diff options
| author | Daniel Baumann <daniel.baumann@progress-linux.org> | 2024-01-23 05:54:13 +0000 |
|---|---|---|
| committer | Daniel Baumann <daniel.baumann@progress-linux.org> | 2024-01-23 05:54:13 +0000 |
| commit | e50d8921980602c5569b31dd9d12a24b43a196e8 (patch) | |
| tree | d7240fd2cd209b129f72dac13832b6cfce13dc76 | |
| parent | Releasing debian version 1.12-3. (diff) | |
| download | zutils-e50d8921980602c5569b31dd9d12a24b43a196e8.tar.xz zutils-e50d8921980602c5569b31dd9d12a24b43a196e8.zip | |
Merging upstream version 1.13~rc1.
Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>
| -rw-r--r-- | ChangeLog | 15 | ||||
| -rw-r--r-- | INSTALL | 7 | ||||
| -rw-r--r-- | Makefile.in | 7 | ||||
| -rw-r--r-- | NEWS | 70 | ||||
| -rw-r--r-- | README | 9 | ||||
| -rw-r--r-- | arg_parser.cc | 2 | ||||
| -rw-r--r-- | arg_parser.h | 2 | ||||
| -rwxr-xr-x | configure | 10 | ||||
| -rw-r--r-- | doc/zcat.1 | 8 | ||||
| -rw-r--r-- | doc/zcmp.1 | 17 | ||||
| -rw-r--r-- | doc/zdiff.1 | 19 | ||||
| -rw-r--r-- | doc/zgrep.1 | 8 | ||||
| -rw-r--r-- | doc/ztest.1 | 28 | ||||
| -rw-r--r-- | doc/zupdate.1 | 20 | ||||
| -rw-r--r-- | doc/zutils.info | 201 | ||||
| -rw-r--r-- | doc/zutils.texi | 204 | ||||
| -rw-r--r-- | rc.cc | 4 | ||||
| -rw-r--r-- | rc.h | 4 | ||||
| -rw-r--r-- | recursive.cc | 2 | ||||
| -rwxr-xr-x | testsuite/check.sh | 110 | ||||
| -rw-r--r-- | zcat.cc | 6 | ||||
| -rw-r--r-- | zcmp.cc | 53 | ||||
| -rw-r--r-- | zcmpdiff.cc | 33 | ||||
| -rw-r--r-- | zdiff.cc | 15 | ||||
| -rw-r--r-- | zgrep.cc | 11 | ||||
| -rw-r--r-- | ztest.cc | 26 | ||||
| -rw-r--r-- | zupdate.cc | 58 | ||||
| -rw-r--r-- | zutils.cc | 38 | ||||
| -rw-r--r-- | zutils.conf | 2 |
29 files changed, 472 insertions, 517 deletions
@@ -1,3 +1,14 @@ +2023-12-31 Antonio Diaz Diaz <antonio@gnu.org> + + * Version 1.13-rc1 released. + * zutils.cc (test_format): Fix detection of bzip2 with no blocks. + * rc.h (format_order): Put fmt_gz before fmt_bz2. + * zcmpdiff.cc (open_other_instream): Try also other compressed formats. + * zcmp.cc (cmp): Report EOF on empty file like GNU cmp. + * zupdate.cc: Reformat file diagnostics as 'PROGRAM: FILE: MESSAGE'. + * Replace 'verify' with 'check'. + * configure, Makefile.in: New variable 'MAKEINFO'. + 2023-01-07 Antonio Diaz Diaz <antonio@gnu.org> * Version 1.12 released. @@ -113,7 +124,7 @@ * Version 1.3 released. * check.sh: Fix two values of expected exit status. - * zutils.texi: Document that '--format' does not verify format. + * zutils.texi: Document that '--format' does not check format. * Add two missing #includes. * Change license to GPL version 2 or later. @@ -175,7 +186,7 @@ * ztest.cc: New file implementing ztest functionality in C++. * Makefile.in: Add quotes to directory names. * check.sh: Use 'test.txt' instead of 'COPYING' for testing. - * Remove environment safeguards from configure as requested by + * configure: Remove environment safeguards as requested by Richard Stallman. Now environment variables affect configure. 2009-10-21 Antonio Diaz Diaz <ant_diaz@teleline.es> @@ -20,8 +20,8 @@ gzip scripts, the recommended method is to configure gzip as follows: ./configure --program-transform-name='s/^z/gz/' This renames, at installation time, the gzip scripts and man pages to -'gzcat', 'gzcat.1', etc, avoiding the name clashing with the programs -and man pages from zutils. +'gzcat', 'gzcat.1', etc, avoiding the name clashing with the programs and +man pages from zutils. Procedure @@ -48,7 +48,8 @@ extracted from the archive. 4. Optionally, type 'make check' to run the tests that come with zutils. 5. Type 'make install' to install the programs and any data files and - documentation. + documentation. You need root privileges to install into a prefix owned + by root. Or type 'make install-compress', which additionally compresses the info manual and the man pages after installation. diff --git a/Makefile.in b/Makefile.in index fbd7102..b8984fd 100644 --- a/Makefile.in +++ b/Makefile.in @@ -66,6 +66,10 @@ zgrep.o : zgrep.cc %.o : %.cc $(CXX) $(CPPFLAGS) $(CXXFLAGS) -c -o $@ $< +# prevent 'make' from trying to remake source files +$(VPATH)/configure $(VPATH)/Makefile.in $(VPATH)/doc/$(pkgname).texi : ; +%.h %.cc : ; + $(objs) : Makefile $(scripts) : Makefile arg_parser.o : arg_parser.h @@ -78,7 +82,6 @@ ztest.o : arg_parser.h rc.h zutils.h recursive.cc zupdate.o : arg_parser.h rc.h recursive.cc zutils.o : rc.h zutils.h - doc : info man info : $(VPATH)/doc/$(pkgname).info @@ -106,7 +109,7 @@ $(VPATH)/doc/zgrep.1 : zgrep -o $@ --info-page=$(pkgname) ./zgrep $(VPATH)/doc/ztest.1 : ztest - help2man -n 'verify the integrity of compressed files' \ + help2man -n 'check the integrity of compressed files' \ -o $@ --info-page=$(pkgname) ./ztest $(VPATH)/doc/zupdate.1 : zupdate @@ -1,64 +1,18 @@ -Changes in version 1.12: +Changes in version 1.13: -The zutils configuration file 'zutilsrc' has been renamed to 'zutils.conf'. -Zutils now looks for the configuration file in $XDG_CONFIG_HOME/zutils.conf -instead of $HOME/.zutilsrc. (XDG_CONFIG_HOME defaults to $HOME/.config). -(Suggested by Adam Tuja). +The detection of bzip2 files with no compressed blocks has been fixed. +(Error introduced in version 1.9). -In zcat, zcmp, zdiff, and zgrep, the option '-O, --force-format' now can -force also "uncompressed" format. +When zcat, zcmp, zdiff, or zgrep need to try compressed file names, gzip +(.gz) is now tried before bzip2 (.bz2). -zcmp now accepts the option '-H, --hexadecimal' to print byte values in -hexadecimal instead of octal. +When only one compressed file is passed to zcmp or zdiff, they now try to +compare it with a compressed file of any of the remaining formats if the +corresponding uncompressed file does not exist. -In zcmp: - The long name of option '-s' has been changed to '--script' following a - similar change made to GNU ed. +zcmp now reports EOF on empty file like GNU cmp: +"zcmp: EOF on FILE which is empty". - The short name '-q' has been assigned to options '--quiet' and '--silent'. +File diagnostics in zupdate have been reformatted as 'PROGRAM: FILE: MESSAGE'. - Option '-q' now only suppresses diagnostic messages written to stderr. - - Option '-s' now only suppresses messages about file differences written to - stdout or stderr. - - Option '-l, --list' is now different from option '-v, --verbose', which - now undoes the effect of '--quiet'. - -zcmp now prints byte and line in EOF message like GNU cmp: -"zcmp: EOF on FILE after byte B, in line L". - -zgrep now also accepts the following options: '-G, --basic-regexp', -'--label=<label>', '--line-buffered', '-P, --perl-regexp', '--silent', -'-T, --initial-tab', '-U, --binary', and '-Z, --null'. -(Reported by Chris Jamboretz and Leah Neukirchen). - -ztest now exits with status 2 if an uncompressed file has a compressed file -name extension, or if a compressed file has a wrong compressed extension. - -zupdate now accepts option '-d, --destdir' to write recompressed files to -another directory. This allows, for example, recompressing files from a -read-only file system to another place without needing to copy or link them -to the destination directory first. - -zupdate now accepts option '-e, --expand-extensions', which makes it expand -combined file name extensions; tgz --> tar.lz. - -zupdate now also accepts option '-i, --ignore-errors', which makes it ignore -non-fatal errors. (Suggested by Antoni Sawicki). - -All utilities now support compress'd (.Z) files through gzip. For this to -work, the gzip program used (for example GNU gzip) must be able to -decompress .Z files. - -At verbosity level 1 (2 for zdiff and zgrep) or higher, '-V, --version' now -prints the versions of the compressors used (limited by option '-M, --format'). -(The compressors used must support option '-V' for this to work). - -Diagnostics caused by invalid arguments to command line options now show the -argument and the name of the option. - -It has been documented in the manual that the data format is detected by its -magic bytes, not by the file name extension. - -The testsuite now tests tarlz (if available) as compressor for zupdate. +The variable MAKEINFO has been added to configure and Makefile.in. @@ -4,8 +4,8 @@ Zutils is a collection of utilities able to process any combination of compressed and uncompressed files transparently. If any file given, including standard input, is compressed, its decompressed content is used. Compressed files are decompressed on the fly; no temporary files are -created. Data format is detected by its magic bytes, not by the file name -extension. +created. Data format is detected by its identifier string (magic bytes), not +by the file name extension. Empty files are considered uncompressed. These utilities are not wrapper scripts but safer and more efficient C++ programs. In particular the option '--recursive' is very efficient in @@ -45,6 +45,5 @@ Copyright (C) 2009-2023 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 configure -itself. +The file Makefile.in is a data file used by configure to produce the Makefile. +It has the same copyright owner and permissions that configure itself. diff --git a/arg_parser.cc b/arg_parser.cc index 5d46a9d..766abe0 100644 --- a/arg_parser.cc +++ b/arg_parser.cc @@ -1,4 +1,4 @@ -/* Arg_parser - POSIX/GNU command line argument parser. (C++ version) +/* Arg_parser - POSIX/GNU command-line argument parser. (C++ version) Copyright (C) 2006-2023 Antonio Diaz Diaz. This library is free software. Redistribution and use in source and diff --git a/arg_parser.h b/arg_parser.h index 272e919..a24ffd1 100644 --- a/arg_parser.h +++ b/arg_parser.h @@ -1,4 +1,4 @@ -/* Arg_parser - POSIX/GNU command line argument parser. (C++ version) +/* Arg_parser - POSIX/GNU command-line argument parser. (C++ version) Copyright (C) 2006-2023 Antonio Diaz Diaz. This library is free software. Redistribution and use in source and @@ -6,7 +6,7 @@ # to copy, distribute, and modify it. pkgname=zutils -pkgversion=1.12 +pkgversion=1.13-rc1 srctrigger=doc/${pkgname}.texi # clear some things potentially inherited from environment. @@ -69,10 +69,10 @@ while [ $# != 0 ] ; do echo " --mandir=DIR man pages directory [${mandir}]" echo " --sysconfdir=DIR read-only single-machine data directory [${sysconfdir}]" echo " CXX=COMPILER C++ compiler to use [${CXX}]" - echo " CPPFLAGS=OPTIONS command line options for the preprocessor [${CPPFLAGS}]" - echo " CXXFLAGS=OPTIONS command line options for the C++ compiler [${CXXFLAGS}]" + echo " CPPFLAGS=OPTIONS command-line options for the preprocessor [${CPPFLAGS}]" + echo " CXXFLAGS=OPTIONS command-line options for the C++ compiler [${CXXFLAGS}]" echo " CXXFLAGS+=OPTIONS append options to the current value of CXXFLAGS" - echo " LDFLAGS=OPTIONS command line options for the linker [${LDFLAGS}]" + echo " LDFLAGS=OPTIONS command-line options for the linker [${LDFLAGS}]" echo " MAKEINFO=NAME makeinfo program to use [${MAKEINFO}]" echo " DIFF=NAME diff program to use with zdiff [${DIFF}]" echo " GREP=NAME grep program to use with zgrep [${GREP}]" @@ -159,7 +159,7 @@ if [ -z "${no_create}" ] ; then # This script is free software: you have unlimited permission # to copy, distribute, and modify it. -exec /bin/sh $0 ${args} --no-create +exec /bin/sh "$0" ${args} --no-create EOF chmod +x config.status fi @@ -1,5 +1,5 @@ -.