[patch] 0001-improvements-to-AC_INIT-argument-quoting.patch

0001-improvements-to-AC_INIT-argument-quoting.patch (text/plain), 22.30 KB, created by Michael Orlitzky on 2020-10-17 19:41:20 UTC

From 8a4571772a5aadc7a005eb288f66ed52b5f52eef Mon Sep 17 00:00:00 2001
From: Zack Weinberg <[e-mail]>
Date: Wed, 14 Oct 2020 18:03:21 -0400
Subject: [PATCH 1/1] improvements to AC_INIT argument quoting

---
 doc/autoconf.texi       |  33 ++++---
 lib/autoconf/general.m4 | 149 +++++++++++++++-----------------
 lib/autoconf/status.m4  |  29 ++++---
 tests/base.at           | 184 +++++++++++++++++++++++++++++++++++++---
 4 files changed, 279 insertions(+), 116 deletions(-)

diff --git a/doc/autoconf.texi b/doc/autoconf.texi
index 9a52fbdb..a89f1469 100644
--- a/doc/autoconf.texi
+++ b/doc/autoconf.texi
@@ -1876,21 +1876,24 @@ distribution tar ball names (e.g., @samp{autoconf}).  It defaults to
 other than alphanumerics and underscores are changed to @samp{-}.  If
 provided, @var{url} should be the home page for the package.
 
-All the arguments of @code{AC_INIT} must be static, i.e., there should not
-be any shell computation, quotes, or newlines, but they can be computed
-by M4.  This is because the package information strings are expanded at
-M4 time into several contexts, and must give the same text at shell time
-whether used in single-quoted strings, double-quoted strings, quoted
-here-documents, or unquoted here-documents.  It is permissible to use
-@code{m4_esyscmd} or @code{m4_esyscmd_s} for computing a version string
-that changes with every commit to a version control system (in fact,
-Autoconf does just that, for all builds of the development tree made
-between releases).
+Leading and trailing whitespace is stripped from all the arguments to
+@code{AC_INIT}, and interior whitespace is collapsed to a single space.
+
+The arguments to @code{AC_INIT} may be computed by M4, when
+@command{autoconf} is run.  For instance, it is fine for the
+@var{version} argument to be an invocation of @code{m4_esyscmd} that
+runs a command that determines the package's version from information
+stored in the package's version control system.  However, they may not
+be computed by the shell, when @command{configure} is run; if they
+contain any construct that would cause computation by the shell,
+Autoconf will issue an error.  This restriction is because the arguments
+to AC_INIT are written into @file{configure} several times, in different
+places, only some of which are subject to shell variable and command
+substitution.
 
 The @var{tarname} argument is used to construct filenames.
-In addition to being static, it should not contain wildcard
-characters, white space, or anything else that could be troublesome
-as part of a file or directory name.
+It should not contain wildcard characters, white space, or anything else
+that could be troublesome as part of a file or directory name.
 
 The following M4 macros (e.g., @code{AC_PACKAGE_NAME}), output variables
 (e.g., @code{PACKAGE_NAME}), and preprocessor symbols (e.g.,
@@ -1947,6 +1950,10 @@ of updating @samp{$@@} and @samp{$*}.  However, we suggest that you use
 standard macros like @code{AC_ARG_ENABLE} instead of attempting to
 implement your own option processing.  @xref{Site Configuration}.
 
+If you use the @code{AC_PACKAGE} M4 macros, beware that they may contain
+characters that are significant to M4.  In almost all cases, you should
+refer to them using @code{m4_defn}.  @xref{Programming in M4sugar}.
+
 @node Versioning
 @section Dealing with Autoconf versions
 @cindex Autoconf version
diff --git a/lib/autoconf/general.m4 b/lib/autoconf/general.m4
index eaa1d91b..5955b672 100644
--- a/lib/autoconf/general.m4
+++ b/lib/autoconf/general.m4
@@ -230,56 +230,47 @@ m4_define([_AC_INIT_LITERAL],
 
