From a886e62e977f8b1433cfdd607fe343094c45a307 Mon Sep 17 00:00:00 2001 From: millert Date: Sun, 17 Sep 2023 14:49:44 +0000 Subject: [PATCH] Update to the One True Awk, 2nd edition (Sep 12, 2023). This corresponds to the 2nd edition of "The AWK Programming Language" and adds support for UTF-8 and comma-separated value inputs. --- usr.bin/awk/FIXES | 1417 +--------------------------------------- usr.bin/awk/FIXES.1e | 1429 +++++++++++++++++++++++++++++++++++++++++ usr.bin/awk/LICENSE | 23 + usr.bin/awk/README.md | 78 ++- usr.bin/awk/awk.1 | 17 +- usr.bin/awk/awk.h | 16 +- usr.bin/awk/b.c | 269 ++++++-- usr.bin/awk/lex.c | 27 +- usr.bin/awk/lib.c | 123 +++- usr.bin/awk/main.c | 13 +- usr.bin/awk/proto.h | 7 +- usr.bin/awk/run.c | 560 ++++++++++++++-- usr.bin/awk/tran.c | 10 +- 13 files changed, 2438 insertions(+), 1551 deletions(-) create mode 100644 usr.bin/awk/FIXES.1e create mode 100644 usr.bin/awk/LICENSE diff --git a/usr.bin/awk/FIXES b/usr.bin/awk/FIXES index 8cbd6ac1a09..6c2f1505e96 100644 --- a/usr.bin/awk/FIXES +++ b/usr.bin/awk/FIXES @@ -22,1408 +22,35 @@ 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. +This file lists all bug fixes, changes, etc., made since the +second edition of the AWK book was published in September 2023. -Sep 06, 2023: - Fix edge case where FS is changed on commandline. Thanks to - Gordon Shephard and Miguel Pineiro Jr. +Sep 12, 2023: + Fixed a length error in u8_byte2char that set RSTART to + incorrect (cannot happen) value for EOL match(str, /$/). - Fix regular expression clobbering in the lexer, where lexer does - not make a copy of regexp literals. also makedfa memory leaks have - been plugged. Thanks to Miguel Pineiro Jr. - -Dec 15, 2022: - Force hex escapes in strings to be no more than two characters, - as they already are in regular expressions. This brings internal - consistency, as well as consistency with gawk. Thanks to - Arnold Robbins. -Sep 12, 2022: - adjbuf minlen error (cannot be 0) in cat, resulting in NULL pbuf. - discovered by todd miller. also use-after-free issue with - tempfree in cat, thanks to Miguel Pineiro Jr and valgrind. +----------------------------------------------------------------- -Aug 30, 2022: - Various leaks and use-after-free issues plugged/fixed. - Thanks to Miguel Pineiro Jr. . +[This entry is a summary, not a precise list of changes.] -May 23, 2022: - Memory leak when assigning a string to some of the built-in - variables. allocated string erroneously marked DONTFREE. - Thanks to Miguel Pineiro Jr. . + Added --csv option to enable processing of comma-separated + values inputs. When --csv is enabled, fields are separated + by commas, fields may be quoted with " double quotes, fields + may contain embedded newlines. -Mar 14, 2022: - Historic bug: command-line "name=value" assignment had been - truncating its entry in ARGV. (circa 1989) Thanks to - Miguel Pineiro Jr. . + If no explicit separator argument is provided, split() uses + the setting of --csv to determine how fields are split. -Mar 3, 2022: - Fixed file management memory leak that appears to have been - there since the files array was first initialized with stdin, - stdout, and stderr (circa 1992). Thanks to Miguel Pineiro Jr. - . + Strings may now contain UTF-8 code points (not necessarily + characters). Functions that operate on characters, like + length, substr, index, match, etc., use UTF-8, so the length + of a string of 3 emojis is 3, not 12 as it would be if bytes + were counted. -December 8, 2021: - The error handling in closefile and closeall was mangled. Long - standing warnings had been made fatal and some fatal errors went - undetected. Thanks to Miguel Pineiro Jr. . - -Nov 03, 2021: - getline accesses uninitialized data after getrec() - returns 0 on EOF and leaves the contents of buf unchanged. - Thanks to Volodymyr Gubarkov, and Todd C Miller. - -Oct 12, 2021: - The fix for #83 changed the code to insert 2 chars, but the - call to adjbuf just above it only allows for 1 char. This can - cause a heap buffer overflow. - -July 27, 2021: - As per IEEE Std 1003.1-2008, -F "str" is now consistent with - -v FS="str" when str is null. Thanks to Warner Losh. - -July 24, 2021: - Fix readrec's definition of a record. This fixes an issue - with NetBSD's RS regular expression support that can cause - an infinite read loop. Thanks to Miguel Pineiro Jr. - - Fix regular expression RS ^-anchoring. RS ^-anchoring needs to - know if it is reading the first record of a file. This change - restores a missing line that was overlooked when porting NetBSD's - RS regex functionality. Thanks to Miguel Pineiro Jr. - - Fix size computation in replace_repeat() for special case - REPEAT_WITH_Q. Thanks to Todd C. Miller. - -February 15, 2021: - Small fix so that awk will compile again with g++. Thanks to - Arnold Robbins. - -January 06, 2021: - Fix a decision bug with trailing stuff in lib.c:is_valid_number - after recent changes. Thanks to Ozan Yigit. - -December 18, 2020: - Fix problems converting inf and NaN values in lib.c:is_valid_number. - Enhance number to string conversion to do the right thing for - NaN and inf values. Things are now pretty much the same as in - gawk. (Found a gawk bug while we're at it.) Added a torture - test for these values. Thanks to Arnold Robbins. Allows closing - of PR #101. - -December 15, 2020: - Merge PR #99, which gets the right header for strcasecmp. - Thanks to GitHub user michaelforney. - -December 8, 2020: - Merge PR #98: Disallow hex data. Allow only +nan, -nan, - +inf, -inf (case independent) to give NaN and infinity values. - Improve things so that string to double conversion is only - done once, yielding something of a speedup. This obviate - PR #95. Thanks to Arnold Robbins. - -December 3, 2020: - Fix to argument parsing to avoid printing spurious newlines. - Thanks to Todd Miller. Merges PR #97. - -October 13, 2020: - Add casts before all the calls to malloc/calloc/realloc in order - to get it to compile with g++. Thanks to Arnold Robbins. - -August 16, 2020: - Additional fixes for DJGPP. Thanks to Eli Zaretskii for - the testing. - -August 7, 2020: - Merge PR #93, which adds casts to (void*) for debug prints - using the %p format specifier. Thanks to GitHub user YongHaoWu - ("Chris") for the fixes. - -August 4, 2020: - In run.c, use non-restartable multibyte routines to attain - portability to DJGPP. Should fix Issue 92. Thanks to Albert Wik - for the report and to Todd Miller for the suggested fix. - -July 30, 2020: - Merge PRs 88-91 which fix small bugs. Thanks to Todd Miller and - Tim van der Molen for the fixes. - - In order to make life easier, we move exclusively to bison - as the parser generator. - -July 2, 2020: - Merge PRs 85 and 86 which fix regressions. Thanks to - Tim van der Molen for the fixes. - -June 25, 2020: - Merge PRs 82 and 84. The latter fixes issue #83. Thanks to - Todd Miller and awkfan77. - -June 12, 2020: - Clear errno before calling errcheck to avoid any spurious errors - left over from previous calls that may have set it. Thanks to - Todd Miller for the fix, from PR #80. - - Fix Issue #78 by allowing \r to follow floating point numbers in - lib.c:is_number. Thanks to GitHub user ajcarr for the report - and to Arnold Robbins for the fix. - -June 5, 2020: - In fldbld(), make sure that inputFS is set before trying to - use it. Thanks to Steffen Nurpmeso - for the report. - -May 5, 2020: - Fix checks for compilers that can handle noreturn. Thanks to - GitHub user enh-google for pointing it out. Closes Issue #79. - -April 16, 2020: - Handle old compilers that don't support C11 (for noreturn). - Thanks to Arnold Robbins. - -April 5, 2020: - Use and noreturn instead of GCC attributes. - Thanks to GitHub user awkfan77. Closes PR #77. - -February 28, 2020: - More cleanups from Christos Zoulas: notably backslash continuation - inside strings removes the newline and a fix for RS = "^a". - Fix for address sanitizer-found problem. Thanks to GitHub user - enh-google. - -February 19, 2020: - More small cleanups from Christos Zoulas. - -February 18, 2020: - Additional cleanups from Christos Zoulas. It's no longer necessary - to use the -y flag to bison. - -February 6, 2020: - Additional small cleanups from Christos Zoulas. awk is now - a little more robust about reporting I/O errors upon exit. - -January 31, 2020: - Merge PR #70, which avoids use of variable length arrays. Thanks - to GitHub user michaelforney. Fix issue #60 ({0} in interval - expressions doesn't work). Also get all tests working again. - Thanks to Arnold Robbins. - -January 24, 2020: - A number of small cleanups from Christos Zoulas. Add the close - on exec flag to files/pipes opened for redirection; courtesy of - Arnold Robbins. - -January 19, 2020: - If POSIXLY_CORRECT is set in the environment, then sub and gsub - use POSIX rules for multiple backslashes. This fixes Issue #66, - while maintaining backwards compatibility. - -January 9, 2020: - Input/output errors on closing files are now fatal instead of - mere warnings. Thanks to Martijn Dekker . - -January 5, 2020: - Fix a bug in the concatentation of two string constants into - one done in the grammar. Fixes GitHub issue #61. Thanks - to GitHub user awkfan77 for pointing out the direction for - the fix. New test