diff --git a/usr.bin/diff/diff.1 b/usr.bin/diff/diff.1 index 5f211372e15f..559434d8e4fb 100644 --- a/usr.bin/diff/diff.1 +++ b/usr.bin/diff/diff.1 @@ -1,821 +1,821 @@ .\" $OpenBSD: diff.1,v 1.47 2015/11/24 19:35:41 jmc Exp $ .\" .\" Copyright (c) 1980, 1990, 1993 .\" The Regents of the University of California. All rights reserved. .\" .\" Redistribution and use in source and binary forms, with or without .\" modification, are permitted provided that the following conditions .\" are met: .\" 1. Redistributions of source code must retain the above copyright .\" notice, this list of conditions and the following disclaimer. .\" 2. Redistributions in binary form must reproduce the above copyright .\" notice, this list of conditions and the following disclaimer in the .\" documentation and/or other materials provided with the distribution. .\" 3. Neither the name of the University nor the names of its contributors .\" may be used to endorse or promote products derived from this software .\" without specific prior written permission. .\" .\" THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND .\" ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE .\" IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE .\" ARE DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE .\" FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL .\" DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS .\" OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) .\" HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT .\" LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY .\" OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF .\" SUCH DAMAGE. .\" -.Dd June 29, 2024 +.Dd July 26, 2024 .Dt DIFF 1 .Os .Sh NAME .Nm diff .Nd differential file and directory comparator .Sh SYNOPSIS .Nm diff .Op Fl aBbdipTtw .Oo .Fl c | e | f | .Fl n | q | u | y .Oc .Op Fl A Ar algo | Fl -algorithm Ar algo .Op Fl -brief .Op Fl -color Ns = Ns Ar when .Op Fl -changed-group-format Ar GFMT .Op Fl -ed .Op Fl -expand-tabs .Op Fl -forward-ed .Op Fl -ignore-all-space .Op Fl -ignore-case .Op Fl -ignore-space-change .Op Fl -initial-tab .Op Fl -minimal .Op Fl -no-dereference .Op Fl -no-ignore-file-name-case .Op Fl -normal .Op Fl -rcs .Op Fl -show-c-function .Op Fl -starting-file .Op Fl -speed-large-files .Op Fl -strip-trailing-cr .Op Fl -tabsize Ar number .Op Fl -text .Op Fl -unified .Op Fl I Ar pattern | Fl -ignore-matching-lines Ar pattern .Op Fl F Ar pattern | Fl -show-function-line Ar pattern .Op Fl L Ar label | Fl -label Ar label .Ar file1 file2 .Nm diff .Op Fl aBbdilpTtw .Op Fl A Ar algo | Fl -algorithm Ar algo .Op Fl I Ar pattern | Fl -ignore-matching-lines Ar pattern .Op Fl F Ar pattern | Fl -show-function-line Ar pattern .Op Fl L Ar label | Fl -label Ar label .Op Fl -brief .Op Fl -color Ns = Ns Ar when .Op Fl -changed-group-format Ar GFMT .Op Fl -ed .Op Fl -expand-tabs .Op Fl -forward-ed .Op Fl -ignore-all-space .Op Fl -ignore-case .Op Fl -ignore-space-change .Op Fl -initial-tab .Op Fl -minimal .Op Fl -no-dereference .Op Fl -no-ignore-file-name-case .Op Fl -normal .Op Fl -paginate .Op Fl -rcs .Op Fl -show-c-function .Op Fl -speed-large-files .Op Fl -starting-file .Op Fl -strip-trailing-cr .Op Fl -tabsize Ar number .Op Fl -text .Fl C Ar number | -context Ar number .Ar file1 file2 .Nm diff .Op Fl aBbdiltw .Op Fl A Ar algo | Fl -algorithm Ar algo .Op Fl I Ar pattern | Fl -ignore-matching-lines Ar pattern .Op Fl -brief .Op Fl -color Ns = Ns Ar when .Op Fl -changed-group-format Ar GFMT .Op Fl -ed .Op Fl -expand-tabs .Op Fl -forward-ed .Op Fl -ignore-all-space .Op Fl -ignore-case .Op Fl -ignore-space-change .Op Fl -initial-tab .Op Fl -minimal .Op Fl -no-dereference .Op Fl -no-ignore-file-name-case .Op Fl -normal .Op Fl -paginate .Op Fl -rcs .Op Fl -show-c-function .Op Fl -speed-large-files .Op Fl -starting-file .Op Fl -strip-trailing-cr .Op Fl -tabsize Ar number .Op Fl -text .Fl D Ar string | Fl -ifdef Ar string .Ar file1 file2 .Nm diff .Op Fl aBbdilpTtw .Op Fl A Ar algo | Fl -algorithm Ar algo .Op Fl I Ar pattern | Fl -ignore-matching-lines Ar pattern .Op Fl F Ar pattern | Fl -show-function-line Ar pattern .Op Fl L Ar label | Fl -label Ar label .Op Fl -brief .Op Fl -color Ns = Ns Ar when .Op Fl -changed-group-format Ar GFMT .Op Fl -ed .Op Fl -expand-tabs .Op Fl -forward-ed .Op Fl -ignore-all-space .Op Fl -ignore-case .Op Fl -ignore-space-change .Op Fl -initial-tab .Op Fl -minimal .Op Fl -no-dereference .Op Fl -no-ignore-file-name-case .Op Fl -normal .Op Fl -paginate .Op Fl -rcs .Op Fl -show-c-function .Op Fl -speed-large-files .Op Fl -starting-file .Op Fl -strip-trailing-cr .Op Fl -tabsize Ar number .Op Fl -text .Fl U Ar number | Fl -unified Ar number .Ar file1 file2 .Nm diff .Op Fl aBbdilNPprsTtw .Oo .Fl c | e | f | .Fl n | q | u .Oc .Op Fl A Ar algo | Fl -algorithm Ar algo .Op Fl -brief .Op Fl -color Ns = Ns Ar when .Op Fl -changed-group-format Ar GFMT .Op Fl -context .Op Fl -ed .Op Fl -expand-tabs .Op Fl -forward-ed .Op Fl -ignore-all-space .Op Fl -ignore-case .Op Fl -ignore-space-change .Op Fl -initial-tab .Op Fl -minimal .Op Fl -new-file .Op Fl -no-dereference .Op Fl -no-ignore-file-name-case .Op Fl -normal .Op Fl -paginate .Op Fl -rcs .Op Fl -recursive .Op Fl -report-identical-files .Op Fl -show-c-function .Op Fl -speed-large-files .Op Fl -strip-trailing-cr .Op Fl -tabsize Ar number .Op Fl -text .Op Fl -unidirectional-new-file .Op Fl -unified .Op Fl I Ar pattern | Fl -ignore-matching-lines Ar pattern .Op Fl F Ar pattern | Fl -show-function-line Ar pattern .Bk -words .Op Fl L Ar label | Fl -label Ar label .Op Fl S Ar name | Fl -starting-file Ar name .Op Fl X Ar file | Fl -exclude-from Ar file .Op Fl x Ar pattern | Fl -exclude Ar pattern .Ek .Ar dir1 dir2 .Nm diff .Op Fl aBbditwW .Op Fl -color Ns = Ns Ar when .Op Fl -expand-tabs -.Op Fl -ignore-all-blanks +.Op Fl -ignore-all-space .Op Fl -ignore-blank-lines .Op Fl -ignore-case .Op Fl -minimal .Op Fl -no-dereference .Op Fl -no-ignore-file-name-case .Op Fl -strip-trailing-cr .Op Fl -suppress-common-lines .Op Fl -tabsize Ar number .Op Fl -text .Op Fl -width .Fl y | Fl -side-by-side .Ar file1 file2 .Nm diff .Op Fl -help .Op Fl -version .Sh DESCRIPTION The .Nm utility compares the contents of .Ar file1 and .Ar file2 and writes to the standard output the list of changes necessary to convert one file into the other. No output is produced if the files are identical. .Pp Output options (mutually exclusive): .Bl -tag -width Ds .It Fl C Ar number Fl -context Ar number Like .Fl c but produces a diff with .Ar number lines of context. .It Fl c Produces a diff with 3 lines of context. With .Fl c the output format is modified slightly: the output begins with identification of the files involved and their creation dates and then each change is separated by a line with fifteen .Li * Ns 's . The lines removed from .Ar file1 are marked with .Sq \&-\ \& ; those added to .Ar file2 are marked .Sq +\ \& . Lines which are changed from one file to the other are marked in both files with .Sq !\ \& . Changes which lie within 3 lines of each other are grouped together on output. .It Fl D Ar string Fl -ifdef Ar string Creates a merged version of .Ar file1 and .Ar file2 on the standard output, with C preprocessor controls included so that a compilation of the result without defining .Ar string is equivalent to compiling .Ar file1 , while defining .Ar string will yield .Ar file2 . .It Fl e -ed Produces output in a form suitable as input for the editor utility, .Xr ed 1 , which can then be used to convert file1 into file2. .Pp Extra commands are added to the output when comparing directories with .Fl e , so that the result is a .Xr sh 1 script for converting text files which are common to the two directories from their state in .Ar dir1 to their state in .Ar dir2 . Note that when comparing directories with .Fl e , the resulting file may no longer be interpreted as an .Xr ed 1 script. Output is added to indicate which file each set of .Xr ed 1 commands applies to. These hunks can be manually extracted to produce an .Xr ed 1 script, which can also be applied with .Xr patch 1 . .It Fl f -forward-ed Identical output to that of the .Fl e flag, but in reverse order. It cannot be digested by .Xr ed 1 . .It Fl -help This option prints a summary to stdout and exits with status 0. .It Fl n Produces a script similar to that of .Fl e , but in the opposite order and with a count of changed lines on each insert or delete command. This is the form used by rcsdiff. .It Fl q -brief Just print a line when the files differ. Does not output a list of changes. .It Fl U Ar number Fl -unified Ar number Like .Fl u but produces a diff with .Ar number lines of context. .It Fl u Produces a .Em unified diff with 3 lines of context. A unified diff is similar to the context diff produced by the .Fl c option. However, unlike with .Fl c , all lines to be changed (added and/or removed) are present in a single section. .It Fl -version This option prints a version string to stdout and exits with status 0. .It Fl y Fl -side-by-side Output in two columns with a marker between them. The marker can be one of the following: .Pp .Bl -tag -width Ds -offset indent -compact .It space Corresponding lines are identical. .It '|' Corresponding lines are different. .It '<' Files differ and only the first file contains the line. .It '>' Files differ and only the second file contains the line. .El .El .Pp Comparison options: .Bl -tag -width Ds .It Fl A Ar algo, Fl -algorithm Ar algo Configure the algorithm used when comparing files. .Nm supports 3 algorithms: .Pp .Bl -tag -width Ds -compact .It Cm myers The Myers diff algorithm finds the shortest edit which transforms one input into the other. It generally runs in O(N+D\(S2) time, requiring O(N) space, where N is the sum of the lengths of the inputs and D is the length of the difference between them, with a theoretical O(N\(pcD) worst case. If it encounters worst-case input, the implementation used by .Nm falls back to a less optimal but faster algorithm. .It Cm patience The Patience variant of the Myers algorithm attempts to create more aesthetically pleasing diff output by logically grouping lines. .It Cm stone The Stone algorithm (commonly known as Hunt-McIlroy or Hunt-Szymanski) looks for the longest common subsequence between compared files. Stone encounters worst case performance when there are long common subsequences. In large files this can lead to a significant performance impact. The Stone algorithm is maintained for compatibility. .El .Pp The .Nm utility defaults to the Myers algorithm, but will fall back to the Stone algorithm if the input or output options are not supported by the Myers implementation. .It Fl a -text Treat all files as ASCII text. Normally .Nm will simply print .Dq Binary files ... differ if files contain binary characters. Use of this option forces .Nm to produce a diff. .It Fl B Fl -ignore-blank-lines Causes chunks that include only blank lines to be ignored. .It Fl b -ignore-space-change Causes trailing blanks (spaces and tabs) to be ignored, and other strings of blanks to compare equal. .It Fl -color= Ns Oo Ar when Oc Color the additions green, and removals red, or the value in the .Ev DIFFCOLORS environment variable. The possible values of .Ar when are .Dq Cm never , .Dq Cm always and .Dq Cm auto . .Cm auto will use color if the output is a tty and the .Ev COLORTERM environment variable is set to a non-empty string. .It Fl d -minimal Try very hard to produce a diff as small as possible. This may consume a lot of processing power and memory when processing large files with many changes. .It Fl F Ar pattern, Fl -show-function-line Ar pattern Like .Fl p, but display the last line that matches provided pattern. .It Fl I Ar pattern Fl -ignore-matching-lines Ar pattern Ignores changes, insertions, and deletions whose lines match the extended regular expression .Ar pattern . Multiple .Fl I patterns may be specified. All lines in the change must match some pattern for the change to be ignored. See .Xr re_format 7 for more information on regular expression patterns. .It Fl i -ignore-case Ignores the case of letters. E.g., .Dq A will compare equal to .Dq a . .It Fl l -paginate Pass the output through .Xr pr 1 to paginate it. .It Fl L Ar label Fl -label Ar label Print .Ar label instead of the first (and second, if this option is specified twice) file name and time in the context or unified diff header. .It Fl p -show-c-function With unified and context diffs, show with each change the first 40 characters of the last line before the context beginning with a letter, an underscore or a dollar sign. For C and Objective-C source code following standard layout conventions, this will show the prototype of the function the change applies to. .It Fl T -initial-tab Print a tab rather than a space before the rest of the line for the normal, context or unified output formats. This makes the alignment of tabs in the line consistent. .It Fl t -expand-tabs Will expand tabs in output lines. Normal or .Fl c output adds character(s) to the front of each line which may screw up the indentation of the original source lines and make the output listing difficult to interpret. This option will preserve the original source's indentation. -.It Fl w -ignore-all-blanks +.It Fl w -ignore-all-space Is similar to .Fl b -ignore-space-change but causes whitespace (blanks and tabs) to be totally ignored. E.g., .Dq if (\ \&a == b \&) will compare equal to .Dq if(a==b) . .It Fl W Ar number Fl -width Ar number Output at most .Ar number columns when using side by side format. The default value is 130. Note that unless .It Fl t was specified, .Nm will always align the second column to a tab stop, so values of .Fl -width smaller than approximately five times the value of .Fl -tabsize may yield surprising results. .It Fl -changed-group-format Ar GFMT Format input groups in the provided .Pp the format is a string with special keywords: .Bl -tag -width %< .It %< lines from FILE1 .It %< lines from FILE2 .El .It Fl -ignore-file-name-case ignore case when comparing file names .It Fl -no-dereference do not follow symbolic links .It Fl -no-ignore-file-name-case do not ignore case when comparing file names (default) .It Fl -normal default diff output .It Fl -speed-large-files stub option for compatibility with GNU diff .It Fl -strip-trailing-cr strip carriage return on input files .It Fl -suppress-common-lines Do not output common lines when using the side by side format .It Fl -tabsize Ar number Number of spaces representing a tab (default 8) .El .Pp Directory comparison options: .Bl -tag -width Ds .It Fl N -new-file If a file is found in only one directory, act as if it was found in the other directory too but was of zero size. .It Fl P -unidirectional-new-file If a file is found only in .Ar dir2 , act as if it was found in .Ar dir1 too but was of zero size. .It Fl r -recursive Causes application of .Nm recursively to common subdirectories encountered. .It Fl S Ar name Fl -starting-file Ar name Re-starts a directory .Nm in the middle, beginning with file .Ar name . .It Fl s -report-identical-files Causes .Nm to report files which are the same, which are otherwise not mentioned. .It Fl X Ar file Fl -exclude-from Ar file Exclude files and subdirectories from comparison whose basenames match lines in .Ar file . Multiple .Fl X options may be specified. .It Fl x Ar pattern Fl -exclude Ar pattern Exclude files and subdirectories from comparison whose basenames match .Ar pattern . Patterns are matched using shell-style globbing via .Xr fnmatch 3 . Multiple .Fl x options may be specified. .El .Pp If both arguments are directories, .Nm sorts the contents of the directories by name, and then runs the regular file .Nm algorithm, producing a change list, on text files which are different. Binary files which differ, common subdirectories, and files which appear in only one directory are described as such. In directory mode only regular files and directories are compared. If a non-regular file such as a device special file or FIFO is encountered, a diagnostic message is printed. .Pp If only one of .Ar file1 and .Ar file2 is a directory, .Nm is applied to the non-directory file and the file contained in the directory file with a filename that is the same as the last component of the non-directory file. .Pp If either .Ar file1 or .Ar file2 is .Sq - , the standard input is used in its place. .Ss Output Style The default (without .Fl e , .Fl c , or .Fl n -rcs .\" -C options) output contains lines of these forms, where .Va XX , YY , ZZ , QQ are line numbers respective of file order. .Pp .Bl -tag -width "XX,YYcZZ,QQ" -compact .It Li XX Ns Ic a Ns Li YY At (the end of) line .Va XX of .Ar file1 , append the contents of line .Va YY of .Ar file2 to make them equal. .It Li XX Ns Ic a Ns Li YY,ZZ Same as above, but append the range of lines, .Va YY through .Va ZZ of .Ar file2 to line .Va XX of file1. .It Li XX Ns Ic d Ns Li YY At line .Va XX delete the line. The value .Va YY tells to which line the change would bring .Ar file1 in line with .Ar file2 . .It Li XX,YY Ns Ic d Ns Li ZZ Delete the range of lines .Va XX through .Va YY in .Ar file1 . .It Li XX Ns Ic c Ns Li YY Change the line .Va XX in .Ar file1 to the line .Va YY in .Ar file2 . .It Li XX,YY Ns Ic c Ns Li ZZ Replace the range of specified lines with the line .Va ZZ . .It Li XX,YY Ns Ic c Ns Li ZZ,QQ Replace the range .Va XX , Ns Va YY from .Ar file1 with the range .Va ZZ , Ns Va QQ from .Ar file2 . .El .Pp These lines resemble .Xr ed 1 subcommands to convert .Ar file1 into .Ar file2 . The line numbers before the action letters pertain to .Ar file1 ; those after pertain to .Ar file2 . Thus, by exchanging .Ic a for .Ic d and reading the line in reverse order, one can also determine how to convert .Ar file2 into .Ar file1 . As in .Xr ed 1 , identical pairs (where num1 = num2) are abbreviated as a single number. .Sh ENVIRONMENT .Bl -tag -width DIFFCOLORS .It Ev DIFFCOLORS The value of this variable is the form .Ar add Ns : Ns Ar rm , where .Ar add is the ASCII escape sequence for additions and .Ar rm is the ASCII escape sequence for deletions. If this is unset, .Nm uses green for additions and red for removals. .El .Sh FILES .Bl -tag -width /tmp/diff.XXXXXXXX -compact .It Pa /tmp/diff.XXXXXXXX Temporary file used when comparing a device or the standard input. Note that the temporary file is unlinked as soon as it is created so it will not