Index: head/contrib/one-true-awk/ChangeLog =================================================================== --- head/contrib/one-true-awk/ChangeLog (nonexistent) +++ head/contrib/one-true-awk/ChangeLog (revision 348511) @@ -0,0 +1,245 @@ +2019-05-29 Arnold D. Robbins + + * lib.c (isclvar): Remove check for additional '=' after + first one. No longer needed. + +2019-01-26 Arnold D. Robbins + + * main.c (version): Updated. + +2019-01-25 Arnold D. Robbins + + * run.c (awkgetline): Check for numeric value in all getline + variants. See the numeric-getline.* files in bugs-fixed directory. + +2018-08-29 Arnold D. Robbins + + * REGRESS: Check for existence of a.out. If not there, run + make. Enable core dumps for T.arnold system status test + to work on MacOS X. + +2018-08-22 Arnold D. Robbins + + * awktest.tar (testdir/T.expr): Fix test for unary plus. + +2018-08-22 Arnold D. Robbins + + * REGRESS: Extract tests if necessary, set PATH to include '.'. + * regdir/beebe.tar (Makefile): Fix longwrds test to prefix + sort with LC_ALL=C. + * awktest.tar: Updated from fixed test suite, directory + it extracts is now called 'testdir' to match what's in top-level + REGRESS script. + * regdir: Removed, as Brian wants to keep the test suite in + the tar file. + +2018-08-22 Arnold D. Robbins + + * FIXES, lib.c, run.c, makefile, main.c: Merge from Brian's tree. + * REGRESS: New file, from Brian. + * awktest.tar: Restored from Brian's tree. + +2018-08-22 Arnold D. Robbins + + * awkgram.y (UPLUS): New token. In the grammar, call op1() + with it. + * maketab.c (proc): Add entry for UPLUS. + * run.c (arith): Handle UPLUS. + * main.c (version): Updated. + * bugs-fixed/unary-plus.awk, bugs-fixed/unary-plus.bad, + bugs-fixed/unary-plus.ok: New files. + +2018-08-10 Arnold D. Robbins + + * TODO: Updated. + * awk.1: Improve use of macros, add some additional explanation + in a few places, alphabetize list of variables. + +2018-08-08 Arnold D. Robbins + + * awk.h (Cell): Add new field `fmt' to track xFMT value used + for a string conversion. + [CONVC, CONVO]: New flag macros. + * bugs-fixed/README: Updated. + * bugs-fixed/string-conv.awk, bugs-fixed/string-conv.bad, + bugs-fixed/string-conv.ok: New files. + * main.c (version): Updated. + * proto.h (flags2str): Add declaration. + * tran.c (setfval): Clear CONVC and CONVO flags and set vp->fmt + to NULL. + (setsval): Ditto. Add large comment and new code to manage + correct conversion of number to string based on various flags + and the value of vp->fmt. The idea is to not convert again + if xFMT is the same as before and we're doing the same conversion. + Otherwise, clear the old flags, set the new, and reconvert. + (flags2str): New function. For debug prints and for use from a debugger. + +2018-08-05 Arnold D. Robbins + + Fix filename conflicts in regdir where the only difference was + in letter case. This caused problems on Windows systems. + + * regdir/Compare.T1: Renamed from regdir/Compare.T. + * regdir/t.delete0: Renamed from regdir/t.delete. + * regdir/t.getline1: Renamed from regdir/t.getline. + * regdir/t.redir1: Renamed from regdir/t.redir. + * regdir/t.split1: Renamed from regdir/t.split. + * regdir/t.sub0: Renamed from regdir/t.sub. + * regdir/REGRESS: Adjusted. + +2018-08-04 Arnold D. Robbins + + With scalpel, tweasers, magnifying glass and bated breath, + borrow code from the NetBSD version of nawk to fix the years-old + bug whereby decrementing the value of NF did not change the + record. + + * lib.c (fldbld): Set donerec to 1 when done. + (setlastfld): New function. + * proto.h (setlastfld): Add declaration. + * run.c (copycell): Make code smarter about flags (from NetBSD code). + * tran.c (setfree): New function. + * tran.c (setfval): Normalize negative zero to positive zero. + If setting NF, clear donerec and call setlastfld(). + (setsval): Remove call to save_old_OFS(). If setting OFS, call + recbld(). If setting NF, clear donerec and call setlastfld(). + + As part of the process, revert OFS-related changes of 2018-05-22: + + * awk.h (saveOFS, saveOFSlen, save_old_OFS): Remove declarations. + * lib.c (recbld): Use *OFS instead of saveOFS. + * run.c (saveOFS, saveOFSlen, save_old_OFS): Remove. + * tran.c (syminit): Remove initialization of saveOFS and saveOFSlen. + + General stuff that goes along with all this: + + * bugs-fixed/README: Updated. + * bugs-fixed/decr-NF.awk, bugs-fixed/decr-NF.bad, + bugs-fixed/decr-NF.ok: New files. + * main.c (version): Updated. + * regdir/README.TESTS: Fix awk book title. + * regdir/T.misc: Revise test to match fixed code. + * run.c (format): Increase size of buffer used for %a test. (Unrelated + to NF or OFS, but fixes a compiler complaint.) + +2018-06-07 Arnold D. Robbins + + * regdir/beebe.tar: Fix longwrds.ok so that the test will pass. + The file was incorrectly sorted. + +2018-06-06 Arnold D. Robbins + + * regdir/T.lilly: Fix the bug again in the second instance + of the code. Thanks to BWK for pointing this out. + +2018-05-31 Arnold D. Robbins + + * regdir/T.lilly: Fix a syntax error and ordering bug + in creating the 'foo' file. + +2018-05-23 Arnold D. Robbins + + * awk.1: Remove standalone 'awk' at the top of file, it messed up + the formatting. Arrange built-in variable list in alphabetical + order. + +2018-05-23 Arnold D. Robbins + + * main.c (version): Add my email address and a date so that + users can tell this isn't straight BWK awk. + * README.md: Minor updates. + * TODO: Updated. + +2018-05-22 Arnold D. Robbins + + Add POSIX-required formats %a and %A. + + * run.c (format): Check for %a support in C library. If there, + allow %a and %A as valid formats. + * TODO: Updated. + * bugs-fixed/README: Updated. + * bugs-fixed/a-format.awk, bugs-fixed/a-format.bad, + bugs-fixed/a-format.ok: New files. + +2018-05-22 Arnold D. Robbins + + * FIXES: Restored a line from a much earlier version that + apparently got lost when the dates were reordered. + * TODO: Updated. + +2018-05-22 Arnold D. Robbins + + * README.md: New file. + +2018-05-22 Arnold D. Robbins + + * regdir/echo.c, regdir/time.c: Minor fixes to compile without + warning on current GCC / Linux. + +2018-05-22 Arnold D. Robbins + + * TODO: New file. + +2018-05-22 Arnold D. Robbins + + * makefile (gitadd, gitpush): Remove these targets. They + should not be automated and were incorrect for things that + would be done regularly. + +2018-05-22 Arnold D. Robbins + + Fix nawk so that [[:blank:]] only matches space and tab instead + of any whitespace character, originally made May 10, 2018. + See bugs-fixed/space.awk. + + This appears to have been a thinko on Brian's part. + + * b.c (charclasses): Use xisblank() function for [[:blank:]]. + * bugs-fixed/README: Updated. + * bugs-fixed/space.awk, bugs-fixed/space.bad, + bugs-fixed/space.ok: New files. + +2018-05-22 Arnold D. Robbins + + * .gitignore: New file. + +2018-05-22 Arnold D. Robbins + + Fix nawk to provide reasonable exit status for system(), + a la gawk, originally made March 12, 2016. See + bugs-fixed/system-status.awk. + + * run.c (bltin): For FSYSTEM, use the macros defined for wait(2) + to produce a reasonable exit value, instead of doing a floating-point + division by 256. + * awk.1: Document the return status values. + * bugs-fixed/README: Updated. + * bugs-fixed/system-status.awk, bugs-fixed/system-status.bad, + bugs-fixed/system-status.ok: New files. + +2018-05-22 Arnold D. Robbins + + Bug fix with respect to rebuilding a record, originally + made August 19, 2014. See bugs-fixed/ofs-rebuild.awk. + + * awk.h (saveOFS, saveOFSlen): Declare new variables. + * lib.c (recbld): Use them when rebuilding the record. + * run.c (saveOFS, saveOFSlen): Define new variables. + (save_old_OFS): New function to save OFS aside. + * tran.c (syminit): Initialize saveOFS and saveOFSlen. + (setsval): If setting a field, call save_old_OFS(). + * bugs-fixed/README, bugs-fixed/ofs-rebuild.awk, + bugs-fixed/ofs-rebuild.bad, bugs-fixed/ofs-rebuild.ok: New files. + +2018-05-22 Arnold D. Robbins + + * makefile (YACC): Use bison. + +2018-05-22 Arnold D. Robbins + + * ChangeLog: Created. + * regdir: Created. Based on contents of awktest.a. + * .gitattributes: Created, to preserve CR LF in regdir/t.crlf. + * awktest.a: Removed. + * regdir/T.gawk, regdir/T.latin1: Updated from awktest.tar. + * awktest.tar: Removed. Index: head/contrib/one-true-awk/FIXES =================================================================== --- head/contrib/one-true-awk/FIXES (revision 348510) +++ head/contrib/one-true-awk/FIXES (revision 348511) @@ -1,1026 +1,1135 @@ /**************************************************************** Copyright (C) Lucent Technologies 1997 All Rights Reserved Permission to use, copy, modify, and distribute this software and its documentation for any purpose and without fee is hereby granted, provided that the above copyright notice appear in all copies and that both that the copyright notice and this permission notice and warranty disclaimer appear in supporting documentation, and that the name Lucent Technologies or any of its entities not be used in advertising or publicity pertaining to distribution of the software without specific, written prior permission. LUCENT DISCLAIMS ALL WARRANTIES WITH REGARD TO THIS SOFTWARE, INCLUDING ALL IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL LUCENT OR ANY OF ITS ENTITIES BE LIABLE FOR ANY SPECIAL, 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. ****************************************************************/ This file lists all bug fixes, changes, etc., made since the AWK book was sent to the printers in August, 1987. +May 29,2019: + Fix check for command line arguments to no longer require that + first character after '=' not be another '='. Reverts change of + August 11, 1989. Thanks to GitHub user Jamie Landeg Jones for + pointing out the issue; from Issue #38. + +Apr 7, 2019: + Update awktest.tar(p.50) to use modern options to sort. Needed + for Android development. Thanks to GitHub user mohd-akram (Mohamed + Akram). From Comment #33. + +Mar 12, 2019: + Added very simplistic support for cross-compiling in the + makefile. We are NOT going to go in the direction of the + autotools, though. Thanks to GitHub user nee-san for + the basic change. (Merged from PR #34.) + +Mar 5, 2019: + Added support for POSIX-standard interval expressions (a.k.a. + bounds, a.k.a. repetition expressions) in regular expressions, + backported (via NetBSD) from Apple awk-24 (20070501). + Thanks to Martijn Dekker for the port. + (Merged from PR #30.) + +Mar 3, 2019: + Merge PRs as follows: + #12: Avoid undefined behaviour when using ctype(3) functions in + relex(). Thanks to GitHub user iamleot. + #31: Make getline handle numeric strings, and update FIXES. Thanks + to GitHub user arnoldrobbins + #32: maketab: support build systems with read-only source. Thanks + to GitHub user enh. + +Jan 25, 2019: + Make getline handle numeric strings properly in all cases. + (Thanks, Arnold.) + +Jan 21, 2019: + Merged a number of small fixes from GitHub pull requests. + Thanks to GitHub users Arnold Robbins (arnoldrobbins), + Cody Mello (melloc) and Christoph Junghans (junghans). + PR numbers: 13-21, 23, 24, 27. + +Oct 25, 2018: + Added test in maketab.c to prevent generating a proctab entry + for YYSTYPE_IS_DEFINED. It was harmless but some gcc settings + generated a warning message. Thanks to Nan Xiao for report. + +Aug 27, 2018: + Disallow '$' in printf formats; arguments evaluated in order + and printed in order. + + Added some casts to silence warnings on debugging printfs. + (Thanks, Arnold.) + +Aug 23, 2018: + A long list of fixes courtesy of Arnold Robbins, + to whom profound thanks. + + 1. ofs-rebuild: OFS value used to rebuild the record was incorrect. + Fixed August 19, 2014. Revised fix August 2018. + + 2. system-status: Instead of a floating-point division by 256, use + the wait(2) macros to create a reasonable exit status. + Fixed March 12, 2016. + + 3. space: Use provided xisblank() function instead of ispace() for + matching [[:blank:]]. + + 4. a-format: Add POSIX standard %a and %A to supported formats. Check + at runtime that this format is available. + + 5. decr-NF: Decrementing NF did not change $0. This is a decades-old + bug. There are interactions with the old and new value of OFS as well. + Most of the fix came from the NetBSD awk. + + 6. string-conv: String conversions of scalars were sticky. Once a + conversion to string happened, even with OFMT, that value was used until + a new numeric value was assigned, even if OFMT differed from CONVFMT, + and also if CONVFMT changed. + + 7. unary-plus: Unary plus on a string constant returned the string. + Instead, it should convert the value to numeric and give that value. + + Also added Arnold's tests for these to awktest.tar as T.arnold. + +Aug 15, 2018: + fixed mangled awktest.tar (thanks, Arnold), posted all + current (very minor) fixes to github / onetrueawk + +Jun 7, 2018: + (yes, a long layoff) + Updated some broken tests (beebe.tar, T.lilly) + [thanks to Arnold Robbins] + +Mar 26, 2015: + buffer overflow in error reporting; thanks to tobias ulmer + and john-mark gurney for spotting it and the fix. + +Feb 4, 2013: + cleaned up a handful of tests that didn't seem to actually + test for correct behavior: T.latin1, T.gawk. + +Jan 5, 2013: + added ,NULL initializer to static Cells in run.c; not really + needed but cleaner. Thanks to Michael Bombardieri. + Dec 20, 2012: fiddled makefile to get correct yacc and bison flags. pick yacc (linux) or bison (mac) as necessary. added __attribute__((__noreturn__)) to a couple of lines in proto.h, to silence someone's enthusiastic checker. fixed obscure call by value bug in split(a[1],a) reported on 9fans. the management of temporary values is just a mess; i took a shortcut by making an extra string copy. thanks to paul patience and arnold robbins for passing it on and for proposed patches. tiny fiddle in setfval to eliminate -0 results in T.expr, which has irritated me for 20+ years. Aug 10, 2011: another fix to avoid core dump with delete(ARGV); again, many thanks to ruslan ermilov. Aug 7, 2011: split(s, a, //) now behaves the same as split(s, a, "") Jun 12, 2011: /pat/, \n /pat/ {...} is now legal, though bad style to use. added checks to new -v code that permits -vnospace; thanks to ruslan ermilov for spotting this and providing the patch. removed fixed limit on number of open files; thanks to aleksey cheusov and christos zoulos. fixed day 1 bug that resurrected deleted elements of ARGV when used as filenames (in lib.c). minor type fiddles to make gcc -Wall -pedantic happier (but not totally so); turned on -fno-strict-aliasing in makefile. May 6, 2011: added #ifdef for isblank. now allows -ffoo as well as -f foo arguments. (thanks, ruslan) May 1, 2011: after advice from todd miller, kevin lo, ruslan ermilov, and arnold robbins, changed srand() to return the previous seed (which is 1 on the first call of srand). the seed is an Awkfloat internally though converted to unsigned int to pass to the library srand(). thanks, everyone. fixed a subtle (and i hope low-probability) overflow error in fldbld, by adding space for one extra \0. thanks to robert bassett for spotting this one and providing a fix. removed the files related to compilation on windows. i no longer have anything like a current windows environment, so i can't test any of it. May 23, 2010: fixed long-standing overflow bug in run.c; many thanks to nelson beebe for spotting it and providing the fix. fixed bug that didn't parse -vd=1 properly; thanks to santiago vila for spotting it. Feb 8, 2010: i give up. replaced isblank with isspace in b.c; there are no consistent header files. Nov 26, 2009: fixed a long-standing issue with when FS takes effect. a change to FS is now noticed immediately for subsequent splits. changed the name getline() to awkgetline() to avoid yet another name conflict somewhere. Feb 11, 2009: temporarily for now defined HAS_ISBLANK, since that seems to be the best way through the thicket. isblank arrived in C99, but seems to be arriving at different systems at different times. Oct 8, 2008: fixed typo in b.c that set tmpvec wrongly. no one had ever run into the problem, apparently. thanks to alistair crooks. Oct 23, 2007: minor fix in lib.c: increase inputFS to 100, change malloc for fields to n+1. fixed memory fault caused by out of order test in setsval. thanks to david o'brien, freebsd, for both fixes. May 1, 2007: fiddle in makefile to fix for BSD make; thanks to igor sobrado. Mar 31, 2007: fixed some null pointer refs calling adjbuf. Feb 21, 2007: fixed a bug in matching the null RE in sub and gsub. thanks to al aho who actually did the fix (in b.c), and to wolfgang seeberg for finding it and providing a very compact test case. fixed quotation in b.c; thanks to Hal Pratt and the Princeton Dante Project. removed some no-effect asserts in run.c. fiddled maketab.c to not complain about bison-generated values. removed the obsolete -V argument; fixed --version to print the version and exit. fixed wording and an outright error in the usage message; thanks to igor sobrado and jason mcintyre. fixed a bug in -d that caused core dump if no program followed. Jan 1, 2007: dropped mac.code from makefile; there are few non-MacOSX mac's these days. Jan 17, 2006: system() not flagged as unsafe in the unadvertised -safe option. found it while enhancing tests before shipping the ;login: article. practice what you preach. removed the 9-years-obsolete -mr and -mf flags. added -version and --version options. core dump on linux with BEGIN {nextfile}, now fixed. removed some #ifdef's in run.c and lex.c that appear to no longer be necessary. Apr 24, 2005: modified lib.c so that values of $0 et al are preserved in the END block, apparently as required by posix. thanks to havard eidnes for the report and code. Jan 14, 2005: fixed infinite loop in parsing, originally found by brian tsang. thanks to arnold robbins for a suggestion that started me rethinking it. Dec 31, 2004: prevent overflow of -f array in main, head off potential error in call of SYNTAX(), test malloc return in lib.c, all with thanks to todd miller. Dec 22, 2004: cranked up size of NCHARS; coverity thinks it can be overrun with smaller size, and i think that's right. added some assertions to b.c to catch places where it might overrun. the RE code is still fragile. Dec 5, 2004: fixed a couple of overflow problems with ridiculous field numbers: e.g., print $(2^32-1). thanks to ruslan ermilov, giorgos keramidas and david o'brien at freebsd.org for patches. this really should be re-done from scratch. Nov 21, 2004: fixed another 25-year-old RE bug, in split. it's another failure to (re-)initialize. thanks to steve fisher for spotting this and providing a good test case. Nov 22, 2003: fixed a bug in regular expressions that dates (so help me) from 1977; it's been there from the beginning. an anchored longest match that was longer than the number of states triggered a failure to initialize the machine properly. many thanks to moinak ghosh for not only finding this one but for providing a fix, in some of the most mysterious code known to man. fixed a storage leak in call() that appears to have been there since 1983 or so -- a function without an explicit return that assigns a string to a parameter leaked a Cell. thanks to moinak ghosh for spotting this very subtle one. Jul 31, 2003: fixed, thanks to andrey chernov and ruslan ermilov, a bug in lex.c that mis-handled the character 255 in input. (it was being compared to EOF with a signed comparison.) Jul 29, 2003: fixed (i think) the long-standing botch that included the beginning of line state ^ for RE's in the set of valid characters; this led to a variety of odd problems, including failure to properly match certain regular expressions in non-US locales. thanks to ruslan for keeping at this one. Jul 28, 2003: n-th try at getting internationalization right, with thanks to volker kiefel, arnold robbins and ruslan ermilov for advice, though they should not be blamed for the outcome. according to posix, "." is the radix character in programs and command line arguments regardless of the locale; otherwise, the locale should prevail for input and output of numbers. so it's intended to work that way. i have rescinded the attempt to use strcoll in expanding shorthands in regular expressions (cclenter). its properties are much too surprising; for example [a-c] matches aAbBc in locale en_US but abBcC in locale fr_CA. i can see how this might arise by implementation but i cannot explain it to a human user. (this behavior can be seen in gawk as well; we're leaning on the same library.) the issue appears to be that strcoll is meant for sorting, where merging upper and lower case may make sense (though note that unix sort does not do this by default either). it is not appropriate for regular expressions, where the goal is to match specific patterns of characters. in any case, the notations [:lower:], etc., are available in awk, and they are more likely to work correctly in most locales. a moratorium is hereby declared on internationalization changes. i apologize to friends and colleagues in other parts of the world. i would truly like to get this "right", but i don't know what that is, and i do not want to keep making changes until it's clear. Jul 4, 2003: fixed bug that permitted non-terminated RE, as in "awk /x". Jun 1, 2003: subtle change to split: if source is empty, number of elems is always 0 and the array is not set. Mar 21, 2003: added some parens to isblank, in another attempt to make things internationally portable. Mar 14, 2003: the internationalization changes, somewhat modified, are now reinstated. in theory awk will now do character comparisons and case conversions in national language, but "." will always be the decimal point separator on input and output regardless of national language. isblank(){} has an #ifndef. this no longer compiles on windows: LC_MESSAGES isn't defined in vc6++. fixed subtle behavior in field and record splitting: if FS is a single character and RS is not empty, \n is NOT a separator. this tortuous reading is found in the awk book; behavior now matches gawk and mawk. Dec 13, 2002: for the moment, the internationalization changes of nov 29 are rolled back -- programs like x = 1.2 don't work in some locales, because the parser is expecting x = 1,2. until i understand this better, this will have to wait. Nov 29, 2002: modified b.c (with tiny changes in main and run) to support locales, using strcoll and iswhatever tests for posix character classes. thanks to ruslan ermilov (ru@freebsd.org) for code. the function isblank doesn't seem to have propagated to any header file near me, so it's there explicitly. not properly tested on non-ascii character sets by me. Jun 28, 2002: modified run/format() and tran/getsval() to do a slightly better job on using OFMT for output from print and CONVFMT for other number->string conversions, as promised by posix and done by gawk and mawk. there are still places where it doesn't work right if CONVFMT is changed; by then the STR attribute of the variable has been irrevocably set. thanks to arnold robbins for code and examples. fixed subtle bug in format that could get core dump. thanks to Jaromir Dolecek for finding and fixing. minor cleanup in run.c / format() at the same time. added some tests for null pointers to debugging printf's, which were never intended for external consumption. thanks to dave kerns (dkerns@lucent.com) for pointing this out. GNU compatibility: an empty regexp matches anything (thanks to dag-erling smorgrav, des@ofug.org). subject to reversion if this does more harm than good. pervasive small changes to make things more const-correct, as reported by gcc's -Wwrite-strings. as it says in the gcc manual, this may be more nuisance than useful. provoked by a suggestion and code from arnaud desitter, arnaud@nimbus.geog.ox.ac.uk minor documentation changes to note that this now compiles out of the box on Mac OS X. Feb 10, 2002: changed types in posix chars structure to quiet solaris cc. Jan 1, 2002: fflush() or fflush("") flushes all files and pipes. length(arrayname) returns number of elements; thanks to arnold robbins for suggestion. added a makefile.win to make it easier to build on windows. based on dan allen's buildwin.bat. Nov 16, 2001: added support for posix character class names like [:digit:], which are not exactly shorter than [0-9] and perhaps no more portable. thanks to dag-erling smorgrav for code. Feb 16, 2001: removed -m option; no longer needed, and it was actually broken (noted thanks to volker kiefel). Feb 10, 2001: fixed an appalling bug in gettok: any sequence of digits, +,-, E, e, and period was accepted as a valid number if it started with a period. this would never have happened with the lex version. other 1-character botches, now fixed, include a bare $ and a bare " at the end of the input. Feb 7, 2001: more (const char *) casts in b.c and tran.c to silence warnings. Nov 15, 2000: fixed a bug introduced in august 1997 that caused expressions like $f[1] to be syntax errors. thanks to arnold robbins for noticing this and providing a fix. Oct 30, 2000: fixed some nextfile bugs: not handling all cases. thanks to arnold robbins for pointing this out. new regressions added. close() is now a function. it returns whatever the library fclose returns, and -1 for closing a file or pipe that wasn't opened. Sep 24, 2000: permit \n explicitly in character classes; won't work right if comes in as "[\n]" but ok as /[\n]/, because of multiple processing of \'s. thanks to arnold robbins. July 5, 2000: minor fiddles in tran.c to keep compilers happy about uschar. thanks to norman wilson. May 25, 2000: yet another attempt at making 8-bit input work, with another band-aid in b.c (member()), and some (uschar) casts to head off potential errors in subscripts (like isdigit). also changed HAT to NCHARS-2. thanks again to santiago vila. changed maketab.c to ignore apparently out of range definitions instead of halting; new freeBSD generates one. thanks to jon snader for pointing out the problem. May 2, 2000: fixed an 8-bit problem in b.c by making several char*'s into unsigned char*'s. not clear i have them all yet. thanks to Santiago Vila for the bug report. Apr 21, 2000: finally found and fixed a memory leak in function call; it's been there since functions were added ~1983. thanks to jon bentley for the test case that found it. added test in envinit to catch environment "variables" with names beginning with '='; thanks to Berend Hasselman. Jul 28, 1999: added test in defn() to catch function foo(foo), which otherwise recurses until core dump. thanks to arnold robbins for noticing this. Jun 20, 1999: added *bp in gettok in lex.c; appears possible to exit function without terminating the string. thanks to russ cox. Jun 2, 1999: added function stdinit() to run to initialize files[] array, in case stdin, etc., are not constants; some compilers care. May 10, 1999: replaced the ERROR ... FATAL, etc., macros with functions based on vprintf, to avoid problems caused by overrunning fixed-size errbuf array. thanks to ralph corderoy for the impetus, and for pointing out a string termination bug in qstring as well. Apr 21, 1999: fixed bug that caused occasional core dumps with commandline variable with value ending in \. (thanks to nelson beebe for the test case.) Apr 16, 1999: with code kindly provided by Bruce Lilly, awk now parses /=/ and similar constructs more sensibly in more places. Bruce also provided some helpful test cases. Apr 5, 1999: changed true/false to True/False in run.c to make it easier to compile with C++. Added some casts on malloc and realloc to be honest about casts; ditto. changed ltype int to long in struct rrow to reduce some 64-bit complaints; other changes scattered throughout for the same purpose. thanks to Nelson Beebe for these portability improvements. removed some horrible pointer-int casting in b.c and elsewhere by adding ptoi and itonp to localize the casts, which are all benign. fixed one incipient bug that showed up on sgi in 64-bit mode. reset lineno for new source file; include filename in error message. also fixed line number error in continuation lines. (thanks to Nelson Beebe for both of these.) Mar 24, 1999: Nelson Beebe notes that irix 5.3 yacc dies with a bogus error; use a newer version or switch to bison, since sgi is unlikely to fix it. Mar 5, 1999: changed isnumber to is_number to avoid the problem caused by versions of ctype.h that include the name isnumber. distribution now includes a script for building on a Mac, thanks to Dan Allen. Feb 20, 1999: fixed memory leaks in run.c (call) and tran.c (setfval). thanks to Stephen Nutt for finding these and providing the fixes. Jan 13, 1999: replaced srand argument by (unsigned int) in run.c; avoids problem on Mac and potentially on Unix & Windows. thanks to Dan Allen. added a few (int) casts to silence useless compiler warnings. e.g., errorflag= in run.c jump(). added proctab.c to the bundle outout; one less thing to have to compile out of the box. added calls to _popen and _pclose to the win95 stub for pipes (thanks to Steve Adams for this helpful suggestion). seems to work, though properties are not well understood by me, and it appears that under some circumstances the pipe output is truncated. Be careful. Oct 19, 1998: fixed a couple of bugs in getrec: could fail to update $0 after a getline var; because inputFS wasn't initialized, could split $0 on every character, a misleading diversion. fixed caching bug in makedfa: LRU was actually removing least often used. thanks to ross ridge for finding these, and for providing great bug reports. May 12, 1998: fixed potential bug in readrec: might fail to update record pointer after growing. thanks to dan levy for spotting this and suggesting the fix. Mar 12, 1998: added -V to print version number and die. + +[notify dave kerns, dkerns@dacsoup.ih.lucent.com] Feb 11, 1998: subtle silent bug in lex.c: if the program ended with a number longer than 1 digit, part of the input would be pushed back and parsed again because token buffer wasn't terminated right. example: awk 'length($0) > 10'. blush. at least i found it myself. Aug 31, 1997: s/adelete/awkdelete/: SGI uses this in malloc.h. thanks to nelson beebe for pointing this one out. Aug 21, 1997: fixed some bugs in sub and gsub when replacement includes \\. this is a dark, horrible corner, but at least now i believe that the behavior is the same as gawk and the intended posix standard. thanks to arnold robbins for advice here. Aug 9, 1997: somewhat regretfully, replaced the ancient lex-based lexical analyzer with one written in C. it's longer, generates less code, and more portable; the old one depended too much on mysterious properties of lex that were not preserved in other environments. in theory these recognize the same language. now using strtod to test whether a string is a number, instead of the convoluted original function. should be more portable and reliable if strtod is implemented right. removed now-pointless optimization in makefile that tries to avoid recompilation when awkgram.y is changed but symbols are not. removed most fixed-size arrays, though a handful remain, some of which are unchecked. you have been warned. Aug 4, 1997: with some trepidation, replaced the ancient code that managed fields and $0 in fixed-size arrays with arrays that grow on demand. there is still some tension between trying to make this run fast and making it clean; not sure it's right yet. the ill-conceived -mr and -mf arguments are now useful only for debugging. previous dynamic string code removed. numerous other minor cleanups along the way. Jul 30, 1997: using code provided by dan levy (to whom profuse thanks), replaced fixed-size arrays and awkward kludges by a fairly uniform mechanism to grow arrays as needed for printf, sub, gsub, etc. Jul 23, 1997: falling off the end of a function returns "" and 0, not 0. thanks to arnold robbins. Jun 17, 1997: replaced several fixed-size arrays by dynamically-created ones in run.c; added overflow tests to some previously unchecked cases. getline, toupper, tolower. getline code is still broken in that recursive calls may wind up using the same space. [fixed later] increased RECSIZE to 8192 to push problems further over the horizon. added \r to \n as input line separator for programs, not data. damn CRLFs. modified format() to permit explicit printf("%c", 0) to include a null byte in output. thanks to ken stailey for the fix. added a "-safe" argument that disables file output (print >, print >>), process creation (cmd|getline, print |, system), and access to the environment (ENVIRON). this is a first approximation to a "safe" version of awk, but don't rely on it too much. thanks to joan feigenbaum and matt blaze for the inspiration long ago. Jul 8, 1996: fixed long-standing bug in sub, gsub(/a/, "\\\\&"); thanks to ralph corderoy. Jun 29, 1996: fixed awful bug in new field splitting; didn't get all the places where input was done. Jun 28, 1996: changed field-splitting to conform to posix definition: fields are split using the value of FS at the time of input; it used to be the value when the field or NF was first referred to, a much less predictable definition. thanks to arnold robbins for encouragement to do the right thing. May 28, 1996: fixed appalling but apparently unimportant bug in parsing octal numbers in reg exprs. explicit hex in reg exprs now limited to 2 chars: \xa, \xaa. May 27, 1996: cleaned up some declarations so gcc -Wall is now almost silent. makefile now includes backup copies of ytab.c and lexyy.c in case one makes before looking; it also avoids recreating lexyy.c unless really needed. s/aprintf/awkprint, s/asprintf/awksprintf/ to avoid some name clashes with unwisely-written header files. thanks to jeffrey friedl for several of these. May 26, 1996: an attempt to rationalize the (unsigned) char issue. almost all instances of unsigned char have been removed; the handful of places in b.c where chars are used as table indices have been hand-crafted. added some latin-1 tests to the regression, but i'm not confident; none of my compilers seem to care much. thanks to nelson beebe for pointing out some others that do care. May 2, 1996: removed all register declarations. enhanced split(), as in gawk, etc: split(s, a, "") splits s into a[1]...a[length(s)] with each character a single element. made the same changes for field-splitting if FS is "". added nextfile, as in gawk: causes immediate advance to next input file. (thanks to arnold robbins for inspiration and code). small fixes to regexpr code: can now handle []], [[], and variants; [] is now a syntax error, rather than matching everything; [z-a] is now empty, not z. far from complete or correct, however. (thanks to jeffrey friedl for pointing out some awful behaviors.) Apr 29, 1996: replaced uchar by uschar everywhere; apparently some compilers usurp this name and this causes conflicts. fixed call to time in run.c (bltin); arg is time_t *. replaced horrible pointer/long punning in b.c by a legitimate union. should be safer on 64-bit machines and cleaner everywhere. (thanks to nelson beebe for pointing out some of these problems.) replaced nested comments by #if 0...