From 45e58bf16e075ebcfcc33e44c85af1b480949325 Mon Sep 17 00:00:00 2001 From: tv Date: Fri, 12 Feb 1999 12:45:03 +0000 Subject: [PATCH] Use dist layout for diffutils, and add Texinfo doc. --- gnu/usr.bin/diff/COPYING | 339 ----------- gnu/usr.bin/diff/Makefile | 21 +- gnu/usr.bin/diff/analyze.c | 1084 ------------------------------------ 3 files changed, 14 insertions(+), 1430 deletions(-) delete mode 100644 gnu/usr.bin/diff/COPYING delete mode 100644 gnu/usr.bin/diff/analyze.c diff --git a/gnu/usr.bin/diff/COPYING b/gnu/usr.bin/diff/COPYING deleted file mode 100644 index a43ea2126fb6..000000000000 --- a/gnu/usr.bin/diff/COPYING +++ /dev/null @@ -1,339 +0,0 @@ - GNU GENERAL PUBLIC LICENSE - Version 2, June 1991 - - Copyright (C) 1989, 1991 Free Software Foundation, Inc. - 675 Mass Ave, Cambridge, MA 02139, USA - Everyone is permitted to copy and distribute verbatim copies - of this license document, but changing it is not allowed. - - Preamble - - The licenses for most software are designed to take away your -freedom to share and change it. By contrast, the GNU General Public -License is intended to guarantee your freedom to share and change free -software--to make sure the software is free for all its users. This -General Public License applies to most of the Free Software -Foundation's software and to any other program whose authors commit to -using it. (Some other Free Software Foundation software is covered by -the GNU Library General Public License instead.) You can apply it to -your programs, too. - - When we speak of free software, we are referring to freedom, not -price. Our General Public Licenses are designed to make sure that you -have the freedom to distribute copies of free software (and charge for -this service if you wish), that you receive source code or can get it -if you want it, that you can change the software or use pieces of it -in new free programs; and that you know you can do these things. - - To protect your rights, we need to make restrictions that forbid -anyone to deny you these rights or to ask you to surrender the rights. -These restrictions translate to certain responsibilities for you if you -distribute copies of the software, or if you modify it. - - For example, if you distribute copies of such a program, whether -gratis or for a fee, you must give the recipients all the rights that -you have. You must make sure that they, too, receive or can get the -source code. And you must show them these terms so they know their -rights. - - We protect your rights with two steps: (1) copyright the software, and -(2) offer you this license which gives you legal permission to copy, -distribute and/or modify the software. - - Also, for each author's protection and ours, we want to make certain -that everyone understands that there is no warranty for this free -software. If the software is modified by someone else and passed on, we -want its recipients to know that what they have is not the original, so -that any problems introduced by others will not reflect on the original -authors' reputations. - - Finally, any free program is threatened constantly by software -patents. We wish to avoid the danger that redistributors of a free -program will individually obtain patent licenses, in effect making the -program proprietary. To prevent this, we have made it clear that any -patent must be licensed for everyone's free use or not licensed at all. - - The precise terms and conditions for copying, distribution and -modification follow. - - GNU GENERAL PUBLIC LICENSE - TERMS AND CONDITIONS FOR COPYING, DISTRIBUTION AND MODIFICATION - - 0. This License applies to any program or other work which contains -a notice placed by the copyright holder saying it may be distributed -under the terms of this General Public License. The "Program", below, -refers to any such program or work, and a "work based on the Program" -means either the Program or any derivative work under copyright law: -that is to say, a work containing the Program or a portion of it, -either verbatim or with modifications and/or translated into another -language. (Hereinafter, translation is included without limitation in -the term "modification".) Each licensee is addressed as "you". - -Activities other than copying, distribution and modification are not -covered by this License; they are outside its scope. The act of -running the Program is not restricted, and the output from the Program -is covered only if its contents constitute a work based on the -Program (independent of having been made by running the Program). -Whether that is true depends on what the Program does. - - 1. You may copy and distribute verbatim copies of the Program's -source code as you receive it, in any medium, provided that you -conspicuously and appropriately publish on each copy an appropriate -copyright notice and disclaimer of warranty; keep intact all the -notices that refer to this License and to the absence of any warranty; -and give any other recipients of the Program a copy of this License -along with the Program. - -You may charge a fee for the physical act of transferring a copy, and -you may at your option offer warranty protection in exchange for a fee. - - 2. You may modify your copy or copies of the Program or any portion -of it, thus forming a work based on the Program, and copy and -distribute such modifications or work under the terms of Section 1 -above, provided that you also meet all of these conditions: - - a) You must cause the modified files to carry prominent notices - stating that you changed the files and the date of any change. - - b) You must cause any work that you distribute or publish, that in - whole or in part contains or is derived from the Program or any - part thereof, to be licensed as a whole at no charge to all third - parties under the terms of this License. - - c) If the modified program normally reads commands interactively - when run, you must cause it, when started running for such - interactive use in the most ordinary way, to print or display an - announcement including an appropriate copyright notice and a - notice that there is no warranty (or else, saying