| 1 | # From hankedr@dms.auburn.edu Sun Jan 28 12:25:43 2001
|
|---|
| 2 | # Received: from mail.actcom.co.il [192.114.47.13]
|
|---|
| 3 | # by localhost with POP3 (fetchmail-5.5.0)
|
|---|
| 4 | # for arnold@localhost (single-drop); Sun, 28 Jan 2001 12:25:43 +0200 (IST)
|
|---|
| 5 | # Received: by actcom.co.il (mbox arobbins)
|
|---|
| 6 | # (with Cubic Circle's cucipop (v1.31 1998/05/13) Sun Jan 28 12:27:08 2001)
|
|---|
| 7 | # X-From_: hankedr@dms.auburn.edu Sat Jan 27 15:15:57 2001
|
|---|
| 8 | # Received: from lmail.actcom.co.il by actcom.co.il with ESMTP
|
|---|
| 9 | # (8.9.1a/actcom-0.2) id PAA23801 for <arobbins@actcom.co.il>;
|
|---|
| 10 | # Sat, 27 Jan 2001 15:15:55 +0200 (EET)
|
|---|
| 11 | # (rfc931-sender: lmail.actcom.co.il [192.114.47.13])
|
|---|
| 12 | # Received: from billohost.com (www.billohost.com [209.196.35.10])
|
|---|
| 13 | # by lmail.actcom.co.il (8.9.3/8.9.1) with ESMTP id PAA15998
|
|---|
| 14 | # for <arobbins@actcom.co.il>; Sat, 27 Jan 2001 15:16:27 +0200
|
|---|
| 15 | # Received: from yak.dms.auburn.edu (yak.dms.auburn.edu [131.204.53.2])
|
|---|
| 16 | # by billohost.com (8.9.3/8.9.3) with ESMTP id IAA00467
|
|---|
| 17 | # for <arnold@skeeve.com>; Sat, 27 Jan 2001 08:15:52 -0500
|
|---|
| 18 | # Received: (from hankedr@localhost)
|
|---|
| 19 | # by yak.dms.auburn.edu (8.9.3/8.9.3/Debian/GNU) id HAA24441;
|
|---|
| 20 | # Sat, 27 Jan 2001 07:15:44 -0600
|
|---|
| 21 | # Date: Sat, 27 Jan 2001 07:15:44 -0600
|
|---|
| 22 | # Message-Id: <200101271315.HAA24441@yak.dms.auburn.edu>
|
|---|
| 23 | # From: Darrel Hankerson <hankedr@dms.auburn.edu>
|
|---|
| 24 | # To: arnold@skeeve.com
|
|---|
| 25 | # Subject: [stolfi@ic.unicamp.br: Bug in [...]* matching with acute-u]
|
|---|
| 26 | # Mime-Version: 1.0 (generated by tm-edit 7.106)
|
|---|
| 27 | # Content-Type: message/rfc822
|
|---|
| 28 | # Status: R
|
|---|
| 29 | #
|
|---|
| 30 | # From: Jorge Stolfi <stolfi@ic.unicamp.br>
|
|---|
| 31 | # To: bug-gnu-utils@gnu.org
|
|---|
| 32 | # Subject: Bug in [...]* matching with acute-u
|
|---|
| 33 | # MIME-Version: 1.0
|
|---|
| 34 | # Reply-To: stolfi@ic.unicamp.br
|
|---|
| 35 | # X-MIME-Autoconverted: from 8bit to quoted-printable by grande.dcc.unicamp.br id GAA10716
|
|---|
| 36 | # Sender: bug-gnu-utils-admin@gnu.org
|
|---|
| 37 | # Errors-To: bug-gnu-utils-admin@gnu.org
|
|---|
| 38 | # X-BeenThere: bug-gnu-utils@gnu.org
|
|---|
| 39 | # X-Mailman-Version: 2.0
|
|---|
| 40 | # Precedence: bulk
|
|---|
| 41 | # List-Help: <mailto:bug-gnu-utils-request@gnu.org?subject=help>
|
|---|
| 42 | # List-Post: <mailto:bug-gnu-utils@gnu.org>
|
|---|
