From 3db388b0bf83d3138562f09ce25fab8ba89bcc81 Mon Sep 17 00:00:00 2001 From: Paul Eggert Date: Wed, 4 Oct 2017 14:29:58 -0700 Subject: [PATCH] Speed up (format "%s" STRING) and the like MIME-Version: 1.0 Content-Type: text/plain; charset=utf8 Content-Transfer-Encoding: 8bit Although the Lisp manual said that ‘format’ returns a newly-allocated string, this was not true for a few cases like (format "%s" ""), and fixing the documentation to allow reuse of arguments lets us improve performance in common cases like (format "foo") and (format "%s" "foo") (Bug#28625). * doc/lispref/strings.texi (Formatting Strings): * etc/NEWS: Say that the result of ‘format’ might not be newly allocated. * src/callint.c (Fcall_interactively): * src/dbusbind.c (XD_OBJECT_TO_STRING): * src/editfns.c (Fmessage, Fmessage_box): * src/xdisp.c (vadd_to_log, Ftrace_to_stderr): Just use Fformat or Fformat_message, as that’s simpler and no longer makes unnecessary copies. * src/editfns.c (styled_format): Remove last argument, as it is no longer needed: all callers now want it to behave as if it were true. All remaining callers changed. Make this function static again. Simplify the function now that we no longer need to worry about whether the optimization is allowed. --- doc/lispref/strings.texi | 10 +++++++--- etc/NEWS | 7 +++++++ src/callint.c | 4 ++-- src/dbusbind.c | 3 +-- src/editfns.c | 28 +++++++++++----------------- src/lisp.h | 1 - src/xdisp.c | 4 ++-- 7 files changed, 30 insertions(+), 27 deletions(-) diff --git a/doc/lispref/strings.texi b/doc/lispref/strings.texi index dd004927caf..09c3bdf71f6 100644 --- a/doc/lispref/strings.texi +++ b/doc/lispref/strings.texi @@ -812,15 +812,19 @@ formatting feature described here; they differ from @code{format-message} only in how they use the result of formatting. @defun format string &rest objects -This function returns a new string that is made by copying -@var{string} and then replacing any format specification -in the copy with encodings of the corresponding @var{objects}. The +This function returns a string equal to @var{string}, replacing any format +specifications with encodings of the corresponding @var{objects}. The arguments @var{objects} are the computed values to be formatted. The characters in @var{string}, other than the format specifications, are copied directly into the output, including their text properties, if any. Any text properties of the format specifications are copied to the produced string representations of the argument @var{objects}. + +The output string need not be newly-allocated. For example, if +@code{x} is the string @code{"foo"}, the expressions @code{(eq x +(format x))} and @code{(eq x (format "%s" x))} might both yield +@code{t}. @end defun @defun format-message string &rest objects diff --git a/etc/NEWS b/etc/NEWS index 62d2450f9a3..62a9ea2181c 100644 --- a/etc/NEWS +++ b/etc/NEWS @@ -1556,6 +1556,13 @@ Emacs integers with %e, %f, or %g conversions. For example, on these hosts (eql N (string-to-number (format "%.0f" N))) now returns t for all Emacs integers N. ++++ +** 'format' is no longer documented to return a newly-allocated string. +This documentation was not correct, as (eq x (format x)) returned t +when x was the empty string. 'format' now takes advantage of the doc +change to avoid making copies of strings in common cases like (format +"foo") and (format "%s" "foo"). + --- ** Calls that accept floating-point integers (for use on hosts with limited integer range) now signal an error if arguments are not diff --git a/src/callint.c b/src/callint.c index 469205cc380..5d88082e38d 100644 --- a/src/callint.c +++ b/src/callint.c @@ -272,7 +272,7 @@ invoke it. If KEYS is omitted or nil, the return value of { /* `args' will contain the array of arguments to pass to the function. `visargs' will contain the same list but in a nicer form, so that if we - pass it to styled_format it will be understandable to a human. */ + pass it to Fformat_message it will be understandable to a human. */ Lisp_Object *args, *visargs; Lisp_Object specs; Lisp_Object filter_specs; @@ -502,7 +502,7 @@ invoke it. If KEYS is omitted or nil, the return value of for (i = 2; *tem; i++) { visargs[1] = make_string (tem + 1, strcspn (tem + 1, "\n")); - callint_message = styled_format (i - 1, visargs + 1, true, false); + callint_message = Fformat_message (i - 1, visargs + 1); switch (*tem) { diff --git a/src/dbusbind.c b/src/dbusbind.c index 789aa008611..4a7068416fe 100644 --- a/src/dbusbind.c +++ b/src/dbusbind.c @@ -237,8 +237,7 @@ static char * XD_OBJECT_TO_STRING (Lisp_Object object) { AUTO_STRING (format, "%s"); - Lisp_Object args[] = { format, object }; - return SSDATA (styled_format (ARRAYELTS (args), args, false, false)); + return SSDATA (CALLN (Fformat, format, object)); } #define XD_DBUS_VALIDATE_BUS_ADDRESS(bus) \ diff --git a/src/editfns.c b/src/editfns.c