bzip2.c: Check argc >= 1 && argv[0] != NULL

This should never happen, but if there is no, or a NULL argv[0] then
use a hard coded string "bzip2" when calling copyFileName to define
progNameReally.

https://sourceware.org/bugzilla/show_bug.cgi?id=33046

Makefile

@@ -135,7 +135,7 @@ bzip2recover.o: bzip2recover.c
 
 
 distclean: clean
-	rm -f manual.ps manual.html manual.pdf
+	rm -f manual.ps manual.html manual.pdf bzip2.txt bzip2.1.preformatted
 
 DISTNAME=bzip2-1.0.8
 dist: check manual
@@ -205,7 +205,13 @@ dist: check manual
 MANUAL_SRCS= 	bz-common.xsl bz-fo.xsl bz-html.xsl bzip.css \
 		entities.xml manual.xml 
 
-manual: manual.html manual.ps manual.pdf
+bzip2.txt: bzip2.1
+	MANWIDTH=67 man --ascii ./$^ > $@
+
+bzip2.1.preformatted: bzip2.1
+	MAN_KEEP_FORMATTING=1 MANWIDTH=67 man -E UTF-8 ./$^ > $@
+
+manual: manual.html manual.ps manual.pdf bzip2.txt bzip2.1.preformatted
 
 manual.ps: $(MANUAL_SRCS)
 	./xmlproc.sh -ps manual.xml

bzdiff.1

@@ -38,7 +38,12 @@ or
 .I diff
 is preserved.
 .SH "SEE ALSO"
-cmp(1), diff(1), bzmore(1), bzless(1), bzgrep(1), bzip2(1)
+.BR cmp (1),
+.BR diff (1),
+.BR bzmore (1),
+.BR bzless (1),
+.BR bzgrep (1),
+.BR bzip2 (1)
 .SH BUGS
 Messages from the
 .I cmp

bzgrep.1

@@ -53,4 +53,10 @@ program to be invoked. For example:
 Charles Levert (charles@comm.polymtl.ca). Adapted to bzip2 by Philippe
 Troin <phil@fifi.org> for Debian GNU/Linux.
 .SH "SEE ALSO"
-grep(1), egrep(1), fgrep(1), bzdiff(1), bzmore(1), bzless(1), bzip2(1)
+.BR grep (1),
+.BR egrep (1),
+.BR fgrep (1),
+.BR bzdiff (1),
+.BR bzmore (1),
+.BR bzless (1),
+.BR bzip2 (1)

bzip2.1

@@ -1,4 +1,3 @@
-.PU
 .TH bzip2 1
 .SH NAME
 bzip2, bunzip2 \- a block-sorting file compressor, v1.0.8
@@ -14,19 +13,28 @@ bzip2recover \- recovers data from damaged bzip2 files
 [
 .I "filenames \&..."
 ]
+.br
+.B bzip2
+.RB [ " \-h|\-\-help " ]
 .ll -8
 .br
 .B bunzip2
 .RB [ " \-fkvsVL " ]
-[ 
+[
+.I "filenames \&..."
+]
+.br
+.B bunzip2
+.RB [ " \-h|\-\-help " ]
+.br
+.B bzcat
+.RB [ " \-s " ]
+[
 .I "filenames \&..."
 ]
 .br
 .B bzcat
-.RB [ " \-s " ]
-[ 
-.I "filenames \&..."
-]
+.RB [ " \-h|\-\-help " ]
 .br
 .B bzip2recover
 .I "filename"
@@ -39,15 +47,15 @@ generally considerably better than that achieved by more conventional
 LZ77/LZ78-based compressors, and approaches the performance of the PPM
 family of statistical compressors.
 
-The command-line options are deliberately very similar to 
-those of 
-.I GNU gzip, 
+The command-line options are deliberately very similar to
+those of
+.I GNU gzip,
 but they are not identical.
 
 .I bzip2
 expects a list of file names to accompany the
 command-line flags.  Each file is replaced by a compressed version of
-itself, with the name "original_name.bz2".  
+itself, with the name "original_name.bz2".
 Each compressed file
 has the same modification date, permissions, and, when possible,
 ownership as the corresponding original, so that these properties can
@@ -74,13 +82,13 @@ incomprehensible and therefore pointless.
 
 .I bunzip2
 (or
-.I bzip2 \-d) 
+.I bzip2 \-d)
 decompresses all
-specified files.  Files which were not created by 
+specified files.  Files which were not created by
 .I bzip2
-will be detected and ignored, and a warning issued.  
+will be detected and ignored, and a warning issued.
 .I bzip2
-attempts to guess the filename for the decompressed file 
+attempts to guess the filename for the decompressed file
 from that of the compressed file as follows:
 
        filename.bz2    becomes   filename
@@ -89,13 +97,13 @@ from that of the compressed file as follows:
        filename.tbz    becomes   filename.tar
        anyothername    becomes   anyothername.out
 
-If the file does not end in one of the recognised endings, 
-.I .bz2, 
-.I .bz, 
+If the file does not end in one of the recognised endings,
+.I .bz2,
+.I .bz,
 .I .tbz2
 or
-.I .tbz, 
-.I bzip2 
+.I .tbz,
+.I bzip2
 complains that it cannot
 guess the name of the original file, and uses the original name
 with
@@ -103,25 +111,25 @@ with
 appended.
 
 As with compression, supplying no
-filenames causes decompression from 
+filenames causes decompression from
 standard input to standard output.
 
-.I bunzip2 
+.I bunzip2
 will correctly decompress a file which is the
 concatenation of two or more compressed files.  The result is the
 concatenation of the corresponding uncompressed files.  Integrity
-testing (\-t) 
-of concatenated 
+testing (\-t)
+of concatenated
 compressed files is also supported.
 
 You can also compress or decompress files to the standard output by
 giving the \-c flag.  Multiple files may be compressed and
 decompressed like this.  The resulting outputs are fed sequentially to
-stdout.  Compression of multiple files 
+stdout.  Compression of multiple files
 in this manner generates a stream
 containing multiple compressed file representations.  Such a stream
 can be decompressed correctly only by
-.I bzip2 
+.I bzip2
 version 0.9.0 or
 later.  Earlier versions of
 .I bzip2
@@ -130,7 +138,7 @@ the first file in the stream.
 
 .I bzcat
 (or
-.I bzip2 -dc) 
+.I bzip2 -dc)
 decompresses all specified files to
 the standard output.
 
@@ -140,10 +148,10 @@ will read arguments from the environment variables
 and
 .I BZIP,
 in that order, and will process them
-before any arguments read from the command line.  This gives a 
+before any arguments read from the command line.  This gives a
 convenient way to supply default arguments.
 
-Compression is always performed, even if the compressed 
+Compression is always performed, even if the compressed
 file is slightly
 larger than the original.  Files of less than about one hundred bytes
 tend to get larger, since the compression mechanism has a constant
@@ -151,9 +159,8 @@ overhead in the region of 50 bytes.  Random data (including the output
 of most file compressors) is coded at about 8.05 bits per byte, giving
 an expansion of around 0.5%.
 
