summaryrefslogtreecommitdiffstats
diff options
context:
space:
mode:
Diffstat
-rw-r--r--ChangeLog38
-rw-r--r--LzmaDec.c4
-rw-r--r--Makefile.in8
-rw-r--r--NEWS17
-rw-r--r--README28
-rw-r--r--carg_parser.c18
-rw-r--r--carg_parser.h11
-rwxr-xr-xconfigure4
-rw-r--r--doc/pdlzip.124
-rw-r--r--lzip.h11
-rw-r--r--main.c101
-rwxr-xr-xtestsuite/check.sh100
-rw-r--r--testsuite/fox_nz.lzbin0 -> 80 bytes
-rw-r--r--testsuite/test.txt6
-rw-r--r--testsuite/test.txt.lzbin7376 -> 7341 bytes
-rw-r--r--testsuite/test.txt.lzmabin7363 -> 7328 bytes
-rw-r--r--testsuite/test_em.txt.lzbin14024 -> 0 bytes
17 files changed, 216 insertions, 154 deletions
diff --git a/ChangeLog b/ChangeLog
index bc4b2e7..abdeed0 100644
--- a/ChangeLog
+++ b/ChangeLog
@@ -1,3 +1,10 @@
+2024-11-08 Antonio Diaz Diaz <antonio@gnu.org>
+
+ * Version 1.14-rc1 released.
+ * main.c (decompress): Return 2 if empty member in multimember file.
+ (Pp_free): New function.
+ * check.sh: Use 'cp' instead of 'cat'.
+
2024-01-21 Antonio Diaz Diaz <antonio@gnu.org>
* Version 1.13 released.
@@ -39,12 +46,12 @@
2018-02-04 Antonio Diaz Diaz <antonio@gnu.org>
* Version 1.9 released.
- * main.c: New option '--loose-trailing'.
- * main.c (decompress): Improve corrupt header detection to HD=3.
+ * New option '--loose-trailing'.
* Replace 'bits/byte' with inverse compression ratio in output.
- * main.c: Show final diagnostic when testing multiple files.
- * main.c: Do not add a second .lz extension to the arg of -o.
- * main.c (lzip_decode): Show stored sizes also in hex.
+ * main.c (decompress): Improve corrupt header detection to HD=3.
+ (main): Show final diagnostic when testing multiple files.
+ (set_c_outname): Do not add a second '.lz' to the arg of '-o'.
+ (lzip_decode): Show stored sizes also in hex.
Show dictionary size at verbosity level 4 (-vvvv).
2017-04-12 Antonio Diaz Diaz <antonio@gnu.org>
@@ -58,10 +65,9 @@
* Version 1.7 released.
* main.c: New option '-a, --trailing-error'.
* main.c (main): Delete '--output' file if infd is a terminal.
- * main.c (main): Don't use stdin more than once.
+ (main): Don't use stdin more than once.
* configure: Avoid warning on some shells when testing for gcc.
- * check.sh: A POSIX shell is required to run the tests.
- * check.sh: Don't check error messages.
+ * check.sh: Require a POSIX shell. Don't check error messages.
2015-05-26 Antonio Diaz Diaz <antonio@gnu.org>
@@ -78,16 +84,16 @@
2013-05-27 Antonio Diaz Diaz <antonio@gnu.org>
* Version 1.4 released.
+ * Decompression time has been reduced by 5%.
* main.c: New options '-f, --force', '-F, --recompress',
'-k, --keep', and '-o, --output'.
- * main.c: Accept more than one file in command line.
- * Decompression time has been reduced by 5%.
- * main.c: '--test' no longer needs '/dev/null'.
- * Fix return value of '-d' and '-t' in case of data error.
- * main.c: Change info shown at verbosity levels 2 and 3.
- * Ignore option '-n, --threads' for compatibility with plzip.
+ Accept more than one file in command line.
+ (main): '--test' no longer needs '/dev/null'.
+ (main): Fix return value of '-d' and '-t' in case of data error.
+ Change info shown at verbosity levels 2 and 3.
+ (main): Ignore option '-n, --threads' for compatibility with plzip.
* configure: Options now accept a separate argument.
- * configure: Rename 'datadir' to 'datarootdir'.
+ Rename 'datadir' to 'datarootdir'.
* Makefile.in: New targets 'install-as-lzip' and 'install-bin'.
2012-01-03 Antonio Diaz Diaz <ant_diaz@teleline.es>
@@ -95,7 +101,7 @@
* Version 1.3 released.
* Small change in '--help' output and man page.
* Change quote characters in messages as advised by GNU Standards.
- * main.c: Set stdin/stdout in binary mode on OS2.
+ * main.c (main): Set stdin/stdout in binary mode on OS2.