that you provide - a warranty) and that users may redistribute the program under - these conditions, and telling the user how to view a copy of this - License. (Exception: if the Program itself is interactive but - does not normally print such an announcement, your work based on - the Program is not required to print an announcement.) - -These requirements apply to the modified work as a whole. If -identifiable sections of that work are not derived from the Program, -and can be reasonably considered independent and separate works in -themselves, then this License, and its terms, do not apply to those -sections when you distribute them as separate works. But when you -distribute the same sections as part of a whole which is a work based -on the Program, the distribution of the whole must be on the terms of -this License, whose permissions for other licensees extend to the -entire whole, and thus to each and every part regardless of who wrote it. - -Thus, it is not the intent of this section to claim rights or contest -your rights to work written entirely by you; rather, the intent is to -exercise the right to control the distribution of derivative or -collective works based on the Program. - -In addition, mere aggregation of another work not based on the Program -with the Program (or with a work based on the Program) on a volume of -a storage or distribution medium does not bring the other work under -the scope of this License. - - 3. You may copy and distribute the Program (or a work based on it, -under Section 2) in object code or executable form under the terms of -Sections 1 and 2 above provided that you also do one of the following: - - a) Accompany it with the complete corresponding machine-readable - source code, which must be distributed under the terms of Sections - 1 and 2 above on a medium customarily used for software interchange; or, - - b) Accompany it with a written offer, valid for at least three - years, to give any third party, for a charge no more than your - cost of physically performing source distribution, a complete - machine-readable copy of the corresponding source code, to be - distributed under the terms of Sections 1 and 2 above on a medium - customarily used for software interchange; or, - - c) Accompany it with the information you received as to the offer - to distribute corresponding source code. (This alternative is - allowed only for noncommercial distribution and only if you - received the program in object code or executable form with such - an offer, in accord with Subsection b above.) - -The source code for a work means the preferred form of the work for -making modifications to it. For an executable work, complete source -code means all the source code for all modules it contains, plus any -associated interface definition files, plus the scripts used to -control compilation and installation of the executable. However, as a -special exception, the source code distributed need not include -anything that is normally distributed (in either source or binary -form) with the major components (compiler, kernel, and so on) of the -operating system on which the executable runs, unless that component -itself accompanies the executable. - -If distribution of executable or object code is made by offering -access to copy from a designated place, then offering equivalent -access to copy the source code from the same place counts as -distribution of the source code, even though third parties are not -compelled to copy the source along with the object code. - - 4. You may not copy, modify, sublicense, or distribute the Program -except as expressly provided under this License. Any attempt -otherwise to copy, modify, sublicense or distribute the Program is -void, and will automatically terminate your rights under this License. -However, parties who have received copies, or rights, from you under -this License will not have their licenses terminated so long as such -parties remain in full compliance. - - 5. You are not required to accept this License, since you have not -signed it. However, nothing else grants you permission to modify or -distribute the Program or its derivative works. These actions are -prohibited by law if you do not accept this License. Therefore, by -modifying or distributing the Program (or any work based on the -Program), you indicate your acceptance of this License to do so, and -all its terms and conditions for copying, distributing or modifying -the Program or works based on it. - - 6. Each time you redistribute the Program (or any work based on the -Program), the recipient automatically receives a license from the -original licensor to copy, distribute or modify the Program subject to -these terms and conditions. You may not impose any further -restrictions on the recipients' exercise of the rights granted herein. -You are not responsible for enforcing compliance by third parties to -this License. - - 7. If, as a consequence of a court judgment or allegation of patent -infringement or for any other reason (not limited to patent issues), -conditions are imposed on you (whether by court order, agreement or -otherwise) that contradict the conditions of this License, they do not -excuse you from the conditions of this License. If you cannot -distribute so as to satisfy simultaneously your obligations under this -License and any other pertinent obligations, then as a consequence you -may not distribute the Program at all. For example, if a patent -license would not permit royalty-free redistribution of the Program by -all those who receive copies directly or indirectly through you, then -the only way you could satisfy both it and this License would be to -refrain entirely from distribution of the Program. - -If any portion of this section is held invalid or unenforceable under -any particular circumstance, the balance of the section is intended to -apply and the section as a whole is intended to apply in other -circumstances. - -It is not the purpose of this section to induce you to infringe any -patents or other property right claims or to contest validity of any -such claims; this section has the sole