-As a self-check for your protection, 
-.I 
-bzip2
+As a self-check for your protection,
+.I bzip2
 uses 32-bit CRCs to
 make sure that the decompressed version of a file is identical to the
 original.  This guards against corruption of the compressed data, and
@@ -163,9 +170,9 @@ against undetected bugs in
 chances of data corruption going undetected is microscopic, about one
 chance in four billion for each file processed.  Be aware, though, that
 the check occurs upon decompression, so it can only tell you that
-something is wrong.  It can't help you 
+something is wrong.  It can't help you
 recover the original uncompressed
-data.  You can use 
+data.  You can use
 .I bzip2recover
 to try to recover data from
 damaged files.
@@ -183,15 +190,15 @@ to panic.
 Compress or decompress to standard output.
 .TP
 .B \-d --decompress
-Force decompression.  
-.I bzip2, 
-.I bunzip2 
+Force decompression.
+.I bzip2,
+.I bunzip2
 and
-.I bzcat 
+.I bzcat
 are
 really the same program, and the decision about what actions to take is
 done on the basis of which name is used.  This flag overrides that
-mechanism, and forces 
+mechanism, and forces
 .I bzip2
 to decompress.
 .TP
@@ -205,10 +212,10 @@ This really performs a trial decompression and throws away the result.
 .TP
 .B \-f --force
 Force overwrite of output files.  Normally,
-.I bzip2 
+.I bzip2
 will not overwrite
-existing output files.  Also forces 
-.I bzip2 
+existing output files.  Also forces
+.I bzip2
 to break hard links
 to files, which it otherwise wouldn't do.
 
@@ -224,9 +231,9 @@ or decompression.
 Reduce memory usage, for compression, decompression and testing.  Files
 are decompressed and tested using a modified algorithm which only
 requires 2.5 bytes per block byte.  This means any file can be
-decompressed in 2300k of memory, albeit at about half the normal speed.
+decompressed in 2300\ k of memory, albeit at about half the normal speed.
 
-During compression, \-s selects a block size of 200k, which limits
+During compression, \-s selects a block size of 200\ k, which limits
 memory use to around the same figure, at the expense of your compression
 ratio.  In short, if your machine is low on memory (8 megabytes or
 less), use \-s for everything.  See MEMORY MANAGEMENT below.
@@ -240,15 +247,18 @@ Verbose mode -- show the compression ratio for each file processed.
 Further \-v's increase the verbosity level, spewing out lots of
 information which is primarily of interest for diagnostic purposes.
 .TP
+.B \-h \-\-help
+Print a help message and exit.
+.TP
 .B \-L --license -V --version
 Display the software version, license terms and conditions.
 .TP
 .B \-1 (or \-\-fast) to \-9 (or \-\-best)
-Set the block size to 100 k, 200 k ..  900 k when compressing.  Has no
+Set the block size to 100 k, 200 k ...  900 k when compressing.  Has no
 effect when decompressing.  See MEMORY MANAGEMENT below.
-The \-\-fast and \-\-best aliases are primarily for GNU gzip 
+The \-\-fast and \-\-best aliases are primarily for GNU gzip
 compatibility.  In particular, \-\-fast doesn't make things
-significantly faster.  
+significantly faster.
 And \-\-best merely selects the default behaviour.
 .TP
 .B \--
@@ -263,7 +273,7 @@ earlier versions, which was sometimes useful.  0.9.5 and above have an
 improved algorithm which renders these flags irrelevant.
 
 .SH MEMORY MANAGEMENT
-.I bzip2 
+.I bzip2
 compresses large files in blocks.  The block size affects
 both the compression ratio achieved, and the amount of memory needed for
 compression and decompression.  The flags \-1 through \-9
@@ -276,13 +286,13 @@ the file.  Since block sizes are stored in compressed files, it follows
 that the flags \-1 to \-9 are irrelevant to and so ignored
 during decompression.
 
-Compression and decompression requirements, 
+Compression and decompression requirements,
 in bytes, can be estimated as:
 
-       Compression:   400k + ( 8 x block size )
+       Compression:   400\ k + ( 8 x block size )
 
-       Decompression: 100k + ( 4 x block size ), or
-                      100k + ( 2.5 x block size )
+       Decompression: 100\ k + ( 4 x block size ), or
+                      100\ k + ( 2.5 x block size )
 
 Larger block sizes give rapidly diminishing marginal returns.  Most of
 the compression comes from the first two or three hundred k of block
@@ -292,10 +302,10 @@ on small machines.
 It is also important to appreciate that the decompression memory
 requirement is set at compression time by the choice of block size.
 
-For files compressed with the default 900k block size,
+For files compressed with the default 900\ k block size,
 .I bunzip2
 will require about 3700 kbytes to decompress.  To support decompression
-of any file on a 4 megabyte machine, 
+of any file on a 4 megabyte machine,
 .I bunzip2
 has an option to
 decompress using approximately half this amount of memory, about 2300
@@ -311,9 +321,9 @@ Another significant point applies to files which fit in a single block
 amount of real memory touched is proportional to the size of the file,
 since the file is smaller than a block.  For example, compressing a file
 20,000 bytes long with the flag -9 will cause the compressor to
-allocate around 7600k of memory, but only touch 400k + 20000 * 8 = 560
-kbytes of it.  Similarly, the decompressor will allocate 3700k but only
-touch 100k + 20000 * 4 = 180 kbytes.
+allocate around 7600\ k of memory, but only touch 400\ k + 20000 * 8 = 560
+kbytes of it.  Similarly, the decompressor will allocate 3700\ k but only
+touch 100\ k + 20000 * 4 = 180 kbytes.
 
 Here is a table which summarises the maximum memory usage for different
 block sizes.  Also recorded is the total compressed size for 14 files of
@@ -337,7 +347,7 @@ larger files, since the Corpus is dominated by smaller files.
 
 .SH RECOVERING DATA FROM DAMAGED FILES
 .I bzip2
-compresses files in blocks, usually 900kbytes long.  Each
+compresses files in blocks, usually 900\ kbytes long.  Each
 block is handled independently.  If a media or transmission error causes
 a multi-block .bz2
 file to become damaged, it may be possible to
@@ -350,36 +360,36 @@ damaged blocks can be distinguished from undamaged ones.
 
 .I bzip2recover
 is a simple program whose purpose is to search for
-blocks in .bz2 files, and write each block out into its own .bz2 
+blocks in .bz2 files, and write each block out into its own .bz2
 file.  You can then use
-.I bzip2 
+.I bzip2
 \-t
 to test the
 integrity of the resulting files, and decompress those which are
 undamaged.
 
 .I bzip2recover
-takes a single argument, the name of the damaged file, 
+takes a single argument, the name of the damaged file,
 and writes a number of files "rec00001file.bz2",
-"rec00002file.bz2", etc, containing the  extracted  blocks.
-The  output  filenames  are  designed  so  that the use of
-wildcards in subsequent processing -- for example,  
-"bzip2 -dc  rec*file.bz2 > recovered_data" -- processes the files in
+"rec00002file.bz2", etc., containing the  extracted  blocks.
+The output filenames are designed so that the use of
+wildcards in subsequent processing -- for example,
+"bzip2 -dc rec*file.bz2 > recovered_data" -- processes the files in
 the correct order.
 
 .I bzip2recover
 should be of most use dealing with large .bz2
-files,  as  these will contain many blocks.  It is clearly
-futile to use it on damaged single-block  files,  since  a
-damaged  block  cannot  be recovered.  If you wish to minimise 
-any potential data loss through media  or  transmission errors, 
+files, as these will contain many blocks.  It is clearly
+futile to use it on damaged single-block files, since a
+damaged block cannot be recovered.  If you wish to minimise
+any potential data loss through media or transmission errors,
 you might consider compressing with a smaller
 block size.
 
 .SH PERFORMANCE NOTES
 The sorting phase of compression gathers together similar strings in the
 file.  Because of this, files containing very long runs of repeated
-symbols, like "aabaabaabaab ..."  (repeated several hundred times) may
+symbols, like "aabaabaabaab ...\&" (repeated several hundred times) may
 compress more slowly than normal.  Versions 0.9.5 and above fare much
 better than previous versions in this respect.  The ratio between
 worst-case and average-case compression time is in the region of 10:1.
@@ -395,7 +405,7 @@ that performance, both for compressing and decompressing, is largely
 determined by the speed at which your machine can service cache misses.
 Because of this, small changes to the code to reduce the miss rate have
 been observed to give disproportionately large performance improvements.
-I imagine 
+I imagine
 .I bzip2
 will perform best on machines with very large caches.
 
