without even the implied warranty of
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
GNU General Public License for more details.
You should have received a copy of the GNU General Public License
along with this program. If not, see <http://www.gnu.org/licenses/>.
*/
void show_ztest_help() throw()
{
std::printf( "Ztest verifies the integrity of the specified compressed files.\n" );
std::printf( "Non-compressed files are ignored. If no files are specified, the\n" );
std::printf( "integrity of compressed data read from standard input is verified. Data\n" );
std::printf( "read from standard input must be all compressed with the same compressor.\n" );
std::printf( "The supported compressors are bzip2, gzip, lzip and xz.\n" );
std::printf( "\nUsage: ztest [options] [files]\n" );
std::printf( "\nExit status is 2 if any compressed file is corrupt, 0 otherwise.\n" );
std::printf( "\nOptions:\n" );
std::printf( " -h, --help display this help and exit\n" );
std::printf( " -V, --version output version information and exit\n" );
std::printf( " -q, --quiet suppress all messages\n" );
std::printf( " -r, --recursive operate recursively on directories\n" );
std::printf( " -v, --verbose be verbose (a 2nd -v gives more)\n" );
show_help_addr();
}
int ztest_stdin( const int infd,
const std::vector< const char * > & ztest_args )
{
std::string file_type;
const uint8_t * magic_data;
int magic_size = 0;
if( !test_format( infd, file_type, &magic_data, &magic_size ) )
{ show_error( "Unknown data format read from stdin." ); return 2; }
int fda[2];
if( pipe( fda ) < 0 )
{ show_error( "Can't create pipe", errno ); return 1; }
const pid_t pid = fork();
if( pid == 0 ) // child (decompressor)
{
if( dup2( fda[0], STDIN_FILENO ) >= 0 &&
close( fda[0] ) == 0 && close( fda[1] ) == 0 )
{
const char ** const argv = new const char *[ztest_args.size()+3];
argv[0] = file_type.c_str();
for( unsigned int i = 0; i < ztest_args.size(); ++i )
argv[i+1] = ztest_args[i];
argv[ztest_args.size()+1] = "-t";
argv[ztest_args.size()+2] = 0;
execvp( argv[0], (char **)argv );
}
if( verbosity >= 0 )
std::fprintf( stderr, "%s: Can't exec `%s': %s.\n",
util_name, file_type.c_str(), std::strerror( errno ) );
_exit( 1 );
}
// parent
if( pid < 0 )
{
if( verbosity >= 0 )
std::fprintf( stderr, "%s: Can't fork `%s': %s.\n",
util_name, file_type.c_str(), std::strerror( errno ) );
return 1;
}
close( fda[0] );
if( !feed_data( infd, fda[1], magic_data, magic_size ) ) return 1;
if( close( fda[1] ) != 0 )
{ show_error( "Can't close output of data feeder", errno ); return 1; }
return wait_for_child( pid, file_type.c_str() );
}
int ztest_file( const int infd, const std::string & input_filename,
const std::vector< const char * > & ztest_args )
{
std::string file_type;
const uint8_t * magic_data;
int magic_size = 0;
if( !test_format( infd, file_type, &magic_data, &magic_size ) )
return 0; // ignored
const pid_t pid = fork();
if( pid == 0 ) // child (decompressor)
{
const char ** const argv = new const char *[ztest_args.size()+5];
argv[0] = file_type.c_str();
for( unsigned int i = 0; i < ztest_args.size(); ++i )
argv[i+1] = ztest_args[i];
argv[ztest_args.size()+1] = "-t";
argv[ztest_args.size()+2] = "--";
argv[ztest_args.size()+3] = input_filename.c_str();
argv[ztest_args.size()+4] = 0;
execvp( argv[0], (char **)argv );
if( verbosity >= 0 )
std::fprintf( stderr, "%s: Can't exec `%s': %s.\n",
util_name, argv[0], std::strerror( errno ) );
_exit( 1 );
}
// parent
if( pid < 0 )
{
if( verbosity >= 0 )
std::fprintf( stderr, "%s: Can't fork `%s': %s.\n",
util_name, file_type.c_str(), std::strerror( errno ) );
return 1;
}
return wait_for_child( pid, file_type.c_str() );
}

101
ztest.in
View file