purpose of protecting the -integrity of the free software distribution system, which is -implemented by public license practices. Many people have made -generous contributions to the wide range of software distributed -through that system in reliance on consistent application of that -system; it is up to the author/donor to decide if he or she is willing -to distribute software through any other system and a licensee cannot -impose that choice. - -This section is intended to make thoroughly clear what is believed to -be a consequence of the rest of this License. - - 8. If the distribution and/or use of the Program is restricted in -certain countries either by patents or by copyrighted interfaces, the -original copyright holder who places the Program under this License -may add an explicit geographical distribution limitation excluding -those countries, so that distribution is permitted only in or among -countries not thus excluded. In such case, this License incorporates -the limitation as if written in the body of this License. - - 9. The Free Software Foundation may publish revised and/or new versions -of the General Public License from time to time. Such new versions will -be similar in spirit to the present version, but may differ in detail to -address new problems or concerns. - -Each version is given a distinguishing version number. If the Program -specifies a version number of this License which applies to it and "any -later version", you have the option of following the terms and conditions -either of that version or of any later version published by the Free -Software Foundation. If the Program does not specify a version number of -this License, you may choose any version ever published by the Free Software -Foundation. - - 10. If you wish to incorporate parts of the Program into other free -programs whose distribution conditions are different, write to the author -to ask for permission. For software which is copyrighted by the Free -Software Foundation, write to the Free Software Foundation; we sometimes -make exceptions for this. Our decision will be guided by the two goals -of preserving the free status of all derivatives of our free software and -of promoting the sharing and reuse of software generally. - - NO WARRANTY - - 11. BECAUSE THE PROGRAM IS LICENSED FREE OF CHARGE, THERE IS NO WARRANTY -FOR THE PROGRAM, TO THE EXTENT PERMITTED BY APPLICABLE LAW. EXCEPT WHEN -OTHERWISE STATED IN WRITING THE COPYRIGHT HOLDERS AND/OR OTHER PARTIES -PROVIDE THE PROGRAM "AS IS" WITHOUT WARRANTY OF ANY KIND, EITHER EXPRESSED -OR IMPLIED, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF -MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE. THE ENTIRE RISK AS -TO THE QUALITY AND PERFORMANCE OF THE PROGRAM IS WITH YOU. SHOULD THE -PROGRAM PROVE DEFECTIVE, YOU ASSUME THE COST OF ALL NECESSARY SERVICING, -REPAIR OR CORRECTION. - - 12. IN NO EVENT UNLESS REQUIRED BY APPLICABLE LAW OR AGREED TO IN WRITING -WILL ANY COPYRIGHT HOLDER, OR ANY OTHER PARTY WHO MAY MODIFY AND/OR -REDISTRIBUTE THE PROGRAM AS PERMITTED ABOVE, BE LIABLE TO YOU FOR DAMAGES, -INCLUDING ANY GENERAL, SPECIAL, INCIDENTAL OR CONSEQUENTIAL DAMAGES ARISING -OUT OF THE USE OR INABILITY TO USE THE PROGRAM (INCLUDING BUT NOT LIMITED -TO LOSS OF DATA OR DATA BEING RENDERED INACCURATE OR LOSSES SUSTAINED BY -YOU OR THIRD PARTIES OR A FAILURE OF THE PROGRAM TO OPERATE WITH ANY OTHER -PROGRAMS), EVEN IF SUCH HOLDER OR OTHER PARTY HAS BEEN ADVISED OF THE -POSSIBILITY OF SUCH DAMAGES. - - END OF TERMS AND CONDITIONS - - Appendix: How to Apply These Terms to Your New Programs - - If you develop a new program, and you want it to be of the greatest -possible use to the public, the best way to achieve this is to make it -free software which everyone can redistribute and change under these terms. - - To do so, attach the following notices to the program. It is safest -to attach them to the start of each source file to most effectively -convey the exclusion of warranty; and each file should have at least -the "copyright" line and a pointer to where the full notice is found. - - - Copyright (C) 19yy - - This program is free software; you can redistribute it and/or modify - it under the terms of the GNU General Public License as published by - the Free Software Foundation; either version 2 of the License, or - (at your option) any later version. - - This program is distributed in the hope that it will be useful, - but WITHOUT ANY WARRANTY; without even the implied warranty of - MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - GNU General Public License for more details. - - You should have received a copy of the GNU General Public License - along with this program; if not, write to the Free Software - Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA. - -Also add information on how to contact you by electronic and paper mail. - -If the program is interactive, make it output a short notice like this -when it starts in an interactive mode: - - Gnomovision version 69, Copyright (C) 19yy name of author - Gnomovision comes with ABSOLUTELY NO WARRANTY; for details type `show w'. - This is free software, and you are welcome to redistribute it - under certain conditions; type `show c' for details. - -The hypothetical commands `show w' and `show c' should show the appropriate -parts of the General Public License. Of course, the commands you use may -be called something other than `show w' and `show c'; they could even be -mouse-clicks or menu items--whatever suits your program. - -You should also get your employer (if you work as a programmer) or your -school, if any, to sign a "copyright disclaimer" for the program, if -necessary. Here is a sample; alter the names: - - Yoyodyne, Inc., hereby disclaims all copyright interest in the program - `Gnomovision' (which makes passes at compilers) written by James Hacker. - - , 1 April 1989 - Ty Coon, President of Vice - -This General Public License does not permit incorporating your program into -proprietary programs. If your program is a subroutine library, you may -consider it more useful to permit linking proprietary applications with the -library. If