\" DO NOT MODIFY THIS FILE! It was generated by help2man 1.47.16. -.TH ZCAT "1" "January 2023" "zutils 1.12" "User Commands" +.\" DO NOT MODIFY THIS FILE! It was generated by help2man 1.49.2. +.TH ZCAT "1" "December 2023" "zutils 1.13-rc1" "User Commands" .SH NAME zcat \- decompress and concatenate files to standard output .SH SYNOPSIS @@ -10,8 +10,8 @@ zcat copies each file argument to standard output in sequence. If any file given is compressed, its decompressed content is copied. If a file given does not exist, and its name does not end with one of the known extensions, zcat tries the compressed file names corresponding to the -formats supported. If a file fails to decompress, zcat continues copying the -rest of the files. +formats supported until one is found. If a file fails to decompress, zcat +continues copying the rest of the files. .PP If a file is specified as '\-', data are read from standard input, decompressed if needed, and sent to standard output. Data read from @@ -1,5 +1,5 @@ -.\" DO NOT MODIFY THIS FILE! It was generated by help2man 1.47.16. -.TH ZCMP "1" "January 2023" "zutils 1.12" "User Commands" +.\" DO NOT MODIFY THIS FILE! It was generated by help2man 1.49.2. +.TH ZCMP "1" "December 2023" "zutils 1.13-rc1" "User Commands" .SH NAME zcmp \- decompress and compare two files byte by byte .SH SYNOPSIS @@ -15,15 +15,10 @@ files are decompressed on the fly; no temporary files are created. The formats supported are bzip2, gzip, lzip, xz, and zstd. .PP zcmp compares file1 to file2. The standard input is used only if file1 or -file2 refers to standard input. If file2 is omitted zcmp tries the -following: -.IP -\- If file1 is compressed, compares its decompressed contents with -the corresponding uncompressed file (the name of file1 with the -extension removed). -.IP -\- If file1 is uncompressed, compares it with the decompressed -contents of file1.[lz|bz2|gz|zst|xz] (the first one that is found). +file2 refers to standard input. If file2 is omitted zcmp tries to compare +file1 with the corresponding uncompressed file (if file1 is compressed), and +then with the corresponding compressed files of the remaining formats until +one is found. .PP Exit status is 0 if inputs are identical, 1 if different, 2 if trouble. .SH OPTIONS diff --git a/doc/zdiff.1 b/doc/zdiff.1 index 05a95cd..c169de1 100644 --- a/doc/zdiff.1 +++ b/doc/zdiff.1 @@ -1,5 +1,5 @@ -.\" DO NOT MODIFY THIS FILE! It was generated by help2man 1.47.16. -.TH ZDIFF "1" "January 2023" "zutils 1.12" "User Commands" +.\" DO NOT MODIFY THIS FILE! It was generated by help2man 1.49.2. +.TH ZDIFF "1" "December 2023" "zutils 1.13-rc1" "User Commands" .SH NAME zdiff \- decompress and compare two files line by line .SH SYNOPSIS @@ -17,15 +17,10 @@ from diff refer to temporary file names instead of those specified. The formats supported are bzip2, gzip, lzip, xz, and zstd. .PP zdiff compares file1 to file2. The standard input is used only if file1 or -file2 refers to standard input. If file2 is omitted zdiff tries the -following: -.IP -\- If file1 is compressed, compares its decompressed contents with -the corresponding uncompressed file (the name of file1 with the -extension removed). -.IP -\- If file1 is uncompressed, compares it with the decompressed -contents of file1.[lz|bz2|gz|zst|xz] (the first one that is found). +file2 refers to standard input. If file2 is omitted zdiff tries to compare +file1 with the corresponding uncompressed file (if file1 is compressed), and +then with the corresponding compressed files of the remaining formats until +one is found. .PP Exit status is 0 if inputs are identical, 1 if different, 2 if trouble. Some options only work if the diff program used supports them. @@ -59,7 +54,7 @@ try hard to find a smaller set of changes ignore changes due to tab expansion .TP \fB\-i\fR, \fB\-\-ignore\-case\fR -ignore case differences in file contents +ignore case differences .TP \fB\-M\fR, \fB\-\-format=\fR<list> process only the formats in <list> diff --git a/doc/zgrep.1 b/doc/zgrep.1 index 19d6909..dd5699f 100644 --- a/doc/zgrep.1 +++ b/doc/zgrep.1 @@ -1,5 +1,5 @@ -.\" DO NOT MODIFY THIS FILE! It was generated by help2man 1.47.16. -.TH ZGREP "1" "January 2023" "zutils 1.12" "User Commands" +.\" DO NOT MODIFY THIS FILE! It was generated by help2man 1.49.2. +.TH ZGREP "1" "December 2023" "zutils 1.13-rc1" "User Commands" .SH NAME zgrep \- search compressed files for a regular expression .SH SYNOPSIS @@ -11,8 +11,8 @@ on any combination of compressed and uncompressed files. If any file given is compressed, its decompressed content is used. If a file given does not exist, and its name does not end with one of the known extensions, zgrep tries the compressed file names corresponding to the -formats supported. If a file fails to decompress, zgrep continues -searching the rest of the files. +formats supported until one is found. If a file fails to decompress, zgrep +continues searching the rest of the files. .PP If a file is specified as '\-', data are read from standard input, decompressed if needed, and fed to grep. Data read from standard input diff --git a/doc/ztest.1 b/doc/ztest.1 index 73f3f8c..7ecb7c5 100644 --- a/doc/ztest.1 +++ b/doc/ztest.1 @@ -1,19 +1,19 @@ -.\" DO NOT MODIFY THIS FILE! It was generated by help2man 1.47.16. -.TH ZTEST "1" "January 2023" "zutils 1.12" "User Commands" +.\" DO NOT MODIFY THIS FILE! It was generated by help2man 1.49.2. +.TH ZTEST "1" "December 2023" "zutils 1.13-rc1" "User Commands" .SH NAME -ztest \- verify the integrity of compressed files +ztest \- check the integrity of compressed files .SH SYNOPSIS .B ztest [\fI\,options\/\fR] [\fI\,files\/\fR] .SH DESCRIPTION -ztest verifies the integrity of the compressed files specified. It +ztest checks the integrity of the compressed files specified. It also warns if an uncompressed file has a compressed file name extension, or if a compressed file has a wrong compressed extension. Uncompressed files are otherwise ignored. If a file is specified as '\-', the integrity of -compressed data read from standard input is verified. Data read from +compressed data read from standard input is checked. Data read from standard input must be all in the same compressed format. If a file fails to decompress, does not exist, can't be opened, or is a terminal, ztest -continues verifying the rest of the files. A final diagnostic is shown at +continues testing the rest of the files. A final diagnostic is shown at verbosity level 1 or higher if any file fails the test when testing multiple files. .PP @@ -22,15 +22,15 @@ working directory, and nonrecursive searches read standard input. .PP The formats supported are bzip2, gzip, lzip, xz, and zstd. .PP -Note that error detection in the xz format is broken. First, some xz -files lack integrity information. Second, not all xz decompressors can -verify the integrity of all xz files. Third, section 2.1.1.2 'Stream -Flags' of the xz format specification allows xz decompressors to produce -garbage output without issuing any warning. Therefore, xz files can't -always be verified as reliably as files in the other formats can. +Note that error detection in the xz format is broken. First, some xz files +lack integrity information. Second, not all xz decompressors can check the +integrity of all xz files. Third, section 2.1.1.2 'Stream Flags' of the +xz format specification allows xz decompressors to produce garbage output +without issuing any warning. Therefore, xz files can't always be checked as +reliably as files in the other formats can. .PP -Exit status is 0 if all compressed files verify OK, 1 if environmental -problems (file not found, invalid command line options, I/O errors, etc), +Exit status is 0 if all compressed files check OK, 1 if environmental +problems (file not found, invalid command\-line options, I/O errors, etc), 2 if any compressed file is corrupt or invalid, or if any file has an incorrect file name extension. .SH OPTIONS diff --git a/doc/zupdate.1 b/doc/zupdate.1 index 5731862..c45b2bd 100644 --- a/doc/zupdate.1 +++ b/doc/zupdate.1 @@ -1,5 +1,5 @@ -.\" DO NOT MODIFY THIS FILE! It was generated by help2man 1.47.16. -.TH ZUPDATE "1" "January 2023" "zutils 1.12" "User Commands" +.\" DO NOT MODIFY THIS FILE! It was generated by help2man 1.49.2. +.TH ZUPDATE "1" "December 2023" "zutils 1.13-rc1" "User Commands" .SH NAME zupdate \- recompress bzip2, gzip, xz, zstd files to lzip format .SH SYNOPSIS @@ -12,17 +12,17 @@ Only regular files with standard file name extensions are recompressed, other files are ignored. Compressed files are decompressed and then recompressed on the fly; no temporary files are created. The lzip format is chosen as destination because it is the most appropriate for -long\-term data archiving. +long\-term archiving. .PP If no files are specified, recursive searches examine the current working directory, and nonrecursive searches do nothing. .PP -If the lzip compressed version of a file already exists, the file is -skipped unless the option '\-\-force' is given. In this case, if the -comparison with the existing lzip version fails, an error is returned -and the original file is not deleted. The operation of zupdate is meant -to be safe and not cause any data loss. Therefore, existing lzip -compressed files are never overwritten nor deleted. +If the lzip\-compressed version of a file already exists, the file is skipped +unless the option '\-\-force' is given. In this case, if the comparison with +the existing lzip version fails, an error is returned and the original file +is not deleted. The operation of zupdate is meant to be safe and not cause +any data loss. Therefore, existing lzip\-compressed files are never +overwritten nor deleted. .PP The names of the original files must have one of the following extensions: .PP @@ -33,7 +33,7 @@ The names of the original files must have one of the following extensions: Exit status is 0 if all the compressed files were successfully recompressed (if needed), compared, and deleted (if requested). 1 if a non\-fatal error occurred (file not found or not regular, or has invalid format, or can't be -deleted). 2 if a fatal error occurred (invalid command line options, +deleted). 2 if a fatal error occurred (invalid command\-line options, compressor can't be run, or comparison fails). .SH OPTIONS .TP diff --git a/doc/zutils.info b/doc/zutils.info index a344507..78e5996 100644 --- a/doc/zutils.info +++ b/doc/zutils.info @@ -11,7 +11,7 @@ File: zutils.info, Node: Top, Next: Introduction, Up: (dir) Zutils Manual ************* -This manual is for Zutils (version 1.12, 7 January 2023). +This manual is for Zutils (version 1.13-rc1, 31 December 2023). * Menu: @@ -43,8 +43,8 @@ Zutils is a collection of utilities able to process any combination of compressed and uncompressed files transparently. If any file given, including standard input, is compressed, its decompressed content is used. Compressed files are decompressed on the fly; no temporary files are -created. Data format is detected by its magic bytes, not by the file name -extension. +created. Data format is detected by its identifier string (magic bytes), not +by the file name extension. Empty files are considered uncompressed. These utilities are not wrapper scripts but safer and more efficient C++ programs. In particular the option '--recursive' is very efficient in those @@ -60,6 +60,10 @@ is configurable at runtime. shell scripts provided by GNU gzip. 