@ -1,102 +1,3 @@
#! /bin/sh
# Ztest - Test integrity of compressed files.
# Copyright (C) 2009 Antonio Diaz Diaz.
#
# This script is free software: you have unlimited permission
# to copy, distribute and modify it.
LC_ALL=C
export LC_ALL
args=
recursive=0
two_hyphens=0
# Loop over args until a filename is found
while [ -n "$1" ] ; do
case "$1" in
--help | --he* | -h)
echo "Ztest - Test integrity of compressed files."
echo
echo "Ztest verifies the integrity of the specified compressed files."
echo "Non-compressed files are ignored. If no files are specified, the"
echo "integrity of compressed data read from standard input is verified. Data"
echo "read from standard input must be all compressed with the same compressor."
echo "The supported compressors are bzip2, gzip, lzip and xz."
echo
echo "Usage: $0 [OPTIONS] [FILES]"
echo
echo "The exit status is 1 if any compressed file is corrupt, 0 otherwise."
echo
echo "Options:"
echo " -h, --help display this help and exit"
echo " -V, --version output version information and exit"
echo " -q, --quiet suppress all messages"
echo " -r, --recursive operate recursively on directories"
echo " -v, --verbose be verbose (a 2nd -v gives more)"
echo
echo "Report bugs to zutils-bug@nongnu.org"
echo "Zutils home page: http://www.nongnu.org/zutils/zutils.html"
exit 0 ;;
--version | --ve* | -V)
echo "Ztest (zutils) VERSION"
echo "Copyright (C) 2009 Antonio Diaz Diaz."
echo "This script is free software: you have unlimited permission"
echo "to copy, distribute and modify it."
exit 0 ;;
-r | --re*)
recursive=1 ;;
-v | -vv | -vvv | --ve* | -q | --qu*)
args="${args} $1" ;;
--)
shift ; two_hyphens=1 ; break ;;
- | -?*)
;;
*)
break ;;
esac
shift
done
if [ $# = 0 ] ; then
bindir=`echo "$0" | sed -e 's,[^/]*$,,'`
prog=`"${bindir}"zutils -t`
case "${prog}" in
bzip2 | gzip | lzip | xz)
;;
*) echo "$0: Unknown data format read from stdin" 1>&2
exit 1 ;;
esac
{ "${bindir}"zutils -m ${prog} ; cat ; } | ${prog} -t ${args}
exit $?
fi
retval=0
for i in "$@" ; do
if [ "$i" = "--" ] && [ ${two_hyphens} = 0 ] ; then two_hyphens=1
else
if [ ! -f "$i" ] ; then
if [ ${recursive} = 1 ] && [ -d "$i" ] ; then
bad_files=`find "$i" -type f \( -exec "$0" ${args} '{}' ';' -o -print \)`
if [ ${retval} = 0 ] && [ -n "${bad_files}" ] ; then retval=1 ; fi
continue
else
echo "$0: File \"$i\" not found or not a regular file" 1>&2
if [ ${retval} = 0 ] ; then retval=1 ; fi
continue
fi
fi
bindir=`echo "$0" | sed -e 's,[^/]*$,,'`
prog=`"${bindir}"zutils -t -- "$i"`
case "${prog}" in
bzip2 | gzip | lzip | xz)
;;
*) continue ;;
esac
${prog} -t ${args} -- "$i"
r=$?
if [ $r != 0 ] ; then retval=$r ; fi
fi
done
exit ${retval}
exec "${bindir}"zutils --ztest "$@"

301
zutils.cc Normal file
View file

@ -0,0 +1,301 @@
/* Zutils - Utilities dealing with compressed files
Copyright (C) 2009, 2010 Antonio Diaz Diaz.
This program is free software: you can redistribute it and/or modify
it under the terms of the GNU General Public License as published by
the Free Software Foundation, either version 3 of the License, or
(at your option) any later version.
