From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from gproxy4-pub.mail.unifiedlayer.com (gproxy4-pub.mail.unifiedlayer.com [69.89.23.142]) by sourceware.org (Postfix) with ESMTPS id 590F33857C7E for ; Thu, 17 Feb 2022 22:05:52 +0000 (GMT) DMARC-Filter: OpenDMARC Filter v1.4.1 sourceware.org 590F33857C7E Authentication-Results: sourceware.org; dmarc=none (p=none dis=none) header.from=tromey.com Authentication-Results: sourceware.org; spf=pass smtp.mailfrom=tromey.com Received: from cmgw11.mail.unifiedlayer.com (unknown [10.0.90.126]) by progateway6.mail.pro1.eigbox.com (Postfix) with ESMTP id BEAEC10047D9A for ; Thu, 17 Feb 2022 22:05:51 +0000 (UTC) Received: from box5379.bluehost.com ([162.241.216.53]) by cmsmtp with ESMTP id KouNnqK4zwm8iKouNnrDyb; Thu, 17 Feb 2022 22:05:51 +0000 X-Authority-Reason: nr=8 X-Authority-Analysis: v=2.4 cv=DpSTREz+ c=1 sm=1 tr=0 ts=620ec6bf a=ApxJNpeYhEAb1aAlGBBbmA==:117 a=ApxJNpeYhEAb1aAlGBBbmA==:17 a=dLZJa+xiwSxG16/P+YVxDGlgEgI=:19 a=oGFeUVbbRNcA:10:nop_rcvd_month_year a=Qbun_eYptAEA:10:endurance_base64_authed_username_1 a=woyHvxjDZUzMLWgaIIsA:9 DKIM-Signature: v=1; a=rsa-sha256; q=dns/txt; c=relaxed/relaxed; d=tromey.com; s=default; h=Content-Transfer-Encoding:MIME-Version:References:In-Reply-To: Message-Id:Date:Subject:Cc:To:From:Sender:Reply-To:Content-Type:Content-ID: Content-Description:Resent-Date:Resent-From:Resent-Sender:Resent-To:Resent-Cc :Resent-Message-ID:List-Id:List-Help:List-Unsubscribe:List-Subscribe: List-Post:List-Owner:List-Archive; bh=gcrnpl8zW8VSv/LMV269QXG5dSqMP9dqnL5WgFNNoAc=; b=D30XMZIW7mdp/rk2Mq8gaplSbl o7HjXO40dnOKHZNfDbEZTA7Nl1DUmZb7vHpqRXdwZNWnI+rKYEyaKj/C7ieYng+XPsCuw9yPdCYfa 2bWaYbAfCIek0xyTWcBijniGr; Received: from 75-166-146-214.hlrn.qwest.net ([75.166.146.214]:41036 helo=prentzel.Home) by box5379.bluehost.com with esmtpsa (TLS1.2) tls TLS_ECDHE_RSA_WITH_AES_256_GCM_SHA384 (Exim 4.94.2) (envelope-from ) id 1nKouM-002A2c-Q8; Thu, 17 Feb 2022 15:05:50 -0700 From: Tom Tromey To: gdb-patches@sourceware.org Cc: Tom Tromey Subject: [PATCH v2 06/18] Fix a latent bug in print_wchar Date: Thu, 17 Feb 2022 15:05:34 -0700 Message-Id: <20220217220547.3874030-7-tom@tromey.com> X-Mailer: git-send-email 2.31.1 In-Reply-To: <20220217220547.3874030-1-tom@tromey.com> References: <20220217220547.3874030-1-tom@tromey.com> MIME-Version: 1.0 Content-Transfer-Encoding: 8bit X-AntiAbuse: This header was added to track abuse, please include it with any abuse report X-AntiAbuse: Primary Hostname - box5379.bluehost.com X-AntiAbuse: Original Domain - sourceware.org X-AntiAbuse: Originator/Caller UID/GID - [47 12] / [47 12] X-AntiAbuse: Sender Address Domain - tromey.com X-BWhitelist: no X-Source-IP: 75.166.146.214 X-Source-L: No X-Exim-ID: 1nKouM-002A2c-Q8 X-Source: X-Source-Args: X-Source-Dir: X-Source-Sender: 75-166-146-214.hlrn.qwest.net (prentzel.Home) [75.166.146.214]:41036 X-Source-Auth: tom+tromey.com X-Email-Count: 12 X-Source-Cap: ZWx5bnJvYmk7ZWx5bnJvYmk7Ym94NTM3OS5ibHVlaG9zdC5jb20= X-Local-Domain: yes X-Spam-Status: No, score=-3031.3 required=5.0 tests=BAYES_00, DKIM_SIGNED, DKIM_VALID, GIT_PATCH_0, JMQ_SPF_NEUTRAL, RCVD_IN_DNSWL_NONE, RCVD_IN_MSPIKE_H2, SPF_HELO_NONE, SPF_PASS, TXREP, T_SCC_BODY_TEXT_LINE autolearn=ham autolearn_force=no version=3.4.4 X-Spam-Checker-Version: SpamAssassin 3.4.4 (2020-01-24) on server2.sourceware.org X-BeenThere: gdb-patches@sourceware.org X-Mailman-Version: 2.1.29 Precedence: list List-Id: Gdb-patches mailing list List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Thu, 17 Feb 2022 22:05:54 -0000 print_wchar keeps track of when escape sequences are emitted, to force an escape sequence if needed by a subsequent character. For example