'ztest' is unique to zutils. 'zupdate' is similar to gzip's znew. + When 'zcat', 'zcmp', 'zdiff', or 'zgrep' need to try compressed file +names, the search order is: lzip, gzip, bzip2, zstd, xz. +(FILE.[lz|gz|bz2|zst|xz]). + NOTE: Bzip2 and lzip provide well-defined values of exit status, which makes them safe to use with zutils. Gzip and xz may return ambiguous warning values, making them less reliable back ends for zutils. Zstd currently does @@ -79,22 +83,6 @@ example GNU gzip) must be able to decompress .Z files. have been compressed. Decompressed is used to refer to data which have undergone the process of decompression. - - Numbers given as arguments to options (positions, sizes) may be followed -by a multiplier and an optional 'B' for "byte". - - Table of SI and binary prefixes (unit multipliers): - -Prefix Value | Prefix Value -k kilobyte (10^3 = 1000) | Ki kibibyte (2^10 = 1024) -M megabyte (10^6) | Mi mebibyte (2^20) -G gigabyte (10^9) | Gi gibibyte (2^30) -T terabyte (10^12) | Ti tebibyte (2^40) -P petabyte (10^15) | Pi pebibyte (2^50) -E exabyte (10^18) | Ei exbibyte (2^60) -Z zettabyte (10^21) | Zi zebibyte (2^70) -Y yottabyte (10^24) | Yi yobibyte (2^80) - File: zutils.info, Node: Common options, Next: Configuration, Prev: Introduction, Up: Top @@ -103,7 +91,8 @@ File: zutils.info, Node: Common options, Next: Configuration, Prev: Introduct The following options: are available in all the utilities. Rather than writing identical descriptions for each of the programs, they are described -here. *Note Argument syntax: (arg_parser)Argument syntax. +here. Remember to prepend './' to any file name beginning with a hyphen, or +use '--'. *Note Argument syntax: (arg_parser)Argument syntax. '-h' '--help' @@ -168,6 +157,24 @@ here. *Note Argument syntax: (arg_parser)Argument syntax. otherwise. + Numbers given as arguments to options may be expressed in decimal, +hexadecimal, or octal (using the same syntax as integer constants in C++), +and may be followed by a multiplier and an optional 'B' for "byte". + + Table of SI and binary prefixes (unit multipliers): + +Prefix Value | Prefix Value +k kilobyte (10^3 = 1000) | Ki kibibyte (2^10 = 1024) +M megabyte (10^6) | Mi mebibyte (2^20) +G gigabyte (10^9) | Gi gibibyte (2^30) +T terabyte (10^12) | Ti tebibyte (2^40) +P petabyte (10^15) | Pi pebibyte (2^50) +E exabyte (10^18) | Ei exbibyte (2^60) +Z zettabyte (10^21) | Zi zebibyte (2^70) +Y yottabyte (10^24) | Yi yobibyte (2^80) +R ronnabyte (10^27) | Ri robibyte (2^90) +Q quettabyte (10^30) | Qi quebibyte (2^100) + File: zutils.info, Node: Configuration, Next: Zcat, Prev: Common options, Up: Top @@ -204,8 +211,8 @@ File: zutils.info, Node: Zcat, Next: Zcmp, Prev: Configuration, Up: Top file given is compressed, its decompressed content is copied. If a file given does not exist, and its name does not end with one of the known extensions, 'zcat' tries the compressed file names corresponding to the -formats supported. If a file fails to decompress, 'zcat' continues copying -the rest of the files. +formats supported until one is found. *Note search-order::. If a file fails +to decompress, 'zcat' continues copying the rest of the files. If a file is specified as '-', data are read from standard input, decompressed if needed, and sent to standard output. Data read from @@ -248,8 +255,8 @@ Exit status is 0 if no errors occurred, 1 otherwise. Force the compressed format given. Valid values for FORMAT are 'bz2', 'gz', 'lz', 'xz', 'zst', and 'un' for 'uncompressed'. If this option is used, the files are passed to the corresponding decompressor (or - transmitted unmodified) without verifying their format, and the exact - file name must be given. Other names won't be tried. + transmitted unmodified) without checking their format, and the exact + file name must be given. Other names are not tried. '-q' '--quiet' @@ -306,15 +313,10 @@ are created. zcmp [OPTIONS] FILE1 [FILE2] This compares FILE1 to FILE2. The standard input is used only if FILE1 or -FILE2 refers to standard input. If FILE2 is omitted 'zcmp' tries the -following: - - - If FILE1 is compressed, compares its decompressed contents with the - corresponding uncompressed file (the name of FILE1 with the extension - removed). - - - If FILE1 is uncompressed, compares it with the decompressed contents - of FILE1.[lz|bz2|gz|zst|xz] (the first one that is found). +FILE2 refers to standard input. If FILE2 is omitted 'zcmp' tries to compare +FILE1 with the corresponding uncompressed file (if FILE1 is compressed), +and then with the corresponding compressed files of the remaining formats +until one is found. *Note search-order::. An exit status of 0 means no differences were found, 1 means some differences were found, and 2 means trouble. @@ -351,14 +353,13 @@ differences were found, and 2 means trouble. '-O [FORMAT1][,FORMAT2]' '--force-format=[FORMAT1][,FORMAT2]' - Force the compressed formats given. Any of FORMAT1 or FORMAT2 may be - omitted and the corresponding format will be automatically detected. - Valid values for FORMAT are 'bz2', 'gz', 'lz', 'xz', 'zst', and 'un' - for 'uncompressed'. If at least one format is specified with this - option, the file is passed to the corresponding decompressor (or - transmitted unmodified) without verifying its format, and the exact - file names of both FILE1 and FILE2 must be given. Other names won't be - tried. + Force the compressed formats given. If FORMAT1 or FORMAT2 is omitted, + the corresponding format is automatically detected. Valid values for + FORMAT are 'bz2', 'gz', 'lz', 'xz', 'zst', and 'un' for + 'uncompressed'. If at least one format is specified with this option, + the file is passed to the corresponding decompressor (or transmitted + unmodified) without checking its format, and the exact file names of + both FILE1 and FILE2 must be given. Other names are not tried. '-q' '--quiet' @@ -382,22 +383,6 @@ differences were found, and 2 means trouble. the verbosity level. *Note version::. - Byte counts given as arguments to options may be expressed in decimal, -hexadecimal, or octal (using the same syntax as integer constants in C++), -and may be followed by a multiplier and an optional 'B' for "byte". - - Table of SI and binary prefixes (unit multipliers): - -Prefix Value | Prefix Value -k kilobyte (10^3 = 1000) | Ki kibibyte (2^10 = 1024) -M megabyte (10^6) | Mi mebibyte (2^20) -G gigabyte (10^9) | Gi gibibyte (2^30) -T terabyte (10^12) | Ti tebibyte (2^40) -P petabyte (10^15) | Pi pebibyte (2^50) -E exabyte (10^18) | Ei exbibyte (2^60) -Z zettabyte (10^21) | Zi zebibyte (2^70) -Y yottabyte (10^24) | Yi yobibyte (2^80) - File: zutils.info, Node: Zdiff, Next: Zgrep, Prev: Zcmp, Up: Top @@ -416,15 +401,10 @@ specified. zdiff [OPTIONS] FILE1 [FILE2] This compares FILE1 to FILE2. The standard input is used only if FILE1 or -FILE2 refers to standard input. If FILE2 is omitted 'zdiff' tries the -following: - - - If FILE1 is compressed, compares its decompressed contents with the - corresponding uncompressed file (the name of FILE1 with the extension - removed). - - - If FILE1 is uncompressed, compares it with the decompressed contents - of FILE1.[lz|bz2|gz|zst|xz] (the first one that is found). +FILE2 refers to standard input. If FILE2 is omitted 'zdiff' tries to +compare FILE1 with the corresponding uncompressed file (if FILE1 is +compressed), and then with the corresponding compressed files of the +remaining formats until one is found. *Note search-order::. An exit status of 0 means no differences were found, 1 means some differences were found, and 2 means trouble. @@ -461,18 +441,18 @@ diff program used supports them): '-i' '--ignore-case' - Ignore case differences in file contents. + Ignore case differences. Consider uppercase and lowercase letters + equivalent. '-O [FORMAT1][,FORMAT2]' '--force-format=[FORMAT1][,FORMAT2]' - Force the compressed formats given. Any of FORMAT1 or FORMAT2 may be - omitted and the corresponding format will be automatically detected. - Valid values for FORMAT are 'bz2', 'gz', 'lz', 'xz', 'zst', and 'un' - for 'uncompressed'. If at least one format is specified with this - option, the file is passed to the corresponding decompressor (or - transmitted unmodified) without verifying its format, and the exact - file names of both FILE1 and FILE2 must be given. Other names won't be - tried. + Force the compressed formats given. If FORMAT1 or FORMAT2 is omitted, + the corresponding format is automatically detected. Valid values for + FORMAT are 'bz2', 'gz', 'lz', 'xz', 'zst', and 'un' for + 'uncompressed'. If at least one format is specified with this option, + the file is passed to the corresponding decompressor (or transmitted + unmodified) without checking its format, and the exact file names of + both FILE1 and FILE2 must be given. Other names are not tried. '-p' '--show-c-function' @@ -531,9 +511,9 @@ File: zutils.info, Node: Zgrep, Next: Ztest, Prev: Zdiff, Up: Top on any combination of compressed and uncompressed files. If any file given is compressed, its decompressed content is used. If a file given does not exist, and its name does not end with one of the known extensions, 'zgrep' -tries the compressed file names corresponding to the formats supported. If -a file fails to decompress, 'zgrep' continues searching the rest of the -files. +tries the compressed file names corresponding to the formats supported +until one is found. *Note search-order::. If a file fails to decompress, +'zgrep' continues searching the rest of the files. If a file is specified as '-', data are read from standard input, decompressed if needed, and fed to grep. Data read from standard input must @@ -665,8 +645,8 @@ by 'zgrep' and not passed to grep): Force the compressed format given. Valid values for FORMAT are 'bz2', 'gz', 'lz', 'xz', 'zst', and 'un' for 'uncompressed'. If this option is used, the files are passed to the corresponding decompressor (or - transmitted unmodified) without verifying their format, and the exact - file name must be given. Other names won't be tried. + transmitted unmodified) without checking their format, and the exact + file name must be given. Other names are not tried. '-P' '--perl-regexp' @@ -735,14 +715,14 @@ File: zutils.info, Node: Ztest, Next: Zupdate, Prev: Zgrep, Up: Top 8 Ztest ******* -'ztest' verifies the integrity of the compressed files specified. It also +'ztest' checks the integrity of the compressed files specified. It also warns if an uncompressed file has a compressed file name extension, or if a compressed file has a wrong compressed extension. Uncompressed files are otherwise ignored. If a file is specified as '-', the integrity of -compressed data read from standard input is verified. Data read from +compressed data read from standard input is checked. Data read from standard input must be all in the same compressed format. If a file fails to decompress, does not exist, can't be opened, or is a terminal, 'ztest' -continues verifying the rest of the files. A final diagnostic is shown at +continues testing the rest of the files. A final diagnostic is shown at verbosity level 1 or higher if any file fails the test when testing multiple files. @@ -755,17 +735,17 @@ corresponding files are ignored. Note that error detection in the xz