 # _AC_INIT_PACKAGE(PACKAGE-NAME, VERSION, BUG-REPORT, [TARNAME], [URL])
 # ---------------------------------------------------------------------
+# Set the values of AC_PACKAGE_{NAME,VERSION,STRING,BUGREPORT,TARNAME,URL}
+# from the arguments.
 m4_define([_AC_INIT_PACKAGE],
-[m4_pushdef([_ac_init_NAME],     m4_normalize([$1]))
-m4_pushdef([_ac_init_VERSION],   m4_normalize([$2]))
-m4_pushdef([_ac_init_BUGREPORT], m4_normalize([$3]))
-m4_pushdef([_ac_init_TARNAME],   m4_normalize([$4]))
-m4_pushdef([_ac_init_URL],       m4_normalize([$5]))
-# NAME, VERSION, BUGREPORT, and URL should all be safe for use in shell
-# strings of all kinds.
-_AC_INIT_LITERAL(m4_defn([_ac_init_NAME]))
-_AC_INIT_LITERAL(m4_defn([_ac_init_VERSION]))
-_AC_INIT_LITERAL(m4_defn([_ac_init_BUGREPORT]))
-_AC_INIT_LITERAL(m4_defn([_ac_init_URL]))
+[_AC_INIT_PACKAGE_N(m4_normalize([$1]), m4_normalize([$2]), m4_normalize([$3]),
+                    m4_normalize([$4]), m4_normalize([$5]))])
+
+# _AC_INIT_PACKAGE_N(PACKAGE-NAME, VERSION, BUG-REPORT, [TARNAME], [URL])
+# -----------------------------------------------------------------------
+# Subroutine of _AC_INIT_PACKAGE.
+m4_define([_AC_INIT_PACKAGE_N],
+[# PACKAGE-NAME, VERSION, BUGREPORT, and URL should all be safe for use
+# in shell strings of all kinds.
+_AC_INIT_LITERAL([$1])
+_AC_INIT_LITERAL([$2])
+_AC_INIT_LITERAL([$3])
+_AC_INIT_LITERAL([$5])
 # TARNAME is even more constrained: it should not contain any shell
 # metacharacters or whitespace, because it is used to construct
 # filenames.
-AS_LITERAL_WORD_IF(m4_defn([_ac_init_TARNAME]), [],
+AS_LITERAL_WORD_IF([$4], [],
   [m4_warn([syntax],
-	   [AC_INIT: unsafe as a filename: "]m4_defn([_ac_init_TARNAME])["])])
+	   [AC_INIT: unsafe as a filename: "$4"])])
 #
-# These do not use m4_copy because we don't want to copy the pushdef stack.
-m4_ifndef([AC_PACKAGE_NAME],
-	  [m4_define([AC_PACKAGE_NAME],
-		     m4_defn([_ac_init_NAME]))])
-m4_ifndef([AC_PACKAGE_VERSION],
-	  [m4_define([AC_PACKAGE_VERSION],
-		     m4_defn([_ac_init_VERSION]))])
-m4_ifndef([AC_PACKAGE_STRING],
-	  [m4_define([AC_PACKAGE_STRING],
-		     m4_defn([_ac_init_NAME])[ ]m4_defn([_ac_init_VERSION]))])
-m4_ifndef([AC_PACKAGE_BUGREPORT],
-	  [m4_define([AC_PACKAGE_BUGREPORT], _ac_init_BUGREPORT)])
-m4_ifndef([AC_PACKAGE_TARNAME],
-	  [m4_define([AC_PACKAGE_TARNAME],
-		     m4_default(m4_defn([_ac_init_TARNAME]),
-				[m4_bpatsubst(m4_tolower(
-				 m4_bpatsubst(m4_defn([_ac_init_NAME]),
-					      [GNU ])),
-				 [[^_abcdefghijklmnopqrstuvwxyz0123456789]],
-				 [-])]))])
-m4_ifndef([AC_PACKAGE_URL],
-	  [m4_define([AC_PACKAGE_URL],
-		     m4_default(m4_defn([_ac_init_URL]),
-				[m4_if(m4_index(m4_defn([_ac_init_NAME]),
-						[GNU ]), [0],
-    [[https://www.gnu.org/software/]m4_defn([AC_PACKAGE_TARNAME])[/]])]))])
-m4_popdef([_ac_init_NAME])
-m4_popdef([_ac_init_VERSION])
-m4_popdef([_ac_init_BUGREPORT])
-m4_popdef([_ac_init_TARNAME])
-m4_popdef([_ac_init_URL])
+m4_define_default([AC_PACKAGE_NAME],      [$1])
+m4_define_default([AC_PACKAGE_VERSION],   [$2])
+# The m4_strip makes AC_PACKAGE_STRING be [], not [ ], when
+# both $1 and $2 are empty.
+m4_define_default([AC_PACKAGE_STRING],    m4_strip([$1 $2]))
+m4_define_default([AC_PACKAGE_BUGREPORT], [$3])
+#
+# N.B. m4_ifnblank strips one layer of quotation from whichever of its
+# second and third argument it evaluates to.
+m4_define_default([AC_PACKAGE_TARNAME],
+  m4_ifnblank([$4], [[$4]],
+    [m4_quote(m4_bpatsubst(m4_tolower(m4_bpatsubst([$1], [^GNU ], [])),
+      [[^_abcdefghijklmnopqrstuvwxyz0123456789]], [-]))]))
+m4_define_default([AC_PACKAGE_URL],
+  m4_ifnblank([$5], [[$5]],
+    [m4_if(m4_index([$1], [GNU ]), [0],
+      [[https://www.gnu.org/software/]m4_defn([AC_PACKAGE_TARNAME])[/]],
+      [])]))
 ])
 