@@ -406,7 +416,7 @@ tries hard to detect I/O errors and exit cleanly, but the details of
 what the problem is sometimes seem rather misleading.
 
 This manual page pertains to version 1.0.8 of
-.I bzip2.  
+.I bzip2.
 Compressed data created by this version is entirely forwards and
 backwards compatible with the previous public releases, versions
 0.1pl2, 0.9.0, 0.9.5, 1.0.0, 1.0.1, 1.0.2 and above, but with the following
@@ -440,13 +450,13 @@ Fenwick (for the structured coding model in the original
 .I bzip,
 and many refinements), and Alistair Moffat, Radford Neal and Ian Witten
 (for the arithmetic coder in the original
-.I bzip).  
+.I bzip).
 I am much
 indebted for their help, support and advice.  See the manual in the
 source distribution for pointers to sources of documentation.  Christian
 von Roques encouraged me to look for faster sorting algorithms, so as to
 speed up compression.  Bela Lubkin encouraged me to improve the
-worst-case compression performance.  
+worst-case compression performance.
 Donna Robinson XMLised the documentation.
 The bz* scripts are derived from those of GNU gzip.
 Many people sent patches, helped

bzip2.1.preformatted

@@ -1,399 +0,0 @@
-bzip2(1)                                                 bzip2(1)
-
-
-
-NNAAMMEE
-       bzip2, bunzip2 − a block‐sorting file compressor, v1.0.8
-       bzcat − decompresses files to stdout
-       bzip2recover − recovers data from damaged bzip2 files
-
-
-SSYYNNOOPPSSIISS
-       bbzziipp22 [ −−ccddffkkqqssttvvzzVVLL112233445566778899 ] [ _f_i_l_e_n_a_m_e_s _._._.  ]
-       bbuunnzziipp22 [ −−ffkkvvssVVLL ] [ _f_i_l_e_n_a_m_e_s _._._.  ]
-       bbzzccaatt [ −−ss ] [ _f_i_l_e_n_a_m_e_s _._._.  ]
-       bbzziipp22rreeccoovveerr _f_i_l_e_n_a_m_e
-
-
-DDEESSCCRRIIPPTTIIOONN
-       _b_z_i_p_2  compresses  files  using  the Burrows‐Wheeler block
-       sorting text compression algorithm,  and  Huffman  coding.
-       Compression  is  generally  considerably  better than that
-       achieved by more conventional LZ77/LZ78‐based compressors,
-       and  approaches  the performance of the PPM family of sta­
-       tistical compressors.
-
-       The command‐line options are deliberately very similar  to
-       those of _G_N_U _g_z_i_p_, but they are not identical.
-
-       _b_z_i_p_2  expects  a list of file names to accompany the com­
-       mand‐line flags.  Each file is replaced  by  a  compressed
-       version  of  itself,  with  the  name "original_name.bz2".
-       Each compressed file has the same modification date,  per­
-       missions, and, when possible, ownership as the correspond­
-       ing original, so that these properties  can  be  correctly
-       restored  at  decompression  time.   File name handling is
-       naive in the sense that there is no mechanism for preserv­
-       ing  original file names, permissions, ownerships or dates
-       in filesystems which lack these concepts, or have  serious
-       file name length restrictions, such as MS‐DOS.
-
-       _b_z_i_p_2  and  _b_u_n_z_i_p_2 will by default not overwrite existing
-       files.  If you want this to happen, specify the −f flag.
-
-       If no file names  are  specified,  _b_z_i_p_2  compresses  from
-       standard  input  to  standard output.  In this case, _b_z_i_p_2
-       will decline to write compressed output to a terminal,  as
-       this  would  be  entirely  incomprehensible  and therefore
-       pointless.
-
-       _b_u_n_z_i_p_2 (or _b_z_i_p_2 _−_d_) decompresses  all  specified  files.
-       Files which were not created by _b_z_i_p_2 will be detected and
-       ignored, and a warning issued.  _b_z_i_p_2  attempts  to  guess
-       the  filename  for  the decompressed file from that of the
-       compressed file as follows:
-
-              filename.bz2    becomes   filename
-              filename.bz     becomes   filename
-              filename.tbz2   becomes   filename.tar
-              filename.tbz    becomes   filename.tar
-              anyothername    becomes   anyothername.out
-
-       If the file does not end in one of the recognised endings,
-       _._b_z_2_,  _._b_z_,  _._t_b_z_2 or _._t_b_z_, _b_z_i_p_2 complains that it cannot
-       guess the name of the original file, and uses the original
-       name with _._o_u_t appended.
-
-       As  with compression, supplying no filenames causes decom­
-       pression from standard input to standard output.
-
-       _b_u_n_z_i_p_2 will correctly decompress a file which is the con­
-       catenation of two or more compressed files.  The result is
-       the concatenation of the corresponding uncompressed files.
-       Integrity testing (−t) of concatenated compressed files is
-       also supported.
-
-       You can also compress or decompress files to the  standard
-       output  by giving the −c flag.  Multiple files may be com­
-       pressed and decompressed like this.  The resulting outputs
-       are  fed  sequentially to stdout.  Compression of multiple
-       files in this manner generates a stream containing  multi­
-       ple compressed file representations.  Such a stream can be
-       decompressed correctly only  by  _b_z_i_p_2  version  0.9.0  or
-       later.   Earlier  versions of _b_z_i_p_2 will stop after decom­
-       pressing the first file in the stream.
-
-       _b_z_c_a_t (or _b_z_i_p_2 _‐_d_c_) decompresses all specified  files  to
-       the standard output.
-
-       _b_z_i_p_2  will  read arguments from the environment variables
-       _B_Z_I_P_2 and _B_Z_I_P_, in  that  order,  and  will  process  them
-       before  any  arguments  read  from the command line.  This
-       gives a convenient way to supply default arguments.
-
-       Compression is always performed, even  if  the  compressed
-       file  is slightly larger than the original.  Files of less
-       than about one hundred bytes tend to get larger, since the
-       compression  mechanism  has  a  constant  overhead  in the
-       region of 50 bytes.  Random data (including the output  of
-       most  file  compressors)  is  coded at about 8.05 bits per
-       byte, giving an expansion of around 0.5%.
-
-       As a self‐check for your  protection,  _b_z_i_p_2  uses  32‐bit
-       CRCs  to make sure that the decompressed version of a file
-       is identical to the original.  This guards against corrup­
-       tion  of  the compressed data, and against undetected bugs
-       in _b_z_i_p_2 (hopefully very unlikely).  The chances  of  data
-       corruption  going  undetected  is  microscopic,  about one
-       chance in four billion for each file processed.  Be aware,
-       though,  that  the  check occurs upon decompression, so it
-       can only tell you that something is wrong.  It can’t  help
-       you  recover  the original uncompressed data.  You can use
-       _b_z_i_p_2_r_e_c_o_v_e_r to try to recover data from damaged files.
-
-       Return values: 0 for a normal exit,  1  for  environmental
-       problems  (file not found, invalid flags, I/O errors, &c),
-       2 to indicate a corrupt compressed file, 3 for an internal
-       consistency error (eg, bug) which caused _b_z_i_p_2 to panic.
-
-
-OOPPTTIIOONNSS
-       −−cc ‐‐‐‐ssttddoouutt
-              Compress or decompress to standard output.
-
-       −−dd ‐‐‐‐ddeeccoommpprreessss
-              Force  decompression.  _b_z_i_p_2_, _b_u_n_z_i_p_2 and _b_z_c_a_t are
-              really the same program,  and  the  decision  about
-              what  actions to take is done on the basis of which
-              name is used.  This flag overrides that  mechanism,
-              and forces _b_z_i_p_2 to decompress.
-
-       −−zz ‐‐‐‐ccoommpprreessss
-              The   complement   to   −d:   forces   compression,
-              regardless of the invocation name.
-
-       −−tt ‐‐‐‐tteesstt
-              Check integrity of the specified file(s), but don’t
-              decompress  them.   This  really  performs  a trial
-              decompression and throws away the result.
-
-       −−ff ‐‐‐‐ffoorrccee
-              Force overwrite of output files.   Normally,  _b_z_i_p_2
-              will  not  overwrite  existing  output files.  Also
-              forces _b_z_i_p_2 to break hard links to files, which it
-              otherwise wouldn’t do.
-
-              bzip2  normally  declines to decompress files which
-              don’t have the  correct  magic  header  bytes.   If
-              forced  (‐f),  however,  it  will  pass  such files
-              through unmodified.  This is how GNU gzip  behaves.
-
-       −−kk ‐‐‐‐kkeeeepp
-              Keep  (don’t delete) input files during compression
-              or decompression.
-
-       −−ss ‐‐‐‐ssmmaallll
-              Reduce memory usage, for compression, decompression
-              and  testing.   Files  are  decompressed and tested
-              using a modified algorithm which only requires  2.5
-              bytes  per  block byte.  This means any file can be
-              decompressed in 2300k of memory,  albeit  at  about
-              half the normal speed.
-
-              During  compression,  −s  selects  a  block size of
-              200k, which limits memory use to  around  the  same
-              figure,  at  the expense of your compression ratio.
-              In short, if your  machine  is  low  on  memory  (8
-              megabytes  or  less),  use  −s for everything.  See
-              MEMORY MANAGEMENT below.
-
-       −−qq ‐‐‐‐qquuiieett
-              Suppress non‐essential warning messages.   Messages
-              pertaining  to I/O errors and other critical events
-              will not be suppressed.
-
-       −−vv ‐‐‐‐vveerrbboossee
-              Verbose mode ‐‐ show the compression ratio for each
-              file  processed.   Further  −v’s  increase the ver­
-              bosity level, spewing out lots of information which
-              is primarily of interest for diagnostic purposes.
-
-       −−LL ‐‐‐‐lliicceennssee ‐‐VV ‐‐‐‐vveerrssiioonn
-              Display  the  software  version,  license terms and
-              conditions.
-
-       −−11 ((oorr −−−−ffaasstt)) ttoo −−99 ((oorr −−−−bbeesstt))
-              Set the block size to 100 k, 200 k ..  900  k  when
-              compressing.   Has  no  effect  when decompressing.
-              See MEMORY MANAGEMENT below.  The −−fast and −−best
-              aliases  are  primarily for GNU gzip compatibility.
-              In particular, −−fast doesn’t make things  signifi­
-              cantly  faster.   And  −−best  merely  selects  the
-              default behaviour.
-