2011-01-05 Antonio Diaz Diaz <ant_diaz@teleline.es>
diff --git a/LzmaDec.c b/LzmaDec.c
index 1236bd3..bd2a45a 100644
--- a/LzmaDec.c
+++ b/LzmaDec.c
@@ -716,8 +716,8 @@ static bool LzmaDec_DecodeToDic(CLzmaDec *p, uint32_t dicLimit,
*status = LZMA_STATUS_NEEDS_MORE_INPUT;
return true;
}
- if (p->tempBuf[0] != 0)
- return false;
+ /* check first byte of the LZMA stream */
+ if (p->tempBuf[0] != 0) return false;
LzmaDec_InitRc(p, p->tempBuf);
p->tempBufSize = 0;
diff --git a/Makefile.in b/Makefile.in
index 4b8c791..fc59256 100644
--- a/Makefile.in
+++ b/Makefile.in
@@ -2,8 +2,8 @@
DISTNAME = $(pkgname)-$(pkgversion)
INSTALL = install
INSTALL_PROGRAM = $(INSTALL) -m 755
-INSTALL_DATA = $(INSTALL) -m 644
INSTALL_DIR = $(INSTALL) -d -m 755
+INSTALL_DATA = $(INSTALL) -m 644
SHELL = /bin/sh
CAN_RUN_INSTALLINFO = $(SHELL) -c "install-info --version" > /dev/null 2>&1
@@ -30,7 +30,8 @@ main.o : main.c
# prevent 'make' from trying to remake source files
$(VPATH)/configure $(VPATH)/Makefile.in $(VPATH)/doc/$(pkgname).texi : ;
-%.h %.c : ;
+MAKEFLAGS += -r
+.SUFFIXES :
$(objs) : Makefile
carg_parser.o : carg_parser.h
@@ -125,8 +126,7 @@ dist : doc
$(DISTNAME)/testsuite/fox.lz \
$(DISTNAME)/testsuite/fox_*.lz \
$(DISTNAME)/testsuite/test.txt.lz \
- $(DISTNAME)/testsuite/test.txt.lzma \
- $(DISTNAME)/testsuite/test_em.txt.lz
+ $(DISTNAME)/testsuite/test.txt.lzma
rm -f $(DISTNAME)
lzip -v -9 $(DISTNAME).tar
diff --git a/NEWS b/NEWS
index c719405..e715e5e 100644
--- a/NEWS
+++ b/NEWS
@@ -1,15 +1,4 @@
-Changes in version 1.13:
+Changes in version 1.14:
-File diagnostics have been reformatted as 'PROGRAM: FILE: MESSAGE'.
-
-Diagnostics caused by invalid arguments to command-line options now show the
-argument and the name of the option.
-
-The option '-o, --output' now preserves dates, permissions, and ownership of
-the file when (de)compressing exactly one file.
-
-The variable MAKEINFO has been added to configure and Makefile.in.
-
-It has been documented in INSTALL that when choosing a C standard, the POSIX
-features need to be enabled explicitly:
- ./configure CFLAGS+='--std=c99 -D_XOPEN_SOURCE=500'
+pdlzip now exits with error status 2 if any empty member is found in a
+multimember file.
diff --git a/README b/README
index dba78b8..ed2815c 100644
--- a/README
+++ b/README
@@ -3,19 +3,19 @@ Description
Pdlzip is a permissively licensed implementation of the lzip data
compressor, intended for those who can't distribute (or even use) GPL
licensed Free Software. The name of pdlzip comes from 'public domain lzip'.
-Pdlzip is written in C and is compatible with lzip 1.4 or newer.
+Pdlzip is written in C.
Lzip is a lossless data compressor with a user interface similar to the one
-of gzip or bzip2. Lzip uses a simplified form of the 'Lempel-Ziv-Markov
-chain-Algorithm' (LZMA) stream format to maximize interoperability. The
-maximum dictionary size is 512 MiB so that any lzip file can be decompressed
-on 32-bit machines. Lzip provides accurate and robust 3-factor integrity
-checking. Lzip can compress about as fast as gzip (lzip -0) or compress most
-files more than bzip2 (lzip -9). Decompression speed is intermediate between
-gzip and bzip2. Lzip is better than gzip and bzip2 from a data recovery
-perspective. Lzip has been designed, written, and tested with great care to
-replace gzip and bzip2 as the standard general-purpose compressed format for
-Unix-like systems.
+of gzip or bzip2. Lzip uses a simplified form of LZMA (Lempel-Ziv-Markov
+chain-Algorithm) designed to achieve complete interoperability between
+implementations. The maximum dictionary size is 512 MiB so that any lzip
+file can be decompressed on 32-bit machines. Lzip provides accurate and
+robust 3-factor integrity checking. 'lzip -0' compresses about as fast as
+gzip, while 'lzip -9' compresses most files more than bzip2. Decompression
+speed is intermediate between gzip and bzip2. Lzip provides better data
+recovery capabilities than gzip and bzip2. Lzip has been designed, written,
+and tested with great care to replace gzip and bzip2 as general-purpose
+compressed format for Unix-like systems.
The lzip file format is designed for data sharing and long-term archiving,
taking into account both data integrity and decoder availability:
@@ -50,12 +50,6 @@ without recompressing.
Pdlzip includes public domain compression/decompression code from the LZMA
SDK (Software Development Kit) written by Igor Pavlov.
-I would not write non-copylefted software unless it is too simple to be
-worth copylefting it, but one of the uses of the lzip format is the
-interchange of information, and it is therefore desirable that even the
-users of the most non-free platforms can share lzip files with everybody
-else.
-
Copyright (C) 2010-2024 Antonio Diaz Diaz.
diff --git a/carg_parser.c b/carg_parser.c
index edb4eb9..e16fa73 100644
--- a/carg_parser.c
+++ b/carg_parser.c
@@ -148,21 +148,21 @@ static char parse_long_option( struct Arg_parser * const ap,
add_error( ap, "' requires an argument" );
return 1;
}
- return push_back_record( ap, options[index].code,
- options[index].long_name, &opt[len+3] );
+ return push_back_record( ap, options[index].code, options[index].long_name,
+ &opt[len+3] ); /* argument may be empty */
}
- if( options[index].has_arg == ap_yes )
+ if( options[index].has_arg == ap_yes || options[index].has_arg == ap_yme )
{
- if( !arg || !arg[0] )
+ if( !arg || ( options[index].has_arg == ap_yes && !arg[0] ) )
{
add_error( ap, "option '--" ); add_error( ap, options[index].long_name );
add_error( ap, "' requires an argument" );
return 1;
}
++*argindp;
- return push_back_record( ap, options[index].code,
- options[index].long_name, arg );
+ return push_back_record( ap, options[index].code, options[index].long_name,
+ arg ); /* argument may be empty */
}
return push_back_record( ap, options[index].code,
@@ -204,15 +204,15 @@ static char parse_short_option( struct Arg_parser * const ap,
if( !push_back_record( ap, c, 0, &opt[cind] ) ) return 0;
++*argindp; cind = 0;
}
- else if( options[index].has_arg == ap_yes )
+ else if( options[index].has_arg == ap_yes || options[index].has_arg == ap_yme )
{
- if( !arg || !arg[0] )
+ if( !arg || ( options[index].has_arg == ap_yes && !arg[0] ) )
{
add_error( ap, "option requires an argument -- '" );
add_error( ap, code_str ); add_error( ap, "'" );
return 1;
}
- ++*argindp; cind = 0;
+ ++*argindp; cind = 0; /* argument may be empty */
if( !push_back_record( ap, c, 0, arg ) ) return 0;
}
else if( !push_back_record( ap, c, 0, 0 ) ) return 0;
diff --git a/carg_parser.h b/carg_parser.h
index 69ce271..65a6d7d 100644
--- a/carg_parser.h
+++ b/carg_parser.h
@@ -37,15 +37,20 @@
The argument '--' terminates all options; any following arguments are
treated as non-option arguments, even if they begin with a hyphen.