 
@@ -363,13 +354,13 @@ m4_define([_AC_INIT_NOTICE],
 [m4_divert_text([HEADER-COMMENT],
 [@%:@ Guess values for system-dependent variables and create Makefiles.
 @%:@ Generated by m4_PACKAGE_STRING[]dnl
-m4_ifset([AC_PACKAGE_STRING], [ for AC_PACKAGE_STRING]).])
-
+m4_ifset([AC_PACKAGE_STRING], [ for m4_defn([AC_PACKAGE_STRING]).
+])dnl
 m4_ifset([AC_PACKAGE_BUGREPORT],
 	 [m4_divert_text([HEADER-COMMENT],
 			 [@%:@
-@%:@ Report bugs to <AC_PACKAGE_BUGREPORT>.])])
-])
+@%:@ Report bugs to: m4_defn([AC_PACKAGE_BUGREPORT])])])
+])])
 
 
 # _AC_INIT_COPYRIGHT
@@ -436,18 +427,12 @@ AC_SUBST([SHELL])dnl
 AC_SUBST([PATH_SEPARATOR])dnl
 
 # Identity of this package.
-AC_SUBST([PACKAGE_NAME],
-	 [m4_ifdef([AC_PACKAGE_NAME],      ['AC_PACKAGE_NAME'])])dnl
-AC_SUBST([PACKAGE_TARNAME],
-	 [m4_ifdef([AC_PACKAGE_TARNAME],   ['AC_PACKAGE_TARNAME'])])dnl
-AC_SUBST([PACKAGE_VERSION],
-	 [m4_ifdef([AC_PACKAGE_VERSION],   ['AC_PACKAGE_VERSION'])])dnl
-AC_SUBST([PACKAGE_STRING],
-	 [m4_ifdef([AC_PACKAGE_STRING],    ['AC_PACKAGE_STRING'])])dnl
-AC_SUBST([PACKAGE_BUGREPORT],
-	 [m4_ifdef([AC_PACKAGE_BUGREPORT], ['AC_PACKAGE_BUGREPORT'])])dnl
-AC_SUBST([PACKAGE_URL],
-	 [m4_ifdef([AC_PACKAGE_URL],       ['AC_PACKAGE_URL'])])dnl
+AC_SUBST([PACKAGE_NAME],      ['m4_defn([AC_PACKAGE_NAME])'])dnl
+AC_SUBST([PACKAGE_TARNAME],   ['m4_defn([AC_PACKAGE_TARNAME])'])dnl
+AC_SUBST([PACKAGE_VERSION],   ['m4_defn([AC_PACKAGE_VERSION])'])dnl
+AC_SUBST([PACKAGE_STRING],    ['m4_defn([AC_PACKAGE_STRING])'])dnl
+AC_SUBST([PACKAGE_BUGREPORT], ['m4_defn([AC_PACKAGE_BUGREPORT])'])dnl
+AC_SUBST([PACKAGE_URL],       ['m4_defn([AC_PACKAGE_URL])'])dnl
 