#endif in run.c, lib.c. removed getsval, setsval, execute macros from run.c and lib.c. machines are 100x faster than they were when these macros were first used. revised filenames: awk.g.y => awkgram.y, awk.lx.l => awklex.l, y.tab.[ch] => ytab.[ch], lex.yy.c => lexyy.c, all in the aid of portability to nameless systems. "make bundle" now includes yacc and lex output files for recipients who don't have yacc or lex. Aug 15, 1995: initialized Cells in setsymtab more carefully; some fields were not set. (thanks to purify, all of whose complaints i think i now understand.) fixed at least one error in gsub that looked at -1-th element of an array when substituting for a null match (e.g., $). delete arrayname is now legal; it clears the elements but leaves the array, which may not be the right behavior. modified makefile: my current make can't cope with the test used to avoid unnecessary yacc invocations. Jul 17, 1995: added dynamically growing strings to awk.lx.l and b.c to permit regular expressions to be much bigger. the state arrays can still overflow. Aug 24, 1994: detect duplicate arguments in function definitions (mdm). May 11, 1994: trivial fix to printf to limit string size in sub(). Apr 22, 1994: fixed yet another subtle self-assignment problem: $1 = $2; $1 = $1 clobbered $1. Regression tests now use private echo, to avoid quoting problems. Feb 2, 1994: changed error() to print line number as %d, not %g. Jul 23, 1993: cosmetic changes: increased sizes of some arrays, reworded some error messages. added CONVFMT as in posix (just replaced OFMT in getsval) FILENAME is now "" until the first thing that causes a file to be opened. Nov 28, 1992: deleted yyunput and yyoutput from proto.h; different versions of lex give these different declarations. May 31, 1992: added -mr N and -mf N options: more record and fields. these really ought to adjust automatically. cleaned up some error messages; "out of space" now means malloc returned NULL in all cases. changed rehash so that if it runs out, it just returns; things will continue to run slow, but maybe a bit longer. Apr 24, 1992: remove redundant close of stdin when using -f -. got rid of core dump with -d; awk -d just prints date. Apr 12, 1992: added explicit check for /dev/std(in,out,err) in redirection. unlike gawk, no /dev/fd/n yet. added (file/pipe) builtin. hard to test satisfactorily. not posix. Feb 20, 1992: recompile after abortive changes; should be unchanged. Dec 2, 1991: die-casting time: converted to ansi C, installed that. Nov 30, 1991: fixed storage leak in freefa, failing to recover [N]CCL. thanks to Bill Jones (jones@cs.usask.ca) Nov 19, 1991: use RAND_MAX instead of literal in builtin(). Nov 12, 1991: cranked up some fixed-size arrays in b.c, and added a test for overflow in penter. thanks to mark larsen. Sep 24, 1991: increased buffer in gsub. a very crude fix to a general problem. and again on Sep 26. Aug 18, 1991: enforce variable name syntax for commandline variables: has to start with letter or _. Jul 27, 1991: allow newline after ; in for statements. Jul 21, 1991: fixed so that in self-assignment like $1=$1, side effects like recomputing $0 take place. (this is getting subtle.) Jun 30, 1991: better test for detecting too-long output record. Jun 2, 1991: better defense against very long printf strings. made break and continue illegal outside of loops. May 13, 1991: removed extra arg on gettemp, tempfree. minor error message rewording. May 6, 1991: fixed silly bug in hex parsing in hexstr(). removed an apparently unnecessary test in isnumber(). warn about weird printf conversions. fixed unchecked array overwrite in relex(). changed for (i in array) to access elements in sorted order. then unchanged it -- it really does run slower in too many cases. left the code in place, commented out. Feb 10, 1991: check error status on all writes, to avoid banging on full disks. Jan 28, 1991: awk -f - reads the program from stdin. Jan 11, 1991: failed to set numeric state on $0 in cmd|getline context in run.c. Nov 2, 1990: fixed sleazy test for integrality in getsval; use modf. Oct 29, 1990: fixed sleazy buggy code in lib.c that looked (incorrectly) for too long input lines. Oct 14, 1990: fixed the bug on p. 198 in which it couldn't deduce that an argument was an array in some contexts. replaced the error message in intest() by code that damn well makes it an array. Oct 8, 1990: fixed horrible bug: types and values were not preserved in some kinds of self-assignment. (in assign().) Aug 24, 1990: changed NCHARS to 256 to handle 8-bit characters in strings presented to match(), etc. Jun 26, 1990: changed struct rrow (awk.h) to use long instead of int for lval, since cfoll() stores a pointer in it. now works better when int's are smaller than pointers! May 6, 1990: AVA fixed the grammar so that ! is uniformly of the same precedence as unary + and -. This renders illegal some constructs like !x=y, which now has to be parenthesized as !(x=y), and makes others work properly: !x+y is (!x)+y, and x!y is x !y, not two pattern-action statements. (These problems were pointed out by Bob Lenk of Posix.) Added \x to regular expressions (already in strings). Limited octal to octal digits; \8 and \9 are not octal. Centralized the code for parsing escapes in regular expressions. Added a bunch of tests to T.re and T.sub to verify some of this. Feb 9, 1990: fixed null pointer dereference bug in main.c: -F[nothing]. sigh. restored srand behavior: it returns the current seed. Jan 18, 1990: srand now returns previous seed value (0 to start). Jan 5, 1990: fix potential problem in tran.c -- something was freed, then used in freesymtab. Oct 18, 1989: another try to get the max number of open files set with relatively machine-independent code. small fix to input() in case of multiple reads after EOF. Oct 11, 1989: FILENAME is now defined in the BEGIN block -- too many old programs broke. "-" means stdin in getline as well as on the commandline. added a bunch of casts to the code to tell the truth about char * vs. unsigned char *, a right royal pain. added a setlocale call to the front of main, though probably no one has it usefully implemented yet. Aug 24, 1989: removed redundant relational tests against nullnode if parse tree already had a relational at that point. Aug 11, 1989: fixed bug: commandline variable assignment has to look like var=something. (consider the man page for =, in file =.1) changed number of arguments to functions to static arrays to avoid repeated malloc calls. Aug 2, 1989: restored -F (space) separator Jul 30, 1989: added -v x=1 y=2 ... for immediate commandline variable assignment; done before the BEGIN block for sure. they have to precede the program if the program is on the commandline. Modified Aug 2 to require a separate -v for each assignment. Jul 10, 1989: fixed ref-thru-zero bug in environment code in tran.c Jun 23, 1989: add newline to usage message. Jun 14, 1989: added some missing ansi printf conversion letters: %i %X %E %G. no sensible meaning for h or L, so they may not do what one expects. made %* conversions work. changed x^y so that if n is a positive integer, it's done by explicit multiplication, thus achieving maximum accuracy. (this should be done by pow() but it seems not to be locally.) done to x ^= y as well. Jun 4, 1989: ENVIRON array contains environment: if shell variable V=thing, ENVIRON["V"] is "thing" multiple -f arguments permitted. error reporting is naive. (they were permitted before, but only the last was used.) fixed a really stupid botch in the debugging macro dprintf fixed order of evaluation of commandline assignments to match what the book claims: an argument of the form x=e is evaluated at the time it would have been opened if it were a filename (p 63). this invalidates the suggested answer to ex 4-1 (p 195). removed some code that permitted -F (space) fieldseparator, since it didn't quite work right anyway. (restored aug 2) Apr 27, 1989: Line number now accumulated correctly for comment lines. Apr 26, 1989: Debugging output now includes a version date, if one compiles it into the source each time. Apr 9, 1989: Changed grammar to prohibit constants as 3rd arg of sub and gsub; prevents class of overwriting-a-constant errors. (Last one?) This invalidates the "banana" example on page 43 of the book. Added \a ("alert"), \v (vertical tab), \xhhh (hexadecimal), as in ANSI, for strings. Rescinded the sloppiness that permitted non-octal digits in \ooo. Warning: not all compilers and libraries will be able to deal with \x correctly. Jan 9, 1989: Fixed bug that caused tempcell list to contain a duplicate. The fix is kludgy. Dec 17, 1988: Catches some more commandline errors in main. Removed redundant decl of modf in run.c (confuses some compilers). Warning: there's no single declaration of malloc, etc., in awk.h that seems to satisfy all compilers. Dec 7, 1988: Added a bit of code to error printing to avoid printing nulls. (Not clear that it actually would.) Nov 27, 1988: With fear and trembling, modified the grammar to permit multiple pattern-action statements on one line without an explicit separator. By definition, this capitulation to the ghost of ancient implementations remains undefined and thus subject to change without notice or apology. DO NOT COUNT ON IT. Oct 30, 1988: Fixed bug in call() that failed to recover storage. A warning is now generated if there are more arguments in the call than in the definition (in lieu of fixing another storage leak). Oct 20, 1988: Fixed %c: if expr is numeric, use numeric value; otherwise print 1st char of string value. still doesn't work if the value is 0 -- won't print \0. Added a few more checks for running out of malloc. Oct 12, 1988: Fixed bug in call() that freed local arrays twice. Fixed to handle deletion of non-existent array right; complains about attempt to delete non-array element. Sep 30, 1988: Now guarantees to evaluate all arguments of built-in functions, as in C; the appearance is that arguments are evaluated before the function is called. Places affected are sub (gsub was ok), substr, printf, and all the built-in arithmetic functions in bltin(). A warning is generated if a bltin() is called with the wrong number of arguments. This requires changing makeprof on p167 of the book. Aug 23, 1988: setting FILENAME in BEGIN caused core dump, apparently because it was freeing space not allocated by malloc. July 24, 1988: fixed egregious error in toupper/tolower functions. still subject to rescinding, however. July 2, 1988: flush stdout before opening file or pipe July 2, 1988: performance bug in b.c/cgoto(): not freeing some sets of states. partial fix only right now, and the number of states increased to make it less obvious. June 1, 1988: check error status on close May 28, 1988: srand returns seed value it's using. see 1/18/90 May 22, 1988: Removed limit on depth of function calls. May 10, 1988: Fixed lib.c to permit _ in commandline variable names. Mar 25, 1988: main.c fixed to recognize -- as terminator of command- line options. Illegal options flagged. Error reporting slightly cleaned up. Dec 2, 1987: Newer C compilers apply a strict scope rule to extern declarations within functions. Two extern declarations in lib.c and tran.c have been moved to obviate this problem. Oct xx, 1987: Reluctantly added toupper and tolower functions. Subject to rescinding without notice. Sep 17, 1987: Error-message printer had printf(s) instead of printf("%s",s); got core dumps when the message included a %. Sep 12, 1987: Very long printf strings caused core dump; fixed aprintf, asprintf, format to catch them. Can still get a core dump in printf itself. Index: head/contrib/one-true-awk/LICENSE =================================================================== --- head/contrib/one-true-awk/LICENSE (nonexistent) +++ head/contrib/one-true-awk/LICENSE (revision 348511) @@ -0,0 +1,23 @@ +/**************************************************************** +Copyright (C) Lucent Technologies 1997 +All Rights Reserved + +Permission to use, copy, modify, and distribute this software and +its documentation for any purpose and without fee is hereby +granted, provided that the above copyright notice appear in all +copies and that both that the copyright notice and this +permission notice and warranty disclaimer appear in supporting +documentation, and that the name Lucent Technologies or any of +its entities not be used in advertising or publicity pertaining +to distribution of the software without specific, written prior +permission. + +LUCENT DISCLAIMS ALL WARRANTIES WITH REGARD TO THIS SOFTWARE, +INCLUDING ALL IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS. +IN NO EVENT SHALL LUCENT OR ANY OF ITS ENTITIES BE LIABLE FOR ANY +SPECIAL, 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. +****************************************************************/ Index: head/contrib/one-true-awk/REGRESS =================================================================== --- head/contrib/one-true-awk/REGRESS (nonexistent) +++ head/contrib/one-true-awk/REGRESS (revision 348511) @@ -0,0 +1,35 @@ +#! /bin/sh + +case `uname` in +CYGWIN) EXE=a.exe ;; +*) EXE=a.out ;; +esac + +if [ ! -f $EXE ] +then + make || exit 1 +fi + +if [ -d testdir ] +then + true # do nothing +elif [ -f awktest.tar ] +then + echo extracting testdir + tar -xpf awktest.tar +else + echo $0: No testdir directory and no awktest.tar to extract it from! >&2 + exit 1 +fi + +cd testdir +pwd +PATH=.:$PATH +export PATH +if (ulimit -c unlimited > /dev/null 2>&1) +then + # Workaround broken default on MacOS X + ulimit -c unlimited +fi + +REGRESS Property changes on: head/contrib/one-true-awk/REGRESS ___________________________________________________________________ Added: svn:executable ## -0,0 +1 ## +* \ No newline at end of property Index: head/contrib/one-true-awk/awk.1 =================================================================== --- head/contrib/one-true-awk/awk.1 (revision 348510) +++ head/contrib/one-true-awk/awk.1 (revision 348511) @@ -1,533 +1,565 @@ .de EX .nf .ft CW .. .de EE .br .fi .ft 1 .. -awk .TH AWK 1 .CT 1 files prog_other .SH NAME awk \- pattern-directed scanning and processing language .SH SYNOPSIS .B awk [ .BI \-F .I fs ] [ .BI \-v .I var=value ] [ .I 'prog' | .BI \-f .I progfile ] [ .I file ... ] .SH DESCRIPTION .I Awk scans each input .I file for lines that match any of a set of patterns specified literally in -.IR prog +.I prog or in one or more files specified as .B \-f .IR progfile . With each pattern there can be an associated action that will be performed when a line of a .I file matches the pattern. Each line is matched against the pattern portion of every pattern-action statement; the associated action is performed for each matched pattern. The file name .B \- means the standard input. Any -.IR file +.I file of the form .I var=value is treated as an assignment, not a filename, and is executed at the time it would have been opened if it were a filename. The option .B \-v followed by .I var=value is an assignment to be done before .I prog is executed; any number of .B \-v options may be present. The .B \-F -.IR fs +.I fs option defines the input field separator to be the regular expression -.IR fs. +.IR fs . .PP An input line is normally made up of fields separated by white space, -or by regular expression +or by the regular expression .BR FS . The fields are denoted .BR $1 , .BR $2 , \&..., while .B $0 refers to the entire line. If .BR FS is null, the input line is split into one field per character. .PP -A pattern-action statement has the form +A pattern-action statement has the form: .IP .IB pattern " { " action " } .PP A missing .BI { " action " } means print the line; a missing pattern always matches. Pattern-action statements are separated by newlines or semicolons. .PP An action is a sequence of statements. A statement can be one of the following: .PP .EX -.ta \w'\f(CWdelete array[expression]'u +.ta \w'\f(CWdelete array[expression]\fR'u .RS .nf .ft CW if(\fI expression \fP)\fI statement \fP\fR[ \fPelse\fI statement \fP\fR]\fP while(\fI expression \fP)\fI statement\fP for(\fI expression \fP;\fI expression \fP;\fI expression \fP)\fI statement\fP for(\fI var \fPin\fI array \fP)\fI statement\fP do\fI statement \fPwhile(\fI expression \fP) break continue {\fR [\fP\fI statement ... \fP\fR] \fP} \fIexpression\fP #\fR commonly\fP\fI var = expression\fP print\fR [ \fP\fIexpression-list \fP\fR] \fP\fR[ \fP>\fI expression \fP\fR]\fP printf\fI format \fP\fR[ \fP,\fI expression-list \fP\fR] \fP\fR[ \fP>\fI expression \fP\fR]\fP return\fR [ \fP\fIexpression \fP\fR]\fP next #\fR skip remaining patterns on this input line\fP nextfile #\fR skip rest of this file, open next, start at top\fP delete\fI array\fP[\fI expression \fP] #\fR delete an array element\fP delete\fI array\fP #\fR delete all elements of array\fP exit\fR [ \fP\fIexpression \fP\fR]\fP #\fR exit immediately; status is \fP\fIexpression\fP .fi .RE .EE .DT .PP Statements are terminated by semicolons, newlines or right braces. An empty .I expression-list stands for .BR $0 . String constants are quoted \&\f(CW"\ "\fR, with the usual C escapes recognized within. Expressions take on string or numeric values as appropriate, and are built using the operators .B + \- * / % ^ (exponentiation), and concatenation (indicated by white space). The operators .B ! ++ \-\- += \-= *= /= %= ^= > >= < <= == != ?: are also available in expressions. Variables may be scalars, array elements (denoted -.IB x [ i ] ) +.IB x [ i ] \fR) or fields. Variables are initialized to the null string. Array subscripts may be any string, not necessarily numeric; this allows for a form of associative memory. Multiple subscripts such as .B [i,j,k] are permitted; the constituents are concatenated, separated by the value of .BR SUBSEP . .PP The .B print statement prints its arguments on the standard output (or on a file if -.BI > file +.BI > " file or -.BI >> file +.BI >> " file is present or on a pipe if -.BI | cmd +.BI | " cmd is present), separated by the current output field separator, and terminated by the output record separator. .I file and .I cmd may be literal names or parenthesized expressions; identical string values in different statements denote the same open file. The .B printf -statement formats its expression list according to the format +statement formats its expression list according to the +.I format (see -.IR printf (3)) . +.IR printf (3)). The built-in function .BI close( expr ) closes the file or pipe .IR expr . The built-in function .BI fflush( expr ) flushes any buffered output for the file or pipe .IR expr . .PP The mathematical functions +.BR atan2 , +.BR cos , .BR exp , .BR log , -.BR sqrt , .BR sin , -.BR cos , and -.BR atan2 +.B sqrt are built in. Other built-in functions: .TF length .TP .B length the length of its argument taken as a string, -or of +number of elements in an array for an array argument, +or length of .B $0 if no argument. .TP .B rand random number on [0,1) .TP .B srand sets seed for .B rand and returns the previous seed. .TP .B int truncates to an integer value .TP -.BI substr( s , " m" , " n\fB) +\fBsubstr(\fIs\fB, \fIm\fR [\fB, \fIn\^\fR]\fB)\fR the .IR n -character substring of .I s that begins at position -.IR m +.I m counted from 1. +If no +.IR m , +use the rest of the string +.I .TP .BI index( s , " t" ) the position in .I s where the string .I t occurs, or 0 if it does not. .TP .BI match( s , " r" ) the position in .I s where the regular expression .I r occurs, or 0 if it does not. The variables .B RSTART and .B RLENGTH are set to the position and length of the matched string. .TP -.BI split( s , " a" , " fs\fB) +\fBsplit(\fIs\fB, \fIa \fR[\fB, \fIfs\^\fR]\fB)\fR splits the string .I s into array elements -.IB a [1] , -.IB a [2] , +.IB a [1] \fR, +.IB a [2] \fR, \&..., -.IB a [ n ] , +.IB a [ n ] \fR, and returns .IR n . The separation is done with the regular expression .I fs or with the field separator .B FS if .I fs is not given. An empty string as field separator splits the string into one array element per character. .TP -.BI sub( r , " t" , " s\fB) +\fBsub(\fIr\fB, \fIt \fR[, \fIs\^\fR]\fB) substitutes .I t for the first occurrence of the regular expression .I r in the string .IR s . If .I s is not given, .B $0 is used. .TP -.B gsub +\fBgsub(\fIr\fB, \fIt \fR[, \fIs\^\fR]\fB) same as .B sub except that all occurrences of the regular expression are replaced; .B sub and .B gsub return the number of replacements. .TP -.BI sprintf( fmt , " expr" , " ...\fB ) +.BI sprintf( fmt , " expr" , " ...\fB) the string resulting from formatting .I expr ... according to the .IR printf (3) format -.I fmt +.IR fmt . .TP .BI system( cmd ) executes .I cmd -and returns its exit status +and returns its exit status. This will be \-1 upon error, +.IR cmd 's +exit status upon a normal exit, +256 + +.I sig +upon death-by-signal, where +.I sig +is the number of the murdering signal, +or 512 + +.I sig +if there was a core dump. .TP .BI tolower( str ) returns a copy of .I str with all upper-case characters translated to their corresponding lower-case equivalents. .TP .BI toupper( str ) returns a copy of .I str with all lower-case characters translated to their corresponding upper-case equivalents. .PD .PP The ``function'' .B getline sets .B $0 to the next input record from the current input file; .B getline -.BI < file +.BI < " file sets .B $0 to the next record from .IR file . .B getline .I x sets variable .I x instead. Finally, .IB cmd " | getline pipes the output of .I cmd into .BR getline ; each call of .B getline returns the next line of output from .IR cmd . In all cases, .B getline returns 1 for a successful input, 0 for end of file, and \-1 for an error. .PP Patterns are arbitrary Boolean combinations (with .BR "! || &&" ) of regular expressions and relational expressions. Regular expressions are as in .IR egrep (1) except numeric quantifiers are not supported beyond the basic .B + and .B ? for quantities \&\f(CW"0 or 1"\fP and \&\f(CW"1 or more"\fP respectively. Isolated regular expressions in a pattern apply to the entire line. Regular expressions may also occur in relational expressions, using the operators -.BR ~ +.B ~ and .BR !~ . .BI / re / is a constant regular expression; any string (constant or variable) may be used as a regular expression, except in the position of an isolated regular expression in a pattern. .PP A pattern may consist of two patterns separated by a comma; in this case, the action is performed for all lines from an occurrence of the first pattern though an occurrence of the second. .PP A relational expression is one of the following: .IP .I expression matchop regular-expression .br .I expression relop expression .br .IB expression " in " array-name .br .BI ( expr , expr,... ") in " array-name .PP -where a relop is any of the six relational operators in C, -and a matchop is either +where a +.I relop +is any of the six relational operators in C, +and a +.I matchop +is either .B ~ (matches) or .B !~ (does not match). A conditional is an arithmetic expression, a relational expression, or a Boolean combination of these. .PP The special patterns .B BEGIN and .B END may be used to capture control before the first input line is read and after the last. .B BEGIN and .B END do not combine with other patterns. +They may appear multiple times in a program and execute +in the order they are read by +.IR awk . .PP Variable names with special meanings: .TF FILENAME .TP +.B ARGC +argument count, assignable. +.TP +.B ARGV +argument array, assignable; +non-null members are taken as filenames. +.TP .B CONVFMT conversion format used when converting numbers (default -.BR "%.6g" ) +.BR "%.6g" ). .TP +.B ENVIRON +array of environment variables; subscripts are names. +.TP +.B FILENAME +the name of the current input file. +.TP +.B FNR +ordinal number of the current record in the current file. +.TP .B FS regular expression used to separate fields; also settable by option -.BI \-F fs. +.BI \-F fs\fR. .TP .BR NF -number of fields in the current record +number of fields in the current record. .TP .B NR -ordinal number of the current record +ordinal number of the current record. .TP -.B FNR -ordinal number of the current record in the current file +.B OFMT +output format for numbers (default +.BR "%.6g" ). .TP -.B FILENAME -the name of the current input file -.TP -.B RS -input record separator (default newline) -.TP .B OFS -output field separator (default blank) +output field separator (default space). .TP .B ORS -output record separator (default newline) +output record separator (default newline). .TP -.B OFMT -output format for numbers (default -.BR "%.6g" ) +.B RLENGTH +the length of a string matched by +.BR match . .TP -.B SUBSEP -separates multiple subscripts (default 034) +.B RS +input record separator (default newline). .TP -.B ARGC -argument count, assignable +.B RSTART +the start position of a string matched by +.BR match . .TP -.B ARGV -argument array, assignable; -non-null members are taken as filenames -.TP -.B ENVIRON -array of environment variables; subscripts are names. +.B SUBSEP +separates multiple subscripts (default 034). .PD .PP Functions may be defined (at the position of a pattern-action statement) thus: .IP .B function foo(a, b, c) { ...; return x } .PP Parameters are passed by value if scalar and by reference if array name; functions may be called recursively. Parameters are local to the function; all other variables are global. Thus local variables may be created by providing excess parameters in the function definition. .SH EXAMPLES .TP .EX length($0) > 72 .EE Print lines longer than 72 characters. .TP .EX { print $2, $1 } .EE Print first two fields in opposite order. .PP .EX BEGIN { FS = ",[ \et]*|[ \et]+" } { print $2, $1 } .EE .ns .IP -Same, with input fields separated by comma and/or blanks and tabs. +Same, with input fields separated by comma and/or spaces and tabs. .PP .EX .nf { s += $1 } END { print "sum is", s, " average is", s/NR } .fi .EE .ns .IP Add up first column, print sum and average. .TP .EX /start/, /stop/ .EE Print all lines between start/stop pairs. .PP .EX .nf BEGIN { # Simulate echo(1) for (i = 1; i < ARGC; i++) printf "%s ", ARGV[i] printf "\en" exit } .fi .EE .SH SEE ALSO +.IR grep (1), .IR lex (1), .IR sed (1) .br A. V. Aho, B. W. Kernighan, P. J. Weinberger, -.I -The AWK Programming Language, -Addison-Wesley, 1988. ISBN 0-201-07981-X +.IR "The AWK Programming Language" , +Addison-Wesley, 1988. ISBN 0-201-07981-X. .SH BUGS There are no explicit conversions between numbers and strings. To force an expression to be treated as a number add 0 to it; to force it to be treated as a string concatenate \&\f(CW""\fP to it. .br The scope rules for variables in functions are a botch; the syntax is worse. +.br +Only eight-bit characters sets are handled correctly. Index: head/contrib/one-true-awk/awk.h =================================================================== --- head/contrib/one-true-awk/awk.h (revision 348510) +++ head/contrib/one-true-awk/awk.h (revision 348511) @@ -1,239 +1,247 @@ /**************************************************************** Copyright (C) Lucent Technologies 1997 All Rights Reserved Permission to use, copy, modify, and distribute this software and its documentation for any purpose and without fee is hereby granted, provided that the above copyright notice appear in all copies and that both that the copyright notice and this permission notice and warranty disclaimer appear in supporting documentation, and that the name Lucent Technologies or any of its entities not be used in advertising or publicity pertaining to distribution of the software without specific, written prior permission. LUCENT DISCLAIMS ALL WARRANTIES WITH REGARD TO THIS SOFTWARE, INCLUDING ALL IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL LUCENT OR ANY OF ITS ENTITIES BE LIABLE FOR ANY SPECIAL, 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. ****************************************************************/ #include typedef double Awkfloat; /* unsigned char is more trouble than it's worth */ typedef unsigned char uschar; #define xfree(a) { if ((a) != NULL) { free((void *) (a)); (a) = NULL; } } #define NN(p) ((p) ? (p) : "(null)") /* guaranteed non-null for dprintf */ #define DEBUG #ifdef DEBUG /* uses have to be doubly parenthesized */ # define dprintf(x) if (dbg) printf x #else # define dprintf(x) #endif extern int compile_time; /* 1 if compiling, 0 if running */ extern int safe; /* 0 => unsafe, 1 => safe */ #define RECSIZE (8 * 1024) /* sets limit on records, fields, etc., etc. */ extern int recsize; /* size of current record, orig RECSIZE */ extern char **FS; extern char **RS; extern char **ORS; extern char **OFS; extern char **OFMT; extern Awkfloat *NR; extern Awkfloat *FNR; extern Awkfloat *NF; extern char **FILENAME; extern char **SUBSEP; extern Awkfloat *RSTART; extern Awkfloat *RLENGTH; extern char *record; /* points to $0 */ extern int lineno; /* line number in awk program */ extern int errorflag; /* 1 if error has occurred */ extern int donefld; /* 1 if record broken into fields */ extern int donerec; /* 1 if record is valid (no fld has changed */ extern char inputFS[]; /* FS at time of input, for field splitting */ extern int dbg; extern char *patbeg; /* beginning of pattern matched */ extern int patlen; /* length of pattern matched. set in b.c */ /* Cell: all information about a variable or constant */ typedef struct Cell { uschar ctype; /* OCELL, OBOOL, OJUMP, etc. */ uschar csub; /* CCON, CTEMP, CFLD, etc. */ char *nval; /* name, for variables only */ char *sval; /* string value */ Awkfloat fval; /* value as number */ - int tval; /* type info: STR|NUM|ARR|FCN|FLD|CON|DONTFREE */ + int tval; /* type info: STR|NUM|ARR|FCN|FLD|CON|DONTFREE|CONVC|CONVO */ + char *fmt; /* CONVFMT/OFMT value used to convert from number */ struct Cell *cnext; /* ptr to next if chained */ } Cell; typedef struct Array { /* symbol table array */ int nelem; /* elements in table right now */ int size; /* size of tab */ Cell **tab; /* hash table pointers */ } Array; #define NSYMTAB 50 /* initial size of a symbol table */ extern Array *symtab; extern Cell *nrloc; /* NR */ extern Cell *fnrloc; /* FNR */ +extern Cell *fsloc; /* FS */ extern Cell *nfloc; /* NF */ +extern Cell *ofsloc; /* OFS */ +extern Cell *orsloc; /* ORS */ +extern Cell *rsloc; /* RS */ extern Cell *rstartloc; /* RSTART */ extern Cell *rlengthloc; /* RLENGTH */ +extern Cell *subseploc; /* SUBSEP */ /* Cell.tval values: */ #define NUM 01 /* number value is valid */ #define STR 02 /* string value is valid */ #define DONTFREE 04 /* string space is not freeable */ #define CON 010 /* this is a constant */ #define ARR 020 /* this is an array */ #define FCN 040 /* this is a function name */ #define FLD 0100 /* this is a field $1, $2, ... */ #define REC 0200 /* this is $0 */ +#define CONVC 0400 /* string was converted from number via CONVFMT */ +#define CONVO 01000 /* string was converted from number via OFMT */ /* function types */ #define FLENGTH 1 #define FSQRT 2 #define FEXP 3 #define FLOG 4 #define FINT 5 #define FSYSTEM 6 #define FRAND 7 #define FSRAND 8 #define FSIN 9 #define FCOS 10 #define FATAN 11 #define FTOUPPER 12 #define FTOLOWER 13 #define FFLUSH 14 #define FAND 15 #define FFOR 16 #define FXOR 17 #define FCOMPL 18 #define FLSHIFT 19 #define FRSHIFT 20 /* Node: parse tree is made of nodes, with Cell's at bottom */ typedef struct Node { int ntype; struct Node *nnext; int lineno; int nobj; struct Node *narg[1]; /* variable: actual size set by calling malloc */ } Node; #define NIL ((Node *) 0) extern Node *winner; extern Node *nullstat; extern Node *nullnode; /* ctypes */ #define OCELL 1 #define OBOOL 2 #define OJUMP 3 /* Cell subtypes: csub */ #define CFREE 7 #define CCOPY 6 #define CCON 5 #define CTEMP 4 #define CNAME 3 #define CVAR 2 #define CFLD 1 #define CUNK 0 /* bool subtypes */ #define BTRUE 11 #define BFALSE 12 /* jump subtypes */ #define JEXIT 21 #define JNEXT 22 #define JBREAK 23 #define JCONT 24 #define JRET 25 #define JNEXTFILE 26 /* node types */ #define NVALUE 1 #define NSTAT 2 #define NEXPR 3 extern int pairstack[], paircnt; #define notlegal(n) (n <= FIRSTTOKEN || n >= LASTTOKEN || proctab[n-FIRSTTOKEN] == nullproc) #define isvalue(n) ((n)->ntype == NVALUE) #define isexpr(n) ((n)->ntype == NEXPR) #define isjump(n) ((n)->ctype == OJUMP) #define isexit(n) ((n)->csub == JEXIT) #define isbreak(n) ((n)->csub == JBREAK) #define iscont(n) ((n)->csub == JCONT) #define isnext(n) ((n)->csub == JNEXT || (n)->csub == JNEXTFILE) #define isret(n) ((n)->csub == JRET) #define isrec(n) ((n)->tval & REC) #define isfld(n) ((n)->tval & FLD) #define isstr(n) ((n)->tval & STR) #define isnum(n) ((n)->tval & NUM) #define isarr(n) ((n)->tval & ARR) #define isfcn(n) ((n)->tval & FCN) #define istrue(n) ((n)->csub == BTRUE) #define istemp(n) ((n)->csub == CTEMP) #define isargument(n) ((n)->nobj == ARG) /* #define freeable(p) (!((p)->tval & DONTFREE)) */ #define freeable(p) ( ((p)->tval & (STR|DONTFREE)) == STR ) /* structures used by regular expression matching machinery, mostly b.c: */ #define NCHARS (256+3) /* 256 handles 8-bit chars; 128 does 7-bit */ /* watch out in match(), etc. */ #define NSTATES 32 typedef struct rrow { long ltype; /* long avoids pointer warnings on 64-bit */ union { int i; Node *np; uschar *up; } lval; /* because Al stores a pointer in it! */ int *lfollow; } rrow; typedef struct fa { uschar gototab[NSTATES][NCHARS]; uschar out[NSTATES]; uschar *restr; int *posns[NSTATES]; int anchor; int use; int initstat; int curstat; int accept; int reset; struct rrow re[1]; /* variable: actual size set by calling malloc */ } fa; #include "proto.h" Index: head/contrib/one-true-awk/awkgram.y =================================================================== --- head/contrib/one-true-awk/awkgram.y (revision 348510) +++ head/contrib/one-true-awk/awkgram.y (revision 348511) @@ -1,486 +1,486 @@ /**************************************************************** Copyright (C) Lucent Technologies 1997 All Rights Reserved Permission to use, copy, modify, and distribute this software and its documentation for any purpose and without fee is hereby granted, provided that the above copyright notice appear in all copies and that both that the copyright notice and this permission notice and warranty disclaimer appear in supporting documentation, and that the name Lucent Technologies or any of its entities not be used in advertising or publicity pertaining to distribution of the software without specific, written prior permission. LUCENT DISCLAIMS ALL WARRANTIES WITH REGARD TO THIS SOFTWARE, INCLUDING ALL IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL LUCENT OR ANY OF ITS ENTITIES BE LIABLE FOR ANY SPECIAL, 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. ****************************************************************/ %{ #include #include #include "awk.h" void checkdup(Node *list, Cell *item); int yywrap(void) { return(1); } Node *beginloc = 0; Node *endloc = 0; int infunc = 0; /* = 1 if in arglist or body of func */ int inloop = 0; /* = 1 if in while, for, do */ char *curfname = 0; /* current function name */ Node *arglist = 0; /* list of args for current function */ %} %union { Node *p; Cell *cp; int i; char *s; } %token FIRSTTOKEN /* must be first */ %token