- The syntax for optional option arguments is '-<short_option><argument>'
- (without whitespace), or '--<long_option>=<argument>'.
+ The syntax of options with an optional argument is
+ '-<short_option><argument>' (without whitespace), or
+ '--<long_option>=<argument>'.
+
+ The syntax of options with an empty argument is '-<short_option> ""',
+ '--<long_option> ""', or '--<long_option>=""'.
*/
#ifdef __cplusplus
extern "C" {
#endif
-enum ap_Has_arg { ap_no, ap_yes, ap_maybe };
+/* ap_yme = yes but maybe empty */
+enum ap_Has_arg { ap_no, ap_yes, ap_maybe, ap_yme };
struct ap_Option
{
diff --git a/configure b/configure
index 2a5e46e..9f6e7da 100755
--- a/configure
+++ b/configure
@@ -6,7 +6,7 @@
# to copy, distribute, and modify it.
pkgname=pdlzip
-pkgversion=1.13
+pkgversion=1.14-rc1
progname=pdlzip
srctrigger=doc/${progname}.1
@@ -109,7 +109,7 @@ while [ $# != 0 ] ; do
exit 1 ;;
esac
- # Check if the option took a separate argument
+ # Check whether the option took a separate argument
if [ "${arg2}" = yes ] ; then
if [ $# != 0 ] ; then args="${args} \"$1\"" ; shift
else echo "configure: Missing argument to '${option}'" 1>&2
diff --git a/doc/pdlzip.1 b/doc/pdlzip.1
index 1a16448..15fb29a 100644
--- a/doc/pdlzip.1
+++ b/doc/pdlzip.1
@@ -1,5 +1,5 @@
.\" DO NOT MODIFY THIS FILE! It was generated by help2man 1.49.2.
-.TH PDLZIP "1" "January 2024" "pdlzip 1.13" "User Commands"
+.TH PDLZIP "1" "November 2024" "pdlzip 1.14-rc1" "User Commands"
.SH NAME
pdlzip \- reduces the size of files
.SH SYNOPSIS
@@ -9,19 +9,19 @@ pdlzip \- reduces the size of files
Pdlzip is a permissively licensed implementation of the lzip data
compressor, intended for those who can't distribute (or even use) GPL
licensed Free Software. The name of pdlzip comes from 'public domain lzip'.
-Pdlzip is written in C and is compatible with lzip 1.4 or newer.
+Pdlzip is written in C.
.PP
Lzip is a lossless data compressor with a user interface similar to the one
-of gzip or bzip2. Lzip uses a simplified form of the 'Lempel\-Ziv\-Markov
-chain\-Algorithm' (LZMA) stream format to maximize interoperability. The
-maximum dictionary size is 512 MiB so that any lzip file can be decompressed
-on 32\-bit machines. Lzip provides accurate and robust 3\-factor integrity
-checking. Lzip can compress about as fast as gzip (lzip \fB\-0\fR) or compress most
-files more than bzip2 (lzip \fB\-9\fR). Decompression speed is intermediate between
-gzip and bzip2. Lzip is better than gzip and bzip2 from a data recovery
-perspective. Lzip has been designed, written, and tested with great care to
-replace gzip and bzip2 as the standard general\-purpose compressed format for
-Unix\-like systems.
+of gzip or bzip2. Lzip uses a simplified form of LZMA (Lempel\-Ziv\-Markov
+chain\-Algorithm) designed to achieve complete interoperability between
+implementations. The maximum dictionary size is 512 MiB so that any lzip
+file can be decompressed on 32\-bit machines. Lzip provides accurate and
+robust 3\-factor integrity checking. 'lzip \fB\-0\fR' compresses about as fast as
+gzip, while 'lzip \fB\-9\fR' compresses most files more than bzip2. Decompression
+speed is intermediate between gzip and bzip2. Lzip provides better data
+recovery capabilities than gzip and bzip2. Lzip has been designed, written,
+and tested with great care to replace gzip and bzip2 as general\-purpose
+compressed format for Unix\-like systems.
.PP
Pdlzip is also able to decompress legacy lzma\-alone (.lzma) files.
Lzma\-alone is a very bad format; it is essentially a raw LZMA stream.