format is broken. First, some xz files lack integrity information. Second, not all xz decompressors can -verify the integrity of all xz files. Third, section 2.1.1.2 'Stream Flags' +check the integrity of all xz files. Third, section 2.1.1.2 'Stream Flags' of the xz format specification allows xz decompressors to produce garbage output without issuing any warning. Therefore, xz files can't always be -verified as reliably as files in the other formats can. +checked as reliably as files in the other formats can. The format for running 'ztest' is: ztest [OPTIONS] [FILES] -Exit status is 0 if all compressed files verify OK, 1 if environmental -problems (file not found, invalid command line options, I/O errors, etc), 2 +Exit status is 0 if all compressed files check OK, 1 if environmental +problems (file not found, invalid command-line options, I/O errors, etc), 2 if any compressed file is corrupt or invalid, or if any file has an incorrect file name extension. @@ -775,9 +755,9 @@ incorrect file name extension. '--force-format=FORMAT' Force the compressed format given. Valid values for FORMAT are 'bz2', 'gz', 'lz', 'xz', and 'zst'. If this option is used, the files are - passed to the corresponding decompressor without verifying their + passed to the corresponding decompressor without checking their format, and any files in a format that the decompressor can't - understand will fail. + understand fail the test. '-q' '--quiet' @@ -796,7 +776,7 @@ incorrect file name extension. '-v' '--verbose' - Verbose mode. Show the verify status for each file processed. Further + Verbose mode. Show the check status for each file processed. Further -v's increase the verbosity level. *Note version::. @@ -813,20 +793,20 @@ files are ignored. Compressed files are decompressed and then recompressed on the fly; no temporary files are created. If an error happens while recompressing a file, 'zupdate' exits immediately without recompressing the rest of the files. The lzip format is chosen as destination because it is -the most appropriate for long-term data archiving. +the most appropriate for long-term archiving. If no files are specified, recursive searches examine the current working directory, and nonrecursive searches do nothing. - If the lzip compressed version of a file already exists, the file is + If the lzip-compressed version of a file already exists, the file is skipped unless the option '--force' is given. In this case, if the comparison with the existing lzip version fails, an error is returned and the original file is not deleted. The operation of 'zupdate' is meant to be -safe and not cause any data loss. Therefore, existing lzip compressed files +safe and not cause any data loss. Therefore, existing lzip-compressed files are never overwritten nor deleted. Combining the options '--force' and '--keep', as in -'zupdate -f -k *.gz', verifies that there are no differences between each +'zupdate -f -k *.gz', checks that there are no differences between each pair of files in a multiformat set of files. The names of the original files must have one of the following @@ -854,7 +834,7 @@ permission bits S_ISUID and S_ISGID are cleared). Exit status is 0 if all the compressed files were successfully recompressed (if needed), compared, and deleted (if requested). 1 if a non-fatal error occurred (file not found or not regular, or has invalid format, or can't be -deleted). 2 if a fatal error occurred (invalid command line options, +deleted). 2 if a fatal error occurred (invalid command-line options, compressor can't be run, or comparison fails). 'zupdate' supports the following options: @@ -883,7 +863,7 @@ compressor can't be run, or comparison fails). '-f' '--force' - Don't skip a file for which a lzip compressed version already exists. + Don't skip a file for which a lzip-compressed version already exists. '--force' compares the content of the input file with the content of the existing lzip file and deletes the input file if both contents are identical. @@ -984,20 +964,21 @@ Concept index Tag Table: Node: Top217 -Node: Introduction1151 -Node: Common options3998 -Ref: version4484 -Ref: compressor-requirements6435 -Node: Configuration6830 -Node: Zcat7863 -Node: Zcmp10563 -Node: Zdiff14820 -Node: Zgrep18003 -Node: Ztest24111 -Node: Zupdate26910 -Ref: lz-compressor32325 -Node: Problems33026 -Node: Concept index33560 +Node: Introduction1157 +Ref: search-order2309 +Node: Common options3466 +Ref: version4032 +Ref: compressor-requirements5983 +Node: Configuration7372 +Node: Zcat8405 +Node: Zcmp11144 +Node: Zdiff14412 +Node: Zgrep17495 +Node: Ztest23642 +Node: Zupdate26435 +Ref: lz-compressor31843 +Node: Problems32544 +Node: Concept index33078 End Tag Table diff --git a/doc/zutils.texi b/doc/zutils.texi index a263099..824f5b1 100644 --- a/doc/zutils.texi +++ b/doc/zutils.texi @@ -6,8 +6,8 @@ @finalout @c %**end of header -@set UPDATED 7 January 2023 -@set VERSION 1.12 +@set UPDATED 31 December 2023 +@set VERSION 1.13-rc1 @dircategory Compression @direntry @@ -66,8 +66,8 @@ is a collection of utilities able to process any combination of compressed and uncompressed files transparently. If any file given, including standard input, is compressed, its decompressed content is used. Compressed files are decompressed on the fly; no temporary files are -created. Data format is detected by its magic bytes, not by the file name -extension. +created. Data format is detected by its identifier string (magic bytes), not +by the file name extension. Empty files are considered uncompressed. These utilities are not wrapper scripts but safer and more efficient C++ programs. In particular the option @option{--recursive} is very efficient in @@ -86,6 +86,11 @@ improved replacements for the shell scripts provided by GNU gzip. @command{ztest} is unique to zutils. @command{zupdate} is similar to gzip's znew. +@anchor{search-order} +When @command{zcat}, @command{zcmp}, @command{zdiff}, or @command{zgrep} +need to try compressed file names, the search order is: lzip, gzip, bzip2, +zstd, xz. (@var{file}.[lz|gz|bz2|zst|xz]). + NOTE: Bzip2 and lzip provide well-defined values of exit status, which makes them safe to use with zutils. Gzip and xz may return ambiguous warning values, making them less reliable back ends for zutils. Zstd currently does @@ -106,24 +111,6 @@ LANGUAGE NOTE: Uncompressed = not compressed = plain data; it may never have been compressed. Decompressed is used to refer to data which have undergone the process of decompression. -@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 Common options @chapter Common options @@ -132,7 +119,8 @@ Table of SI and binary prefixes (unit multipliers): The following @uref{http://www.nongnu.org/arg-parser/manual/arg_parser_manual.html#Argument-syntax,,options}: are available in all the utilities. Rather than writing identical -descriptions for each of the programs, they are described here. +descriptions for each of the programs, they are described here. Remember to +prepend @file{./} to any file name beginning with a hyphen, or use @samp{--}. @ifnothtml @xref{Argument syntax,,,arg_parser}. @end ifnothtml @@ -209,6 +197,26 @@ It must return 0 if no errors occurred, and a non-zero value otherwise. @end table +Numbers given as arguments to options may be expressed in decimal, +hexadecimal, or octal (using the same syntax as integer constants in C++), +and 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) +@item R @tab ronnabyte (10^27) @tab | @tab Ri @tab robibyte (2^90) +@item Q @tab quettabyte (10^30) @tab | @tab Qi @tab quebibyte (2^100) +@end multitable + @node Configuration @chapter The configuration file 'zutils.conf' @@ -249,8 +257,9 @@ where <format> is one of @samp{bz2}, @samp{gz}, @samp{lz}, @samp{xz}, or sequence. If any file given is compressed, its decompressed content is copied. If a file given does not exist, and its name does not end with one of the known extensions, @command{zcat} tries the compressed file names -corresponding to the formats supported. If a file fails to decompress, -@command{zcat} continues copying the rest of the files. +corresponding to the formats supported until one is found. +@xref{search-order}. If a file fails to decompress, @command{zcat} continues +copying the rest of the files. If a file is specified as @samp{-}, data are read from standard input, decompressed if needed, and sent to standard output. Data read from @@ -297,8 +306,8 @@ Number all output lines, starting with 1. The line count is unlimited. Force the compressed format given. Valid values for @var{format} are @samp{bz2}, @samp{gz}, @samp{lz}, @samp{xz}, @samp{zst}, and @samp{un} for @samp{uncompressed}. If this option is used, the files are passed to the -corresponding decompressor (or transmitted unmodified) without verifying -their format, and the exact file name must be given. Other names won't be +corresponding decompressor (or transmitted unmodified) without checking +their format, and the exact file name must be given. Other names are not tried. @item -q @@ -360,17 +369,10 @@ zcmp [@var{options}] @var{file1} [@var{file2}] @noindent This compares @var{file1} to @var{file2}. The standard input is used only if @var{file1} or @var{file2} refers to standard input. If @var{file2} is -omitted @command{zcmp} tries the following: - -@itemize - -@item -If @var{file1} is compressed, compares its decompressed contents with -the corresponding uncompressed file (the name of @var{file1} with the -extension removed). -@item -If @var{file1} is uncompressed, compares it with the decompressed -contents of @var{file1}.[lz|bz2|gz|zst|xz] (the first one that is found). -@end itemize +omitted @command{zcmp} tries to compare @var{file1} with the corresponding +uncompressed file (if @var{file1} is compressed), and then with the +corresponding compressed files of the remaining formats until one is found. +@xref{search-order}. @noindent An exit status of 0 means no differences were found, 1 means some @@ -409,14 +411,14 @@ Compare at most @var{count} input bytes. @item -O [@var{format1}][,@var{format2}] @itemx --force-format=[@var{format1}][,@var{format2}] -Force the compressed formats given. Any of @var{format1} or @var{format2} -may be omitted and the corresponding format will be automatically detected. -Valid values for @var{format} are @samp{bz2}, @samp{gz}, @samp{lz}, -@samp{xz}, @samp{zst}, and @samp{un} for @samp{uncompressed}. If at least -one format is specified with this option, the file is passed to the -corresponding decompressor (or transmitted unmodified) without verifying its -format, and the exact file names of both @var{file1} and @var{file2} must be -given. Other names won't be tried. +Force the compressed formats given. If @var{format1} or @var{format2} is +omitted, the corresponding format is automatically detected. Valid values +for @var{format} are @samp{bz2}, @samp{gz}, @samp{lz}, @samp{xz}, +@samp{zst}, and @samp{un} for @samp{uncompressed}. If at least one format is +specified with this option, the file is passed to the corresponding +decompressor (or transmitted unmodified) without checking its format, and +the exact file names of both @var{file1} and @var{file2} must be given. +Other names are not tried. @item -q @itemx --quiet @@ -441,24 +443,6 @@ the verbosity level. @xref{version}. @end table -Byte counts given as arguments to options may be expressed in decimal, -hexadecimal, or octal (using the same syntax as integer constants in C++), -and 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 Zdiff @chapter Zdiff @@ -480,17 +464,10 @@ zdiff [@var{options}] @var{file1} [@var{file2}] @noindent This compares @var{file1} to @var{file2}. The standard input is used only if @var{file1} or @var{file2} refers to standard input. If @var{file2} is -omitted @command{zdiff} tries the following: - -@itemize - -@item -If @var{file1} is compressed, compares its decompressed contents with -the corresponding uncompressed file (the name of @var{file1} with the -extension removed). -@item -If @var{file1} is uncompressed, compares it with the decompressed -contents of @var{file1}.