PROGRAM PASTAT PASTAT2 XBEGIN XEND %token NL ',' '{' '(' '|' ';' '/' ')' '}' '[' ']' %token ARRAY %token MATCH NOTMATCH MATCHOP %token FINAL DOT ALL CCL NCCL CHAR OR STAR QUEST PLUS EMPTYRE %token AND BOR APPEND EQ GE GT LE LT NE IN %token ARG BLTIN BREAK CLOSE CONTINUE DELETE DO EXIT FOR FUNC %token SUB GSUB IF INDEX LSUBSTR MATCHFCN NEXT NEXTFILE %token ADD MINUS MULT DIVIDE MOD %token ASSIGN ASGNOP ADDEQ SUBEQ MULTEQ DIVEQ MODEQ POWEQ %token PRINT PRINTF SPRINTF %token

ELSE INTEST CONDEXPR %token POSTINCR PREINCR POSTDECR PREDECR %token VAR IVAR VARNF CALL NUMBER STRING %token REGEXPR %type

pas pattern ppattern plist pplist patlist prarg term re %type

pa_pat pa_stat pa_stats %type reg_expr %type

simple_stmt opt_simple_stmt stmt stmtlist %type

var varname funcname varlist %type

for if else while %type do st %type pst opt_pst lbrace rbrace rparen comma nl opt_nl and bor %type subop print %right ASGNOP %right '?' %right ':' %left BOR %left AND %left GETLINE %nonassoc APPEND EQ GE GT LE LT NE MATCHOP IN '|' %left ARG BLTIN BREAK CALL CLOSE CONTINUE DELETE DO EXIT FOR FUNC %left GSUB IF INDEX LSUBSTR MATCHFCN NEXT NUMBER %left PRINT PRINTF RETURN SPLIT SPRINTF STRING SUB SUBSTR %left REGEXPR VAR VARNF IVAR WHILE '(' %left CAT %left '+' '-' %left '*' '/' '%' -%left NOT UMINUS +%left NOT UMINUS UPLUS %right POWER %right DECR INCR %left INDIRECT %token LASTTOKEN /* must be last */ %% program: pas { if (errorflag==0) winner = (Node *)stat3(PROGRAM, beginloc, $1, endloc); } | error { yyclearin; bracecheck(); SYNTAX("bailing out"); } ; and: AND | and NL ; bor: BOR | bor NL ; comma: ',' | comma NL ; do: DO | do NL ; else: ELSE | else NL ; for: FOR '(' opt_simple_stmt ';' opt_nl pattern ';' opt_nl opt_simple_stmt rparen {inloop++;} stmt { --inloop; $$ = stat4(FOR, $3, notnull($6), $9, $12); } | FOR '(' opt_simple_stmt ';' ';' opt_nl opt_simple_stmt rparen {inloop++;} stmt { --inloop; $$ = stat4(FOR, $3, NIL, $7, $10); } | FOR '(' varname IN varname rparen {inloop++;} stmt { --inloop; $$ = stat3(IN, $3, makearr($5), $8); } ; funcname: VAR { setfname($1); } | CALL { setfname($1); } ; if: IF '(' pattern rparen { $$ = notnull($3); } ; lbrace: '{' | lbrace NL ; nl: NL | nl NL ; opt_nl: /* empty */ { $$ = 0; } | nl ; opt_pst: /* empty */ { $$ = 0; } | pst ; opt_simple_stmt: /* empty */ { $$ = 0; } | simple_stmt ; pas: opt_pst { $$ = 0; } | opt_pst pa_stats opt_pst { $$ = $2; } ; pa_pat: pattern { $$ = notnull($1); } ; pa_stat: pa_pat { $$ = stat2(PASTAT, $1, stat2(PRINT, rectonode(), NIL)); } | pa_pat lbrace stmtlist '}' { $$ = stat2(PASTAT, $1, $3); } | pa_pat ',' opt_nl pa_pat { $$ = pa2stat($1, $4, stat2(PRINT, rectonode(), NIL)); } | pa_pat ',' opt_nl pa_pat lbrace stmtlist '}' { $$ = pa2stat($1, $4, $6); } | lbrace stmtlist '}' { $$ = stat2(PASTAT, NIL, $2); } | XBEGIN lbrace stmtlist '}' { beginloc = linkum(beginloc, $3); $$ = 0; } | XEND lbrace stmtlist '}' { endloc = linkum(endloc, $3); $$ = 0; } | FUNC funcname '(' varlist rparen {infunc++;} lbrace stmtlist '}' { infunc--; curfname=0; defn((Cell *)$2, $4, $8); $$ = 0; } ; pa_stats: pa_stat | pa_stats opt_pst pa_stat { $$ = linkum($1, $3); } ; patlist: pattern | patlist comma pattern { $$ = linkum($1, $3); } ; ppattern: var ASGNOP ppattern { $$ = op2($2, $1, $3); } | ppattern '?' ppattern ':' ppattern %prec '?' { $$ = op3(CONDEXPR, notnull($1), $3, $5); } | ppattern bor ppattern %prec BOR { $$ = op2(BOR, notnull($1), notnull($3)); } | ppattern and ppattern %prec AND { $$ = op2(AND, notnull($1), notnull($3)); } | ppattern MATCHOP reg_expr { $$ = op3($2, NIL, $1, (Node*)makedfa($3, 0)); } | ppattern MATCHOP ppattern { if (constnode($3)) $$ = op3($2, NIL, $1, (Node*)makedfa(strnode($3), 0)); else $$ = op3($2, (Node *)1, $1, $3); } | ppattern IN varname { $$ = op2(INTEST, $1, makearr($3)); } | '(' plist ')' IN varname { $$ = op2(INTEST, $2, makearr($5)); } | ppattern term %prec CAT { $$ = op2(CAT, $1, $2); } | re | term ; pattern: var ASGNOP pattern { $$ = op2($2, $1, $3); } | pattern '?' pattern ':' pattern %prec '?' { $$ = op3(CONDEXPR, notnull($1), $3, $5); } | pattern bor pattern %prec BOR { $$ = op2(BOR, notnull($1), notnull($3)); } | pattern and pattern %prec AND { $$ = op2(AND, notnull($1), notnull($3)); } | pattern EQ pattern { $$ = op2($2, $1, $3); } | pattern GE pattern { $$ = op2($2, $1, $3); } | pattern GT pattern { $$ = op2($2, $1, $3); } | pattern LE pattern { $$ = op2($2, $1, $3); } | pattern LT pattern { $$ = op2($2, $1, $3); } | pattern NE pattern { $$ = op2($2, $1, $3); } | pattern MATCHOP reg_expr { $$ = op3($2, NIL, $1, (Node*)makedfa($3, 0)); } | pattern MATCHOP pattern { if (constnode($3)) $$ = op3($2, NIL, $1, (Node*)makedfa(strnode($3), 0)); else $$ = op3($2, (Node *)1, $1, $3); } | pattern IN varname { $$ = op2(INTEST, $1, makearr($3)); } | '(' plist ')' IN varname { $$ = op2(INTEST, $2, makearr($5)); } | pattern '|' GETLINE var { if (safe) SYNTAX("cmd | getline is unsafe"); else $$ = op3(GETLINE, $4, itonp($2), $1); } | pattern '|' GETLINE { if (safe) SYNTAX("cmd | getline is unsafe"); else $$ = op3(GETLINE, (Node*)0, itonp($2), $1); } | pattern term %prec CAT { $$ = op2(CAT, $1, $2); } | re | term ; plist: pattern comma pattern { $$ = linkum($1, $3); } | plist comma pattern { $$ = linkum($1, $3); } ; pplist: ppattern | pplist comma ppattern { $$ = linkum($1, $3); } ; prarg: /* empty */ { $$ = rectonode(); } | pplist | '(' plist ')' { $$ = $2; } ; print: PRINT | PRINTF ; pst: NL | ';' | pst NL | pst ';' ; rbrace: '}' | rbrace NL ; re: reg_expr { $$ = op3(MATCH, NIL, rectonode(), (Node*)makedfa($1, 0)); } | NOT re { $$ = op1(NOT, notnull($2)); } ; reg_expr: '/' {startreg();} REGEXPR '/' { $$ = $3; } ; rparen: ')' | rparen NL ; simple_stmt: print prarg '|' term { if (safe) SYNTAX("print | is unsafe"); else $$ = stat3($1, $2, itonp($3), $4); } | print prarg APPEND term { if (safe) SYNTAX("print >> is unsafe"); else $$ = stat3($1, $2, itonp($3), $4); } | print prarg GT term { if (safe) SYNTAX("print > is unsafe"); else $$ = stat3($1, $2, itonp($3), $4); } | print prarg { $$ = stat3($1, $2, NIL, NIL); } | DELETE varname '[' patlist ']' { $$ = stat2(DELETE, makearr($2), $4); } | DELETE varname { $$ = stat2(DELETE, makearr($2), 0); } | pattern { $$ = exptostat($1); } | error { yyclearin; SYNTAX("illegal statement"); } ; st: nl | ';' opt_nl ; stmt: BREAK st { if (!inloop) SYNTAX("break illegal outside of loops"); $$ = stat1(BREAK, NIL); } | CONTINUE st { if (!inloop) SYNTAX("continue illegal outside of loops"); $$ = stat1(CONTINUE, NIL); } | do {inloop++;} stmt {--inloop;} WHILE '(' pattern ')' st { $$ = stat2(DO, $3, notnull($7)); } | EXIT pattern st { $$ = stat1(EXIT, $2); } | EXIT st { $$ = stat1(EXIT, NIL); } | for | if stmt else stmt { $$ = stat3(IF, $1, $2, $4); } | if stmt { $$ = stat3(IF, $1, $2, NIL); } | lbrace stmtlist rbrace { $$ = $2; } | NEXT st { if (infunc) SYNTAX("next is illegal inside a function"); $$ = stat1(NEXT, NIL); } | NEXTFILE st { if (infunc) SYNTAX("nextfile is illegal inside a function"); $$ = stat1(NEXTFILE, NIL); } | RETURN pattern st { $$ = stat1(RETURN, $2); } | RETURN st { $$ = stat1(RETURN, NIL); } | simple_stmt st | while {inloop++;} stmt { --inloop; $$ = stat2(WHILE, $1, $3); } | ';' opt_nl { $$ = 0; } ; stmtlist: stmt | stmtlist stmt { $$ = linkum($1, $2); } ; subop: SUB | GSUB ; term: term '/' ASGNOP term { $$ = op2(DIVEQ, $1, $4); } | term '+' term { $$ = op2(ADD, $1, $3); } | term '-' term { $$ = op2(MINUS, $1, $3); } | term '*' term { $$ = op2(MULT, $1, $3); } | term '/' term { $$ = op2(DIVIDE, $1, $3); } | term '%' term { $$ = op2(MOD, $1, $3); } | term POWER term { $$ = op2(POWER, $1, $3); } | '-' term %prec UMINUS { $$ = op1(UMINUS, $2); } - | '+' term %prec UMINUS { $$ = $2; } + | '+' term %prec UMINUS { $$ = op1(UPLUS, $2); } | NOT term %prec UMINUS { $$ = op1(NOT, notnull($2)); } | BLTIN '(' ')' { $$ = op2(BLTIN, itonp($1), rectonode()); } | BLTIN '(' patlist ')' { $$ = op2(BLTIN, itonp($1), $3); } | BLTIN { $$ = op2(BLTIN, itonp($1), rectonode()); } | CALL '(' ')' { $$ = op2(CALL, celltonode($1,CVAR), NIL); } | CALL '(' patlist ')' { $$ = op2(CALL, celltonode($1,CVAR), $3); } | CLOSE term { $$ = op1(CLOSE, $2); } | DECR var { $$ = op1(PREDECR, $2); } | INCR var { $$ = op1(PREINCR, $2); } | var DECR { $$ = op1(POSTDECR, $1); } | var INCR { $$ = op1(POSTINCR, $1); } | GETLINE var LT term { $$ = op3(GETLINE, $2, itonp($3), $4); } | GETLINE LT term { $$ = op3(GETLINE, NIL, itonp($2), $3); } | GETLINE var { $$ = op3(GETLINE, $2, NIL, NIL); } | GETLINE { $$ = op3(GETLINE, NIL, NIL, NIL); } | INDEX '(' pattern comma pattern ')' { $$ = op2(INDEX, $3, $5); } | INDEX '(' pattern comma reg_expr ')' { SYNTAX("index() doesn't permit regular expressions"); $$ = op2(INDEX, $3, (Node*)$5); } | '(' pattern ')' { $$ = $2; } | MATCHFCN '(' pattern comma reg_expr ')' { $$ = op3(MATCHFCN, NIL, $3, (Node*)makedfa($5, 1)); } | MATCHFCN '(' pattern comma pattern ')' { if (constnode($5)) $$ = op3(MATCHFCN, NIL, $3, (Node*)makedfa(strnode($5), 1)); else $$ = op3(MATCHFCN, (Node *)1, $3, $5); } | NUMBER { $$ = celltonode($1, CCON); } | SPLIT '(' pattern comma varname comma pattern ')' /* string */ { $$ = op4(SPLIT, $3, makearr($5), $7, (Node*)STRING); } | SPLIT '(' pattern comma varname comma reg_expr ')' /* const /regexp/ */ { $$ = op4(SPLIT, $3, makearr($5), (Node*)makedfa($7, 1), (Node *)REGEXPR); } | SPLIT '(' pattern comma varname ')' { $$ = op4(SPLIT, $3, makearr($5), NIL, (Node*)STRING); } /* default */ | SPRINTF '(' patlist ')' { $$ = op1($1, $3); } | STRING { $$ = celltonode($1, CCON); } | subop '(' reg_expr comma pattern ')' { $$ = op4($1, NIL, (Node*)makedfa($3, 1), $5, rectonode()); } | subop '(' pattern comma pattern ')' { if (constnode($3)) $$ = op4($1, NIL, (Node*)makedfa(strnode($3), 1), $5, rectonode()); else $$ = op4($1, (Node *)1, $3, $5, rectonode()); } | subop '(' reg_expr comma pattern comma var ')' { $$ = op4($1, NIL, (Node*)makedfa($3, 1), $5, $7); } | subop '(' pattern comma pattern comma var ')' { if (constnode($3)) $$ = op4($1, NIL, (Node*)makedfa(strnode($3), 1), $5, $7); else $$ = op4($1, (Node *)1, $3, $5, $7); } | SUBSTR '(' pattern comma pattern comma pattern ')' { $$ = op3(SUBSTR, $3, $5, $7); } | SUBSTR '(' pattern comma pattern ')' { $$ = op3(SUBSTR, $3, $5, NIL); } | var ; var: varname | varname '[' patlist ']' { $$ = op2(ARRAY, makearr($1), $3); } | IVAR { $$ = op1(INDIRECT, celltonode($1, CVAR)); } | INDIRECT term { $$ = op1(INDIRECT, $2); } ; varlist: /* nothing */ { arglist = $$ = 0; } | VAR { arglist = $$ = celltonode($1,CVAR); } | varlist comma VAR { checkdup($1, $3); arglist = $$ = linkum($1,celltonode($3,CVAR)); } ; varname: VAR { $$ = celltonode($1, CVAR); } | ARG { $$ = op1(ARG, itonp($1)); } | VARNF { $$ = op1(VARNF, (Node *) $1); } ; while: WHILE '(' pattern rparen { $$ = notnull($3); } ; %% void setfname(Cell *p) { if (isarr(p)) SYNTAX("%s is an array, not a function", p->nval); else if (isfcn(p)) SYNTAX("you can't define function %s more than once", p->nval); curfname = p->nval; } int constnode(Node *p) { return isvalue(p) && ((Cell *) (p->narg[0]))->csub == CCON; } char *strnode(Node *p) { return ((Cell *)(p->narg[0]))->sval; } Node *notnull(Node *n) { switch (n->nobj) { case LE: case LT: case EQ: case NE: case GT: case GE: case BOR: case AND: case NOT: return n; default: return op2(NE, n, nullnode); } } void checkdup(Node *vl, Cell *cp) /* check if name already in list */ { char *s = cp->nval; for ( ; vl; vl = vl->nnext) { if (strcmp(s, ((Cell *)(vl->narg[0]))->nval) == 0) { SYNTAX("duplicate argument %s", s); break; } } } Index: head/contrib/one-true-awk/b.c =================================================================== --- head/contrib/one-true-awk/b.c (revision 348510) +++ head/contrib/one-true-awk/b.c (revision 348511) @@ -1,976 +1,1227 @@ /**************************************************************** Copyright (C) Lucent Technologies 1997 All Rights Reserved Permission to use, copy, modify, and distribute this software and its documentation for any purpose and without fee is hereby granted, provided that the above copyright notice appear in all copies and that both that the copyright notice and this permission notice and warranty disclaimer appear in supporting documentation, and that the name Lucent Technologies or any of its entities not be used in advertising or publicity pertaining to distribution of the software without specific, written prior permission. LUCENT DISCLAIMS ALL WARRANTIES WITH REGARD TO THIS SOFTWARE, INCLUDING ALL IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL LUCENT OR ANY OF ITS ENTITIES BE LIABLE FOR ANY SPECIAL, 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. ****************************************************************/ /* lasciate ogne speranza, voi ch'intrate. */ #include __FBSDID("$FreeBSD$"); #define DEBUG #include +#include #include #include #include #include "awk.h" #include "ytab.h" #define HAT (NCHARS+2) /* matches ^ in regular expr */ /* NCHARS is 2**n */ #define MAXLIN 22 #define type(v) (v)->nobj /* badly overloaded here */ #define info(v) (v)->ntype /* badly overloaded here */ #define left(v) (v)->narg[0] #define right(v) (v)->narg[1] #define parent(v) (v)->nnext #define LEAF case CCL: case NCCL: case CHAR: case DOT: case FINAL: case ALL: #define ELEAF case EMPTYRE: /* empty string in regexp */ #define UNARY case STAR: case PLUS: case QUEST: /* encoding in tree Nodes: leaf (CCL, NCCL, CHAR, DOT, FINAL, ALL, EMPTYRE): left is index, right contains value or pointer to value unary (STAR, PLUS, QUEST): left is child, right is null binary (CAT, OR): left and right are children parent contains pointer to parent */ int *setvec; int *tmpset; int maxsetvec = 0; int rtok; /* next token in current re */ int rlxval; static uschar *rlxstr; static uschar *prestr; /* current position in current re */ static uschar *lastre; /* origin of last re */ +static uschar *lastatom; /* origin of last Atom */ +static uschar *starttok; +static uschar *basestr; /* starts with original, replaced during + repetition processing */ +static uschar *firstbasestr; static int setcnt; static int poscnt; char *patbeg; int patlen; #define NFA 20 /* cache this many dynamic fa's */ fa *fatab[NFA]; int nfatab = 0; /* entries in fatab */ fa *makedfa(const char *s, int anchor) /* returns dfa for reg expr s */ { int i, use, nuse; fa *pfa; static int now = 1; - if (setvec == NULL) { /* first time through any RE */ + if (setvec == 0) { /* first time through any RE */ maxsetvec = MAXLIN; setvec = (int *) malloc(maxsetvec * sizeof(int)); tmpset = (int *) malloc(maxsetvec * sizeof(int)); - if (setvec == NULL || tmpset == NULL) + if (setvec == 0 || tmpset == 0) overflo("out of space initializing makedfa"); } if (compile_time) /* a constant for sure */ return mkdfa(s, anchor); for (i = 0; i < nfatab; i++) /* is it there already? */ if (fatab[i]->anchor == anchor && strcmp((const char *) fatab[i]->restr, s) == 0) { fatab[i]->use = now++; return fatab[i]; } pfa = mkdfa(s, anchor); if (nfatab < NFA) { /* room for another */ fatab[nfatab] = pfa; fatab[nfatab]->use = now++; nfatab++; return pfa; } use = fatab[0]->use; /* replace least-recently used */ nuse = 0; for (i = 1; i < nfatab; i++) if (fatab[i]->use < use) { use = fatab[i]->use; nuse = i; } freefa(fatab[nuse]); fatab[nuse] = pfa; pfa->use = now++; return pfa; } fa *mkdfa(const char *s, int anchor) /* does the real work of making a dfa */ /* anchor = 1 for anchored matches, else 0 */ { Node *p, *p1; fa *f; + firstbasestr = (uschar *) s; + basestr = firstbasestr; p = reparse(s); p1 = op2(CAT, op2(STAR, op2(ALL, NIL, NIL), NIL), p); /* put ALL STAR in front of reg. exp. */ p1 = op2(CAT, p1, op2(FINAL, NIL, NIL)); /* put FINAL after reg. exp. */ poscnt = 0; penter(p1); /* enter parent pointers and leaf indices */ if ((f = (fa *) calloc(1, sizeof(fa) + poscnt*sizeof(rrow))) == NULL) overflo("out of space for fa"); f->accept = poscnt-1; /* penter has computed number of positions in re */ cfoll(f, p1); /* set up follow sets */ freetr(p1); - if ((f->posns[0] = (int *) calloc(*(f->re[0].lfollow), sizeof(int))) == NULL) + if ((f->posns[0] = (int *) calloc(1, *(f->re[0].lfollow)*sizeof(int))) == NULL) overflo("out of space in makedfa"); if ((f->posns[1] = (int *) calloc(1, sizeof(int))) == NULL) overflo("out of space in makedfa"); *f->posns[1] = 0; f->initstat = makeinit(f, anchor); f->anchor = anchor; f->restr = (uschar *) tostring(s); + if (firstbasestr != basestr) { + if (basestr) + xfree(basestr); + } return f; } int makeinit(fa *f, int anchor) { int i, k; f->curstat = 2; f->out[2] = 0; f->reset = 0; k = *(f->re[0].lfollow); xfree(f->posns[2]); - if ((f->posns[2] = (int *) calloc(k+1, sizeof(int))) == NULL) + if ((f->posns[2] = (int *) calloc(1, (k+1)*sizeof(int))) == NULL) overflo("out of space in makeinit"); for (i=0; i <= k; i++) { (f->posns[2])[i] = (f->re[0].lfollow)[i]; } if ((f->posns[2])[1] == f->accept) f->out[2] = 1; for (i=0; i < NCHARS; i++) f->gototab[2][i] = 0; f->curstat = cgoto(f, 2, HAT); if (anchor) { *f->posns[2] = k-1; /* leave out position 0 */ for (i=0; i < k; i++) { (f->posns[0])[i] = (f->posns[2])[i]; } f->out[0] = f->out[2]; if (f->curstat != 2) --(*f->posns[f->curstat]); } return f->curstat; } void penter(Node *p) /* set up parent pointers and leaf indices */ { switch (type(p)) { ELEAF LEAF info(p) = poscnt; poscnt++; break; UNARY penter(left(p)); parent(left(p)) = p; break; case CAT: case OR: penter(left(p)); penter(right(p)); parent(left(p)) = p; parent(right(p)) = p; break; default: /* can't happen */ FATAL("can't happen: unknown type %d in penter", type(p)); break; } } void freetr(Node *p) /* free parse tree */ { switch (type(p)) { ELEAF LEAF xfree(p); break; UNARY freetr(left(p)); xfree(p); break; case CAT: case OR: freetr(left(p)); freetr(right(p)); xfree(p); break; default: /* can't happen */ FATAL("can't happen: unknown type %d in freetr", type(p)); break; } } /* in the parsing of regular expressions, metacharacters like . have */ /* to be seen literally; \056 is not a metacharacter. */ int hexstr(uschar **pp) /* find and eval hex string at pp, return new p */ { /* only pick up one 8-bit byte (2 chars) */ uschar *p; int n = 0; int i; for (i = 0, p = (uschar *) *pp; i < 2 && isxdigit(*p); i++, p++) { if (isdigit(*p)) n = 16 * n + *p - '0'; else if (*p >= 'a' && *p <= 'f') n = 16 * n + *p - 'a' + 10; else if (*p >= 'A' && *p <= 'F') n = 16 * n + *p - 'A' + 10; } *pp = (uschar *) p; return n; } #define isoctdigit(c) ((c) >= '0' && (c) <= '7') /* multiple use of arg */ int quoted(uschar **pp) /* pick up next thing after a \\ */ /* and increment *pp */ { uschar *p = *pp; int c; if ((c = *p++) == 't') c = '\t'; else if (c == 'n') c = '\n'; else if (c == 'f') c = '\f'; else if (c == 'r') c = '\r'; else if (c == 'b') c = '\b'; else if (c == '\\') c = '\\'; else if (c == 'x') { /* hexadecimal goo follows */ c = hexstr(&p); /* this adds a null if number is invalid */ } else if (isoctdigit(c)) { /* \d \dd \ddd */ int n = c - '0'; if (isoctdigit(*p)) { n = 8 * n + *p++ - '0'; if (isoctdigit(*p)) n = 8 * n + *p++ - '0'; } c = n; } /* else */ /* c = c; */ *pp = p; return c; } static int collate_range_cmp(int a, int b) { static char s[2][2]; if ((uschar)a == (uschar)b) return 0; s[0][0] = a; s[1][0] = b; return (strcoll(s[0], s[1])); } char *cclenter(const char *argp) /* add a character class */ { int i, c, c2; int j; uschar *p = (uschar *) argp; uschar *op, *bp; - static uschar *buf = NULL; + static uschar *buf = 0; static int bufsz = 100; op = p; - if (buf == NULL && (buf = (uschar *) malloc(bufsz)) == NULL) + if (buf == 0 && (buf = (uschar *) malloc(bufsz)) == NULL) FATAL("out of space for character class [%.10s...] 1", p); bp = buf; for (i = 0; (c = *p++) != 0; ) { if (c == '\\') { c = quoted(&p); } else if (c == '-' && i > 0 && bp[-1] != 0) { if (*p != 0) { c = bp[-1]; c2 = *p++; if (c2 == '\\') c2 = quoted(&p); if (collate_range_cmp(c, c2) > 0) { bp--; i--; continue; } for (j = 0; j < NCHARS; j++) { if ((collate_range_cmp(c, j) > 0) || collate_range_cmp(j, c2) > 0) continue; if (!adjbuf((char **) &buf, &bufsz, bp-buf+2, 100, (char **) &bp, "cclenter1")) FATAL("out of space for character class [%.10s...] 2", p); *bp++ = j; i++; } continue; } } if (!adjbuf((char **) &buf, &bufsz, bp-buf+2, 100, (char **) &bp, "cclenter2")) FATAL("out of space for character class [%.10s...] 3", p); *bp++ = c; i++; } *bp = 0; dprintf( ("cclenter: in = |%s|, out = |%s|\n", op, buf) ); xfree(op); return (char *) tostring((char *) buf); } void overflo(const char *s) { FATAL("regular expression too big: %.30s...", s); } void cfoll(fa *f, Node *v) /* enter follow set of each leaf of vertex v into lfollow[leaf] */ { int i; int *p; switch (type(v)) { ELEAF LEAF f->re[info(v)].ltype = type(v); f->re[info(v)].lval.np = right(v); while (f->accept >= maxsetvec) { /* guessing here! */ maxsetvec *= 4; setvec = (int *) realloc(setvec, maxsetvec * sizeof(int)); tmpset = (int *) realloc(tmpset, maxsetvec * sizeof(int)); - if (setvec == NULL || tmpset == NULL) + if (setvec == 0 || tmpset == 0) overflo("out of space in cfoll()"); } for (i = 0; i <= f->accept; i++) setvec[i] = 0; setcnt = 0; follow(v); /* computes setvec and setcnt */ - if ((p = (int *) calloc(setcnt+1, sizeof(int))) == NULL) + if ((p = (int *) calloc(1, (setcnt+1)*sizeof(int))) == NULL) overflo("out of space building follow set"); f->re[info(v)].lfollow = p; *p = setcnt; for (i = f->accept; i >= 0; i--) if (setvec[i] == 1) *++p = i; break; UNARY cfoll(f,left(v)); break; case CAT: case OR: cfoll(f,left(v)); cfoll(f,right(v)); break; default: /* can't happen */ FATAL("can't happen: unknown type %d in cfoll", type(v)); } } int first(Node *p) /* collects initially active leaves of p into setvec */ /* returns 0 if p matches empty string */ { int b, lp; switch (type(p)) { ELEAF LEAF lp = info(p); /* look for high-water mark of subscripts */ while (setcnt >= maxsetvec || lp >= maxsetvec) { /* guessing here! */ maxsetvec *= 4; setvec = (int *) realloc(setvec, maxsetvec * sizeof(int)); tmpset = (int *) realloc(tmpset, maxsetvec * sizeof(int)); - if (setvec == NULL || tmpset == NULL) + if (setvec == 0 || tmpset == 0) overflo("out of space in first()"); } if (type(p) == EMPTYRE) { setvec[lp] = 0; return(0); } if (setvec[lp] != 1) { setvec[lp] = 1; setcnt++; } if (type(p) == CCL && (*(char *) right(p)) == '\0') return(0); /* empty CCL */ else return(1); case PLUS: if (first(left(p)) == 0) return(0); return(1); case STAR: case QUEST: first(left(p)); return(0); case CAT: if (first(left(p)) == 0 && first(right(p)) == 0) return(0); return(1); case OR: b = first(right(p)); if (first(left(p)) == 0 || b == 0) return(0); return(1); } FATAL("can't happen: unknown type %d in first", type(p)); /* can't happen */ return(-1); } void follow(Node *v) /* collects leaves that can follow v into setvec */ { Node *p; if (type(v) == FINAL) return; p = parent(v); switch (type(p)) { case STAR: case PLUS: first(v); follow(p); return; case OR: case QUEST: follow(p); return; case CAT: if (v == left(p)) { /* v is left child of p */ if (first(right(p)) == 0) { follow(p); return; } } else /* v is right child */ follow(p); return; } } int member(int c, const char *sarg) /* is c in s? */ { uschar *s = (uschar *) sarg; while (*s) if (c == *s++) return(1); return(0); } int match(fa *f, const char *p0) /* shortest match ? */ { int s, ns; uschar *p = (uschar *) p0; s = f->reset ? makeinit(f,0) : f->initstat; if (f->out[s]) return(1); do { /* assert(*p < NCHARS); */ if ((ns = f->gototab[s][*p]) != 0) s = ns; else s = cgoto(f, s, *p); if (f->out[s]) return(1); } while (*p++ != 0); return(0); } int pmatch(fa *f, const char *p0) /* longest match, for sub */ { int s, ns; uschar *p = (uschar *) p0; uschar *q; int i, k; /* s = f->reset ? makeinit(f,1) : f->initstat; */ if (f->reset) { f->initstat = s = makeinit(f,1); } else { s = f->initstat; } patbeg = (char *) p; patlen = -1; do { q = p; do { if (f->out[s]) /* final state */ patlen = q-p; /* assert(*q < NCHARS); */ if ((ns = f->gototab[s][*q]) != 0) s = ns; else s = cgoto(f, s, *q); if (s == 1) { /* no transition */ if (patlen >= 0) { patbeg = (char *) p; return(1); } else goto nextin; /* no match */ } } while (*q++ != 0); if (f->out[s]) patlen = q-p-1; /* don't count $ */ if (patlen >= 0) { patbeg = (char *) p; return(1); } nextin: s = 2; if (f->reset) { for (i = 2; i <= f->curstat; i++) xfree(f->posns[i]); k = *f->posns[0]; - if ((f->posns[2] = (int *) calloc(k+1, sizeof(int))) == NULL) + if ((f->posns[2] = (int *) calloc(1, (k+1)*sizeof(int))) == NULL) overflo("out of space in pmatch"); for (i = 0; i <= k; i++) (f->posns[2])[i] = (f->posns[0])[i]; f->initstat = f->curstat = 2; f->out[2] = f->out[0]; for (i = 0; i < NCHARS; i++) f->gototab[2][i] = 0; } } while (*p++ != 0); return (0); } int nematch(fa *f, const char *p0) /* non-empty match, for sub */ { int s, ns; uschar *p = (uschar *) p0; uschar *q; int i, k; /* s = f->reset ? makeinit(f,1) : f->initstat; */ if (f->reset) { f->initstat = s = makeinit(f,1); } else { s = f->initstat; } patlen = -1; while (*p) { q = p; do { if (f->out[s]) /* final state */ patlen = q-p; /* assert(*q < NCHARS); */ if ((ns = f->gototab[s][*q]) != 0) s = ns; else s = cgoto(f, s, *q); if (s == 1) { /* no transition */ if (patlen > 0) { patbeg = (char *) p; return(1); } else goto nnextin; /* no nonempty match */ } } while (*q++ != 0); if (f->out[s]) patlen = q-p-1; /* don't count $ */ if (patlen > 0 ) { patbeg = (char *) p; return(1); } nnextin: s = 2; if (f->reset) { for (i = 2; i <= f->curstat; i++) xfree(f->posns[i]); k = *f->posns[0]; - if ((f->posns[2] = (int *) calloc(k+1, sizeof(int))) == NULL) + if ((f->posns[2] = (int *) calloc(1, (k+1)*sizeof(int))) == NULL) overflo("out of state space"); for (i = 0; i <= k; i++) (f->posns[2])[i] = (f->posns[0])[i]; f->initstat = f->curstat = 2; f->out[2] = f->out[0]; for (i = 0; i < NCHARS; i++) f->gototab[2][i] = 0; } p++; } return (0); } Node *reparse(const char *p) /* parses regular expression pointed to by p */ { /* uses relex() to scan regular expression */ Node *np; dprintf( ("reparse <%s>\n", p) ); lastre = prestr = (uschar *) p; /* prestr points to string to be parsed */ rtok = relex(); /* GNU compatibility: an empty regexp matches anything */ if (rtok == '\0') { /* FATAL("empty regular expression"); previous */ return(op2(EMPTYRE, NIL, NIL)); } np = regexp(); if (rtok != '\0') FATAL("syntax error in regular expression %s at %s", lastre, prestr); return(np); } Node *regexp(void) /* top-level parse of reg expr */ { return (alt(concat(primary()))); } Node *primary(void) { Node *np; + int savelastatom; switch (rtok) { case CHAR: + lastatom = starttok; np = op2(CHAR, NIL, itonp(rlxval)); rtok = relex(); return (unary(np)); case ALL: rtok = relex(); return (unary(op2(ALL, NIL, NIL))); case EMPTYRE: rtok = relex(); - return (unary(op2(ALL, NIL, NIL))); + return (unary(op2(EMPTYRE, NIL, NIL))); case DOT: + lastatom = starttok; rtok = relex(); return (unary(op2(DOT, NIL, NIL))); case CCL: np = op2(CCL, NIL, (Node*) cclenter((char *) rlxstr)); + lastatom = starttok; rtok = relex(); return (unary(np)); case NCCL: np = op2(NCCL, NIL, (Node *) cclenter((char *) rlxstr)); + lastatom = starttok; rtok = relex(); return (unary(np)); case '^': rtok = relex(); return (unary(op2(CHAR, NIL, itonp(HAT)))); case '$': rtok = relex(); return (unary(op2(CHAR, NIL, NIL))); case '(': + lastatom = starttok; + savelastatom = starttok - basestr; /* Retain over recursion */ rtok = relex(); if (rtok == ')') { /* special pleading for () */ rtok = relex(); return unary(op2(CCL, NIL, (Node *) tostring(""))); } np = regexp(); if (rtok == ')') { + lastatom = basestr + savelastatom; /* Restore */ rtok = relex(); return (unary(np)); } else FATAL("syntax error in regular expression %s at %s", lastre, prestr); default: FATAL("illegal primary in regular expression %s at %s", lastre, prestr); } return 0; /*NOTREACHED*/ } Node *concat(Node *np) { switch (rtok) { - case CHAR: case DOT: case ALL: case EMPTYRE: case CCL: case NCCL: case '$': case '(': + case CHAR: case DOT: case ALL: case CCL: case NCCL: case '$': case '(': return (concat(op2(CAT, np, primary()))); + case EMPTYRE: + rtok = relex(); + return (concat(op2(CAT, op2(CCL, NIL, (Node *) tostring("")), + primary()))); } return (np); } Node *alt(Node *np) { if (rtok == OR) { rtok = relex(); return (alt(op2(OR, np, concat(primary())))); } return (np); } Node *unary(Node *np) { switch (rtok) { case STAR: rtok = relex(); return (unary(op2(STAR, np, NIL))); case PLUS: rtok = relex(); return (unary(op2(PLUS, np, NIL))); case QUEST: rtok = relex(); return (unary(op2(QUEST, np, NIL))); default: return (np); } } /* * Character class definitions conformant to the POSIX locale as * defined in IEEE P1003.1 draft 7 of June 2001, assuming the source * and operating character sets are both ASCII (ISO646) or supersets * thereof. * * Note that to avoid overflowing the temporary buffer used in * relex(), the expanded character class (prior to range expansion) * must be less than twice the size of their full name. */ /* Because isblank doesn't show up in any of the header files on any * system i use, it's defined here. if some other locale has a richer * definition of "blank", define HAS_ISBLANK and provide your own * version. * the parentheses here are an attempt