-       −−‐‐     Treats all subsequent arguments as file names, even
-              if they start with a dash.  This is so you can han­
-              dle files with names beginning  with  a  dash,  for
-              example: bzip2 −‐ −myfilename.
-
-       −−‐‐rreeppeettiittiivvee‐‐ffaasstt ‐‐‐‐rreeppeettiittiivvee‐‐bbeesstt
-              These  flags  are  redundant  in versions 0.9.5 and
-              above.  They provided some coarse control over  the
-              behaviour  of the sorting algorithm in earlier ver­
-              sions, which was sometimes useful.  0.9.5 and above
-              have  an  improved  algorithm  which  renders these
-              flags irrelevant.
-
-
-MMEEMMOORRYY MMAANNAAGGEEMMEENNTT
-       _b_z_i_p_2 compresses large files in blocks.   The  block  size
-       affects  both  the  compression  ratio  achieved,  and the
-       amount of memory needed for compression and decompression.
-       The  flags  −1  through  −9  specify  the block size to be
-       100,000 bytes through 900,000 bytes (the default)  respec­
-       tively.   At  decompression  time, the block size used for
-       compression is read from  the  header  of  the  compressed
-       file, and _b_u_n_z_i_p_2 then allocates itself just enough memory
-       to decompress the file.  Since block sizes are  stored  in
-       compressed  files,  it follows that the flags −1 to −9 are
-       irrelevant to and so ignored during decompression.
-
-       Compression and decompression requirements, in bytes,  can
-       be estimated as:
-
-              Compression:   400k + ( 8 x block size )
-
-              Decompression: 100k + ( 4 x block size ), or
-                             100k + ( 2.5 x block size )
-
-       Larger  block  sizes  give  rapidly  diminishing  marginal
-       returns.  Most of the compression comes from the first two
-       or  three hundred k of block size, a fact worth bearing in
-       mind when using _b_z_i_p_2  on  small  machines.   It  is  also
-       important  to  appreciate  that  the  decompression memory
-       requirement is set at compression time by  the  choice  of
-       block size.
-
-       For  files  compressed  with  the default 900k block size,
-       _b_u_n_z_i_p_2 will require about 3700 kbytes to decompress.   To
-       support decompression of any file on a 4 megabyte machine,
-       _b_u_n_z_i_p_2 has an option to  decompress  using  approximately
-       half this amount of memory, about 2300 kbytes.  Decompres­
-       sion speed is also halved, so you should use  this  option
-       only where necessary.  The relevant flag is ‐s.
-
-       In general, try and use the largest block size memory con­
-       straints  allow,  since  that  maximises  the  compression
-       achieved.   Compression and decompression speed are virtu­
-       ally unaffected by block size.
-
-       Another significant point applies to files which fit in  a
-       single  block  ‐‐  that  means  most files you’d encounter
-       using a large block  size.   The  amount  of  real  memory
-       touched is proportional to the size of the file, since the
-       file is smaller than a block.  For example, compressing  a
-       file  20,000  bytes  long  with the flag ‐9 will cause the
-       compressor to allocate around 7600k of  memory,  but  only
-       touch 400k + 20000 * 8 = 560 kbytes of it.  Similarly, the
-       decompressor will allocate 3700k but  only  touch  100k  +
-       20000 * 4 = 180 kbytes.
-
-       Here  is a table which summarises the maximum memory usage
-       for different block sizes.  Also  recorded  is  the  total
-       compressed  size for 14 files of the Calgary Text Compres­
-       sion Corpus totalling 3,141,622 bytes.  This column  gives
-       some  feel  for  how  compression  varies with block size.
-       These figures tend to understate the advantage  of  larger
-       block  sizes  for  larger files, since the Corpus is domi­
-       nated by smaller files.
-
-                  Compress   Decompress   Decompress   Corpus
-           Flag     usage      usage       ‐s usage     Size
-
-            ‐1      1200k       500k         350k      914704
-            ‐2      2000k       900k         600k      877703
-            ‐3      2800k      1300k         850k      860338
-            ‐4      3600k      1700k        1100k      846899
-            ‐5      4400k      2100k        1350k      845160
-            ‐6      5200k      2500k        1600k      838626
-            ‐7      6100k      2900k        1850k      834096
-            ‐8      6800k      3300k        2100k      828642
-            ‐9      7600k      3700k        2350k      828642
-
-
-RREECCOOVVEERRIINNGG DDAATTAA FFRROOMM DDAAMMAAGGEEDD FFIILLEESS
-       _b_z_i_p_2 compresses files in blocks, usually 900kbytes  long.
-       Each block is handled independently.  If a media or trans­
-       mission error causes a multi‐block  .bz2  file  to  become
-       damaged,  it  may  be  possible  to  recover data from the
-       undamaged blocks in the file.
-
-       The compressed representation of each block  is  delimited
-       by  a  48‐bit pattern, which makes it possible to find the
-       block boundaries with reasonable  certainty.   Each  block
-       also  carries its own 32‐bit CRC, so damaged blocks can be
-       distinguished from undamaged ones.
-
-       _b_z_i_p_2_r_e_c_o_v_e_r is a  simple  program  whose  purpose  is  to
-       search  for blocks in .bz2 files, and write each block out
-       into its own .bz2 file.  You can then use _b_z_i_p_2 −t to test
-       the integrity of the resulting files, and decompress those
-       which are undamaged.
-
-       _b_z_i_p_2_r_e_c_o_v_e_r takes a single argument, the name of the dam­
-       aged    file,    and    writes    a    number   of   files
-       "rec00001file.bz2",  "rec00002file.bz2",  etc,  containing
-       the   extracted   blocks.   The   output   filenames   are
-       designed  so  that the use of wildcards in subsequent pro­
-       cessing  ‐‐ for example, "bzip2 ‐dc  rec*file.bz2 > recov­
-       ered_data" ‐‐ processes the files in the correct order.
-
-       _b_z_i_p_2_r_e_c_o_v_e_r should be of most use dealing with large .bz2
-       files,  as  these will contain many blocks.  It is clearly
-       futile to use it on damaged single‐block  files,  since  a
-       damaged  block  cannot  be recovered.  If you wish to min­
-       imise any potential data loss through media  or  transmis­
-       sion errors, you might consider compressing with a smaller
-       block size.
-
-
-PPEERRFFOORRMMAANNCCEE NNOOTTEESS
-       The sorting phase of compression gathers together  similar
-       strings  in  the  file.  Because of this, files containing
-       very long runs of  repeated  symbols,  like  "aabaabaabaab
-       ..."   (repeated  several hundred times) may compress more
-       slowly than normal.  Versions 0.9.5 and  above  fare  much
-       better  than previous versions in this respect.  The ratio
-       between worst‐case and average‐case compression time is in
-       the  region  of  10:1.  For previous versions, this figure
-       was more like 100:1.  You can use the −vvvv option to mon­
-       itor progress in great detail, if you want.
-
-       Decompression speed is unaffected by these phenomena.
-
-       _b_z_i_p_2  usually  allocates  several  megabytes of memory to
-       operate in, and then charges all over it in a fairly  ran­
-       dom  fashion.   This means that performance, both for com­
-       pressing and decompressing, is largely determined  by  the
-       speed  at  which  your  machine  can service cache misses.
-       Because of this, small changes to the code to  reduce  the
-       miss  rate  have  been observed to give disproportionately
-       large performance improvements.  I imagine _b_z_i_p_2 will per­
-       form best on machines with very large caches.
-
-
-CCAAVVEEAATTSS
-       I/O  error  messages  are not as helpful as they could be.
-       _b_z_i_p_2 tries hard to detect I/O errors  and  exit  cleanly,
-       but  the  details  of  what  the problem is sometimes seem
-       rather misleading.
-
-       This manual page pertains to version 1.0.8 of _b_z_i_p_2_.  Com­
-       pressed  data created by this version is entirely forwards
-       and  backwards  compatible  with   the   previous   public
-       releases,  versions  0.1pl2,  0.9.0,  0.9.5, 1.0.0, 1.0.1, 
-       1.0.2 and above, but with the  following  exception: 0.9.0
-       and above can  correctly decompress  multiple concatenated
-       compressed files.  0.1pl2  cannot do this;  it  will  stop 
-       after  decompressing just the first file in the stream.
-
-       _b_z_i_p_2_r_e_c_o_v_e_r  versions prior to 1.0.2 used 32‐bit integers
-       to represent bit positions in compressed  files,  so  they
-       could  not handle compressed files more than 512 megabytes
-       long.  Versions 1.0.2 and above use 64‐bit  ints  on  some
-       platforms  which  support them (GNU supported targets, and
-       Windows).  To establish whether or  not  bzip2recover  was
-       built  with  such  a limitation, run it without arguments.
-       In any event you can build yourself an  unlimited  version
-       if  you  can  recompile  it  with MaybeUInt64 set to be an
-       unsigned 64‐bit integer.
-
-
-
-
-AAUUTTHHOORR
-       Julian Seward, jseward@acm.org.
-
-       https://sourceware.org/bzip2/
-
-       The ideas embodied in _b_z_i_p_2 are due to (at least) the fol­
-       lowing  people: Michael Burrows and David Wheeler (for the
-       block sorting transformation), David Wheeler  (again,  for
-       the Huffman coder), Peter Fenwick (for the structured cod­
-       ing model in the original _b_z_i_p_, and many refinements), and
-       Alistair  Moffat,  Radford  Neal  and  Ian Witten (for the
-       arithmetic  coder  in  the  original  _b_z_i_p_)_.   I  am  much
-       indebted for their help, support and advice.  See the man­
-       ual in the source distribution for pointers to sources  of
-       documentation.  Christian von Roques encouraged me to look
-       for faster sorting algorithms, so as to speed up  compres­
-       sion.  Bela Lubkin encouraged me to improve the worst‐case
-       compression performance.  Donna Robinson XMLised the docu­
-       mentation.   The bz* scripts are derived from those of GNU
-       gzip.  Many people sent patches, helped  with  portability
-       problems,  lent  machines,  gave advice and were generally
-       helpful.
-
-
-
-                                                         bzip2(1)