diff --git a/lzip.h b/lzip.h
index a1c78ab..74b8019 100644
--- a/lzip.h
+++ b/lzip.h
@@ -188,9 +188,20 @@ static inline void Lt_set_member_size( Lzip_trailer data, unsigned long long sz
{ int i; for( i = 12; i <= 19; ++i ) { data[i] = (uint8_t)sz; sz >>= 8; } }
+struct Cl_options /* command-line options */
+ {
+ bool ignore_trailing;
+ bool loose_trailing;
+ };
+
+static inline void Cl_options_init( struct Cl_options * cl_opts )
+ { cl_opts->ignore_trailing = true; cl_opts->loose_trailing = false; }
+
+
static inline void set_retval( int * retval, const int new_val )
{ if( *retval < new_val ) *retval = new_val; }
+static const char * const empty_msg = "Empty member not allowed.";
static const char * const trailing_msg = "Trailing data not allowed.";
static const char * const mem_msg = "Not enough memory.";
diff --git a/main.c b/main.c
index 6d0fcc1..722ebe3 100644
--- a/main.c
+++ b/main.c
@@ -28,7 +28,7 @@
#include <errno.h>
#include <fcntl.h>
-#include <limits.h> /* SSIZE_MAX */
+#include <limits.h> /* CHAR_BIT, SSIZE_MAX */
#include <signal.h>
#include <stdbool.h>
#include <stdint.h> /* SIZE_MAX */
@@ -114,18 +114,18 @@ static void show_help( void )
printf( "Pdlzip is a permissively licensed implementation of the lzip data\n"
"compressor, intended for those who can't distribute (or even use) GPL\n"
"licensed Free Software. The name of pdlzip comes from 'public domain lzip'.\n"
- "Pdlzip is written in C and is compatible with lzip 1.4 or newer.\n"
+ "Pdlzip is written in C.\n"
"\nLzip is a lossless data compressor with a user interface similar to the one\n"
- "of gzip or bzip2. Lzip uses a simplified form of the 'Lempel-Ziv-Markov\n"
- "chain-Algorithm' (LZMA) stream format to maximize interoperability. The\n"
- "maximum dictionary size is 512 MiB so that any lzip file can be decompressed\n"
- "on 32-bit machines. Lzip provides accurate and robust 3-factor integrity\n"
- "checking. Lzip can compress about as fast as gzip (lzip -0) or compress most\n"
- "files more than bzip2 (lzip -9). Decompression speed is intermediate between\n"
- "gzip and bzip2. Lzip is better than gzip and bzip2 from a data recovery\n"
- "perspective. Lzip has been designed, written, and tested with great care to\n"
- "replace gzip and bzip2 as the standard general-purpose compressed format for\n"
- "Unix-like systems.\n"
+ "of gzip or bzip2. Lzip uses a simplified form of LZMA (Lempel-Ziv-Markov\n"
+ "chain-Algorithm) designed to achieve complete interoperability between\n"
+ "implementations. The maximum dictionary size is 512 MiB so that any lzip\n"
+ "file can be decompressed on 32-bit machines. Lzip provides accurate and\n"
+ "robust 3-factor integrity checking. 'lzip -0' compresses about as fast as\n"
+ "gzip, while 'lzip -9' compresses most files more than bzip2. Decompression\n"
+ "speed is intermediate between gzip and bzip2. Lzip provides better data\n"
+ "recovery capabilities than gzip and bzip2. Lzip has been designed, written,\n"
+ "and tested with great care to replace gzip and bzip2 as general-purpose\n"
+ "compressed format for Unix-like systems.\n"
"\nPdlzip is also able to decompress legacy lzma-alone (.lzma) files.\n"
"Lzma-alone is a very bad format; it is essentially a raw LZMA stream.\n"
"If you keep any lzma-alone files, it is advisable to recompress them to\n"
@@ -226,6 +226,9 @@ static void Pp_init( struct Pretty_print * const pp,
if( pp->longest_name == 0 ) pp->longest_name = stdin_name_len;
}
+void Pp_free( struct Pretty_print * const pp )
+ { if( pp->padded_name ) { free( pp->padded_name ); pp->padded_name = 0; } }
+
static void Pp_set_name( struct Pretty_print * const pp,
const char * const filename )
{
@@ -268,7 +271,7 @@ static void show_header( const unsigned dictionary_size )
const char * p = "";
const char * np = " ";
unsigned num = dictionary_size;
- bool exact = ( num % factor == 0 );
+ bool exact = num % factor == 0;
int i; for( i = 0; i < n && ( num > 9999 || ( exact && num >= factor ) ); ++i )
{ num /= factor; if( num % factor != 0 ) exact = false;
@@ -277,7 +280,7 @@ static void show_header( const unsigned dictionary_size )
}
-/* separate numbers of 5 or more digits in groups of 3 digits using '_' */
+/* separate numbers of 6 or more digits in groups of 3 digits using '_' */
static const char * format_num3( unsigned long long num )
{
enum { buffers = 8, bufsize = 4 * sizeof num, n = 10 };
@@ -289,7 +292,7 @@ static const char * format_num3( unsigned long long num )
char * const buf = buffer[current++]; current %= buffers;
char * p = buf + bufsize - 1; /* fill the buffer backwards */
*p = 0; /* terminator */
- if( num > 1024 )
+ if( num > 9999 )
{
char prefix = 0; /* try binary first, then si */
for( i = 0; i < n && num != 0 && num % 1024 == 0; ++i )
@@ -300,7 +303,7 @@ static const char * format_num3( unsigned long long num )