show up in a directory listing. .El .Sh EXIT STATUS The .Nm utility exits with one of the following values: .Pp .Bl -tag -width Ds -offset indent -compact .It 0 No differences were found. .It 1 Differences were found. .It >1 An error occurred. .El .Pp The .Fl -help and .Fl -version options exit with a status of 0. .Sh EXAMPLES Compare .Pa old_dir and .Pa new_dir recursively generating an unified diff and treating files found only in one of those directories as new files: .Bd -literal -offset indent $ diff -ruN /path/to/old_dir /path/to/new_dir .Ed .Pp Same as above but excluding files matching the expressions .Dq *.h and .Dq *.c : .Bd -literal -offset indent $ diff -ruN -x '*.h' -x '*.c' /path/to/old_dir /path/to/new_dir .Ed .Pp Show a single line indicating if the files differ: .Bd -literal -offset indent $ diff -q /boot/loader.conf /boot/defaults/loader.conf Files /boot/loader.conf and /boot/defaults/loader.conf differ .Ed .Pp Assuming a file named .Pa example.txt with the following contents: .Bd -literal -offset indent FreeBSD is an operating system Linux is a kernel OpenBSD is an operating system .Ed .Pp Compare stdin with .Pa example.txt excluding from the comparison those lines containing either .Qq Linux or .Qq Open : .Bd -literal -offset indent $ echo "FreeBSD is an operating system" | diff -q -I 'Linux|Open' example.txt - .Ed .Sh SEE ALSO .Xr cmp 1 , .Xr comm 1 , .Xr diff3 1 , .Xr ed 1 , .Xr patch 1 , .Xr pr 1 , .Xr sdiff 1 .Rs .%A James W. Hunt .%A M. Douglas McIlroy .%T "An Algorithm for Differential File Comparison" .%J Computing Science Technical Report .%Q Bell Laboratories 41 .%D June 1976 .Re .Sh STANDARDS The .Nm utility is compliant with the .St -p1003.1-2008 specification. .Pp The flags .Op Fl AaDdIiLlNnPpqSsTtwXxy are extensions to that specification. .Sh HISTORY A .Nm command appeared in .At v6 . The .Nm implementation used in .Fx was GNU diff until .Fx 11.4 . This was replaced in .Fx 12.0 by a BSD-licensed implementation written by .An Todd Miller . Some GNUisms were lost in the process. .Pp libdiff was imported from the Game of Trees version control system and default algorithm was changed to Myers for FreeBSD 15. diff --git a/usr.bin/diff/diff.c b/usr.bin/diff/diff.c index 5ca9a36505ce..83aa20c52cf3 100644 --- a/usr.bin/diff/diff.c +++ b/usr.bin/diff/diff.c @@ -1,689 +1,689 @@ /* $OpenBSD: diff.c,v 1.67 2019/06/28 13:35:00 deraadt Exp $ */ /* * Copyright (c) 2003 Todd C. Miller * * Permission to use, copy, modify, and distribute this software for any * purpose with or without fee is hereby granted, provided that the above * copyright notice and this permission notice appear in all copies. * * THE SOFTWARE IS PROVIDED "AS IS" AND THE AUTHOR DISCLAIMS ALL WARRANTIES * WITH REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES OF * MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR * ANY SPECIAL, DIRECT, INDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES * WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN * ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF * OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE. * * Sponsored in part by the Defense Advanced Research Projects * Agency (DARPA) and Air Force Research Laboratory, Air Force * Materiel Command, USAF, under agreement number F39502-99-1-0512. */ #include #include #include #include #include #include #include #include #include #include #include "diff.h" #include "xmalloc.h" static const char diff_version[] = "FreeBSD diff 20240307"; bool lflag, Nflag, Pflag, rflag, sflag, Tflag, cflag; bool ignore_file_case, suppress_common, color, noderef; static bool help = false; int diff_format, diff_context, diff_algorithm, status; bool diff_algorithm_set; int tabsize = 8, width = 130; static int colorflag = COLORFLAG_NEVER; char *start, *ifdefname, *diffargs, *label[2]; char *ignore_pats, *most_recent_pat; char *group_format = NULL; const char *add_code, *del_code; struct stat stb1, stb2; struct excludes *excludes_list; regex_t ignore_re, most_recent_re; static struct algorithm { const char *name; int id; } algorithms[] = { {"stone", D_DIFFSTONE}, {"myers", D_DIFFMYERS}, {"patience", D_DIFFPATIENCE}, {NULL, D_DIFFNONE} }; #define OPTIONS "0123456789A:aBbC:cdD:efF:HhI:iL:lnNPpqrS:sTtU:uwW:X:x:y" enum { OPT_TSIZE = CHAR_MAX + 1, OPT_STRIPCR, OPT_IGN_FN_CASE, OPT_NO_IGN_FN_CASE, OPT_NORMAL, OPT_HELP, OPT_HORIZON_LINES, OPT_CHANGED_GROUP_FORMAT, OPT_SUPPRESS_COMMON, OPT_COLOR, OPT_NO_DEREFERENCE, OPT_VERSION, }; static struct option longopts[] = { { "algorithm", required_argument, 0, 'A' }, { "text", no_argument, 0, 'a' }, { "ignore-space-change", no_argument, 