bzip2.c

@@ -150,6 +150,8 @@
          ERROR_IF_MINUS_ONE ( retVal );               \
       } while ( 0 )
 
+#   define STDERR_FILENO _fileno(stderr)
+
 #endif /* BZ_LCCWIN32 */
 
 
@@ -815,10 +817,9 @@ void mySignalCatcher ( IntNative n )
 static 
 void mySIGSEGVorSIGBUScatcher ( IntNative n )
 {
+   const char *msg;
    if (opMode == OM_Z)
-      fprintf ( 
-      stderr,
-      "\n%s: Caught a SIGSEGV or SIGBUS whilst compressing.\n"
+      msg = ": Caught a SIGSEGV or SIGBUS whilst compressing.\n"
       "\n"
       "   Possible causes are (most likely first):\n"
       "   (1) This computer has unreliable memory or cache hardware\n"
@@ -834,12 +835,9 @@ void mySIGSEGVorSIGBUScatcher ( IntNative n )
       "   bug report should have.  If the manual is available on your\n"
       "   system, please try and read it before mailing me.  If you don't\n"
       "   have the manual or can't be bothered to read it, mail me anyway.\n"
-      "\n",
-      progName );
-      else
-      fprintf ( 
-      stderr,
-      "\n%s: Caught a SIGSEGV or SIGBUS whilst decompressing.\n"
+      "\n";
+   else
+      msg = ": Caught a SIGSEGV or SIGBUS whilst decompressing.\n"
       "\n"
       "   Possible causes are (most likely first):\n"
       "   (1) The compressed data is corrupted, and bzip2's usual checks\n"
@@ -857,13 +855,25 @@ void mySIGSEGVorSIGBUScatcher ( IntNative n )
       "   bug report should have.  If the manual is available on your\n"
       "   system, please try and read it before mailing me.  If you don't\n"
       "   have the manual or can't be bothered to read it, mail me anyway.\n"
-      "\n",
-      progName );
+      "\n";
+   write ( STDERR_FILENO, "\n", 1 );
+   write ( STDERR_FILENO, progName, strlen ( progName ) );
+   write ( STDERR_FILENO, msg, strlen ( msg ) );
 
-   showFileNames();
-   if (opMode == OM_Z)
-      cleanUpAndFail( 3 ); else
-      { cadvise(); cleanUpAndFail( 2 ); }
+   msg = "\tInput file = ";
+   write ( STDERR_FILENO, msg, strlen (msg) );
+   write ( STDERR_FILENO, inName, strlen (inName) );
+   write ( STDERR_FILENO, "\n", 1 );
+   msg = "\tOutput file = ";
+   write ( STDERR_FILENO, msg, strlen (msg) );
+   write ( STDERR_FILENO, outName, strlen (outName) );
+   write ( STDERR_FILENO, "\n", 1 );
+
+   /* Don't call cleanupAndFail. If we ended up here something went
+      terribly wrong. Trying to clean up might fail spectacularly. */
+
+   if (opMode == OM_Z) setExit(3); else setExit(2);
+   _exit(exitValue);
 }
 