[lz|bz2|gz|zst|xz] (the first one that is found). -@end itemize +omitted @command{zdiff} tries to compare @var{file1} with the corresponding +uncompressed file (if @var{file1} is compressed), and then with the +corresponding compressed files of the remaining formats until one is found. +@xref{search-order}. @noindent An exit status of 0 means no differences were found, 1 means some @@ -529,18 +506,18 @@ Ignore changes due to tab expansion. @item -i @itemx --ignore-case -Ignore case differences in file contents. +Ignore case differences. Consider uppercase and lowercase letters equivalent. @item -O [@var{format1}][,@var{format2}] @itemx --force-format=[@var{format1}][,@var{format2}] -Force the compressed formats given. Any of @var{format1} or @var{format2} -may be omitted and the corresponding format will be automatically detected. -Valid values for @var{format} are @samp{bz2}, @samp{gz}, @samp{lz}, -@samp{xz}, @samp{zst}, and @samp{un} for @samp{uncompressed}. If at least -one format is specified with this option, the file is passed to the -corresponding decompressor (or transmitted unmodified) without verifying its -format, and the exact file names of both @var{file1} and @var{file2} must be -given. Other names won't be tried. +Force the compressed formats given. If @var{format1} or @var{format2} is +omitted, the corresponding format is automatically detected. Valid values +for @var{format} are @samp{bz2}, @samp{gz}, @samp{lz}, @samp{xz}, +@samp{zst}, and @samp{un} for @samp{uncompressed}. If at least one format is +specified with this option, the file is passed to the corresponding +decompressor (or transmitted unmodified) without checking its format, and +the exact file names of both @var{file1} and @var{file2} must be given. +Other names are not tried. @item -p @itemx --show-c-function @@ -599,13 +576,12 @@ search on any combination of compressed and uncompressed files. If any file given is compressed, its decompressed content is used. If a file given does not exist, and its name does not end with one of the known extensions, @command{zgrep} tries the compressed file names corresponding to the formats -supported. If a file fails to decompress, @command{zgrep} continues -searching the rest of the files. +supported until one is found. @xref{search-order}. If a file fails to +decompress, @command{zgrep} continues searching the rest of the files. If a file is specified as @samp{-}, data are 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 in the same -compressed format. +decompressed if needed, and fed to grep. Data read from standard input must +be of the same type; all uncompressed or all in the same compressed format. If no files are specified, recursive searches examine the current working directory, and nonrecursive searches read standard input. @@ -738,8 +714,8 @@ Show only the part of matching lines that actually matches @var{pattern}. Force the compressed format given. Valid values for @var{format} are @samp{bz2}, @samp{gz}, @samp{lz}, @samp{xz}, @samp{zst}, and @samp{un} for @samp{uncompressed}. If this option is used, the files are passed to the -corresponding decompressor (or transmitted unmodified) without verifying -their format, and the exact file name must be given. Other names won't be +corresponding decompressor (or transmitted unmodified) without checking +their format, and the exact file name must be given. Other names are not tried. @item -P @@ -809,14 +785,14 @@ unusual characters like newlines. @chapter Ztest @cindex ztest -@command{ztest} verifies the integrity of the compressed files specified. It +@command{ztest} checks the integrity of the compressed files specified. It also warns if an uncompressed file has a compressed file name extension, or if a compressed file has a wrong compressed extension. Uncompressed files are otherwise ignored. If a file is specified as @samp{-}, the integrity of -compressed data read from standard input is verified. Data read from +compressed data read from standard input is checked. Data read from standard input must be all in the same compressed format. If a file fails to decompress, does not exist, can't be opened, or is a terminal, @command{ztest} -continues verifying the rest of the files. A final diagnostic is shown at +continues testing the rest of the files. A final diagnostic is shown at verbosity level 1 or higher if any file fails the test when testing multiple files. @@ -827,14 +803,14 @@ Bzip2, gzip, and lzip are the primary formats. Xz and zstd are optional. If the decompressor for the xz or zstd formats is not found, the corresponding files are ignored. -Note that error detection in the xz format is broken. First, some xz -files lack integrity information. Second, not all xz decompressors can -@uref{http://www.nongnu.org/lzip/xz_inadequate.html#fragmented,,verify the integrity} +Note that error detection in the xz format is broken. First, some xz files +lack integrity information. Second, not all xz decompressors can +@uref{http://www.nongnu.org/lzip/xz_inadequate.html#fragmented,,check the integrity} of all xz files. Third, section 2.1.1.2 'Stream Flags' of the @uref{http://tukaani.org/xz/xz-file-format.txt,,xz format specification} allows xz decompressors to produce garbage output without issuing any -warning. Therefore, xz files can't always be verified as reliably as -files in the other formats can. +warning. Therefore, xz files can't always be checked as reliably as files in +the other formats can. @c We can only hope that xz is soon abandoned. The format for running @command{ztest} is: @@ -844,8 +820,8 @@ ztest [@var{options}] [@var{files}] @end example @noindent -Exit status is 0 if all compressed files verify OK, 1 if environmental -problems (file not found, invalid command line options, I/O errors, etc), +Exit status is 0 if all compressed files check OK, 1 if environmental +problems (file not found, invalid command-line options, I/O errors, etc), 2 if any compressed file is corrupt or invalid, or if any file has an incorrect file name extension. @@ -857,8 +833,8 @@ incorrect file name extension. Force the compressed format given. Valid values for @var{format} are @samp{bz2}, @samp{gz}, @samp{lz}, @samp{xz}, and @samp{zst}. If this option is used, the files are passed to the corresponding decompressor without -verifying their format, and any files in a format that the decompressor -can't understand will fail. +checking their format, and any files in a format that the decompressor can't +understand fail the test. @item -q @itemx --quiet @@ -877,7 +853,7 @@ recursively, following all symbolic links. @item -v @itemx --verbose -Verbose mode. Show the verify status for each file processed. Further -v's +Verbose mode. Show the check status for each file processed. Further -v's increase the verbosity level. @xref{version}. @end table @@ -894,21 +870,21 @@ recompressed, other files are ignored. Compressed files are decompressed and then recompressed on the fly; no temporary files are created. If an error happens while recompressing a file, @command{zupdate} exits immediately without recompressing the rest of the files. The lzip format is chosen as -destination because it is the most appropriate for long-term data archiving. +destination because it is the most appropriate for long-term archiving. If no files are specified, recursive searches examine the current working directory, and nonrecursive searches do nothing. -If the lzip compressed version of a file already exists, the file is skipped +If the lzip-compressed version of a file already exists, the file is skipped unless the option @option{--force} is given. In this case, if the comparison with the existing lzip version fails, an error is returned and the original file is not deleted. The operation of @command{zupdate} is meant to be safe -and not cause any data loss. Therefore, existing lzip compressed files are +and not cause any data loss. Therefore, existing lzip-compressed files are never overwritten nor deleted. Combining the options @option{--force} and @option{--keep}, as in -@w{@samp{zupdate -f -k *.gz}}, verifies that there are no differences -between each pair of files in a multiformat set of files. +@w{@samp{zupdate -f -k *.gz}}, checks that there are no differences between +each pair of files in a multiformat set of files. The names of the original files must have one of the following extensions:@* @samp{.bz2}, @samp{.gz}, @samp{.xz}, @samp{.zst}, or @samp{.Z}, which are @@ -938,7 +914,7 @@ zupdate [@var{options}] [@var{files}] Exit status is 0 if all the compressed files were successfully recompressed (if needed), compared, and deleted (if requested). 1 if a non-fatal error occurred (file not found or not regular, or has invalid format, or can't be -deleted). 2 if a fatal error occurred (invalid command line options, +deleted). 2 if a fatal error occurred (invalid command-line options, compressor can't be run, or comparison fails). @command{zupdate} supports the following options: @@ -968,10 +944,10 @@ Expand combined file name extensions; recompress @samp{.tbz}, @samp{.tbz2}, @item -f @itemx --force -Don't skip a file for which a lzip compressed version already exists. -@option{--force} compares the content of the input file with the content -of the existing lzip file and deletes the input file if both contents -are identical. +Don't skip a file for which a lzip-compressed version already exists. +@option{--force} compares the content of the input file with the content of +the existing lzip file and deletes the input file if both contents are +identical. @item -i @itemx --ignore-errors @@ -46,7 +46,7 @@ std::string compressor_names[num_formats] = std::vector< std::string > compressor_args[num_formats]; // vector of enabled formats plus [num_formats] for uncompressed. -// empty means all enabled. +// empty or incomplete (size <= num_formats) means all enabled. std::vector< bool > enabled_formats; const struct { const char * from; const char * to; int format_index; } @@ -292,7 +292,7 @@ int extension_format( const int eindex ) { return ( eindex >= 0 ) ? known_extensions[eindex].format_index : -1; } const char * extension_from( const int eindex ) - { return known_extensions[eindex].from; } + { return ( eindex >= 0 ) ? known_extensions[eindex].from : ""; } const char * extension_to( const int eindex ) { return known_extensions[eindex].to; } @@ -23,7 +23,7 @@ const char * const format_names[num_formats] = const char * const simple_extensions[num_formats] = { ".bz2", ".gz", ".lz", ".xz", ".zst" }; const int format_order[num_formats] = - { fmt_lz, fmt_bz2, fmt_gz, fmt_zst, fmt_xz }; // search order + { fmt_lz, fmt_gz, fmt_bz2, fmt_zst, fmt_xz }; // search order bool enabled_format( const int format_index ); // -1 == uncompressed void parse_format_list( const std::string & arg, const char * const pn ); @@ -33,7 +33,7 @@ int parse_format_type( const std::string & arg, const char * const pn, int extension_index( const std::string & name ); // -1 if unknown int extension_format( const int eindex ); // -1 if uncompressed -const char * extension_from( const int eindex ); +const char * extension_from( const int eindex ); // -1 if uncompressed const char * extension_to( const int eindex ); // Return format_index, or -1 if uncompressed. diff --git a/recursive.cc b/recursive.cc index fd87010..d992258 100644 --- a/recursive.cc +++ b/recursive.cc @@ -41,7 +41,7 @@ bool test_full_name( const std::string & full_name, const struct stat * stp, { loop = true; break; } } if( loop ) // full_name already visited or above tree - show_file_error( full_name.c_str(), "warning: Recursive directory loop." ); + show_file_error( full_name.c_str(), "warning: recursive directory loop." ); return !loop; // (link to) directory } diff --git a/testsuite/check.sh b/testsuite/check.sh index 833eab7..dc6ae2c 100755 --- a/testsuite/check.sh +++ b/testsuite/check.sh @@ -43,6 +43,8 @@ for i in ${compressors}; do $i in || compressor_needed printf "Hello World!