 m4_divert_pop([DEFAULTS])dnl
 m4_wrap_lifo([m4_divert_text([DEFAULTS],
@@ -1048,9 +1033,9 @@ if test "$ac_init_help" = "long"; then
   # Omit some internal or obsolete options to make the list less imposing.
   # This message is too long to be a string in the A/UX 3.1 sh.
   cat <<_ACEOF
-\`configure' configures m4_ifset([AC_PACKAGE_STRING],
-			[AC_PACKAGE_STRING],
-			[this package]) to adapt to many kinds of systems.
+\`configure' configures m4_default_nblank(m4_defn([AC_PACKAGE_STRING]),
+					  [this package])dnl
+ to adapt to many kinds of systems.
 
 Usage: $[0] [[OPTION]]... [[VAR=VALUE]]...
 
@@ -1099,9 +1084,8 @@ Fine tuning of the installation directories:
   --infodir=DIR           info documentation [DATAROOTDIR/info]
   --localedir=DIR         locale-dependent data [DATAROOTDIR/locale]
   --mandir=DIR            man documentation [DATAROOTDIR/man]
-]AS_HELP_STRING([--docdir=DIR],
-  [documentation root ]@<:@DATAROOTDIR/doc/m4_ifset([AC_PACKAGE_TARNAME],
-    [AC_PACKAGE_TARNAME], [PACKAGE])@:>@)[
+  --docdir=DIR            documentation root @<:@DATAROOTDIR/doc/]dnl
+m4_default_quoted(m4_defn([AC_PACKAGE_TARNAME]), [PACKAGE])[@:>@
   --htmldir=DIR           html documentation [DOCDIR]
   --dvidir=DIR            dvi documentation [DOCDIR]
   --pdfdir=DIR            pdf documentation [DOCDIR]
@@ -1139,18 +1123,22 @@ fi
 if test -n "$ac_init_help"; then
 m4_ifset([AC_PACKAGE_STRING],
 [  case $ac_init_help in
-     short | recursive ) echo "Configuration of AC_PACKAGE_STRING:";;
+     short | recursive )
+       AS_ECHO(["Configuration of m4_defn([AC_PACKAGE_STRING]):"]);;
    esac])
   cat <<\_ACEOF
 m4_divert_pop([HELP_ENABLE])dnl
 m4_divert_push([HELP_END])dnl
 
-Report bugs to m4_ifset([AC_PACKAGE_BUGREPORT], [<AC_PACKAGE_BUGREPORT>],
-  [the package provider]).dnl
-m4_ifdef([AC_PACKAGE_NAME], [m4_ifset([AC_PACKAGE_URL], [
-AC_PACKAGE_NAME home page: <AC_PACKAGE_URL>.])dnl
-m4_if(m4_index(m4_defn([AC_PACKAGE_NAME]), [GNU ]), [0], [
-General help using GNU software: <https://www.gnu.org/gethelp/>.])])
+m4_ifset([AC_PACKAGE_BUGREPORT],
+[Report bugs to: m4_defn([AC_PACKAGE_BUGREPORT])
+])dnl
+m4_ifset([AC_PACKAGE_NAME], [m4_ifset([AC_PACKAGE_URL],
+[m4_defn([AC_PACKAGE_NAME]) home page: m4_defn([AC_PACKAGE_URL])
+])])dnl
+m4_if(m4_index(m4_defn([AC_PACKAGE_NAME]), [GNU ]), [0],
+[General help using GNU software: <https://www.gnu.org/gethelp/>.
+])dnl
 _ACEOF
 ac_status=$?
 fi
@@ -1189,9 +1177,9 @@ m4_define([_AC_INIT_VERSION],
 [m4_divert_text([VERSION_BEGIN],
 [if $ac_init_version; then
   cat <<\_ACEOF
-m4_ifset([AC_PACKAGE_NAME], [AC_PACKAGE_NAME ])configure[]dnl
-m4_ifset([AC_PACKAGE_VERSION], [ AC_PACKAGE_VERSION])
-generated by m4_PACKAGE_STRING])
+m4_ifset([AC_PACKAGE_NAME], [m4_defn([AC_PACKAGE_NAME]) ])configure[]dnl
+m4_ifset([AC_PACKAGE_VERSION], [ m4_defn([AC_PACKAGE_VERSION])])
+generated by m4_defn([m4_PACKAGE_STRING])])
 m4_divert_text([VERSION_END],
 [_ACEOF
   exit
@@ -1230,9 +1218,10 @@ cat >config.log <<_ACEOF
 This file contains any messages produced by compilers while
 running configure, to aid debugging if configure makes a mistake.
 