this is what you want to do, use the GNU Library General -Public License instead of this License. diff --git a/gnu/usr.bin/diff/Makefile b/gnu/usr.bin/diff/Makefile index 7b10534882e6..01c7320b9cc1 100644 --- a/gnu/usr.bin/diff/Makefile +++ b/gnu/usr.bin/diff/Makefile @@ -1,11 +1,18 @@ -# $NetBSD: Makefile,v 1.11 1997/10/25 10:10:30 lukem Exp $ +# $NetBSD: Makefile,v 1.12 1999/02/12 12:45:03 tv Exp $ -PROG= diff -SRCS= diff.c analyze.c cmpbuf.c io.c context.c ed.c normal.c util.c dir.c \ - regex.c side.c ifdef.c version.c getopt.c getopt1.c +PROG= diff +SRCS= diff.c analyze.c cmpbuf.c io.c context.c ed.c normal.c util.c \ + dir.c regex.c side.c ifdef.c version.c getopt.c getopt1.c -CPPFLAGS+=-DHAVE_CONFIG_H -I${.CURDIR} -DPR_PROGRAM=\"/usr/bin/pr\" -LDADD+= -lgnumalloc -DPADD+= ${LIBGNUMALLOC} +CPPFLAGS+= -DHAVE_CONFIG_H -I${.CURDIR} -I${DIST}/diffutils \ + -DPR_PROGRAM=\"/usr/bin/pr\" +LDADD+= -lgnumalloc +DPADD+= ${LIBGNUMALLOC} +TEXINFO= diff.texi + +DIST= ${.CURDIR}/../../dist +.PATH: ${DIST}/diffutils + +.include .include diff --git a/gnu/usr.bin/diff/analyze.c b/gnu/usr.bin/diff/analyze.c deleted file mode 100644 index 556d388c46a4..000000000000 --- a/gnu/usr.bin/diff/analyze.c +++ /dev/null @@ -1,1084 +0,0 @@ -/* Analyze file differences for GNU DIFF. - Copyright (C) 1988, 1989, 1992, 1993 Free Software Foundation, Inc. - -This file is part of GNU DIFF. - -GNU DIFF is free software; you can redistribute it and/or modify -it under the terms of the GNU General Public License as published by -the Free Software Foundation; either version 2, or (at your option) -any later version. - -GNU DIFF is distributed in the hope that it will be useful, -but WITHOUT ANY WARRANTY; without even the implied warranty of -MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the -GNU General Public License for more details. - -You should have received a copy of the GNU General Public License -along with GNU DIFF; see the file COPYING. If not, write to -the Free Software Foundation, 675 Mass Ave, Cambridge, MA 02139, USA. */ - -/* The basic algorithm is described in: - "An O(ND) Difference Algorithm and its Variations", Eugene Myers, - Algorithmica Vol. 1 No. 2, 1986, pp. 251-266; - see especially section 4.2, which describes the variation used below. - Unless the --minimal option is specified, this code uses the TOO_EXPENSIVE - heuristic, by Paul Eggert, to limit the cost to O(N**1.5 log N) - at the price of producing suboptimal output for large inputs with - many differences. - - The basic algorithm was independently discovered as described in: - "Algorithms for Approximate String Matching", E. Ukkonen, - Information and Control Vol. 64, 1985, pp. 100-118. */ - -#include "diff.h" -#include "cmpbuf.h" - -extern int no_discards; - -static int *xvec, *yvec; /* Vectors being compared. */ -static int *fdiag; /* Vector, indexed by diagonal, containing - 1 + the X coordinate of the point furthest - along the given diagonal in the forward - search of the edit matrix. */ -static int *bdiag; /* Vector, indexed by diagonal, containing - the X coordinate of the point furthest - along the given diagonal in the backward - search of the edit matrix. */ -static int too_expensive; /* Edit scripts longer than this are too - expensive to compute. */ - -#define SNAKE_LIMIT 20 /* Snakes bigger than this are considered `big'. */ - -struct partition -{ - int xmid, ymid; /* Midpoints of this partition. */ - int lo_minimal; /* Nonzero if low half will be analyzed minimally. */ - int hi_minimal; /* Likewise for high half. */ -}; - -static int diag PARAMS((int, int, int, int, int, struct partition *)); -static struct change *add_change PARAMS((int, int, int, int, struct change *)); -static struct change *build_reverse_script PARAMS((struct file_data const[])); -static struct change *build_script PARAMS((struct file_data const[])); -static void briefly_report PARAMS((int, struct file_data const[])); -static void compareseq PARAMS((int, int, int, int, int)); -static void discard_confusing_lines PARAMS((struct file_data[])); -static void shift_boundaries PARAMS((struct file_data[])); - -/* Find the midpoint of the shortest edit script for a specified - portion of the two files. - - Scan from the beginnings of the files, and simultaneously from the ends, - doing a breadth-first search through the space of edit-sequence. - When the two searches meet, we have found the midpoint of the shortest - edit sequence. - - If MINIMAL is nonzero, find the minimal edit script regardless - of expense. Otherwise, if the search is too expensive, use - heuristics to stop the search and report a suboptimal answer. - - Set PART->(XMID,YMID) to the midpoint (XMID,YMID). The diagonal number - XMID - YMID equals the number of inserted lines minus the number - of deleted lines (counting only lines before the midpoint). - Return the approximate edit cost; this is the total number of - lines inserted or deleted (counting only lines before the midpoint), - unless a heuristic is used to terminate the search prematurely. - - Set PART->LEFT_MINIMAL to nonzero iff the minimal edit script for the - left half of the partition is known; similarly for PART->RIGHT_MINIMAL. - - This function assumes that the first lines of the specified portions - of the two files do not match, and likewise that the last lines do not - match. The caller must trim matching lines from the beginning and end - of the portions it is going to specify. - - If we return the "wrong" partitions, - the worst this can do is cause suboptimal diff output. - It cannot cause incorrect diff output. */ - -static int -diag (xoff, xlim, yoff, ylim, minimal, part) - int xoff, xlim, yoff, ylim, minimal; - struct partition *part; -{ - int *const fd = fdiag; /* Give the compiler a chance. */ - int *const bd = bdiag; /* Additional help for the compiler. */ - int const *const xv = xvec; /* Still more help for the compiler. */ - int const *const yv = yvec; /* And more and more . . . */ - int const dmin = xoff - ylim; /* Minimum valid diagonal. */ - int const dmax = xlim - yoff; /* Maximum valid diagonal. */ - int const fmid = xoff - yoff; /* Center diagonal of top-down