 
@@ -1757,8 +1767,8 @@ void addFlagsFromEnvVar ( Cell** argList, Char* varName )
          if (p[i] == 0) break;
          p += i;
          i = 0;
-         while (isspace((Int32)(p[0]))) p++;
-         while (p[i] != 0 && !isspace((Int32)(p[i]))) i++;
+         while (isspace((UChar)(p[0]))) p++;
+         while (p[i] != 0 && !isspace((UChar)(p[i]))) i++;
          if (i > 0) {
             k = i; if (k > FILE_NAME_LEN-10) k = FILE_NAME_LEN-10;
             for (j = 0; j < k; j++) tmpName[j] = p[j];
@@ -1815,7 +1825,11 @@ IntNative main ( IntNative argc, Char *argv[] )
    copyFileName ( inName,  (Char*)"(none)" );
    copyFileName ( outName, (Char*)"(none)" );
 
-   copyFileName ( progNameReally, argv[0] );
+   if (argc >= 1 && argv[0] != NULL)
+      copyFileName ( progNameReally, argv[0] );
+   else
+      copyFileName ( progNameReally, (Char*)"bzip2" );
+
    progName = &progNameReally[0];
    for (tmp = &progNameReally[0]; *tmp != '\0'; tmp++)
       if (*tmp == PATH_SEP) progName = tmp + 1;