{ num /= 1000; prefix = si_prefix[i]; }
if( prefix ) *(--p) = prefix;
}
- const bool split = num >= 10000;
+ const bool split = num >= 100000;
for( i = 0; ; )
{
@@ -335,7 +338,7 @@ static unsigned long getnum( const char * const arg,
if( !errno && tail[0] )
{
- const unsigned factor = ( tail[1] == 'i' ) ? 1024 : 1000;
+ const unsigned factor = (tail[1] == 'i') ? 1024 : 1000;
int exponent = 0; /* 0 = bad multiplier */
int i;
switch( tail[0] )
@@ -458,7 +461,7 @@ static int open_instream( const char * const name, struct stat * const in_statsp
if( program_mode == m_compress && !recompress && eindex >= 0 )
{
if( verbosity >= 0 )
- fprintf( stderr, "%s: %s: Input file already has '%s' suffix.\n",
+ fprintf( stderr, "%s: %s: Input file already has '%s' suffix, ignored.\n",
program_name, name, known_extensions[eindex].from );
return -1;
}
@@ -469,9 +472,9 @@ static int open_instream( const char * const name, struct stat * const in_statsp
{
const int i = fstat( infd, in_statsp );
const mode_t mode = in_statsp->st_mode;
- const bool can_read = ( i == 0 &&
- ( S_ISBLK( mode ) || S_ISCHR( mode ) ||
- S_ISFIFO( mode ) || S_ISSOCK( mode ) ) );
+ const bool can_read = i == 0 &&
+ ( S_ISBLK( mode ) || S_ISCHR( mode ) ||
+ S_ISFIFO( mode ) || S_ISSOCK( mode ) );
if( i != 0 || ( !S_ISREG( mode ) && ( !can_read || one_to_one ) ) )
{
if( verbosity >= 0 )
@@ -616,7 +619,7 @@ static int compress( const int infd, const struct Lzma_options * const
}
if( writeblock( outfd, header, Lh_size ) != Lh_size )
- { show_error( "Can't write output file", errno, false ); retval = 1; }
+ { show_error( "Write error", errno, false ); retval = 1; }
else
if( LzmaEnc_Encode( encoder ) != 0 )
{ Pp_show_msg( pp, "Encoder error." ); retval = 1; }
@@ -684,7 +687,7 @@ static int lzma_decode( uint64_t unpackSize, CLzmaDec *decoder, const int infd,
unsigned long long member_size = lzma_header_size, data_size = 0;
uint8_t outBuf[OUT_BUF_SIZE];
int outPos = 0;
- const bool thereIsSize = (unpackSize != (uint64_t)-1);
+ const bool thereIsSize = unpackSize != (uint64_t)-1;
for (;;)
{
@@ -711,7 +714,7 @@ static int lzma_decode( uint64_t unpackSize, CLzmaDec *decoder, const int infd,
unpackSize -= outProcessed;
if( outfd >= 0 && writeblock( outfd, outBuf, outPos ) != outPos )
- { show_error( "Can't write output file", errno, false ); return 1; }
+ { show_error( "Write error", errno, false ); return 1; }
data_size += outPos;
outPos = 0;
@@ -734,7 +737,7 @@ static int lzma_decode( uint64_t unpackSize, CLzmaDec *decoder, const int infd,
static int lzip_decode( CLzmaDec *decoder, const int infd,
struct Pretty_print * const pp, uint8_t inBuf[],
int * const inPos, int * const inSize,
- const unsigned dictionary_size )
+ const unsigned dictionary_size, bool * const data0p )
{
unsigned long long member_size = Lh_size, data_size = 0;
uint8_t outBuf[OUT_BUF_SIZE];
@@ -762,7 +765,7 @@ static int lzip_decode( CLzmaDec *decoder, const int infd,
outPos += outProcessed;
if( outfd >= 0 && writeblock( outfd, outBuf, outPos ) != outPos )
- { show_error( "Can't write output file", errno, false ); return 1; }
+ { show_error( "Write error", errno, false ); return 1; }
CRC32_update_buf( &crc, outBuf, outPos );
data_size += outPos;
@@ -830,15 +833,16 @@ static int lzip_decode( CLzmaDec *decoder, const int infd,
}
if( error ) return 2;
show_results( data_size, member_size, td_crc, dictionary_size, true );
+ *data0p = data_size == 0;
return 0;
}
}
}
-static int decompress( const int infd, struct Pretty_print * const pp,
- const bool ignore_trailing, const bool loose_trailing,
- const bool testing )
+static int decompress( const int infd, const struct Cl_options * const cl_opts,
+ struct Pretty_print * const pp,
+ const bool from_stdin, const bool testing )
{
uint64_t unpackSize = 0;
CLzmaDec decoder;
@@ -848,6 +852,7 @@ static int decompress( const int infd, struct Pretty_print * const pp,
bool lzip_mode = true;
bool first_member;
uint8_t raw_props[lzma_header_size];
+ bool empty = false, multi = false;
for( first_member = true; ; first_member = false )
{
@@ -867,7 +872,7 @@ static int decompress( const int infd, struct Pretty_print * const pp,
else if( Lh_check_prefix( header, size ) )
{ Pp_show_msg( pp, "Truncated header in multimember file." );
retval = 2; }
- else if( size > 0 && !ignore_trailing )
+ else if( size > 0 && !cl_opts->ignore_trailing )
{ Pp_show_msg( pp, trailing_msg ); retval = 2; }
break;
}
@@ -875,10 +880,10 @@ static int decompress( const int infd, struct Pretty_print * const pp,
{
if( !first_member )
{
- if( !loose_trailing && Lh_check_corrupt( header ) )
+ if( !cl_opts->loose_trailing && Lh_check_corrupt( header ) )
{ Pp_show_msg( pp, "Corrupt header in multimember file." );
retval = 2; }
- else if( !ignore_trailing )
+ else if( !cl_opts->ignore_trailing )