0, 'b' }, { "context", optional_argument, 0, 'C' }, { "ifdef", required_argument, 0, 'D' }, { "minimal", no_argument, 0, 'd' }, { "ed", no_argument, 0, 'e' }, { "forward-ed", no_argument, 0, 'f' }, { "show-function-line", required_argument, 0, 'F' }, { "speed-large-files", no_argument, NULL, 'H' }, { "ignore-blank-lines", no_argument, 0, 'B' }, { "ignore-matching-lines", required_argument, 0, 'I' }, { "ignore-case", no_argument, 0, 'i' }, { "paginate", no_argument, NULL, 'l' }, { "label", required_argument, 0, 'L' }, { "new-file", no_argument, 0, 'N' }, { "rcs", no_argument, 0, 'n' }, { "unidirectional-new-file", no_argument, 0, 'P' }, { "show-c-function", no_argument, 0, 'p' }, { "brief", no_argument, 0, 'q' }, { "recursive", no_argument, 0, 'r' }, { "report-identical-files", no_argument, 0, 's' }, { "starting-file", required_argument, 0, 'S' }, { "expand-tabs", no_argument, 0, 't' }, { "initial-tab", no_argument, 0, 'T' }, { "unified", optional_argument, 0, 'U' }, { "ignore-all-space", no_argument, 0, 'w' }, { "width", required_argument, 0, 'W' }, { "exclude", required_argument, 0, 'x' }, { "exclude-from", required_argument, 0, 'X' }, { "side-by-side", no_argument, NULL, 'y' }, { "ignore-file-name-case", no_argument, NULL, OPT_IGN_FN_CASE }, { "help", no_argument, NULL, OPT_HELP}, { "horizon-lines", required_argument, NULL, OPT_HORIZON_LINES }, { "no-dereference", no_argument, NULL, OPT_NO_DEREFERENCE}, { "no-ignore-file-name-case", no_argument, NULL, OPT_NO_IGN_FN_CASE }, { "normal", no_argument, NULL, OPT_NORMAL }, { "strip-trailing-cr", no_argument, NULL, OPT_STRIPCR }, { "tabsize", required_argument, NULL, OPT_TSIZE }, { "changed-group-format", required_argument, NULL, OPT_CHANGED_GROUP_FORMAT}, { "suppress-common-lines", no_argument, NULL, OPT_SUPPRESS_COMMON }, { "color", optional_argument, NULL, OPT_COLOR }, { "version", no_argument, NULL, OPT_VERSION}, { NULL, 0, 0, '\0'} }; static void checked_regcomp(char const *, regex_t *); static void usage(void) __dead2; static void conflicting_format(void) __dead2; static void push_excludes(char *); static void push_ignore_pats(char *); static void read_excludes_file(char *file); static void set_argstr(char **, char **); static char *splice(char *, char *); static bool do_color(void); int main(int argc, char **argv) { const char *errstr = NULL; char *ep, **oargv; long l; int ch, dflags, lastch, gotstdin, prevoptind, newarg; oargv = argv; gotstdin = 0; dflags = 0; lastch = '\0'; prevoptind = 1; newarg = 1; diff_context = 3; diff_format = D_UNSET; diff_algorithm = D_DIFFMYERS; diff_algorithm_set = false; #define FORMAT_MISMATCHED(type) \ (diff_format != D_UNSET && diff_format != (type)) while ((ch = getopt_long(argc, argv, OPTIONS, longopts, NULL)) != -1) { switch (ch) { case '0': case '1': case '2': case '3': case '4': case '5': case '6': case '7': case '8': case '9': if (newarg) usage(); /* disallow -[0-9]+ */ else if (lastch == 'c' || lastch == 'u') diff_context = 0; else if (!isdigit(lastch) || diff_context > INT_MAX / 10) usage(); diff_context = (diff_context * 10) + (ch - '0'); break; case 'A': diff_algorithm = D_DIFFNONE; for (struct algorithm *a = algorithms; a->name;a++) { if(strcasecmp(optarg, a->name) == 0) { diff_algorithm = a->id; diff_algorithm_set = true; break; } } if (diff_algorithm == D_DIFFNONE) { printf("unknown algorithm: %s\n", optarg); usage(); } break; case 'a': dflags |= D_FORCEASCII; break; case 'b': dflags |= D_FOLDBLANKS; break; case 'C': case 'c': if (FORMAT_MISMATCHED(D_CONTEXT)) conflicting_format(); cflag = true; diff_format = D_CONTEXT; if (optarg != NULL) { l = strtol(optarg, &ep, 10); if (*ep != '\0' || l < 0 || l >= INT_MAX) usage(); diff_context = (int)l; } break; case 'd': dflags |= D_MINIMAL; break; case 'D': if (FORMAT_MISMATCHED(D_IFDEF)) conflicting_format(); diff_format = D_IFDEF; ifdefname = optarg; break; case 'e': if (FORMAT_MISMATCHED(D_EDIT)) conflicting_format(); diff_format = D_EDIT; break; case 'f': if (FORMAT_MISMATCHED(D_REVERSE)) conflicting_format(); diff_format = D_REVERSE; break; case 'H': /* ignore but needed for compatibility with GNU diff */ break; case 'h': /* silently ignore for backwards compatibility */ break; case 'B': dflags |= D_SKIPBLANKLINES; break; case 'F': if (dflags & D_PROTOTYPE) conflicting_format(); dflags |= D_MATCHLAST; most_recent_pat = xstrdup(optarg); break; case 'I': push_ignore_pats(optarg); break; case 'i': dflags |= D_IGNORECASE; break; case 'L': if (label[0] == NULL) label[0] = optarg; else if (label[1] == NULL) label[1] = optarg; else usage(); break; case 'l': lflag = true; break; case 