| 43 | # List-Subscribe: <http://mail.gnu.org/mailman/listinfo/bug-gnu-utils>,
|
|---|
| 44 | # <mailto:bug-gnu-utils-request@gnu.org?subject=subscribe>
|
|---|
| 45 | # List-Id: Bug reports for the GNU utilities <bug-gnu-utils.gnu.org>
|
|---|
| 46 | # List-Unsubscribe: <http://mail.gnu.org/mailman/listinfo/bug-gnu-utils>,
|
|---|
| 47 | # <mailto:bug-gnu-utils-request@gnu.org?subject=unsubscribe>
|
|---|
| 48 | # List-Archive: <http://mail.gnu.org/pipermail/bug-gnu-utils/>
|
|---|
| 49 | # Date: Sat, 27 Jan 2001 06:46:11 -0200 (EDT)
|
|---|
| 50 | # Content-Transfer-Encoding: 8bit
|
|---|
| 51 | # X-MIME-Autoconverted: from quoted-printable to 8bit by manatee.dms.auburn.edu id CAA14936
|
|---|
| 52 | # Content-Type: text/plain; charset=iso-8859-1
|
|---|
| 53 | # <mailto:bug-gnu-utils-request@gnu.org?subject=subscribe>
|
|---|
| 54 | # <mailto:bug-gnu-utils-request@gnu.org?subject=uns
|
|---|
| 55 | # Content-Length: 3137
|
|---|
| 56 | #
|
|---|
| 57 | #
|
|---|
| 58 | #
|
|---|
| 59 | # Hi,
|
|---|
| 60 | #
|
|---|
| 61 | # I think I have run into a bug in gawk's handling of REs of the
|
|---|
| 62 | # form [...]* when the bracketed list includes certain 8-bit characters,
|
|---|
| 63 | # specifically u-acute (octal \372).
|
|---|
| 64 | #
|
|---|
| 65 | # The problem occurs in GNU Awk 3.0.4, both under
|
|---|
| 66 | # Linux 2.2.14-5.0 (intel i686) and SunOS 5.5 (Sun sparc).
|
|---|
| 67 | #
|
|---|
| 68 | # Here is a program that illustrates the bug, and its output.
|
|---|
| 69 | # The first two lines of the output should be equal, shouldn't they?
|
|---|
| 70 | #
|
|---|
| 71 | # ----------------------------------------------------------------------
|
|---|
| 72 | #! /usr/bin/gawk -f
|
|---|
| 73 |
|
|---|
| 74 | BEGIN {
|
|---|
| 75 | s = "bananas and ananases in canaan";
|
|---|
| 76 | t = s; gsub(/[an]*n/, "AN", t); printf "%-8s %s\n", "[an]*n", t;
|
|---|
| 77 | t = s; gsub(/[anú]*n/, "AN", t); printf "%-8s %s\n", "[anú]*n", t;
|
|---|
| 78 | print "";
|
|---|
| 79 | t = s; gsub(/[aú]*n/, "AN", t); printf "%-8s %s\n", "[aú]*n", t;
|
|---|
| 80 | print "";
|
|---|
| 81 | t = s; gsub(/[an]n/, "AN", t); printf "%-8s %s\n", "[an]n", t;
|
|---|
| 82 | t = s; gsub(/[aú]n/, "AN", t); printf "%-8s %s\n", "[aú]n", t;
|
|---|
| 83 | t = s; gsub(/[anú]n/, "AN", t); printf "%-8s %s\n", "[anú]n", t;
|
|---|
| 84 | print "";
|
|---|
| 85 | t = s; gsub(/[an]?n/, "AN", t); printf "%-8s %s\n", "[an]?n", t;
|
|---|
| 86 | t = s; gsub(/[aú]?n/, "AN", t); printf "%-8s %s\n", "[aú]?n", t;
|
|---|
| 87 | t = s; gsub(/[anú]?n/, "AN", t); printf "%-8s %s\n", "[anú]?n", t;
|
|---|
| 88 | print "";
|
|---|