to find a path through the maze * of macro definition and/or function and/or version provided. thanks * to nelson beebe for the suggestion; let's see if it works everywhere. */ /* #define HAS_ISBLANK */ #ifndef HAS_ISBLANK int (xisblank)(int c) { return c==' ' || c=='\t'; } #endif struct charclass { const char *cc_name; int cc_namelen; int (*cc_func)(int); } charclasses[] = { { "alnum", 5, isalnum }, { "alpha", 5, isalpha }, #ifndef HAS_ISBLANK - { "blank", 5, isspace }, /* was isblank */ + { "blank", 5, xisblank }, #else { "blank", 5, isblank }, #endif { "cntrl", 5, iscntrl }, { "digit", 5, isdigit }, { "graph", 5, isgraph }, { "lower", 5, islower }, { "print", 5, isprint }, { "punct", 5, ispunct }, { "space", 5, isspace }, { "upper", 5, isupper }, { "xdigit", 6, isxdigit }, { NULL, 0, NULL }, }; +#define REPEAT_SIMPLE 0 +#define REPEAT_PLUS_APPENDED 1 +#define REPEAT_WITH_Q 2 +#define REPEAT_ZERO 3 +static int +replace_repeat(const uschar *reptok, int reptoklen, const uschar *atom, + int atomlen, int firstnum, int secondnum, int special_case) +{ + int i, j; + uschar *buf = 0; + int ret = 1; + int init_q = (firstnum==0); /* first added char will be ? */ + int n_q_reps = secondnum-firstnum; /* m>n, so reduce until {1,m-n} left */ + int prefix_length = reptok - basestr; /* prefix includes first rep */ + int suffix_length = strlen((char *) reptok) - reptoklen; /* string after rep specifier */ + int size = prefix_length + suffix_length; + + if (firstnum > 1) { /* add room for reps 2 through firstnum */ + size += atomlen*(firstnum-1); + } + + /* Adjust size of buffer for special cases */ + if (special_case == REPEAT_PLUS_APPENDED) { + size++; /* for the final + */ + } else if (special_case == REPEAT_WITH_Q) { + size += init_q + (atomlen+1)* n_q_reps; + } else if (special_case == REPEAT_ZERO) { + size += 2; /* just a null ERE: () */ + } + if ((buf = (uschar *) malloc(size+1)) == NULL) + FATAL("out of space in reg expr %.10s..", lastre); + memcpy(buf, basestr, prefix_length); /* copy prefix */ + j = prefix_length; + if (special_case == REPEAT_ZERO) { + j -= atomlen; + buf[j++] = '('; + buf[j++] = ')'; + } + for (i=1; i < firstnum; i++) { /* copy x reps */ + memcpy(&buf[j], atom, atomlen); + j += atomlen; + } + if (special_case == REPEAT_PLUS_APPENDED) { + buf[j++] = '+'; + } else if (special_case == REPEAT_WITH_Q) { + if (init_q) buf[j++] = '?'; + for (i=0; i < n_q_reps; i++) { /* copy x? reps */ + memcpy(&buf[j], atom, atomlen); + j += atomlen; + buf[j++] = '?'; + } + } + memcpy(&buf[j], reptok+reptoklen, suffix_length); + if (special_case == REPEAT_ZERO) { + buf[j+suffix_length] = '\0'; + } else { + buf[size] = '\0'; + } + /* free old basestr */ + if (firstbasestr != basestr) { + if (basestr) + xfree(basestr); + } + basestr = buf; + prestr = buf + prefix_length; + if (special_case == REPEAT_ZERO) { + prestr -= atomlen; + ret++; + } + return ret; +} + +static int repeat(const uschar *reptok, int reptoklen, const uschar *atom, + int atomlen, int firstnum, int secondnum) +{ + /* + In general, the repetition specifier or "bound" is replaced here + by an equivalent ERE string, repeating the immediately previous atom + and appending ? and + as needed. Note that the first copy of the + atom is left in place, except in the special_case of a zero-repeat + (i.e., {0}). + */ + if (secondnum < 0) { /* means {n,} -> repeat n-1 times followed by PLUS */ + if (firstnum < 2) { + /* 0 or 1: should be handled before you get here */ + FATAL("internal error"); + } else { + return replace_repeat(reptok, reptoklen, atom, atomlen, + firstnum, secondnum, REPEAT_PLUS_APPENDED); + } + } else if (firstnum == secondnum) { /* {n} or {n,n} -> simply repeat n-1 times */ + if (firstnum == 0) { /* {0} or {0,0} */ + /* This case is unusual because the resulting + replacement string might actually be SMALLER than + the original ERE */ + return replace_repeat(reptok, reptoklen, atom, atomlen, + firstnum, secondnum, REPEAT_ZERO); + } else { /* (firstnum >= 1) */ + return replace_repeat(reptok, reptoklen, atom, atomlen, + firstnum, secondnum, REPEAT_SIMPLE); + } + } else if (firstnum < secondnum) { /* {n,m} -> repeat n-1 times then alternate */ + /* x{n,m} => xx...x{1, m-n+1} => xx...x?x?x?..x? */ + return replace_repeat(reptok, reptoklen, atom, atomlen, + firstnum, secondnum, REPEAT_WITH_Q); + } else { /* Error - shouldn't be here (n>m) */ + FATAL("internal error"); + } + return 0; +} + int relex(void) /* lexical analyzer for reparse */ { int c, n; int cflag; - static uschar *buf = NULL; + static uschar *buf = 0; static int bufsz = 100; uschar *bp; struct charclass *cc; int i; + int num, m, commafound, digitfound; + const uschar *startreptok; +rescan: + starttok = prestr; + switch (c = *prestr++) { case '|': return OR; case '*': return STAR; case '+': return PLUS; case '?': return QUEST; case '.': return DOT; case '\0': prestr--; return '\0'; case '^': case '$': case '(': case ')': return c; case '\\': rlxval = quoted(&prestr); return CHAR; default: rlxval = c; return CHAR; case '[': - if (buf == NULL && (buf = (uschar *) malloc(bufsz)) == NULL) + if (buf == 0 && (buf = (uschar *) malloc(bufsz)) == NULL) FATAL("out of space in reg expr %.10s..", lastre); bp = buf; if (*prestr == '^') { cflag = 1; prestr++; } else cflag = 0; n = 2 * strlen((const char *) prestr)+1; if (!adjbuf((char **) &buf, &bufsz, n, n, (char **) &bp, "relex1")) FATAL("out of space for reg expr %.10s...", lastre); for (; ; ) { if ((c = *prestr++) == '\\') { *bp++ = '\\'; if ((c = *prestr++) == '\0') FATAL("nonterminated character class %.20s...", lastre); *bp++ = c; /* } else if (c == '\n') { */ /* FATAL("newline in character class %.20s...", lastre); */ } else if (c == '[' && *prestr == ':') { /* POSIX char class names, Dag-Erling Smorgrav, des@ofug.org */ for (cc = charclasses; cc->cc_name; cc++) if (strncmp((const char *) prestr + 1, (const char *) cc->cc_name, cc->cc_namelen) == 0) break; if (cc->cc_name != NULL && prestr[1 + cc->cc_namelen] == ':' && prestr[2 + cc->cc_namelen] == ']') { prestr += cc->cc_namelen + 3; - for (i = 1; i < NCHARS; i++) { + /* + * BUG: We begin at 1, instead of 0, since we + * would otherwise prematurely terminate the + * string for classes like [[:cntrl:]]. This + * means that we can't match the NUL character, + * not without first adapting the entire + * program to track each string's length. + */ + for (i = 1; i <= UCHAR_MAX; i++) { if (!adjbuf((char **) &buf, &bufsz, bp-buf+1, 100, (char **) &bp, "relex2")) FATAL("out of space for reg expr %.10s...", lastre); if (cc->cc_func(i)) { *bp++ = i; n++; } } } else *bp++ = c; + } else if (c == '[' && *prestr == '.') { + char collate_char; + prestr++; + collate_char = *prestr++; + if (*prestr == '.' && prestr[1] == ']') { + prestr += 2; + /* Found it: map via locale TBD: for + now, simply return this char. This + is sufficient to pass conformance + test awk.ex 156 + */ + if (*prestr == ']') { + prestr++; + rlxval = collate_char; + return CHAR; + } + } + } else if (c == '[' && *prestr == '=') { + char equiv_char; + prestr++; + equiv_char = *prestr++; + if (*prestr == '=' && prestr[1] == ']') { + prestr += 2; + /* Found it: map via locale TBD: for now + simply return this char. This is + sufficient to pass conformance test + awk.ex 156 + */ + if (*prestr == ']') { + prestr++; + rlxval = equiv_char; + return CHAR; + } + } } else if (c == '\0') { FATAL("nonterminated character class %.20s", lastre); } else if (bp == buf) { /* 1st char is special */ *bp++ = c; } else if (c == ']') { *bp++ = 0; rlxstr = (uschar *) tostring((char *) buf); if (cflag == 0) return CCL; else return NCCL; } else *bp++ = c; } + break; + case '{': + if (isdigit(*(prestr))) { + num = 0; /* Process as a repetition */ + n = -1; m = -1; + commafound = 0; + digitfound = 0; + startreptok = prestr-1; + /* Remember start of previous atom here ? */ + } else { /* just a { char, not a repetition */ + rlxval = c; + return CHAR; + } + for (; ; ) { + if ((c = *prestr++) == '}') { + if (commafound) { + if (digitfound) { /* {n,m} */ + m = num; + if (m 0) { + if ((n==0) && (m==0)) { + return EMPTYRE; + } + /* must rescan input for next token */ + goto rescan; + } + /* Failed to replace: eat up {...} characters + and treat like just PLUS */ + return PLUS; + } else if (c == '\0') { + FATAL("nonterminated character class %.20s", + lastre); + } else if (isdigit(c)) { + num = 10 * num + c - '0'; + digitfound = 1; + } else if (c == ',') { + if (commafound) + FATAL("illegal repetition expression: class %.20s", + lastre); + /* looking for {n,} or {n,m} */ + commafound = 1; + n = num; + digitfound = 0; /* reset */ + num = 0; + } else { + FATAL("illegal repetition expression: class %.20s", + lastre); + } + } + break; } } int cgoto(fa *f, int s, int c) { int i, j, k; int *p, *q; assert(c == HAT || c < NCHARS); while (f->accept >= maxsetvec) { /* guessing here! */ maxsetvec *= 4; setvec = (int *) realloc(setvec, maxsetvec * sizeof(int)); tmpset = (int *) realloc(tmpset, maxsetvec * sizeof(int)); - if (setvec == NULL || tmpset == NULL) + if (setvec == 0 || tmpset == 0) overflo("out of space in cgoto()"); } for (i = 0; i <= f->accept; i++) setvec[i] = 0; setcnt = 0; /* compute positions of gototab[s,c] into setvec */ p = f->posns[s]; for (i = 1; i <= *p; i++) { if ((k = f->re[p[i]].ltype) != FINAL) { if ((k == CHAR && c == ptoi(f->re[p[i]].lval.np)) || (k == DOT && c != 0 && c != HAT) || (k == ALL && c != 0) || (k == EMPTYRE && c != 0) || (k == CCL && member(c, (char *) f->re[p[i]].lval.up)) || (k == NCCL && !member(c, (char *) f->re[p[i]].lval.up) && c != 0 && c != HAT)) { q = f->re[p[i]].lfollow; for (j = 1; j <= *q; j++) { if (q[j] >= maxsetvec) { maxsetvec *= 4; setvec = (int *) realloc(setvec, maxsetvec * sizeof(int)); tmpset = (int *) realloc(tmpset, maxsetvec * sizeof(int)); - if (setvec == NULL || tmpset == NULL) + if (setvec == 0 || tmpset == 0) overflo("cgoto overflow"); } if (setvec[q[j]] == 0) { setcnt++; setvec[q[j]] = 1; } } } } } /* determine if setvec is a previous state */ tmpset[0] = setcnt; j = 1; for (i = f->accept; i >= 0; i--) if (setvec[i]) { tmpset[j++] = i; } /* tmpset == previous state? */ for (i = 1; i <= f->curstat; i++) { p = f->posns[i]; if ((k = tmpset[0]) != p[0]) goto different; for (j = 1; j <= k; j++) if (tmpset[j] != p[j]) goto different; /* setvec is state i */ f->gototab[s][c] = i; return i; different:; } /* add tmpset to current set of states */ if (f->curstat >= NSTATES-1) { f->curstat = 2; f->reset = 1; for (i = 2; i < NSTATES; i++) xfree(f->posns[i]); } else ++(f->curstat); for (i = 0; i < NCHARS; i++) f->gototab[f->curstat][i] = 0; xfree(f->posns[f->curstat]); - if ((p = (int *) calloc(setcnt+1, sizeof(int))) == NULL) + if ((p = (int *) calloc(1, (setcnt+1)*sizeof(int))) == NULL) overflo("out of space in cgoto"); f->posns[f->curstat] = p; f->gototab[s][c] = f->curstat; for (i = 0; i <= setcnt; i++) p[i] = tmpset[i]; if (setvec[f->accept]) f->out[f->curstat] = 1; else f->out[f->curstat] = 0; return f->curstat; } void freefa(fa *f) /* free a finite automaton */ { int i; if (f == NULL) return; for (i = 0; i <= f->curstat; i++) xfree(f->posns[i]); for (i = 0; i <= f->accept; i++) { xfree(f->re[i].lfollow); if (f->re[i].ltype == CCL || f->re[i].ltype == NCCL) xfree((f->re[i].lval.np)); } xfree(f->restr); xfree(f); } Index: head/contrib/one-true-awk/bugs-fixed/README =================================================================== --- head/contrib/one-true-awk/bugs-fixed/README (nonexistent) +++ head/contrib/one-true-awk/bugs-fixed/README (revision 348511) @@ -0,0 +1,57 @@ +List of bugs fixed. + +1. ofs-rebuild: OFS value used to rebuild the record was incorrect. +Fixed August 19, 2014. Revised fix August 2018. + +2. system-status: Instead of a floating-point division by 256, use +the wait(2) macros to create a reasonable exit status. Fixed March 12, 2016. + +3. space: Use provided xisblank() function instead of ispace() for +matching [[:blank:]]. + +4. a-format: Add POSIX standard %a and %A to supported formats. Check +at runtime that this format is available. + +5. decr-NF: Decrementing NF did not change $0. This is a decades-old +bug. There are interactions with the old and new value of OFS as well. +Most of the fix came from the NetBSD awk. + +6. string-conv: String conversions of scalars were sticky. Once a +conversion to string happened, even with OFMT, that value was used until +a new numeric value was assigned, even if OFMT differed from CONVFMT, +and also if CONVFMT changed. + +7. unary-plus: Unary plus on a string constant returned the string. +Instead, it should convert the value to numeric and give that value. + +8. concat-assign-same: Concatenation previously evaluated both sides of the +expression before doing its work, which, since assign() evaluates to the cell +being assigned to, meant that expressions like "print (a = 1) (a = 2)" would +print "22" rather than "12". + +9. missing-precision: When using the format string "%*s", the precision +argument was used without checking if it was present first. + +10. missing-precision: When using the format string "%*s", the precision +argument was used without checking if it was present first. + +11. fmt-overflow: The buffer used for OFMT/CONVFMT conversions was written +to with sprintf(), which meant that some conversions could write past the +end. + +12. numeric-subsep, numeric-fs, numeric-output-seps, numerics-rs: If SUBSEP, +FS, RS, OFS, or ORS were set to a numeric value, then their string values +wouldn't always be generated before being needed. + +13. subsep-overflow: The length of SUBSEP needs to be rechecked after +calling execute(), in case SUBSEP itself has been changed. + +14. split-fs-from-array: If the third argument to split() comes from the +array passed as the second argument, then split() would previously read +from the freed memory and possibly produce incorrect results (depending +on the system's malloc()/free() behaviour.) + +15. getline-numeric: The `getline xx < file' syntax did not check if +values were numeric, in discordance from POSIX. Test case adapted from +one posted by Ben Bacarisse in comp.lang.awk, +January 2019. Index: head/contrib/one-true-awk/bugs-fixed/a-format.awk =================================================================== --- head/contrib/one-true-awk/bugs-fixed/a-format.awk (nonexistent) +++ head/contrib/one-true-awk/bugs-fixed/a-format.awk (revision 348511) @@ -0,0 +1,3 @@ +BEGIN { + printf("%a\n", 42) +} Property changes on: head/contrib/one-true-awk/bugs-fixed/a-format.awk ___________________________________________________________________ Added: svn:eol-style ## -0,0 +1 ## +native \ No newline at end of property Added: svn:keywords ## -0,0 +1 ## +FreeBSD=%H \ No newline at end of property Added: svn:mime-type ## -0,0 +1 ## +text/plain \ No newline at end of property Index: head/contrib/one-true-awk/bugs-fixed/a-format.bad =================================================================== --- head/contrib/one-true-awk/bugs-fixed/a-format.bad (nonexistent) +++ head/contrib/one-true-awk/bugs-fixed/a-format.bad (revision 348511) @@ -0,0 +1,3 @@ +nawk: weird printf conversion %a + source line number 2 +%a42 Index: head/contrib/one-true-awk/bugs-fixed/a-format.ok =================================================================== --- head/contrib/one-true-awk/bugs-fixed/a-format.ok (nonexistent) +++ head/contrib/one-true-awk/bugs-fixed/a-format.ok (revision 348511) @@ -0,0 +1 @@ +0x1.5p+5 Index: head/contrib/one-true-awk/bugs-fixed/concat-assign-same.awk =================================================================== --- head/contrib/one-true-awk/bugs-fixed/concat-assign-same.awk (nonexistent) +++ head/contrib/one-true-awk/bugs-fixed/concat-assign-same.awk (revision 348511) @@ -0,0 +1,4 @@ +BEGIN { + print (a = 1) (a = 2) (a = 3) (a = 4) (a = 5); + print (a = 1), (a = 2), (a = 3), (a = 4), (a = 5); +} Property changes on: head/contrib/one-true-awk/bugs-fixed/concat-assign-same.awk ___________________________________________________________________ Added: svn:eol-style ## -0,0 +1 ## +native \ No newline at end of property Added: svn:keywords ## -0,0 +1 ## +FreeBSD=%H \ No newline at end of property Added: svn:mime-type ## -0,0 +1 ## +text/plain \ No newline at end of property Index: head/contrib/one-true-awk/bugs-fixed/concat-assign-same.bad =================================================================== --- head/contrib/one-true-awk/bugs-fixed/concat-assign-same.bad (nonexistent) +++ head/contrib/one-true-awk/bugs-fixed/concat-assign-same.bad (revision 348511) @@ -0,0 +1,2 @@ +22345 +1 2 3 4 5 Index: head/contrib/one-true-awk/bugs-fixed/concat-assign-same.ok =================================================================== --- head/contrib/one-true-awk/bugs-fixed/concat-assign-same.ok (nonexistent) +++ head/contrib/one-true-awk/bugs-fixed/concat-assign-same.ok (revision 348511) @@ -0,0 +1,2 @@ +12345 +1 2 3 4 5 Index: head/contrib/one-true-awk/bugs-fixed/decr-NF.awk =================================================================== --- head/contrib/one-true-awk/bugs-fixed/decr-NF.awk (nonexistent) +++ head/contrib/one-true-awk/bugs-fixed/decr-NF.awk (revision 348511) @@ -0,0 +1,11 @@ +BEGIN { + $0 = "a b c d e f" + print NF + OFS = ":" + NF-- + print $0 + print NF + NF++ + print $0 + print NF +} Property changes on: head/contrib/one-true-awk/bugs-fixed/decr-NF.awk ___________________________________________________________________ Added: svn:eol-style ## -0,0 +1 ## +native \ No newline at end of property Added: svn:keywords ## -0,0 +1 ## +FreeBSD=%H \ No newline at end of property Added: svn:mime-type ## -0,0 +1 ## +text/plain \ No newline at end of property Index: head/contrib/one-true-awk/bugs-fixed/decr-NF.bad =================================================================== --- head/contrib/one-true-awk/bugs-fixed/decr-NF.bad (nonexistent) +++ head/contrib/one-true-awk/bugs-fixed/decr-NF.bad (revision 348511) @@ -0,0 +1,5 @@ +6 +a b c d e f +5 +a b c d e f +6 Index: head/contrib/one-true-awk/bugs-fixed/decr-NF.ok =================================================================== --- head/contrib/one-true-awk/bugs-fixed/decr-NF.ok (nonexistent) +++ head/contrib/one-true-awk/bugs-fixed/decr-NF.ok (revision 348511) @@ -0,0 +1,5 @@ +6 +a:b:c:d:e +5 +a:b:c:d:e: +6 Index: head/contrib/one-true-awk/bugs-fixed/fmt-overflow.awk =================================================================== --- head/contrib/one-true-awk/bugs-fixed/fmt-overflow.awk (nonexistent) +++ head/contrib/one-true-awk/bugs-fixed/fmt-overflow.awk (revision 348511) @@ -0,0 +1 @@ +BEGIN { OFMT = "%.1000f"; print 1.25; } Property changes on: head/contrib/one-true-awk/bugs-fixed/fmt-overflow.awk ___________________________________________________________________ Added: svn:eol-style ## -0,0 +1 ## +native \ No newline at end of property Added: svn:keywords ## -0,0 +1 ## +FreeBSD=%H \ No newline at end of property Added: svn:mime-type ## -0,0 +1 ## +text/plain \ No newline at end of property Index: head/contrib/one-true-awk/bugs-fixed/fmt-overflow.ok =================================================================== --- head/contrib/one-true-awk/bugs-fixed/fmt-overflow.ok (nonexistent) +++ head/contrib/one-true-awk/bugs-fixed/fmt-overflow.ok (revision 348511) @@ -0,0 +1 @@ +1.2500000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000 Index: head/contrib/one-true-awk/bugs-fixed/fs-overflow.awk =================================================================== --- head/contrib/one-true-awk/bugs-fixed/fs-overflow.awk (nonexistent) +++ head/contrib/one-true-awk/bugs-fixed/fs-overflow.awk (revision 348511) @@ -0,0 +1,13 @@ +function foo() { + a = ""; + for (i = 0; i < 10000; i++) { + a = a "c"; + } + return a; +} + +BEGIN { + FS = foo(); + $0="foo"; + print $1; +} Property changes on: head/contrib/one-true-awk/bugs-fixed/fs-overflow.awk ___________________________________________________________________ Added: svn:eol-style ## -0,0 +1 ## +native \ No newline at end of property Added: svn:keywords ## -0,0 +1 ## +FreeBSD=%H \ No newline at end of property Added: svn:mime-type ## -0,0 +1 ## +text/plain \ No newline at end of property Index: head/contrib/one-true-awk/bugs-fixed/getline-numeric.awk =================================================================== --- head/contrib/one-true-awk/bugs-fixed/getline-numeric.awk (nonexistent) +++ head/contrib/one-true-awk/bugs-fixed/getline-numeric.awk (revision 348511) @@ -0,0 +1,6 @@ +{ + print $0, ($0 <= 50 ? "<=" : ">"), 50 + getline dd < ARGV[1] + print dd, (dd <= 50 ? "<=" : ">"), 50 + if (dd == $0) print "same" +} Property changes on: head/contrib/one-true-awk/bugs-fixed/getline-numeric.awk ___________________________________________________________________ Added: svn:eol-style ## -0,0 +1 ## +native \ No newline at end of property Added: svn:keywords ## -0,0 +1 ## +FreeBSD=%H \ No newline at end of property Added: svn:mime-type ## -0,0 +1 ## +text/plain \ No newline at end of property Index: head/contrib/one-true-awk/bugs-fixed/getline-numeric.bad =================================================================== --- head/contrib/one-true-awk/bugs-fixed/getline-numeric.bad (nonexistent) +++ head/contrib/one-true-awk/bugs-fixed/getline-numeric.bad (revision 348511) @@ -0,0 +1,3 @@ +120 > 50 +120 <= 50 +same Index: head/contrib/one-true-awk/bugs-fixed/getline-numeric.in =================================================================== --- head/contrib/one-true-awk/bugs-fixed/getline-numeric.in (nonexistent) +++ head/contrib/one-true-awk/bugs-fixed/getline-numeric.in (revision 348511) @@ -0,0 +1 @@ +120 Property changes on: head/contrib/one-true-awk/bugs-fixed/getline-numeric.in ___________________________________________________________________ Added: svn:eol-style ## -0,0 +1 ## +native \ No newline at end of property Added: svn:keywords ## -0,0 +1 ## +FreeBSD=%H \ No newline at end of property Added: svn:mime-type ## -0,0 +1 ## +text/plain \ No newline at end of property Index: head/contrib/one-true-awk/bugs-fixed/getline-numeric.ok =================================================================== --- head/contrib/one-true-awk/bugs-fixed/getline-numeric.ok (nonexistent) +++ head/contrib/one-true-awk/bugs-fixed/getline-numeric.ok (revision 348511) @@ -0,0 +1,3 @@ +120 > 50 +120 > 50 +same Index: head/contrib/one-true-awk/bugs-fixed/missing-precision.awk =================================================================== --- head/contrib/one-true-awk/bugs-fixed/missing-precision.awk (nonexistent) +++ head/contrib/one-true-awk/bugs-fixed/missing-precision.awk (revision 348511) @@ -0,0 +1 @@ +BEGIN { printf("%*s"); } Property changes on: head/contrib/one-true-awk/bugs-fixed/missing-precision.awk ___________________________________________________________________ Added: svn:eol-style ## -0,0 +1 ## +native \ No newline at end of property Added: svn:keywords ## -0,0 +1 ## +FreeBSD=%H \ No newline at end of property Added: svn:mime-type ## -0,0 +1 ## +text/plain \ No newline at end of property Index: head/contrib/one-true-awk/bugs-fixed/missing-precision.ok =================================================================== --- head/contrib/one-true-awk/bugs-fixed/missing-precision.ok (nonexistent) +++ head/contrib/one-true-awk/bugs-fixed/missing-precision.ok (revision 348511) @@ -0,0 +1,2 @@ +./a.out: not enough args in printf(%*s) + source line number 1 Index: head/contrib/one-true-awk/bugs-fixed/negative-nf.awk =================================================================== --- head/contrib/one-true-awk/bugs-fixed/negative-nf.awk (nonexistent) +++ head/contrib/one-true-awk/bugs-fixed/negative-nf.awk (revision 348511) @@ -0,0 +1 @@ +BEGIN { NF = -5; } Property changes on: head/contrib/one-true-awk/bugs-fixed/negative-nf.awk ___________________________________________________________________ Added: svn:eol-style ## -0,0 +1 ## +native \ No newline at end of property Added: svn:keywords ## -0,0 +1 ## +FreeBSD=%H \ No newline at end of property Added: svn:mime-type ## -0,0 +1 ## +text/plain \ No newline at end of property Index: head/contrib/one-true-awk/bugs-fixed/negative-nf.ok =================================================================== --- head/contrib/one-true-awk/bugs-fixed/negative-nf.ok (nonexistent) +++ head/contrib/one-true-awk/bugs-fixed/negative-nf.ok (revision 348511) @@ -0,0 +1,2 @@ +./a.out: cannot set NF to a negative value + source line number 1 Index: head/contrib/one-true-awk/bugs-fixed/nf-self-assign.awk =================================================================== --- head/contrib/one-true-awk/bugs-fixed/nf-self-assign.awk (nonexistent) +++ head/contrib/one-true-awk/bugs-fixed/nf-self-assign.awk (revision 348511) @@ -0,0 +1,6 @@ +BEGIN { + $0="a b c"; + OFS=","; + NF = NF; + print; +} Property changes on: head/contrib/one-true-awk/bugs-fixed/nf-self-assign.awk ___________________________________________________________________ Added: svn:eol-style ## -0,0 +1 ## +native \ No newline at end of property Added: svn:keywords ## -0,0 +1 ## +FreeBSD=%H \ No newline at end of property Added: svn:mime-type ## -0,0 +1 ## +text/plain \ No newline at end of property Index: head/contrib/one-true-awk/bugs-fixed/nf-self-assign.bad =================================================================== --- head/contrib/one-true-awk/bugs-fixed/nf-self-assign.bad (nonexistent) +++ head/contrib/one-true-awk/bugs-fixed/nf-self-assign.bad (revision 348511) @@ -0,0 +1 @@ +a b c Index: head/contrib/one-true-awk/bugs-fixed/nf-self-assign.ok =================================================================== --- head/contrib/one-true-awk/bugs-fixed/nf-self-assign.ok (nonexistent) +++ head/contrib/one-true-awk/bugs-fixed/nf-self-assign.ok (revision 348511) @@ -0,0 +1 @@ +a,b,c Index: head/contrib/one-true-awk/bugs-fixed/numeric-fs.awk =================================================================== --- head/contrib/one-true-awk/bugs-fixed/numeric-fs.awk (nonexistent) +++ head/contrib/one-true-awk/bugs-fixed/numeric-fs.awk (revision 348511) @@ -0,0 +1,5 @@ +BEGIN { + FS = 0; split("20202", a); print a[1]; + FS = 1; $0="31313"; print $1; + FS = 2; "echo 42424" | getline; print $1; +} Property changes on: head/contrib/one-true-awk/bugs-fixed/numeric-fs.awk ___________________________________________________________________ Added: svn:eol-style ## -0,0 +1 ## +native \ No newline at end of property Added: svn:keywords ## -0,0 +1 ## +FreeBSD=%H \ No newline at end of property Added: svn:mime-type ## -0,0 +1 ## +text/plain \ No newline at end of property Index: head/contrib/one-true-awk/bugs-fixed/numeric-fs.ok =================================================================== --- head/contrib/one-true-awk/bugs-fixed/numeric-fs.ok (nonexistent) +++ head/contrib/one-true-awk/bugs-fixed/numeric-fs.ok (revision 348511) @@ -0,0 +1,3 @@ +2 +3 +4 Index: head/contrib/one-true-awk/bugs-fixed/numeric-output-seps.awk =================================================================== --- head/contrib/one-true-awk/bugs-fixed/numeric-output-seps.awk (nonexistent) +++ head/contrib/one-true-awk/bugs-fixed/numeric-output-seps.awk (revision 348511) @@ -0,0 +1,8 @@ +BEGIN { + $0 = "a b c"; + OFS = 1; + ORS = 2; + NF = 2; + print; + print "d", "e"; +} Property changes on: head/contrib/one-true-awk/bugs-fixed/numeric-output-seps.awk ___________________________________________________________________ Added: svn:eol-style ## -0,0 +1 ## +native \ No newline at end of property Added: svn:keywords ## -0,0 +1 ## +FreeBSD=%H \ No newline at end of property Added: svn:mime-type ## -0,0 +1 ## +text/plain \ No newline at end of property Index: head/contrib/one-true-awk/bugs-fixed/numeric-output-seps.bad =================================================================== --- head/contrib/one-true-awk/bugs-fixed/numeric-output-seps.bad (nonexistent) +++ head/contrib/one-true-awk/bugs-fixed/numeric-output-seps.bad (revision 348511) @@ -0,0 +1,2 @@ +a b +d e Index: head/contrib/one-true-awk/bugs-fixed/numeric-output-seps.ok =================================================================== --- head/contrib/one-true-awk/bugs-fixed/numeric-output-seps.ok (nonexistent) +++ head/contrib/one-true-awk/bugs-fixed/numeric-output-seps.ok (revision 348511) @@ -0,0 +1 @@ +a1b2d1e2 \ No newline at end of file Index: head/contrib/one-true-awk/bugs-fixed/numeric-rs.awk =================================================================== --- head/contrib/one-true-awk/bugs-fixed/numeric-rs.awk (nonexistent) +++ head/contrib/one-true-awk/bugs-fixed/numeric-rs.awk (revision 348511) @@ -0,0 +1,6 @@ +BEGIN { + RS = 1; + while ("echo a1b1c1d" | getline > 0) { + print $1; + } +} Property changes on: head/contrib/one-true-awk/bugs-fixed/numeric-rs.awk ___________________________________________________________________ Added: svn:eol-style ## -0,0 +1 ## +native \ No newline at end of property Added: svn:keywords ## -0,0 +1 ## +FreeBSD=%H \ No newline at end of property Added: svn:mime-type ## -0,0 +1 ## +text/plain \ No newline at end of property Index: head/contrib/one-true-awk/bugs-fixed/numeric-rs.bad =================================================================== --- head/contrib/one-true-awk/bugs-fixed/numeric-rs.bad (nonexistent) +++ head/contrib/one-true-awk/bugs-fixed/numeric-rs.bad (revision 348511) @@ -0,0 +1 @@ +a1b1c1d Index: head/contrib/one-true-awk/bugs-fixed/numeric-rs.ok =================================================================== --- head/contrib/one-true-awk/bugs-fixed/numeric-rs.ok (nonexistent) +++ head/contrib/one-true-awk/bugs-fixed/numeric-rs.ok (revision 348511) @@ -0,0 +1,4 @@ +a +b +c +d Index: head/contrib/one-true-awk/bugs-fixed/numeric-subsep.awk =================================================================== --- head/contrib/one-true-awk/bugs-fixed/numeric-subsep.awk (nonexistent) +++ head/contrib/one-true-awk/bugs-fixed/numeric-subsep.awk (revision 348511) @@ -0,0 +1,5 @@ +BEGIN { + SUBSEP = 123.456; + a["hello", "world"] = "foo"; + print a["hello" SUBSEP "world"]; +} Property changes on: head/contrib/one-true-awk/bugs-fixed/numeric-subsep.awk ___________________________________________________________________ Added: svn:eol-style ## -0,0 +1 ## +native \ No newline at end of property Added: svn:keywords ## -0,0 +1 ## +FreeBSD=%H \ No newline at end of property Added: svn:mime-type ## -0,0 +1 ## +text/plain \ No newline at end of property Index: head/contrib/one-true-awk/bugs-fixed/numeric-subsep.bad =================================================================== Cannot display: file marked as a binary type. svn:mime-type = application/octet-stream Property changes on: head/contrib/one-true-awk/bugs-fixed/numeric-subsep.bad ___________________________________________________________________ Added: svn:mime-type ## -0,0 +1 ## +application/octet-stream \ No newline at end of property Index: head/contrib/one-true-awk/bugs-fixed/numeric-subsep.ok =================================================================== --- head/contrib/one-true-awk/bugs-fixed/numeric-subsep.ok (nonexistent) +++ head/contrib/one-true-awk/bugs-fixed/numeric-subsep.ok (revision 348511) @@ -0,0 +1 @@ +foo Index: head/contrib/one-true-awk/bugs-fixed/ofs-rebuild.awk =================================================================== --- head/contrib/one-true-awk/bugs-fixed/ofs-rebuild.awk (nonexistent) +++ head/contrib/one-true-awk/bugs-fixed/ofs-rebuild.awk (revision 348511) @@ -0,0 +1,17 @@ +# The bug here is that nawk should use the value of OFS that +# was current when $0 became invalid to rebuild the record. + +BEGIN { + OFS = ":" + $0 = "a b c d e f g" + $3 = "3333" + # Conceptually, $0 should now be "a:b:3333:d:e:f:g" + + # Change OFS after (conceptually) rebuilding the record + OFS = "<>" + + # Unmodifed nawk prints "a<>b<>3333<>d<>e<>f<>g" because + # it delays rebuilding $0 until it's needed, and then it uses + # the current value of OFS. Oops. + print +} Property changes on: head/contrib/one-true-awk/bugs-fixed/ofs-rebuild.awk ___________________________________________________________________ Added: svn:eol-style ## -0,0 +1 ## +native \ No newline at end of property Added: svn:keywords ## -0,0 +1 ## +FreeBSD=%H \ No newline at end of property Added: svn:mime-type ## -0,0 +1 ## +text/plain \ No newline at end of property Index: head/contrib/one-true-awk/bugs-fixed/ofs-rebuild.bad =================================================================== --- head/contrib/one-true-awk/bugs-fixed/ofs-rebuild.bad (nonexistent) +++ head/contrib/one-true-awk/bugs-fixed/ofs-rebuild.bad (revision 348511) @@ -0,0 +1 @@ +a<>b<>3333<>d<>e<>f<>g Index: head/contrib/one-true-awk/bugs-fixed/ofs-rebuild.ok =================================================================== --- head/contrib/one-true-awk/bugs-fixed/ofs-rebuild.ok (nonexistent) +++ head/contrib/one-true-awk/bugs-fixed/ofs-rebuild.ok (revision 348511) @@ -0,0 +1 @@ +a:b:3333:d:e:f:g Index: head/contrib/one-true-awk/bugs-fixed/space.awk =================================================================== --- head/contrib/one-true-awk/bugs-fixed/space.awk (nonexistent) +++ head/contrib/one-true-awk/bugs-fixed/space.awk (revision 348511) @@ -0,0 +1,22 @@ +BEGIN { + c[" "] = "\" \"" + c["\a"] = "\\a" + c["\b"] = "\\b" + c["\f"] = "\\f" + c["\n"] = "\\n" + c["\r"] = "\\r" + c["\t"] = "\\t" + c["\v"] = "\\v" + + sort = "LC_ALL=C sort" + + for (i in c) + printf("%s %s [[:space:]]\n", c[i], + i ~ /[[:space:]]/ ? "~" : "!