index e326604467c..d88a913c667 100644 --- a/src/editfns.c +++ b/src/editfns.c @@ -74,6 +74,7 @@ static Lisp_Object format_time_string (char const *, ptrdiff_t, struct timespec, static long int tm_gmtoff (struct tm *); static int tm_diff (struct tm *, struct tm *); static void update_buffer_properties (ptrdiff_t, ptrdiff_t); +static Lisp_Object styled_format (ptrdiff_t, Lisp_Object *, bool); #ifndef HAVE_TM_GMTOFF # define HAVE_TM_GMTOFF false @@ -3958,7 +3959,7 @@ usage: (message FORMAT-STRING &rest ARGS) */) } else { - Lisp_Object val = styled_format (nargs, args, true, false); + Lisp_Object val = Fformat_message (nargs, args); message3 (val); return val; } @@ -3984,7 +3985,7 @@ usage: (message-box FORMAT-STRING &rest ARGS) */) } else { - Lisp_Object val = styled_format (nargs, args, true, false); + Lisp_Object val = Fformat_message (nargs, args); Lisp_Object pane, menu; pane = list1 (Fcons (build_string ("OK"), Qt)); @@ -4140,7 +4141,7 @@ produced text. usage: (format STRING &rest OBJECTS) */) (ptrdiff_t nargs, Lisp_Object *args) { - return styled_format (nargs, args, false, true); + return styled_format (nargs, args, false); } DEFUN ("format-message", Fformat_message, Sformat_message, 1, MANY, 0, @@ -4156,16 +4157,13 @@ and right quote replacement characters are specified by usage: (format-message STRING &rest OBJECTS) */) (ptrdiff_t nargs, Lisp_Object *args) { - return styled_format (nargs, args, true, true); + return styled_format (nargs, args, true); } -/* Implement ‘format-message’ if MESSAGE is true, ‘format’ otherwise. - If NEW_RESULT, the result is a new string; otherwise, the result - may be one of the arguments. */ +/* Implement ‘format-message’ if MESSAGE is true, ‘format’ otherwise. */ -Lisp_Object -styled_format (ptrdiff_t nargs, Lisp_Object *args, bool message, - bool new_result) +static Lisp_Object +styled_format (ptrdiff_t nargs, Lisp_Object *args, bool message) { ptrdiff_t n; /* The number of the next arg to substitute. */ char initial_buffer[4000]; @@ -4195,9 +4193,6 @@ styled_format (ptrdiff_t nargs, Lisp_Object *args, bool message, /* The start and end bytepos in the output string. */ ptrdiff_t start, end; - /* Whether the argument is a newly created string. */ - bool_bf new_string : 1; - /* Whether the argument is a string with intervals. */ bool_bf intervals : 1; } *info; @@ -4241,6 +4236,9 @@ styled_format (ptrdiff_t nargs, Lisp_Object *args, bool message, ptrdiff_t ispec; ptrdiff_t nspec = 0; + /* True if a string needs to be allocated to hold the result. */ + bool new_result = false; + /* If we start out planning a unibyte result, then discover it has to be multibyte, we jump back to retry. */ retry: @@ -4360,7 +4358,6 @@ styled_format (ptrdiff_t nargs, Lisp_Object *args, bool message, if (nspec < ispec) { spec->argument = args[n]; - spec->new_string = false; spec->intervals = false; nspec = ispec; } @@ -4378,7 +4375,6 @@ styled_format (ptrdiff_t nargs, Lisp_Object *args, bool message, { Lisp_Object noescape = conversion == 'S' ? Qnil : Qt; spec->argument = arg = Fprin1_to_string (arg, noescape); - spec->new_string = true; if (STRING_MULTIBYTE (arg) && ! multibyte) { multibyte = true; @@ -4397,7 +4393,6 @@ styled_format (ptrdiff_t nargs, Lisp_Object *args, bool message, goto retry; } spec->argument = arg = Fchar_to_string (arg); - spec->new_string = true; } if (!EQ (arg, args[n])) @@ -4421,7 +4416,6 @@ styled_format (ptrdiff_t nargs, Lisp_Object *args, bool message, if (conversion == 's') { if (format == end && format - format_start == 2 - && (!new_result || spec->new_string) && ! string_intervals (args[0])) return arg; diff --git a/src/lisp.h b/src/lisp.h index bdb162aea4c..266370333f5 100644 --- a/src/lisp.h +++ b/src/lisp.h @@ -3970,7 +3970,6 @@ extern _Noreturn void time_overflow (void); extern Lisp_Object make_buffer_string (ptrdiff_t, ptrdiff_t, bool); extern Lisp_Object make_buffer_string_both (ptrdiff_t, ptrdiff_t, ptrdiff_t, ptrdiff_t, bool); -extern Lisp_Object styled_format (ptrdiff_t, Lisp_Object *, bool, bool); extern void init_editfns (bool); extern void syms_of_editfns (void); diff --git a/src/xdisp.c b/src/xdisp.c index 86164eb9f6f..141275f15a0 100644 --- a/src/xdisp.c +++ b/src/xdisp.c @@ -10194,7 +10194,7 @@ vadd_to_log (char const *format, va_list ap) for (ptrdiff_t i = 1; i <= nargs; i++) args[i] = va_arg (ap, Lisp_Object); Lisp_Object msg = Qnil; - msg = styled_format (nargs, args, true, false); + msg = Fformat_message (nargs, args); ptrdiff_t len = SBYTES (msg) + 1; USE_SAFE_ALLOCA; @@ -19525,7 +19525,7 @@ DEFUN ("trace-to-stderr", Ftrace_to_stderr, Strace_to_stderr, 1, MANY, "", usage: (trace-to-stderr STRING &rest OBJECTS) */) (ptrdiff_t nargs, Lisp_Object *args) { - Lisp_Object s = styled_format (nargs, args, false, false); + Lisp_Object s = Fformat (nargs, args); fwrite (SDATA (s), 1, SBYTES (s), stderr); return Qnil; } -- 2.39.5