{ Pp_show_msg( pp, trailing_msg ); retval = 2; }
break;
}
@@ -929,19 +934,23 @@ static int decompress( const int infd, struct Pretty_print * const pp,
if( !LzmaDec_Init( &decoder, raw_props ) )
{ Pp_show_msg( pp, mem_msg ); return 1; }
+ bool data0 = false;
if( lzip_mode )
retval = lzip_decode( &decoder, infd, pp, inBuf, &inPos, &inSize,
- dictionary_size );
+ dictionary_size, &data0 );
else
retval = lzma_decode( unpackSize, &decoder, infd, inBuf, &inPos,
&inSize, dictionary_size, testing );
LzmaDec_Free(&decoder);
if( retval != 0 || !lzip_mode ) break;
+ if( !from_stdin ) { multi = !first_member; if( data0 ) empty = true; }
if( verbosity >= 2 )
{ fputs( testing ? "ok\n" : "done\n", stderr ); Pp_reset( pp ); }
}
if( lzip_mode && verbosity == 1 && retval == 0 )
fputs( testing ? "ok\n" : "done\n", stderr );
+ if( empty && multi && retval == 0 )
+ { show_file_error( pp->name, empty_msg, 0 ); retval = 2; }
return retval;
}
@@ -1038,10 +1047,10 @@ int main( const int argc, const char * const argv[] )
const char * default_output_filename = "";
enum Mode program_mode = m_compress;
int i;
+ struct Cl_options cl_opts; /* command-line options */
+ Cl_options_init( &cl_opts );
bool force = false;
- bool ignore_trailing = true;
bool keep_input_files = false;
- bool loose_trailing = false;
bool recompress = false;
bool to_stdout = false;
if( argc > 0 ) invocation_name = argv[0];
@@ -1077,7 +1086,7 @@ int main( const int argc, const char * const argv[] )
{ 'v', "verbose", ap_no },
{ 'V', "version", ap_no },
{ opt_lt, "loose-trailing", ap_no },
- { 0, 0, ap_no } };
+ { 0, 0, ap_no } };
CRC32_init();
@@ -1097,11 +1106,11 @@ int main( const int argc, const char * const argv[] )
const char * const arg = ap_argument( &parser, argind );
switch( code )
{
- case '0': case '1': case '2': case '3': case '4':
- case '5': case '6': case '7': case '8': case '9':
+ case '0': case '1': case '2': case '3': case '4': case '5':
+ case '6': case '7': case '8': case '9':
encoder_options = option_mapping[code-'0']; break;
- case 'a': ignore_trailing = false; break;
- case 'b': break;
+ case 'a': cl_opts.ignore_trailing = false; break;
+ case 'b': break; /* ignored */
case 'c': to_stdout = true; break;
case 'd': set_mode( &program_mode, m_decompress ); break;
case 'f': force = true; break;
@@ -1110,17 +1119,17 @@ int main( const int argc, const char * const argv[] )
case 'k': keep_input_files = true; break;
case 'm': encoder_options.match_len_limit =
getnum( arg, pn, min_match_len_limit, max_match_len ); break;
- case 'n': break;
+ case 'n': break; /* ignored */
case 'o': if( strcmp( arg, "-" ) == 0 ) to_stdout = true;
else { default_output_filename = arg; } break;
case 'q': verbosity = -1; break;
case 's': encoder_options.dictionary_size = get_dict_size( arg, pn );
break;
- case 'S': break;
+ case 'S': break; /* ignored */
case 't': set_mode( &program_mode, m_test ); break;
case 'v': if( verbosity < 4 ) ++verbosity; break;
case 'V': show_version(); return 0;
- case opt_lt: loose_trailing = true; break;
+ case opt_lt: cl_opts.loose_trailing = true; break;
default: internal_error( "uncaught option." );
}
} /* end process options */
@@ -1168,9 +1177,10 @@ int main( const int argc, const char * const argv[] )
{
const char * input_filename = "";
int infd;
+ const bool from_stdin = strcmp( filenames[i], "-" ) == 0;
Pp_set_name( &pp, filenames[i] );
- if( strcmp( filenames[i], "-" ) == 0 )
+ if( from_stdin )
{
if( stdin_used ) continue; else stdin_used = true;
infd = STDIN_FILENO;
@@ -1215,7 +1225,7 @@ int main( const int argc, const char * const argv[] )
if( program_mode == m_compress )
tmp = compress( infd, &encoder_options, &pp );
else
- tmp = decompress( infd, &pp, ignore_trailing, loose_trailing,
+ tmp = decompress( infd, &cl_opts, &pp, from_stdin,
program_mode == m_test );
if( close( infd ) != 0 )
{ show_file_error( pp.name, "Error closing input file", errno );
@@ -1243,6 +1253,7 @@ int main( const int argc, const char * const argv[] )
program_name, failed_tests,
( failed_tests == 1 ) ? "file" : "files" );
free( output_filename );
+ Pp_free( &pp );
free( filenames );
ap_free( &parser );
return retval;
diff --git a/testsuite/check.sh b/testsuite/check.sh
index 6b7522e..0651ab3 100755
--- a/testsuite/check.sh
+++ b/testsuite/check.sh
@@ -28,10 +28,10 @@ if [ -d tmp ] ; then rm -rf tmp ; fi
mkdir tmp
cd "${objdir}"/tmp || framework_failure
-cat "${testdir}"/test.txt > in || framework_failure
+cp "${testdir}"/test.txt in || framework_failure
in_lz="${testdir}"/test.txt.lz
-in_em="${testdir}"/test_em.txt.lz
fox_lz="${testdir}"/fox.lz
+fnz_lz="${testdir}"/fox_nz.lz
fail=0
test_failed() { fail=1 ; printf " $1" ; [ -z "$2" ] || printf "($2)" ; }
@@ -95,7 +95,7 @@ printf "LZIP\001+.............................." | "${LZIP}" -t 2> /dev/null
printf "\ntesting decompression..."