\n" > hello || framework_failure $i hello || compressor_needed + touch zero || framework_failure + $i zero || compressor_needed done cat "${testdir}"/test.txt > in || framework_failure @@ -56,24 +58,34 @@ cat in in in in in in > in6 || framework_failure bad0_lz="${testdir}"/zero_bad_crc.lz bad0_gz="${testdir}"/zero_bad_crc.gz bad1_lz="${testdir}"/test_bad_crc.lz -touch empty empty.bz2 empty.gz empty.lz +touch empty empty.bz2 empty.gz empty.lz || framework_failure fail=0 test_failed() { fail=1 ; printf " $1" ; [ -z "$2" ] || printf "($2)" ; } printf "testing zcat-%s..." "$2" for i in ${extensions}; do - "${ZCAT}" -N in.$i > copy || test_failed $LINENO $i - cmp in copy || test_failed $LINENO $i - "${ZCAT}" -N empty.$i in.$i > copy || test_failed $LINENO $i - cmp in copy || test_failed $LINENO $i - "${ZCAT}" -N --format=un in.$i > copy || test_failed $LINENO $i - cmp in copy || test_failed $LINENO $i - "${ZCAT}" -N --force-format=$i in.$i > copy || test_failed $LINENO $i - cmp in copy || test_failed $LINENO $i - "${ZCAT}" -N in.$i | dd bs=1000 count=1 > copy 2> /dev/null || + "${ZCAT}" -N in.$i > out || test_failed $LINENO $i + cmp in out || test_failed $LINENO $i + "${ZCAT}" -N empty in.$i > out || test_failed $LINENO $i + cmp in out || test_failed $LINENO $i + "${ZCAT}" -N empty.$i in.$i > out || test_failed $LINENO $i + cmp in out || test_failed $LINENO $i + "${ZCAT}" -N in.$i empty > out || test_failed $LINENO $i + cmp in out || test_failed $LINENO $i + "${ZCAT}" -N in.$i empty.$i > out || test_failed $LINENO $i + cmp in out || test_failed $LINENO $i + "${ZCAT}" -N zero.$i in.$i > out || test_failed $LINENO $i + cmp in out || test_failed $LINENO $i + "${ZCAT}" -N in.$i zero.$i > out || test_failed $LINENO $i + cmp in out || test_failed $LINENO $i + "${ZCAT}" -N --format=un in.$i > out || test_failed $LINENO $i + cmp in out || test_failed $LINENO $i + "${ZCAT}" -N --force-format=$i in.$i > out || test_failed $LINENO $i + cmp in out || test_failed $LINENO $i + "${ZCAT}" -N in.$i | dd bs=1000 count=1 > out 2> /dev/null || test_failed $LINENO $i - dd if=in bs=1000 count=1 2> /dev/null | cmp - copy || + dd if=in bs=1000 count=1 2> /dev/null | cmp - out || test_failed $LINENO $i done @@ -82,34 +94,34 @@ printf "LZIP\001-.............................." | "${ZCAT}" -N > /dev/null 2>&1 printf "LZIPxxxxxx" | "${ZCAT}" -N > /dev/null || test_failed $LINENO printf "BZh9xxxxxx" | "${ZCAT}" -N > /dev/null || test_failed $LINENO "${ZCAT}" -N -v -s "${testdir}"/zcat_vs.dat > /dev/null || test_failed $LINENO -"${ZCAT}" -N < in > copy || test_failed $LINENO -cmp in copy || test_failed $LINENO -"${ZCAT}" -N < in.gz > copy || test_failed $LINENO -cmp in copy || test_failed $LINENO -"${ZCAT}" -N < in.bz2 > copy || test_failed $LINENO -cmp in copy || test_failed $LINENO -"${ZCAT}" -N < in.lz > copy || test_failed $LINENO -cmp in copy || test_failed $LINENO -"${ZCAT}" -N -O lz - - < in.lz > copy || test_failed $LINENO -cmp in copy || test_failed $LINENO -"${ZCAT}" -N -O un in.lz | lzip -d > copy || test_failed $LINENO -cmp in copy || test_failed $LINENO -"${ZCAT}" -N --lz='lzip -q' < in.lz > copy || test_failed $LINENO -cmp in copy || test_failed $LINENO -"${ZCAT}" -N in > copy || test_failed $LINENO -cmp in copy || test_failed $LINENO -"${ZCAT}" -N lz_only > copy || test_failed $LINENO -cmp in copy || test_failed $LINENO -cat in.lz in in in in | "${ZCAT}" -N > copy || test_failed $LINENO # tdata -cmp in copy || test_failed $LINENO -"${ZCAT}" -N in in.gz in.bz2 in.lz -- -in- -in-.lz > copy || test_failed $LINENO -cmp in6 copy || test_failed $LINENO -"${ZCAT}" -Nq in in.gz in.bz2 in.lz "${bad0_lz}" -- -in- -in-.lz > copy +"${ZCAT}" -N < in > out || test_failed $LINENO +cmp in out || test_failed $LINENO +"${ZCAT}" -N < in.gz > out || test_failed $LINENO +cmp in out || test_failed $LINENO +"${ZCAT}" -N < in.bz2 > out || test_failed $LINENO +cmp in out || test_failed $LINENO +"${ZCAT}" -N < in.lz > out || test_failed $LINENO +cmp in out || test_failed $LINENO +"${ZCAT}" -N -O lz - - < in.lz > out || test_failed $LINENO +cmp in out || test_failed $LINENO +"${ZCAT}" -N -O un in.lz | lzip -d > out || test_failed $LINENO +cmp in out || test_failed $LINENO +"${ZCAT}" -N --lz='lzip -q' < in.lz > out || test_failed $LINENO +cmp in out || test_failed $LINENO +"${ZCAT}" -N in > out || test_failed $LINENO +cmp in out || test_failed $LINENO +"${ZCAT}" -N lz_only > out || test_failed $LINENO +cmp in out || test_failed $LINENO +cat in.lz in in in in | "${ZCAT}" -N > out || test_failed $LINENO # tdata +cmp in out || test_failed $LINENO +"${ZCAT}" -N in in.gz in.bz2 in.lz -- -in- -in-.lz > out || test_failed $LINENO +cmp in6 out || test_failed $LINENO +"${ZCAT}" -Nq in in.gz in.bz2 in.lz "${bad0_lz}" -- -in- -in-.lz > out [ $? = 1 ] || test_failed $LINENO -cmp in6 copy || test_failed $LINENO -"${ZCAT}" -Nq "${bad1_lz}" -- -in-.lz in in.gz in.bz2 in.lz > copy +cmp in6 out || test_failed $LINENO +"${ZCAT}" -Nq "${bad1_lz}" -- -in-.lz in in.gz in.bz2 in.lz > out [ $? = 1 ] || test_failed $LINENO -cmp in6 copy || test_failed $LINENO +cmp in6 out || test_failed $LINENO "${ZCAT}" -N . || test_failed $LINENO "${ZCAT}" -N -r . > /dev/null || test_failed $LINENO "${ZCAT}" -N -r > /dev/null || test_failed $LINENO @@ -151,6 +163,7 @@ for i in ${extensions}; do "${ZCMP}" -N -i 1kB:1000 -n 500 in6 in.$i || test_failed $LINENO $i "${ZCMP}" -N -i 1KiB:1024 -n 50 in.$i in6 || test_failed $LINENO $i "${ZCMP}" -N empty empty.$i || test_failed $LINENO $i + "${ZCMP}" -N empty zero.$i || test_failed $LINENO $i done "${ZCMP}" -N -q in in6 @@ -214,10 +227,18 @@ cat in.lz | "${ZCMP}" -N -O un,un in.lz - || test_failed $LINENO [ $? = 2 ] || test_failed $LINENO "${ZCMP}" -N --bad-option in in 2> /dev/null [ $? = 2 ] || test_failed $LINENO +cat in.gz > a.gz || framework_failure +cat in.lz > a.lz || framework_failure +"${ZCMP}" -N a.gz || test_failed $LINENO +"${ZCMP}" -N a.lz || test_failed $LINENO printf "\ntesting zdiff-%s..." "$2" +"${ZDIFF}" -N a.gz || test_failed $LINENO +"${ZDIFF}" -N a.lz || test_failed $LINENO +rm -f a.gz a.lz || framework_failure + for i in ${extensions}; do "${ZDIFF}" -N in.$i > /dev/null || test_failed $LINENO $i "${ZDIFF}" -N in in.$i > /dev/null || test_failed $LINENO $i @@ -227,11 +248,12 @@ for i in ${extensions}; do "${ZDIFF}" -N in.$i in --force-format=$i, > /dev/null || test_failed $LINENO $i "${ZDIFF}" -N empty empty.$i > /dev/null || test_failed $LINENO $i + "${ZDIFF}" -N empty zero.$i > /dev/null || test_failed $LINENO $i done "${ZDIFF}" -N in in6 > /dev/null [ $? = 1 ] || test_failed $LINENO -# GNU diff 3.0 returns 2 when binary files differ +# GNU diff 3.0 returns 2 (instead of 1) when binary files differ "${ZDIFF}" -N in.tar pin.tar4 > /dev/null && test_failed $LINENO "${ZDIFF}" -N - - || test_failed $LINENO "${ZDIFF}" -N - 2> /dev/null @@ -307,8 +329,10 @@ for i in ${extensions}; do "${ZGREP}" -N --force-format=$i "GNU" in 2> /dev/null [ $? = 2 ] || test_failed $LINENO $i "${ZGREP}" -N "nx_pattern" empty.$i && test_failed $LINENO $i + "${ZGREP}" -N "nx_pattern" zero.$i && test_failed $LINENO $i done +"${ZGREP}" -N "nx_pattern" empty && test_failed $LINENO "${ZGREP}" -N pin.tar4 -e "GNU" > /dev/null || test_failed $LINENO "${ZGREP}" -N "GNU" < pin.tar4 > /dev/null || test_failed $LINENO "${ZGREP}" -N -r "GNU" . > /dev/null || test_failed $LINENO @@ -379,7 +403,6 @@ rm -f empty.bz2 empty.gz empty.lz || framework_failure "${ZTEST}" -N -R . || test_failed $LINENO "${ZTEST}" -N -R || test_failed $LINENO "${ZTEST}" -N empty || test_failed $LINENO -rm -f empty || framework_failure # test wrong compressed extensions cat in.bz2 > in_bz2.gz || framework_failure @@ -569,6 +592,13 @@ cat in.gz > 'name with spaces.gz' || framework_failure "${ZCMP}" -N in 'name with spaces.lz' || test_failed $LINENO rm -f 'name with spaces.lz' || framework_failure +cat zero.gz > z.gz || framework_failure +"${ZUPDATE}" -N -0 -q z.gz || test_failed $LINENO +[ ! -e z.gz ] || test_failed $LINENO +[ -e z.lz ] || test_failed $LINENO +"${ZCMP}" -N empty z.lz || test_failed $LINENO +rm -f empty z.lz || framework_failure + mkdir tmp2 mkdir tmp2/tmp3 cat in.bz2 > tmp2/tmp3/a.bz2 || framework_failure @@ -584,7 +614,7 @@ cat in.gz > tmp2/tmp3/a.gz || framework_failure [ -e tmp2/tmp3/a.gz ] || test_failed $LINENO [ -e ddir2/tmp3/a.lz ] || test_failed $LINENO # test non-recursive to destdir -"${ZUPDATE}" -N -0 -k --destdir=ddir3 tmp2/tmp3/a.gz || test_failed $LINENO +"${ZUPDATE}" -N -0 -k --destdir=ddir3/// tmp2/tmp3/a.gz || test_failed $LINENO [ -e tmp2/tmp3/a.bz2 ] || test_failed $LINENO [ -e tmp2/tmp3/a.gz ] || test_failed $LINENO [ -e ddir3/a.lz ] || test_failed $LINENO @@ -94,8 +94,8 @@ void show_help() "file given is compressed, its decompressed content is copied. If a file\n" "given does not exist, and its name does not end with one of the known\n" "extensions, zcat tries the compressed file names corresponding to the\n" - "formats supported. If a file fails to decompress, zcat continues copying the\n" - "rest of the files.\n" + "formats supported until one is found. If a file fails to decompress, zcat\n" + "continues copying the rest of the files.\n" "\nIf a file is specified as '-', data are read from standard input,\n" "decompressed if needed, and sent to standard output. Data read from\n" "standard input must be of the same type; all uncompressed or all in the\n" @@ -345,7 +345,7 @@ int main( const int argc, const char * const argv[] ) case lz_opt: parse_compressor( arg, pn, fmt_lz, 1 ); break; case xz_opt: parse_compressor( arg, pn, fmt_xz, 1 ); break; case zst_opt: parse_compressor( arg, pn, fmt_zst, 1 ); break; - default : internal_error( "uncaught option." ); + default: internal_error( "uncaught option." ); } } // end process options @@ -58,13 +58,10 @@ void show_help() "\nThe formats supported are bzip2, gzip, lzip, xz, and zstd.