I've written a feature I find useful for bash that escapes a single ampersand
if it is surrounded on both sides by any non-blank or non-meta characters. This
logic is toggled by a set option, "compressedand" that can be enabled with `set
[-|+]c` or `set -o compressedand`.
As an example:
$ echo this&echo that
[1] 32324
that
this
[1]+ Done echo this
$ set -c
$ echo this&echo that
this&echo that
Handling of multi-character metas, such as &>, |&, &&, et al, is still parsed
by BASH and their functions remain unaffected.
$ echo this& echo that
[1] 1373
that
this
[1]+ Done echo this
$ echo this &echo that
[1] 1375
that
this
[1]+ Done echo this
$ echo this&&echo that
this
that
$ ps ax&>/tmp/ps&echo
$ ls /tmp/ps\&echo
/tmp/ps&echo
The primary use case for the option is to ease using unquoted URLs as arguments
that have multiple query parameters. Yes, quoting the URL precludes the need
for this feature, but I forget sometimes (okay, too often):
$ set +c
$ echo https://example.com/inputs?v=22&time=now&cp=key
[1] 32335
[2] 32336
https://example.com/inputs?v=22
[1]- Done echo https://example.com/inputs?v=22
[2]+ Done time=now
$ set -c
$ echo https://example.com/inputs?v=22&time=now&cp=key
https://example.com/inputs?v=22&time=now&cp=key
I've attached a patch that was written against bash-4.4 and tested to work
against the most recent DEVEL commit (3235014e5b) as of 04/22. The patch
provides the logic, set option control, and updates to the man and info pages.
I'm still working on getting some tests worked up. I wanted to get this
submitted to get a feel for general likeability and for input on things I need
to do for a proper contribution.
And, for completeness, here are the bash VERSIONs I've tested this on:
GNU bash, version 4.4.23(1)-release (x86_64-pc-linux-gnu)
GNU bash, version 5.0.16(1)-maint (x86_64-pc-linux-gnu)
I haven't looked up to see what POSIX has to say about this, but I'm fairly
confident that this flies in the face of it. If that's the case and this patch
is dismissed accordingly, I'll accept that. This was a fun exercise anyway. .)
- Eric.
-------------------------------
Fudd's First Law of Opposition:
"If you push something hard enough, it will fall over."
- Firesign Theater
diff --git a/builtins/set.def b/builtins/set.def
index 8122361..2467e73 100644
--- a/builtins/set.def
+++ b/builtins/set.def
@@ -59,7 +59,7 @@ extern int no_line_editing;
$BUILTIN set
$FUNCTION set_builtin
-$SHORT_DOC set [-abefhkmnptuvxBCHP] [-o option-name] [--] [arg ...]
+$SHORT_DOC set [-abcefhkmnptuvxBCHP] [-o option-name] [--] [arg ...]
Set or unset values of shell options and positional parameters.
Change the value of shell attributes and positional parameters, or
@@ -68,6 +68,7 @@ display the names and values of shell variables.
Options:
-a Mark variables which are modified or created for export.
-b Notify of job termination immediately.
+ -c Escape a single ampersand surrounded by non-blank/non-meta text.
-e Exit immediately if a command exits with a non-zero status.
-f Disable file name generation (globbing).
-h Remember the location of commands as they are looked up.
@@ -77,50 +78,51 @@ Options:
-n Read commands but do not execute them.