~") | sort + + for (i in c) + printf("%s %s [[:blank:]]\n", c[i], + i ~ /[[:blank:]]/ ? "~" : "!~") | sort + + close(sort) +} Property changes on: head/contrib/one-true-awk/bugs-fixed/space.awk ___________________________________________________________________ Added: svn:eol-style ## -0,0 +1 ## +native \ No newline at end of property Added: svn:keywords ## -0,0 +1 ## +FreeBSD=%H \ No newline at end of property Added: svn:mime-type ## -0,0 +1 ## +text/plain \ No newline at end of property Index: head/contrib/one-true-awk/bugs-fixed/space.bad =================================================================== --- head/contrib/one-true-awk/bugs-fixed/space.bad (nonexistent) +++ head/contrib/one-true-awk/bugs-fixed/space.bad (revision 348511) @@ -0,0 +1,16 @@ +" " ~ [[:blank:]] +" " ~ [[:space:]] +\a !~ [[:blank:]] +\a !~ [[:space:]] +\b !~ [[:blank:]] +\b !~ [[:space:]] +\f ~ [[:blank:]] +\f ~ [[:space:]] +\n ~ [[:blank:]] +\n ~ [[:space:]] +\r ~ [[:blank:]] +\r ~ [[:space:]] +\t ~ [[:blank:]] +\t ~ [[:space:]] +\v ~ [[:blank:]] +\v ~ [[:space:]] Index: head/contrib/one-true-awk/bugs-fixed/space.ok =================================================================== --- head/contrib/one-true-awk/bugs-fixed/space.ok (nonexistent) +++ head/contrib/one-true-awk/bugs-fixed/space.ok (revision 348511) @@ -0,0 +1,16 @@ +" " ~ [[:blank:]] +" " ~ [[:space:]] +\a !~ [[:blank:]] +\a !~ [[:space:]] +\b !~ [[:blank:]] +\b !~ [[:space:]] +\f !~ [[:blank:]] +\f ~ [[:space:]] +\n !~ [[:blank:]] +\n ~ [[:space:]] +\r !~ [[:blank:]] +\r ~ [[:space:]] +\t ~ [[:blank:]] +\t ~ [[:space:]] +\v !~ [[:blank:]] +\v ~ [[:space:]] Index: head/contrib/one-true-awk/bugs-fixed/split-fs-from-array.awk =================================================================== --- head/contrib/one-true-awk/bugs-fixed/split-fs-from-array.awk (nonexistent) +++ head/contrib/one-true-awk/bugs-fixed/split-fs-from-array.awk (revision 348511) @@ -0,0 +1,5 @@ +BEGIN { + a[1] = "elephantie" + a[2] = "e" + print split(a[1],a,a[2]), a[2], a[3], split(a[2],a,a[2]) +} Property changes on: head/contrib/one-true-awk/bugs-fixed/split-fs-from-array.awk ___________________________________________________________________ Added: svn:eol-style ## -0,0 +1 ## +native \ No newline at end of property Added: svn:keywords ## -0,0 +1 ## +FreeBSD=%H \ No newline at end of property Added: svn:mime-type ## -0,0 +1 ## +text/plain \ No newline at end of property Index: head/contrib/one-true-awk/bugs-fixed/split-fs-from-array.ok =================================================================== --- head/contrib/one-true-awk/bugs-fixed/split-fs-from-array.ok (nonexistent) +++ head/contrib/one-true-awk/bugs-fixed/split-fs-from-array.ok (revision 348511) @@ -0,0 +1 @@ +4 l phanti 2 Index: head/contrib/one-true-awk/bugs-fixed/string-conv.awk =================================================================== --- head/contrib/one-true-awk/bugs-fixed/string-conv.awk (nonexistent) +++ head/contrib/one-true-awk/bugs-fixed/string-conv.awk (revision 348511) @@ -0,0 +1,13 @@ +BEGIN { + OFMT = ">>%.6g<<" + a = 12.1234 + print "a =", a + b = a "" + print "1 ->", b + CONVFMT = "%2.2f" + b = a "" + print "2 ->", b + CONVFMT = "%.12g" + b = a "" + print "3 ->", b +} Property changes on: head/contrib/one-true-awk/bugs-fixed/string-conv.awk ___________________________________________________________________ Added: svn:eol-style ## -0,0 +1 ## +native \ No newline at end of property Added: svn:keywords ## -0,0 +1 ## +FreeBSD=%H \ No newline at end of property Added: svn:mime-type ## -0,0 +1 ## +text/plain \ No newline at end of property Index: head/contrib/one-true-awk/bugs-fixed/string-conv.bad =================================================================== --- head/contrib/one-true-awk/bugs-fixed/string-conv.bad (nonexistent) +++ head/contrib/one-true-awk/bugs-fixed/string-conv.bad (revision 348511) @@ -0,0 +1,4 @@ +a = >>12.1234<< +1 -> >>12.1234<< +2 -> >>12.1234<< +3 -> >>12.1234<< Index: head/contrib/one-true-awk/bugs-fixed/string-conv.ok =================================================================== --- head/contrib/one-true-awk/bugs-fixed/string-conv.ok (nonexistent) +++ head/contrib/one-true-awk/bugs-fixed/string-conv.ok (revision 348511) @@ -0,0 +1,4 @@ +a = >>12.1234<< +1 -> 12.1234 +2 -> 12.12 +3 -> 12.1234 Index: head/contrib/one-true-awk/bugs-fixed/subsep-overflow.awk =================================================================== --- head/contrib/one-true-awk/bugs-fixed/subsep-overflow.awk (nonexistent) +++ head/contrib/one-true-awk/bugs-fixed/subsep-overflow.awk (revision 348511) @@ -0,0 +1,24 @@ +function foo(c, n) { + s = ""; + for (i = 0; i < n; i++) { + s = s c; + } + return s; +} + +BEGIN { + str1 = foo("a", 4500); + str2 = foo("b", 9000); + + a[(SUBSEP = str1), (SUBSEP = str2), "c"] = 1; + + for (k in a) { + print length(k); + } + + print (((SUBSEP = str1), (SUBSEP = str2), "c") in a); + print (((SUBSEP = str1) SUBSEP (SUBSEP = str2) SUBSEP "c") in a); + delete a[(SUBSEP = str1), (SUBSEP = str2), "c"]; + print (((SUBSEP = str1), (SUBSEP = str2), "c") in a); + print (((SUBSEP = str1) SUBSEP (SUBSEP = str2) SUBSEP "c") in a); +} Property changes on: head/contrib/one-true-awk/bugs-fixed/subsep-overflow.awk ___________________________________________________________________ Added: svn:eol-style ## -0,0 +1 ## +native \ No newline at end of property Added: svn:keywords ## -0,0 +1 ## +FreeBSD=%H \ No newline at end of property Added: svn:mime-type ## -0,0 +1 ## +text/plain \ No newline at end of property Index: head/contrib/one-true-awk/bugs-fixed/subsep-overflow.ok =================================================================== --- head/contrib/one-true-awk/bugs-fixed/subsep-overflow.ok (nonexistent) +++ head/contrib/one-true-awk/bugs-fixed/subsep-overflow.ok (revision 348511) @@ -0,0 +1,5 @@ +27001 +1 +1 +0 +0 Index: head/contrib/one-true-awk/bugs-fixed/system-status.awk =================================================================== --- head/contrib/one-true-awk/bugs-fixed/system-status.awk (nonexistent) +++ head/contrib/one-true-awk/bugs-fixed/system-status.awk (revision 348511) @@ -0,0 +1,19 @@ +# Unmodified nawk prints the 16 bit exit status divided by 256, but +# does so using floating point arithmetic, yielding strange results. +# +# The fix is to use the various macros defined for wait(2) and to +# use the signal number + 256 for death by signal, or signal number + 512 +# for death by signal with core dump. + +BEGIN { + status = system("exit 42") + print "normal status", status + + status = system("kill -HUP $$") + print "death by signal status", status + + status = system("kill -ABRT $$") + print "death by signal with core dump status", status + + system("rm -f core*") +} Property changes on: head/contrib/one-true-awk/bugs-fixed/system-status.awk ___________________________________________________________________ Added: svn:eol-style ## -0,0 +1 ## +native \ No newline at end of property Added: svn:keywords ## -0,0 +1 ## +FreeBSD=%H \ No newline at end of property Added: svn:mime-type ## -0,0 +1 ## +text/plain \ No newline at end of property Index: head/contrib/one-true-awk/bugs-fixed/system-status.bad =================================================================== --- head/contrib/one-true-awk/bugs-fixed/system-status.bad (nonexistent) +++ head/contrib/one-true-awk/bugs-fixed/system-status.bad (revision 348511) @@ -0,0 +1,3 @@ +normal status 42 +death by signal status 0.00390625 +death by signal with core dump status 0.523438 Index: head/contrib/one-true-awk/bugs-fixed/system-status.ok =================================================================== --- head/contrib/one-true-awk/bugs-fixed/system-status.ok (nonexistent) +++ head/contrib/one-true-awk/bugs-fixed/system-status.ok (revision 348511) @@ -0,0 +1,3 @@ +normal status 42 +death by signal status 257 +death by signal with core dump status 518 Index: head/contrib/one-true-awk/bugs-fixed/unary-plus.awk =================================================================== --- head/contrib/one-true-awk/bugs-fixed/unary-plus.awk (nonexistent) +++ head/contrib/one-true-awk/bugs-fixed/unary-plus.awk (revision 348511) @@ -0,0 +1,4 @@ +BEGIN { + print +"q" + print +"43.12345678912345678" +} Property changes on: head/contrib/one-true-awk/bugs-fixed/unary-plus.awk ___________________________________________________________________ Added: svn:eol-style ## -0,0 +1 ## +native \ No newline at end of property Added: svn:keywords ## -0,0 +1 ## +FreeBSD=%H \ No newline at end of property Added: svn:mime-type ## -0,0 +1 ## +text/plain \ No newline at end of property Index: head/contrib/one-true-awk/bugs-fixed/unary-plus.bad =================================================================== --- head/contrib/one-true-awk/bugs-fixed/unary-plus.bad (nonexistent) +++ head/contrib/one-true-awk/bugs-fixed/unary-plus.bad (revision 348511) @@ -0,0 +1,2 @@ +q +43.12345678912345678 Index: head/contrib/one-true-awk/bugs-fixed/unary-plus.ok =================================================================== --- head/contrib/one-true-awk/bugs-fixed/unary-plus.ok (nonexistent) +++ head/contrib/one-true-awk/bugs-fixed/unary-plus.ok (revision 348511) @@ -0,0 +1,2 @@ +0 +43.1235 Index: head/contrib/one-true-awk/lex.c =================================================================== --- head/contrib/one-true-awk/lex.c (revision 348510) +++ head/contrib/one-true-awk/lex.c (revision 348511) @@ -1,588 +1,592 @@ /**************************************************************** Copyright (C) Lucent Technologies 1997 All Rights Reserved Permission to use, copy, modify, and distribute this software and its documentation for any purpose and without fee is hereby granted, provided that the above copyright notice appear in all copies and that both that the copyright notice and this permission notice and warranty disclaimer appear in supporting documentation, and that the name Lucent Technologies or any of its entities not be used in advertising or publicity pertaining to distribution of the software without specific, written prior permission. LUCENT DISCLAIMS ALL WARRANTIES WITH REGARD TO THIS SOFTWARE, INCLUDING ALL IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL LUCENT OR ANY OF ITS ENTITIES BE LIABLE FOR ANY SPECIAL, 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. ****************************************************************/ #include #include #include #include #include "awk.h" #include "ytab.h" extern YYSTYPE yylval; extern int infunc; int lineno = 1; int bracecnt = 0; int brackcnt = 0; int parencnt = 0; typedef struct Keyword { const char *word; int sub; int type; } Keyword; Keyword keywords[] ={ /* keep sorted: binary searched */ { "BEGIN", XBEGIN, XBEGIN }, { "END", XEND, XEND }, { "NF", VARNF, VARNF }, { "and", FAND, BLTIN }, { "atan2", FATAN, BLTIN }, { "break", BREAK, BREAK }, { "close", CLOSE, CLOSE }, { "compl", FCOMPL, BLTIN }, { "continue", CONTINUE, CONTINUE }, { "cos", FCOS, BLTIN }, { "delete", DELETE, DELETE }, { "do", DO, DO }, { "else", ELSE, ELSE }, { "exit", EXIT, EXIT }, { "exp", FEXP, BLTIN }, { "fflush", FFLUSH, BLTIN }, { "for", FOR, FOR }, { "func", FUNC, FUNC }, { "function", FUNC, FUNC }, { "getline", GETLINE, GETLINE }, { "gsub", GSUB, GSUB }, { "if", IF, IF }, { "in", IN, IN }, { "index", INDEX, INDEX }, { "int", FINT, BLTIN }, { "length", FLENGTH, BLTIN }, { "log", FLOG, BLTIN }, { "lshift", FLSHIFT, BLTIN }, { "match", MATCHFCN, MATCHFCN }, { "next", NEXT, NEXT }, { "nextfile", NEXTFILE, NEXTFILE }, { "or", FFOR, BLTIN }, { "print", PRINT, PRINT }, { "printf", PRINTF, PRINTF }, { "rand", FRAND, BLTIN }, { "return", RETURN, RETURN }, { "rshift", FRSHIFT, BLTIN }, { "sin", FSIN, BLTIN }, { "split", SPLIT, SPLIT }, { "sprintf", SPRINTF, SPRINTF }, { "sqrt", FSQRT, BLTIN }, { "srand", FSRAND, BLTIN }, { "sub", SUB, SUB }, { "substr", SUBSTR, SUBSTR }, { "system", FSYSTEM, BLTIN }, { "tolower", FTOLOWER, BLTIN }, { "toupper", FTOUPPER, BLTIN }, { "while", WHILE, WHILE }, { "xor", FXOR, BLTIN }, }; #define RET(x) { if(dbg)printf("lex %s\n", tokname(x)); return(x); } int peek(void) { int c = input(); unput(c); return c; } int gettok(char **pbuf, int *psz) /* get next input token */ { int c, retc; char *buf = *pbuf; int sz = *psz; char *bp = buf; c = input(); if (c == 0) return 0; buf[0] = c; buf[1] = 0; if (!isalnum(c) && c != '.' && c != '_') return c; *bp++ = c; if (isalpha(c) || c == '_') { /* it's a varname */ for ( ; (c = input()) != 0; ) { if (bp-buf >= sz) if (!adjbuf(&buf, &sz, bp-buf+2, 100, &bp, "gettok")) FATAL( "out of space for name %.10s...", buf ); if (isalnum(c) || c == '_') *bp++ = c; else { *bp = 0; unput(c); break; } } *bp = 0; retc = 'a'; /* alphanumeric */ } else { /* maybe it's a number, but could be . */ char *rem; /* read input until can't be a number */ for ( ; (c = input()) != 0; ) { if (bp-buf >= sz) if (!adjbuf(&buf, &sz, bp-buf+2, 100, &bp, "gettok")) FATAL( "out of space for number %.10s...", buf ); if (isdigit(c) || c == 'e' || c == 'E' || c == '.' || c == '+' || c == '-') *bp++ = c; else { unput(c); break; } } *bp = 0; strtod(buf, &rem); /* parse the number */ if (rem == buf) { /* it wasn't a valid number at all */ buf[1] = 0; /* return one character as token */ retc = buf[0]; /* character is its own type */ unputstr(rem+1); /* put rest back for later */ } else { /* some prefix was a number */ unputstr(rem); /* put rest back for later */ rem[0] = 0; /* truncate buf after number part */ retc = '0'; /* type is number */ } } *pbuf = buf; *psz = sz; return retc; } int word(char *); int string(void); int regexpr(void); int sc = 0; /* 1 => return a } right now */ int reg = 0; /* 1 => return a REGEXPR now */ int yylex(void) { int c; - static char *buf = NULL; + static char *buf = 0; static int bufsize = 5; /* BUG: setting this small causes core dump! */ - if (buf == NULL && (buf = (char *) malloc(bufsize)) == NULL) + if (buf == 0 && (buf = (char *) malloc(bufsize)) == NULL) FATAL( "out of space in yylex" ); if (sc) { sc = 0; RET('}'); } if (reg) { reg = 0; return regexpr(); } for (;;) { c = gettok(&buf, &bufsize); if (c == 0) return 0; if (isalpha(c) || c == '_') return word(buf); if (isdigit(c)) { yylval.cp = setsymtab(buf, tostring(buf), atof(buf), CON|NUM, symtab); /* should this also have STR set? */ RET(NUMBER); } yylval.i = c; switch (c) { case '\n': /* {EOL} */ + lineno++; RET(NL); case '\r': /* assume \n is coming */ case ' ': /* {WS}+ */ case '\t': break; case '#': /* #.* strip comments */ while ((c = input()) != '\n' && c != 0) ; unput(c); break; case ';': RET(';'); case '\\': if (peek() == '\n') { input(); + lineno++; } else if (peek() == '\r') { input(); input(); /* \n */ lineno++; } else { RET(c); } break; case '&': if (peek() == '&') { input(); RET(AND); } else RET('&'); case '|': if (peek() == '|') { input(); RET(BOR); } else RET('|'); case '!': if (peek() == '=') { input(); yylval.i = NE; RET(NE); } else if (peek() == '~') { input(); yylval.i = NOTMATCH; RET(MATCHOP); } else RET(NOT); case '~': yylval.i = MATCH; RET(MATCHOP); case '<': if (peek() == '=') { input(); yylval.i = LE; RET(LE); } else { yylval.i = LT; RET(LT); } case '=': if (peek() == '=') { input(); yylval.i = EQ; RET(EQ); } else { yylval.i = ASSIGN; RET(ASGNOP); } case '>': if (peek() == '=') { input(); yylval.i = GE; RET(GE); } else if (peek() == '>') { input(); yylval.i = APPEND; RET(APPEND); } else { yylval.i = GT; RET(GT); } case '+': if (peek() == '+') { input(); yylval.i = INCR; RET(INCR); } else if (peek() == '=') { input(); yylval.i = ADDEQ; RET(ASGNOP); } else RET('+'); case '-': if (peek() == '-') { input(); yylval.i = DECR; RET(DECR); } else if (peek() == '=') { input(); yylval.i = SUBEQ; RET(ASGNOP); } else RET('-'); case '*': if (peek() == '=') { /* *= */ input(); yylval.i = MULTEQ; RET(ASGNOP); } else if (peek() == '*') { /* ** or **= */ input(); /* eat 2nd * */ if (peek() == '=') { input(); yylval.i = POWEQ; RET(ASGNOP); } else { RET(POWER); } } else RET('*'); case '/': RET('/'); case '%': if (peek() == '=') { input(); yylval.i = MODEQ; RET(ASGNOP); } else RET('%'); case '^': if (peek() == '=') { input(); yylval.i = POWEQ; RET(ASGNOP); } else RET(POWER); case '$': /* BUG: awkward, if not wrong */ c = gettok(&buf, &bufsize); if (isalpha(c)) { if (strcmp(buf, "NF") == 0) { /* very special */ unputstr("(NF)"); RET(INDIRECT); } c = peek(); if (c == '(' || c == '[' || (infunc && isarg(buf) >= 0)) { unputstr(buf); RET(INDIRECT); } yylval.cp = setsymtab(buf, "", 0.0, STR|NUM, symtab); RET(IVAR); } else if (c == 0) { /* */ SYNTAX( "unexpected end of input after $" ); RET(';'); } else { unputstr(buf); RET(INDIRECT); } case '}': if (--bracecnt < 0) SYNTAX( "extra }" ); sc = 1; RET(';'); case ']': if (--brackcnt < 0) SYNTAX( "extra ]" ); RET(']'); case ')': if (--parencnt < 0) SYNTAX( "extra )" ); RET(')'); case '{': bracecnt++; RET('{'); case '[': brackcnt++; RET('['); case '(': parencnt++; RET('('); case '"': return string(); /* BUG: should be like tran.c ? */ default: RET(c); } } } int string(void) { int c, n; char *s, *bp; - static char *buf = NULL; + static char *buf = 0; static int bufsz = 500; - if (buf == NULL && (buf = (char *) malloc(bufsz)) == NULL) + if (buf == 0 && (buf = (char *) malloc(bufsz)) == NULL) FATAL("out of space for strings"); for (bp = buf; (c = input()) != '"'; ) { if (!adjbuf(&buf, &bufsz, bp-buf+2, 500, &bp, "string")) FATAL("out of space for string %.10s...", buf); switch (c) { case '\n': case '\r': case 0: + *bp = '\0'; SYNTAX( "non-terminated string %.10s...", buf ); - lineno++; if (c == 0) /* hopeless */ FATAL( "giving up" ); + lineno++; break; case '\\': c = input(); switch (c) { case '"': *bp++ = '"'; break; case 'n': *bp++ = '\n'; break; case 't': *bp++ = '\t'; break; case 'f': *bp++ = '\f'; break; case 'r': *bp++ = '\r'; break; case 'b': *bp++ = '\b'; break; case 'v': *bp++ = '\v'; break; case 'a': *bp++ = '\007'; break; case '\\': *bp++ = '\\'; break; case '0': case '1': case '2': /* octal: \d \dd \ddd */ case '3': case '4': case '5': case '6': case '7': n = c - '0'; if ((c = peek()) >= '0' && c < '8') { n = 8 * n + input() - '0'; if ((c = peek()) >= '0' && c < '8') n = 8 * n + input() - '0'; } *bp++ = n; break; case 'x': /* hex \x0-9a-fA-F + */ { char xbuf[100], *px; for (px = xbuf; (c = input()) != 0 && px-xbuf < 100-2; ) { if (isdigit(c) || (c >= 'a' && c <= 'f') || (c >= 'A' && c <= 'F')) *px++ = c; else break; } *px = 0; unput(c); sscanf(xbuf, "%x", (unsigned int *) &n); *bp++ = n; break; } default: *bp++ = c; break; } break; default: *bp++ = c; break; } } *bp = 0; s = tostring(buf); *bp++ = ' '; *bp++ = 0; yylval.cp = setsymtab(buf, s, 0.0, CON|STR|DONTFREE, symtab); RET(STRING); } int binsearch(char *w, Keyword *kp, int n) { int cond, low, mid, high; low = 0; high = n - 1; while (low <= high) { mid = (low + high) / 2; if ((cond = strcmp(w, kp[mid].word)) < 0) high = mid - 1; else if (cond > 0) low = mid + 1; else return mid; } return -1; } int word(char *w) { Keyword *kp; int c, n; n = binsearch(w, keywords, sizeof(keywords)/sizeof(keywords[0])); /* BUG: this ought to be inside the if; in theory could fault (daniel barrett) */ kp = keywords + n; if (n != -1) { /* found in table */ yylval.i = kp->sub; switch (kp->type) { /* special handling */ case BLTIN: if (kp->sub == FSYSTEM && safe) SYNTAX( "system is unsafe" ); RET(kp->type); case FUNC: if (infunc) SYNTAX( "illegal nested function" ); RET(kp->type); case RETURN: if (!infunc) SYNTAX( "return not in function" ); RET(kp->type); case VARNF: yylval.cp = setsymtab("NF", "", 0.0, NUM, symtab); RET(VARNF); default: RET(kp->type); } } c = peek(); /* look for '(' */ if (c != '(' && infunc && (n=isarg(w)) >= 0) { yylval.i = n; RET(ARG); } else { yylval.cp = setsymtab(w, "", 0.0, STR|NUM|DONTFREE, symtab); if (c == '(') { RET(CALL); } else { RET(VAR); } } } void startreg(void) /* next call to yylex will return a regular expression */ { reg = 1; } int regexpr(void) { int c; - static char *buf = NULL; + static char *buf = 0; static int bufsz = 500; char *bp; - if (buf == NULL && (buf = (char *) malloc(bufsz)) == NULL) + if (buf == 0 && (buf = (char *) malloc(bufsz)) == NULL) FATAL("out of space for rex expr"); bp = buf; for ( ; (c = input()) != '/' && c != 0; ) { if (!adjbuf(&buf, &bufsz, bp-buf+3, 500, &bp, "regexpr")) FATAL("out of space for reg expr %.10s...", buf); if (c == '\n') { + *bp = '\0'; SYNTAX( "newline in regular expression %.10s...", buf ); unput('\n'); break; } else if (c == '\\') { *bp++ = '\\'; *bp++ = input(); } else { *bp++ = c; } } *bp = 0; if (c == 0) SYNTAX("non-terminated regular expression %.10s...", buf); yylval.s = tostring(buf); unput('/'); RET(REGEXPR); } /* low-level lexical stuff, sort of inherited from lex */ char ebuf[300]; char *ep = ebuf; char yysbuf[100]; /* pushback buffer */ char *yysptr = yysbuf; -FILE *yyin = NULL; +FILE *yyin = 0; int input(void) /* get next lexical input character */ { int c; extern char *lexprog; if (yysptr > yysbuf) c = (uschar)*--yysptr; else if (lexprog != NULL) { /* awk '...' */ if ((c = (uschar)*lexprog) != 0) lexprog++; } else /* awk -f ... */ c = pgetc(); - if (c == '\n') - lineno++; - else if (c == EOF) + if (c == EOF) c = 0; if (ep >= ebuf + sizeof ebuf) ep = ebuf; - return *ep++ = c; + *ep = c; + if (c != 0) { + ep++; + } + return (c); } void unput(int c) /* put lexical character back on input */ { - if (c == '\n') - lineno--; if (yysptr >= yysbuf + sizeof(yysbuf)) FATAL("pushed back too much: %.20s...", yysbuf); *yysptr++ = c; if (--ep < ebuf) ep = ebuf + sizeof(ebuf) - 1; } void unputstr(const char *s) /* put a string back on input */ { int i; for (i = strlen(s)-1; i >= 0; i--) unput(s[i]); } Index: head/contrib/one-true-awk/lib.c =================================================================== --- head/contrib/one-true-awk/lib.c (revision 348510) +++ head/contrib/one-true-awk/lib.c (revision 348511) @@ -1,707 +1,729 @@ /**************************************************************** Copyright (C) Lucent Technologies 1997 All Rights Reserved Permission to use, copy, modify, and distribute this software and its documentation for any purpose and without fee is hereby granted, provided that the above copyright notice appear in all copies and that both that the copyright notice and this permission notice and warranty disclaimer appear in supporting documentation, and that the name Lucent Technologies or any of its entities not be used in advertising or publicity pertaining to distribution of the software without specific, written prior permission. LUCENT DISCLAIMS ALL WARRANTIES WITH REGARD TO THIS SOFTWARE, INCLUDING ALL IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL LUCENT OR ANY OF ITS ENTITIES BE LIABLE FOR ANY SPECIAL, 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. ****************************************************************/ #define DEBUG #include #include #include #include #include #include #include "awk.h" #include "ytab.h" FILE *infile = NULL; char *file = ""; char *record; int recsize = RECSIZE; char *fields; int fieldssize = RECSIZE; Cell **fldtab; /* pointers to Cells */ char inputFS[100] = " "; #define MAXFLD 2 int nfields = MAXFLD; /* last allocated slot for $i */ int donefld; /* 1 = implies rec broken into fields */ int donerec; /* 1 = record is valid (no flds have changed) */ int lastfld = 0; /* last used field */ int argno = 1; /* current input argument number */ extern Awkfloat *ARGC; static Cell dollar0 = { OCELL, CFLD, NULL, "", 0.0, REC|STR|DONTFREE }; static Cell dollar1 = { OCELL, CFLD, NULL, "", 0.0, FLD|STR|DONTFREE }; void recinit(unsigned int n) { if ( (record = (char *) malloc(n)) == NULL || (fields = (char *) malloc(n+1)) == NULL - || (fldtab = (Cell **) malloc((nfields+1) * sizeof(Cell *))) == NULL + || (fldtab = (Cell **) malloc((nfields+2) * sizeof(Cell *))) == NULL || (fldtab[0] = (Cell *) malloc(sizeof(Cell))) == NULL ) FATAL("out of space for $0 and fields"); *record = '\0'; *fldtab[0] = dollar0; fldtab[0]->sval = record; fldtab[0]->nval = tostring("0"); makefields(1, nfields); } void makefields(int n1, int n2) /* create $n1..$n2 inclusive */ { char temp[50]; int i; for (i = n1; i <= n2; i++) { fldtab[i] = (Cell *) malloc(sizeof (struct Cell)); if (fldtab[i] == NULL) FATAL("out of space in makefields %d", i); *fldtab[i] = dollar1; sprintf(temp, "%d", i); fldtab[i]->nval = tostring(temp); } } void initgetrec(void) { int i; char *p; for (i = 1; i < *ARGC; i++) { p = getargv(i); /* find 1st real filename */ if (p == NULL || *p == '\0') { /* deleted or zapped */ argno++; continue; } if (!isclvar(p)) { setsval(lookup("FILENAME", symtab), p); return; } setclvar(p); /* a commandline assignment before filename */ argno++; } infile = stdin; /* no filenames, so use stdin */ } static int firsttime = 1; int getrec(char **pbuf, int *pbufsize, int isrecord) /* get next input record */ { /* note: cares whether buf == record */ int c; char *buf = *pbuf; uschar saveb0; int bufsize = *pbufsize, savebufsize = bufsize; if (firsttime) { firsttime = 0; initgetrec(); } dprintf( ("RS=<%s>, FS=<%s>, ARGC=%g, FILENAME=%s\n", *RS, *FS, *ARGC, *FILENAME) ); if (isrecord) { donefld = 0; donerec = 1; } saveb0 = buf[0]; buf[0] = 0; while (argno < *ARGC || infile == stdin) { dprintf( ("argno=%d, file=|%s|\n", argno, file) ); if (infile == NULL) { /* have to open a new file */ file = getargv(argno); if (file == NULL || *file == '\0') { /* deleted or zapped */ argno++; continue; } if (isclvar(file)) { /* a var=value arg */ setclvar(file); argno++; continue; } *FILENAME = file; dprintf( ("opening file %s\n", file) ); if (*file == '-' && *(file+1) == '\0') infile = stdin; else if ((infile = fopen(file, "r")) == NULL) FATAL("can't open file %s", file); setfval(fnrloc, 0.0); } c = readrec(&buf, &bufsize, infile); if (c != 0 || buf[0] != '\0') { /* normal record */ if (isrecord) { if (freeable(fldtab[0])) xfree(fldtab[0]->sval); fldtab[0]->sval = buf; /* buf == record */ fldtab[0]->tval = REC | STR | DONTFREE; if (is_number(fldtab[0]->sval)) { fldtab[0]->fval = atof(fldtab[0]->sval); fldtab[0]->tval |= NUM; } } setfval(nrloc, nrloc->fval+1); setfval(fnrloc, fnrloc->fval+1); *pbuf = buf; *pbufsize = bufsize; return 1; } /* EOF arrived on this file; set up next */ if (infile != stdin) fclose(infile); infile = NULL; argno++; } buf[0] = saveb0; *pbuf = buf; *pbufsize = savebufsize; return 0; /* true end of file */ } void nextfile(void) { if (infile != NULL && infile != stdin) fclose(infile); infile = NULL; argno++; } int readrec(char **pbuf, int *pbufsize, FILE *inf) /* read one record into buf */ { int sep, c; char *rr, *buf = *pbuf; int bufsize = *pbufsize; + char *rs = getsval(rsloc); - if (strlen(*FS) >= sizeof(inputFS)) + if (strlen(getsval(fsloc)) >= sizeof (inputFS)) FATAL("field separator %.10s... is too long", *FS); /*fflush(stdout); avoids some buffering problem but makes it 25% slower*/ strcpy(inputFS, *FS); /* for subsequent field splitting */ - if ((sep = **RS) == 0) { + if ((sep = *rs) == 0) { sep = '\n'; while ((c=getc(inf)) == '\n' && c != EOF) /* skip leading \n's */ ; if (c != EOF) ungetc(c, inf); } for (rr = buf; ; ) { for (; (c=getc(inf)) != sep && c != EOF; ) { if (rr-buf+1 > bufsize) if (!adjbuf(&buf, &bufsize, 1+rr-buf, recsize, &rr, "readrec 1")) FATAL("input record `%.30s...' too long", buf); *rr++ = c; } - if (**RS == sep || c == EOF) + if (*rs == sep || c == EOF) break; if ((c = getc(inf)) == '\n' || c == EOF) /* 2 in a row */ break; if (!adjbuf(&buf, &bufsize, 2+rr-buf, recsize, &rr, "readrec 2")) FATAL("input record `%.30s...' too long", buf); *rr++ = '\n'; *rr++ = c; } if (!adjbuf(&buf, &bufsize, 1+rr-buf, recsize, &rr, "readrec 3")) FATAL("input record `%.30s...' too long", buf); *rr = 0; dprintf( ("readrec saw <%s>, returns %d\n", buf, c == EOF && rr == buf ? 0 : 1) ); *pbuf = buf; *pbufsize = bufsize; return c == EOF && rr == buf ? 0 : 1; } char *getargv(int n) /* get ARGV[n] */ { Cell *x; char *s, temp[50]; extern Array *ARGVtab; sprintf(temp, "%d", n); if (lookup(temp, ARGVtab) == NULL) return NULL; x = setsymtab(temp, "", 0.0, STR, ARGVtab); s = getsval(x); dprintf( ("getargv(%d) returns |%s|\n", n, s) ); return s; } void setclvar(char *s) /* set var=value from s */ { char *p; Cell *q; for (p=s; *p != '='; p++) ; *p++ = 0; p = qstring(p, '\0'); q = setsymtab(s, p, 0.0, STR, symtab); setsval(q, p); if (is_number(q->sval)) { q->fval = atof(q->sval); q->tval |= NUM; } dprintf( ("command line set %s to |%s|\n", s, p) ); } void fldbld(void) /* create fields from current record */ { /* this relies on having fields[] the same length as $0 */ /* the fields are all stored in this one array with \0's */ /* possibly with a final trailing \0 not associated with any field */ char *r, *fr, sep; Cell *p; int i, j, n; if (donefld) return; if (!isstr(fldtab[0])) getsval(fldtab[0]); r = fldtab[0]->sval; n = strlen(r); if (n > fieldssize) { xfree(fields); if ((fields = (char *) malloc(n+2)) == NULL) /* possibly 2 final \0s */ FATAL("out of space for fields in fldbld %d", n); fieldssize = n; } fr = fields; i = 0; /* number of fields accumulated here */ + if (strlen(getsval(fsloc)) >= sizeof (inputFS)) + FATAL("field separator %.10s... is too long", *FS); strcpy(inputFS, *FS); if (strlen(inputFS) > 1) { /* it's a regular expression */ i = refldbld(r, inputFS); } else if ((sep = *inputFS) == ' ') { /* default whitespace */ for (i = 0; ; ) { while (*r == ' ' || *r == '\t' || *r == '\n') r++; if (*r == 0) break; i++; if (i > nfields) growfldtab(i); if (freeable(fldtab[i])) xfree(fldtab[i]->sval); fldtab[i]->sval = fr; fldtab[i]->tval = FLD | STR | DONTFREE; do *fr++ = *r++; while (*r != ' ' && *r != '\t' && *r != '\n' && *r != '\0'); *fr++ = 0; } *fr = 0; } else if ((sep = *inputFS) == 0) { /* new: FS="" => 1 char/field */ for (i = 0; *r != 0; r++) { char buf[2]; i++; if (i > nfields) growfldtab(i); if (freeable(fldtab[i])) xfree(fldtab[i]->sval); buf[0] = *r; buf[1] = 0; fldtab[i]->sval = tostring(buf); fldtab[i]->tval = FLD | STR; } *fr = 0; } else if (*r != 0) { /* if 0, it's a null field */ /* subtlecase : if length(FS) == 1 && length(RS > 0) * \n is NOT a field separator (cf awk book 61,84). * this variable is tested in the inner while loop. */ int rtest = '\n'; /* normal case */ if (strlen(*RS) > 0) rtest = '\0'; for (;;) { i++; if (i > nfields) growfldtab(i); if (freeable(fldtab[i])) xfree(fldtab[i]->sval); fldtab[i]->sval = fr; fldtab[i]->tval = FLD | STR | DONTFREE; while (*r != sep && *r != rtest && *r != '\0') /* \n is always a separator */ *fr++ = *r++; *fr++ = 0; if (*r++ == 0) break; } *fr = 0; } if (i > nfields) FATAL("record `%.30s...' has too many fields; can't happen", r); cleanfld(i+1, lastfld); /* clean out junk from previous record */ lastfld = i; donefld = 1; for (j = 1; j <= lastfld; j++) { p = fldtab[j]; if(is_number(p->sval)) { p->fval = atof(p->sval); p->tval |= NUM; } } setfval(nfloc, (Awkfloat) lastfld); + donerec = 1; /* restore */ if (dbg) { for (j = 0; j <= lastfld; j++) { p = fldtab[j]; printf("field %d (%s): |%s|\n", j, p->nval, p->sval); } } } void cleanfld(int n1, int n2) /* clean out fields n1 .. n2 inclusive */ { /* nvals remain intact */ Cell *p; int i; for (i = n1; i <= n2; i++) { p = fldtab[i]; if (freeable(p)) xfree(p->sval); p->sval = ""; p->tval = FLD | STR | DONTFREE; } } void newfld(int n) /* add field n after end of existing lastfld */ { if (n > nfields) growfldtab(n); cleanfld(lastfld+1, n); lastfld = n; setfval(nfloc, (Awkfloat) n); } +void setlastfld(int n) /* set lastfld cleaning fldtab cells if necessary */ +{ + if (n < 0) + FATAL("cannot set NF to a negative value"); + if (n > nfields) + growfldtab(n); + + if (lastfld < n) + cleanfld(lastfld+1, n); + else + cleanfld(n+1, lastfld); + + lastfld = n; +} + Cell *fieldadr(int n) /* get nth field */ { if (n < 0) FATAL("trying to access out of range field %d", n); if (n > nfields) /* fields after NF are empty */ growfldtab(n); /* but does not increase NF */ return(fldtab[n]); } void growfldtab(int n) /* make new fields up to at least $n */ { int nf = 2 * nfields; size_t s; if (n > nf) nf = n; s = (nf+1) * (sizeof (struct Cell *)); /* freebsd: how much do we need? */ if (s / sizeof(struct Cell *) - 1 == nf) /* didn't overflow */ fldtab = (Cell **) realloc(fldtab, s); else /* overflow sizeof int */ xfree(fldtab); /* make it null */ if (fldtab == NULL) FATAL("out of space creating %d fields", nf); makefields(nfields+1, nf); nfields = nf; } int refldbld(const char *rec, const char *fs) /* build fields from reg expr in FS */ { /* this relies on having fields[] the same length as $0 */ /* the fields are all stored in this one array with \0's */ char *fr; int i, tempstat, n; fa *pfa; n = strlen(rec); if (n > fieldssize) { xfree(fields); if ((fields = (char *) malloc(n+1)) == NULL) FATAL("out of space for fields in refldbld %d", n); fieldssize = n; } fr = fields; *fr = '\0'; if (*rec == '\0') return 0; pfa = makedfa(fs, 1); dprintf( ("into refldbld, rec = <%s>, pat = <%s>\n", rec, fs) ); tempstat = pfa->initstat; for (i = 1; ; i++) { if (i > nfields) growfldtab(i); if (freeable(fldtab[i])) xfree(fldtab[i]->sval); fldtab[i]->tval = FLD | STR | DONTFREE; fldtab[i]->sval = fr; dprintf( ("refldbld: i=%d\n", i) ); if (nematch(pfa, rec)) { pfa->initstat = 2; /* horrible coupling to b.c */ dprintf( ("match %s (%d chars)\n", patbeg, patlen) ); strncpy(fr, rec, patbeg-rec); fr += patbeg - rec + 1; *(fr-1) = '\0'; rec = patbeg + patlen; } else { dprintf( ("no match %s\n", rec) ); strcpy(fr, rec); pfa->initstat = tempstat; break; } } return i; } void recbld(void) /* create $0 from $1..