This program is distributed in the hope that it will be useful,
but WITHOUT ANY WARRANTY; without even the implied warranty of
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
GNU General Public License for more details.
You should have received a copy of the GNU General Public License
along with this program. If not, see <http://www.gnu.org/licenses/>.
*/
#define _FILE_OFFSET_BITS 64
#include <cerrno>
#include <cstdio>
#include <cstdlib>
#include <cstring>
#include <string>
#include <stdint.h>
#include <unistd.h>
#include <sys/wait.h>
#include "zutils.h"
const char * invocation_name = 0;
const char * util_name = program_name;
int verbosity = 0;
// Returns the number of bytes really read.
// If (returned value < size) and (errno == 0), means EOF was reached.
//
int readblock( const int fd, uint8_t * const buf, const int size ) throw()
{
int rest = size;
errno = 0;
while( rest > 0 )
{
errno = 0;
const int n = read( fd, buf + size - rest, rest );
if( n > 0 ) rest -= n;
else if( n == 0 ) break;
else if( errno != EINTR && errno != EAGAIN ) break;
}
return ( rest > 0 ) ? size - rest : size;
}
// Returns the number of bytes really written.
// If (returned value < size), it is always an error.
//
int writeblock( const int fd, const uint8_t * const buf, const int size ) throw()
{
int rest = size;
errno = 0;
while( rest > 0 )
{
errno = 0;
const int n = write( fd, buf + size - rest, rest );
if( n > 0 ) rest -= n;
else if( errno && errno != EINTR && errno != EAGAIN ) break;
}
return ( rest > 0 ) ? size - rest : size;
}
bool feed_data( const int infd, const int outfd,
const uint8_t * magic_data, const int magic_size )
{
if( writeblock( outfd, magic_data, magic_size ) != magic_size )
{ show_error( "Write error", errno ); return false; }
enum { buffer_size = 4096 };
uint8_t buffer[buffer_size];
while( true )
{
const int size = readblock( infd, buffer, buffer_size );
if( size != buffer_size && errno )
{ show_error( "Read error", errno ); return false; }
if( size > 0 && writeblock( outfd, buffer, size ) != size )
{ show_error( "Write error", errno ); return false; }
if( size < buffer_size ) break;
}
return true;
}
bool set_data_feeder( int * const infdp, pid_t * const pidp )
{
std::string file_type;
const uint8_t * magic_data;
int magic_size;
const bool compressed =
test_format( *infdp, file_type, &magic_data, &magic_size );
if( compressed ) // compressed with `file_type'
{
int fda[2]; // pipe from feeder
int fda2[2]; // pipe from decompressor
if( pipe( fda ) < 0 || pipe( fda2 ) < 0 )
{ show_error( "Can't create pipe", errno ); return false; }
const int old_infd = *infdp;
*infdp = fda2[0];
const pid_t pid = fork();
if( pid == 0 ) // child (decompressor feeder)
{
const pid_t pid2 = fork();
if( pid2 == 0 ) // grandchild (decompressor)
{
if( dup2( fda[0], STDIN_FILENO ) >= 0 &&
dup2( fda2[1], STDOUT_FILENO ) >= 0 &&
close( fda[0] ) == 0 && close( fda[1] ) == 0 &&
close( fda2[0] ) == 0 && close( fda2[1] ) == 0 )
execlp( file_type.c_str(), file_type.c_str(), "-cdfq", (char *)0 );
if( verbosity >= 0 )
std::fprintf( stderr, "%s: Can't exec `%s': %s.\n",
util_name, file_type.c_str(), std::strerror( errno ) );
_exit( 2 );
}
if( pid2 < 0 )
{
if( verbosity >= 0 )
std::fprintf( stderr, "%s: Can't fork `%s': %s.\n",
util_name, file_type.c_str(), std::strerror( errno ) );
_exit( 2 );
}
if( close( fda[0] ) != 0 ||