-o option-name
Set the variable corresponding to option-name:
- allexport same as -a
- braceexpand same as -B
+ allexport same as -a
+ braceexpand same as -B
+ compressedand same as -c
#if defined (READLINE)
- emacs use an emacs-style line editing interface
+ emacs use an emacs-style line editing interface
#endif /* READLINE */
- errexit same as -e
- errtrace same as -E
- functrace same as -T
- hashall same as -h
+ errexit same as -e
+ errtrace same as -E
+ functrace same as -T
+ hashall same as -h
#if defined (BANG_HISTORY)
- histexpand same as -H
+ histexpand same as -H
#endif /* BANG_HISTORY */
#if defined (HISTORY)
- history enable command history
+ history enable command history
#endif
- ignoreeof the shell will not exit upon reading EOF
+ ignoreeof the shell will not exit upon reading EOF
interactive-comments
- allow comments to appear in interactive commands
- keyword same as -k
+ allow comments to appear in interactive commands
+ keyword same as -k
#if defined (JOB_CONTROL)
- monitor same as -m
+ monitor same as -m
#endif
- noclobber same as -C
- noexec same as -n
- noglob same as -f
- nolog currently accepted but ignored
+ noclobber same as -C
+ noexec same as -n
+ noglob same as -f
+ nolog currently accepted but ignored
#if defined (JOB_CONTROL)
- notify same as -b
+ notify same as -b
#endif
- nounset same as -u
- onecmd same as -t
- physical same as -P
- pipefail the return value of a pipeline is the status of
- the last command to exit with a non-zero status,
- or zero if no command exited with a non-zero status
- posix change the behavior of bash where the default
- operation differs from the Posix standard to
- match the standard
- privileged same as -p
- verbose same as -v
+ nounset same as -u
+ onecmd same as -t
+ physical same as -P
+ pipefail the return value of a pipeline is the status of
+ the last command to exit with a non-zero status,
+ or zero if no command exited with a non-zero status
+ posix change the behavior of bash where the default
+ operation differs from the Posix standard to
+ match the standard
+ privileged same as -p
+ verbose same as -v
#if defined (READLINE)
- vi use a vi-style line editing interface
+ vi use a vi-style line editing interface
#endif /* READLINE */
- xtrace same as -x
+ xtrace same as -x
-p Turned on whenever the real and effective user ids do not match.
Disables processing of the $ENV file and importing of shell
functions. Turning this option off causes the effective uid and
@@ -197,6 +199,7 @@ const struct {
#if defined (BRACE_EXPANSION)
{ "braceexpand",'B', (int *)NULL, (setopt_set_func_t *)NULL, (setopt_get_func_t *)NULL },
#endif
+ { "compressedand", 'c', (int *)NULL, (setopt_set_func_t *)NULL, (setopt_get_func_t *)NULL },
#if defined (READLINE)
{ "emacs", '\0', (int *)NULL, set_edit_mode, get_edit_mode },
#endif
diff --git a/doc/bash.1 b/doc/bash.1
index 9a7a384..f2d33d9 100644
--- a/doc/bash.1
+++ b/doc/bash.1
@@ -9019,10 +9019,10 @@ function and not during execution of a script by \fB.\fP\^ or \fBsource\fP.
Any command associated with the \fBRETURN\fP trap is executed
before execution resumes after the function or script.
.TP
-\fBset\fP [\fB\-\-abefhkmnptuvxBCEHPT\fP] [\fB\-o\fP \fIoption\-name\fP] [\fIarg\fP ...]
+\fBset\fP [\fB\-\-abcefhkmnptuvxBCEHPT\fP] [\fB\-o\fP \fIoption\-name\fP] [\fIarg\fP ...]
.PD 0
.TP
-\fBset\fP [\fB+abefhkmnptuvxBCEHPT\fP] [\fB+o\fP \fIoption\-name\fP] [\fIarg\fP ...]
+\fBset\fP [\fB+abcefhkmnptuvxBCEHPT\fP] [\fB+o\fP \fIoption\-name\fP] [\fIarg\fP ...]
.PD
Without options, the name and value of each shell variable are displayed
in a format that can be reused as input
@@ -9051,6 +9051,10 @@ Report the status of terminated background jobs
immediately, rather than before the next primary prompt. This is
effective only when job control is enabled.
.TP 8
+.B \-c
+Escape a single ampersand if surrounded by non-blank or non-meta
+characters.
+.TP 8
.B \-e
Exit immediately if a
\fIpipeline\fP (which may consist of a single \fIsimple command\fP),
@@ -9141,6 +9145,10 @@ Same as
Same as
.BR \-B .
.TP 8
+.B compressedand
+Same as
+.BR \-c .
+.TP 8
.B emacs
Use an emacs-style command line editing interface. This is enabled
by default when the shell is interactive, unless the shell is started
diff --git a/doc/bash.info b/doc/bash.info
index fac6786..d79e19d 100644
--- a/doc/bash.info
+++ b/doc/bash.info
@@ -3950,8 +3950,8 @@ allows you to change the values of shell options and set the positional
parameters, or to display the names and values of shell variables.