T.concat added to the test suite. - Fix a few memory leaks reported by valgrind, as well. - -December 27, 2019: - Fix a bug whereby a{0,3} could match four a's. Thanks to - "Anonymous AWK fan" for the report. - -December 11, 2019: - Further printf-related fixes for 32 bit systems. - Thanks again to Christos Zoulas. - -December 8, 2019: - Fix the return value of sprintf("%d") on 32 bit systems. - Thanks to Jim Lowe for the report and to Christos Zoulas - for the fix. - -November 10, 2019: - Convert a number of Boolean integer variables into - actual bools. Convert compile_time variable into an - enum and simplify some of the related code. Thanks - to Arnold Robbins. - -November 8, 2019: - Fix from Ori Bernstein to get UTF-8 characters instead of - bytes when FS = "". This is currently the only bit of - the One True Awk that understands multibyte characters. - From Arnold Robbins, apply some cleanups in the test suite. - -October 25, 2019: - More fixes and cleanups from NetBSD, courtesy of Christos - Zoulas. Merges PRs 54 and 55. - -October 24, 2019: - Import second round of code cleanups from NetBSD. Much thanks - to Christos Zoulas (GitHub user zoulasc). Merges PR 53. - Add an optimization for string concatenation, also from - Christos. - -October 17, 2019: - Import code cleanups from NetBSD. Much thanks to Christos - Zoulas (GitHub user zoulasc). Merges PR 51. - -October 6, 2019: - Import code from NetBSD awk that implements RS as a regular - expression. - -September 10, 2019: - Fixes for various array / memory overruns found via gcc's - -fsanitize=unknown. Thanks to Alexander Richardson (GitHub - user arichardson). Merges PRs 47 and 48. - -July 28, 2019: - Import grammar optimization from NetBSD: Two string constants - concatenated together get turned into a single string. - -July 26, 2019: - Support POSIX-specified C-style escape sequences "\a" (alarm) - and "\v" (vertical tab) in command line arguments and regular - expressions, further to the support for them in strings added on - Apr 9, 1989. These now no longer match as literal "a" and "v" - characters (as they don't on other awk implementations). - Thanks to Martijn Dekker. - -July 17, 2019: - Pull in a number of code cleanups and minor fixes from - Warner Losh's bsd-ota branch. The only user visible change - is the use of random(3) as the random number generator. - Thanks to Warner Losh for collecting all these fixes in - one easy place to get them from. - -July 16, 2019: - Fix field splitting to use FS value as of the time a record - was read or assigned to. Thanks to GitHub user Cody Mello (melloc) - for the fix. (Merged from his branch, via PR #42.) Updated - testdir/T.split per said PR as well. - -June 24, 2019: - Extract awktest.tar into testdir directory. Add some very - simple mechanics to the makefile for running the tests and - for cleaning up. No changes to awk itself. - -June 17, 2019: - Disallow deleting SYMTAB and its elements, which creates - use-after-free bugs. Thanks to GitHub user Cody Mello (melloc) - for the fix. (Merged from PR #43.) - -June 5, 2019: - Allow unmatched right parenthesis in a regular expression to - be treated literally. Fixes Issue #40. Thanks to GitHub user - Warner Losh (bsdimp) for the report. Thanks to Arnold Robbins - for the fix. - -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 Issue #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 Arnold Robbins (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. + Regular expressions are processes as UTF-8. + Unicode literals can be written as \u followed by one + to eight hexadecimal digits. These may appear in strings and + regular expressions. diff --git a/usr.bin/awk/FIXES.1e b/usr.bin/awk/FIXES.1e new file mode 100644 index 00000000000..8cbd6ac1a09 --- /dev/null +++ b/usr.bin/awk/FIXES.1e @@ -0,0 +1,1429 @@ +/**************************************************************** +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. + +Sep 06, 2023: + Fix edge case where FS is changed on commandline. Thanks to + Gordon Shephard and Miguel Pineiro Jr. + + Fix regular expression clobbering in the lexer, where lexer does + not make a copy of regexp literals. also makedfa memory leaks have + been plugged. Thanks to Miguel Pineiro Jr. + +Dec 15, 2022: + Force hex escapes in strings to be no more than two characters, + as they already are in regular expressions. This brings internal + consistency, as well as consistency with gawk. Thanks to + Arnold Robbins. + +Sep 12, 2022: + adjbuf minlen error (cannot be 0) in cat, resulting in NULL pbuf. + discovered by todd miller. also use-after-free issue with + tempfree in cat, thanks to Miguel Pineiro Jr and valgrind. + +Aug 30, 2022: + Various leaks and use-after-free issues plugged/fixed. + Thanks to Miguel Pineiro Jr. . + +May 23, 2022: + Memory leak when assigning a string to some of the built-in + variables. allocated string erroneously marked DONTFREE. + Thanks to Miguel Pineiro Jr. . + +Mar 14, 2022: + Historic bug: command-line "name=value" assignment had been + truncating its entry in ARGV. (circa 1989) Thanks to + Miguel Pineiro Jr. . + +Mar 3, 2022: + Fixed file management memory leak that appears to have been + there since the files array was first initialized with stdin, + stdout, and stderr (circa 1992). Thanks to Miguel Pineiro Jr. + . + +December 8, 2021: + The error handling in closefile and closeall was mangled. Long + standing warnings had been made fatal and some fatal errors went + undetected. Thanks to Miguel Pineiro Jr. . + +Nov 03, 2021: + getline accesses uninitialized data after getrec() + returns 0 on EOF and leaves the contents of buf unchanged. + Thanks to Volodymyr Gubarkov, and Todd C Miller. + +Oct 12, 2021: + The fix for #83 changed the code to insert 2 chars, but the + call to adjbuf just above it only allows for 1 char. This can + cause a heap buffer overflow. + +July 27, 2021: + As per IEEE Std 1003.1-2008, -F "str" is now consistent with + -v FS="str" when str is null. Thanks to Warner Losh. + +July 24, 2021: + Fix readrec's definition of a record. This fixes an issue + with NetBSD's RS regular expression support that can cause + an infinite read loop. Thanks to Miguel Pineiro Jr. + + Fix regular expression RS ^-anchoring. RS ^-anchoring needs to + know if it is reading the first record of a file. This change + restores a missing line that was overlooked when porting NetBSD's + RS regex functionality. Thanks to Miguel Pineiro Jr. + + Fix size computation in replace_repeat() for special case + REPEAT_WITH_Q. Thanks to Todd C. Miller. + +February 15, 2021: + Small fix so that awk will compile again with g++. Thanks to + Arnold Robbins. + +January 06, 2021: + Fix a decision bug with trailing stuff in lib.c:is_valid_number + after recent changes. Thanks to Ozan Yigit. + +December 18, 2020: + Fix problems converting inf and NaN values in lib.c:is_valid_number. + Enhance number to string conversion to do the right thing for + NaN and inf values. Things are now pretty much the same as in + gawk. (Found a gawk bug while we're at it.) Added a torture + test for these values. Thanks to Arnold Robbins. Allows closing + of PR #101. + +December 15, 2020: + Merge PR #99, which gets the right header for strcasecmp. + Thanks to GitHub user michaelforney. + +December 8, 2020: + Merge PR #98: Disallow hex data. Allow only +nan, -nan, + +inf, -inf (case independent) to give NaN and infinity values. + Improve things so that string to double conversion is only + done once, yielding something of a speedup. This obviate + PR #95. Thanks to Arnold Robbins. + +December 3, 2020: + Fix to argument parsing to avoid printing spurious newlines. + Thanks to Todd Miller. Merges PR #97. + +October 13, 2020: + Add casts before all the calls to malloc/calloc/realloc in order + to get it to compile with g++. Thanks to Arnold Robbins. + +August 16, 2020: + Additional fixes for DJGPP. Thanks to Eli Zaretskii for + the testing. + +August 7, 2020: + Merge PR #93, which adds casts to (void*) for debug prints + using the %p format specifier. Thanks to GitHub user YongHaoWu + ("Chris") for the fixes. + +August 4, 2020: + In run.c, use non-restartable multibyte routines to attain + portability to DJGPP. Should fix Issue 92. Thanks to Albert Wik + for the report and to Todd Miller for the suggested fix. + +July 30, 2020: + Merge PRs 88-91 which fix small bugs. Thanks to Todd Miller and + Tim van der Molen for the fixes. + + In order to make life easier, we move exclusively to bison + as the parser generator. + +July 2, 2020: + Merge PRs 85 and 86 which fix regressions. Thanks to + Tim van der Molen for the fixes. + +June 25, 2020: + Merge PRs 82 and 84. The latter fixes issue #83. Thanks to + Todd Miller and awkfan77. + +June 12, 2020: + Clear errno before calling errcheck to avoid any spurious errors + left over from previous calls that may have set it. Thanks to + Todd Miller for the fix, from PR #80. + + Fix Issue #78 by allowing \r to follow floating point numbers in + lib.c:is_number. Thanks to GitHub user ajcarr for the report + and to Arnold Robbins for the fix. + +June 5, 2020: + In fldbld(), make sure that inputFS is set before trying to + use it. Thanks to Steffen Nurpmeso + for the report. + +May 5, 2020: + Fix checks for