Mercurial > hg > xemacs-beta
view src/strftime.c @ 665:fdefd0186b75
[xemacs-hg @ 2001-09-20 06:28:42 by ben]
The great integral types renaming.
The purpose of this is to rationalize the names used for various
integral types, so that they match their intended uses and follow
consist conventions, and eliminate types that were not semantically
different from each other.
The conventions are:
-- All integral types that measure quantities of anything are
signed. Some people disagree vociferously with this, but their
arguments are mostly theoretical, and are vastly outweighed by
the practical headaches of mixing signed and unsigned values,
and more importantly by the far increased likelihood of
inadvertent bugs: Because of the broken "viral" nature of
unsigned quantities in C (operations involving mixed
signed/unsigned are done unsigned, when exactly the opposite is
nearly always wanted), even a single error in declaring a
quantity unsigned that should be signed, or even the even more
subtle error of comparing signed and unsigned values and
forgetting the necessary cast, can be catastrophic, as
comparisons will yield wrong results. -Wsign-compare is turned
on specifically to catch this, but this tends to result in a
great number of warnings when mixing signed and unsigned, and
the casts are annoying. More has been written on this
elsewhere.
-- All such quantity types just mentioned boil down to EMACS_INT,
which is 32 bits on 32-bit machines and 64 bits on 64-bit
machines. This is guaranteed to be the same size as Lisp
objects of type `int', and (as far as I can tell) of size_t
(unsigned!) and ssize_t. The only type below that is not an
EMACS_INT is Hashcode, which is an unsigned value of the same
size as EMACS_INT.
-- Type names should be relatively short (no more than 10
characters or so), with the first letter capitalized and no
underscores if they can at all be avoided.
-- "count" == a zero-based measurement of some quantity. Includes
sizes, offsets, and indexes.
-- "bpos" == a one-based measurement of a position in a buffer.
"Charbpos" and "Bytebpos" count text in the buffer, rather than
bytes in memory; thus Bytebpos does not directly correspond to
the memory representation. Use "Membpos" for this.
-- "Char" refers to internal-format characters, not to the C type
"char", which is really a byte.
-- For the actual name changes, see the script below.
I ran the following script to do the conversion. (NOTE: This script
is idempotent. You can safely run it multiple times and it will
not screw up previous results -- in fact, it will do nothing if
nothing has changed. Thus, it can be run repeatedly as necessary
to handle patches coming in from old workspaces, or old branches.)
There are two tags, just before and just after the change:
`pre-integral-type-rename' and `post-integral-type-rename'. When
merging code from the main trunk into a branch, the best thing to
do is first merge up to `pre-integral-type-rename', then apply the
script and associated changes, then merge from
`post-integral-type-change' to the present. (Alternatively, just do
the merging in one operation; but you may then have a lot of
conflicts needing to be resolved by hand.)
Script `fixtypes.sh' follows:
----------------------------------- cut ------------------------------------
files="*.[ch] s/*.h m/*.h config.h.in ../configure.in Makefile.in.in ../lib-src/*.[ch] ../lwlib/*.[ch]"
gr Memory_Count Bytecount $files
gr Lstream_Data_Count Bytecount $files
gr Element_Count Elemcount $files
gr Hash_Code Hashcode $files
gr extcount bytecount $files
gr bufpos charbpos $files
gr bytind bytebpos $files
gr memind membpos $files
gr bufbyte intbyte $files
gr Extcount Bytecount $files
gr Bufpos Charbpos $files
gr Bytind Bytebpos $files
gr Memind Membpos $files
gr Bufbyte Intbyte $files
gr EXTCOUNT BYTECOUNT $files
gr BUFPOS CHARBPOS $files
gr BYTIND BYTEBPOS $files
gr MEMIND MEMBPOS $files
gr BUFBYTE INTBYTE $files
gr MEMORY_COUNT BYTECOUNT $files
gr LSTREAM_DATA_COUNT BYTECOUNT $files
gr ELEMENT_COUNT ELEMCOUNT $files
gr HASH_CODE HASHCODE $files
----------------------------------- cut ------------------------------------
`fixtypes.sh' is a Bourne-shell script; it uses 'gr':
----------------------------------- cut ------------------------------------
#!/bin/sh
# Usage is like this:
# gr FROM TO FILES ...
# globally replace FROM with TO in FILES. FROM and TO are regular expressions.
# backup files are stored in the `backup' directory.
from="$1"
to="$2"
shift 2
echo ${1+"$@"} | xargs global-replace "s/$from/$to/g"
----------------------------------- cut ------------------------------------
`gr' in turn uses a Perl script to do its real work,
`global-replace', which follows:
----------------------------------- cut ------------------------------------
: #-*- Perl -*-
### global-modify --- modify the contents of a file by a Perl expression
## Copyright (C) 1999 Martin Buchholz.
## Copyright (C) 2001 Ben Wing.
## Authors: Martin Buchholz <martin@xemacs.org>, Ben Wing <ben@xemacs.org>
## Maintainer: Ben Wing <ben@xemacs.org>
## Current Version: 1.0, May 5, 2001
# This program is free software; you can redistribute it and/or modify
# it under the terms of the GNU General Public License as published by
# the Free Software Foundation; either version 2, or (at your option)
# any later version.
#
# This program is distributed in the hope that it will be useful, but
# WITHOUT ANY WARRANTY; without even the implied warranty of
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
# General Public License for more details.
#
# You should have received a copy of the GNU General Public License
# along with XEmacs; see the file COPYING. If not, write to the Free
# Software Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA
# 02111-1307, USA.
eval 'exec perl -w -S $0 ${1+"$@"}'
if 0;
use strict;
use FileHandle;
use Carp;
use Getopt::Long;
use File::Basename;
(my $myName = $0) =~ s@.*/@@; my $usage="
Usage: $myName [--help] [--backup-dir=DIR] [--line-mode] [--hunk-mode]
PERLEXPR FILE ...
Globally modify a file, either line by line or in one big hunk.
Typical usage is like this:
[with GNU print, GNU xargs: guaranteed to handle spaces, quotes, etc.
in file names]
find . -name '*.[ch]' -print0 | xargs -0 $0 's/\bCONST\b/const/g'\n
[with non-GNU print, xargs]
find . -name '*.[ch]' -print | xargs $0 's/\bCONST\b/const/g'\n
The file is read in, either line by line (with --line-mode specified)
or in one big hunk (with --hunk-mode specified; it's the default), and
the Perl expression is then evalled with \$_ set to the line or hunk of
text, including the terminating newline if there is one. It should
destructively modify the value there, storing the changed result in \$_.
Files in which any modifications are made are backed up to the directory
specified using --backup-dir, or to `backup' by default. To disable this,
use --backup-dir= with no argument.
Hunk mode is the default because it is MUCH MUCH faster than line-by-line.
Use line-by-line only when it matters, e.g. you want to do a replacement
only once per line (the default without the `g' argument). Conversely,
when using hunk mode, *ALWAYS* use `g'; otherwise, you will only make one
replacement in the entire file!
";
my %options = ();
$Getopt::Long::ignorecase = 0;
&GetOptions (
\%options,
'help', 'backup-dir=s', 'line-mode', 'hunk-mode',
);
die $usage if $options{"help"} or @ARGV <= 1;
my $code = shift;
die $usage if grep (-d || ! -w, @ARGV);
sub SafeOpen {
open ((my $fh = new FileHandle), $_[0]);
confess "Can't open $_[0]: $!" if ! defined $fh;
return $fh;
}
sub SafeClose {
close $_[0] or confess "Can't close $_[0]: $!";
}
sub FileContents {
my $fh = SafeOpen ("< $_[0]");
my $olddollarslash = $/;
local $/ = undef;
my $contents = <$fh>;
$/ = $olddollarslash;
return $contents;
}
sub WriteStringToFile {
my $fh = SafeOpen ("> $_[0]");
binmode $fh;
print $fh $_[1] or confess "$_[0]: $!\n";
SafeClose $fh;
}
foreach my $file (@ARGV) {
my $changed_p = 0;
my $new_contents = "";
if ($options{"line-mode"}) {
my $fh = SafeOpen $file;
while (<$fh>) {
my $save_line = $_;
eval $code;
$changed_p = 1 if $save_line ne $_;
$new_contents .= $_;
}
} else {
my $orig_contents = $_ = FileContents $file;
eval $code;
if ($_ ne $orig_contents) {
$changed_p = 1;
$new_contents = $_;
}
}
if ($changed_p) {
my $backdir = $options{"backup-dir"};
$backdir = "backup" if !defined ($backdir);
if ($backdir) {
my ($name, $path, $suffix) = fileparse ($file, "");
my $backfulldir = $path . $backdir;
my $backfile = "$backfulldir/$name";
mkdir $backfulldir, 0755 unless -d $backfulldir;
print "modifying $file (original saved in $backfile)\n";
rename $file, $backfile;
}
WriteStringToFile ($file, $new_contents);
}
}
----------------------------------- cut ------------------------------------
In addition to those programs, I needed to fix up a few other
things, particularly relating to the duplicate definitions of
types, now that some types merged with others. Specifically:
1. in lisp.h, removed duplicate declarations of Bytecount. The
changed code should now look like this: (In each code snippet
below, the first and last lines are the same as the original, as
are all lines outside of those lines. That allows you to locate
the section to be replaced, and replace the stuff in that
section, verifying that there isn't anything new added that
would need to be kept.)