$NF if necessary */ { int i; char *r, *p; + char *sep = getsval(ofsloc); if (donerec == 1) return; r = record; for (i = 1; i <= *NF; i++) { p = getsval(fldtab[i]); if (!adjbuf(&record, &recsize, 1+strlen(p)+r-record, recsize, &r, "recbld 1")) FATAL("created $0 `%.30s...' too long", record); while ((*r = *p++) != 0) r++; if (i < *NF) { - if (!adjbuf(&record, &recsize, 2+strlen(*OFS)+r-record, recsize, &r, "recbld 2")) + if (!adjbuf(&record, &recsize, 2+strlen(sep)+r-record, recsize, &r, "recbld 2")) FATAL("created $0 `%.30s...' too long", record); - for (p = *OFS; (*r = *p++) != 0; ) + for (p = sep; (*r = *p++) != 0; ) r++; } } if (!adjbuf(&record, &recsize, 2+r-record, recsize, &r, "recbld 3")) FATAL("built giant record `%.30s...'", record); *r = '\0'; dprintf( ("in recbld inputFS=%s, fldtab[0]=%p\n", inputFS, (void*)fldtab[0]) ); if (freeable(fldtab[0])) xfree(fldtab[0]->sval); fldtab[0]->tval = REC | STR | DONTFREE; fldtab[0]->sval = record; dprintf( ("in recbld inputFS=%s, fldtab[0]=%p\n", inputFS, (void*)fldtab[0]) ); dprintf( ("recbld = |%s|\n", record) ); donerec = 1; } int errorflag = 0; void yyerror(const char *s) { SYNTAX("%s", s); } void SYNTAX(const char *fmt, ...) { extern char *cmdname, *curfname; static int been_here = 0; va_list varg; if (been_here++ > 2) return; fprintf(stderr, "%s: ", cmdname); va_start(varg, fmt); vfprintf(stderr, fmt, varg); va_end(varg); fprintf(stderr, " at source line %d", lineno); if (curfname != NULL) fprintf(stderr, " in function %s", curfname); if (compile_time == 1 && cursource() != NULL) fprintf(stderr, " source file %s", cursource()); fprintf(stderr, "\n"); errorflag = 2; eprint(); } void fpecatch(int n) { FATAL("floating point exception %d", n); } extern int bracecnt, brackcnt, parencnt; void bracecheck(void) { int c; static int beenhere = 0; if (beenhere++) return; while ((c = input()) != EOF && c != '\0') bclass(c); bcheck2(bracecnt, '{', '}'); bcheck2(brackcnt, '[', ']'); bcheck2(parencnt, '(', ')'); } void bcheck2(int n, int c1, int c2) { if (n == 1) fprintf(stderr, "\tmissing %c\n", c2); else if (n > 1) fprintf(stderr, "\t%d missing %c's\n", n, c2); else if (n == -1) fprintf(stderr, "\textra %c\n", c2); else if (n < -1) fprintf(stderr, "\t%d extra %c's\n", -n, c2); } void FATAL(const char *fmt, ...) { extern char *cmdname; va_list varg; fflush(stdout); fprintf(stderr, "%s: ", cmdname); va_start(varg, fmt); vfprintf(stderr, fmt, varg); va_end(varg); error(); if (dbg > 1) /* core dump if serious debugging on */ abort(); exit(2); } void WARNING(const char *fmt, ...) { extern char *cmdname; va_list varg; fflush(stdout); fprintf(stderr, "%s: ", cmdname); va_start(varg, fmt); vfprintf(stderr, fmt, varg); va_end(varg); error(); } void error() { extern Node *curnode; fprintf(stderr, "\n"); if (compile_time != 2 && NR && *NR > 0) { fprintf(stderr, " input record number %d", (int) (*FNR)); if (strcmp(*FILENAME, "-") != 0) fprintf(stderr, ", file %s", *FILENAME); fprintf(stderr, "\n"); } if (compile_time != 2 && curnode) fprintf(stderr, " source line number %d", curnode->lineno); else if (compile_time != 2 && lineno) fprintf(stderr, " source line number %d", lineno); if (compile_time == 1 && cursource() != NULL) fprintf(stderr, " source file %s", cursource()); fprintf(stderr, "\n"); eprint(); } void eprint(void) /* try to print context around error */ { char *p, *q; int c; static int been_here = 0; extern char ebuf[], *ep; if (compile_time == 2 || compile_time == 0 || been_here++ > 0 || ebuf == ep) return; + if (ebuf == ep) + return; p = ep - 1; if (p > ebuf && *p == '\n') p--; for ( ; p > ebuf && *p != '\n' && *p != '\0'; p--) ; while (*p == '\n') p++; fprintf(stderr, " context is\n\t"); for (q=ep-1; q>=p && *q!=' ' && *q!='\t' && *q!='\n'; q--) ; for ( ; p < q; p++) if (*p) putc(*p, stderr); fprintf(stderr, " >>> "); for ( ; p < ep; p++) if (*p) putc(*p, stderr); fprintf(stderr, " <<< "); if (*ep) while ((c = input()) != '\n' && c != '\0' && c != EOF) { putc(c, stderr); bclass(c); } putc('\n', stderr); ep = ebuf; } void bclass(int c) { switch (c) { case '{': bracecnt++; break; case '}': bracecnt--; break; case '[': brackcnt++; break; case ']': brackcnt--; break; case '(': parencnt++; break; case ')': parencnt--; break; } } double errcheck(double x, const char *s) { if (errno == EDOM) { errno = 0; WARNING("%s argument out of domain", s); x = 1; } else if (errno == ERANGE) { errno = 0; WARNING("%s result out of range", s); x = 1; } return x; } int isclvar(const char *s) /* is s of form var=something ? */ { const char *os = s; if (!isalpha((uschar) *s) && *s != '_') return 0; for ( ; *s; s++) if (!(isalnum((uschar) *s) || *s == '_')) break; - return *s == '=' && s > os && *(s+1) != '='; + return *s == '=' && s > os; } /* strtod is supposed to be a proper test of what's a valid number */ /* appears to be broken in gcc on linux: thinks 0x123 is a valid FP number */ /* wrong: violates 4.10.1.4 of ansi C standard */ #include int is_number(const char *s) { double r; char *ep; errno = 0; r = strtod(s, &ep); if (ep == s || r == HUGE_VAL || errno == ERANGE) return 0; while (*ep == ' ' || *ep == '\t' || *ep == '\n') ep++; if (*ep == '\0') return 1; else return 0; } Index: head/contrib/one-true-awk/main.c =================================================================== --- head/contrib/one-true-awk/main.c (revision 348510) +++ head/contrib/one-true-awk/main.c (revision 348511) @@ -1,218 +1,225 @@ /**************************************************************** Copyright (C) Lucent Technologies 1997 All Rights Reserved Permission to use, copy, modify, and distribute this software and its documentation for any purpose and without fee is hereby granted, provided that the above copyright notice appear in all copies and that both that the copyright notice and this permission notice and warranty disclaimer appear in supporting documentation, and that the name Lucent Technologies or any of its entities not be used in advertising or publicity pertaining to distribution of the software without specific, written prior permission. LUCENT DISCLAIMS ALL WARRANTIES WITH REGARD TO THIS SOFTWARE, INCLUDING ALL IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL LUCENT OR ANY OF ITS ENTITIES BE LIABLE FOR ANY SPECIAL, 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. ****************************************************************/ #include __FBSDID("$FreeBSD$"); +const char *version = "version 20190529 (FreeBSD)"; -const char *version = "version 20121220 (FreeBSD)"; - #define DEBUG #include #include #include #include #include #include #include "awk.h" #include "ytab.h" extern char **environ; extern int nfields; int dbg = 0; Awkfloat srand_seed = 1; char *cmdname; /* gets argv[0] for error messages */ extern FILE *yyin; /* lex input file */ char *lexprog; /* points to program argument if it exists */ extern int errorflag; /* non-zero if any syntax errors; set by yyerror */ int compile_time = 2; /* for error printing: */ /* 2 = cmdline, 1 = compile, 0 = running */ #define MAX_PFILE 20 /* max number of -f's */ char *pfile[MAX_PFILE]; /* program filenames from -f's */ int npfile = 0; /* number of filenames */ int curpfile = 0; /* current filename */ int safe = 0; /* 1 => "safe" mode */ +/* Can this work with recursive calls? I don't think so. +void segvcatch(int n) +{ + FATAL("segfault. Do you have an unbounded recursive call?", n); +} +*/ + int main(int argc, char *argv[]) { const char *fs = NULL; setlocale(LC_CTYPE, ""); setlocale(LC_COLLATE, ""); setlocale(LC_NUMERIC, "C"); /* for parsing cmdline & prog */ cmdname = argv[0]; if (argc == 1) { fprintf(stderr, "usage: %s [-F fs] [-v var=value] [-f progfile | 'prog'] [file ...]\n", cmdname); exit(1); } signal(SIGFPE, fpecatch); + /*signal(SIGSEGV, segvcatch); experiment */ srand_seed = 1; srandom((unsigned long) srand_seed); yyin = NULL; symtab = makesymtab(NSYMTAB/NSYMTAB); while (argc > 1 && argv[1][0] == '-' && argv[1][1] != '\0') { if (strcmp(argv[1],"-version") == 0 || strcmp(argv[1],"--version") == 0) { printf("awk %s\n", version); exit(0); break; } - if (strncmp(argv[1], "--", 2) == 0) { /* explicit end of args */ + if (strcmp(argv[1], "--") == 0) { /* explicit end of args */ argc--; argv++; break; } switch (argv[1][1]) { case 's': if (strcmp(argv[1], "-safe") == 0) safe = 1; break; case 'f': /* next argument is program filename */ if (argv[1][2] != 0) { /* arg is -fsomething */ if (npfile >= MAX_PFILE - 1) FATAL("too many -f options"); pfile[npfile++] = &argv[1][2]; } else { /* arg is -f something */ argc--; argv++; if (argc <= 1) FATAL("no program filename"); if (npfile >= MAX_PFILE - 1) FATAL("too many -f options"); pfile[npfile++] = argv[1]; } break; case 'F': /* set field separator */ if (argv[1][2] != 0) { /* arg is -Fsomething */ if (argv[1][2] == 't' && argv[1][3] == 0) /* wart: t=>\t */ fs = "\t"; else if (argv[1][2] != 0) fs = &argv[1][2]; } else { /* arg is -F something */ argc--; argv++; if (argc > 1 && argv[1][0] == 't' && argv[1][1] == 0) /* wart: t=>\t */ fs = "\t"; else if (argc > 1 && argv[1][0] != 0) fs = &argv[1][0]; } if (fs == NULL || *fs == '\0') WARNING("field separator FS is empty"); break; case 'v': /* -v a=1 to be done NOW. one -v for each */ if (argv[1][2] != 0) { /* arg is -vsomething */ if (isclvar(&argv[1][2])) setclvar(&argv[1][2]); else FATAL("invalid -v option argument: %s", &argv[1][2]); } else { /* arg is -v something */ argc--; argv++; if (argc <= 1) FATAL("no variable name"); if (isclvar(argv[1])) setclvar(argv[1]); else FATAL("invalid -v option argument: %s", argv[1]); } break; case 'd': dbg = atoi(&argv[1][2]); if (dbg == 0) dbg = 1; printf("awk %s\n", version); break; default: WARNING("unknown option %s ignored", argv[1]); break; } argc--; argv++; } /* argv[1] is now the first argument */ if (npfile == 0) { /* no -f; first argument is program */ if (argc <= 1) { if (dbg) exit(0); FATAL("no program given"); } dprintf( ("program = |%s|\n", argv[1]) ); lexprog = argv[1]; argc--; argv++; } recinit(recsize); syminit(); compile_time = 1; argv[0] = cmdname; /* put prog name at front of arglist */ dprintf( ("argc=%d, argv[0]=%s\n", argc, argv[0]) ); arginit(argc, argv); if (!safe) envinit(environ); yyparse(); setlocale(LC_NUMERIC, ""); /* back to whatever it is locally */ if (fs) *FS = qstring(fs, '\0'); dprintf( ("errorflag=%d\n", errorflag) ); if (errorflag == 0) { compile_time = 0; run(winner); } else bracecheck(); return(errorflag); } int pgetc(void) /* get 1 character from awk program */ { int c; for (;;) { if (yyin == NULL) { if (curpfile >= npfile) return EOF; if (strcmp(pfile[curpfile], "-") == 0) yyin = stdin; else if ((yyin = fopen(pfile[curpfile], "r")) == NULL) FATAL("can't open file %s", pfile[curpfile]); lineno = 1; } if ((c = getc(yyin)) != EOF) return c; if (yyin != stdin) fclose(yyin); yyin = NULL; curpfile++; } } char *cursource(void) /* current source file name */ { if (npfile > 0) return pfile[curpfile]; else return NULL; } Index: head/contrib/one-true-awk/makefile =================================================================== --- head/contrib/one-true-awk/makefile (revision 348510) +++ head/contrib/one-true-awk/makefile (revision 348511) @@ -1,86 +1,109 @@ # /**************************************************************** # Copyright (C) Lucent Technologies 1997 # All Rights Reserved # # Permission to use, copy, modify, and distribute this software and # its documentation for any purpose and without fee is hereby # granted, provided that the above copyright notice appear in all # copies and that both that the copyright notice and this # permission notice and warranty disclaimer appear in supporting # documentation, and that the name Lucent Technologies or any of # its entities not be used in advertising or publicity pertaining # to distribution of the software without specific, written prior # permission. # # LUCENT DISCLAIMS ALL WARRANTIES WITH REGARD TO THIS SOFTWARE, # INCLUDING ALL IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS. # IN NO EVENT SHALL LUCENT OR ANY OF ITS ENTITIES BE LIABLE FOR ANY # SPECIAL, 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. # ****************************************************************/ CFLAGS = -g -CFLAGS = -O2 CFLAGS = +CFLAGS = -O2 -CC = gcc -Wall -g -Wwrite-strings -CC = gcc -fprofile-arcs -ftest-coverage # then gcov f1.c; cat f1.c.gcov -CC = gcc -g -Wall -pedantic -CC = gcc -O4 -Wall -pedantic -fno-strict-aliasing +# compiler options +#CC = gcc -Wall -g -Wwrite-strings +#CC = gcc -O4 -Wall -pedantic -fno-strict-aliasing +#CC = gcc -fprofile-arcs -ftest-coverage # then gcov f1.c; cat f1.c.gcov +HOSTCC = gcc -g -Wall -pedantic +CC = $(HOSTCC) # change this is cross-compiling. -YACC = bison -d -y -YACC = yacc -d -S +# yacc options. pick one; this varies a lot by system. #YFLAGS = -d -S - # -S uses sprintf in yacc parser instead of sprint +YACC = bison -d -y +#YACC = yacc -d +# -S uses sprintf in yacc parser instead of sprint OFILES = b.o main.o parse.o proctab.o tran.o lib.o run.o lex.o SOURCE = awk.h ytab.c ytab.h proto.h awkgram.y lex.c b.c main.c \ maketab.c parse.c lib.c run.c tran.c proctab.c LISTING = awk.h proto.h awkgram.y lex.c b.c main.c maketab.c parse.c \ lib.c run.c tran.c -SHIP = README FIXES $(SOURCE) ytab[ch].bak makefile \ +SHIP = README LICENSE FIXES $(SOURCE) ytab[ch].bak makefile \ awk.1 a.out: ytab.o $(OFILES) $(CC) $(CFLAGS) ytab.o $(OFILES) $(ALLOC) -lm $(OFILES): awk.h ytab.h proto.h -ytab.o: awk.h proto.h awkgram.y +#Clear dependency for parallel build: (make -j) +#YACC generated y.tab.c and y.tab.h at the same time +#this needs to be a static pattern rules otherwise multiple target +#are mapped onto multiple executions of yacc, which overwrite +#each others outputs. +y%.c y%.h: awk.h proto.h awkgram.y $(YACC) $(YFLAGS) awkgram.y - mv y.tab.c ytab.c - mv y.tab.h ytab.h - $(CC) $(CFLAGS) -c ytab.c + mv y.$*.c y$*.c + mv y.$*.h y$*.h +ytab.h: ytab.c + proctab.c: maketab - ./maketab >proctab.c + ./maketab ytab.h >proctab.c maketab: ytab.h maketab.c - $(CC) $(CFLAGS) maketab.c -o maketab + $(HOSTCC) $(CFLAGS) maketab.c -o maketab bundle: @cp ytab.h ytabh.bak @cp ytab.c ytabc.bak @bundle $(SHIP) tar: @cp ytab.h ytabh.bak @cp ytab.c ytabc.bak @bundle $(SHIP) >awk.shar @tar cf awk.tar $(SHIP) gzip awk.tar ls -l awk.tar.gz @zip awk.zip $(SHIP) ls -l awk.zip +gitadd: + git add README LICENSE FIXES \ + awk.h proto.h awkgram.y lex.c b.c main.c maketab.c parse.c \ + lib.c run.c tran.c \ + makefile awk.1 awktest.tar + +gitpush: + # only do this once: + # git remote add origin https://github.com/onetrueawk/awk.git + git push -u origin master + names: @echo $(LISTING) clean: rm -f a.out *.o *.obj maketab maketab.exe *.bb *.bbg *.da *.gcov *.gcno *.gcda # proctab.c + +cleaner: + rm -f a.out *.o *.obj maketab maketab.exe *.bb *.bbg *.da *.gcov *.gcno *.gcda proctab.c ytab* Index: head/contrib/one-true-awk/maketab.c =================================================================== --- head/contrib/one-true-awk/maketab.c (revision 348510) +++ head/contrib/one-true-awk/maketab.c (revision 348511) @@ -1,168 +1,175 @@ /**************************************************************** Copyright (C) Lucent Technologies 1997 All Rights Reserved Permission to use, copy, modify, and distribute this software and its documentation for any purpose and without fee is hereby granted, provided that the above copyright notice appear in all copies and that both that the copyright notice and this permission notice and warranty disclaimer appear in supporting documentation, and that the name Lucent Technologies or any of its entities not be used in advertising or publicity pertaining to distribution of the software without specific, written prior permission. LUCENT DISCLAIMS ALL WARRANTIES WITH REGARD TO THIS SOFTWARE, INCLUDING ALL IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL LUCENT OR ANY OF ITS ENTITIES BE LIABLE FOR ANY SPECIAL, 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. ****************************************************************/ /* * this program makes the table to link function names * and type indices that is used by execute() in run.c. * it finds the indices in ytab.h, produced by yacc. */ #include #include #include #include "awk.h" #include "ytab.h" struct xx { int token; const char *name; const char *pname; } proc[] = { { PROGRAM, "program", NULL }, { BOR, "boolop", " || " }, { AND, "boolop", " && " }, { NOT, "boolop", " !" }, { NE, "relop", " != " }, { EQ, "relop", " == " }, { LE, "relop", " <= " }, { LT, "relop", " < " }, { GE, "relop", " >= " }, { GT, "relop", " > " }, { ARRAY, "array", NULL }, { INDIRECT, "indirect", "$(" }, { SUBSTR, "substr", "substr" }, { SUB, "sub", "sub" }, { GSUB, "gsub", "gsub" }, { INDEX, "sindex", "sindex" }, { SPRINTF, "awksprintf", "sprintf " }, { ADD, "arith", " + " }, { MINUS, "arith", " - " }, { MULT, "arith", " * " }, { DIVIDE, "arith", " / " }, { MOD, "arith", " % " }, { UMINUS, "arith", " -" }, + { UPLUS, "arith", " +" }, { POWER, "arith", " **" }, { PREINCR, "incrdecr", "++" }, { POSTINCR, "incrdecr", "++" }, { PREDECR, "incrdecr", "--" }, { POSTDECR, "incrdecr", "--" }, { CAT, "cat", " " }, { PASTAT, "pastat", NULL }, { PASTAT2, "dopa2", NULL }, { MATCH, "matchop", " ~ " }, { NOTMATCH, "matchop", " !~ " }, { MATCHFCN, "matchop", "matchop" }, { INTEST, "intest", "intest" }, { PRINTF, "awkprintf", "printf" }, { PRINT, "printstat", "print" }, { CLOSE, "closefile", "closefile" }, { DELETE, "awkdelete", "awkdelete" }, { SPLIT, "split", "split" }, { ASSIGN, "assign", " = " }, { ADDEQ, "assign", " += " }, { SUBEQ, "assign", " -= " }, { MULTEQ, "assign", " *= " }, { DIVEQ, "assign", " /= " }, { MODEQ, "assign", " %= " }, { POWEQ, "assign", " ^= " }, { CONDEXPR, "condexpr", " ?: " }, { IF, "ifstat", "if(" }, { WHILE, "whilestat", "while(" }, { FOR, "forstat", "for(" }, { DO, "dostat", "do" }, { IN, "instat", "instat" }, { NEXT, "jump", "next" }, { NEXTFILE, "jump", "nextfile" }, { EXIT, "jump", "exit" }, { BREAK, "jump", "break" }, { CONTINUE, "jump", "continue" }, { RETURN, "jump", "ret" }, { BLTIN, "bltin", "bltin" }, { CALL, "call", "call" }, { ARG, "arg", "arg" }, { VARNF, "getnf", "NF" }, { GETLINE, "awkgetline", "getline" }, { 0, "", "" }, }; #define SIZE (LASTTOKEN - FIRSTTOKEN + 1) const char *table[SIZE]; char *names[SIZE]; int main(int argc, char *argv[]) { const struct xx *p; int i, n, tok; char c; FILE *fp; char buf[200], name[200], def[200]; printf("#include \n"); printf("#include \"awk.h\"\n"); printf("#include \"ytab.h\"\n\n"); for (i = SIZE; --i >= 0; ) names[i] = ""; - if ((fp = fopen("ytab.h", "r")) == NULL) { - fprintf(stderr, "maketab can't open ytab.h!\n"); + if (argc != 2) { + fprintf(stderr, "usage: maketab YTAB_H\n"); exit(1); } + if ((fp = fopen(argv[1], "r")) == NULL) { + fprintf(stderr, "maketab can't open %s!\n", argv[1]); + exit(1); + } printf("static char *printname[%d] = {\n", SIZE); i = 0; while (fgets(buf, sizeof buf, fp) != NULL) { n = sscanf(buf, "%1c %s %s %d", &c, def, name, &tok); if (c != '#' || (n != 4 && strcmp(def,"define") != 0)) /* not a valid #define */ continue; + if (strcmp(name, "YYSTYPE_IS_DECLARED") == 0) + continue; if (tok < FIRSTTOKEN || tok > LASTTOKEN) { /* fprintf(stderr, "maketab funny token %d %s ignored\n", tok, buf); */ continue; } names[tok-FIRSTTOKEN] = (char *) malloc(strlen(name)+1); strcpy(names[tok-FIRSTTOKEN], name); printf("\t(char *) \"%s\",\t/* %d */\n", name, tok); i++; } printf("};\n\n"); for (p=proc; p->token!=0; p++) table[p->token-FIRSTTOKEN] = p->name; printf("\nCell *(*proctab[%d])(Node **, int) = {\n", SIZE); for (i=0; i LASTTOKEN) {\n"); printf(" sprintf(buf, \"token %%d\", n);\n"); printf(" return buf;\n"); printf(" }\n"); printf(" return printname[n-FIRSTTOKEN];\n"); printf("}\n"); return 0; } Index: head/contrib/one-true-awk/parse.c =================================================================== --- head/contrib/one-true-awk/parse.c (revision 348510) +++ head/contrib/one-true-awk/parse.c (revision 348511) @@ -1,276 +1,276 @@ /**************************************************************** Copyright (C) Lucent Technologies 1997 All Rights Reserved Permission to use, copy, modify, and distribute this software and its documentation for any purpose and without fee is hereby granted, provided that the above copyright notice appear in all copies and that both that the copyright notice and this permission notice and warranty disclaimer appear in supporting documentation, and that the name Lucent Technologies or any of its entities not be used in advertising or publicity pertaining to distribution of the software without specific, written prior permission. LUCENT DISCLAIMS ALL WARRANTIES WITH REGARD TO THIS SOFTWARE, INCLUDING ALL IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL LUCENT OR ANY OF ITS ENTITIES BE LIABLE FOR ANY SPECIAL, 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. ****************************************************************/ #define DEBUG #include #include #include #include "awk.h" #include "ytab.h" Node *nodealloc(int n) { Node *x; x = (Node *) malloc(sizeof(Node) + (n-1)*sizeof(Node *)); if (x == NULL) FATAL("out of space in nodealloc"); x->nnext = NULL; x->lineno = lineno; return(x); } Node *exptostat(Node *a) { a->ntype = NSTAT; return(a); } Node *node1(int a, Node *b) { Node *x; x = nodealloc(1); x->nobj = a; x->narg[0]=b; return(x); } Node *node2(int a, Node *b, Node *c) { Node *x; x = nodealloc(2); x->nobj = a; x->narg[0] = b; x->narg[1] = c; return(x); } Node *node3(int a, Node *b, Node *c, Node *d) { Node *x; x = nodealloc(3); x->nobj = a; x->narg[0] = b; x->narg[1] = c; x->narg[2] = d; return(x); } Node *node4(int a, Node *b, Node *c, Node *d, Node *e) { Node *x; x = nodealloc(4); x->nobj = a; x->narg[0] = b; x->narg[1] = c; x->narg[2] = d; x->narg[3] = e; return(x); } Node *stat1(int a, Node *b) { Node *x; x = node1(a,b); x->ntype = NSTAT; return(x); } Node *stat2(int a, Node *b, Node *c) { Node *x; x = node2(a,b,c); x->ntype = NSTAT; return(x); } Node *stat3(int a, Node *b, Node *c, Node *d) { Node *x; x = node3(a,b,c,d); x->ntype = NSTAT; return(x); } Node *stat4(int a, Node *b, Node *c, Node *d, Node *e) { Node *x; x = node4(a,b,c,d,e); x->ntype = NSTAT; return(x); } Node *op1(int a, Node *b) { Node *x; x = node1(a,b); x->ntype = NEXPR; return(x); } Node *op2(int a, Node *b, Node *c) { Node *x; x = node2(a,b,c); x->ntype = NEXPR; return(x); } Node *op3(int a, Node *b, Node *c, Node *d) { Node *x; x = node3(a,b,c,d); x->ntype = NEXPR; return(x); } Node *op4(int a, Node *b, Node *c, Node *d, Node *e) { Node *x; x = node4(a,b,c,d,e); x->ntype = NEXPR; return(x); } Node *celltonode(Cell *a, int b) { Node *x; a->ctype = OCELL; a->csub = b; x = node1(0, (Node *) a); x->ntype = NVALUE; return(x); } Node *rectonode(void) /* make $0 into a Node */ { extern Cell *literal0; return op1(INDIRECT, celltonode(literal0, CUNK)); } Node *makearr(Node *p) { Cell *cp; if (isvalue(p)) { cp = (Cell *) (p->narg[0]); if (isfcn(cp)) SYNTAX( "%s is a function, not an array", cp->nval ); else if (!isarr(cp)) { xfree(cp->sval); cp->sval = (char *) makesymtab(NSYMTAB); cp->tval = ARR; } } return p; } #define PA2NUM 50 /* max number of pat,pat patterns allowed */ int paircnt; /* number of them in use */ int pairstack[PA2NUM]; /* state of each pat,pat */ Node *pa2stat(Node *a, Node *b, Node *c) /* pat, pat {...} */ { Node *x; x = node4(PASTAT2, a, b, c, itonp(paircnt)); if (paircnt++ >= PA2NUM) SYNTAX( "limited to %d pat,pat statements", PA2NUM ); x->ntype = NSTAT; return(x); } Node *linkum(Node *a, Node *b) { Node *c; if (errorflag) /* don't link things that are wrong */ return a; if (a == NULL) return(b); else if (b == NULL) return(a); for (c = a; c->nnext != NULL; c = c->nnext) ; c->nnext = b; return(a); } void defn(Cell *v, Node *vl, Node *st) /* turn on FCN bit in definition, */ { /* body of function, arglist */ Node *p; int n; if (isarr(v)) { SYNTAX( "`%s' is an array name and a function name", v->nval ); return; } if (isarg(v->nval) != -1) { SYNTAX( "`%s' is both function name and argument name", v->nval ); return; } v->tval = FCN; v->sval = (char *) st; n = 0; /* count arguments */ for (p = vl; p; p = p->nnext) n++; v->fval = n; dprintf( ("defining func %s (%d args)\n", v->nval, n) ); } int isarg(const char *s) /* is s in argument list for current function? */ { /* return -1 if not, otherwise arg # */ extern Node *arglist; Node *p = arglist; int n; - for (n = 0; p != NULL; p = p->nnext, n++) + for (n = 0; p != 0; p = p->nnext, n++) if (strcmp(((Cell *)(p->narg[0]))->nval, s) == 0) return n; return -1; } int ptoi(void *p) /* convert pointer to integer */ { return (int) (long) p; /* swearing that p fits, of course */ } Node *itonp(int i) /* and vice versa */ { return (Node *) (long) i; } Index: head/contrib/one-true-awk/proctab.c =================================================================== --- head/contrib/one-true-awk/proctab.c (nonexistent) +++ head/contrib/one-true-awk/proctab.c (revision 348511) @@ -0,0 +1,209 @@ +#include +#include "awk.h" +#include "ytab.h" + +static char *printname[94] = { + (char *) "FIRSTTOKEN", /* 258 */ + (char *) "PROGRAM", /* 259 */ + (char *) "PASTAT", /* 260 */ + (char *) "PASTAT2", /* 261 */ + (char *) "XBEGIN", /* 262 */ + (char *) "XEND", /* 263 */ + (char *) "NL", /* 264 */ + (char *) "ARRAY", /* 265 */ + (char *) "MATCH", /* 266 */ + (char *) "NOTMATCH", /* 267 */ + (char *) "MATCHOP", /* 268 */ + (char *) "FINAL", /* 269 */ + (char *) "DOT", /* 270 */ + (char *) "ALL", /* 271 */ + (char *) "CCL", /* 272 */ + (char *) "NCCL", /* 273 */ + (char *) "CHAR", /* 274 */ + (char *) "OR", /* 275 */ + (char *) "STAR", /* 276 */ + (char *) "QUEST", /* 277 */ + (char *) "PLUS", /* 278 */ + (char *) "EMPTYRE", /* 279 */ + (char *) "AND", /* 280 */ + (char *) "BOR", /* 281 */ + (char *) "APPEND", /* 282 */ + (char *) "EQ", /* 283 */ + (char *) "GE", /* 284 */ + (char *) "GT", /* 285 */ + (char *) "LE", /* 286 */ + (char *) "LT", /* 287 */ + (char *) "NE", /* 288 */ + (char *) "IN", /* 289 */ + (char *) "ARG", /* 290 */ + (char *) "BLTIN", /* 291 */ + (char *) "BREAK", /* 292 */ + (char *) "CLOSE", /* 293 */ + (char *) "CONTINUE", /* 294 */ + (char *) "DELETE", /* 295 */ + (char *) "DO", /* 296 */ + (char *) "EXIT", /* 297 */ + (char *) "FOR", /* 298 */ + (char *) "FUNC", /* 299 */ + (char *) "SUB", /* 300 */ + (char *) "GSUB", /* 301 */ + (char *) "IF", /* 302 */ + (char *) "INDEX", /* 303 */ + (char *) "LSUBSTR", /* 304 */ + (char *) "MATCHFCN", /* 305 */ + (char *) "NEXT", /* 306 */ + (char *) "NEXTFILE", /* 307 */ + (char *) "ADD", /* 308 */ + (char *) "MINUS", /* 309 */ + (char *) "MULT", /* 310 */ + (char *) "DIVIDE", /* 311 */ + (char *) "MOD", /* 312 */ + (char *) "ASSIGN", /* 313 */ + (char *) "ASGNOP", /* 314 */ + (char *) "ADDEQ", /* 315 */ + (char *) "SUBEQ", /* 316 */ + (char *) "MULTEQ", /* 317 */ + (char *) "DIVEQ", /* 318 */ + (char *) "MODEQ", /* 319 */ + (char *) "POWEQ", /* 320 */ + (char *) "PRINT", /* 321 */ + (char *) "PRINTF", /* 322 */ + (char *) "SPRINTF", /* 323 */ + (char *) "ELSE", /* 324 */ + (char *) "INTEST", /* 325 */ + (char *) "CONDEXPR", /* 326 */ + (char *) "POSTINCR", /* 327 */ + (char *) "PREINCR", /* 328 */ + (char *) "POSTDECR", /* 329 */ + (char *) "PREDECR", /* 330 */ + (char *) "VAR", /* 331 */ + (char *) "IVAR", /* 332 */ + (char *) "VARNF", /* 333 */ + (char *) "CALL", /* 334 */ + (char *) "NUMBER", /* 335 */ + (char *) "STRING", /* 336 */ + (char *) "REGEXPR", /* 337 */ + (char *) "GETLINE", /* 338 */ + (char *) "RETURN", /* 339 */ + (char *) "SPLIT", /* 340 */ + (char *) "SUBSTR", /* 341 */ + (char *) "WHILE", /* 342 */ + (char *) "CAT", /* 343 */ + (char *) "NOT", /* 344 */ + (char *) "UMINUS", /* 345 */ + (char *) "UPLUS", /* 346 */ + (char *) "POWER", /* 347 */ + (char *) "DECR", /* 348 */ + (char *) "INCR", /* 349 */ + (char *) "INDIRECT", /* 350 */ + (char *) "LASTTOKEN", /* 351 */ +}; + + +Cell *(*proctab[94])(Node **, int) = { + nullproc, /* FIRSTTOKEN */ + program, /* PROGRAM */ + pastat, /* PASTAT */ + dopa2, /* PASTAT2 */ + nullproc, /* XBEGIN */ + nullproc, /* XEND */ + nullproc, /* NL */ + array, /* ARRAY */ + matchop, /* MATCH */ + matchop, /* NOTMATCH */ + nullproc, /* MATCHOP */ + nullproc, /* FINAL */ + nullproc, /* DOT */ + nullproc, /* ALL */ + nullproc, /* CCL */ + nullproc, /* NCCL */ + nullproc, /* CHAR */ + nullproc, /* OR */ + nullproc, /* STAR */ + nullproc, /* QUEST */ + nullproc, /* PLUS */ + nullproc, /* EMPTYRE */ + boolop, /* AND */ + boolop, /* BOR */ + nullproc, /* APPEND */ + relop, /* EQ */ + relop, /* GE */ + relop, /* GT */ + relop, /* LE */ + relop, /* LT */ + relop, /* NE */ + instat, /* IN */ + arg, /* ARG */ + bltin, /* BLTIN */ + jump, /* BREAK */ + closefile, /* CLOSE */ + jump, /* CONTINUE */ + awkdelete, /* DELETE */ + dostat, /* DO */ + jump, /* EXIT */ + forstat, /* FOR */ + nullproc, /* FUNC */ + sub, /* SUB */ + gsub, /* GSUB */ + ifstat, /* IF */ + sindex, /* INDEX */ + nullproc, /* LSUBSTR */ + matchop, /* MATCHFCN */ + jump, /* NEXT */ + jump, /* NEXTFILE */ + arith, /* ADD */ + arith, /* MINUS */ + arith, /* MULT */ + arith, /* DIVIDE */ + arith, /* MOD */ + assign, /* ASSIGN */ + nullproc, /* ASGNOP */ + assign, /* ADDEQ */ + assign, /* SUBEQ */ + assign, /* MULTEQ */ + assign, /* DIVEQ */ + assign, /* MODEQ */ + assign, /* POWEQ */ + printstat, /* PRINT */ + awkprintf, /* PRINTF */ + awksprintf, /* SPRINTF */ + nullproc, /* ELSE */ + intest, /* INTEST */ + condexpr, /* CONDEXPR */ + incrdecr, /* POSTINCR */ + incrdecr, /* PREINCR */ + incrdecr, /* POSTDECR */ + incrdecr, /* PREDECR */ + nullproc, /* VAR */ + nullproc, /* IVAR */ + getnf, /* VARNF */ + call, /* CALL */ + nullproc, /* NUMBER */ + nullproc, /* STRING */ + nullproc, /* REGEXPR */ + awkgetline, /* GETLINE */ + jump, /* RETURN */ + split, /* SPLIT */ + substr, /* SUBSTR */ + whilestat, /* WHILE */ + cat, /* CAT */ + boolop, /* NOT */ + arith, /* UMINUS */ + arith, /* UPLUS */ + arith, /* POWER */ + nullproc, /* DECR */ + nullproc, /* INCR */ + indirect, /* INDIRECT */ + nullproc, /* LASTTOKEN */ +}; + +char *tokname(int n) +{ + static char buf[100]; + + if (n < FIRSTTOKEN || n > LASTTOKEN) { + sprintf(buf, "token %d", n); + return buf; + } + return printname[n-FIRSTTOKEN]; +} Property changes on: head/contrib/one-true-awk/proctab.c ___________________________________________________________________ Added: svn:eol-style ## -0,0 +1 ## +native \ No newline at end of property Added: svn:keywords ## -0,0 +1 ## +FreeBSD=%H \ No newline at end of property Added: svn:mime-type ## -0,0 +1 ## +text/plain \ No newline at end of property Index: head/contrib/one-true-awk/proto.h =================================================================== --- head/contrib/one-true-awk/proto.h (revision 348510) +++ head/contrib/one-true-awk/proto.h (revision 348511) @@ -1,195 +1,198 @@ /**************************************************************** Copyright (C) Lucent Technologies 1997 All Rights Reserved Permission to use, copy, modify, and distribute this software and its documentation for any purpose and without fee is hereby granted, provided that the above copyright notice appear in all copies and that both that the copyright notice and this permission notice and warranty disclaimer appear in supporting documentation, and that the name Lucent Technologies or any of its entities not be used in advertising or publicity pertaining to distribution of the software without specific, written prior permission. LUCENT DISCLAIMS ALL WARRANTIES WITH REGARD TO THIS SOFTWARE, INCLUDING ALL IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL LUCENT OR ANY OF ITS ENTITIES BE LIABLE FOR ANY SPECIAL, 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. ****************************************************************/ extern int yywrap(void); extern void setfname(Cell *); extern int constnode(Node *); extern char *strnode(Node *); extern Node *notnull(Node *); extern int yyparse(void); extern int yylex(void); extern void startreg(void); extern int input(void); extern void unput(int); extern void unputstr(const char *); extern int yylook(void); extern int yyback(int *, int); extern int yyinput(void); extern fa *makedfa(const char *, int); extern fa *mkdfa(const char *, int); extern int makeinit(fa *, int); extern void penter(Node *); extern void freetr(Node *); extern int hexstr(uschar **); extern int quoted(uschar **); extern char *cclenter(const char *); extern void overflo(const char *) __attribute__((__noreturn__)); extern void cfoll(fa *, Node *); extern int first(Node *); extern void follow(Node *); extern int member(int, const char *); extern int match(fa *, const char *); extern int pmatch(fa *, const char *); extern int nematch(fa *, const char *); extern Node *reparse(const char *); extern Node *regexp(void); extern Node *primary(void); extern Node *concat(Node *); extern Node *alt(Node *); extern Node *unary(Node *); extern int relex(void); extern int cgoto(fa *, int, int); extern void freefa(fa *); extern int pgetc(void); extern char *cursource(void); extern Node *nodealloc(int); extern Node *exptostat(Node *); extern Node *node1(int, Node *); extern Node *node2(int, Node *, Node *); extern Node *node3(int, Node *, Node *, Node *); extern Node *node4(int, Node *, Node *, Node *, Node *); extern Node *stat3(int, Node *, Node *, Node *); extern Node *op2(int, Node *, Node *); extern Node *op1(int, Node *); extern Node *stat1(int, Node *); extern Node *op3(int, Node *, Node *, Node *); extern Node *op4(int, Node *, Node *, Node *, Node *); extern Node *stat2(int, Node *, Node *); extern Node *stat4(int, Node *, Node *, Node *, Node *); extern Node *celltonode(Cell *, int); extern Node *rectonode(void); extern Node *makearr(Node *); extern Node *pa2stat(Node *, Node *, Node *); extern Node *linkum(Node *, Node *); extern void defn(Cell *, Node *, Node *); extern int isarg(const char *); extern char *tokname(int); extern Cell *(*proctab[])(Node **, int); extern int ptoi(void *); extern Node *itonp(int); extern void syminit(void); extern void arginit(int, char **); extern void envinit(char **); extern Array *makesymtab(int); extern void freesymtab(Cell *); extern void freeelem(Cell *, const char *); extern Cell *setsymtab(const char *, const char *, double, unsigned int, Array *); extern int hash(const char *, int); extern void rehash(Array *); extern Cell *lookup(const char *, Array *); extern double setfval(Cell *, double); extern void funnyvar(Cell *, const char *); extern char *setsval(Cell *, const char *); extern double getfval(Cell *); extern char *getsval(Cell *); extern char *getpssval(Cell *); /* for print */ extern char *tostring(const char *); extern char *qstring(const char *, int); extern void recinit(unsigned int); extern void initgetrec(void); extern void makefields(int, int); extern void growfldtab(int n); extern int getrec(char **, int *, int); extern void nextfile(void); extern int readrec(char **buf, int *bufsize, FILE *inf); extern char *getargv(int); extern void setclvar(char *); extern void fldbld(void); extern void cleanfld(int, int); extern void newfld(int); +extern void setlastfld(int); extern int refldbld(const char *, const char *); extern void recbld(void); extern Cell *fieldadr(int); extern void yyerror(const char *); extern void fpecatch(int); extern void bracecheck(void); extern void bcheck2(int, int, int); extern void SYNTAX(const char *, ...); extern void FATAL(const char *, ...) __attribute__((__noreturn__)); extern void WARNING(const char *, ...); extern void error(void); extern void eprint(void); extern void bclass(int); extern double errcheck(double, const char *); extern int isclvar(const char *); extern int is_number(const char *); extern int adjbuf(char **pb, int *sz, int min, int q, char **pbp, const char *what); extern void run(Node *); extern Cell *execute(Node *); extern Cell *program(Node **, int); extern Cell *call(Node **, int); extern Cell *copycell(Cell *); extern Cell *arg(Node **, int); extern Cell *jump(Node **, int); extern Cell *awkgetline(Node **, int); extern Cell *getnf(Node **, int); extern Cell *array(Node **, int); extern Cell *awkdelete(Node **, int); extern Cell *intest(Node **, int); extern Cell *matchop(Node **, int); extern Cell *boolop(Node **, int); extern Cell *relop(Node **, int); extern void tfree(Cell *); extern Cell *gettemp(void); extern Cell *field(Node **, int); extern Cell *indirect(Node **, int); extern Cell *substr(Node **, int); extern Cell *sindex(Node **, int); extern int format(char **, int *, const char *, Node *); extern Cell *awksprintf(Node **, int); extern Cell *awkprintf(Node **, int); extern Cell *arith(Node **, int); extern double ipow(double, int); extern Cell *incrdecr(Node **, int); extern Cell *assign(Node **, int); extern Cell *cat(Node **, int); extern Cell *pastat(Node **, int); extern Cell *dopa2(Node **, int); extern Cell *split(Node **, int); extern Cell *condexpr(Node **, int); extern Cell *ifstat(Node **, int); extern Cell *whilestat(Node **, int); extern Cell *dostat(Node **, int); extern Cell *forstat(Node **, int); extern Cell *instat(Node **, int); extern Cell *bltin(Node **, int); extern Cell *printstat(Node **, int); extern Cell *nullproc(Node **, int); extern FILE *redirect(int, Node *); extern FILE *openfile(int, const char *); extern const char *filename(FILE *); extern Cell *closefile(Node **, int); extern void closeall(void); extern Cell *sub(Node **, int); extern Cell *gsub(Node **, int); extern FILE *popen(const char *, const char *); extern int pclose(FILE *); + +extern const char *flags2str(int flags); Index: head/contrib/one-true-awk/run.c =================================================================== --- head/contrib/one-true-awk/run.c (revision 348510) +++ head/contrib/one-true-awk/run.c (revision 348511) @@ -1,2033 +1,2088 @@ /**************************************************************** Copyright (C) Lucent Technologies 1997 All Rights Reserved Permission to use, copy, modify, and distribute this software and its documentation for any purpose and without fee is hereby granted, provided that the above copyright notice appear in all copies and that both that the copyright notice and this permission notice and warranty disclaimer appear in supporting documentation, and that the name Lucent Technologies or any of its entities not be used in advertising or publicity pertaining to distribution of the software without specific, written prior permission. LUCENT DISCLAIMS ALL WARRANTIES WITH REGARD TO THIS SOFTWARE, INCLUDING ALL IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL LUCENT OR ANY OF ITS ENTITIES BE LIABLE FOR ANY SPECIAL, 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. ****************************************************************/ #include __FBSDID("$FreeBSD$"); #define DEBUG #include #include #include #include #include #include #include #include +#include +#include #include "awk.h" #include "ytab.h" #define tempfree(x) if (istemp(x)) tfree(x); else /* #undef tempfree void tempfree(Cell *p) { if (p->ctype == OCELL && (p->csub < CUNK || p->csub > CFREE)) { WARNING("bad csub %d in Cell %d %s", p->csub, p->ctype, p->sval); } if (istemp(p)) tfree(p); } */ /* do we really need these? */ /* #ifdef _NFILE */ /* #ifndef FOPEN_MAX */ /* #define FOPEN_MAX _NFILE */ /* #endif */ /* #endif */ /* */ /* #ifndef FOPEN_MAX */ /* #define FOPEN_MAX 40 */ /* max number of open files */ /* #endif */ /* */ /* #ifndef RAND_MAX */ /* #define RAND_MAX 32767 */ /* all that ansi guarantees */ /* #endif */ jmp_buf env; extern int pairstack[]; extern Awkfloat srand_seed; Node *winner = NULL; /* root of parse tree */ Cell *tmps; /* free temporary cells for execution */ -static Cell truecell ={ OBOOL, BTRUE, 0, 0, 1.0, NUM }; +static Cell truecell ={ OBOOL, BTRUE, 0, 0, 1.0, NUM, NULL }; Cell *True = &truecell; -static Cell falsecell ={ OBOOL, BFALSE, 0, 0, 0.0, NUM }; +static Cell falsecell ={ OBOOL, BFALSE, 0, 0, 0.0, NUM, NULL }; Cell *False = &falsecell; -static Cell breakcell ={ OJUMP, JBREAK, 0, 0, 0.0, NUM }; +static Cell breakcell ={ OJUMP, JBREAK, 0, 0, 0.0, NUM, NULL }; Cell *jbreak = &breakcell; -static Cell contcell ={ OJUMP, JCONT, 0, 0, 0.0, NUM }; +static Cell contcell ={ OJUMP, JCONT, 0, 0, 0.0, NUM, NULL }; Cell *jcont = &contcell; -static Cell nextcell ={ OJUMP, JNEXT, 0, 0, 0.0, NUM }; +static Cell nextcell ={ OJUMP, JNEXT, 0, 0, 0.0, NUM, NULL }; Cell *jnext = &nextcell; -static Cell nextfilecell ={ OJUMP, JNEXTFILE, 0, 0, 0.0, NUM }; +static Cell nextfilecell ={ OJUMP, JNEXTFILE, 0, 0, 0.0, NUM, NULL }; Cell *jnextfile = &nextfilecell; -static Cell exitcell ={ OJUMP, JEXIT, 0, 0, 0.0, NUM }; +static Cell exitcell ={ OJUMP, JEXIT, 0, 0, 0.0, NUM, NULL }; Cell *jexit = &exitcell; -static Cell retcell ={ OJUMP, JRET, 0, 0, 0.0, NUM }; +static Cell retcell ={ OJUMP, JRET, 0, 0, 0.0, NUM, NULL }; Cell *jret = &retcell; -static Cell tempcell ={ OCELL, CTEMP, 0, "", 0.0, NUM|STR|DONTFREE }; +static Cell tempcell ={ OCELL, CTEMP, 0, "", 0.0, NUM|STR|DONTFREE, NULL }; Node *curnode = NULL; /* the node being executed, for debugging */ /* buffer memory management */ int adjbuf(char **pbuf, int *psiz, int minlen, int quantum, char **pbptr, const char *whatrtn) /* pbuf: address of pointer to buffer being managed * psiz: address of buffer size variable * minlen: minimum length of buffer needed * quantum: buffer size quantum * pbptr: address of movable pointer into buffer, or 0 if none * whatrtn: name of the calling routine if failure should cause fatal error * * return 0 for realloc failure, !=0 for success */ { if (minlen > *psiz) { char *tbuf; int rminlen = quantum ? minlen % quantum : 0; int boff = pbptr ? *pbptr - *pbuf : 0; /* round up to next multiple of quantum */ if (rminlen) minlen += quantum - rminlen; tbuf = (char *) realloc(*pbuf, minlen); - dprintf( ("adjbuf %s: %d %d (pbuf=%p, tbuf=%p)\n", whatrtn, *psiz, minlen, *pbuf, tbuf) ); + dprintf( ("adjbuf %s: %d %d (pbuf=%p, tbuf=%p)\n", whatrtn, *psiz, minlen, (void *) *pbuf, (void *) tbuf) ); if (tbuf == NULL) { if (whatrtn) FATAL("out of memory in %s", whatrtn); return 0; } *pbuf = tbuf; *psiz = minlen; if (pbptr) *pbptr = tbuf + boff; } return 1; } void run(Node *a) /* execution of parse tree starts here */ { extern void stdinit(void); stdinit(); execute(a); closeall(); } Cell *execute(Node *u) /* execute a node of the parse tree */ { Cell *(*proc)(Node **, int); Cell *x; Node *a; if (u == NULL) return(True); for (a = u; ; a = a->nnext) { curnode = a; if (isvalue(a)) { x = (Cell *) (a->narg[0]); if (isfld(x) && !donefld) fldbld(); else if (isrec(x) && !donerec) recbld(); return(x); } if (notlegal(a->nobj)) /* probably a Cell* but too risky to print */ FATAL("illegal statement"); proc = proctab[a->nobj-FIRSTTOKEN]; x = (*proc)(a->narg, a->nobj); if (isfld(x) && !donefld) fldbld(); else if (isrec(x) && !donerec) recbld(); if (isexpr(a)) return(x); if (isjump(x)) return(x); if (a->nnext == NULL) return(x); tempfree(x); } } Cell *program(Node **a, int n) /* execute an awk program */ { /* a[0] = BEGIN, a[1] = body, a[2] = END */ Cell *x; if (setjmp(env) != 0) goto ex; if (a[0]) { /* BEGIN */ x = execute(a[0]); if (isexit(x)) return(True); if (isjump(x)) FATAL("illegal break, continue, next or nextfile from BEGIN"); tempfree(x); } if (a[1] || a[2]) while (getrec(&record, &recsize, 1) > 0) { x = execute(a[1]); if (isexit(x)) break; tempfree(x); } ex: if (setjmp(env) != 0) /* handles exit within END */ goto ex1; if (a[2]) { /* END */ x = execute(a[2]); if (isbreak(x) || isnext(x) || iscont(x)) FATAL("illegal break, continue, next or nextfile from END"); tempfree(x); } ex1: return(True); } struct Frame { /* stack frame for awk function calls */ int nargs; /* number of arguments in this call */ Cell *fcncell; /* pointer to Cell for function */ Cell **args; /* pointer to array of arguments after execute */ Cell *retval; /* return value */ }; #define NARGS 50 /* max args in a call */ struct Frame *frame = NULL; /* base of stack frames; dynamically allocated */ int nframe = 0; /* number of frames allocated */ struct Frame *fp = NULL; /* frame pointer. bottom level unused */ Cell *call(Node **a, int n) /* function call. very kludgy and fragile */ { - static Cell newcopycell = { OCELL, CCOPY, 0, "", 0.0, NUM|STR|DONTFREE }; + static Cell newcopycell = { OCELL, CCOPY, 0, "", 0.0, NUM|STR|DONTFREE, NULL }; int i, ncall, ndef; int freed = 0; /* handles potential double freeing when fcn & param share a tempcell */ Node *x; Cell *args[NARGS], *oargs[NARGS]; /* BUG: fixed size arrays */ Cell *y, *z, *fcn; char *s; fcn = execute(a[0]); /* the function itself */ s = fcn->nval; if (!isfcn(fcn)) FATAL("calling undefined function %s", s); if (frame == NULL) { fp = frame = (struct Frame *) calloc(nframe += 100, sizeof(struct Frame)); if (frame == NULL) FATAL("out of space for stack frames calling %s", s); } for (ncall = 0, x = a[1]; x != NULL; x = x->nnext) /* args in call */ ncall++; ndef = (int) fcn->fval; /* args in defn */ dprintf( ("calling %s, %d args (%d in defn), fp=%d\n", s, ncall, ndef, (int) (fp-frame)) ); if (ncall > ndef) WARNING("function %s called with %d args, uses only %d", s, ncall, ndef); if (ncall + ndef > NARGS) FATAL("function %s has %d arguments, limit %d", s, ncall+ndef, NARGS); for (i = 0, x = a[1]; x != NULL; i++, x = x->nnext) { /* get call args */ dprintf( ("evaluate args[%d], fp=%d:\n", i, (int) (fp-frame)) ); y = execute(x); oargs[i] = y; dprintf( ("args[%d]: %s %f <%s>, t=%o\n", i, NN(y->nval), y->fval, isarr(y) ? "(array)" : NN(y->sval), y->tval) ); if (isfcn(y)) FATAL("can't use function %s as argument in %s", y->nval, s); if (isarr(y)) args[i] = y; /* arrays by ref */ else args[i] = copycell(y); tempfree(y); } for ( ; i < ndef; i++) { /* add null args for ones not provided */ args[i] = gettemp(); *args[i] = newcopycell; } fp++; /* now ok to up frame */ if (fp >= frame + nframe) { int dfp = fp - frame; /* old index */ frame = (struct Frame *) realloc((char *) frame, (nframe += 100) * sizeof(struct Frame)); if (frame == NULL) FATAL("out of space for stack frames in %s", s); fp = frame + dfp; } fp->fcncell = fcn; fp->args = args; fp->nargs = ndef; /* number defined with (excess are locals) */ fp->retval = gettemp(); dprintf( ("start exec of %s, fp=%d\n", s, (int) (fp-frame)) ); y = execute((Node *)(fcn->sval)); /* execute body */ dprintf( ("finished exec of %s, fp=%d\n", s, (int) (fp-frame)) ); for (i = 0; i < ndef; i++) { Cell *t = fp->args[i]; if (isarr(t)) { if (t->csub == CCOPY) { if (i >= ncall) { freesymtab(t); t->csub = CTEMP; tempfree(t); } else { oargs[i]->tval = t->tval; oargs[i]->tval &= ~(STR|NUM|DONTFREE); oargs[i]->sval = t->sval; tempfree(t); } } } else if (t != y) { /* kludge to prevent freeing twice */ t->csub = CTEMP; tempfree(t); } else if (t == y && t->csub == CCOPY) { t->csub = CTEMP; tempfree(t); freed = 1; } } tempfree(fcn); if (isexit(y) || isnext(y)) return y; if (freed == 0) { tempfree(y); /* don't free twice! */ } z = fp->retval; /* return value */ dprintf( ("%s returns %g |%s| %o\n", s, getfval(z), getsval(z), z->tval) ); fp--; return(z); } Cell *copycell(Cell *x) /* make a copy of a cell in a temp */ { Cell *y; + /* copy is not constant or field */ + y = gettemp(); + y->tval = x->tval & ~(CON|FLD|REC); y->csub = CCOPY; /* prevents freeing until call is over */ y->nval = x->nval; /* BUG? */ - if (isstr(x)) + if (isstr(x) /* || x->ctype == OCELL */) { y->sval = tostring(x->sval); + y->tval &= ~DONTFREE; + } else + y->tval |= DONTFREE; y->fval = x->fval; - y->tval = x->tval & ~(CON|FLD|REC|DONTFREE); /* copy is not constant or field */ - /* is DONTFREE right? */ return y; } Cell *arg(Node **a, int n) /* nth argument of a function */ { n = ptoi(a[0]); /* argument number, counting from 0 */ dprintf( ("arg(%d), fp->nargs=%d\n", n, fp->nargs) ); if (n+1 > fp->nargs) FATAL("argument #%d of function %s was not supplied", n+1, fp->fcncell->nval); return fp->args[n]; } Cell *jump(Node **a, int n) /* break, continue, next, nextfile, return */ { Cell *y; switch (n) { case EXIT: if (a[0] != NULL) { y = execute(a[0]); errorflag = (int) getfval(y); tempfree(y); } longjmp(env, 1); case RETURN: if (a[0] != NULL) { y = execute(a[0]); if ((y->tval & (STR|NUM)) == (STR|NUM)) { setsval(fp->retval, getsval(y)); fp->retval->fval = getfval(y); fp->retval->tval |= NUM; } else if (y->tval & STR) setsval(fp->retval, getsval(y)); else if (y->tval & NUM) setfval(fp->retval, getfval(y)); else /* can't happen */ FATAL("bad type variable %d", y->tval); tempfree(y); } return(jret); case NEXT: return(jnext); case NEXTFILE: nextfile(); return(jnextfile); case BREAK: return(jbreak); case CONTINUE: return(jcont); default: /* can't happen */ FATAL("illegal jump type %d", n); } return 0; /* not reached */ } Cell *awkgetline(Node **a, int n) /* get next line from specific input */ { /* a[0] is variable, a[1] is operator, a[2] is filename */ Cell *r, *x; extern Cell **fldtab; FILE *fp; char *buf; int bufsize = recsize; int mode; if ((buf = (char *) malloc(bufsize)) == NULL) FATAL("out of memory in getline"); fflush(stdout); /* in case someone is waiting for a prompt */ r = gettemp(); if (a[1] != NULL) { /* getline < file */ x = execute(a[2]); /* filename */ mode = ptoi(a[1]); if (mode == '|') /* input pipe */ mode = LE; /* arbitrary flag */ fp = openfile(mode, getsval(x)); tempfree(x); if (fp == NULL) n = -1; else n = readrec(&buf, &bufsize, fp); if (n <= 0) { ; } else if (a[0] != NULL) { /* getline var sval)) { + x->fval = atof(x->sval); + x->tval |= NUM; + } tempfree(x); } else { /* getline sval)) { fldtab[0]->fval = atof(fldtab[0]->sval); fldtab[0]->tval |= NUM; } } } else { /* bare getline; use current input */ if (a[0] == NULL) /* getline */ n = getrec(&record, &recsize, 1); else { /* getline var */ n = getrec(&buf, &bufsize, 0); x = execute(a[0]); setsval(x, buf); + if (is_number(x->sval)) { + x->fval = atof(x->sval); + x->tval |= NUM; + } tempfree(x); } } setfval(r, (Awkfloat) n); free(buf); return r; } Cell *getnf(Node **a, int n) /* get NF */ { if (donefld == 0) fldbld(); return (Cell *) a[0]; } Cell *array(Node **a, int n) /* a[0] is symtab, a[1] is list of subscripts */ { Cell *x, *y, *z; char *s; Node *np; char *buf; int bufsz = recsize; - int nsub = strlen(*SUBSEP); + int nsub; if ((buf = (char *) malloc(bufsz)) == NULL) FATAL("out of memory in array"); x = execute(a[0]); /* Cell* for symbol table */ buf[0] = 0; for (np = a[1]; np; np = np->nnext) { y = execute(np); /* subscript */ s = getsval(y); + nsub = strlen(getsval(subseploc)); if (!adjbuf(&buf, &bufsz, strlen(buf)+strlen(s)+nsub+1, recsize, 0, "array")) FATAL("out of memory for %s[%s...]", x->nval, buf); strcat(buf, s); if (np->nnext) strcat(buf, *SUBSEP); tempfree(y); } if (!isarr(x)) { dprintf( ("making %s into an array\n", NN(x->nval)) ); if (freeable(x)) xfree(x->sval); x->tval &= ~(STR|NUM|DONTFREE); x->tval |= ARR; x->sval = (char *) makesymtab(NSYMTAB); } z = setsymtab(buf, "", 0.0, STR|NUM, (Array *) x->sval); z->ctype = OCELL; z->csub = CVAR; tempfree(x); free(buf); return(z); } Cell *awkdelete(Node **a, int n) /* a[0] is symtab, a[1] is list of subscripts */ { Cell *x, *y; Node *np; char *s; - int nsub = strlen(*SUBSEP); + int nsub; x = execute(a[0]); /* Cell* for symbol table */ if (!isarr(x)) return True; - if (a[1] == NULL) { /* delete the elements, not the table */ + if (a[1] == 0) { /* delete the elements, not the table */ freesymtab(x); x->tval &= ~STR; x->tval |= ARR; x->sval = (char *) makesymtab(NSYMTAB); } else { int bufsz = recsize; char *buf; if ((buf = (char *) malloc(bufsz)) == NULL) FATAL("out of memory in adelete"); buf[0] = 0; for (np = a[1]; np; np = np->nnext) { y = execute(np); /* subscript */ s = getsval(y); + nsub = strlen(getsval(subseploc)); if (!adjbuf(&buf, &bufsz, strlen(buf)+strlen(s)+nsub+1, recsize, 0, "awkdelete")) FATAL("out of memory deleting %s[%s...]", x->nval, buf); - strcat(buf, s); + strcat(buf, s); if (np->nnext) strcat(buf, *SUBSEP); tempfree(y); } freeelem(x, buf); free(buf); } tempfree(x); return True; } Cell *intest(Node **a, int n) /* a[0] is index (list), a[1] is symtab */ { Cell *x, *ap, *k; Node *p; char *buf; char *s; int bufsz = recsize; - int nsub = strlen(*SUBSEP); + int nsub; ap = execute(a[1]); /* array name */ if (!isarr(ap)) { dprintf( ("making %s into an array\n", ap->nval) ); if (freeable(ap)) xfree(ap->sval); ap->tval &= ~(STR|NUM|DONTFREE); ap->tval |= ARR; ap->sval = (char *) makesymtab(NSYMTAB); } if ((buf = (char *) malloc(bufsz)) == NULL) { FATAL("out of memory in intest"); } buf[0] = 0; for (p = a[0]; p; p = p->nnext) { x = execute(p); /* expr */ s = getsval(x); + nsub = strlen(getsval(subseploc)); if (!adjbuf(&buf, &bufsz, strlen(buf)+strlen(s)+nsub+1, recsize, 0, "intest")) FATAL("out of memory deleting %s[%s...]", x->nval, buf); strcat(buf, s); tempfree(x); if (p->nnext) strcat(buf, *SUBSEP); } k = lookup(buf, (Array *) ap->sval); tempfree(ap); free(buf); if (k == NULL) return(False); else return(True); } Cell *matchop(Node **a, int n) /* ~ and match() */ { Cell *x, *y; char *s, *t; int i; fa *pfa; int (*mf)(fa *, const char *) = match, mode = 0; if (n == MATCHFCN) { mf = pmatch; mode = 1; } x = execute(a[1]); /* a[1] = target text */ s = getsval(x); - if (a[0] == NULL) /* a[1] == 0: already-compiled reg expr */ + if (a[0] == 0) /* a[1] == 0: already-compiled reg expr */ i = (*mf)((fa *) a[2], s); else { y = execute(a[2]); /* a[2] = regular expr */ t = getsval(y); pfa = makedfa(t, mode); i = (*mf)(pfa, s); tempfree(y); } tempfree(x); if (n == MATCHFCN) { int start = patbeg - s + 1; if (patlen < 0) start = 0; setfval(rstartloc, (Awkfloat) start); setfval(rlengthloc, (Awkfloat) patlen); x = gettemp(); x->tval = NUM; x->fval = start; return x; } else if ((n == MATCH && i == 1) || (n == NOTMATCH && i == 0)) return(True); else return(False); } Cell *boolop(Node **a, int n) /* a[0] || a[1], a[0] && a[1], !a[0] */ { Cell *x, *y; int i; x = execute(a[0]); i = istrue(x); tempfree(x); switch (n) { case BOR: if (i) return(True); y = execute(a[1]); i = istrue(y); tempfree(y); if (i) return(True); else return(False); case AND: if ( !i ) return(False); y = execute(a[1]); i = istrue(y); tempfree(y); if (i) return(True); else return(False); case NOT: if (i) return(False); else return(True); default: /* can't happen */ FATAL("unknown boolean operator %d", n); } return 0; /*NOTREACHED*/ } Cell *relop(Node **a, int n) /* a[0 < a[1], etc. */ { int i; Cell *x, *y; Awkfloat j; x = execute(a[0]); y = execute(a[1]); if (x->tval&NUM && y->tval&NUM) { j = x->fval - y->fval; i = j<0? -1: (j>0? 1: 0); } else { i = strcoll(getsval(x), getsval(y)); } tempfree(x); tempfree(y); switch (n) { case LT: if (i<0) return(True); else return(False); case LE: if (i<=0) return(True); else return(False); case NE: if (i!=0) return(True); else return(False); case EQ: if (i == 0) return(True); else return(False); case GE: if (i>=0) return(True); else return(False); case GT: if (i>0) return(True); else return(False); default: /* can't happen */ FATAL("unknown relational operator %d", n); } return 0; /*NOTREACHED*/ } void tfree(Cell *a) /* free a tempcell */ { if (freeable(a)) { dprintf( ("freeing %s %s %o\n", NN(a->nval), NN(a->sval), a->tval) ); xfree(a->sval); } if (a == tmps) FATAL("tempcell list is curdled"); a->cnext = tmps; tmps = a; } Cell *gettemp(void) /* get a tempcell */ { int i; Cell *x; if (!tmps) { tmps = (Cell *) calloc(100, sizeof(Cell)); if (!tmps) FATAL("out of space for temporaries"); for(i = 1; i < 100; i++) tmps[i-1].cnext = &tmps[i]; - tmps[i-1].cnext = NULL; + tmps[i-1].cnext = 0; } x = tmps; tmps = x->cnext; *x = tempcell; return(x); } Cell *indirect(Node **a, int n) /* $( a[0] ) */ { Awkfloat val; Cell *x; int m; char *s; x = execute(a[0]); val = getfval(x); /* freebsd: defend against super large field numbers */ if ((Awkfloat)INT_MAX < val) FATAL("trying to access out of range field %s", x->nval); m = (int) val; if (m == 0 && !is_number(s = getsval(x))) /* suspicion! */ FATAL("illegal field $(%s), name \"%s\"", s, x->nval); /* BUG: can x->nval ever be null??? */ tempfree(x); x = fieldadr(m); x->ctype = OCELL; /* BUG? why are these needed? */ x->csub = CFLD; return(x); } Cell *substr(Node **a, int nnn) /* substr(a[0], a[1], a[2]) */ { int k, m, n; char *s; int temp; - Cell *x, *y, *z = NULL; + Cell *x, *y, *z = 0; x = execute(a[0]); y = execute(a[1]); - if (a[2] != NULL) + if (a[2] != 0) z = execute(a[2]); s = getsval(x); k = strlen(s) + 1; if (k <= 1) { tempfree(x); tempfree(y); - if (a[2] != NULL) { + if (a[2] != 0) { tempfree(z); } x = gettemp(); setsval(x, ""); return(x); } m = (int) getfval(y); if (m <= 0) m = 1; else if (m > k) m = k; tempfree(y); - if (a[2] != NULL) { + if (a[2] != 0) { n = (int) getfval(z); tempfree(z); } else n = k - 1; if (n < 0) n = 0; else if (n > k - m) n = k - m; dprintf( ("substr: m=%d, n=%d, s=%s\n", m, n, s) ); y = gettemp(); temp = s[n+m-1]; /* with thanks to John Linderman */ s[n+m-1] = '\0'; setsval(y, s + m - 1); s[n+m-1] = temp; tempfree(x); return(y); } Cell *sindex(Node **a, int nnn) /* index(a[0], a[1]) */ { Cell *x, *y, *z; char *s1, *s2, *p1, *p2, *q; Awkfloat v = 0.0; x = execute(a[0]); s1 = getsval(x); y = execute(a[1]); s2 = getsval(y); z = gettemp(); for (p1 = s1; *p1 != '\0'; p1++) { for (q=p1, p2=s2; *p2 != '\0' && *q == *p2; q++, p2++) ; if (*p2 == '\0') { v = (Awkfloat) (p1 - s1 + 1); /* origin 1 */ break; } } tempfree(x); tempfree(y); setfval(z, v); return(z); } #define MAXNUMSIZE 50 int format(char **pbuf, int *pbufsize, const char *s, Node *a) /* printf-like conversions */ { char *fmt; char *p, *t; const char *os; Cell *x; int flag = 0, n; int fmtwd; /* format width */ int fmtsz = recsize; char *buf = *pbuf; int bufsize = *pbufsize; + static int first = 1; + static int have_a_format = 0; + + if (first) { + char buf[100]; + + sprintf(buf, "%a", 42.0); + have_a_format = (strcmp(buf, "0x1.5p+5") == 0); + first = 0; + } + os = s; p = buf; if ((fmt = (char *) malloc(fmtsz)) == NULL) FATAL("out of memory in format()"); while (*s) { adjbuf(&buf, &bufsize, MAXNUMSIZE+1+p-buf, recsize, &p, "format1"); if (*s != '%') { *p++ = *s++; continue; } if (*(s+1) == '%') { *p++ = '%'; s += 2; continue; } /* have to be real careful in case this is a huge number, eg, %100000d */ fmtwd = atoi(s+1); if (fmtwd < 0) fmtwd = -fmtwd; adjbuf(&buf, &bufsize, fmtwd+1+p-buf, recsize, &p, "format2"); for (t = fmt; (*t++ = *s) != '\0'; s++) { if (!adjbuf(&fmt, &fmtsz, MAXNUMSIZE+1+t-fmt, recsize, &t, "format3")) FATAL("format item %.30s... ran format() out of memory", os); if (isalpha((uschar)*s) && *s != 'l' && *s != 'h' && *s != 'L') break; /* the ansi panoply */ + if (*s == '$') { + FATAL("'$' not permitted in awk formats"); + } if (*s == '*') { + if (a == NULL) { + FATAL("not enough args in printf(%s)", os); + } x = execute(a); a = a->nnext; sprintf(t-1, "%d", fmtwd=(int) getfval(x)); if (fmtwd < 0) fmtwd = -fmtwd; adjbuf(&buf, &bufsize, fmtwd+1+p-buf, recsize, &p, "format"); t = fmt + strlen(fmt); tempfree(x); } } *t = '\0'; if (fmtwd < 0) fmtwd = -fmtwd; adjbuf(&buf, &bufsize, fmtwd+1+p-buf, recsize, &p, "format4"); - switch (*s) { + case 'a': case 'A': + if (have_a_format) + flag = *s; + else + flag = 'f'; + break; case 'f': case 'e': case 'g': case 'E': case 'G': flag = 'f'; break; case 'd': case 'i': flag = 'd'; if(*(s-1) == 'l') break; *(t-1) = 'l'; *t = 'd'; *++t = '\0'; break; case 'o': case 'x': case 'X': case 'u': flag = *(s-1) == 'l' ? 'd' : 'u'; break; case 's': flag = 's'; break; case 'c': flag = 'c'; break; default: WARNING("weird printf conversion %s", fmt); flag = '?'; break; } if (a == NULL) FATAL("not enough args in printf(%s)", os); x = execute(a); a = a->nnext; n = MAXNUMSIZE; if (fmtwd > n) n = fmtwd; adjbuf(&buf, &bufsize, 1+n+p-buf, recsize, &p, "format5"); switch (flag) { case '?': sprintf(p, "%s", fmt); /* unknown, so dump it too */ t = getsval(x); n = strlen(t); if (fmtwd > n) n = fmtwd; adjbuf(&buf, &bufsize, 1+strlen(p)+n+p-buf, recsize, &p, "format6"); p += strlen(p); sprintf(p, "%s", t); break; + case 'a': + case 'A': case 'f': sprintf(p, fmt, getfval(x)); break; case 'd': sprintf(p, fmt, (long) getfval(x)); break; case 'u': sprintf(p, fmt, (int) getfval(x)); break; case 's': t = getsval(x); n = strlen(t); if (fmtwd > n) n = fmtwd; if (!adjbuf(&buf, &bufsize, 1+n+p-buf, recsize, &p, "format7")) FATAL("huge string/format (%d chars) in printf %.30s... ran format() out of memory", n, t); sprintf(p, fmt, t); break; case 'c': if (isnum(x)) { if ((int)getfval(x)) sprintf(p, fmt, (int) getfval(x)); else { *p++ = '\0'; /* explicit null byte */ *p = '\0'; /* next output will start here */ } } else sprintf(p, fmt, getsval(x)[0]); break; default: FATAL("can't happen: bad conversion %c in format()", flag); } tempfree(x); p += strlen(p); s++; } *p = '\0'; free(fmt); for ( ; a; a = a->nnext) /* evaluate any remaining args */ execute(a); *pbuf = buf; *pbufsize = bufsize; return p - buf; } Cell *awksprintf(Node **a, int n) /* sprintf(a[0]) */ { Cell *x; Node *y; char *buf; int bufsz=3*recsize; if ((buf = (char *) malloc(bufsz)) == NULL) FATAL("out of memory in awksprintf"); y = a[0]->nnext; x = execute(a[0]); if (format(&buf, &bufsz, getsval(x), y) == -1) FATAL("sprintf string %.30s... too long. can't happen.", buf); tempfree(x); x = gettemp(); x->sval = buf; x->tval = STR; return(x); } Cell *awkprintf(Node **a, int n) /* printf */ { /* a[0] is list of args, starting with format string */ /* a[1] is redirection operator, a[2] is redirection file */ FILE *fp; Cell *x; Node *y; char *buf; int len; int bufsz=3*recsize; if ((buf = (char *) malloc(bufsz)) == NULL) FATAL("out of memory in awkprintf"); y = a[0]->nnext; x = execute(a[0]); if ((len = format(&buf, &bufsz, getsval(x), y)) == -1) FATAL("printf string %.30s... too long. can't happen.", buf); tempfree(x); if (a[1] == NULL) { /* fputs(buf, stdout); */ fwrite(buf, len, 1, stdout); if (ferror(stdout)) FATAL("write error on stdout"); } else { fp = redirect(ptoi(a[1]), a[2]); /* fputs(buf, fp); */ fwrite(buf, len, 1, fp); fflush(fp); if (ferror(fp)) FATAL("write error on %s", filename(fp)); } free(buf); return(True); } Cell *arith(Node **a, int n) /* a[0] + a[1], etc. also -a[0] */ { Awkfloat i, j = 0; double v; Cell *x, *y, *z; x = execute(a[0]); i = getfval(x); tempfree(x); - if (n != UMINUS) { + if (n != UMINUS && n != UPLUS) { y = execute(a[1]); j = getfval(y); tempfree(y); } z = gettemp(); switch (n) { case ADD: i += j; break; case MINUS: i -= j; break; case MULT: i *= j; break; case DIVIDE: if (j == 0) FATAL("division by zero"); i /= j; break; case MOD: if (j == 0) FATAL("division by zero in mod"); modf(i/j, &v); i = i - j * v; break; case UMINUS: i = -i; break; + case UPLUS: /* handled by getfval(), above */ + break; case POWER: if (j >= 0 && modf(j, &v) == 0.0) /* pos integer exponent */ i = ipow(i, (int) j); else i = errcheck(pow(i, j), "pow"); break; default: /* can't happen */ FATAL("illegal arithmetic operator %d", n); } setfval(z, i); return(z); } double ipow(double x, int n) /* x**n. ought to be done by pow, but isn't always */ { double v; if (n <= 0) return 1; v = ipow(x, n/2); if (n % 2 == 0) return v * v; else return x * v * v; } Cell *incrdecr(Node **a, int n) /* a[0]++, etc. */ { Cell *x, *z; int k; Awkfloat xf; x = execute(a[0]); xf = getfval(x); k = (n == PREINCR || n == POSTINCR) ? 1 : -1; if (n == PREINCR || n == PREDECR) { setfval(x, xf + k); return(x); } z = gettemp(); setfval(z, xf); setfval(x, xf + k); tempfree(x); return(z); } Cell *assign(Node **a, int n) /* a[0] = a[1], a[0] += a[1], etc. */ { /* this is subtle; don't muck with it. */ Cell *x, *y; Awkfloat xf, yf; double v; y = execute(a[1]); x = execute(a[0]); if (n == ASSIGN) { /* ordinary assignment */ - if (x == y && !(x->tval & (FLD|REC))) /* self-assignment: */ - ; /* leave alone unless it's a field */ + if (x == y && !(x->tval & (FLD|REC)) && x != nfloc) + ; /* self-assignment: leave alone unless it's a field or NF */ else if ((y->tval & (STR|NUM)) == (STR|NUM)) { setsval(x, getsval(y)); x->fval = getfval(y); x->tval |= NUM; } else if (isstr(y)) setsval(x, getsval(y)); else if (isnum(y)) setfval(x, getfval(y)); else funnyvar(y, "read value of"); tempfree(y); return(x); } xf = getfval(x); yf = getfval(y); switch (n) { case ADDEQ: xf += yf; break; case SUBEQ: xf -= yf; break; case MULTEQ: xf *= yf; break; case DIVEQ: if (yf == 0) FATAL("division by zero in /="); xf /= yf; break; case MODEQ: if (yf == 0) FATAL("division by zero in %%="); modf(xf/yf, &v); xf = xf - yf * v; break; case POWEQ: if (yf >= 0 && modf(yf, &v) == 0.0) /* pos integer exponent */ xf = ipow(xf, (int) yf); else xf = errcheck(pow(xf, yf), "pow"); break; default: FATAL("illegal assignment operator %d", n); break; } tempfree(y); setfval(x, xf); return(x); } Cell *cat(Node **a, int q) /* a[0] cat a[1] */ { Cell *x, *y, *z; int n1, n2; - char *s; + char *s = NULL; + int ssz = 0; x = execute(a[0]); + n1 = strlen(getsval(x)); + adjbuf(&s, &ssz, n1 + 1, recsize, 0, "cat1"); + (void) strncpy(s, x->sval, ssz); + y = execute(a[1]); - getsval(x); - getsval(y); - n1 = strlen(x->sval); - n2 = strlen(y->sval); - s = (char *) malloc(n1 + n2 + 1); - if (s == NULL) - FATAL("out of space concatenating %.15s... and %.15s...", - x->sval, y->sval); - strcpy(s, x->sval); - strcpy(s+n1, y->sval); + n2 = strlen(getsval(y)); + adjbuf(&s, &ssz, n1 + n2 + 1, recsize, 0, "cat2"); + (void) strncpy(s + n1, y->sval, ssz - n1); + tempfree(x); tempfree(y); + z = gettemp(); z->sval = s; z->tval = STR; + return(z); } Cell *pastat(Node **a, int n) /* a[0] { a[1] } */ { Cell *x; - if (a[0] == NULL) + if (a[0] == 0) x = execute(a[1]); else { x = execute(a[0]); if (istrue(x)) { tempfree(x); x = execute(a[1]); } } return x; } Cell *dopa2(Node **a, int n) /* a[0], a[1] { a[2] } */ { Cell *x; int pair; pair = ptoi(a[3]); if (pairstack[pair] == 0) { x = execute(a[0]); if (istrue(x)) pairstack[pair] = 1; tempfree(x); } if (pairstack[pair] == 1) { x = execute(a[1]); if (istrue(x)) pairstack[pair] = 0; tempfree(x); x = execute(a[2]); return(x); } return(False); } Cell *split(Node **a, int nnn) /* split(a[0], a[1], a[2]); a[3] is type */ { - Cell *x = NULL, *y, *ap; + Cell *x = 0, *y, *ap; char *s, *origs; + char *fs, *origfs = NULL; int sep; - char *t, temp, num[50], *fs = NULL; + char *t, temp, num[50]; int n, tempstat, arg3type; y = execute(a[0]); /* source string */ origs = s = strdup(getsval(y)); arg3type = ptoi(a[3]); - if (a[2] == NULL) /* fs string */ - fs = *FS; + if (a[2] == 0) /* fs string */ + fs = getsval(fsloc); else if (arg3type == STRING) { /* split(str,arr,"string") */ x = execute(a[2]); - fs = getsval(x); + origfs = fs = strdup(getsval(x)); + tempfree(x); } else if (arg3type == REGEXPR) fs = "(regexpr)"; /* split(str,arr,/regexpr/) */ else FATAL("illegal type of split"); sep = *fs; ap = execute(a[1]); /* array name */ freesymtab(ap); dprintf( ("split: s=|%s|, a=%s, sep=|%s|\n", s, NN(ap->nval), fs) ); ap->tval &= ~STR; ap->tval |= ARR; ap->sval = (char *) makesymtab(NSYMTAB); n = 0; if (arg3type == REGEXPR && strlen((char*)((fa*)a[2])->restr) == 0) { /* split(s, a, //); have to arrange that it looks like empty sep */ arg3type = 0; fs = ""; sep = 0; } if (*s != '\0' && (strlen(fs) > 1 || arg3type == REGEXPR)) { /* reg expr */ fa *pfa; if (arg3type == REGEXPR) { /* it's ready already */ pfa = (fa *) a[2]; } else { pfa = makedfa(fs, 1); } if (nematch(pfa,s)) { tempstat = pfa->initstat; pfa->initstat = 2; do { n++; sprintf(num, "%d", n); temp = *patbeg; *patbeg = '\0'; if (is_number(s)) setsymtab(num, s, atof(s), STR|NUM, (Array *) ap->sval); else setsymtab(num, s, 0.0, STR, (Array *) ap->sval); *patbeg = temp; s = patbeg + patlen; if (*(patbeg+patlen-1) == 0 || *s == 0) { n++; sprintf(num, "%d", n); setsymtab(num, "", 0.0, STR, (Array *) ap->sval); pfa->initstat = tempstat; goto spdone; } } while (nematch(pfa,s)); pfa->initstat = tempstat; /* bwk: has to be here to reset */ /* cf gsub and refldbld */ } n++; sprintf(num, "%d", n); if (is_number(s)) setsymtab(num, s, atof(s), STR|NUM, (Array *) ap->sval); else setsymtab(num, s, 0.0, STR, (Array *) ap->sval); spdone: pfa = NULL; } else if (sep == ' ') { for (n = 0; ; ) { while (*s == ' ' || *s == '\t' || *s == '\n') s++; if (*s == 0) break; n++; t = s; do s++; while (*s!