close( fda2[0] ) != 0 || close( fda2[1] ) != 0 ||
!feed_data( old_infd, fda[1], magic_data, magic_size ) )
_exit( 2 );
if( close( fda[1] ) != 0 )
{ show_error( "Can't close output of decompressor feeder", errno );
_exit( 2 ); }
_exit( wait_for_child( pid2, file_type.c_str() ) );
}
// parent
close( fda[0] ); close( fda[1] ); close( fda2[1] );
if( pid < 0 )
{ show_error( "Can't fork decompressor feeder", errno ); return false; }
*pidp = pid;
}
else // not compressed
{
int fda[2]; // pipe from feeder
if( pipe( fda ) < 0 )
{ show_error( "Can't create pipe", errno ); return false; }
const int old_infd = *infdp;
*infdp = fda[0];
const pid_t pid = fork();
if( pid == 0 ) // child (feeder)
{
if( close( fda[0] ) != 0 ||
!feed_data( old_infd, fda[1], magic_data, magic_size ) )
_exit( 2 );
if( close( fda[1] ) != 0 )
{ show_error( "Can't close output of data feeder", errno );
_exit( 2 ); }
_exit( 0 );
}
// parent
close( fda[1] );
if( pid < 0 )
{ show_error( "Can't fork data feeder", errno ); return false; }
*pidp = pid;
}
return true;
}
void show_help_addr() throw()
{
std::printf( "\nReport bugs to zutils-bug@nongnu.org\n" );
std::printf( "Zutils home page: http://www.nongnu.org/zutils/zutils.html\n" );
}
void show_version( const char * const Util_name ) throw()
{
if( !Util_name || !*Util_name )
std::printf( "%s %s\n", Program_name, PROGVERSION );
else
std::printf( "%s (%s) %s\n", Util_name, program_name, PROGVERSION );
std::printf( "Copyright (C) %s Antonio Diaz Diaz.\n", program_year );
std::printf( "License GPLv3+: GNU GPL version 3 or later <http://gnu.org/licenses/gpl.html>\n" );
std::printf( "This is free software: you are free to change and redistribute it.\n" );
std::printf( "There is NO WARRANTY, to the extent permitted by law.\n" );
}
void show_error( const char * const msg, const int errcode,
const bool help ) throw()
{
if( verbosity >= 0 )
{
if( msg && msg[0] )
{
std::fprintf( stderr, "%s: %s", util_name, msg );
if( errcode > 0 )
std::fprintf( stderr, ": %s", std::strerror( errcode ) );
std::fprintf( stderr, "\n" );
}
if( help && invocation_name && invocation_name[0] )
std::fprintf( stderr, "Try `%s --help' for more information.\n",
invocation_name );
}
}
void internal_error( const char * const msg )
{
if( verbosity >= 0 )
std::fprintf( stderr, "%s: internal error: %s.\n", util_name, msg );
std::exit( 3 );
}
unsigned char xdigit( const int value ) throw()
{
if( value >= 0 && value <= 9 ) return '0' + value;
if( value >= 10 && value <= 15 ) return 'A' + ( value - 10 );
return 0;
}
bool test_format( const int infd, std::string & file_type,
const uint8_t ** const magic_datap, int * const magic_sizep )
{
enum { buf_size = 5 };
static uint8_t buf[buf_size];
int i = 0;
file_type.clear();
if( readblock( infd, buf, 1 ) == 1 )
{
++i;
if( buf[0] == bzip2_magic[0] )
{
if( readblock( infd, &buf[i], 1 ) == 1 && buf[i++] == bzip2_magic[1] &&
readblock( infd, &buf[i], 1 ) == 1 && buf[i++] == bzip2_magic[2] )
{ file_type = "bzip2";
*magic_datap = bzip2_magic; *magic_sizep = bzip2_magic_size; }
}
else if( buf[0] == gzip_magic[0] )
{
if( readblock( infd, &buf[i], 1 ) == 1 && buf[i++] == gzip_magic[1] )
{ file_type = "gzip";
*magic_datap = gzip_magic; *magic_sizep = gzip_magic_size; }
}
else if( buf[0] == lzip_magic[0] )
{
if( readblock( infd, &buf[i], 1 ) == 1 && buf[i++] == lzip_magic[1] &&