for the string concatenation "\0" "1", gdb will print "\000\061" -- because printing "\0001" might be confusing. However, this code has two errors. First, this logic is not needed for octal escapes, because there is a length limit of 3 for octal escapes, and gdb always prints these with "%.3o". Second, though, this *is* needed for hex escapes, because those do not have a length limit. This patch fixes these problems and adds the appropriate tests. --- gdb/gdb_wchar.h | 4 ++-- gdb/testsuite/gdb.base/charset.exp | 8 ++++++++ gdb/valprint.c | 22 ++++++++++++++-------- 3 files changed, 24 insertions(+), 10 deletions(-) diff --git a/gdb/gdb_wchar.h b/gdb/gdb_wchar.h index ba5baf3a2a0..8c6e4fc9fd6 100644 --- a/gdb/gdb_wchar.h +++ b/gdb/gdb_wchar.h @@ -66,7 +66,7 @@ typedef wint_t gdb_wint_t; #define gdb_wcslen wcslen #define gdb_iswprint iswprint -#define gdb_iswdigit iswdigit +#define gdb_iswxdigit iswxdigit #define gdb_btowc btowc #define gdb_WEOF WEOF @@ -103,7 +103,7 @@ typedef int gdb_wint_t; #define gdb_wcslen strlen #define gdb_iswprint isprint -#define gdb_iswdigit isdigit +#define gdb_iswxdigit isxdigit #define gdb_btowc /* empty */ #define gdb_WEOF EOF diff --git a/gdb/testsuite/gdb.base/charset.exp b/gdb/testsuite/gdb.base/charset.exp index 5df2ec1a8de..359968df696 100644 --- a/gdb/testsuite/gdb.base/charset.exp +++ b/gdb/testsuite/gdb.base/charset.exp @@ -503,6 +503,11 @@ gdb_test "print '\\9'" " = \[0-9\]+ '9'" # An octal escape can only be 3 digits. gdb_test "print \"\\1011\"" " = \"A1\"" +# The final digit does not need to be escaped here. +foreach val {0 1 2 3 4 5 6 7 8 9 a b c d e f} { + gdb_test "print \"\\0\" \"${val}\"" " = \"\\\\000${val}\"" +} + # Tests for wide- or unicode- strings. L is the prefix letter to use, # either "L" (for wide strings), "u" (for UTF-16), or "U" (for UTF-32). # NAME is used in the test names and should be related to the prefix @@ -519,6 +524,9 @@ proc test_wide_or_unicode {L name} { gdb_test "print $L\"\" \"abcdef\" \"g\"" \ "$L\"abcdefg\"" \ "concatenate three strings with empty $name string" + gdb_test "print $L\"\\xffef\" $L\"f\"" \ + "$L\"\\\\xffef\\\\146\"" \ + "test multi-char escape sequence case for $name" gdb_test "print $L'a'" "= \[0-9\]+ $L'a'" \ "basic $name character" diff --git a/gdb/valprint.c b/gdb/valprint.c index 17ad46c87b5..545dfbca73f 100644 --- a/gdb/valprint.c +++ b/gdb/valprint.c @@ -2222,9 +2222,7 @@ print_wchar (gdb_wint_t w, const gdb_byte *orig, break; default: { - if (gdb_iswprint (w) && (!need_escape || (!gdb_iswdigit (w) - && w != LCST ('8') - && w != LCST ('9')))) + if (gdb_iswprint (w) && !(need_escape && gdb_iswxdigit (w))) { gdb_wchar_t wchar = w; @@ -2246,10 +2244,19 @@ print_wchar (gdb_wint_t w, const gdb_byte *orig, /* If the value fits in 3 octal digits, print it that way. Otherwise, print it as a hex escape. */ if (value <= 0777) - xsnprintf (octal, sizeof (octal), "\\%.3o", - (int) (value & 0777)); + { + xsnprintf (octal, sizeof (octal), "\\%.3o", + (int) (value & 0777)); + *need_escapep = false; + } else - xsnprintf (octal, sizeof (octal), "\\x%lx", (long) value); + { + xsnprintf (octal, sizeof (octal), "\\x%lx", (long) value); + /* A hex escape might require the next character + to be escaped, because, unlike with octal, + hex escapes have no length limit. */ + *need_escapep = true; + } append_string_as_wide (octal, output); } /* If we somehow have extra bytes, print them now. */ @@ -2258,11 +2265,10 @@ print_wchar (gdb_wint_t w, const gdb_byte *orig, char octal[5]; xsnprintf (octal, sizeof (octal), "\\%.3o", orig[i] & 0xff); + *need_escapep = false; append_string_as_wide (octal, output); ++i; } - - *need_escapep = true; } break; } -- 2.31.1