-It was created by m4_ifset([AC_PACKAGE_NAME], [AC_PACKAGE_NAME ])dnl
-$as_me[]m4_ifset([AC_PACKAGE_VERSION], [ AC_PACKAGE_VERSION]), which was
-generated by m4_PACKAGE_STRING.  Invocation command line was
+It was created by m4_ifset([AC_PACKAGE_NAME], [m4_defn([AC_PACKAGE_NAME]) ])dnl
+$as_me[]m4_ifset([AC_PACKAGE_VERSION],
+                 [ m4_defn([AC_PACKAGE_VERSION])]), which was
+generated by m4_defn([m4_PACKAGE_STRING]).  Invocation command line was
 
   $ $[0]$ac_configure_args_raw
 
@@ -1446,7 +1435,7 @@ m4_define([_AS_FORCE_REEXEC_WITH_CONFIG_SHELL], [yes])
 AS_INIT[]dnl
 AS_PREPARE[]dnl
 m4_divert_push([KILL])
-m4_ifval([$2], [_AC_INIT_PACKAGE($@)])
+_AC_INIT_PACKAGE($@)
 _AC_INIT_DEFAULTS
 _AC_INIT_PARSE_ARGS
 _AC_INIT_DIRCHECK
diff --git a/lib/autoconf/status.m4 b/lib/autoconf/status.m4
index 1389f328..aa8324f0 100644
--- a/lib/autoconf/status.m4
+++ b/lib/autoconf/status.m4
@@ -1343,9 +1343,11 @@ cat >>$CONFIG_STATUS <<\_ACEOF || ac_write_fail=1
 # report actual input values of CONFIG_FILES etc. instead of their
 # values after options handling.
 ac_log="
-This file was extended by m4_ifset([AC_PACKAGE_NAME], [AC_PACKAGE_NAME ])dnl
-$as_me[]m4_ifset([AC_PACKAGE_VERSION], [ AC_PACKAGE_VERSION]), which was
-generated by m4_PACKAGE_STRING.  Invocation command line was
+This file was extended by m4_ifset([AC_PACKAGE_NAME],
+                                   [m4_defn([AC_PACKAGE_NAME]) ])dnl
+$as_me[]m4_ifset([AC_PACKAGE_VERSION],
+                 [ m4_defn([AC_PACKAGE_VERSION])]), which was
+generated by m4_defn([m4_PACKAGE_STRING]).  Invocation command line was
 
   CONFIG_FILES    = $CONFIG_FILES
   CONFIG_HEADERS  = $CONFIG_HEADERS
@@ -1431,12 +1433,15 @@ m4_ifdef([_AC_SEEN_CONFIG(COMMANDS)],
 $config_commands
 
 ])dnl
-Report bugs to m4_ifset([AC_PACKAGE_BUGREPORT], [<AC_PACKAGE_BUGREPORT>],
-  [the package provider]).dnl
-m4_ifdef([AC_PACKAGE_NAME], [m4_ifset([AC_PACKAGE_URL], [
-AC_PACKAGE_NAME home page: <AC_PACKAGE_URL>.])dnl
-m4_if(m4_index(m4_defn([AC_PACKAGE_NAME]), [GNU ]), [0], [
-General help using GNU software: <https://www.gnu.org/gethelp/>.])])"
+m4_ifset([AC_PACKAGE_BUGREPORT],
+[Report bugs to: m4_defn([AC_PACKAGE_BUGREPORT])
+]))dnl
+m4_ifset([AC_PACKAGE_NAME], [m4_ifset([AC_PACKAGE_URL],
+[m4_defn([AC_PACKAGE_NAME]) home page: m4_defn([AC_PACKAGE_URL])
+])])dnl
+m4_if(m4_index(m4_defn([AC_PACKAGE_NAME]), [GNU ]), [0],
+[General help using GNU software: <https://www.gnu.org/gethelp/>.
+])"
 