=' ' && *s!='\t' && *s!='\n' && *s!='\0'); temp = *s; *s = '\0'; sprintf(num, "%d", n); if (is_number(t)) setsymtab(num, t, atof(t), STR|NUM, (Array *) ap->sval); else setsymtab(num, t, 0.0, STR, (Array *) ap->sval); *s = temp; if (*s != 0) s++; } } else if (sep == 0) { /* new: split(s, a, "") => 1 char/elem */ for (n = 0; *s != 0; s++) { char buf[2]; n++; sprintf(num, "%d", n); buf[0] = *s; buf[1] = 0; if (isdigit((uschar)buf[0])) setsymtab(num, buf, atof(buf), STR|NUM, (Array *) ap->sval); else setsymtab(num, buf, 0.0, STR, (Array *) ap->sval); } } else if (*s != 0) { for (;;) { n++; t = s; while (*s != sep && *s != '\n' && *s != '\0') s++; temp = *s; *s = '\0'; sprintf(num, "%d", n); if (is_number(t)) setsymtab(num, t, atof(t), STR|NUM, (Array *) ap->sval); else setsymtab(num, t, 0.0, STR, (Array *) ap->sval); *s = temp; if (*s++ == 0) break; } } tempfree(ap); tempfree(y); free(origs); - if (a[2] != NULL && arg3type == STRING) { - tempfree(x); - } + free(origfs); x = gettemp(); x->tval = NUM; x->fval = n; return(x); } Cell *condexpr(Node **a, int n) /* a[0] ? a[1] : a[2] */ { Cell *x; x = execute(a[0]); if (istrue(x)) { tempfree(x); x = execute(a[1]); } else { tempfree(x); x = execute(a[2]); } return(x); } Cell *ifstat(Node **a, int n) /* if (a[0]) a[1]; else a[2] */ { Cell *x; x = execute(a[0]); if (istrue(x)) { tempfree(x); x = execute(a[1]); - } else if (a[2] != NULL) { + } else if (a[2] != 0) { tempfree(x); x = execute(a[2]); } return(x); } Cell *whilestat(Node **a, int n) /* while (a[0]) a[1] */ { Cell *x; for (;;) { x = execute(a[0]); if (!istrue(x)) return(x); tempfree(x); x = execute(a[1]); if (isbreak(x)) { x = True; return(x); } if (isnext(x) || isexit(x) || isret(x)) return(x); tempfree(x); } } Cell *dostat(Node **a, int n) /* do a[0]; while(a[1]) */ { Cell *x; for (;;) { x = execute(a[0]); if (isbreak(x)) return True; if (isnext(x) || isexit(x) || isret(x)) return(x); tempfree(x); x = execute(a[1]); if (!istrue(x)) return(x); tempfree(x); } } Cell *forstat(Node **a, int n) /* for (a[0]; a[1]; a[2]) a[3] */ { Cell *x; x = execute(a[0]); tempfree(x); for (;;) { - if (a[1]!=NULL) { + if (a[1]!=0) { x = execute(a[1]); if (!istrue(x)) return(x); else tempfree(x); } x = execute(a[3]); if (isbreak(x)) /* turn off break */ return True; if (isnext(x) || isexit(x) || isret(x)) return(x); tempfree(x); x = execute(a[2]); tempfree(x); } } Cell *instat(Node **a, int n) /* for (a[0] in a[1]) a[2] */ { Cell *x, *vp, *arrayp, *cp, *ncp; Array *tp; int i; vp = execute(a[0]); arrayp = execute(a[1]); if (!isarr(arrayp)) { return True; } tp = (Array *) arrayp->sval; tempfree(arrayp); for (i = 0; i < tp->size; i++) { /* this routine knows too much */ for (cp = tp->tab[i]; cp != NULL; cp = ncp) { setsval(vp, cp->nval); ncp = cp->cnext; x = execute(a[2]); if (isbreak(x)) { tempfree(vp); return True; } if (isnext(x) || isexit(x) || isret(x)) { tempfree(vp); return(x); } tempfree(x); } } return True; } Cell *bltin(Node **a, int n) /* builtin functions. a[0] is type, a[1] is arg list */ { Cell *x, *y; Awkfloat u; int t, i; Awkfloat tmp; char *p, *buf; Node *nextarg; FILE *fp; void flush_all(void); + int status = 0; t = ptoi(a[0]); x = execute(a[1]); nextarg = a[1]->nnext; switch (t) { case FLENGTH: if (isarr(x)) u = ((Array *) x->sval)->nelem; /* GROT. should be function*/ else u = strlen(getsval(x)); break; case FLOG: u = errcheck(log(getfval(x)), "log"); break; case FINT: modf(getfval(x), &u); break; case FEXP: u = errcheck(exp(getfval(x)), "exp"); break; case FSQRT: u = errcheck(sqrt(getfval(x)), "sqrt"); break; case FSIN: u = sin(getfval(x)); break; case FCOS: u = cos(getfval(x)); break; case FATAN: - if (nextarg == NULL) { + if (nextarg == 0) { WARNING("atan2 requires two arguments; returning 1.0"); u = 1.0; } else { y = execute(a[1]->nnext); u = atan2(getfval(x), getfval(y)); tempfree(y); nextarg = nextarg->nnext; } break; case FCOMPL: u = ~((int)getfval(x)); break; case FAND: if (nextarg == NULL) { WARNING("and requires two arguments; returning 0"); u = 0; break; } i = ((int)getfval(x)); while (nextarg != NULL) { y = execute(nextarg); i &= (int)getfval(y); tempfree(y); nextarg = nextarg->nnext; } u = i; break; case FFOR: if (nextarg == NULL) { WARNING("or requires two arguments; returning 0"); u = 0; break; } i = ((int)getfval(x)); while (nextarg != NULL) { y = execute(nextarg); i |= (int)getfval(y); tempfree(y); nextarg = nextarg->nnext; } u = i; break; case FXOR: if (nextarg == NULL) { WARNING("xor requires two arguments; returning 0"); u = 0; break; } i = ((int)getfval(x)); while (nextarg != NULL) { y = execute(nextarg); i ^= (int)getfval(y); tempfree(y); nextarg = nextarg->nnext; } u = i; break; case FLSHIFT: if (nextarg == NULL) { WARNING("lshift requires two arguments; returning 0"); u = 0; break; } y = execute(a[1]->nnext); u = ((int)getfval(x)) << ((int)getfval(y)); tempfree(y); nextarg = nextarg->nnext; break; case FRSHIFT: if (nextarg == NULL) { WARNING("rshift requires two arguments; returning 0"); u = 0; break; } y = execute(a[1]->nnext); u = ((int)getfval(x)) >> ((int)getfval(y)); tempfree(y); nextarg = nextarg->nnext; break; case FSYSTEM: fflush(stdout); /* in case something is buffered already */ - u = (Awkfloat) system(getsval(x)) / 256; /* 256 is unix-dep */ + status = system(getsval(x)); + u = status; + if (status != -1) { + if (WIFEXITED(status)) { + u = WEXITSTATUS(status); + } else if (WIFSIGNALED(status)) { + u = WTERMSIG(status) + 256; +#ifdef WCOREDUMP + if (WCOREDUMP(status)) + u += 256; +#endif + } else /* something else?!? */ + u = 0; + } break; case FRAND: /* random() returns numbers in [0..2^31-1] * in order to get a number in [0, 1), divide it by 2^31 */ u = (Awkfloat) random() / (0x7fffffffL + 0x1UL); break; case FSRAND: if (isrec(x)) /* no argument provided */ u = time((time_t *)0); else u = getfval(x); tmp = u; srandom((unsigned long) u); u = srand_seed; srand_seed = tmp; break; case FTOUPPER: case FTOLOWER: buf = tostring(getsval(x)); if (t == FTOUPPER) { for (p = buf; *p; p++) if (islower((uschar) *p)) *p = toupper((uschar)*p); } else { for (p = buf; *p; p++) if (isupper((uschar) *p)) *p = tolower((uschar)*p); } tempfree(x); x = gettemp(); setsval(x, buf); free(buf); return x; case FFLUSH: if (isrec(x) || strlen(getsval(x)) == 0) { flush_all(); /* fflush() or fflush("") -> all */ u = 0; } else if ((fp = openfile(FFLUSH, getsval(x))) == NULL) u = EOF; else u = fflush(fp); break; default: /* can't happen */ FATAL("illegal function type %d", t); break; } tempfree(x); x = gettemp(); setfval(x, u); - if (nextarg != NULL) { + if (nextarg != 0) { WARNING("warning: function has too many arguments"); for ( ; nextarg; nextarg = nextarg->nnext) execute(nextarg); } return(x); } Cell *printstat(Node **a, int n) /* print a[0] */ { Node *x; Cell *y; FILE *fp; - if (a[1] == NULL) /* a[1] is redirection operator, a[2] is file */ + if (a[1] == 0) /* a[1] is redirection operator, a[2] is file */ fp = stdout; else fp = redirect(ptoi(a[1]), a[2]); for (x = a[0]; x != NULL; x = x->nnext) { y = execute(x); fputs(getpssval(y), fp); tempfree(y); if (x->nnext == NULL) - fputs(*ORS, fp); + fputs(getsval(orsloc), fp); else - fputs(*OFS, fp); + fputs(getsval(ofsloc), fp); } - if (a[1] != NULL) + if (a[1] != 0) fflush(fp); if (ferror(fp)) FATAL("write error on %s", filename(fp)); return(True); } Cell *nullproc(Node **a, int n) { - n = n; - a = a; return 0; } FILE *redirect(int a, Node *b) /* set up all i/o redirections */ { FILE *fp; Cell *x; char *fname; x = execute(b); fname = getsval(x); fp = openfile(a, fname); if (fp == NULL) FATAL("can't open file %s", fname); tempfree(x); return fp; } struct files { FILE *fp; const char *fname; int mode; /* '|', 'a', 'w' => LE/LT, GT */ } *files; int nfiles; void stdinit(void) /* in case stdin, etc., are not constants */ { nfiles = FOPEN_MAX; files = calloc(nfiles, sizeof(*files)); if (files == NULL) FATAL("can't allocate file memory for %u files", nfiles); files[0].fp = stdin; files[0].fname = "/dev/stdin"; files[0].mode = LT; files[1].fp = stdout; files[1].fname = "/dev/stdout"; files[1].mode = GT; files[2].fp = stderr; files[2].fname = "/dev/stderr"; files[2].mode = GT; } FILE *openfile(int a, const char *us) { const char *s = us; int i, m; - FILE *fp = NULL; + FILE *fp = 0; if (*s == '\0') FATAL("null file name in print or getline"); for (i=0; i < nfiles; i++) if (files[i].fname && strcmp(s, files[i].fname) == 0) { if (a == files[i].mode || (a==APPEND && files[i].mode==GT)) return files[i].fp; if (a == FFLUSH) return files[i].fp; } if (a == FFLUSH) /* didn't find it, so don't create it! */ return NULL; for (i=0; i < nfiles; i++) - if (files[i].fp == NULL) + if (files[i].fp == 0) break; if (i >= nfiles) { struct files *nf; int nnf = nfiles + FOPEN_MAX; nf = realloc(files, nnf * sizeof(*nf)); if (nf == NULL) FATAL("cannot grow files for %s and %d files", s, nnf); memset(&nf[nfiles], 0, FOPEN_MAX * sizeof(*nf)); nfiles = nnf; files = nf; } fflush(stdout); /* force a semblance of order */ m = a; if (a == GT) { fp = fopen(s, "w"); } else if (a == APPEND) { fp = fopen(s, "a"); m = GT; /* so can mix > and >> */ } else if (a == '|') { /* output pipe */ fp = popen(s, "w"); } else if (a == LE) { /* input pipe */ fp = popen(s, "r"); } else if (a == LT) { /* getline sval, files[i].fname) == 0) { if (ferror(files[i].fp)) WARNING( "i/o error occurred on %s", files[i].fname ); if (files[i].mode == '|' || files[i].mode == LE) stat = pclose(files[i].fp); else stat = fclose(files[i].fp); if (stat == EOF) WARNING( "i/o error occurred closing %s", files[i].fname ); if (i > 2) /* don't do /dev/std... */ xfree(files[i].fname); files[i].fname = NULL; /* watch out for ref thru this */ files[i].fp = NULL; } } tempfree(x); x = gettemp(); setfval(x, (Awkfloat) stat); return(x); } void closeall(void) { int i, stat; for (i = 0; i < FOPEN_MAX; i++) { if (files[i].fp) { if (ferror(files[i].fp)) WARNING( "i/o error occurred on %s", files[i].fname ); if (files[i].mode == '|' || files[i].mode == LE) stat = pclose(files[i].fp); else stat = fclose(files[i].fp); if (stat == EOF) WARNING( "i/o error occurred while closing %s", files[i].fname ); } } } void flush_all(void) { int i; for (i = 0; i < nfiles; i++) if (files[i].fp) fflush(files[i].fp); } void backsub(char **pb_ptr, char **sptr_ptr); Cell *sub(Node **a, int nnn) /* substitute command */ { char *sptr, *pb, *q; Cell *x, *y, *result; char *t, *buf; fa *pfa; int bufsz = recsize; if ((buf = (char *) malloc(bufsz)) == NULL) FATAL("out of memory in sub"); x = execute(a[3]); /* target string */ t = getsval(x); - if (a[0] == NULL) /* 0 => a[1] is already-compiled regexpr */ + if (a[0] == 0) /* 0 => a[1] is already-compiled regexpr */ pfa = (fa *) a[1]; /* regular expression */ else { y = execute(a[1]); pfa = makedfa(getsval(y), 1); tempfree(y); } y = execute(a[2]); /* replacement string */ result = False; if (pmatch(pfa, t)) { sptr = t; adjbuf(&buf, &bufsz, 1+patbeg-sptr, recsize, 0, "sub"); pb = buf; while (sptr < patbeg) *pb++ = *sptr++; sptr = getsval(y); while (*sptr != 0) { adjbuf(&buf, &bufsz, 5+pb-buf, recsize, &pb, "sub"); if (*sptr == '\\') { backsub(&pb, &sptr); } else if (*sptr == '&') { sptr++; adjbuf(&buf, &bufsz, 1+patlen+pb-buf, recsize, &pb, "sub"); for (q = patbeg; q < patbeg+patlen; ) *pb++ = *q++; } else *pb++ = *sptr++; } *pb = '\0'; if (pb > buf + bufsz) FATAL("sub result1 %.30s too big; can't happen", buf); sptr = patbeg + patlen; if ((patlen == 0 && *patbeg) || (patlen && *(sptr-1))) { adjbuf(&buf, &bufsz, 1+strlen(sptr)+pb-buf, 0, &pb, "sub"); while ((*pb++ = *sptr++) != 0) ; } if (pb > buf + bufsz) FATAL("sub result2 %.30s too big; can't happen", buf); setsval(x, buf); /* BUG: should be able to avoid copy */ - result = True; + result = True;; } tempfree(x); tempfree(y); free(buf); return result; } Cell *gsub(Node **a, int nnn) /* global substitute */ { Cell *x, *y; char *rptr, *sptr, *t, *pb, *q; char *buf; fa *pfa; int mflag, tempstat, num; int bufsz = recsize; if ((buf = (char *) malloc(bufsz)) == NULL) FATAL("out of memory in gsub"); mflag = 0; /* if mflag == 0, can replace empty string */ num = 0; x = execute(a[3]); /* target string */ t = getsval(x); - if (a[0] == NULL) /* 0 => a[1] is already-compiled regexpr */ + if (a[0] == 0) /* 0 => a[1] is already-compiled regexpr */ pfa = (fa *) a[1]; /* regular expression */ else { y = execute(a[1]); pfa = makedfa(getsval(y), 1); tempfree(y); } y = execute(a[2]); /* replacement string */ if (pmatch(pfa, t)) { tempstat = pfa->initstat; pfa->initstat = 2; pb = buf; rptr = getsval(y); do { if (patlen == 0 && *patbeg != 0) { /* matched empty string */ if (mflag == 0) { /* can replace empty */ num++; sptr = rptr; while (*sptr != 0) { adjbuf(&buf, &bufsz, 5+pb-buf, recsize, &pb, "gsub"); if (*sptr == '\\') { backsub(&pb, &sptr); } else if (*sptr == '&') { sptr++; adjbuf(&buf, &bufsz, 1+patlen+pb-buf, recsize, &pb, "gsub"); for (q = patbeg; q < patbeg+patlen; ) *pb++ = *q++; } else *pb++ = *sptr++; } } if (*t == 0) /* at end */ goto done; adjbuf(&buf, &bufsz, 2+pb-buf, recsize, &pb, "gsub"); *pb++ = *t++; if (pb > buf + bufsz) /* BUG: not sure of this test */ FATAL("gsub result0 %.30s too big; can't happen", buf); mflag = 0; } else { /* matched nonempty string */ num++; sptr = t; adjbuf(&buf, &bufsz, 1+(patbeg-sptr)+pb-buf, recsize, &pb, "gsub"); while (sptr < patbeg) *pb++ = *sptr++; sptr = rptr; while (*sptr != 0) { adjbuf(&buf, &bufsz, 5+pb-buf, recsize, &pb, "gsub"); if (*sptr == '\\') { backsub(&pb, &sptr); } else if (*sptr == '&') { sptr++; adjbuf(&buf, &bufsz, 1+patlen+pb-buf, recsize, &pb, "gsub"); for (q = patbeg; q < patbeg+patlen; ) *pb++ = *q++; } else *pb++ = *sptr++; } t = patbeg + patlen; if (patlen == 0 || *t == 0 || *(t-1) == 0) goto done; if (pb > buf + bufsz) FATAL("gsub result1 %.30s too big; can't happen", buf); mflag = 1; } } while (pmatch(pfa,t)); sptr = t; adjbuf(&buf, &bufsz, 1+strlen(sptr)+pb-buf, 0, &pb, "gsub"); while ((*pb++ = *sptr++) != 0) ; done: if (pb < buf + bufsz) *pb = '\0'; else if (*(pb-1) != '\0') FATAL("gsub result2 %.30s truncated; can't happen", buf); setsval(x, buf); /* BUG: should be able to avoid copy + free */ pfa->initstat = tempstat; } tempfree(x); tempfree(y); x = gettemp(); x->tval = NUM; x->fval = num; free(buf); return(x); } void backsub(char **pb_ptr, char **sptr_ptr) /* handle \\& variations */ { /* sptr[0] == '\\' */ char *pb = *pb_ptr, *sptr = *sptr_ptr; if (sptr[1] == '\\') { if (sptr[2] == '\\' && sptr[3] == '&') { /* \\\& -> \& */ *pb++ = '\\'; *pb++ = '&'; sptr += 4; } else if (sptr[2] == '&') { /* \\& -> \ + matched */ *pb++ = '\\'; sptr += 2; } else { /* \\x -> \\x */ *pb++ = *sptr++; *pb++ = *sptr++; } } else if (sptr[1] == '&') { /* literal & */ sptr++; *pb++ = *sptr++; } else /* literal \ */ *pb++ = *sptr++; *pb_ptr = pb; *sptr_ptr = sptr; } Index: head/contrib/one-true-awk/tran.c =================================================================== --- head/contrib/one-true-awk/tran.c (revision 348510) +++ head/contrib/one-true-awk/tran.c (revision 348511) @@ -1,459 +1,596 @@ /**************************************************************** Copyright (C) Lucent Technologies 1997 All Rights Reserved Permission to use, copy, modify, and distribute this software and its documentation for any purpose and without fee is hereby granted, provided that the above copyright notice appear in all copies and that both that the copyright notice and this permission notice and warranty disclaimer appear in supporting documentation, and that the name Lucent Technologies or any of its entities not be used in advertising or publicity pertaining to distribution of the software without specific, written prior permission. LUCENT DISCLAIMS ALL WARRANTIES WITH REGARD TO THIS SOFTWARE, INCLUDING ALL IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL LUCENT OR ANY OF ITS ENTITIES BE LIABLE FOR ANY SPECIAL, 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. ****************************************************************/ #define DEBUG #include #include #include #include #include #include "awk.h" #include "ytab.h" #define FULLTAB 2 /* rehash when table gets this x full */ #define GROWTAB 4 /* grow table by this factor */ Array *symtab; /* main symbol table */ char **FS; /* initial field sep */ char **RS; /* initial record sep */ char **OFS; /* output field sep */ char **ORS; /* output record sep */ char **OFMT; /* output format for numbers */ char **CONVFMT; /* format for conversions in getsval */ Awkfloat *NF; /* number of fields in current record */ Awkfloat *NR; /* number of current record */ Awkfloat *FNR; /* number of current record in current file */ char **FILENAME; /* current filename argument */ Awkfloat *ARGC; /* number of arguments from command line */ char **SUBSEP; /* subscript separator for a[i,j,k]; default \034 */ Awkfloat *RSTART; /* start of re matched with ~; origin 1 (!) */ Awkfloat *RLENGTH; /* length of same */ Cell *fsloc; /* FS */ Cell *nrloc; /* NR */ Cell *nfloc; /* NF */ Cell *fnrloc; /* FNR */ +Cell *ofsloc; /* OFS */ +Cell *orsloc; /* ORS */ +Cell *rsloc; /* RS */ Array *ARGVtab; /* symbol table containing ARGV[...] */ Array *ENVtab; /* symbol table containing ENVIRON[...] */ Cell *rstartloc; /* RSTART */ Cell *rlengthloc; /* RLENGTH */ +Cell *subseploc; /* SUBSEP */ Cell *symtabloc; /* SYMTAB */ Cell *nullloc; /* a guaranteed empty cell */ Node *nullnode; /* zero&null, converted into a node for comparisons */ Cell *literal0; extern Cell **fldtab; +static void +setfree(Cell *vp) +{ + if (&vp->sval == FS || &vp->sval == RS || + &vp->sval == OFS || &vp->sval == ORS || + &vp->sval == OFMT || &vp->sval == CONVFMT || + &vp->sval == FILENAME || &vp->sval == SUBSEP) + vp->tval |= DONTFREE; + else + vp->tval &= ~DONTFREE; +} + void syminit(void) /* initialize symbol table with builtin vars */ { literal0 = setsymtab("0", "0", 0.0, NUM|STR|CON|DONTFREE, symtab); /* this is used for if(x)... tests: */ nullloc = setsymtab("$zero&null", "", 0.0, NUM|STR|CON|DONTFREE, symtab); nullnode = celltonode(nullloc, CCON); fsloc = setsymtab("FS", " ", 0.0, STR|DONTFREE, symtab); FS = &fsloc->sval; - RS = &setsymtab("RS", "\n", 0.0, STR|DONTFREE, symtab)->sval; - OFS = &setsymtab("OFS", " ", 0.0, STR|DONTFREE, symtab)->sval; - ORS = &setsymtab("ORS", "\n", 0.0, STR|DONTFREE, symtab)->sval; + rsloc = setsymtab("RS", "\n", 0.0, STR|DONTFREE, symtab); + RS = &rsloc->sval; + ofsloc = setsymtab("OFS", " ", 0.0, STR|DONTFREE, symtab); + OFS = &ofsloc->sval; + orsloc = setsymtab("ORS", "\n", 0.0, STR|DONTFREE, symtab); + ORS = &orsloc->sval; OFMT = &setsymtab("OFMT", "%.6g", 0.0, STR|DONTFREE, symtab)->sval; CONVFMT = &setsymtab("CONVFMT", "%.6g", 0.0, STR|DONTFREE, symtab)->sval; FILENAME = &setsymtab("FILENAME", "", 0.0, STR|DONTFREE, symtab)->sval; nfloc = setsymtab("NF", "", 0.0, NUM, symtab); NF = &nfloc->fval; nrloc = setsymtab("NR", "", 0.0, NUM, symtab); NR = &nrloc->fval; fnrloc = setsymtab("FNR", "", 0.0, NUM, symtab); FNR = &fnrloc->fval; - SUBSEP = &setsymtab("SUBSEP", "\034", 0.0, STR|DONTFREE, symtab)->sval; + subseploc = setsymtab("SUBSEP", "\034", 0.0, STR|DONTFREE, symtab); + SUBSEP = &subseploc->sval; rstartloc = setsymtab("RSTART", "", 0.0, NUM, symtab); RSTART = &rstartloc->fval; rlengthloc = setsymtab("RLENGTH", "", 0.0, NUM, symtab); RLENGTH = &rlengthloc->fval; symtabloc = setsymtab("SYMTAB", "", 0.0, ARR, symtab); symtabloc->sval = (char *) symtab; } void arginit(int ac, char **av) /* set up ARGV and ARGC */ { Cell *cp; int i; char temp[50]; ARGC = &setsymtab("ARGC", "", (Awkfloat) ac, NUM, symtab)->fval; cp = setsymtab("ARGV", "", 0.0, ARR, symtab); ARGVtab = makesymtab(NSYMTAB); /* could be (int) ARGC as well */ cp->sval = (char *) ARGVtab; for (i = 0; i < ac; i++) { sprintf(temp, "%d", i); if (is_number(*av)) setsymtab(temp, *av, atof(*av), STR|NUM, ARGVtab); else setsymtab(temp, *av, 0.0, STR, ARGVtab); av++; } } void envinit(char **envp) /* set up ENVIRON variable */ { Cell *cp; char *p; cp = setsymtab("ENVIRON", "", 0.0, ARR, symtab); ENVtab = makesymtab(NSYMTAB); cp->sval = (char *) ENVtab; for ( ; *envp; envp++) { if ((p = strchr(*envp, '=')) == NULL) continue; if( p == *envp ) /* no left hand side name in env string */ continue; *p++ = 0; /* split into two strings at = */ if (is_number(p)) setsymtab(*envp, p, atof(p), STR|NUM, ENVtab); else setsymtab(*envp, p, 0.0, STR, ENVtab); p[-1] = '='; /* restore in case env is passed down to a shell */ } } Array *makesymtab(int n) /* make a new symbol table */ { Array *ap; Cell **tp; ap = (Array *) malloc(sizeof(Array)); tp = (Cell **) calloc(n, sizeof(Cell *)); if (ap == NULL || tp == NULL) FATAL("out of space in makesymtab"); ap->nelem = 0; ap->size = n; ap->tab = tp; return(ap); } void freesymtab(Cell *ap) /* free a symbol table */ { Cell *cp, *temp; Array *tp; int i; if (!isarr(ap)) return; tp = (Array *) ap->sval; if (tp == NULL) return; for (i = 0; i < tp->size; i++) { for (cp = tp->tab[i]; cp != NULL; cp = temp) { xfree(cp->nval); if (freeable(cp)) xfree(cp->sval); temp = cp->cnext; /* avoids freeing then using */ free(cp); tp->nelem--; } - tp->tab[i] = NULL; + tp->tab[i] = 0; } if (tp->nelem != 0) WARNING("can't happen: inconsistent element count freeing %s", ap->nval); free(tp->tab); free(tp); } void freeelem(Cell *ap, const char *s) /* free elem s from ap (i.e., ap["s"] */ { Array *tp; Cell *p, *prev = NULL; int h; tp = (Array *) ap->sval; h = hash(s, tp->size); for (p = tp->tab[h]; p != NULL; prev = p, p = p->cnext) if (strcmp(s, p->nval) == 0) { if (prev == NULL) /* 1st one */ tp->tab[h] = p->cnext; else /* middle somewhere */ prev->cnext = p->cnext; if (freeable(p)) xfree(p->sval); free(p->nval); free(p); tp->nelem--; return; } } Cell *setsymtab(const char *n, const char *s, Awkfloat f, unsigned t, Array *tp) { int h; Cell *p; if (n != NULL && (p = lookup(n, tp)) != NULL) { dprintf( ("setsymtab found %p: n=%s s=\"%s\" f=%g t=%o\n", (void*)p, NN(p->nval), NN(p->sval), p->fval, p->tval) ); return(p); } p = (Cell *) malloc(sizeof(Cell)); if (p == NULL) FATAL("out of space for symbol table at %s", n); p->nval = tostring(n); p->sval = s ? tostring(s) : tostring(""); p->fval = f; p->tval = t; p->csub = CUNK; p->ctype = OCELL; tp->nelem++; if (tp->nelem > FULLTAB * tp->size) rehash(tp); h = hash(n, tp->size); p->cnext = tp->tab[h]; tp->tab[h] = p; dprintf( ("setsymtab set %p: n=%s s=\"%s\" f=%g t=%o\n", (void*)p, p->nval, p->sval, p->fval, p->tval) ); return(p); } int hash(const char *s, int n) /* form hash value for string s */ { unsigned hashval; for (hashval = 0; *s != '\0'; s++) hashval = (*s + 31 * hashval); return hashval % n; } void rehash(Array *tp) /* rehash items in small table into big one */ { int i, nh, nsz; Cell *cp, *op, **np; nsz = GROWTAB * tp->size; np = (Cell **) calloc(nsz, sizeof(Cell *)); if (np == NULL) /* can't do it, but can keep running. */ return; /* someone else will run out later. */ for (i = 0; i < tp->size; i++) { for (cp = tp->tab[i]; cp; cp = op) { op = cp->cnext; nh = hash(cp->nval, nsz); cp->cnext = np[nh]; np[nh] = cp; } } free(tp->tab); tp->tab = np; tp->size = nsz; } Cell *lookup(const char *s, Array *tp) /* look for s in tp */ { Cell *p; int h; h = hash(s, tp->size); for (p = tp->tab[h]; p != NULL; p = p->cnext) if (strcmp(s, p->nval) == 0) return(p); /* found it */ return(NULL); /* not found */ } Awkfloat setfval(Cell *vp, Awkfloat f) /* set float val of a Cell */ { int fldno; + f += 0.0; /* normalise negative zero to positive zero */ if ((vp->tval & (NUM | STR)) == 0) funnyvar(vp, "assign to"); if (isfld(vp)) { donerec = 0; /* mark $0 invalid */ fldno = atoi(vp->nval); if (fldno > *NF) newfld(fldno); dprintf( ("setting field %d to %g\n", fldno, f) ); + } else if (&vp->fval == NF) { + donerec = 0; /* mark $0 invalid */ + setlastfld(f); + dprintf( ("setting NF to %g\n", f) ); } else if (isrec(vp)) { donefld = 0; /* mark $1... invalid */ donerec = 1; + } else if (vp == ofsloc) { + if (donerec == 0) + recbld(); } if (freeable(vp)) xfree(vp->sval); /* free any previous string */ - vp->tval &= ~STR; /* mark string invalid */ + vp->tval &= ~(STR|CONVC|CONVO); /* mark string invalid */ + vp->fmt = NULL; vp->tval |= NUM; /* mark number ok */ if (f == -0) /* who would have thought this possible? */ f = 0; dprintf( ("setfval %p: %s = %g, t=%o\n", (void*)vp, NN(vp->nval), f, vp->tval) ); return vp->fval = f; } void funnyvar(Cell *vp, const char *rw) { if (isarr(vp)) FATAL("can't %s %s; it's an array name.", rw, vp->nval); if (vp->tval & FCN) FATAL("can't %s %s; it's a function.", rw, vp->nval); WARNING("funny variable %p: n=%s s=\"%s\" f=%g t=%o", vp, vp->nval, vp->sval, vp->fval, vp->tval); } char *setsval(Cell *vp, const char *s) /* set string val of a Cell */ { char *t; int fldno; + Awkfloat f; dprintf( ("starting setsval %p: %s = \"%s\", t=%o, r,f=%d,%d\n", (void*)vp, NN(vp->nval), s, vp->tval, donerec, donefld) ); if ((vp->tval & (NUM | STR)) == 0) funnyvar(vp, "assign to"); if (isfld(vp)) { donerec = 0; /* mark $0 invalid */ fldno = atoi(vp->nval); if (fldno > *NF) newfld(fldno); - dprintf( ("setting field %d to %s (%p)\n", fldno, s, s) ); + dprintf( ("setting field %d to %s (%p)\n", fldno, s, (void *) s) ); } else if (isrec(vp)) { donefld = 0; /* mark $1... invalid */ donerec = 1; + } else if (vp == ofsloc) { + if (donerec == 0) + recbld(); } - t = tostring(s); /* in case it's self-assign */ + t = s ? tostring(s) : tostring(""); /* in case it's self-assign */ if (freeable(vp)) xfree(vp->sval); - vp->tval &= ~NUM; + vp->tval &= ~(NUM|CONVC|CONVO); vp->tval |= STR; - vp->tval &= ~DONTFREE; + vp->fmt = NULL; + setfree(vp); dprintf( ("setsval %p: %s = \"%s (%p) \", t=%o r,f=%d,%d\n", - (void*)vp, NN(vp->nval), t,t, vp->tval, donerec, donefld) ); - return(vp->sval = t); + (void*)vp, NN(vp->nval), t, (void *) t, vp->tval, donerec, donefld) ); + vp->sval = t; + if (&vp->fval == NF) { + donerec = 0; /* mark $0 invalid */ + f = getfval(vp); + setlastfld(f); + dprintf( ("setting NF to %g\n", f) ); + } + + return(vp->sval); } Awkfloat getfval(Cell *vp) /* get float val of a Cell */ { if ((vp->tval & (NUM | STR)) == 0) funnyvar(vp, "read value of"); if (isfld(vp) && donefld == 0) fldbld(); else if (isrec(vp) && donerec == 0) recbld(); if (!isnum(vp)) { /* not a number */ vp->fval = atof(vp->sval); /* best guess */ if (is_number(vp->sval) && !(vp->tval&CON)) vp->tval |= NUM; /* make NUM only sparingly */ } dprintf( ("getfval %p: %s = %g, t=%o\n", (void*)vp, NN(vp->nval), vp->fval, vp->tval) ); return(vp->fval); } static char *get_str_val(Cell *vp, char **fmt) /* get string val of a Cell */ { - char s[100]; /* BUG: unchecked */ + char s[256]; double dtemp; if ((vp->tval & (NUM | STR)) == 0) funnyvar(vp, "read value of"); if (isfld(vp) && donefld == 0) fldbld(); else if (isrec(vp) && donerec == 0) recbld(); + + /* + * ADR: This is complicated and more fragile than is desirable. + * Retrieving a string value for a number associates the string + * value with the scalar. Previously, the string value was + * sticky, meaning if converted via OFMT that became the value + * (even though POSIX wants it to be via CONVFMT). Or if CONVFMT + * changed after a string value was retrieved, the original value + * was maintained and used. Also not per POSIX. + * + * We work around this design by adding two additional flags, + * CONVC and CONVO, indicating how the string value was + * obtained (via CONVFMT or OFMT) and _also_ maintaining a copy + * of the pointer to the xFMT format string used for the + * conversion. This pointer is only read, **never** dereferenced. + * The next time we do a conversion, if it's coming from the same + * xFMT as last time, and the pointer value is different, we + * know that the xFMT format string changed, and we need to + * redo the conversion. If it's the same, we don't have to. + * + * There are also several cases where we don't do a conversion, + * such as for a field (see the checks below). + */ + + /* Don't duplicate the code for actually updating the value */ +#define update_str_val(vp) \ + { \ + if (freeable(vp)) \ + xfree(vp->sval); \ + if (modf(vp->fval, &dtemp) == 0) /* it's integral */ \ + snprintf(s, sizeof (s), "%.30g", vp->fval); \ + else \ + snprintf(s, sizeof (s), *fmt, vp->fval); \ + vp->sval = tostring(s); \ + vp->tval &= ~DONTFREE; \ + vp->tval |= STR; \ + } + if (isstr(vp) == 0) { - if (freeable(vp)) - xfree(vp->sval); - if (modf(vp->fval, &dtemp) == 0) /* it's integral */ - sprintf(s, "%.30g", vp->fval); - else - sprintf(s, *fmt, vp->fval); - vp->sval = tostring(s); - vp->tval &= ~DONTFREE; - vp->tval |= STR; + update_str_val(vp); + if (fmt == OFMT) { + vp->tval &= ~CONVC; + vp->tval |= CONVO; + } else { + /* CONVFMT */ + vp->tval &= ~CONVO; + vp->tval |= CONVC; + } + vp->fmt = *fmt; + } else if ((vp->tval & DONTFREE) != 0 || ! isnum(vp) || isfld(vp)) { + goto done; + } else if (isstr(vp)) { + if (fmt == OFMT) { + if ((vp->tval & CONVC) != 0 + || ((vp->tval & CONVO) != 0 && vp->fmt != *fmt)) { + update_str_val(vp); + vp->tval &= ~CONVC; + vp->tval |= CONVO; + vp->fmt = *fmt; + } + } else { + /* CONVFMT */ + if ((vp->tval & CONVO) != 0 + || ((vp->tval & CONVC) != 0 && vp->fmt != *fmt)) { + update_str_val(vp); + vp->tval &= ~CONVO; + vp->tval |= CONVC; + vp->fmt = *fmt; + } + } } +done: dprintf( ("getsval %p: %s = \"%s (%p)\", t=%o\n", - (void*)vp, NN(vp->nval), vp->sval, vp->sval, vp->tval) ); + (void*)vp, NN(vp->nval), vp->sval, (void *) vp->sval, vp->tval) ); return(vp->sval); } char *getsval(Cell *vp) /* get string val of a Cell */ { return get_str_val(vp, CONVFMT); } char *getpssval(Cell *vp) /* get string val of a Cell for print */ { return get_str_val(vp, OFMT); } char *tostring(const char *s) /* make a copy of string s */ { char *p; p = (char *) malloc(strlen(s)+1); if (p == NULL) FATAL("out of space in tostring on %s", s); strcpy(p, s); return(p); } char *qstring(const char *is, int delim) /* collect string up to next delim */ { const char *os = is; int c, n; uschar *s = (uschar *) is; uschar *buf, *bp; if ((buf = (uschar *) malloc(strlen(is)+3)) == NULL) FATAL( "out of space in qstring(%s)", s); for (bp = buf; (c = *s) != delim; s++) { if (c == '\n') SYNTAX( "newline in string %.20s...", os ); else if (c != '\\') *bp++ = c; else { /* \something */ c = *++s; if (c == 0) { /* \ at end */ *bp++ = '\\'; break; /* for loop */ } switch (c) { case '\\': *bp++ = '\\'; break; case 'n': *bp++ = '\n'; break; case 't': *bp++ = '\t'; break; case 'b': *bp++ = '\b'; break; case 'f': *bp++ = '\f'; break; case 'r': *bp++ = '\r'; break; default: if (!isdigit(c)) { *bp++ = c; break; } n = c - '0'; if (isdigit(s[1])) { n = 8 * n + *++s - '0'; if (isdigit(s[1])) n = 8 * n + *++s - '0'; } *bp++ = n; break; } } } *bp++ = 0; return (char *) buf; +} + +const char *flags2str(int flags) +{ + static const struct ftab { + const char *name; + int value; + } flagtab[] = { + { "NUM", NUM }, + { "STR", STR }, + { "DONTFREE", DONTFREE }, + { "CON", CON }, + { "ARR", ARR }, + { "FCN", FCN }, + { "FLD", FLD }, + { "REC", REC }, + { "CONVC", CONVC }, + { "CONVO", CONVO }, + { NULL, 0 } + }; + static char buf[100]; + int i; + char *cp = buf; + + for (i = 0; flagtab[i].name != NULL; i++) { + if ((flags & flagtab[i].value) != 0) { + if (cp > buf) + *cp++ = '|'; + strcpy(cp, flagtab[i].name); + cp += strlen(cp); + } + } + + return buf; } Index: head/contrib/one-true-awk =================================================================== --- head/contrib/one-true-awk (revision 348510) +++ head/contrib/one-true-awk (revision 348511) Property changes on: head/contrib/one-true-awk ___________________________________________________________________ Modified: svn:mergeinfo ## -0,0 +0,1 ## Merged /vendor/one-true-awk/dist:r348505