compilers that can handle noreturn. Thanks to + GitHub user enh-google for pointing it out. Closes Issue #79. + +April 16, 2020: + Handle old compilers that don't support C11 (for noreturn). + Thanks to Arnold Robbins. + +April 5, 2020: + Use and noreturn instead of GCC attributes. + Thanks to GitHub user awkfan77. Closes PR #77. + +February 28, 2020: + More cleanups from Christos Zoulas: notably backslash continuation + inside strings removes the newline and a fix for RS = "^a". + Fix for address sanitizer-found problem. Thanks to GitHub user + enh-google. + +February 19, 2020: + More small cleanups from Christos Zoulas. + +February 18, 2020: + Additional cleanups from Christos Zoulas. It's no longer necessary + to use the -y flag to bison. + +February 6, 2020: + Additional small cleanups from Christos Zoulas. awk is now + a little more robust about reporting I/O errors upon exit. + +January 31, 2020: + Merge PR #70, which avoids use of variable length arrays. Thanks + to GitHub user michaelforney. Fix issue #60 ({0} in interval + expressions doesn't work). Also get all tests working again. + Thanks to Arnold Robbins. + +January 24, 2020: + A number of small cleanups from Christos Zoulas. Add the close + on exec flag to files/pipes opened for redirection; courtesy of + Arnold Robbins. + +January 19, 2020: + If POSIXLY_CORRECT is set in the environment, then sub and gsub + use POSIX rules for multiple backslashes. This fixes Issue #66, + while maintaining backwards compatibility. + +January 9, 2020: + Input/output errors on closing files are now fatal instead of + mere warnings. Thanks to Martijn Dekker . + +January 5, 2020: + Fix a bug in the concatentation of two string constants into + one done in the grammar. Fixes GitHub issue #61. Thanks + to GitHub user awkfan77 for pointing out the direction for + the fix. New test T.concat added to the test suite. + Fix a few memory leaks reported by valgrind, as well. + +December 27, 2019: + Fix a bug whereby a{0,3} could match four a's. Thanks to + "Anonymous AWK fan" for the report. + +December 11, 2019: + Further printf-related fixes for 32 bit systems. + Thanks again to Christos Zoulas. + +December 8, 2019: + Fix the return value of sprintf("%d") on 32 bit systems. + Thanks to Jim Lowe for the report and to Christos Zoulas + for the fix. + +November 10, 2019: + Convert a number of Boolean integer variables into + actual bools. Convert compile_time variable into an + enum and simplify some of the related code. Thanks + to Arnold Robbins. + +November 8, 2019: + Fix from Ori Bernstein to get UTF-8 characters instead of + bytes when FS = "". This is currently the only bit of + the One True Awk that understands multibyte characters. + From Arnold Robbins, apply some cleanups in the test suite. + +October 25, 2019: + More fixes and cleanups from NetBSD, courtesy of Christos + Zoulas. Merges PRs 54 and 55. + +October 24, 2019: + Import second round of code cleanups from NetBSD. Much thanks + to Christos Zoulas (GitHub user zoulasc). Merges PR 53. + Add an optimization for string concatenation, also from + Christos. + +October 17, 2019: + Import code cleanups from NetBSD. Much thanks to Christos + Zoulas (GitHub user zoulasc). Merges PR 51. + +October 6, 2019: + Import code from NetBSD awk that implements RS as a regular + expression. + +September 10, 2019: + Fixes for various array / memory overruns found via gcc's + -fsanitize=unknown. Thanks to Alexander Richardson (GitHub + user arichardson). Merges PRs 47 and 48. + +July 28, 2019: + Import grammar optimization from NetBSD: Two string constants + concatenated together get turned into a single string. + +July 26, 2019: + Support POSIX-specified C-style escape sequences "\a" (alarm) + and "\v" (vertical tab) in command line arguments and regular + expressions, further to the support for them in strings added on + Apr 9, 1989. These now no longer match as literal "a" and "v" + characters (as they don't on other awk implementations). + Thanks to Martijn Dekker. + +July 17, 2019: + Pull in a number of code cleanups and minor fixes from + Warner Losh's bsd-ota branch. The only user visible change + is the use of random(3) as the random number generator. + Thanks to Warner Losh for collecting all these fixes in + one easy place to get them from. + +July 16, 2019: + Fix field splitting to use FS value as of the time a record + was read or assigned to. Thanks to GitHub user Cody Mello (melloc) + for the fix. (Merged from his branch, via PR #42.) Updated + testdir/T.split per said PR as well. + +June 24, 2019: + Extract awktest.tar into testdir directory. Add some very + simple mechanics to the makefile for running the tests and + for cleaning up. No changes to awk itself. + +June 17, 2019: + Disallow deleting SYMTAB and its elements, which creates + use-after-free bugs. Thanks to GitHub user Cody Mello (melloc) + for the fix. (Merged from PR #43.) + +June 5, 2019: + Allow unmatched right parenthesis in a regular expression to + be treated literally. Fixes Issue #40. Thanks to GitHub user + Warner Losh (bsdimp) for the report. Thanks to Arnold Robbins + for the fix. + +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 Issue #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 Arnold Robbins (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. + + diff --git a/usr.bin/awk/LICENSE b/usr.bin/awk/LICENSE new file mode 100644 index 00000000000..07dfd7b73b1 --- /dev/null +++ b/usr.bin/awk/LICENSE @@ -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. +****************************************************************/ diff --git a/usr.bin/awk/README.md b/usr.bin/awk/README.md index c50ac08d547..8de0cfee220 100644 --- a/usr.bin/awk/README.md +++ b/usr.bin/awk/README.md @@ -1,10 +1,40 @@ -$OpenBSD: README.md,v 1.6 2022/01/27 16:58:37 millert Exp $ +$OpenBSD: README.md,v 1.7 2023/09/17 14:49:44 millert Exp $ # The One True Awk This is the version of `awk` described in _The AWK Programming Language_, -by Al Aho, Brian Kernighan, and Peter Weinberger -(Addison-Wesley, 1988, ISBN 0-201-07981-X). +Second Edition, by Al Aho, Brian Kernighan, and Peter Weinberger +(Addison-Wesley, 2024, ISBN-13 978-0138269722, ISBN-10 0138269726). + +## What's New? ## + +This version of Awk handles UTF-8 and comma-separated values (CSV) input. + +### Strings ### + +Functions that process strings now count Unicode code points, not bytes; +this affects `length`, `substr`, `index`, `match`, `split`, +`sub`, `gsub`, and others. Note that code +points are not necessarily characters. + +UTF-8 sequences may appear in literal strings and regular expressions. +Aribtrary characters may be included with `\u` followed by 1 to 8 hexadecimal digits. + +### Regular expressions ### + +Regular expressions may include UTF-8 code points, including `\u`. +Character classes are likely to be limited to about 256 characters +when expanded. + +### CSV ### + +The option `--csv` turns on CSV processing of input: +fields are separated by commas, fields may be quoted with +double-quote (`"`) characters, fields may contain embedded newlines. +In CSV mode, `FS` is ignored. + +If no explicit separator argument is provided, +field-splitting in `split` is determined by CSV mode. ## Copyright @@ -69,22 +99,22 @@ The program itself is created by which should produce a sequence of messages roughly like this: - yacc -d awkgram.y - conflicts: 43 shift/reduce, 85 reduce/reduce - mv y.tab.c ytab.c - mv y.tab.h ytab.h - cc -c ytab.c - cc -c b.c - cc -c main.c - cc -c parse.c - cc maketab.c -o maketab - ./maketab >proctab.c - cc -c proctab.c - cc -c tran.c - cc -c lib.c - cc -c run.c - cc -c lex.c - cc ytab.o b.o main.o parse.o proctab.o tran.o lib.o run.o lex.o -lm + bison -d awkgram.y + awkgram.y: warning: 44 shift/reduce conflicts [-Wconflicts-sr] + awkgram.y: warning: 85 reduce/reduce conflicts [-Wconflicts-rr] + awkgram.y: note: rerun with option '-Wcounterexamples' to generate conflict counterexamples + gcc -g -Wall -pedantic -Wcast-qual -O2 -c -o awkgram.tab.o awkgram.tab.c + gcc -g -Wall -pedantic -Wcast-qual -O2 -c -o b.o b.c + gcc -g -Wall -pedantic -Wcast-qual -O2 -c -o main.o main.c + gcc -g -Wall -pedantic -Wcast-qual -O2 -c -o parse.o parse.c + gcc -g -Wall -pedantic -Wcast-qual -O2 maketab.c -o maketab + ./maketab awkgram.tab.h >proctab.c + gcc -g -Wall -pedantic -Wcast-qual -O2 -c -o proctab.o proctab.c + gcc -g -Wall -pedantic -Wcast-qual -O2 -c -o tran.o tran.c + gcc -g -Wall -pedantic -Wcast-qual -O2 -c -o lib.o lib.c + gcc -g -Wall -pedantic -Wcast-qual -O2 -c -o run.o run.c + gcc -g -Wall -pedantic -Wcast-qual -O2 -c -o lex.o lex.c + gcc -g -Wall -pedantic -Wcast-qual -O2 awkgram.tab.o b.o main.o parse.o proctab.o tran.o lib.o run.o lex.o -lm This produces an executable `a.out`; you will eventually want to move this to some place like `/usr/bin/awk`. @@ -104,14 +134,9 @@ the standard developer tools. You can also use `make CC=g++` to build with the GNU C++ compiler, should you choose to do so. -The version of `malloc` that comes with some systems is sometimes -astonishly slow. If `awk` seems slow, you might try fixing that. -More generally, turning on optimization can significantly improve -`awk`'s speed, perhaps by 1/3 for highest levels. - ## A Note About Releases -We don't usually do releases. +We don't usually do releases. ## A Note About Maintenance @@ -122,5 +147,4 @@ is not at the top of our priority list. #### Last Updated -Sun 23 Jan 2022 03:48:01 PM EST - +Sun Sep 3 09:26:43 EDT 2023 diff --git a/usr.bin/awk/awk.1 b/usr.bin/awk/awk.1 index 7f8395d0912..e2d8208b6ce 100644 --- a/usr.bin/awk/awk.1 +++ b/usr.bin/awk/awk.1 @@ -1,4 +1,4 @@ -.