 _ACEOF
 ac_cs_config=`AS_ECHO(["$ac_configure_args"]) | sed "$ac_safe_unquote"`
@@ -1444,9 +1449,9 @@ ac_cs_config_escaped=`AS_ECHO(["$ac_cs_config"]) | sed "s/^ //; s/'/'\\\\\\\\''/
 cat >>$CONFIG_STATUS <<_ACEOF || ac_write_fail=1
 ac_cs_config='$ac_cs_config_escaped'
 ac_cs_version="\\
-m4_ifset([AC_PACKAGE_NAME], [AC_PACKAGE_NAME ])config.status[]dnl
-m4_ifset([AC_PACKAGE_VERSION], [ AC_PACKAGE_VERSION])
-configured by $[0], generated by m4_PACKAGE_STRING,
+m4_ifset([AC_PACKAGE_NAME], [m4_defn([AC_PACKAGE_NAME]) ])config.status[]dnl
+m4_ifset([AC_PACKAGE_VERSION], [ m4_defn([AC_PACKAGE_VERSION])])
+configured by $[0], generated by m4_defn([m4_PACKAGE_STRING]),
   with options \\"\$ac_cs_config\\"
 
 Copyright (C) m4_PACKAGE_YEAR Free Software Foundation, Inc.
diff --git a/tests/base.at b/tests/base.at
index 6a1d9742..bc8e1faa 100644
--- a/tests/base.at
+++ b/tests/base.at
@@ -238,36 +238,124 @@ AT_CLEANUP
 
 AT_SETUP([AC_INIT with unusual version strings])
 
+if echo 'ab*c' | grep -F 'ab*c' >/dev/null 2>&1; then
+  FGREP="grep -F"
+else
+  FGREP=fgrep
+fi
+
+# In both of the arguments that might contain URLs, make sure we test
+# all of the unusual ASCII characters that commonly appear in URLs.
+# The RFC 3986 "unreserved" characters are ASCII letters and digits, plus
+#    - . _ ~
+# The RFC 3986 "gen-delims" and "sub-delims" are
+#    / : ? # [ ] @ ! $ & ' ( ) * + , ; =
+# The URL escape character is
+#    %
+# Characters that are still significant for Bourne shell within a
+# single-quoted string, double-quoted string, quoted here-doc, or
+# unquoted here-doc are explicitly not allowed:
+#    ' $
+# Also, we don't test unbalanced parentheses or brackets here.
+
 AT_DATA([configure.ac],
-[[AC_INIT([GNU String++ with  spaces (foo)],
+[[AC_INIT([GNU String++ with  spaces
+           (foo)],
 	  [2.48++  (2010-07-03)],
-          [[https://example.com/?a=b&c=d#e]],
+          [https://example/~bug/cdfijknoqrvw/-._:@!()[]*+,;/?y=z#1234567890
+],
           [string++],
-          [[https://example.com/?f=g&h=i%2fj#42]])
+          [HTTPS://EXAMPLE/~PKG/BCDFIJNOQRUVW/-._:@!()[]*+,;/?y=z#1234567890
+])
 AC_OUTPUT
 ]])
 