| 89 | t = s; gsub(/[an]+n/, "AN", t); printf "%-8s %s\n", "[an]+n", t;
|
|---|
| 90 | t = s; gsub(/[aú]+n/, "AN", t); printf "%-8s %s\n", "[aú]+n", t;
|
|---|
| 91 | t = s; gsub(/[anú]+n/, "AN", t); printf "%-8s %s\n", "[anú]+n", t;
|
|---|
| 92 | }
|
|---|
| 93 | # ----------------------------------------------------------------------
|
|---|
| 94 | # [an]*n bANas ANd ANases iAN cAN
|
|---|
| 95 | # [anú]*n bananas and ananases in canaan
|
|---|
| 96 | #
|
|---|
| 97 | # [aú]*n bANANas ANd ANANases iAN cANAN
|
|---|
| 98 | #
|
|---|
| 99 | # [an]n bANANas ANd ANANases in cANaAN
|
|---|
| 100 | # [aú]n bANANas ANd ANANases in cANaAN
|
|---|
| 101 | # [anú]n bANANas ANd ANANases in cANaAN
|
|---|
| 102 | #
|
|---|
| 103 | # [an]?n bANANas ANd ANANases iAN cANaAN
|
|---|
| 104 | # [aú]?n bANANas ANd ANANases iAN cANaAN
|
|---|
| 105 | # [anú]?n bANANas ANd ANANases iAN cANaAN
|
|---|
| 106 | #
|
|---|
| 107 | # [an]+n bANas ANd ANases in cAN
|
|---|
| 108 | # [aú]+n bANANas ANd ANANases in cANAN
|
|---|
| 109 | # [anú]+n bananas and ananases in canaan
|
|---|
| 110 | # ----------------------------------------------------------------------
|
|---|
| 111 | #
|
|---|
| 112 | # Apparently the problem is specific to u-acute; I've tried several
|
|---|
| 113 | # other 8-bit characters and they seem to behave as expected.
|
|---|
| 114 | #
|
|---|
| 115 | # By comparing the second and third output lines, it would seem that the
|
|---|
| 116 | # problem involves backtracking out of a partial match of [...]* in
|
|---|
| 117 | # order to match the next sub-expression, when the latter begins with
|
|---|
| 118 | # one of the given characters.
|
|---|
| 119 | #
|
|---|
| 120 | #
|
|---|
| 121 | # All the best,
|
|---|
| 122 | #
|
|---|
| 123 | # --stolfi
|
|---|
| 124 | #
|
|---|
| 125 | # ------------------------------------------------------------------------
|
|---|
| 126 | # Jorge Stolfi | http://www.dcc.unicamp.br/~stolfi | stolfi@dcc.unicamp.br
|
|---|
| 127 | # Institute of Computing (formerly DCC-IMECC) | Wrk +55 (19)3788-5858
|
|---|
| 128 | # Universidade Estadual de Campinas (UNICAMP) | +55 (19)3788-5840
|
|---|
| 129 | # Av. Albert Einstein 1251 - Caixa Postal 6176 | Fax +55 (19)3788-5847
|
|---|
| 130 | # 13083-970 Campinas, SP -- Brazil | Hom +55 (19)3287-4069
|
|---|
| 131 | # ------------------------------------------------------------------------
|
|---|
| 132 | #
|
|---|
| 133 | # _______________________________________________
|
|---|
| 134 | # Bug-gnu-utils mailing list
|
|---|
| 135 | # Bug-gnu-utils@gnu.org
|
|---|
| 136 | # http://mail.gnu.org/mailman/listinfo/bug-gnu-utils
|
|---|
| 137 | #
|
|---|
| 138 | #
|
|---|