search. */ - int const bmid = xlim - ylim; /* Center diagonal of bottom-up search. */ - int fmin = fmid, fmax = fmid; /* Limits of top-down search. */ - int bmin = bmid, bmax = bmid; /* Limits of bottom-up search. */ - int c; /* Cost. */ - int odd = (fmid - bmid) & 1; /* True if southeast corner is on an odd - diagonal with respect to the northwest. */ - - fd[fmid] = xoff; - bd[bmid] = xlim; - - for (c = 1;; ++c) - { - int d; /* Active diagonal. */ - int big_snake = 0; - - /* Extend the top-down search by an edit step in each diagonal. */ - fmin > dmin ? fd[--fmin - 1] = -1 : ++fmin; - fmax < dmax ? fd[++fmax + 1] = -1 : --fmax; - for (d = fmax; d >= fmin; d -= 2) - { - int x, y, oldx, tlo = fd[d - 1], thi = fd[d + 1]; - - if (tlo >= thi) - x = tlo + 1; - else - x = thi; - oldx = x; - y = x - d; - while (x < xlim && y < ylim && xv[x] == yv[y]) - ++x, ++y; - if (x - oldx > SNAKE_LIMIT) - big_snake = 1; - fd[d] = x; - if (odd && bmin <= d && d <= bmax && bd[d] <= x) - { - part->xmid = x; - part->ymid = y; - part->lo_minimal = part->hi_minimal = 1; - return 2 * c - 1; - } - } - - /* Similarly extend the bottom-up search. */ - bmin > dmin ? bd[--bmin - 1] = INT_MAX : ++bmin; - bmax < dmax ? bd[++bmax + 1] = INT_MAX : --bmax; - for (d = bmax; d >= bmin; d -= 2) - { - int x, y, oldx, tlo = bd[d - 1], thi = bd[d + 1]; - - if (tlo < thi) - x = tlo; - else - x = thi - 1; - oldx = x; - y = x - d; - while (x > xoff && y > yoff && xv[x - 1] == yv[y - 1]) - --x, --y; - if (oldx - x > SNAKE_LIMIT) - big_snake = 1; - bd[d] = x; - if (!odd && fmin <= d && d <= fmax && x <= fd[d]) - { - part->xmid = x; - part->ymid = y; - part->lo_minimal = part->hi_minimal = 1; - return 2 * c; - } - } - - if (minimal) - continue; - - /* Heuristic: check occasionally for a diagonal that has made - lots of progress compared with the edit distance. - If we have any such, find the one that has made the most - progress and return it as if it had succeeded. - - With this heuristic, for files with a constant small density - of changes, the algorithm is linear in the file size. */ - - if (c > 200 && big_snake && heuristic) - { - int best; - - best = 0; - for (d = fmax; d >= fmin; d -= 2) - { - int dd = d - fmid; - int x = fd[d]; - int y = x - d; - int v = (x - xoff) * 2 - dd; - if (v > 12 * (c + (dd < 0 ? -dd : dd))) - { - if (v > best - && xoff + SNAKE_LIMIT <= x && x < xlim - && yoff + SNAKE_LIMIT <= y && y < ylim) - { - /* We have a good enough best diagonal; - now insist that it end with a significant snake. */ - int k; - - for (k = 1; xv[x - k] == yv[y - k]; k++) - if (k == SNAKE_LIMIT) - { - best = v; - part->xmid = x; - part->ymid = y; - break; - } - } - } - } - if (best > 0) - { - part->lo_minimal = 1; - part->hi_minimal = 0; - return 2 * c - 1; - } - - best = 0; - for (d = bmax; d >= bmin; d -= 2) - { - int dd = d - bmid; - int x = bd[d]; - int y = x - d; - int v = (xlim - x) * 2 + dd; - if (v > 12 * (c + (dd < 0 ? -dd : dd))) - { - if (v > best - && xoff < x && x <= xlim - SNAKE_LIMIT - && yoff < y && y <= ylim - SNAKE_LIMIT) - { - /* We have a good enough best diagonal; - now insist that it end with a significant snake. */ - int k; - - for (k = 0; xv[x + k] == yv[y + k]; k++) - if (k == SNAKE_LIMIT - 1) - { - best = v; - part->xmid = x; - part->ymid = y; - break; - } - } - } - } - if (best > 0) - { - part->lo_minimal = 0; - part->hi_minimal = 1; - return 2 * c - 1; - } - } - - /* Heuristic: if we've gone well beyond the call of duty, - give up and report halfway between our best results so far. */ - if (c >= too_expensive) - { - int fxybest, fxbest; - int bxybest, bxbest; - - fxbest = bxbest = 0; /* Pacify `gcc -Wall'. */ - - /* Find forward diagonal that maximizes X + Y. */ - fxybest = -1; - for (d = fmax; d >= fmin; d -= 2) - { - int x = min (fd[d], xlim); - int y = x - d; - if (ylim < y) - x = ylim + d, y = ylim; - if (fxybest < x + y) - { - fxybest = x + y; - fxbest = x; - } - } - - /* Find backward diagonal that minimizes X + Y. */ - bxybest = INT_MAX; - for (d = bmax; d >= bmin; d -= 2) - { - int x = max (xoff, bd[d]); - int y = x - d; - if (y < yoff) - x = yoff + d, y = yoff; - if (x + y < bxybest) - { - bxybest = x + y; - bxbest = x; - } - } - - /* Use the better of the two diagonals. */ - if ((xlim + ylim) - bxybest < fxybest - (xoff + yoff)) - { - part->xmid = fxbest; - part->ymid = fxybest - fxbest; - part->lo_minimal = 1; - part->hi_minimal = 0; - } - else - { - part->xmid = bxbest; - part->ymid = bxybest - bxbest; - part->lo_minimal = 0; - part->hi_minimal = 1; - } - return 2 * c - 1; - } - } -} - -/* Compare in detail contiguous subsequences of the two files - which are known, as a whole, to match each other. - - The results are recorded in the vectors files[N].changed_flag, by - storing a 1 in the element for each line that is an insertion or deletion. - - The subsequence of file 0 is [XOFF, XLIM) and likewise for file 1. - - Note that XLIM, YLIM are exclusive bounds. - All line numbers are origin-0 and discarded lines are not counted. - - If MINIMAL is nonzero, find a minimal difference no matter how - expensive it is. */ - -static void -compareseq (xoff, xlim, yoff, ylim, minimal) - int xoff, xlim, yoff, ylim, minimal; -{ - int * const xv = xvec; /* Help the compiler. */ - int * const yv = yvec; - - /* Slide down the bottom initial diagonal. */ - while (xoff < xlim && yoff < ylim && xv[xoff] == yv[yoff]) - ++xoff, ++yoff; - /* Slide up the top initial diagonal. */ - while (xlim > xoff && ylim > yoff && xv[xlim - 1] == yv[ylim - 1]) - --xlim, --ylim; - - /* Handle simple cases. */ - if (xoff == xlim) - while (yoff < ylim) - files[1].changed_flag[files[1].realindexes[yoff++]] = 1; - else if (yoff == ylim) - while (xoff < xlim) - files[0].changed_flag[files[0].realindexes[xoff++]] = 1; - else - { - int c; - struct partition part; - - /* Find a point of correspondence in the middle of the files. */ - - c = diag (xoff, xlim, yoff, ylim, minimal, &part); - - if (c == 1) - { - /* This should be impossible, because it implies that - one of the two subsequences is empty, - and that case was handled above without calling `diag'. - Let's verify that this is true. */ - abort (); -#if 0 - /* The two subsequences differ by a single insert or delete; - record it and we are done. */ - if (part.xmid - part.ymid < xoff - yoff) - files[1].changed_flag[files[1].realindexes[part.ymid - 1]] = 1; - else - files[0].changed_flag[files[0].realindexes[part.xmid]] = 1; -#endif - } - else - { - /* Use the partitions to split this problem into subproblems. */ - compareseq (xoff, part.xmid, yoff, part.ymid, part.lo_minimal); - compareseq (part.xmid, xlim, part.ymid, ylim, part.hi_minimal); - } - } -} - -/* Discard lines from one file that have no matches in the other file. - - A line which is discarded will not be considered by the actual - comparison algorithm; it will be as if that line were not in the file. - The file's `realindexes' table maps virtual line numbers - (which don't count the discarded lines) into real line numbers; - this is how the actual comparison algorithm produces results - that are comprehensible when the discarded lines are counted. - - When we discard a line, we also mark it as a deletion or insertion - so that it will be printed in the output. */ - -static void -discard_confusing_lines (filevec) - struct file_data filevec[]; -{ - unsigned int f, i; - char *discarded[2]; - int *equiv_count[2]; - int *p; - - /* Allocate our results. */ - p = (int *) xmalloc ((filevec[0].buffered_lines + filevec[1].buffered_lines) - * (2 * sizeof (int))); - for (f = 0; f < 2; f++) - { - filevec[f].undiscarded = p; p += filevec[f].buffered_lines; - filevec[f].realindexes = p; p += filevec[f].buffered_lines; - } - - /* Set up equiv_count[F][I] as the number of lines in file F - that fall in equivalence class I. */ - - p = (int *) xmalloc (filevec[0].equiv_max * (2 * sizeof (int))); - equiv_count[0] = p; - equiv_count[1] = p + filevec[0].equiv_max; - bzero (p, filevec[0].equiv_max * (2 * sizeof (int))); - - for (i = 0; i < filevec[0].buffered_lines; ++i) - ++equiv_count[0][filevec[0].equivs[i]]; - for (i = 0; i < filevec[1].buffered_lines; ++i) - ++equiv_count[1][filevec[1].equivs[i]]; - - /* Set up tables of which lines are going to be discarded. */ - - discarded[0] = xmalloc (sizeof (char) - * (filevec[0].buffered_lines - + filevec[1].buffered_lines)); - discarded[1] = discarded[0] + filevec[0].buffered_lines; - bzero (discarded[0], sizeof (char) * (filevec[0].buffered_lines - + filevec[1].buffered_lines)); - - /* Mark to be discarded each line that matches no line of the other file. - If a line matches many lines, mark it as provisionally discardable. */ - - for (f = 0; f < 2; f++) - { - unsigned int end = filevec[f].buffered_lines; - char *discards = discarded[f]; - int *counts = equiv_count[1 - f]; - int *equivs = filevec[f].equivs; - unsigned int many = 5; - unsigned int tem = end / 64; - - /* Multiply MANY by approximate square root of number of lines. - That is the threshold for provisionally discardable lines. */ - while ((tem = tem >> 2) > 0) - many *= 2; - - for (i = 0; i < end; i++) - { - int nmatch; - if (equivs[i] == 0) - continue; - nmatch = counts[equivs[i]]; - if (nmatch == 0) - discards[i] = 1; - else if (nmatch > many) - discards[i] = 2; - } - } - - /* Don't really discard the provisional lines except when they occur - in a run of discardables, with nonprovisionals at the beginning - and end. */ - - for (f = 0; f < 2; f++) - { - unsigned int end = filevec[f].buffered_lines; - register char *discards = discarded[f]; - - for (i = 0; i < end; i++) - { - /* Cancel provisional discards not in middle of run of discards. */ - if (discards[i] == 2) - discards[i] = 0; - else if (discards[i] != 0) - { - /* We have found a nonprovisional discard. */ - register int j; - unsigned int length; - unsigned int provisional = 0; - - /* Find end of this run of discardable lines. - Count how many are provisionally discardable. */ - for (j = i; j < end; j++) - { - if (discards[j] == 0) - break; - if (discards[j] == 2) - ++provisional; - } - - /* Cancel provisional discards at end, and shrink the run. */ - while (j > i && discards[j - 1] == 2) - discards[--j] = 0, --provisional; - - /* Now we have the length of a run of discardable lines - whose first and last are not provisional. */ - length = j - i; - - /* If 1/4 of the lines in the run are provisional, - cancel discarding of all provisional lines in the run. */ - if (provisional * 4 > length) - { - while (j > i) - if (discards[--j] == 2) - discards[j] = 0; - } - else - { - register unsigned int consec; - unsigned int minimum = 1; - unsigned int tem = length / 4; - - /* MINIMUM is approximate square root of LENGTH/4. - A subrun of two or more provisionals can stand - when LENGTH is at least 16. - A subrun of 4 or more can stand when LENGTH >= 64. */ - while ((tem = tem >> 2) > 0) - minimum *= 2; - minimum++; - - /* Cancel any subrun of MINIMUM or more provisionals - within the larger run. */ - for (j = 0, consec = 0; j < length; j++) - if (discards[i + j] != 2) - consec = 0; - else if (minimum == ++consec) - /* Back up to start of subrun, to cancel it all. */ - j -= consec; - else if (minimum < consec) - discards[i + j] = 0; - - /* Scan from beginning of run - until we find 3 or more nonprovisionals in a row - or until the first nonprovisional at least 8 lines in. - Until that point, cancel any provisionals. */ - for (j = 0, consec = 0; j < length; j++) - { - if (j >= 8 && discards[i + j] == 1) - break; - if (discards[i + j] == 2) - consec = 0, discards[i + j] = 0; - else if (discards[i + j] == 0) - consec = 0; - else - consec++; - if (consec == 3) - break; - } - - /* I advances to the last line of the run. */ - i += length - 1; - - /* Same thing, from end. */ - for (j = 0, consec = 0; j < length; j++) - { - if (j >= 8 && discards[i - j] == 1) - break; - if (discards[i - j] == 2) - consec = 0, discards[i - j] = 0; - else if (discards[i - j] == 0) - consec = 0; - else - consec++; - if (consec == 3) - break; - } - } - } - } - } - - /* Actually discard the lines. */ - for (f = 0; f < 2; f++) - { - char *discards = discarded[f]; - unsigned int end = filevec[f].buffered_lines; - unsigned int j = 0; - for (i = 0; i < end; ++i) - if (no_discards || discards[i] == 