-if echo 'ab*c' | grep -F 'ab*c' >/dev/null 2>&1; then
-  FGREP="grep -F"
-else
-  FGREP=fgrep
-fi
+AT_CHECK_AUTOCONF([-Werror])
+AT_CHECK_CONFIGURE([-q])
+
+AT_CHECK_CONFIGURE([--help], [], [stdout])
+AT_CHECK([[$FGREP \
+  'https://example/~bug/cdfijknoqrvw/-._:@!()[]*+,;/?y=z#1234567890' \
+  stdout]], [], [ignore])
+AT_CHECK([[$FGREP \
+  'HTTPS://EXAMPLE/~PKG/BCDFIJNOQRUVW/-._:@!()[]*+,;/?y=z#1234567890' \
+  stdout]], [], [ignore])
+
+AT_CHECK_CONFIGURE([--version], [], [stdout])
+AT_CHECK([$FGREP 'GNU String++ with spaces (foo)' stdout], [], [ignore])
+AT_CHECK([$FGREP '2.48++ (2010-07-03)' stdout], [], [ignore])
+
+AT_CHECK([./config.status --help], [], [stdout])
+AT_CHECK([[$FGREP \
+  'https://example/~bug/cdfijknoqrvw/-._:@!()[]*+,;/?y=z#1234567890' \
+  stdout]], [], [ignore])
+AT_CHECK([[$FGREP \
+  'HTTPS://EXAMPLE/~PKG/BCDFIJNOQRUVW/-._:@!()[]*+,;/?y=z#1234567890' \
+  stdout]], [], [ignore])
+
+AT_CHECK([./config.status --version], [], [stdout])
+AT_CHECK([$FGREP 'GNU String++ with spaces (foo)' stdout], [], [ignore])
+AT_CHECK([$FGREP '2.48++ (2010-07-03)' stdout], [], [ignore])
+
+# Repeat the above test using all the unusual characters that might appear
+# in a list of email addresses in both BUG-REPORT and URL.  (URL isn't
+# supposed to contain email addresses, but there's no good reason to
+# restrict its syntax.)
+# The RFC 5822 "atext" characters are ASCII letters and digits, plus
+#    ! # $ % & ' * + - / = ? ^ _ ` { | } ~
+# The RFC 5822 "special" characters, all of which might appear somewhere
+# in an address list, are
+#    ( ) < > [ ] : ; @ \ , . "
+# As above, characters that are significant for Bourne shell within
+# strings and heredocs are explicitly not allowed:
+#    ' " ` \ $
+# Whitespace is allowed but collapsed (just like AC_INIT does itself).
+AT_DATA([configure.ac],
+[[AC_INIT([GNU String++ with  spaces
+           (foo)],
+	  [2.48++  (2010-07-03)],
+          [bugs: fred <A=B?C^D_E@F>,
+                 G!H!I#J@K.L (wilma),
+                 M%N&O@[156.247.38.49],
+                 P*Q+R-S/T@U,
+                 {jon|chyp~}@kqtvxz.VWXYZ;],
+          [string++],
+          [contact: jem <A=B?C^D_E@bd>,
+                    F!G!H#I@fv.J (lugh),
+                    K%L&M@[156.247.38.49],
+                    N*O+P-Q/R@STU,
+                    {qik|~prys}@wxz.VWXYZ;])
+AC_OUTPUT
+]])
 
 AT_CHECK_AUTOCONF([-Werror])
 AT_CHECK_CONFIGURE([-q])
+
 AT_CHECK_CONFIGURE([--help], [], [stdout])
-AT_CHECK([[$FGREP 'com/?a=b&c=d#e' stdout]], [], [ignore])
-AT_CHECK([[$FGREP 'com/?f=g&h=i%2fj#42' stdout]], [], [ignore])
+AT_CHECK([[$FGREP \
+  'bugs: fred <A=B?C^D_E@F>, G!H!I#J@K.L (wilma), M%N&O@[156.247.38.49], P*Q+R-S/T@U, {jon|chyp~}@kqtvxz.VWXYZ;' \
+  stdout]], [], [ignore])
+AT_CHECK([[$FGREP \
+  'contact: jem <A=B?C^D_E@bd>, F!G!H#I@fv.J (lugh), K%L&M@[156.247.38.49], N*O+P-Q/R@STU, {qik|~prys}@wxz.VWXYZ;' \
+  stdout]], [], [ignore])
+
 AT_CHECK_CONFIGURE([--version], [], [stdout])
 AT_CHECK([$FGREP 'GNU String++ with spaces (foo)' stdout], [], [ignore])
 AT_CHECK([$FGREP '2.48++ (2010-07-03)' stdout], [], [ignore])
 