\" $OpenBSD: awk.1,v 1.64 2023/09/15 15:07:08 jsg Exp $ +.\" $OpenBSD: awk.1,v 1.65 2023/09/17 14:49:44 millert Exp $ .\" .\" Copyright (C) Lucent Technologies 1997 .\" All Rights Reserved @@ -22,7 +22,7 @@ .\" ARISING OUT OF OR IN CONNECTION WITH THE USE OR PERFORMANCE OF .\" THIS SOFTWARE. .\" -.Dd $Mdocdate: September 15 2023 $ +.Dd $Mdocdate: September 17 2023 $ .Dt AWK 1 .Os .Sh NAME @@ -33,7 +33,7 @@ .Op Fl safe .Op Fl V .Op Fl d Ns Op Ar n -.Op Fl F Ar fs +.Op Fl F Ar fs | Fl -csv .Op Fl v Ar var Ns = Ns Ar value .Op Ar prog | Fl f Ar progfile .Ar @@ -64,6 +64,14 @@ and is executed at the time it would have been opened if it were a filename. .Pp The options are as follows: .Bl -tag -width "-safe " +.It Fl -csv +Process records using the (more or less) standard comma-separated values +.Pq CSV +format instead of the input field separator. +When the +.Fl -csv +option is specified, attempts to change the input field separator +or record separator are ignored. .It Fl d Ns Op Ar n Debug mode. Set debug level to @@ -1058,4 +1066,5 @@ to it. The scope rules for variables in functions are a botch; the syntax is worse. .Pp -Only eight-bit character sets are handled correctly. +Input is expected to be UTF-8 encoded. +Other multibyte character sets are not handled. diff --git a/usr.bin/awk/awk.h b/usr.bin/awk/awk.h index 1c389ce8c20..bd491ad2908 100644 --- a/usr.bin/awk/awk.h +++ b/usr.bin/awk/awk.h @@ -1,4 +1,4 @@ -/* $OpenBSD: awk.h,v 1.28 2022/09/01 15:21:28 millert Exp $ */ +/* $OpenBSD: awk.h,v 1.29 2023/09/17 14:49:44 millert Exp $ */ /**************************************************************** Copyright (C) Lucent Technologies 1997 All Rights Reserved @@ -80,6 +80,8 @@ extern char **SUBSEP; extern Awkfloat *RSTART; extern Awkfloat *RLENGTH; +extern bool CSV; /* true for csv input */ + extern char *record; /* points to $0 */ extern int lineno; /* line number in awk program */ extern int errorflag; /* 1 if error has occurred */ @@ -236,7 +238,8 @@ extern int pairstack[], paircnt; /* structures used by regular expression matching machinery, mostly b.c: */ -#define NCHARS (256+3) /* 256 handles 8-bit chars; 128 does 7-bit */ +#define NCHARS (1256+3) /* 256 handles 8-bit chars; 128 does 7-bit */ + /* BUG: some overflows (caught) if we use 256 */ /* watch out in match(), etc. */ #define HAT (NCHARS+2) /* matches ^ in regular expr */ #define NSTATES 32 @@ -247,12 +250,19 @@ typedef struct rrow { int i; Node *np; uschar *up; + int *rp; /* rune representation of char class */ } lval; /* because Al stores a pointer in it! */ int *lfollow; } rrow; +typedef struct gtt { /* gototab entry */ + unsigned int ch; + unsigned int state; +} gtt; + typedef struct fa { - unsigned int **gototab; + gtt **gototab; + int gototab_len; uschar *out; uschar *restr; int **posns; diff --git a/usr.bin/awk/b.c b/usr.bin/awk/b.c index e3c45e98094..8601c7465ec 100644 --- a/usr.bin/awk/b.c +++ b/usr.bin/awk/b.c @@ -1,4 +1,4 @@ -/* $OpenBSD: b.c,v 1.37 2021/07/08 21:26:39 millert Exp $ */ +/* $OpenBSD: b.c,v 1.38 2023/09/17 14:49:44 millert Exp $ */ /**************************************************************** Copyright (C) Lucent Technologies 1997 All Rights Reserved @@ -81,6 +81,41 @@ int patlen; fa *fatab[NFA]; int nfatab = 0; /* entries in fatab */ + +/* utf-8 mechanism: + + For most of Awk, utf-8 strings just "work", since they look like + null-terminated sequences of 8-bit bytes. + + Functions like length(), index(), and substr() have to operate + in units of utf-8 characters. The u8_* functions in run.c + handle this. + + Regular expressions are more complicated, since the basic + mechanism of the goto table used 8-bit byte indices into the + gototab entries to compute the next state. Unicode is a lot + bigger, so the gototab entries are now structs with a character + and a next state, and there is a linear search of the characters + to find the state. (Yes, this is slower, by a significant + amount. Tough.) + + Throughout the RE mechanism in b.c, utf-8 characters are + converted to their utf-32 value. This mostly shows up in + cclenter, which expands character class ranges like a-z and now + alpha-omega. The size of a gototab array is still about 256. + This should be dynamic, but for now things work ok for a single + code page of Unicode, which is the most likely case. + + The code changes are localized in run.c and b.c. I have added a + handful of functions to somewhat better hide the implementation, + but a lot more could be done. + + */ + +static int get_gototab(fa*, int, int); +static int set_gototab(fa*, int, int, int); +extern int u8_rune(int *, const uschar *); + static int * intalloc(size_t n, const char *f) { @@ -113,7 +148,7 @@ resizesetvec(const char *f) static void resize_state(fa *f, int state) { - unsigned int **p; + gtt **p; uschar *p2; int **p3; int i, new_count; @@ -123,7 +158,7 @@ resize_state(fa *f, int state) new_count = state + 10; /* needs to be tuned */ - p = (unsigned int **) reallocarray(f->gototab, new_count, sizeof(f->gototab[0])); + p = (gtt **) reallocarray(f->gototab, new_count, sizeof(f->gototab[0])); if (p == NULL) goto out; f->gototab = p; @@ -139,12 +174,13 @@ resize_state(fa *f, int state) f->posns = p3; for (i = f->state_count; i < new_count; ++i) { - f->gototab[i] = (unsigned int *) calloc(NCHARS, sizeof(**f->gototab)); + f->gototab[i] = (gtt *) calloc(NCHARS, sizeof(**f->gototab)); if (f->gototab[i] == NULL) goto out; f->out[i] = 0; f->posns[i] = NULL; } + f->gototab_len = NCHARS; /* should be variable, growable */ f->state_count = new_count; return; out: @@ -239,7 +275,7 @@ int makeinit(fa *f, bool anchor) if ((f->posns[2])[1] == f->accept) f->out[2] = 1; for (i = 0; i < NCHARS; i++) - f->gototab[2][i] = 0; + set_gototab(f, 2, 0, 0); /* f->gototab[2][i] = 0; */ f->curstat = cgoto(f, 2, HAT); if (anchor) { *f->posns[2] = k-1; /* leave out position 0 */ @@ -308,13 +344,13 @@ void freetr(Node *p) /* free parse tree */ /* in the parsing of regular expressions, metacharacters like . have */ /* to be seen literally; \056 is not a metacharacter. */ -int hexstr(const uschar **pp) /* find and eval hex string at pp, return new p */ +int hexstr(const uschar **pp, int max) /* find and eval hex string at pp, return new p */ { /* only pick up one 8-bit byte (2 chars) */ const uschar *p; int n = 0; int i; - for (i = 0, p = *pp; i < 2 && isxdigit(*p); i++, p++) { + for (i = 0, p = *pp; i < max && isxdigit(*p); i++, p++) { if (isdigit(*p)) n = 16 * n + *p - '0'; else if (*p >= 'a' && *p <= 'f') @@ -334,24 +370,28 @@ int quoted(const uschar **pp) /* pick up next thing after a \\ */ const uschar *p = *pp; int c; - if ((c = *p++) == 't') +/* BUG: should advance by utf-8 char even if makes no sense */ + + if ((c = *p++) == 't') { c = '\t'; - else if (c == 'n') + } else if (c == 'n') { c = '\n'; - else if (c == 'f') + } else if (c == 'f') { c = '\f'; - else if (c == 'r') + } else if (c == 'r') { c = '\r'; - else if (c == 'b') + } else if (c == 'b') { c = '\b'; - else if (c == 'v') + } else if (c == 'v') { c = '\v'; - else if (c == 'a') + } else if (c == 'a') { c = '\a'; - else if (c == '\\') + } else if (c == '\\') { c = '\\'; - else if (c == 'x') { /* hexadecimal goo follows */ - c = hexstr(&p); /* this adds a null if number is invalid */ + } else if (c == 'x') { /* 2 hex digits follow */ + c = hexstr(&p, 2); /* this adds a null if number is invalid */ + } else if (c == 'u') { /* unicode char number up to 8 hex digits */ + c = hexstr(&p, 8); } else if (isoctdigit(c)) { /* \d \dd \ddd */ int n = c - '0'; if (isoctdigit(*p)) { @@ -366,50 +406,67 @@ int quoted(const uschar **pp) /* pick up next thing after a \\ */ return c; } -char *cclenter(const char *argp) /* add a character class */ +int *cclenter(const char *argp) /* add a character class */ { int i, c, c2; - const uschar *op, *p = (const uschar *) argp; - uschar *bp; - static uschar *buf = NULL; + int n; + const uschar *p = (const uschar *) argp; + int *bp, *retp; + static int *buf = NULL; static int bufsz = 100; - op = p; - if (buf == NULL && (buf = (uschar *) malloc(bufsz)) == NULL) + if (buf == NULL && (buf = (int *) calloc(bufsz, sizeof(int))) == NULL) FATAL("out of space for character class [%.10s...] 1", p); bp = buf; - for (i = 0; (c = *p++) != 0; ) { + for (i = 0; *p != 0; ) { + n = u8_rune(&c, p); + p += n; if (c == '\\') { c = quoted(&p); } else if (c == '-' && i > 0 && bp[-1] != 0) { if (*p != 0) { c = bp[-1]; - c2 = *p++; + /* c2 = *p++; */ + n = u8_rune(&c2, p); + p += n; if (c2 == '\\') - c2 = quoted(&p); + c2 = quoted(&p); /* BUG: sets p, has to be u8 size */ if (c > c2) { /* empty; ignore */ bp--; i--; continue; } while (c < c2) { - if (!adjbuf((char **) &buf, &bufsz, bp-buf+2, 100, (char **) &bp, "cclenter1")) - FATAL("out of space for character class [%.10s...] 2", p); + if (i >= bufsz) { + buf = (int *) reallocarray(buf, bufsz, sizeof(int) * 2); + if (buf == NULL) + FATAL("out