-for i in "${in_lz}" "${in_em}" "${testdir}"/test.txt.lzma ; do
+for i in "${in_lz}" "${testdir}"/test.txt.lzma ; do
"${LZIP}" -t "$i" || test_failed $LINENO "$i"
"${LZIP}" -d "$i" -o out || test_failed $LINENO "$i"
cmp in out || test_failed $LINENO "$i"
@@ -108,16 +108,13 @@ for i in "${in_lz}" "${in_em}" "${testdir}"/test.txt.lzma ; do
rm -f out || framework_failure
done
-lines=`"${LZIP}" -tvv "${in_em}" 2>&1 | wc -l` || test_failed $LINENO
-[ "${lines}" -eq 8 ] || test_failed $LINENO "${lines}"
-
-cat "${in_lz}" > out.lz || framework_failure
+cp "${in_lz}" out.lz || framework_failure
"${LZIP}" -dk out.lz || test_failed $LINENO
cmp in out || test_failed $LINENO
rm -f out || framework_failure
"${LZIP}" -cd "${fox_lz}" > fox || test_failed $LINENO
-cat fox > copy || framework_failure
-cat "${in_lz}" > copy.lz || framework_failure
+cp fox copy || framework_failure
+cp "${in_lz}" copy.lz || framework_failure
"${LZIP}" -d copy.lz out.lz 2> /dev/null # skip copy, decompress out
[ $? = 1 ] || test_failed $LINENO
[ ! -e out.lz ] || test_failed $LINENO
@@ -139,7 +136,7 @@ rm -f ./- || framework_failure
cmp in ./- || test_failed $LINENO
rm -f ./- || framework_failure
-cat "${in_lz}" > anyothername || framework_failure
+cp "${in_lz}" anyothername || framework_failure
"${LZIP}" -dv - anyothername - < "${in_lz}" > out 2> /dev/null ||
test_failed $LINENO
cmp in out || test_failed $LINENO
@@ -157,7 +154,7 @@ cat out in | cmp in - || test_failed $LINENO # out must be empty
[ $? = 1 ] || test_failed $LINENO
cmp in out || test_failed $LINENO
rm -f out || framework_failure
-cat "${in_lz}" > out.lz || framework_failure
+cp "${in_lz}" out.lz || framework_failure
for i in 1 2 3 4 5 6 7 ; do
printf "g" >> out.lz || framework_failure
"${LZIP}" -atvvvv out.lz "${in_lz}" 2> /dev/null
@@ -186,6 +183,9 @@ cmp in2 out2 || test_failed $LINENO
rm -f out2 || framework_failure
cat "${in_lz}" "${in_lz}" > out2.lz || framework_failure
+lines=`"${LZIP}" -tvv out2.lz 2>&1 | wc -l` || test_failed $LINENO
+[ "${lines}" -eq 2 ] || test_failed $LINENO "${lines}"
+
printf "\ngarbage" >> out2.lz || framework_failure
"${LZIP}" -tvvvv out2.lz 2> /dev/null || test_failed $LINENO
"${LZIP}" -atq out2.lz
@@ -203,6 +203,20 @@ printf "to be overwritten" > out2 || framework_failure
cmp in2 out2 || test_failed $LINENO
rm -f out2 || framework_failure
+touch empty em || framework_failure
+"${LZIP}" -0 em || test_failed $LINENO
+"${LZIP}" -dk em.lz || test_failed $LINENO
+cmp empty em || test_failed $LINENO
+cat em.lz em.lz | "${LZIP}" -t || test_failed $LINENO
+cat em.lz em.lz | "${LZIP}" -d > em || test_failed $LINENO
+cmp empty em || test_failed $LINENO
+cat em.lz "${in_lz}" | "${LZIP}" -t || test_failed $LINENO
+cat em.lz "${in_lz}" | "${LZIP}" -d > out || test_failed $LINENO
+cmp in out || test_failed $LINENO
+cat "${in_lz}" em.lz | "${LZIP}" -t || test_failed $LINENO
+cat "${in_lz}" em.lz | "${LZIP}" -d > out || test_failed $LINENO
+cmp in out || test_failed $LINENO
+
printf "\ntesting compression..."
"${LZIP}" -c -0 in in in -o out3.lz > copy2.lz || test_failed $LINENO
@@ -211,7 +225,7 @@ printf "\ntesting compression..."
"${LZIP}" -d copy2.lz -o out2 || test_failed $LINENO
[ -e copy2.lz ] || test_failed $LINENO
cmp in2 out2 || test_failed $LINENO
-rm -f in2 out2 copy2.lz || framework_failure
+rm -f copy2.lz || framework_failure
"${LZIP}" -cf "${in_lz}" > lzlz 2> /dev/null # /dev/null is a tty on OS/2
[ $? = 1 ] || test_failed $LINENO
@@ -259,11 +273,38 @@ rm -f copy out.lz || framework_failure
printf "\ntesting bad input..."
+cat em.lz em.lz > ee.lz || framework_failure
+"${LZIP}" -t < ee.lz || test_failed $LINENO
+"${LZIP}" -d < ee.lz > em || test_failed $LINENO
+cmp empty em || test_failed $LINENO
+"${LZIP}" -tq ee.lz
+[ $? = 2 ] || test_failed $LINENO
+"${LZIP}" -dq ee.lz
+[ $? = 2 ] || test_failed $LINENO
+[ ! -e ee ] || test_failed $LINENO
+"${LZIP}" -cdq ee.lz > em
+[ $? = 2 ] || test_failed $LINENO
+cmp empty em || test_failed $LINENO
+rm -f empty em || framework_failure
+cat "${in_lz}" em.lz "${in_lz}" > inein.lz || framework_failure
+"${LZIP}" -t < inein.lz || test_failed $LINENO
+"${LZIP}" -d < inein.lz > out2 || test_failed $LINENO
+cmp in2 out2 || test_failed $LINENO
+"${LZIP}" -tq inein.lz
+[ $? = 2 ] || test_failed $LINENO
+"${LZIP}" -dq inein.lz
+[ $? = 2 ] || test_failed $LINENO
+[ ! -e inein ] || test_failed $LINENO
+"${LZIP}" -cdq inein.lz > out2
+[ $? = 2 ] || test_failed $LINENO
+cmp in2 out2 || test_failed $LINENO
+rm -f in2 out2 inein.lz em.lz || framework_failure
+
headers='LZIp LZiP LZip LzIP LzIp LziP lZIP lZIp lZiP lzIP'
-body='\001\014\000\203\377\373\377\377\300\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000$\000\000\000\000\000\000\000'
-cat "${in_lz}" > int.lz || framework_failure
+body='\001\014\000\000\101\376\367\377\377\340\000\200\000\215\357\002\322\001\000\000\000\000\000\000\000\045\000\000\000\000\000\000\000'
+cp "${in_lz}" int.lz || framework_failure
printf "LZIP${body}" >> int.lz || framework_failure
-if "${LZIP}" -tq int.lz ; then
+if "${LZIP}" -t int.lz ; then
for header in ${headers} ; do
printf "${header}${body}" > int.lz || framework_failure
"${LZIP}" -tq int.lz # first member
@@ -278,7 +319,7 @@ if "${LZIP}" -tq int.lz ; then
[ $? = 2 ] || test_failed $LINENO ${header}
"${LZIP}" -cdq --loose-trailing int.lz > /dev/null
[ $? = 2 ] || test_failed $LINENO ${header}
- cat "${in_lz}" > int.lz || framework_failure
+ cp "${in_lz}" int.lz || framework_failure
printf "${header}${body}" >> int.lz || framework_failure
"${LZIP}" -tq int.lz # trailing data
[ $? = 2 ] || test_failed $LINENO ${header}
@@ -300,10 +341,13 @@ if "${LZIP}" -tq int.lz ; then
[ $? = 2 ] || test_failed $LINENO ${header}
done
else
- printf "\nwarning: skipping header test: 'printf' does not work on your system."