bzip2.txt

@@ -1,391 +0,0 @@
-
-NAME
-       bzip2, bunzip2 - a block-sorting file compressor, v1.0.8
-       bzcat - decompresses files to stdout
-       bzip2recover - recovers data from damaged bzip2 files
-
-
-SYNOPSIS
-       bzip2 [ -cdfkqstvzVL123456789 ] [ filenames ...  ]
-       bunzip2 [ -fkvsVL ] [ filenames ...  ]
-       bzcat [ -s ] [ filenames ...  ]
-       bzip2recover filename
-
-
-DESCRIPTION
-       bzip2  compresses  files  using  the Burrows-Wheeler block
-       sorting text compression algorithm,  and  Huffman  coding.
-       Compression  is  generally  considerably  better than that
-       achieved by more conventional LZ77/LZ78-based compressors,
-       and  approaches  the performance of the PPM family of sta-
-       tistical compressors.
-
-       The command-line options are deliberately very similar  to
-       those of GNU gzip, but they are not identical.
-
-       bzip2  expects  a list of file names to accompany the com-
-       mand-line flags.  Each file is replaced  by  a  compressed
-       version  of  itself,  with  the  name "original_name.bz2".
-       Each compressed file has the same modification date,  per-
-       missions, and, when possible, ownership as the correspond-
-       ing original, so that these properties  can  be  correctly
-       restored  at  decompression  time.   File name handling is
-       naive in the sense that there is no mechanism for preserv-
-       ing  original file names, permissions, ownerships or dates
-       in filesystems which lack these concepts, or have  serious
-       file name length restrictions, such as MS-DOS.
-
-       bzip2  and  bunzip2 will by default not overwrite existing
-       files.  If you want this to happen, specify the -f flag.
-
-       If no file names  are  specified,  bzip2  compresses  from
-       standard  input  to  standard output.  In this case, bzip2
-       will decline to write compressed output to a terminal,  as
-       this  would  be  entirely  incomprehensible  and therefore
-       pointless.
-
-       bunzip2 (or bzip2 -d) decompresses  all  specified  files.
-       Files which were not created by bzip2 will be detected and
-       ignored, and a warning issued.  bzip2  attempts  to  guess
-       the  filename  for  the decompressed file from that of the
-       compressed file as follows:
-
-              filename.bz2    becomes   filename
-              filename.bz     becomes   filename
-              filename.tbz2   becomes   filename.tar
-              filename.tbz    becomes   filename.tar
-              anyothername    becomes   anyothername.out
-
-       If the file does not end in one of the recognised endings,
-       .bz2,  .bz,  .tbz2 or .tbz, bzip2 complains that it cannot
-       guess the name of the original file, and uses the original
-       name with .out appended.
-
-       As  with compression, supplying no filenames causes decom-
-       pression from standard input to standard output.
-
-       bunzip2 will correctly decompress a file which is the con-
-       catenation of two or more compressed files.  The result is
-       the concatenation of the corresponding uncompressed files.
-       Integrity testing (-t) of concatenated compressed files is
-       also supported.
-
-       You can also compress or decompress files to the  standard
-       output  by giving the -c flag.  Multiple files may be com-
-       pressed and decompressed like this.  The resulting outputs
-       are  fed  sequentially to stdout.  Compression of multiple
-       files in this manner generates a stream containing  multi-
-       ple compressed file representations.  Such a stream can be
-       decompressed correctly only  by  bzip2  version  0.9.0  or
-       later.   Earlier  versions of bzip2 will stop after decom-
-       pressing the first file in the stream.
-
-       bzcat (or bzip2 -dc) decompresses all specified  files  to
-       the standard output.
-
-       bzip2  will  read arguments from the environment variables
-       BZIP2 and BZIP, in  that  order,  and  will  process  them
-       before  any  arguments  read  from the command line.  This
-       gives a convenient way to supply default arguments.
-
-       Compression is always performed, even  if  the  compressed
-       file  is slightly larger than the original.  Files of less
-       than about one hundred bytes tend to get larger, since the
-       compression  mechanism  has  a  constant  overhead  in the
-       region of 50 bytes.  Random data (including the output  of
-       most  file  compressors)  is  coded at about 8.05 bits per
-       byte, giving an expansion of around 0.5%.
-
-       As a self-check for your  protection,  bzip2  uses  32-bit
-       CRCs  to make sure that the decompressed version of a file
-       is identical to the original.  This guards against corrup-
-       tion  of  the compressed data, and against undetected bugs
-       in bzip2 (hopefully very unlikely).  The chances  of  data
-       corruption  going  undetected  is  microscopic,  about one
-       chance in four billion for each file processed.  Be aware,
-       though,  that  the  check occurs upon decompression, so it
-       can only tell you that something is wrong.  It can't  help
-       you  recover  the original uncompressed data.  You can use
-       bzip2recover to try to recover data from damaged files.
-
-       Return values: 0 for a normal exit,  1  for  environmental
-       problems  (file not found, invalid flags, I/O errors, &c),
-       2 to indicate a corrupt compressed file, 3 for an internal
-       consistency error (eg, bug) which caused bzip2 to panic.
-
-
-OPTIONS
-       -c --stdout
-              Compress or decompress to standard output.
-
-       -d --decompress
-              Force  decompression.  bzip2, bunzip2 and bzcat are
-              really the same program,  and  the  decision  about
-              what  actions to take is done on the basis of which
-              name is used.  This flag overrides that  mechanism,
-              and forces bzip2 to decompress.
-
-       -z --compress
-              The   complement   to   -d:   forces   compression,
-              regardless of the invocation name.
-
-       -t --test
-              Check integrity of the specified file(s), but don't
-              decompress  them.   This  really  performs  a trial
-              decompression and throws away the result.
-
-       -f --force
-              Force overwrite of output files.   Normally,  bzip2
-              will  not  overwrite  existing  output files.  Also
-              forces bzip2 to break hard links to files, which it
-              otherwise wouldn't do.
-
-              bzip2  normally  declines to decompress files which
-              don't have the  correct  magic  header  bytes.   If
-              forced  (-f),  however,  it  will  pass  such files
-              through unmodified.  This is how GNU gzip  behaves.
-
-       -k --keep
-              Keep  (don't delete) input files during compression
-              or decompression.
-
-       -s --small
-              Reduce memory usage, for compression, decompression
-              and  testing.   Files  are  decompressed and tested
-              using a modified algorithm which only requires  2.5
-              bytes  per  block byte.  This means any file can be
-              decompressed in 2300k of memory,  albeit  at  about
-              half the normal speed.
-
-              During  compression,  -s  selects  a  block size of
-              200k, which limits memory use to  around  the  same
-              figure,  at  the expense of your compression ratio.
-              In short, if your  machine  is  low  on  memory  (8
-              megabytes  or  less),  use  -s for everything.  See
-              MEMORY MANAGEMENT below.
-
-       -q --quiet
-              Suppress non-essential warning messages.   Messages
-              pertaining  to I/O errors and other critical events
-              will not be suppressed.
-
-       -v --verbose
-              Verbose mode -- show the compression ratio for each
-              file  processed.   Further  -v's  increase the ver-
-              bosity level, spewing out lots of information which
-              is primarily of interest for diagnostic purposes.
-
-       -L --license -V --version
-              Display  the  software  version,  license terms and
-              conditions.
-
-       -1 (or --fast) to -9 (or --best)
-              Set the block size to 100 k, 200 k ..  900  k  when
-              compressing.   Has  no  effect  when decompressing.
-              See MEMORY MANAGEMENT below.  The --fast and --best
-              aliases  are  primarily for GNU gzip compatibility.
-              In particular, --fast doesn't make things  signifi-
-              cantly  faster.   And  --best  merely  selects  the
-              default behaviour.
-
-       --     Treats all subsequent arguments as file names, even
-              if they start with a dash.  This is so you can han-
-              dle files with names beginning  with  a  dash,  for
-              example: bzip2 -- -myfilename.
-
-       --repetitive-fast --repetitive-best
-              These  flags  are  redundant  in versions 0.9.5 and
-              above.  They provided some coarse control over  the
-              behaviour  of the sorting algorithm in earlier ver-
-              sions, which was sometimes useful.  0.9.5 and above
-              have  an  improved  algorithm  which  renders these
-              flags irrelevant.
-
-
-MEMORY MANAGEMENT
-       bzip2 compresses large files in blocks.   The  block  size
-       affects  both  the  compression  ratio  achieved,  and the
-       amount of memory needed for compression and decompression.
-       The  flags  -1  through  -9  specify  the block size to be
-       100,000 bytes through 900,000 bytes (the default)  respec-
-       tively.   At  decompression  time, the block size used for
-       compression is read from  the  header  of  the  compressed
-       file, and bunzip2 then allocates itself just enough memory
-       to decompress the file.  Since block sizes are  stored  in
-       compressed  files,  it follows that the flags -1 to -9 are
-       irrelevant to and so ignored during decompression.
-
-       Compression and decompression requirements, in bytes,  can
-       be estimated as:
-
-              Compression:   400k + ( 8 x block size )
-
-              Decompression: 100k + ( 4 x block size ), or
-                             100k + ( 2.5 x block size )
-
-       Larger  block  sizes  give  rapidly  diminishing  marginal
-       returns.  Most of the compression comes from the first two
-       or  three hundred k of block size, a fact worth bearing in
-       mind when using bzip2  on  small  machines.   It  is  also
-       important  to  appreciate  that  the  decompression memory
-       requirement is set at compression time by  the  choice  of
-       block size.
-
-       For  files  compressed  with  the default 900k block size,
-       bunzip2 will require about 3700 kbytes to decompress.   To
-       support decompression of any file on a 4 megabyte machine,
-       bunzip2 has an option to  decompress  using  approximately
-       half this amount of memory, about 2300 kbytes.  Decompres-
-       sion speed is also halved, so you should use  this  option
-       only where necessary.  The relevant flag is -s.
-
-       In general, try and use the largest block size memory con-
-       straints  allow,  since  that  maximises  the  compression
-       achieved.   Compression and decompression speed are virtu-
-       ally unaffected by block size.
-
-       Another significant point applies to files which fit in  a
-       single  block  --  that  means  most files you'd encounter
-       using a large block  size.   The  amount  of  real  memory
-       touched is proportional to the size of the file, since the
-       file is smaller than a block.  For example, compressing  a
-       file  20,000  bytes  long  with the flag -9 will cause the
-       compressor to allocate around 7600k of  memory,  but  only
-       touch 400k + 20000 * 8 = 560 kbytes of it.  Similarly, the
-       decompressor will allocate 3700k but  only  touch  100k  +
-       20000 * 4 = 180 kbytes.
-
-       Here  is a table which summarises the maximum memory usage
-       for different block sizes.  Also  recorded  is  the  total
-       compressed  size for 14 files of the Calgary Text Compres-
-       sion Corpus totalling 3,141,622 bytes.  This column  gives
-       some  feel  for  how  compression  varies with block size.
-       These figures tend to understate the advantage  of  larger
-       block  sizes  for  larger files, since the Corpus is domi-
-       nated by smaller files.
-
-                  Compress   Decompress   Decompress   Corpus
-           Flag     usage      usage       -s usage     Size
-
-            -1      1200k       500k         350k      914704
-            -2      2000k       900k         600k      877703
-            -3      2800k      1300k         850k      860338
-            -4      3600k      1700k        1100k      846899
-            -5      4400k      2100k        1350k      845160
-            -6      5200k      2500k        1600k      838626
-            -7      6100k      2900k        1850k      834096
-            -8      6800k      3300k        2100k      828642
-            -9      7600k      3700k        2350k      828642
-
-
-RECOVERING DATA FROM DAMAGED FILES
-       bzip2 compresses files in blocks, usually 900kbytes  long.
-       Each block is handled independently.  If a media or trans-
-       mission error causes a multi-block  .bz2  file  to  become
-       damaged,  it  may  be  possible  to  recover data from the
-       undamaged blocks in the file.
-
-       The compressed representation of each block  is  delimited
-       by  a  48-bit pattern, which makes it possible to find the
-       block boundaries with reasonable  certainty.   Each  block
-       also  carries its own 32-bit CRC, so damaged blocks can be
-       distinguished from undamaged ones.
-
-       bzip2recover is a  simple  program  whose  purpose  is  to
-       search  for blocks in .bz2 files, and write each block out
-       into its own .bz2 file.  You can then use bzip2 -t to test
-       the integrity of the resulting files, and decompress those
-       which are undamaged.
-
-       bzip2recover takes a single argument, the name of the dam-
-       aged    file,    and    writes    a    number   of   files
-       "rec00001file.bz2",  "rec00002file.bz2",  etc,  containing
-       the   extracted   blocks.   The   output   filenames   are
-       designed  so  that the use of wildcards in subsequent pro-
-       cessing  -- for example, "bzip2 -dc  rec*file.bz2 > recov-
-       ered_data" -- processes the files in the correct order.
-
-       bzip2recover should be of most use dealing with large .bz2
-       files,  as  these will contain many blocks.  It is clearly
-       futile to use it on damaged single-block  files,  since  a
-       damaged  block  cannot  be recovered.  If you wish to min-
-       imise any potential data loss through media  or  transmis-
-       sion errors, you might consider compressing with a smaller
-       block size.
-
-
-PERFORMANCE NOTES
-       The sorting phase of compression gathers together  similar
-       strings  in  the  file.  Because of this, files containing
-       very long runs of  repeated  symbols,  like  "aabaabaabaab
-       ..."   (repeated  several hundred times) may compress more
-       slowly than normal.  Versions 0.9.5 and  above  fare  much
-       better  than previous versions in this respect.  The ratio
-       between worst-case and average-case compression time is in
-       the  region  of  10:1.  For previous versions, this figure
-       was more like 100:1.  You can use the -vvvv option to mon-
-       itor progress in great detail, if you want.
-
-       Decompression speed is unaffected by these phenomena.
-
-       bzip2  usually  allocates  several  megabytes of memory to
-       operate in, and then charges all over it in a fairly  ran-
-       dom  fashion.   This means that performance, both for com-
-       pressing and decompressing, is largely determined  by  the
-       speed  at  which  your  machine  can service cache misses.
-       Because of this, small changes to the code to  reduce  the
-       miss  rate  have  been observed to give disproportionately
-       large performance improvements.  I imagine bzip2 will per-
-       form best on machines with very large caches.
-
-
-CAVEATS
-       I/O  error  messages  are not as helpful as they could be.
-       bzip2 tries hard to detect I/O errors  and  exit  cleanly,
-       but  the  details  of  what  the problem is sometimes seem
-       rather misleading.
-
-       This manual page pertains to version 1.0.8 of bzip2.  Com-
-       pressed  data created by this version is entirely forwards
-       and  backwards  compatible  with   the   previous   public
-       releases,  versions  0.1pl2,  0.9.0,  0.9.5, 1.0.0, 1.0.1,
-       1.0.2 and above, but with the  following  exception: 0.9.0
-       and above can  correctly decompress  multiple concatenated
-       compressed files.  0.1pl2  cannot do this;  it  will  stop
-       after  decompressing just the first file in the stream.
-
-       bzip2recover  versions prior to 1.0.2 used 32-bit integers
-       to represent bit positions in compressed  files,  so  they
-       could  not handle compressed files more than 512 megabytes
-       long.  Versions 1.0.2 and above use 64-bit  ints  on  some
-       platforms  which  support them (GNU supported targets, and
-       Windows).  To establish whether or  not  bzip2recover  was
-       built  with  such  a limitation, run it without arguments.
-       In any event you can build yourself an  unlimited  version
-       if  you  can  recompile  it  with MaybeUInt64 set to be an
-       unsigned 64-bit integer.
-
-
-AUTHOR
-       Julian Seward, jseward@acm.org
-
-       https://sourceware.org/bzip2/
-
-       The ideas embodied in bzip2 are due to (at least) the fol-
-       lowing  people: Michael Burrows and David Wheeler (for the
-       block sorting transformation), David Wheeler  (again,  for
-       the Huffman coder), Peter Fenwick (for the structured cod-
-       ing model in the original bzip, and many refinements), and
-       Alistair  Moffat,  Radford  Neal  and  Ian Witten (for the
-       arithmetic  coder  in  the  original  bzip).   I  am  much
-       indebted for their help, support and advice.  See the man-
-       ual in the source distribution for pointers to sources  of
-       documentation.  Christian von Roques encouraged me to look
-       for faster sorting algorithms, so as to speed up  compres-
-       sion.  Bela Lubkin encouraged me to improve the worst-case
-       compression performance.  Donna Robinson XMLised the docu-
-       mentation.   The bz* scripts are derived from those of GNU
-       gzip.  Many people sent patches, helped  with  portability
-       problems,  lent  machines,  gave advice and were generally
-       helpful.
-