of space for character class [%.10s...] 2", p); + bufsz *= 2; + bp = buf + i; + } *bp++ = ++c; i++; } continue; } } - if (!adjbuf((char **) &buf, &bufsz, bp-buf+2, 100, (char **) &bp, "cclenter2")) - FATAL("out of space for character class [%.10s...] 3", p); + if (i >= bufsz) { + buf = (int *) reallocarray(buf, bufsz, sizeof(int) * 2); + if (buf == NULL) + FATAL("out of space for character class [%.10s...] 2", p); + bufsz *= 2; + bp = buf + i; + } *bp++ = c; i++; } *bp = 0; - DPRINTF("cclenter: in = |%s|, out = |%s|\n", op, buf); - xfree(op); - return (char *) tostring((char *) buf); + /* DPRINTF("cclenter: in = |%s|, out = |%s|\n", op, buf); BUG: can't print array of int */ + /* xfree(op); BUG: what are we freeing here? */ + retp = (int *) calloc(bp-buf+1, sizeof(int)); + for (i = 0; i < bp-buf+1; i++) + retp[i] = buf[i]; + return retp; } void overflo(const char *s) @@ -532,9 +589,9 @@ void follow(Node *v) /* collects leaves that can follow v into setvec */ } } -int member(int c, const char *sarg) /* is c in s? */ +int member(int c, int *sarg) /* is c in s? */ { - const uschar *s = (const uschar *) sarg; + int *s = (int *) sarg; while (*s) if (c == *s++) @@ -542,11 +599,41 @@ int member(int c, const char *sarg) /* is c in s? */ return(0); } +static int get_gototab(fa *f, int state, int ch) /* hide gototab inplementation */ +{ + int i; + for (i = 0; i < f->gototab_len; i++) { + if (f->gototab[state][i].ch == 0) + break; + if (f->gototab[state][i].ch == ch) + return f->gototab[state][i].state; + } + return 0; +} + +static int set_gototab(fa *f, int state, int ch, int val) /* hide gototab inplementation */ +{ + int i; + for (i = 0; i < f->gototab_len; i++) { + if (f->gototab[state][i].ch == 0 || f->gototab[state][i].ch == ch) { + f->gototab[state][i].ch = ch; + f->gototab[state][i].state = val; + return val; + } + } + overflo(__func__); + return val; /* not used anywhere at the moment */ +} + int match(fa *f, const char *p0) /* shortest match ? */ { int s, ns; + int n; + int rune; const uschar *p = (const uschar *) p0; + /* return pmatch(f, p0); does it matter whether longest or shortest? */ + s = f->initstat; assert (s < f->state_count); @@ -554,19 +641,25 @@ int match(fa *f, const char *p0) /* shortest match ? */ return(1); do { /* assert(*p < NCHARS); */ - if ((ns = f->gototab[s][*p]) != 0) + n = u8_rune(&rune, p); + if ((ns = get_gototab(f, s, rune)) != 0) s = ns; else - s = cgoto(f, s, *p); + s = cgoto(f, s, rune); if (f->out[s]) return(1); - } while (*p++ != 0); + if (*p == 0) + break; + p += n; + } while (1); /* was *p++ != 0 */ return(0); } int pmatch(fa *f, const char *p0) /* longest match, for sub */ { int s, ns; + int n; + int rune; const uschar *p = (const uschar *) p0; const uschar *q; @@ -581,10 +674,11 @@ int pmatch(fa *f, const char *p0) /* longest match, for sub */ if (f->out[s]) /* final state */ patlen = q-p; /* assert(*q < NCHARS); */ - if ((ns = f->gototab[s][*q]) != 0) + n = u8_rune(&rune, q); + if ((ns = get_gototab(f, s, rune)) != 0) s = ns; else - s = cgoto(f, s, *q); + s = cgoto(f, s, rune); assert(s < f->state_count); @@ -596,7 +690,11 @@ int pmatch(fa *f, const char *p0) /* longest match, for sub */ else goto nextin; /* no match */ } - } while (*q++ != 0); + if (*q == 0) + break; + q += n; + } while (1); + q++; /* was *q++ */ if (f->out[s]) patlen = q-p-1; /* don't count $ */ if (patlen >= 0) { @@ -605,13 +703,19 @@ int pmatch(fa *f, const char *p0) /* longest match, for sub */ } nextin: s = 2; - } while (*p++); + if (*p == 0) + break; + n = u8_rune(&rune, p); + p += n; + } while (1); /* was *p++ */ return (0); } int nematch(fa *f, const char *p0) /* non-empty match, for sub */ { int s, ns; + int n; + int rune; const uschar *p = (const uschar *) p0; const uschar *q; @@ -626,10 +730,11 @@ int nematch(fa *f, const char *p0) /* non-empty match, for sub */ if (f->out[s]) /* final state */ patlen = q-p; /* assert(*q < NCHARS); */ - if ((ns = f->gototab[s][*q]) != 0) + n = u8_rune(&rune, q); + if ((ns = get_gototab(f, s, rune)) != 0) s = ns; else - s = cgoto(f, s, *q); + s = cgoto(f, s, rune); if (s == 1) { /* no transition */ if (patlen > 0) { patbeg = (const char *) p; @@ -637,7 +742,11 @@ int nematch(fa *f, const char *p0) /* non-empty match, for sub */ } else goto nnextin; /* no nonempty match */ } - } while (*q++ != 0); + if (*q == 0) + break; + q += n; + } while (1); + q++; if (f->out[s]) patlen = q-p-1; /* don't count $ */ if (patlen > 0 ) { @@ -651,6 +760,35 @@ int nematch(fa *f, const char *p0) /* non-empty match, for sub */ return (0); } +static int getrune(FILE *fp, char **pbuf, int *pbufsize, int quantum, + int *curpos, int *lastpos) +{ + int c = 0; + char *buf = *pbuf; + static const int max_bytes = 4; // max multiple bytes in UTF-8 is 4 + int i, rune; + uschar private_buf[max_bytes + 1]; + + for (i = 0; i <= max_bytes; i++) { + if (++*curpos == *lastpos) { + if (*lastpos == *pbufsize) + if (!adjbuf((char **) pbuf, pbufsize, *pbufsize+1, quantum, 0, "getrune")) + FATAL("stream '%.30s...' too long", buf); + buf[(*lastpos)++] = (c = getc(fp)) != EOF ? c : 0; + private_buf[i] = c; + } + if (c == 0 || c < 128 || (c >> 6) == 4) { // 10xxxxxx starts a new character + ungetc(c, fp); + private_buf[i] = 0; + break; + } + } + + u8_rune(& rune, private_buf); + + return rune; +} + /* * NAME @@ -672,6 +810,7 @@ bool fnematch(fa *pfa, FILE *f, char **pbuf, int *pbufsize, int quantum) char *buf = *pbuf; int bufsize = *pbufsize; int c, i, j, k, ns, s; + int rune; s = pfa->initstat; patlen = 0; @@ -695,12 +834,19 @@ bool fnematch(fa *pfa, FILE *f, char **pbuf, int *pbufsize, int quantum) buf[k++] = (c = getc(f)) != EOF ? c : 0; } c = (uschar)buf[j]; - /* assert(c < NCHARS); */ + if (c < 128) + rune = c; + else { + j--; + k--; + ungetc(c, f); + rune = getrune(f, &buf, &bufsize, quantum, &j, &k); + } - if ((ns = pfa->gototab[s][c]) != 0) + if ((ns = get_gototab(pfa, s, rune)) != 0) s = ns; else - s = cgoto(pfa, s, c); + s = cgoto(pfa, s, rune); if (pfa->out[s]) { /* final state */ patlen = j - i + 1; @@ -1026,6 +1172,8 @@ static int repeat(const uschar *reptok, int reptoklen, const uschar *atom, return 0; } +extern int u8_rune(int *, const uschar *); /* run.c; should be in header file */ + int relex(void) /* lexical analyzer for reparse */ { int c, n; @@ -1043,6 +1191,12 @@ int relex(void) /* lexical analyzer for reparse */ rescan: starttok = prestr; + if ((n = u8_rune(&rlxval, prestr)) > 1) { + prestr += n; + starttok = prestr; + return CHAR; + } + switch (c = *prestr++) { case '|': return OR; case '*': return STAR; @@ -1080,10 +1234,15 @@ rescan: } else cflag = 0; - n = 2 * strlen((const char *) prestr)+1; + n = 5 * strlen((const char *) prestr)+1; /* BUG: was 2. what value? */ if (!adjbuf((char **) &buf, &bufsz, n, n, (char **) &bp, "relex1")) FATAL("out of space for reg expr %.10s...", lastre); for (; ; ) { + if ((n = u8_rune(&rlxval, prestr)) > 1) { + for (i = 0; i < n; i++) + *bp++ = *prestr++; + continue; + } if ((c = *prestr++) == '\\') { *bp++ = '\\'; if ((c = *prestr++) == '\0') @@ -1250,7 +1409,7 @@ int cgoto(fa *f, int s, int c) int *p, *q; int i, j, k; - assert(c == HAT || c < NCHARS); + /* assert(c == HAT || c < NCHARS); BUG: seg fault if disable test */ while (f->accept >= maxsetvec) { /* guessing here! */ resizesetvec(__func__); } @@ -1266,8 +1425,8 @@ int cgoto(fa *f, int s, int c) || (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)) { + || (k == CCL && member(c, (int *) f->re[p[i]].lval.rp)) + || (k == NCCL && !member(c, (int *) f->re[p[i]].lval.rp) && c != 0 && c != HAT)) { q = f->re[p[i]].lfollow; for (j = 1; j <= *q; j++) { if (q[j] >= maxsetvec) { @@ -1299,7 +1458,7 @@ int cgoto(fa *f, int s, int c) goto different; /* setvec is state i */ if (c != HAT) - f->gototab[s][c] = i; + set_gototab(f, s, c, i); return i; different:; } @@ -1308,13 +1467,13 @@ int cgoto(fa *f, int s, int c) ++(f->curstat); resize_state(f, f->curstat); for (i = 0; i < NCHARS; i++) - f->gototab[f->curstat][i] = 0; + set_gototab(f, f->curstat, 0, 0); xfree(f->posns[f->curstat]); p = intalloc(setcnt + 1, __func__); f->posns[f->curstat] = p; if (c != HAT) - f->gototab[s][c] = f->curstat; + set_gototab(f, s, c, f->curstat); for (i = 0; i <= setcnt; i++) p[i] = tmpset[i]; if (setvec[f->accept]) diff --git a/usr.bin/awk/lex.c b/usr.bin/awk/lex.c index 9ca1d0dda17..b1f422d4093 100644 --- a/usr.bin/awk/lex.c +++ b/usr.bin/awk/lex.c @@ -1,4 +1,4 @@ -/* $OpenBSD: lex.c,v 1.30 2023/09/10 14:59:00 millert Exp $ */ +/* $OpenBSD: lex.c,v 1.31 2023/09/17 14:49:44 millert Exp $ */ /**************************************************************** Copyright (C) Lucent Technologies 1997 All Rights Reserved @@ -379,6 +379,8 @@ int yylex(void) } } +extern int runetochar(char *str, int c); + int string(void) { int c, n; @@ -426,7 +428,7 @@ int string(void) *bp++ = n; break; - case 'x': /* hex \x0-9a-fA-F + */ + case 'x': /* hex \x0-9a-fA-F (exactly two) */ { int i; @@ -452,6 +454,27 @@ int string(void) break; } + case 'u': /* utf \u0-9a-fA-F (1..8) */ + { + int i; + + n = 0; + for (i = 0; i < 8; i++) { + c = input(); + if (!isxdigit(c) || c == 0) + break; + c = tolower(c); + n *= 16; + if (isdigit(c)) + n += (c - '0'); + else + n += 10 + (c - 'a'); + } + unput(c); + bp += runetochar(bp, n); + break; + } + default: *bp++ = c; break; diff --git a/usr.bin/awk/lib.c b/usr.bin/awk/lib.c index 90d34a7eff1..5749a9d5fb2 100644 --- a/usr.bin/awk/lib.c +++ b/usr.bin/awk/lib.c @@ -1,4 +1,4 @@ -/* $OpenBSD: lib.c,v 1.50 2023/09/10 14:59:00 millert Exp $ */ +/* $OpenBSD: lib.c,v 1.51 2023/09/17 14:49:44 millert Exp $ */ /**************************************************************** Copyright (C) Lucent Technologies 1997 All Rights Reserved @@ -34,6 +34,8 @@ THIS SOFTWARE. #include #include "awk.h" +extern int u8_nextlen(const char *s); + char EMPTY[] = { '\0' }; FILE *infile = NULL; bool innew; /* true = infile has not been read by readrec */ @@ -217,14 +219,19 @@ void nextfile(void) argno++; } +extern int readcsvrec(char **pbuf, int *pbufsize, FILE *inf, bool newflag); + int readrec(char **pbuf, int *pbufsize, FILE *inf, bool newflag) /* read one record into buf */ { - int sep, c, isrec; - char *rr, *buf = *pbuf; + int sep, c, isrec; // POTENTIAL BUG? isrec is a macro in awk.h + char *rr = *pbuf, *buf = *pbuf; int bufsize = *pbufsize; char *rs = getsval(rsloc); - if (*rs && rs[1]) { + if (CSV) { + c = readcsvrec(pbuf, pbufsize, inf, newflag); + isrec = (c == EOF && rr == buf) ? false : true; + } else if (*rs && rs[1]) { bool found; fa *pfa = makedfa(rs, 1); @@ -276,6 +283,51 @@ int readrec(char **pbuf, int *pbufsize, FILE *inf, bool newflag) /* read one rec return isrec; } + +/******************* + * loose ends here: + * \r\n should become \n + * what about bare \r? Excel uses that for embedded newlines + * can't have "" in unquoted fields, according to RFC 4180 +*/ + +int readcsvrec(char **pbuf, int *pbufsize, FILE *inf, bool newflag) /* csv can have \n's */ +{ /* so read a complete record that might be multiple lines */ + int sep, c; + char *rr = *pbuf, *buf = *pbuf; + int bufsize = *pbufsize; + bool in_quote = false; + + sep = '\n'; /* the only separator; have to skip over \n embedded in "..." */ + rr = buf; + while ((c = getc(inf)) != EOF) { + if (c == sep) { + if (! in_quote) + break; + if (rr > buf && rr[-1] == '\r') // remove \r if was \r\n + rr--; + } + + if (rr-buf+1 > bufsize) + if (!adjbuf(&buf, &bufsize, 1+rr-buf, + recsize, &rr, "readcsvrec 1")) + FATAL("input record `%.30s...' too long", buf); + *rr++ = c; + if (c == '"') + in_quote = ! in_quote; + } + if (c == '\n' && rr > buf && rr[-1] == '\r') // remove \r if was \r\n + rr--; + + if (!adjbuf(&buf, &bufsize, 1+rr-buf, recsize, &rr, "readcsvrec 4")) + FATAL("input record `%.30s...' too long", buf); + *rr = 0; + *pbuf = buf; + *pbufsize = bufsize; + DPRINTF("readcsvrec saw <%s>, returns %d\n", buf, c); + return c; +} + char *getargv(int n) /* get ARGV[n] */ { Cell *x; @@ -297,6 +349,9 @@ void setclvar(char *s) /* set var=value from s */ Cell *q; double result; +/* commit f3d9187d4e0f02294fb1b0e31152070506314e67 broke T.argv test */ +/* I don't understand why it was changed. */ + for (p=s; *p != '='; p++) ; e = p; @@ -341,7 +396,7 @@ void fldbld(void) /* create fields from current record */ savefs(); if (strlen(inputFS) > 1) { /* it's a regular expression */ i = refldbld(r, inputFS); - } else if ((sep = *inputFS) == ' ') { /* default whitespace */ + } else if (!CSV && (sep = *inputFS) == ' ') { /* default whitespace */ for (i = 0; ; ) { while (*r == ' ' || *r == '\t' || *r == '\n') r++; @@ -360,26 +415,58 @@ void fldbld(void) /* create fields from current record */ *fr++ = 0; } *fr = 0; - } else if ((sep = *inputFS) == 0) { /* new: FS="" => 1 char/field */ - for (i = 0; *r != '\0'; r += n) { - char buf[MB_LEN_MAX + 1]; - + } else if (CSV) { /* CSV processing. no error handling */ + if (*r != 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; + if (*r == '"' ) { /* start of "..." */ + for (r++ ; *r != '\0'; ) { + if (*r == '"' && r[1] != '\0' && r[1] == '"') { + r += 2; /* doubled quote */ + *fr++ = '"'; + } else if (*r == '"' && (r[1] == '\0' || r[1] == ',')) { + r++; /* skip over closing quote */ + break; + } else { + *fr++ = *r++; + } + } + *fr++ = 0; + } else { /* unquoted field */ + while (*r != ',' && *r != '\0') + *fr++ = *r++; + *fr++ = 0; + } + if (*r++ == 0) + break; + + } + } + *fr = 0; + } else if ((sep = *inputFS) == 0) { /* new: FS="" => 1 char/field */ + for (i = 0; *r != '\0'; ) { + char buf[10]; i++; if (i > nfields) growfldtab(i); if (freeable(fldtab[i])) xfree(fldtab[i]->sval); - n = mblen(r, MB_LEN_MAX); - if (n < 0) - n = 1; - memcpy(buf, r, n); - buf[n] = '\0'; + n = u8_nextlen(r); + for (j = 0; j < n; j++) + buf[j] = *r++; + buf[j] = '\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) + /* subtle case: 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. */ @@ -797,11 +884,11 @@ bool is_valid_number(const char *s, bool trailing_stuff_ok, while (isspace((uschar)*s)) s++; - // no hex floating point, sorry + /* no hex floating point, sorry */ if (s[0] == '0' && tolower((uschar)s[1]) == 'x') return false; - // allow +nan, -nan, +inf, -inf, any other letter, no + /* allow +nan, -nan, +inf, -inf, any other letter, no */ if (s[0] == '+' || s[0] == '-') { is_nan = (strncasecmp(s+1, "nan", 3) == 0); is_inf = (strncasecmp(s+1, "inf", 3) == 0); @@ -835,7 +922,7 @@ convert: if (no_trailing != NULL) *no_trailing = (*ep == '\0'); - // return true if found the end, or trailing stuff is allowed + /* return true if found the end, or trailing stuff is allowed */ retval = *ep == '\0' || trailing_stuff_ok; return retval; diff --git a/usr.bin/awk/main.c b/usr.bin/awk/main.c index 67eeff92394..c6e2d074a95 100644 --- a/usr.bin/awk/main.c +++ b/usr.bin/awk/main.c @@ -1,4 +1,4 @@ -/* $OpenBSD: main.c,v 1.58 2023/09/10 14:59:00 millert Exp $ */ +/* $OpenBSD: main.c,v 1.59 2023/09/17 14:49:44 millert Exp $ */ /**************************************************************** Copyright (C) Lucent Technologies 1997 All Rights Reserved @@ -23,7 +23,7 @@ ARISING OUT OF OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE. ****************************************************************/ -const char *version = "version 20230909"; +const char *version = "version 20230913"; #define DEBUG #include @@ -52,6 +52,7 @@ static size_t maxpfile; /* max program filename */ static size_t npfile; /* number of filenames */ static size_t curpfile; /* current filename */ +bool CSV = false; /* true for csv input */ bool safe = false; /* true => "safe" mode */ bool do_posix = false; /* true => POSIX mode */ @@ -170,6 +171,12 @@ int main(int argc, char *argv[]) argv++; break; } + if (strcmp(argv[1], "--csv") == 0) { /* turn on csv input processing */ + CSV = true; + argc--; + argv++; + continue; + } switch (argv[1][1]) { case 's': if (strcmp(argv[1], "-safe") == 0) @@ -179,7 +186,7 @@ int main(int argc, char *argv[]) fn = getarg(&argc, &argv, "no program filename"); if (npfile >= maxpfile) { maxpfile += 20; - pfile = (char **) realloc(pfile, maxpfile * sizeof(*pfile)); + pfile = (char **) reallocarray(pfile, maxpfile, sizeof(*pfile)); if (pfile == NULL) FATAL("error allocating space for -f options"); } diff --git a/usr.bin/awk/proto.h b/usr.bin/awk/proto.h index 374c5af9451..7d9aa3c24cf 100644 --- a/usr.bin/awk/proto.h +++ b/usr.bin/awk/proto.h @@ -1,4 +1,4 @@ -/* $OpenBSD: proto.h,v 1.21 2023/09/10 14:59:00 millert Exp $ */ +/* $OpenBSD: proto.h,v 1.22 2023/09/17 14:49:44 millert Exp $ */ /**************************************************************** Copyright (C) Lucent Technologies 1997 All Rights Reserved @@ -44,14 +44,13 @@ extern fa *mkdfa(const char *, bool); extern int makeinit(fa *, bool); extern void penter(Node *); extern void freetr(Node *); -extern int hexstr(const uschar **); extern int quoted(const uschar **); -extern char *cclenter(const char *); +extern int *cclenter(const char *); extern noreturn void overflo(const char *); extern void cfoll(fa *, Node *); extern int first(Node *); extern void follow(Node *); -extern int member(int, const char *); +extern int member(int, int *); extern int match(fa *, const char *); extern int pmatch(fa *, const char *); extern int nematch(fa *, const char *); diff --git a/usr.bin/awk/run.c b/usr.bin/awk/run.c index 5d87b43e8e6..6d2658fcb75 100644 --- a/usr.bin/awk/run.c +++ b/usr.bin/awk/run.c @@ -1,4 +1,4 @@ -/* $OpenBSD: run.c,v 1.74 2022/09/21 01:42:59 millert Exp $ */ +/* $OpenBSD: run.c,v 1.75 2023/09/17 14:49:44 millert Exp $ */ /**************************************************************** Copyright (C) Lucent Technologies 1997 All Rights Reserved @@ -27,7 +27,6 @@ THIS SOFTWARE. #include #include #include -#include #include #include #include @@ -41,8 +40,10 @@ THIS SOFTWARE. #include "awk.h" #include "awkgram.tab.h" + static void stdinit(void); static void flush_all(void); +static char *wide_char_to_byte_str(int rune, size_t *outlen); #if 1 #define tempfree(x) do { if (istemp(x)) tfree(x); } while (/*CONSTCOND*/0) @@ -580,11 +581,225 @@ Cell *intest(Node **a, int n) /* a[0] is index (list), a[1] is symtab */ } +/* ======== utf-8 code ========== */ + +/* + * Awk strings can contain ascii, random 8-bit items (eg Latin-1), + * or utf-8. u8_isutf tests whether a string starts with a valid + * utf-8 sequence, and returns 0 if not (e.g., high bit set). + * u8_nextlen returns length of next valid sequence, which is + * 1 for ascii, 2..4 for utf-8, or 1 for high bit non-utf. + * u8_strlen returns length of string in valid utf-8 