'set'
- set [--abefhkmnptuvxBCEHPT] [-o OPTION-NAME] [ARGUMENT ...]
- set [+abefhkmnptuvxBCEHPT] [+o OPTION-NAME] [ARGUMENT ...]
+ set [--abcefhkmnptuvxBCEHPT] [-o OPTION-NAME] [ARGUMENT ...]
+ set [+abcefhkmnptuvxBCEHPT] [+o OPTION-NAME] [ARGUMENT ...]
If no options or arguments are supplied, 'set' displays the names
and values of all shell variables and functions, sorted according
@@ -3973,6 +3973,10 @@ parameters, or to display the names and values of shell variables.
immediately, rather than before printing the next primary
prompt.
+ '-c'
+ Escape a single ampersand when surrounded by non-blank or
+ non-meta characters.
+
'-e'
Exit immediately if a pipeline (*note Pipelines::), which may
consist of a single simple command (*note Simple Commands::),
@@ -4035,6 +4039,9 @@ parameters, or to display the names and values of shell variables.
'braceexpand'
Same as '-B'.
+ 'compressedand'
+ Same as '-c'.
+
'emacs'
Use an 'emacs'-style line editing interface (*note
Command Line Editing::). This also affects the editing
diff --git a/flags.c b/flags.c
index 4b94fb0..d41eb1d 100644
--- a/flags.c
+++ b/flags.c
@@ -92,6 +92,10 @@ int unbound_vars_is_error = 0;
int echo_input_at_read = 0;
int verbose_flag = 0;
+/* Non-zero means to escape a single ampersand surrounded by non-blank or
+ non-meta charcters; `echo this&that` -> "this&that" */
+int compressedand = 0;
+
/* Non-zero means type out the command definition after reading, but
before executing. */
int echo_command_at_execute = 0;
@@ -183,6 +187,7 @@ const struct flags_alist shell_flags[] = {
#if defined (JOB_CONTROL)
{ 'b', &asynchronous_notification },
#endif /* JOB_CONTROL */
+ { 'c', &compressedand },
{ 'e', &errexit_flag },
{ 'f', &disallow_filename_globbing },
{ 'h', &hashing_enabled },
@@ -368,6 +373,8 @@ reset_shell_flags ()
exit_immediately_on_error = errexit_flag = 0;
echo_input_at_read = verbose_flag = 0;
+ compressedand = 0;
+
hashing_enabled = interactive_comments = 1;
#if defined (JOB_CONTROL)
diff --git a/flags.h b/flags.h
index d5ed334..ff44a45 100644
--- a/flags.h
+++ b/flags.h
@@ -42,7 +42,7 @@ extern char optflags[];
extern int
mark_modified_vars, errexit_flag, exit_immediately_on_error,
- disallow_filename_globbing,
+ disallow_filename_globbing, compressedand,
place_keywords_in_env, read_but_dont_execute,
just_one_command, unbound_vars_is_error, echo_input_at_read, verbose_flag,
echo_command_at_execute, no_invisible_vars, noclobber,
diff --git a/parse.y b/parse.y
index f415d2e..e2adce4 100644
--- a/parse.y
+++ b/parse.y
@@ -4732,6 +4732,23 @@ read_token_word (character)
cd = current_delimiter (dstack);
+ /* 2020-04-21 EMP: Added a "compressed ampersand" logic that would automatically
+ escape the ampersand if it was surrounded by something that wasn't a space or
+ another meta character. the latter preserves special function of various dbl-
+ meta specials like redirects and AND_AND regardless of bounding.
+ this is all to allow unquoted URLs that have multiple query parameters. */
+ if (compressedand) {
+ if MBTEST(character == '&') {
+ peek_char = shell_getc(0);
+ shell_ungetc(peek_char);
+
+ if MBTEST(!shellblank(peek_char) && !shellmeta(peek_char)) {
+ pass_next_character++;
+ goto got_character;
+ }
+ }
+ }
+
/* Handle backslashes. Quote lots of things when not inside of
double-quotes, quote some things inside of double-quotes. */
if MBTEST(character == '\\')