\n" "\nUsage: zcmp [options] file1 [file2]\n" "\nzcmp compares file1 to file2. The standard input is used only if file1 or\n" - "file2 refers to standard input. If file2 is omitted zcmp tries the\n" - "following:\n" - "\n - If file1 is compressed, compares its decompressed contents with\n" - " the corresponding uncompressed file (the name of file1 with the\n" - " extension removed).\n" - "\n - If file1 is uncompressed, compares it with the decompressed\n" - " contents of file1.[lz|bz2|gz|zst|xz] (the first one that is found).\n" + "file2 refers to standard input. If file2 is omitted zcmp tries to compare\n" + "file1 with the corresponding uncompressed file (if file1 is compressed), and\n" + "then with the corresponding compressed files of the remaining formats until\n" + "one is found.\n" "\nExit status is 0 if inputs are identical, 1 if different, 2 if trouble.\n" "\nOptions:\n" " -h, --help display this help and exit\n" @@ -98,9 +95,9 @@ void show_help() // separate numbers of 5 or more digits in groups of 3 digits using '_' const char * format_num3( long long num ) { - const char * const si_prefix = "kMGTPEZY"; - const char * const binary_prefix = "KMGTPEZY"; - enum { buffers = 8, bufsize = 4 * sizeof num }; + enum { buffers = 8, bufsize = 4 * sizeof num, n = 10 }; + const char * const si_prefix = "kMGTPEZYRQ"; + const char * const binary_prefix = "KMGTPEZYRQ"; static char buffer[buffers][bufsize]; // circle of static buffers for printf static int current = 0; @@ -108,19 +105,22 @@ const char * format_num3( long long num ) char * p = buf + bufsize - 1; // fill the buffer backwards *p = 0; // terminator const bool negative = num < 0; - char prefix = 0; // try binary first, then si - for( int i = 0; i < 8 && num != 0 && ( num / 1024 ) * 1024 == num; ++i ) - { num /= 1024; prefix = binary_prefix[i]; } - if( prefix ) *(--p) = 'i'; - else - for( int i = 0; i < 8 && num != 0 && ( num / 1000 ) * 1000 == num; ++i ) - { num /= 1000; prefix = si_prefix[i]; } - if( prefix ) *(--p) = prefix; + if( num > 1024 || num < -1024 ) + { + char prefix = 0; // try binary first, then si + for( int i = 0; i < n && num != 0 && num % 1024 == 0; ++i ) + { num /= 1024; prefix = binary_prefix[i]; } + if( prefix ) *(--p) = 'i'; + else + for( int i = 0; i < n && num != 0 && num % 1000 == 0; ++i ) + { num /= 1000; prefix = si_prefix[i]; } + if( prefix ) *(--p) = prefix; + } const bool split = num >= 10000 || num <= -10000; for( int i = 0; ; ) { - long long onum = num; num /= 10; + const long long onum = num; num /= 10; *(--p) = llabs( onum - ( 10 * num ) ) + '0'; if( num == 0 ) break; if( split && ++i >= 3 ) { i = 0; *(--p) = '_'; } } @@ -129,6 +129,7 @@ const char * format_num3( long long num ) } +// Recognized formats: <num>k[B], <num>Ki[B], <num>[MGTPEZYRQ][i][B] long long getnum( const char * const arg, const char * const option_name, const char ** const tailp = 0, const long long llimit = 0, @@ -152,6 +153,8 @@ long long getnum( const char * const arg, const char * const option_name, int exponent = -1; // -1 = bad multiplier switch( ch ) { + case 'Q': exponent = 10; break; + case 'R': exponent = 9; break; case 'Y': exponent = 8; break; case 'Z': exponent = 7; break; case 'E': exponent = 6; break; @@ -210,7 +213,7 @@ bool skip_ignore_initial( const long long ignore_initial, const int infd ) 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; + if( rd < size ) break; // EOF rest -= rd; } } @@ -270,6 +273,7 @@ int cmp( const long long max_size, const int infd[2], uint8_t * buffer[2]; buffer[0] = buffer0; buffer[1] = buffer1; int retval = 0; + bool empty[2] = { true, true }; while( rest > 0 ) { @@ -282,6 +286,7 @@ int cmp( const long long max_size, const int infd[2], if( rd[i] != size && errno ) { show_file_error( filenames[i].c_str(), "Read error", errno ); retval = 2; goto done; } + if( rd[i] > 0 ) empty[i] = false; } for( int i = 0; i < 2; ++i ) if( rd[i] < size ) finished[i] = true; @@ -345,11 +350,13 @@ int cmp( const long long max_size, const int infd[2], if( rd[0] != rd[1] ) { + const int i = rd[1] < rd[0]; if( verbosity >= 0 ) - std::fprintf( stderr, list ? + std::fprintf( stderr, empty[i] ? + "%s: EOF on %s which is empty\n" : list ? "%s: EOF on %s after byte %llu\n" : "%s: EOF on %s after byte %llu, in line %llu\n", - program_name, filenames[rd[1]<rd[0]].c_str(), + program_name, filenames[i].c_str(), byte_number - 1, line_number ); retval = 1; break; } @@ -434,7 +441,7 @@ int main( const int argc, const char * const argv[] ) case lz_opt: parse_compressor( sarg, pn, fmt_lz ); break; case xz_opt: parse_compressor( sarg, pn, fmt_xz ); break; case zst_opt: parse_compressor( sarg, pn, fmt_zst ); break; - default : internal_error( "uncaught option." ); + default: internal_error( "uncaught option." ); } } // end process options diff --git a/zcmpdiff.cc b/zcmpdiff.cc index bbbc87e..961a32a 100644 --- a/zcmpdiff.cc +++ b/zcmpdiff.cc @@ -31,21 +31,26 @@ int open_instream( const std::string & input_filename ) int open_other_instream( std::string & name ) { - const int eindex = extension_index( name ); - if( eindex >= 0 && enabled_format( -1 ) ) - { // open uncompressed version - name.resize( name.size() - std::strlen( extension_from( eindex ) ) ); - name += extension_to( eindex ); - return open( name.c_str(), O_RDONLY | O_BINARY ); + const int eindex = extension_index( name ); // search extension + if( eindex >= 0 && enabled_format( -1 ) ) // open uncompressed version + { + std::string s( name, 0, name.size() - std::strlen( extension_from( eindex ) ) ); + s += extension_to( eindex ); + const int infd = open( s.c_str(), O_RDONLY | O_BINARY ); + if( infd >= 0 ) { name = s; return infd; } + } + const int eformat = extension_format( eindex ); + for( int i = 0; i < num_formats; ++i ) // search compressed version + { + const int format_index = format_order[i]; + if( eformat != format_index && enabled_format( format_index ) ) + { + std::string s( name, 0, name.size() - std::strlen( extension_from( eindex ) ) ); + s += simple_extensions[format_index]; + const int infd = open( s.c_str(), O_RDONLY | O_BINARY ); + if( infd >= 0 ) { name = s; return infd; } + } } - if( eindex < 0 ) // search compressed version - for( int i = 0; i < num_formats; ++i ) - if( enabled_format( format_order[i] ) ) - { - const std::string s( name + simple_extensions[format_order[i]] ); - const int infd = open( s.c_str(), O_RDONLY | O_BINARY ); - if( infd >= 0 ) { name = s; return infd; } - } return -1; } @@ -57,13 +57,10 @@ void show_help() "\nThe formats supported are bzip2, gzip, lzip, xz, and zstd.\n" "\nUsage: zdiff [options] file1 [file2]\n" "\nzdiff compares file1 to file2. The standard input is used only if file1 or\n" - "file2 refers to standard input. If file2 is omitted zdiff tries the\n" - "following:\n" - "\n - If file1 is compressed, compares its decompressed contents with\n" - " the corresponding uncompressed file (the name of file1 with the\n" - " extension removed).\n" - "\n - If file1 is uncompressed, compares it with the decompressed\n" - " contents of file1.[lz|bz2|gz|zst|xz] (the first one that is found).\n" + "file2 refers to standard input. If file2 is omitted zdiff tries to compare\n" + "file1 with the corresponding uncompressed file (if file1 is compressed), and\n" + "then with the corresponding compressed files of the remaining formats until\n" + "one is found.\n" "\nExit status is 0 if inputs are identical, 1 if different, 2 if trouble.\n" "Some options only work if the diff program used supports them.\n" "\nOptions:\n" @@ -76,7 +73,7 @@ void show_help() " -C, --context=<n> same as -c but use <n> lines of context\n" " -d, --minimal try hard to find a smaller set of changes\n" " -E, --ignore-tab-expansion ignore changes due to tab expansion\n" - " -i, --ignore-case ignore case differences in file contents\n" + " -i, --ignore-case ignore case differences\n" " -M, --format=<list> process only the formats in <list>\n" " -N, --no-rcfile don't read runtime configuration file\n" " -O, --force-format=[<f1>][,<f2>] force one or both input formats\n" @@ -344,7 +341,7 @@ int main( const int argc, const char * const argv[] ) case lz_opt: parse_compressor( sarg, pn, fmt_lz ); break; case xz_opt: parse_compressor( sarg, pn, fmt_xz ); break; case zst_opt: parse_compressor( sarg, pn, fmt_zst ); break; - default : internal_error( "uncaught option." ); + default: internal_error( "uncaught option." ); } } // end process options @@ -52,8 +52,8 @@ void show_help() "given is compressed, its decompressed content is used. If a file given\n" "does not exist, and its name does not end with one of the known\n" "extensions, zgrep tries the compressed file names corresponding to the\n" - "formats supported. If a file fails to decompress, zgrep continues\n" - "searching the rest of the files.\n" + "formats supported until one is found. If a file fails to decompress, zgrep\n" + "continues searching the rest of the files.\n" "\nIf a file is specified as '-', data are read from standard input,\n" "decompressed if needed, and fed to grep. Data read from standard input\n" "must be of the same type; all uncompressed or all in the same\n" @@ -338,7 +338,8 @@ int main( const int argc, const char * const argv[] ) case color_opt: color_option = "--color"; if( !sarg.empty() ) { color_option += '='; color_option += sarg; } break; - case label_opt: label_option = sarg; label = arg; break; + case label_opt: label_option = "--label="; label_option += sarg; + label = arg; break; case linebuf_opt: grep_args.push_back( "--line-buffered" ); line_buffered = true; break; case bz2_opt: parse_compressor( sarg, pn, fmt_bz2 ); break; @@ -346,14 +347,14 @@ int main( const int argc, const char * const argv[] ) case lz_opt: parse_compressor( sarg, pn, fmt_lz ); break; case xz_opt: parse_compressor( sarg, pn, fmt_xz ); break; case zst_opt: parse_compressor( sarg, pn, fmt_zst ); break; - default : internal_error( "uncaught option." ); + default: internal_error( "uncaught option." ); } } // end process options if( !color_option.empty() ) // push the last value set grep_args.push_back( color_option.c_str() ); if( !label_option.empty() ) // for "Binary file <label> matches" - grep_args.push_back( label_option.insert( 0, "--label=" ).c_str() ); + grep_args.push_back( label_option.c_str() ); #if defined __MSVCRT__ || defined __OS2__ setmode( STDIN_FILENO, O_BINARY ); @@ -1,4 +1,4 @@ -/* Ztest - verify the integrity of compressed files +/* Ztest - check the integrity of compressed files Copyright (C) 2010-2023 Antonio Diaz Diaz. This program is free software: you can redistribute it and/or modify @@ -50,28 +50,28 @@ namespace { void show_help() { - std::printf( "ztest verifies the integrity of the compressed files specified. It\n" + std::printf( "ztest checks the integrity of the compressed files specified. It\n" "also warns if an uncompressed file has a compressed file name extension, or\n" "if a compressed file has a wrong compressed extension. Uncompressed files\n" "are otherwise ignored. If a file is specified as '-', the integrity of\n" - "compressed data read from standard input is verified. Data read from\n" + "compressed data read from standard input is checked. Data read from\n" "standard input must be all in the same compressed format. If a file fails to\n" "decompress, does not exist, can't be opened, or is a terminal, ztest\n" - "continues verifying the rest of the files. A final diagnostic is shown at\n" + "continues testing the rest of the files. A final diagnostic is shown at\n" "verbosity level 1 or higher if any file fails the test when testing multiple\n" "files.