+ printf "warning: skipping header test: 'printf' does not work on your system."
fi
rm -f int.lz || framework_failure
+"${LZIP}" -tq "${fnz_lz}"
+[ $? = 2 ] || test_failed $LINENO
+
for i in fox_v2.lz fox_s11.lz fox_de20.lz \
fox_bcrc.lz fox_crc0.lz fox_das46.lz fox_mes81.lz ; do
"${LZIP}" -tq "${testdir}"/$i
@@ -315,13 +359,13 @@ for i in fox_bcrc.lz fox_crc0.lz fox_das46.lz fox_mes81.lz ; do
[ $? = 2 ] || test_failed $LINENO $i
cmp fox out || test_failed $LINENO $i
done
-rm -f fox out || framework_failure
+rm -f fox || framework_failure
cat "${in_lz}" "${in_lz}" > in2.lz || framework_failure
cat "${in_lz}" "${in_lz}" "${in_lz}" > in3.lz || framework_failure
-if dd if=in3.lz of=trunc.lz bs=14752 count=1 2> /dev/null &&
- [ -e trunc.lz ] && cmp in2.lz trunc.lz > /dev/null 2>&1 ; then
- for i in 6 20 14734 14753 14754 14755 14756 14757 14758 ; do
+if dd if=in3.lz of=trunc.lz bs=14682 count=1 2> /dev/null &&
+ [ -e trunc.lz ] && cmp in2.lz trunc.lz ; then
+ for i in 6 20 14664 14683 14684 14685 14686 14687 14688 ; do
dd if=in3.lz of=trunc.lz bs=$i count=1 2> /dev/null
"${LZIP}" -tq trunc.lz
[ $? = 2 ] || test_failed $LINENO $i
@@ -333,28 +377,32 @@ if dd if=in3.lz of=trunc.lz bs=14752 count=1 2> /dev/null &&
[ $? = 2 ] || test_failed $LINENO $i
done
else
- printf "\nwarning: skipping truncation test: 'dd' does not work on your system."
+ printf "warning: skipping truncation test: 'dd' does not work on your system."
fi
rm -f in2.lz in3.lz trunc.lz || framework_failure
-cat "${in_lz}" > ingin.lz || framework_failure
+cp "${in_lz}" ingin.lz || framework_failure
printf "g" >> ingin.lz || framework_failure
cat "${in_lz}" >> ingin.lz || framework_failure
"${LZIP}" -atq ingin.lz
[ $? = 2 ] || test_failed $LINENO
"${LZIP}" -atq < ingin.lz
[ $? = 2 ] || test_failed $LINENO
-"${LZIP}" -acdq ingin.lz > /dev/null
+"${LZIP}" -acdq ingin.lz > out
[ $? = 2 ] || test_failed $LINENO
-"${LZIP}" -adq < ingin.lz > /dev/null
+cmp in out || test_failed $LINENO
+"${LZIP}" -adq < ingin.lz > out
[ $? = 2 ] || test_failed $LINENO
+cmp in out || test_failed $LINENO
"${LZIP}" -t ingin.lz || test_failed $LINENO
"${LZIP}" -t < ingin.lz || test_failed $LINENO
+"${LZIP}" -dk ingin.lz || test_failed $LINENO
+cmp in ingin || test_failed $LINENO
"${LZIP}" -cd ingin.lz > out || test_failed $LINENO
cmp in out || test_failed $LINENO
"${LZIP}" -d < ingin.lz > out || test_failed $LINENO
cmp in out || test_failed $LINENO
-rm -f out ingin.lz || framework_failure
+rm -f out ingin ingin.lz || framework_failure
echo
if [ ${fail} = 0 ] ; then
diff --git a/testsuite/fox_nz.lz b/testsuite/fox_nz.lz
new file mode 100644
index 0000000..44a4b58
--- /dev/null
+++ b/testsuite/fox_nz.lz
Binary files differ
diff --git a/testsuite/test.txt b/testsuite/test.txt
index 9196a3a..423f0c0 100644
--- a/testsuite/test.txt
+++ b/testsuite/test.txt
@@ -1,8 +1,7 @@
GNU GENERAL PUBLIC LICENSE
Version 2, June 1991
- Copyright (C) 1989, 1991 Free Software Foundation, Inc.,
- 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
+ Copyright (C) 1989, 1991 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.
@@ -339,8 +338,7 @@ Public License instead of this License.
GNU GENERAL PUBLIC LICENSE
Version 2, June 1991
- Copyright (C) 1989, 1991 Free Software Foundation, Inc.,
- 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
+ Copyright (C) 1989, 1991 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.
diff --git a/testsuite/test.txt.lz b/testsuite/test.txt.lz
index 22cea6e..5dc169f 100644
--- a/testsuite/test.txt.lz
+++ b/testsuite/test.txt.lz
Binary files differ
diff --git a/testsuite/test.txt.lzma b/testsuite/test.txt.lzma
index 53e54ea..091c023 100644
--- a/testsuite/test.txt.lzma
+++ b/testsuite/test.txt.lzma
Binary files differ
diff --git a/testsuite/test_em.txt.lz b/testsuite/test_em.txt.lz
deleted file mode 100644
index 7e96250..0000000
--- a/testsuite/test_em.txt.lz
+++ /dev/null
Binary files differ
generated by cgit v1.2.3 (git 2.39.1) at 2024-11-24 11:47:24 +0000