'N': Nflag = true; break; case 'n': if (FORMAT_MISMATCHED(D_NREVERSE)) conflicting_format(); diff_format = D_NREVERSE; break; case 'p': if (dflags & D_MATCHLAST) conflicting_format(); dflags |= D_PROTOTYPE; break; case 'P': Pflag = true; break; case 'r': rflag = true; break; case 'q': if (FORMAT_MISMATCHED(D_BRIEF)) conflicting_format(); diff_format = D_BRIEF; break; case 'S': start = optarg; break; case 's': sflag = true; break; case 'T': Tflag = true; break; case 't': dflags |= D_EXPANDTABS; break; case 'U': case 'u': if (FORMAT_MISMATCHED(D_UNIFIED)) conflicting_format(); diff_format = D_UNIFIED; if (optarg != NULL) { l = strtol(optarg, &ep, 10); if (*ep != '\0' || l < 0 || l >= INT_MAX) usage(); diff_context = (int)l; } break; case 'w': dflags |= D_IGNOREBLANKS; break; case 'W': width = (int) strtonum(optarg, 1, INT_MAX, &errstr); if (errstr) { warnx("Invalid argument for width"); usage(); } break; case 'X': read_excludes_file(optarg); break; case 'x': push_excludes(optarg); break; case 'y': if (FORMAT_MISMATCHED(D_SIDEBYSIDE)) conflicting_format(); diff_format = D_SIDEBYSIDE; break; case OPT_CHANGED_GROUP_FORMAT: if (FORMAT_MISMATCHED(D_GFORMAT)) conflicting_format(); diff_format = D_GFORMAT; group_format = optarg; break; case OPT_HELP: help = true; usage(); break; case OPT_HORIZON_LINES: break; /* XXX TODO for compatibility with GNU diff3 */ case OPT_IGN_FN_CASE: ignore_file_case = true; break; case OPT_NO_IGN_FN_CASE: ignore_file_case = false; break; case OPT_NORMAL: if (FORMAT_MISMATCHED(D_NORMAL)) conflicting_format(); diff_format = D_NORMAL; break; case OPT_TSIZE: tabsize = (int) strtonum(optarg, 1, INT_MAX, &errstr); if (errstr) { warnx("Invalid argument for tabsize"); usage(); } break; case OPT_STRIPCR: dflags |= D_STRIPCR; break; case OPT_SUPPRESS_COMMON: suppress_common = 1; break; case OPT_COLOR: if (optarg == NULL || strncmp(optarg, "auto", 4) == 0) colorflag = COLORFLAG_AUTO; else if (strncmp(optarg, "always", 6) == 0) colorflag = COLORFLAG_ALWAYS; else if (strncmp(optarg, "never", 5) == 0) colorflag = COLORFLAG_NEVER; else errx(2, "unsupported --color value '%s' (must be always, auto, or never)", optarg); break; case OPT_NO_DEREFERENCE: noderef = true; break; case OPT_VERSION: printf("%s\n", diff_version); exit(0); default: usage(); break; } lastch = ch; newarg = optind != prevoptind; prevoptind = optind; } if (diff_format == D_UNSET && (dflags & D_PROTOTYPE) != 0) diff_format = D_CONTEXT; if (diff_format == D_UNSET) diff_format = D_NORMAL; argc -= optind; argv += optind; if (do_color()) { char *p; const char *env; color = true; add_code = "32"; del_code = "31"; env = getenv("DIFFCOLORS"); if (env != NULL && *env != '\0' && (p = strdup(env))) { add_code = p; strsep(&p, ":"); if (p != NULL) del_code = p; } } #ifdef __OpenBSD__ if (pledge("stdio rpath tmppath", NULL) == -1) err(2, "pledge"); #endif /* * Do sanity checks, fill in stb1 and stb2 and call the appropriate * driver routine. Both drivers use the contents of stb1 and stb2. */ if (argc != 2) usage(); checked_regcomp(ignore_pats, &ignore_re); checked_regcomp(most_recent_pat, &most_recent_re); if (strcmp(argv[0], "-") == 0) { fstat(STDIN_FILENO, &stb1); gotstdin = 1; } else if (stat(argv[0], &stb1) != 0) { if (!Nflag || errno != ENOENT) err(2, "%s", argv[0]); dflags |= D_EMPTY1; memset(&stb1, 0, sizeof(struct stat)); } if (strcmp(argv[1], "-") == 0) { fstat(STDIN_FILENO, &stb2); gotstdin = 1; } else if (stat(argv[1], &stb2) != 0) { if (!Nflag || errno != ENOENT) err(2, "%s", argv[1]); dflags |= D_EMPTY2; memset(&stb2, 0, sizeof(stb2)); stb2.st_mode = stb1.st_mode; } if (dflags & D_EMPTY1 && dflags & D_EMPTY2){ warn("%s", argv[0]); warn("%s", argv[1]); exit(2); } if (stb1.st_mode == 0) stb1.st_mode = stb2.st_mode; if (gotstdin && (S_ISDIR(stb1.st_mode) || S_ISDIR(stb2.st_mode))) errx(2, "can't compare - to a directory"); set_argstr(oargv, argv); if (S_ISDIR(stb1.st_mode) && S_ISDIR(stb2.st_mode)) { if (diff_format == D_IFDEF) errx(2, "-D option not supported with directories"); diffdir(argv[0], argv[1], dflags); } else { if (S_ISDIR(stb1.st_mode)) { argv[0] = splice(argv[0], argv[1]); if (stat(argv[0], &stb1) == -1) err(2, "%s", argv[0]); } if (S_ISDIR(stb2.st_mode)) { argv[1] = splice(argv[1], argv[0]); if (stat(argv[1], &stb2) == -1) err(2, "%s", argv[1]); } print_status(diffreg(argv[0], argv[1], dflags, 1), argv[0], argv[1], ""); } if (fflush(stdout) != 0) err(2, "stdout"); exit(status); } static void checked_regcomp(char const *pattern, regex_t *comp) { char buf[BUFSIZ]; int error; if (pattern == NULL) return; error = regcomp(comp, pattern, REG_NEWLINE | REG_EXTENDED); if (error != 0) { regerror(error, comp, buf, sizeof(buf)); if (*pattern != '\0') errx(2, "%s: %s", pattern, buf); else errx(2, "%s", buf); } } static void set_argstr(char **av, char **ave) { size_t argsize; char **ap; argsize = 4 + *ave - *av + 1; diffargs = xmalloc(argsize); strlcpy(diffargs, "diff", argsize); for (ap = av + 1; ap < ave; ap++) { if (strcmp(*ap, "--") != 0) { strlcat(diffargs, " ", argsize); strlcat(diffargs, *ap, argsize); } } } /* * Read in an excludes file and push each line. */ static void read_excludes_file(char *file) { FILE *fp; char *pattern = NULL; size_t blen = 0; ssize_t len; if (strcmp(file, "-") == 0) fp = stdin; else if ((fp = fopen(file, "r")) == NULL) err(2, "%s", file); while ((len = getline(&pattern, &blen, fp)) >= 0) { if ((len > 0) && (pattern[len - 1] == '\n')) pattern[len - 1] = '\0'; push_excludes(pattern); /* we allocate a new string per line */ pattern = NULL; blen = 0; } free(pattern); if (strcmp(file, "-") != 0) fclose(fp); } /* * Push a pattern onto the excludes list. */ static void push_excludes(char *pattern) { struct excludes *entry; entry = xmalloc(sizeof(*entry)); entry->pattern = pattern; entry->next = excludes_list; excludes_list = entry; } static void push_ignore_pats(char *pattern) { size_t len; if (ignore_pats == NULL) ignore_pats = xstrdup(pattern); else { /* old + "|" + new + NUL */ len = strlen(ignore_pats) + strlen(pattern) + 2; ignore_pats = xreallocarray(ignore_pats, 1, len); strlcat(ignore_pats, "|", len); strlcat(ignore_pats, pattern, len); } } void print_status(int val, char *path1, char *path2, const char *entry) { if (label[0] != NULL) path1 = label[0]; if (label[1] != NULL) path2 = label[1]; switch (val) { case D_BINARY: printf("Binary files %s%s and %s%s differ\n", path1, entry, path2, entry); break; case D_DIFFER: if (diff_format == D_BRIEF) printf("Files %s%s and %s%s differ\n", path1, entry, path2, entry); break; case D_SAME: if (sflag) printf("Files %s%s and %s%s are identical\n", path1, entry, path2, entry); break; case D_MISMATCH1: printf("File %s%s is a directory while file %s%s is a regular file\n", path1, entry, path2, entry); break; case D_MISMATCH2: printf("File %s%s is a regular file while file %s%s is a directory\n", path1, entry, path2, entry); break; case D_SKIPPED1: printf("File %s%s is not a regular file or directory and was skipped\n", path1, entry); break; case D_SKIPPED2: printf("File %s%s is not a regular file or directory and was skipped\n", path2, entry); break; case D_ERROR: break; } } static void usage(void) { (void)fprintf(help ? stdout : stderr, "usage: diff [-aBbdilpTtw] [-c | -e | -f | -n | -q | -u] [--ignore-case]\n" " [--no-ignore-case] [--normal] [--strip-trailing-cr] [--tabsize]\n" " [-I pattern] [-F pattern] [-L label] file1 file2\n" " diff [-aBbdilpTtw] [-I pattern] [-L label] [--ignore-case]\n" " [--no-ignore-case] [--normal] [--strip-trailing-cr] [--tabsize]\n" " [-F pattern] -C number file1 file2\n" " diff [-aBbdiltw] [-I pattern] [--ignore-case] [--no-ignore-case]\n" " [--normal] [--strip-trailing-cr] [--tabsize] -D string file1 file2\n" " diff [-aBbdilpTtw] [-I pattern] [-L label] [--ignore-case]\n" " [--no-ignore-case] [--normal] [--tabsize] [--strip-trailing-cr]\n" " [-F pattern] -U number file1 file2\n" " diff [-aBbdilNPprsTtw] [-c | -e | -f | -n | -q | -u] [--ignore-case]\n" " [--no-ignore-case] [--normal] [--tabsize] [-I pattern] [-L label]\n" " [-F pattern] [-S name] [-X file] [-x pattern] dir1 dir2\n" - " diff [-aBbditwW] [--expand-tabs] [--ignore-all-blanks]\n" + " diff [-aBbditwW] [--expand-tabs] [--ignore-all-space]\n" " [--ignore-blank-lines] [--ignore-case] [--minimal]\n" " [--no-ignore-file-name-case] [--strip-trailing-cr]\n" " [--suppress-common-lines] [--tabsize] [--text] [--width]\n" " -y | --side-by-side file1 file2\n" " diff [--help] [--version]\n"); if (help) exit(0); else exit(2); } static void conflicting_format(void) { fprintf(stderr, "error: conflicting output format options.\n"); usage(); } static bool do_color(void) { const char *p, *p2; switch (colorflag) { case COLORFLAG_AUTO: p = getenv("CLICOLOR"); p2 = getenv("COLORTERM"); if ((p != NULL && *p != '\0') || (p2 != NULL && *p2 != '\0')) return isatty(STDOUT_FILENO); break; case COLORFLAG_ALWAYS: return (true); case COLORFLAG_NEVER: return (false); } return (false); } static char * splice(char *dir, char *path) { char *tail, *buf; size_t dirlen; dirlen = strlen(dir); while (dirlen != 0 && dir[dirlen - 1] == '/') dirlen--; if ((tail = strrchr(path, '/')) == NULL) tail = path; else tail++; xasprintf(&buf, "%.*s/%s", (int)dirlen, dir, tail); return (buf); }