\n" "\nIf no files are specified, recursive searches examine the current\n" "working directory, and nonrecursive searches read standard input.\n" "\nThe formats supported are bzip2, gzip, lzip, xz, and zstd.\n" - "\nNote that error detection in the xz format is broken. First, some xz\n" - "files lack integrity information. Second, not all xz decompressors can\n" - "verify the integrity of all xz files. Third, section 2.1.1.2 'Stream\n" - "Flags' of the xz format specification allows xz decompressors to produce\n" - "garbage output without issuing any warning. Therefore, xz files can't\n" - "always be verified as reliably as files in the other formats can.\n" + "\nNote that error detection in the xz format is broken. First, some xz files\n" + "lack integrity information. Second, not all xz decompressors can check the\n" + "integrity of all xz files. Third, section 2.1.1.2 'Stream Flags' of the\n" + "xz format specification allows xz decompressors to produce garbage output\n" + "without issuing any warning. Therefore, xz files can't always be checked as\n" + "reliably as files in the other formats can.\n" "\nUsage: ztest [options] [files]\n" - "\nExit status is 0 if all compressed files verify OK, 1 if environmental\n" - "problems (file not found, invalid command line options, I/O errors, etc),\n" + "\nExit status is 0 if all compressed files check OK, 1 if environmental\n" + "problems (file not found, invalid command-line options, I/O errors, etc),\n" "2 if any compressed file is corrupt or invalid, or if any file has an\n" "incorrect file name extension.\n" "\nOptions:\n" @@ -303,7 +303,7 @@ int main( const int argc, const char * const argv[] ) case lz_opt: parse_compressor( arg, pn, fmt_lz, 1 ); break; case xz_opt: parse_compressor( arg, pn, fmt_xz, 1 ); break; case zst_opt: parse_compressor( arg, pn, fmt_zst, 1 ); break; - default : internal_error( "uncaught option." ); + default: internal_error( "uncaught option." ); } } // end process options @@ -57,15 +57,15 @@ void show_help() "other files are ignored. Compressed files are decompressed and then\n" "recompressed on the fly; no temporary files are created. The lzip format\n" "is chosen as destination because it is the most appropriate for\n" - "long-term data archiving.\n" + "long-term archiving.\n" "\nIf no files are specified, recursive searches examine the current\n" "working directory, and nonrecursive searches do nothing.\n" - "\nIf the lzip compressed version of a file already exists, the file is\n" - "skipped unless the option '--force' is given. In this case, if the\n" - "comparison with the existing lzip version fails, an error is returned\n" - "and the original file is not deleted. The operation of zupdate is meant\n" - "to be safe and not cause any data loss. Therefore, existing lzip\n" - "compressed files are never overwritten nor deleted.\n" + "\nIf the lzip-compressed version of a file already exists, the file is skipped\n" + "unless the option '--force' is given. In this case, if the comparison with\n" + "the existing lzip version fails, an error is returned and the original file\n" + "is not deleted. The operation of zupdate is meant to be safe and not cause\n" + "any data loss. Therefore, existing lzip-compressed files are never\n" + "overwritten nor deleted.\n" "\nThe names of the original files must have one of the following extensions:\n" "\n'.bz2', '.gz', '.xz', '.zst', or '.Z', which are recompressed to '.lz'.\n" "\n'.tbz', '.tbz2', '.tgz', '.txz', or '.tzst', which are recompressed to '.tlz'.\n" @@ -73,7 +73,7 @@ void show_help() "\nExit status is 0 if all the compressed files were successfully recompressed\n" "(if needed), compared, and deleted (if requested). 1 if a non-fatal error\n" "occurred (file not found or not regular, or has invalid format, or can't be\n" - "deleted). 2 if a fatal error occurred (invalid command line options,\n" + "deleted). 2 if a fatal error occurred (invalid command-line options,\n" "compressor can't be run, or comparison fails).\n" "\nOptions:\n" " -h, --help display this help and exit\n" @@ -120,28 +120,28 @@ void extract_srcdir_name( const std::string & name, std::string & srcdir ) bool make_dirs( const std::string & name ) { static std::string cached_dirname; - unsigned dirsize = name.size(); // size of dirname without last slash - - for( unsigned i = name.size(); i > 0; --i ) - if( name[i-1] == '/' ) { dirsize = i - 1; break; } - if( dirsize >= name.size() ) return true; // no dirname - if( dirsize == 0 ) return true; // dirname is '/' + unsigned i = name.size(); + while( i > 0 && name[i-1] != '/' ) --i; // remove last component + while( i > 0 && name[i-1] == '/' ) --i; // remove slash(es) + if( i == 0 ) return true; // dirname is '/' or empty + const unsigned dirsize = i; // size of dirname without trailing slash(es) if( cached_dirname.size() == dirsize && cached_dirname.compare( 0, dirsize, name ) == 0 ) return true; - for( unsigned i = 0; i < dirsize; ) + for( i = 0; i < dirsize; ) { while( i < dirsize && name[i] == '/' ) ++i; const unsigned first = i; while( i < dirsize && name[i] != '/' ) ++i; if( first < i ) { - std::string partial( name, 0, i ); + const std::string partial( name, 0, i ); + const mode_t mode = S_IRWXU | S_IRGRP | S_IXGRP | S_IROTH | S_IXOTH; struct stat st; if( stat( partial.c_str(), &st ) == 0 ) - { if( !S_ISDIR( st.st_mode ) ) return false; } - else if( mkdir( partial.c_str(), S_IRWXU | S_IRGRP | S_IXGRP | S_IROTH | - S_IXOTH ) != 0 && errno != EEXIST ) return false; + { if( !S_ISDIR( st.st_mode ) ) { errno = ENOTDIR; return false; } } + else if( mkdir( partial.c_str(), mode ) != 0 && errno != EEXIST ) + return false; // if EEXIST, another process created the dir } } cached_dirname.assign( name, 0, dirsize ); @@ -168,7 +168,7 @@ void set_permissions( const char * const rname, const struct stat & in_stats ) { bool warning = false; const mode_t mode = in_stats.st_mode; - // chown will in many cases return with EPERM, which can be safely ignored. + // chown in many cases returns with EPERM, which can be safely ignored. if( chown( rname, in_stats.st_uid, in_stats.st_gid ) == 0 ) { if( chmod( rname, mode ) != 0 ) warning = true; } else @@ -180,7 +180,8 @@ void set_permissions( const char * const rname, const struct stat & in_stats ) t.modtime = in_stats.st_mtime; if( utime( rname, &t ) != 0 ) warning = true; if( warning && verbosity >= 2 ) - show_file_error( rname, "Can't change output file attributes.", errno ); + show_file_error( rname, + "warning: can't change output file attributes", errno ); } @@ -204,7 +205,7 @@ int zupdate_file( const std::string & name, const char * const lzip_name, if( format_index == fmt_lz ) { if( verbosity >= 2 ) - std::fprintf( stderr, "%s: Input file '%s' already has '%s' suffix.\n", + std::fprintf( stderr, "%s: %s: Input file already has '%s' suffix.\n", program_name, name.c_str(), extension_from( eindex ) ); return 0; // ignore this file } @@ -227,8 +228,7 @@ int zupdate_file( const std::string & name, const char * const lzip_name, if( !compressor_name ) { if( verbosity >= 2 ) - std::fprintf( stderr, "%s: Unknown extension in file name '%s' -- ignored.\n", - program_name, name.c_str() ); + show_file_error( name.c_str(), "Unknown extension in file name -- ignored." ); return 0; // ignore this file } @@ -247,9 +247,7 @@ int zupdate_file( const std::string & name, const char * const lzip_name, const bool lz_lz_exists = ( stat( rname2.c_str(), &st ) == 0 ); if( lz_exists && !force ) { - if( verbosity >= 0 ) - std::fprintf( stderr, "%s: Output file '%s' already exists, skipping.\n", - program_name, rname.c_str() ); + show_file_error( rname.c_str(), "Output file already exists, skipping." ); return -1; } @@ -283,8 +281,8 @@ int zupdate_file( const std::string & name, const char * const lzip_name, if( verbosity >= 1 ) std::fprintf( stderr, "Recompressing file '%s'\n", name.c_str() ); if( destdir.size() && !make_dirs( rname ) ) - { show_file_error( rname.c_str(), "Error creating intermediate directory." ); - return 2; } + { show_file_error( rname.c_str(), + "Error creating intermediate directory", errno ); return 2; } int fda[2]; // pipe between decompressor and compressor if( pipe( fda ) < 0 ) { show_error( "Can't create pipe", errno ); return 2; } @@ -465,7 +463,7 @@ int main( const int argc, const char * const argv[] ) case lz_opt: parse_compressor( arg, pn, fmt_lz, 1 ); break; case xz_opt: parse_compressor( arg, pn, fmt_xz, 1 ); break; case zst_opt: parse_compressor( arg, pn, fmt_zst, 1 ); break; - default : internal_error( "uncaught option." ); + default: internal_error( "uncaught option." ); } } // end process options @@ -244,7 +244,7 @@ bool set_data_feeder( const std::string & filename, int * const infdp, } -// Return format_index, or -1 if uncompressed. +// Return format_index, or -1 if uncompressed or shorter than magic_buf_size. // int test_format( const int infd, uint8_t magic_data[], int * const magic_sizep ) @@ -269,22 +269,24 @@ int test_format( const int infd, uint8_t magic_data[], { 0x28, 0xB5, 0x2F, 0xFD }; // 0xFD2FB528 LE *magic_sizep = readblock( infd, magic_data, magic_buf_size ); - if( *magic_sizep == magic_buf_size ) // test formats in search order - { - if( std::memcmp( magic_data, lzip_magic, lzip_magic_size ) == 0 && - isvalid_ds( magic_data[lzip_magic_size] ) ) - return fmt_lz; - if( std::memcmp( magic_data, bzip2_magic, bzip2_magic_size ) == 0 && - magic_data[3] >= '1' && magic_data[3] <= '9' && - std::memcmp( magic_data + 4, "1AY&SY", 6 ) == 0 ) - return fmt_bz2; - if( std::memcmp( magic_data, gzip_magic, gzip_magic_size ) == 0 || - std::memcmp( magic_data, compress_magic, compress_magic_size ) == 0 ) - return fmt_gz; - if( std::memcmp( magic_data, zstd_magic, zstd_magic_size ) == 0 ) - return fmt_zst; - if( std::memcmp( magic_data, xz_magic, xz_magic_size ) == 0 ) - return fmt_xz; - } + if( *magic_sizep < magic_buf_size ) + { if( errno ) return -1; // read error + for( int i = *magic_sizep; i < magic_buf_size; ++i ) magic_data[i] = 0; } + // test formats in search order + if( std::memcmp( magic_data, lzip_magic, lzip_magic_size ) == 0 && + isvalid_ds( magic_data[lzip_magic_size] ) ) + return fmt_lz; + if( std::memcmp( magic_data, bzip2_magic, bzip2_magic_size ) == 0 && + magic_data[3] >= '1' && magic_data[3] <= '9' && + ( std::memcmp( magic_data + 4, "1AY&SY", 6 ) == 0 || + std::memcmp( magic_data + 4, "\x17rE8P\x90", 6 ) == 0 ) ) + return fmt_bz2; + if( std::memcmp( magic_data, gzip_magic, gzip_magic_size ) == 0 || + std::memcmp( magic_data, compress_magic, compress_magic_size ) == 0 ) + return fmt_gz; + if( std::memcmp( magic_data, zstd_magic, zstd_magic_size ) == 0 ) + return fmt_zst; + if( std::memcmp( magic_data, xz_magic, xz_magic_size ) == 0 ) + return fmt_xz; return -1; } diff --git a/zutils.conf b/zutils.conf index b642283..3dc4ef5 100644 --- a/zutils.conf +++ b/zutils.conf @@ -7,7 +7,7 @@ # XDG_CONFIG_HOME defaults to $HOME/.config # This file sets the compressor and options to be used for each format. -# The command line options override compressors specified in this file. +# The command-line options override compressors specified in this file. # Syntax: <format> = <compressor> [options] # Uncomment each line you want to take effect. |