readblock( infd, &buf[i], 1 ) == 1 && buf[i++] == lzip_magic[2] &&
readblock( infd, &buf[i], 1 ) == 1 && buf[i++] == lzip_magic[3] )
{ file_type = "lzip";
*magic_datap = lzip_magic; *magic_sizep = lzip_magic_size; }
}
else if( buf[0] == xz_magic[0] )
{
if( readblock( infd, &buf[i], 1 ) == 1 && buf[i++] == xz_magic[1] &&
readblock( infd, &buf[i], 1 ) == 1 && buf[i++] == xz_magic[2] &&
readblock( infd, &buf[i], 1 ) == 1 && buf[i++] == xz_magic[3] &&
readblock( infd, &buf[i], 1 ) == 1 && buf[i++] == xz_magic[4] )
{ file_type = "xz";
*magic_datap = xz_magic; *magic_sizep = xz_magic_size; }
}
}
if( file_type.size() ) return true;
for( int j = 0; j < i; ++j )
{
file_type += xdigit( buf[j] >> 4 );
file_type += xdigit( buf[j] & 0x0F );
}
*magic_datap = buf; *magic_sizep = i;
return false;
}
int wait_for_child( const pid_t pid, const char * const name )
{
int status;
while( waitpid( pid, &status, 0 ) == -1 )
{
if( errno != EINTR )
{
if( verbosity >= 0 )
std::fprintf( stderr, "%s: Error waiting termination of `%s': %s.\n",
util_name, name, std::strerror( errno ) );
_exit( 1 );
}
}
if( WIFEXITED( status ) ) return WEXITSTATUS( status );
else return 1;
}

53
zutils.h Normal file
View file

@ -0,0 +1,53 @@
/* Zutils - Utilities dealing with compressed files
Copyright (C) 2009, 2010 Antonio Diaz Diaz.
This program is free software: you can redistribute it and/or modify
it under the terms of the GNU General Public License as published by
the Free Software Foundation, either version 3 of the License, or
(at your option) any later version.
This program is distributed in the hope that it will be useful,
but WITHOUT ANY WARRANTY; without even the implied warranty of
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
GNU General Public License for more details.
You should have received a copy of the GNU General Public License
along with this program. If not, see <http://www.gnu.org/licenses/>.
*/
const char * const Program_name = "Zutils";
const char * const program_name = "zutils";
const char * const program_year = "2010";
extern const char * invocation_name;
extern const char * util_name;
extern int verbosity;
const char * const simple_extensions[] = { ".gz", ".lz", ".bz2", ".xz", 0 };
enum { bzip2_magic_size = 3 };
enum { gzip_magic_size = 2 };
enum { lzip_magic_size = 4 };
enum { xz_magic_size = 5 };
const uint8_t bzip2_magic[bzip2_magic_size] = { 'B', 'Z', 'h' };
const uint8_t gzip_magic[ gzip_magic_size] = { '\x1F', '\x8B' };
const uint8_t lzip_magic[ lzip_magic_size] = { 'L', 'Z', 'I', 'P' };
const uint8_t xz_magic[ xz_magic_size] = { '\xFD', '7', 'z', 'X', 'Z' };
int readblock( const int fd, uint8_t * const buf, const int size ) throw();
int writeblock( const int fd, const uint8_t * const buf, const int size ) throw();
bool feed_data( const int infd, const int outfd,
const uint8_t * magic_data, const int magic_size );
bool set_data_feeder( int * const infdp, pid_t * const pidp );
void show_help_addr() throw();
void show_version( const char * const Util_name = 0 ) throw();
void show_error( const char * const msg, const int errcode = 0,
const bool help = false ) throw();
void internal_error( const char * const msg );
bool test_format( const int infd, std::string & file_type,
const uint8_t ** magic_data, int * magic_sizep );
int wait_for_child( const pid_t pid, const char * const name );