sequences + * and/or high-bit bytes. Conversion functions go between byte + * number and character number. + * + * In theory, this behaves the same as before for non-utf8 bytes. + * + * Limited checking! This is a potential security hole. + */ + +/* is s the beginning of a valid utf-8 string? */ +/* return length 1..4 if yes, 0 if no */ +int u8_isutf(const char *s) +{ + int n, ret; + unsigned char c; + + c = s[0]; + if (c < 128) + return 1; /* what if it's 0? */ + + n = strlen(s); + if (n >= 2 && ((c>>5) & 0x7) == 0x6 && (s[1] & 0xC0) == 0x80) { + ret = 2; /* 110xxxxx 10xxxxxx */ + } else if (n >= 3 && ((c>>4) & 0xF) == 0xE && (s[1] & 0xC0) == 0x80 + && (s[2] & 0xC0) == 0x80) { + ret = 3; /* 1110xxxx 10xxxxxx 10xxxxxx */ + } else if (n >= 4 && ((c>>3) & 0x1F) == 0x1E && (s[1] & 0xC0) == 0x80 + && (s[2] & 0xC0) == 0x80 && (s[3] & 0xC0) == 0x80) { + ret = 4; /* 11110xxx 10xxxxxx 10xxxxxx 10xxxxxx */ + } else { + ret = 0; + } + return ret; +} + +/* Convert (prefix of) utf8 string to utf-32 rune. */ +/* Sets *rune to the value, returns the length. */ +/* No error checking: watch out. */ +int u8_rune(int *rune, const char *s) +{ + int n, ret; + unsigned char c; + + c = s[0]; + if (c < 128) { + *rune = c; + return 1; + } + + n = strlen(s); + if (n >= 2 && ((c>>5) & 0x7) == 0x6 && (s[1] & 0xC0) == 0x80) { + *rune = ((c & 0x1F) << 6) | (s[1] & 0x3F); /* 110xxxxx 10xxxxxx */ + ret = 2; + } else if (n >= 3 && ((c>>4) & 0xF) == 0xE && (s[1] & 0xC0) == 0x80 + && (s[2] & 0xC0) == 0x80) { + *rune = ((c & 0xF) << 12) | ((s[1] & 0x3F) << 6) | (s[2] & 0x3F); + /* 1110xxxx 10xxxxxx 10xxxxxx */ + ret = 3; + } else if (n >= 4 && ((c>>3) & 0x1F) == 0x1E && (s[1] & 0xC0) == 0x80 + && (s[2] & 0xC0) == 0x80 && (s[3] & 0xC0) == 0x80) { + *rune = ((c & 0x7) << 18) | ((s[1] & 0x3F) << 12) | ((s[2] & 0x3F) << 6) | (s[3] & 0x3F); + /* 11110xxx 10xxxxxx 10xxxxxx 10xxxxxx */ + ret = 4; + } else { + *rune = c; + ret = 1; + } + return ret; /* returns one byte if sequence doesn't look like utf */ +} + +/* return length of next sequence: 1 for ascii or random, 2..4 for valid utf8 */ +int u8_nextlen(const char *s) +{ + int len; + + len = u8_isutf(s); + if (len == 0) + len = 1; + return len; +} + +/* return number of utf characters or single non-utf bytes */ +int u8_strlen(const char *s) +{ + int i, len, n, totlen; + unsigned char c; + + n = strlen(s); + totlen = 0; + for (i = 0; i < n; i += len) { + c = s[i]; + if (c < 128) { + len = 1; + } else { + len = u8_nextlen(&s[i]); + } + totlen++; + if (i > n) + FATAL("bad utf count [%s] n=%d i=%d\n", s, n, i); + } + return totlen; +} + +/* convert utf-8 char number in a string to its byte offset */ +int u8_char2byte(const char *s, int charnum) +{ + int n; + int bytenum = 0; + + while (charnum > 0) { + n = u8_nextlen(s); + s += n; + bytenum += n; + charnum--; + } + return bytenum; +} + +/* convert byte offset in s to utf-8 char number that starts there */ +int u8_byte2char(const char *s, int bytenum) +{ + int i, len, b; + int charnum = 0; /* BUG: what origin? */ + /* should be 0 to match start==0 which means no match */ + + b = strlen(s); + if (bytenum > b) { + return -1; /* ??? */ + } + for (i = 0; i <= bytenum; i += len) { + len = u8_nextlen(s+i); + charnum++; + } + return charnum; +} + +/* runetochar() adapted from rune.c in the Plan 9 distributione */ + +enum +{ + Runeerror = 128, /* from somewhere else */ + Runemax = 0x10FFFF, + + Bit1 = 7, + Bitx = 6, + Bit2 = 5, + Bit3 = 4, + Bit4 = 3, + Bit5 = 2, + + T1 = ((1<<(Bit1+1))-1) ^ 0xFF, /* 0000 0000 */ + Tx = ((1<<(Bitx+1))-1) ^ 0xFF, /* 1000 0000 */ + T2 = ((1<<(Bit2+1))-1) ^ 0xFF, /* 1100 0000 */ + T3 = ((1<<(Bit3+1))-1) ^ 0xFF, /* 1110 0000 */ + T4 = ((1<<(Bit4+1))-1) ^ 0xFF, /* 1111 0000 */ + T5 = ((1<<(Bit5+1))-1) ^ 0xFF, /* 1111 1000 */ + + Rune1 = (1<<(Bit1+0*Bitx))-1, /* 0000 0000 0000 0000 0111 1111 */ + Rune2 = (1<<(Bit2+1*Bitx))-1, /* 0000 0000 0000 0111 1111 1111 */ + Rune3 = (1<<(Bit3+2*Bitx))-1, /* 0000 0000 1111 1111 1111 1111 */ + Rune4 = (1<<(Bit4+3*Bitx))-1, /* 0011 1111 1111 1111 1111 1111 */ + + Maskx = (1< 00-7F */ + if (c <= Rune1) { + str[0] = c; + return 1; + } + + /* two character sequence 00080-007FF => T2 Tx */ + if (c <= Rune2) { + str[0] = T2 | (c >> 1*Bitx); + str[1] = Tx | (c & Maskx); + return 2; + } + + /* three character sequence 00800-0FFFF => T3 Tx Tx */ + if (c > Runemax) + c = Runeerror; + if (c <= Rune3) { + str[0] = T3 | (c >> 2*Bitx); + str[1] = Tx | ((c >> 1*Bitx) & Maskx); + str[2] = Tx | (c & Maskx); + return 3; + } + + /* four character sequence 010000-1FFFFF => T4 Tx Tx Tx */ + str[0] = T4 | (c >> 3*Bitx); + str[1] = Tx | ((c >> 2*Bitx) & Maskx); + str[2] = Tx | ((c >> 1*Bitx) & Maskx); + str[3] = Tx | (c & Maskx); + return 4; +} + + +/* ========== end of utf8 code =========== */ + + + Cell *matchop(Node **a, int n) /* ~ and match() */ { Cell *x, *y; char *s, *t; int i; + int cstart, cpatlen, len; fa *pfa; int (*mf)(fa *, const char *) = match, mode = 0; @@ -605,9 +820,21 @@ Cell *matchop(Node **a, int n) /* ~ and match() */ } tempfree(x); if (n == MATCHFCN) { - int start = patbeg - s + 1; - if (patlen < 0) - start = 0; + int start = patbeg - s + 1; /* origin 1 */ + if (patlen < 0) { + start = 0; /* not found */ + } else { + cstart = u8_byte2char(s, start-1); + cpatlen = 0; + for (i = 0; i < patlen; i += len) { + len = u8_nextlen(patbeg+i); + cpatlen++; + } + + start = cstart; + patlen = cpatlen; + } + setfval(rstartloc, (Awkfloat) start); setfval(rlengthloc, (Awkfloat) patlen); x = gettemp(); @@ -658,10 +885,15 @@ Cell *relop(Node **a, int n) /* a[0 < a[1], etc. */ int i; Cell *x, *y; Awkfloat j; + bool x_is_nan, y_is_nan; x = execute(a[0]); y = execute(a[1]); + x_is_nan = isnan(x->fval); + y_is_nan = isnan(y->fval); if (x->tval&NUM && y->tval&NUM) { + if ((x_is_nan || y_is_nan) && n != NE) + return(False); j = x->fval - y->fval; i = j<0? -1: (j>0? 1: 0); } else { @@ -674,7 +906,8 @@ Cell *relop(Node **a, int n) /* a[0 < a[1], etc. */ else return(False); case LE: if (i<=0) return(True); else return(False); - case NE: if (i!=0) return(True); + case NE: if (x_is_nan && y_is_nan) return(True); + else if (i!=0) return(True); else return(False); case EQ: if (i == 0) return(True); else return(False); @@ -743,6 +976,7 @@ Cell *indirect(Node **a, int n) /* $( a[0] ) */ Cell *substr(Node **a, int nnn) /* substr(a[0], a[1], a[2]) */ { int k, m, n; + int mb, nb; char *s; int temp; Cell *x, *y, *z = NULL; @@ -778,12 +1012,16 @@ Cell *substr(Node **a, int nnn) /* substr(a[0], a[1], a[2]) */ n = 0; else if (n > k - m) n = k - m; + /* m is start, n is length from there */ 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; + mb = u8_char2byte(s, m-1); /* byte offset of start char in s */ + nb = u8_char2byte(s, m-1+n); /* byte offset of end+1 char in s */ + + temp = s[nb]; /* with thanks to John Linderman */ + s[nb] = '\0'; + setsval(y, s + mb); + s[nb] = temp; tempfree(x); return(y); } @@ -804,7 +1042,15 @@ Cell *sindex(Node **a, int nnn) /* index(a[0], a[1]) */ for (q = p1, p2 = s2; *p2 != '\0' && *q == *p2; q++, p2++) continue; if (*p2 == '\0') { - v = (Awkfloat) (p1 - s1 + 1); /* origin 1 */ + /* v = (Awkfloat) (p1 - s1 + 1); origin 1 */ + + /* should be a function: used in match() as well */ + int i, len; + v = 0; + for (i = 0; i < p1-s1+1; i += len) { + len = u8_nextlen(s1+i); + v++; + } break; } } @@ -814,6 +1060,18 @@ Cell *sindex(Node **a, int nnn) /* index(a[0], a[1]) */ return(z); } +int has_utf8(char *s) /* return 1 if s contains any utf-8 (2 bytes or more) character */ +{ + int n; + + for (n = 0; *s != 0; s += n) { + n = u8_nextlen(s); + if (n > 1) + return 1; + } + return 0; +} + #define MAXNUMSIZE 50 int format(char **pbuf, int *pbufsize, const char *s, Node *a) /* printf-like conversions */ @@ -856,7 +1114,6 @@ int format(char **pbuf, int *pbufsize, const char *s, Node *a) /* printf-like co 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; @@ -929,7 +1186,8 @@ int format(char **pbuf, int *pbufsize, const char *s, Node *a) /* printf-like co n = fmtwd; adjbuf(&buf, &bufsize, 1+n+p-buf, recsize, &p, "format5"); switch (flag) { - case '?': snprintf(p, BUFSZ(p), "%s", fmt); /* unknown, so dump it too */ + case '?': + snprintf(p, BUFSZ(p), "%s", fmt); /* unknown, so dump it too */ t = getsval(x); n = strlen(t); if (fmtwd > n) @@ -943,29 +1201,176 @@ int format(char **pbuf, int *pbufsize, const char *s, Node *a) /* printf-like co case 'f': snprintf(p, BUFSZ(p), fmt, getfval(x)); break; case 'd': snprintf(p, BUFSZ(p), fmt, (intmax_t) getfval(x)); break; case 'u': snprintf(p, BUFSZ(p), fmt, (uintmax_t) getfval(x)); break; - case 's': + + 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); - snprintf(p, BUFSZ(p), fmt, t); + /* if simple format or no utf-8 in the string, sprintf works */ + if (!has_utf8(t) || strcmp(fmt,"%s") == 0) { + 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); + snprintf(p, BUFSZ(p), fmt, t); + break; + } + + /* get here if string has utf-8 chars and fmt is not plain %s */ + /* "%-w.ps", where -, w and .p are all optional */ + /* '0' before the w is a flag character */ + /* fmt points at % */ + int ljust = 0, wid = 0, prec = n, pad = 0; + char *f = fmt+1; + if (f[0] == '-') { + ljust = 1; + f++; + } + // flags '0' and '+' are recognized but skipped + if (f[0] == '0') { + f++; + if (f[0] == '+') + f++; + } + if (f[0] == '+') { + f++; + if (f[0] == '0') + f++; + } + if (isdigit((uschar)f[0])) { /* there is a wid */ + wid = strtol(f, &f, 10); + } + if (f[0] == '.') { /* there is a .prec */ + prec = strtol(++f, &f, 10); + } + if (prec > u8_strlen(t)) + prec = u8_strlen(t); + pad = wid>prec ? wid - prec : 0; // has to be >= 0 + int i, k, n; + + if (ljust) { // print prec chars from t, then pad blanks + n = u8_char2byte(t, prec); + for (k = 0; k < n; k++) { + //putchar(t[k]); + *p++ = t[k]; + } + for (i = 0; i < pad; i++) { + //printf(" "); + *p++ = ' '; + } + } else { // print pad blanks, then prec chars from t + for (i = 0; i < pad; i++) { + //printf(" "); + *p++ = ' '; + } + n = u8_char2byte(t, prec); + for (k = 0; k < n; k++) { + //putchar(t[k]); + *p++ = t[k]; + } + } + *p = 0; break; - case 'c': + } + + case 'c': { + /* + * If a numeric value is given, awk should just turn + * it into a character and print it: + * BEGIN { printf("%c\n", 65) } + * prints "A". + * + * But what if the numeric value is > 128 and + * represents a valid Unicode code point?!? We do + * our best to convert it back into UTF-8. If we + * can't, we output the encoding of the Unicode + * "invalid character", 0xFFFD. + */ if (isnum(x)) { - if ((int)getfval(x)) - snprintf(p, BUFSZ(p), fmt, (int) getfval(x)); - else { + int charval = (int) getfval(x); + + if (charval != 0) { + if (charval < 128) + snprintf(p, BUFSZ(p), fmt, charval); + else { + // possible unicode character + size_t count; + char *bs = wide_char_to_byte_str(charval, &count); + + if (bs == NULL) { // invalid character + // use unicode invalid character, 0xFFFD + bs = "\357\277\275"; + count = 3; + } + t = bs; + n = count; + goto format_percent_c; + } + } else { *p++ = '\0'; /* explicit null byte */ *p = '\0'; /* next output will start here */ } - } else + break; + } + t = getsval(x); + n = u8_nextlen(t); + format_percent_c: + if (n < 2) { /* not utf8 */ snprintf(p, BUFSZ(p), fmt, getsval(x)[0]); + break; + } + + // utf8 character, almost same song and dance as for %s + int ljust = 0, wid = 0, prec = n, pad = 0; + char *f = fmt+1; + if (f[0] == '-') { + ljust = 1; + f++; + } + // flags '0' and '+' are recognized but skipped + if (f[0] == '0') { + f++; + if (f[0] == '+') + f++; + } + if (f[0] == '+') { + f++; + if (f[0] == '0') + f++; + } + if (isdigit((uschar)f[0])) { /* there is a wid */ + wid = strtol(f, &f, 10); + } + if (f[0] == '.') { /* there is a .prec */ + prec = strtol(++f, &f, 10); + } + if (prec > 1) // %c --> only one character + prec = 1; + pad = wid>prec ? wid - prec : 0; // has to be >= 0 + int i; + + if (ljust) { // print one char from t, then pad blanks + for (int i = 0; i < n; i++) + *p++ = t[i]; + for (i = 0; i < pad; i++) { + //printf(" "); + *p++ = ' '; + } + } else { // print pad blanks, then prec chars from t + for (i = 0; i < pad; i++) { + //printf(" "); + *p++ = ' '; + } + for (int i = 0; i < n; i++) + *p++ = t[i]; + } + *p = 0; break; + } default: FATAL("can't happen: bad conversion %c in format()", flag); } + tempfree(x); p += strlen(p); s++; @@ -1265,7 +1670,7 @@ Cell *split(Node **a, int nnn) /* split(a[0], a[1], a[2]); a[3] is type */ char *origfs = NULL; int sep; char temp, num[50]; - int n, tempstat, arg3type; + int j, n, tempstat, arg3type; double result; y = execute(a[0]); /* source string */ @@ -1274,20 +1679,22 @@ Cell *split(Node **a, int nnn) /* split(a[0], a[1], a[2]); a[3] is type */ FATAL("out of space in split"); tempfree(y); arg3type = ptoi(a[3]); - if (a[2] == NULL) /* fs string */ + if (a[2] == NULL) { /* BUG: CSV should override implicit fs but not explicit */ fs = getsval(fsloc); - else if (arg3type == STRING) { /* split(str,arr,"string") */ + } else if (arg3type == STRING) { /* split(str,arr,"string") */ x = execute(a[2]); fs = origfs = strdup(getsval(x)); if (fs == NULL) FATAL("out of space in split"); tempfree(x); - } else if (arg3type == REGEXPR) + } else if (arg3type == REGEXPR) { fs = "(regexpr)"; /* split(str,arr,/regexpr/) */ - else + } else { FATAL("illegal type of split"); + } sep = *fs; ap = execute(a[1]); /* array name */ + /* BUG 7/26/22: this appears not to reset array: see C1/asplit */ freesymtab(ap); DPRINTF("split: s=|%s|, a=%s, sep=|%s|\n", s, NN(ap->nval), fs); ap->tval &= ~STR; @@ -1341,7 +1748,41 @@ Cell *split(Node **a, int nnn) /* split(a[0], a[1], a[2]); a[3] is type */ setsymtab(num, s, 0.0, STR, (Array *) ap->sval); spdone: pfa = NULL; - } else if (sep == ' ') { + + } else if (a[2] == NULL && CSV) { /* CSV only if no explicit separator */ + char *newt = (char *) malloc(strlen(s)); /* for building new string; reuse for each field */ + for (;;) { + char *fr = newt; + n++; + if (*s == '"' ) { /* start of "..." */ + for (s++ ; *s != '\0'; ) { + if (*s == '"' && s[1] != '\0' && s[1] == '"') { + s += 2; /* doubled quote */ + *fr++ = '"'; + } else if (*s == '"' && (s[1] == '\0' || s[1] == ',')) { + s++; /* skip over closing quote */ + break; + } else { + *fr++ = *s++; + } + } + *fr++ = 0; + } else { /* unquoted field */ + while (*s != ',' && *s != '\0') + *fr++ = *s++; + *fr++ = 0; + } + snprintf(num, sizeof(num), "%d", n); + if (is_number(newt, &result)) + setsymtab(num, newt, result, STR|NUM, (Array *) ap->sval); + else + setsymtab(num, newt, 0.0, STR, (Array *) ap->sval); + if (*s++ == '\0') + break; + } + free(newt); + + } else if (!CSV && sep == ' ') { /* usual case: split on white space */ for (n = 0; ; ) { #define ISWS(c) ((c) == ' ' || (c) == '\t' || (c) == '\n') while (ISWS(*s)) @@ -1364,19 +1805,25 @@ Cell *split(Node **a, int nnn) /* split(a[0], a[1], a[2]); a[3] is type */ if (*s != '\0') s++; } + } else if (sep == 0) { /* new: split(s, a, "") => 1 char/elem */ - for (n = 0; *s != '\0'; s++) { - char buf[2]; + for (n = 0; *s != '\0'; s += u8_nextlen(s)) { + char buf[10]; n++; snprintf(num, sizeof(num), "%d", n); - buf[0] = *s; - buf[1] = '\0'; + + for (j = 0; j < u8_nextlen(s); j++) { + buf[j] = s[j]; + } + buf[j] = '\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') { + + } else if (*s != '\0') { /* some random single character */ for (;;) { n++; t = s; @@ -1535,6 +1982,7 @@ static char *nawk_convert(const char *s, int (*fun_c)(int), size_t n = 0; wchar_t wc; size_t sz = MB_CUR_MAX; + int unused; if (sz == 1) { buf = tostring(s); @@ -1554,7 +2002,7 @@ static char *nawk_convert(const char *s, int (*fun_c)(int), * doesn't work.) * Increment said variable to avoid a different warning. */ - int unused = wctomb(NULL, L'\0'); + unused = wctomb(NULL, L'\0'); unused++; ps = s; @@ -1629,7 +2077,7 @@ Cell *bltin(Node **a, int n) /* builtin functions. a[0] is type, a[1] is arg lis if (isarr(x)) u = ((Array *) x->sval)->nelem; /* GROT. should be function*/ else - u = strlen(getsval(x)); + u = u8_strlen(getsval(x)); break; case FLOG: errno = 0; @@ -2402,3 +2850,41 @@ void backsub(char **pb_ptr, const char **sptr_ptr) /* handle \\& variations */ *pb_ptr = pb; *sptr_ptr = sptr; } + +static char *wide_char_to_byte_str(int rune, size_t *outlen) +{ + static char buf[5]; + int len; + + if (rune < 0 || rune > 0x10FFFF) + return NULL; + + memset(buf, 0, sizeof(buf)); + + len = 0; + if (rune <= 0x0000007F) { + buf[len++] = rune; + } else if (rune <= 0x000007FF) { + // 110xxxxx 10xxxxxx + buf[len++] = 0xC0 | (rune >> 6); + buf[len++] = 0x80 | (rune & 0x3F); + } else if (rune <= 0x0000FFFF) { + // 1110xxxx 10xxxxxx 10xxxxxx + buf[len++] = 0xE0 | (rune >> 12); + buf[len++] = 0x80 | ((rune >> 6) & 0x3F); + buf[len++] = 0x80 | (rune & 0x3F); + + } else { + // 0x00010000 - 0x10FFFF + // 11110xxx 10xxxxxx 10xxxxxx 10xxxxxx + buf[len++] = 0xF0 | (rune >> 18); + buf[len++] = 0x80 | ((rune >> 12) & 0x3F); + buf[len++] = 0x80 | ((rune >> 6) & 0x3F); + buf[len++] = 0x80 | (rune & 0x3F); + } + + *outlen = len; + buf[len++] = '\0'; + + return buf; +} diff --git a/usr.bin/awk/tran.c b/usr.bin/awk/tran.c index 0e4802ecbf9..0456aed983f 100644 --- a/usr.bin/awk/tran.c +++ b/usr.bin/awk/tran.c @@ -1,4 +1,4 @@ -/* $OpenBSD: tran.c,v 1.36 2022/09/21 01:42:59 millert Exp $ */ +/* $OpenBSD: tran.c,v 1.37 2023/09/17 14:49:44 millert Exp $ */ /**************************************************************** Copyright (C) Lucent Technologies 1997 All Rights Reserved @@ -309,7 +309,7 @@ Awkfloat setfval(Cell *vp, Awkfloat f) /* set float val of a Cell */ } else if (&vp->fval == NF) { donerec = false; /* mark $0 invalid */ setlastfld(f); - DPRINTF("setting NF to %g\n", f); + DPRINTF("setfval: setting NF to %g\n", f); } else if (isrec(vp)) { donefld = false; /* mark $1... invalid */ donerec = true; @@ -349,6 +349,10 @@ char *setsval(Cell *vp, const char *s) /* set string val of a Cell */ (void*)vp, NN(vp->nval), s, vp->tval, donerec, donefld); if ((vp->tval & (NUM | STR)) == 0) funnyvar(vp, "assign to"); + if (CSV && (vp == rsloc)) + WARNING("danger: don't set RS when --csv is in effect"); + if (CSV && (vp == fsloc)) + WARNING("danger: don't set FS when --csv is in effect"); if (isfld(vp)) { donerec = false; /* mark $0 invalid */ fldno = atoi(vp->nval); @@ -376,7 +380,7 @@ char *setsval(Cell *vp, const char *s) /* set string val of a Cell */ donerec = false; /* mark $0 invalid */ f = getfval(vp); setlastfld(f); - DPRINTF("setting NF to %g\n", f); + DPRINTF("setsval: setting NF to %g\n", f); } return(vp->sval); -- 2.20.1