0) - { - filevec[f].undiscarded[j] = filevec[f].equivs[i]; - filevec[f].realindexes[j++] = i; - } - else - filevec[f].changed_flag[i] = 1; - filevec[f].nondiscarded_lines = j; - } - - free (discarded[0]); - free (equiv_count[0]); -} - -/* Adjust inserts/deletes of identical lines to join changes - as much as possible. - - We do something when a run of changed lines include a - line at one end and have an excluded, identical line at the other. - We are free to choose which identical line is included. - `compareseq' usually chooses the one at the beginning, - but usually it is cleaner to consider the following identical line - to be the "change". */ - -int inhibit; - -static void -shift_boundaries (filevec) - struct file_data filevec[]; -{ - int f; - - if (inhibit) - return; - - for (f = 0; f < 2; f++) - { - char *changed = filevec[f].changed_flag; - char const *other_changed = filevec[1-f].changed_flag; - int const *equivs = filevec[f].equivs; - int i = 0; - int j = 0; - int i_end = filevec[f].buffered_lines; - - while (1) - { - int runlength, start, corresponding; - - /* Scan forwards to find beginning of another run of changes. - Also keep track of the corresponding point in the other file. */ - - while (i < i_end && changed[i] == 0) - { - while (other_changed[j++]) - continue; - i++; - } - - if (i == i_end) - break; - - start = i; - - /* Find the end of this run of changes. */ - - while (changed[++i]) - continue; - while (other_changed[j]) - j++; - - do - { - /* Record the length of this run of changes, so that - we can later determine whether the run has grown. */ - runlength = i - start; - - /* Move the changed region back, so long as the - previous unchanged line matches the last changed one. - This merges with previous changed regions. */ - - while (start && equivs[start - 1] == equivs[i - 1]) - { - changed[--start] = 1; - changed[--i] = 0; - while (changed[start - 1]) - start--; - while (other_changed[--j]) - continue; - } - - /* Set CORRESPONDING to the end of the changed run, at the last - point where it corresponds to a changed run in the other file. - CORRESPONDING == I_END means no such point has been found. */ - corresponding = other_changed[j - 1] ? i : i_end; - - /* Move the changed region forward, so long as the - first changed line matches the following unchanged one. - This merges with following changed regions. - Do this second, so that if there are no merges, - the changed region is moved forward as far as possible. */ - - while (i != i_end && equivs[start] == equivs[i]) - { - changed[start++] = 0; - changed[i++] = 1; - while (changed[i]) - i++; - while (other_changed[++j]) - corresponding = i; - } - } - while (runlength != i - start); - - /* If possible, move the fully-merged run of changes - back to a corresponding run in the other file. */ - - while (corresponding < i) - { - changed[--start] = 1; - changed[--i] = 0; - while (other_changed[--j]) - continue; - } - } - } -} - -/* Cons an additional entry onto the front of an edit script OLD. - LINE0 and LINE1 are the first affected lines in the two files (origin 0). - DELETED is the number of lines deleted here from file 0. - INSERTED is the number of lines inserted here in file 1. - - If DELETED is 0 then LINE0 is the number of the line before - which the insertion was done; vice versa for INSERTED and LINE1. */ - -static struct change * -add_change (line0, line1, deleted, inserted, old) - int line0, line1, deleted, inserted; - struct change *old; -{ - struct change *new = (struct change *) xmalloc (sizeof (struct change)); - - new->line0 = line0; - new->line1 = line1; - new->inserted = inserted; - new->deleted = deleted; - new->link = old; - return new; -} - -/* Scan the tables of which lines are inserted and deleted, - producing an edit script in reverse order. */ - -static struct change * -build_reverse_script (filevec) - struct file_data const filevec[]; -{ - struct change *script = 0; - char *changed0 = filevec[0].changed_flag; - char *changed1 = filevec[1].changed_flag; - int len0 = filevec[0].buffered_lines; - int len1 = filevec[1].buffered_lines; - - /* Note that changedN[len0] does exist, and contains 0. */ - - int i0 = 0, i1 = 0; - - while (i0 < len0 || i1 < len1) - { - if (changed0[i0] || changed1[i1]) - { - int line0 = i0, line1 = i1; - - /* Find # lines changed here in each file. */ - while (changed0[i0]) ++i0; - while (changed1[i1]) ++i1; - - /* Record this change. */ - script = add_change (line0, line1, i0 - line0, i1 - line1, script); - } - - /* We have reached lines in the two files that match each other. */ - i0++, i1++; - } - - return script; -} - -/* Scan the tables of which lines are inserted and deleted, - producing an edit script in forward order. */ - -static struct change * -build_script (filevec) - struct file_data const filevec[]; -{ - struct change *script = 0; - char *changed0 = filevec[0].changed_flag; - char *changed1 = filevec[1].changed_flag; - int i0 = filevec[0].buffered_lines, i1 = filevec[1].buffered_lines; - - /* Note that changedN[-1] does exist, and contains 0. */ - - while (i0 >= 0 || i1 >= 0) - { - if (changed0[i0 - 1] || changed1[i1 - 1]) - { - int line0 = i0, line1 = i1; - - /* Find # lines changed here in each file. */ - while (changed0[i0 - 1]) --i0; - while (changed1[i1 - 1]) --i1; - - /* Record this change. */ - script = add_change (i0, i1, line0 - i0, line1 - i1, script); - } - - /* We have reached lines in the two files that match each other. */ - i0--, i1--; - } - - return script; -} - -/* If CHANGES, briefly report that two files differed. */ -static void -briefly_report (changes, filevec) - int changes; - struct file_data const filevec[]; -{ - if (changes) - message (no_details_flag ? "Files %s and %s differ\n" - : "Binary files %s and %s differ\n", - filevec[0].name, filevec[1].name); -} - -/* Report the differences of two files. DEPTH is the current directory - depth. */ -int -diff_2_files (filevec, depth) - struct file_data filevec[]; - int depth; -{ - int diags; - int i; - struct change *e, *p; - struct change *script; - int changes; - - - /* If we have detected that either file is binary, - compare the two files as binary. This can happen - only when the first chunk is read. - Also, --brief without any --ignore-* options means - we can speed things up by treating the files as binary. */ - - if (read_files (filevec, no_details_flag & ~ignore_some_changes)) - { - /* Files with different lengths must be different. */ - if (filevec[0].stat.st_size != filevec[1].stat.st_size - && (filevec[0].desc < 0 || S_ISREG (filevec[0].stat.st_mode)) - && (filevec[1].desc < 0 || S_ISREG (filevec[1].stat.st_mode))) - changes = 1; - - /* Standard input equals itself. */ - else if (filevec[0].desc == filevec[1].desc) - changes = 0; - - else - /* Scan both files, a buffer at a time, looking for a difference. */ - { - /* Allocate same-sized buffers for both files. */ - size_t buffer_size = buffer_lcm (STAT_BLOCKSIZE (filevec[0].stat), - STAT_BLOCKSIZE (filevec[1].stat)); - for (i = 0; i < 2; i++) - filevec[i].buffer = xrealloc (filevec[i].buffer, buffer_size); - - for (;; filevec[0].buffered_chars = filevec[1].buffered_chars = 0) - { - /* Read a buffer's worth from both files. */ - for (i = 0; i < 2; i++) - if (0 <= filevec[i].desc) - while (filevec[i].buffered_chars != buffer_size) - { - int r = read (filevec[i].desc, - filevec[i].buffer - + filevec[i].buffered_chars, - buffer_size - filevec[i].buffered_chars); - if (r == 0) - break; - if (r < 0) - pfatal_with_name (filevec[i].name); - filevec[i].buffered_chars += r; - } - - /* If the buffers differ, the files differ. */ - if (filevec[0].buffered_chars != filevec[1].buffered_chars - || (filevec[0].buffered_chars != 0 - && memcmp (filevec[0].buffer, - filevec[1].buffer, - filevec[0].buffered_chars) != 0)) - { - changes = 1; - break; - } - - /* If we reach end of file, the files are the same. */ - if (filevec[0].buffered_chars != buffer_size) - { - changes = 0; - break; - } - } - } - - briefly_report (changes, filevec); - } - else - { - /* Allocate vectors for the results of comparison: - a flag for each line of each file, saying whether that line - is an insertion or deletion. - Allocate an extra element, always zero, at each end of each vector. */ - - size_t s = filevec[0].buffered_lines + filevec[1].buffered_lines + 4; - filevec[0].changed_flag = xmalloc (s); - bzero (filevec[0].changed_flag, s); - filevec[0].changed_flag++; - filevec[1].changed_flag = filevec[0].changed_flag - + filevec[0].buffered_lines + 2; - - /* Some lines are obviously insertions or deletions - because they don't match anything. Detect them now, and - avoid even thinking about them in the main comparison algorithm. */ - - discard_confusing_lines (filevec); - - /* Now do the main comparison algorithm, considering just the - undiscarded lines. */ - - xvec = filevec[0].undiscarded; - yvec = filevec[1].undiscarded; - diags = filevec[0].nondiscarded_lines + filevec[1].nondiscarded_lines + 3; - fdiag = (int *) xmalloc (diags * (2 * sizeof (int))); - bdiag = fdiag + diags; - fdiag += filevec[1].nondiscarded_lines + 1; - bdiag += filevec[1].nondiscarded_lines + 1; - - /* Set TOO_EXPENSIVE to be approximate square root of input size, - bounded below by 256. */ - too_expensive = 1; - for (i = filevec[0].nondiscarded_lines + filevec[1].nondiscarded_lines; - i != 0; i >>= 2) - too_expensive <<= 1; - too_expensive = max (256, too_expensive); - - files[0] = filevec[0]; - files[1] = filevec[1]; - - compareseq (0, filevec[0].nondiscarded_lines, - 0, filevec[1].nondiscarded_lines, no_discards); - - free (fdiag - (filevec[1].nondiscarded_lines + 1)); - - /* Modify the results slightly to make them prettier - in cases where that can validly be done. */ - - shift_boundaries (filevec); - - /* Get the results of comparison in the form of a chain - of `struct change's -- an edit script. */ - - if (output_style == OUTPUT_ED) - script = build_reverse_script (filevec); - else - script = build_script (filevec); - - /* Set CHANGES if we had any diffs. - If some changes are ignored, we must scan the script to decide. */ - if (ignore_blank_lines_flag || ignore_regexp_list) - { - struct change *next = script; - changes = 0; - - while (next && changes == 0) - { - struct change *this, *end; - int first0, last0, first1, last1, deletes, inserts; - - /* Find a set of changes that belong together. */ - this = next; - end = find_change (next); - - /* Disconnect them from the rest of the changes, making them - a hunk, and remember the rest for next iteration. */ - next = end->link; - end->link = 0; - - /* Determine whether this hunk is really a difference. */ - analyze_hunk (this, &first0, &last0, &first1, &last1, - &deletes, &inserts); - - /* Reconnect the script so it will all be freed properly. */ - end->link = next; - - if (deletes || inserts) - changes = 1; - } - } - else - changes = (script != 0); - - if (no_details_flag) - briefly_report (changes, filevec); - else - { - if (changes || ! no_diff_means_no_output) - { - /* Record info for starting up output, - to be used if and when we have some output to print. */ - setup_output (files[0].name, files[1].name, depth); - - switch (output_style) - { - case OUTPUT_CONTEXT: - print_context_script (script, 0); - break; - - case OUTPUT_UNIFIED: - print_context_script (script, 1); - break; - - case OUTPUT_ED: - print_ed_script (script); - break; - - case OUTPUT_FORWARD_ED: - pr_forward_ed_script (script); - break; - - case OUTPUT_RCS: - print_rcs_script (script); - break; - - case OUTPUT_NORMAL: - print_normal_script (script); - break; - - case OUTPUT_IFDEF: - print_ifdef_script (script); - break; - - case OUTPUT_SDIFF: - print_sdiff_script (script); - } - - finish_output (); - } - } - - free (filevec[0].undiscarded); - - free (filevec[0].changed_flag - 1); - - for (i = 1; i >= 0; --i) - free (filevec[i].equivs); - - for (i = 0; i < 2; ++i) - free (filevec[i].linbuf + filevec[i].linbuf_base); - - for (e = script; e; e = p) - { - p = e->link; - free (e); - } - - if (! ROBUST_OUTPUT_STYLE (output_style)) - for (i = 0; i < 2; ++i) - if (filevec[i].missing_newline) - { - error ("No newline at end of file %s", filevec[i].name, ""); - changes = 2; - } - } - - if (filevec[0].buffer != filevec[1].buffer) - free (filevec[0].buffer); - free (filevec[1].buffer); - - return changes; -}