bzlib.c

@@ -1408,7 +1408,7 @@ BZFILE * bzopen_or_bzdopen
       case 's':
          smallMode = 1; break;
       default:
-         if (isdigit((int)(*mode))) {
+         if (isdigit((unsigned char)(*mode))) {
             blockSize100k = *mode-BZ_HDR_0;
          }
       }

bzlib.h

@@ -22,6 +22,15 @@
 #ifndef _BZLIB_H
 #define _BZLIB_H
 
+#ifndef BZ_NO_STDIO
+/* Need a definitition for FILE */
+#include <stdio.h>
+#endif
+
+#ifdef _WIN32
+#include <windows.h>
+#endif
+
 #ifdef __cplusplus
 extern "C" {
 #endif
@@ -70,13 +79,7 @@ typedef
 #define BZ_EXPORT
 #endif
 
-#ifndef BZ_NO_STDIO
-/* Need a definitition for FILE */
-#include <stdio.h>
-#endif
-
 #ifdef _WIN32
-#   include <windows.h>
 #   ifdef small
       /* windows.h define small to char */
 #      undef small

bzmore.1

@@ -149,4 +149,8 @@ except that a header is printed before each file.
 .DT
 /etc/termcap		Terminal data base
 .SH "SEE ALSO"
-more(1), less(1), bzip2(1), bzdiff(1), bzgrep(1)
+.BR more (1),
+.BR less (1),
+.BR bzip2 (1),
+.BR bzdiff (1),
+.BR bzgrep (1)

compress.c

@@ -321,7 +321,7 @@ void sendMTFValues ( EState* s )
    ---*/
    for (iter = 0; iter < BZ_N_ITERS; iter++) {
 
-      for (t = 0; t < nGroups; t++) fave[t] = 0;
+      for (t = 0; t < BZ_N_GROUPS; t++) fave[t] = 0;
 
       for (t = 0; t < nGroups; t++)
          for (v = 0; v < alphaSize; v++)
@@ -353,7 +353,7 @@ void sendMTFValues ( EState* s )
             Calculate the cost of this group as coded
             by each of the coding tables.
          --*/
-         for (t = 0; t < nGroups; t++) cost[t] = 0;
+         for (t = 0; t < BZ_N_GROUPS; t++) cost[t] = 0;
 
          if (nGroups == 6 && 50 == ge-gs+1) {
             /*--- fast track the common case ---*/

manual.xml

@@ -160,12 +160,21 @@ else.</para>
  <listitem><para><computeroutput>bzip2</computeroutput> [
   -cdfkqstvzVL123456789 ] [ filenames ...  ]</para></listitem>
 
+ <listitem><para><computeroutput>bzip2</computeroutput> [
+  -h | --help ]</para></listitem>
+
  <listitem><para><computeroutput>bunzip2</computeroutput> [
   -fkvsVL ] [ filenames ...  ]</para></listitem>
 
+ <listitem><para><computeroutput>bunzip2</computeroutput> [
+  -h | --help ]</para></listitem>
+
  <listitem><para><computeroutput>bzcat</computeroutput> [ -s ] [
   filenames ...  ]</para></listitem>
 
+ <listitem><para><computeroutput>bzcat</computeroutput> [
+  -h | --help ]</para></listitem>
+
  <listitem><para><computeroutput>bzip2recover</computeroutput>
   filename</para></listitem>
 
@@ -397,6 +406,10 @@ consistency error (eg, bug) which caused
   will not be suppressed.</para></listitem>
  </varlistentry>
 
+ <varlistentry><term><computeroutput>-h --help</computeroutput></term>
+ <listitem><para>Print a help message and exit.</para></listitem>
+ </varlistentry>
+
  <varlistentry>
  <term><computeroutput>-v --verbose</computeroutput></term>
  <listitem><para>Verbose mode -- show the compression ratio for
@@ -1570,6 +1583,8 @@ BZ_MEM_ERROR
 BZ_STREAM_END
   if the logical end of the data stream was detected and all
   output in has been consumed, eg s-->avail_out > 0
+BZ_SEQUENCE_ERROR
+  if called after an earlier call already returned BZ_STREAM_END
 BZ_OK
   otherwise
 </programlisting>

prepare-release.sh

@@ -45,7 +45,7 @@ sed -i -e "s@ENTITY bz-version \".*\"@ENTITY bz-version \"$VERSION\"@" \
 # isn't, so explicitly change it here too.
 sed -i -e "s@This manual page pertains to version .* of@This manual page pertains to version $VERSION of@" \
        -e "s@sorting file compressor, v.*@sorting file compressor, v$VERSION@" \
-  bzip2.1* bzip2.txt
+  bzip2.1
 
 # Update sources. All sources, use bzlib_private.
 # Except bzip2recover, which embeds a version string...