 AT_CHECK([./config.status --help], [], [stdout])
-AT_CHECK([[$FGREP 'com/?a=b&c=d#e' stdout]], [], [ignore])
+AT_CHECK([[$FGREP \
+  'bugs: fred <A=B?C^D_E@F>, G!H!I#J@K.L (wilma), M%N&O@[156.247.38.49], P*Q+R-S/T@U, {jon|chyp~}@kqtvxz.VWXYZ;' \
+  stdout]], [], [ignore])
+AT_CHECK([[$FGREP \
+  'contact: jem <A=B?C^D_E@bd>, F!G!H#I@fv.J (lugh), K%L&M@[156.247.38.49], N*O+P-Q/R@STU, {qik|~prys}@wxz.VWXYZ;' \
+  stdout]], [], [ignore])
+
 AT_CHECK([./config.status --version], [], [stdout])
 AT_CHECK([$FGREP 'GNU String++ with spaces (foo)' stdout], [], [ignore])
 AT_CHECK([$FGREP '2.48++ (2010-07-03)' stdout], [], [ignore])
 
+# Check for invalid characters in each argument.
 AT_DATA([configure.ac],
 [[AC_INIT([GNU "String++"],
 	  [2.48], [https://example.com/], [string++])
@@ -347,6 +435,80 @@ AC_OUTPUT
 AT_CHECK_AUTOCONF([-Werror], [1], [ignore], [stderr])
 AT_CHECK([grep 'AC_INIT: unsafe as a filename: ' stderr], [], [ignore])
 
+# Commas and unbalanced close parentheses are especially troublesome for M4.
+
+AT_DATA([configure.ac],
+[[AC_INIT([GNU, String], [2.48], [[e-mail]],
+          [string], [https://gstring.example/])
+AC_OUTPUT
+]])
+AT_CHECK_AUTOCONF
+
+AT_DATA([configure.ac],
+[[AC_INIT([GNU String)], [2.48], [[e-mail]],
+          [string], [https://gstring.example/])
+AC_OUTPUT
+]])
+AT_CHECK_AUTOCONF
+
+AT_DATA([configure.ac],
+[[AC_INIT([GNU String], [2,48], [[e-mail]],
+          [string], [https://gstring.example/])
+AC_OUTPUT
+]])
+AT_CHECK_AUTOCONF
+
+AT_DATA([configure.ac],
+[[AC_INIT([GNU String], [2.48)], [[e-mail]],
+          [string], [https://gstring.example/])
+AC_OUTPUT
+]])
+AT_CHECK_AUTOCONF
+
+AT_DATA([configure.ac],
+[[AC_INIT([GNU String], [2.48], [[e-mail],
+                                 [e-mail]],
+          [string], [https://gstring.example/])
+AC_OUTPUT
+]])
+AT_CHECK_AUTOCONF
+
+AT_DATA([configure.ac],
+[[AC_INIT([GNU String], [2.48], [bugs)@gstring.example],
+          [string], [https://gstring.example/])
+AC_OUTPUT
+]])
+AT_CHECK_AUTOCONF
+
+AT_DATA([configure.ac],
+[[AC_INIT([GNU String], [2.48], [[e-mail]],
+          [string,], [https://gstring.example/])
+AC_OUTPUT
+]])
+AT_CHECK_AUTOCONF
+
+AT_DATA([configure.ac],
+[[AC_INIT([GNU String], [2.48], [[e-mail]],
+          [string)], [https://gstring.example/])
+AC_OUTPUT
+]])
+AT_CHECK_AUTOCONF([], [0], [ignore], [stderr])
+AT_CHECK([grep 'AC_INIT: unsafe as a filename: ' stderr], [], [ignore])
+
+AT_DATA([configure.ac],
+[[AC_INIT([GNU String], [2.48], [[e-mail]],
+          [string], [https://gstring.example/docs,html])
+AC_OUTPUT
+]])
+AT_CHECK_AUTOCONF
+
+
+AT_DATA([configure.ac],
+[[AC_INIT([GNU String], [2.48], [[e-mail]],
+          [string], [https://gstring.example/weird)/path])
+AC_OUTPUT
+]])
+AT_CHECK_AUTOCONF
 
 AT_CLEANUP
 
-- 
2.26.2