--------------------------------- snip -------------------------------------
/* Counts of bytes or chars */
typedef EMACS_INT Bytecount;
typedef EMACS_INT Charcount;
/* Counts of elements */
typedef EMACS_INT Elemcount;
/* Hash codes */
typedef unsigned long Hashcode;
/* ------------------------ dynamic arrays ------------------- */
--------------------------------- snip -------------------------------------
2. in lstream.h, removed duplicate declaration of Bytecount.
Rewrote the comment about this type. The changed code should
now look like this:
--------------------------------- snip -------------------------------------
#endif
/* The have been some arguments over the what the type should be that
specifies a count of bytes in a data block to be written out or read in,
using Lstream_read(), Lstream_write(), and related functions.
Originally it was long, which worked fine; Martin "corrected" these to
size_t and ssize_t on the grounds that this is theoretically cleaner and
is in keeping with the C standards. Unfortunately, this practice is
horribly error-prone due to design flaws in the way that mixed
signed/unsigned arithmetic happens. In fact, by doing this change,
Martin introduced a subtle but fatal error that caused the operation of
sending large mail messages to the SMTP server under Windows to fail.
By putting all values back to be signed, avoiding any signed/unsigned
mixing, the bug immediately went away. The type then in use was
Lstream_Data_Count, so that it be reverted cleanly if a vote came to
that. Now it is Bytecount.
Some earlier comments about why the type must be signed: This MUST BE
SIGNED, since it also is used in functions that return the number of
bytes actually read to or written from in an operation, and these
functions can return -1 to signal error.
Note that the standard Unix read() and write() functions define the
count going in as a size_t, which is UNSIGNED, and the count going
out as an ssize_t, which is SIGNED. This is a horrible design
flaw. Not only is it highly likely to lead to logic errors when a
-1 gets interpreted as a large positive number, but operations are
bound to fail in all sorts of horrible ways when a number in the
upper-half of the size_t range is passed in -- this number is
unrepresentable as an ssize_t, so code that checks to see how many
bytes are actually written (which is mandatory if you are dealing
with certain types of devices) will get completely screwed up.
--ben
*/
typedef enum lstream_buffering
--------------------------------- snip -------------------------------------
3. in dumper.c, there are four places, all inside of switch()
statements, where XD_BYTECOUNT appears twice as a case tag. In
each case, the two case blocks contain identical code, and you
should *REMOVE THE SECOND* and leave the first.
author | ben |
---|---|
date | Thu, 20 Sep 2001 06:31:11 +0000 |
parents | abe6d1db359e |
children | 943eaba38521 |
line wrap: on
line source
/* strftime - custom formatting of date and/or time Copyright (C) 1989, 1991, 1992 Free Software Foundation, Inc. This program is free software; you can redistribute it and/or modify it under the terms of the GNU General Public License as published by the Free Software Foundation; either version 2, or (at your option) any later version. This program is distributed in the hope that it will be useful, but WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for more details. You should have received a copy of the GNU General Public License along with this program; see the file COPYING. If not, write to the Free Software Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. */ /* Synched up with: FSF 19.30. */ /* Note: this version of strftime lacks locale support, but it is standalone. Performs `%' substitutions similar to those in printf. Except where noted, substituted fields have a fixed size; numeric fields are padded if necessary. Padding is with zeros by default; for fields that display a single number, padding can be changed or inhibited by following the `%' with one of the modifiers described below. Unknown field specifiers are copied as normal characters. All other characters are copied to the output without change. Supports a superset of the ANSI C field specifiers. Literal character fields: % % n newline t tab Numeric modifiers (a nonstandard extension): - do not pad the field _ pad the field with spaces Time fields: %H hour (00..23) %I hour (01..12) %k hour ( 0..23) %l hour ( 1..12) %M minute (00..59) %p locale's AM or PM %r time, 12-hour (hh:mm:ss [AP]M) %R time, 24-hour (hh:mm) %s time in seconds since 00:00:00, Jan 1, 1970 (a nonstandard extension) %S second (00..61) %T time, 24-hour (hh:mm:ss) %X locale's time representation (%H:%M:%S) %Z time zone (EDT), or nothing if no time zone is determinable Date fields: %a locale's abbreviated weekday name (Sun..Sat) %A locale's full weekday name, variable length (Sunday..Saturday) %b locale's abbreviated month name (Jan..Dec) %B locale's full month name, variable length (January..December) %c locale's date and time (Sat Nov 04 12:02:33 EST 1989) %C century (00..99) %d day of month (01..31) %e day of month ( 1..31) %D date (mm/dd/yy) %h same as %b %j day of year (001..366) %m month (01..12) %U week number of year with Sunday as first day of week (00..53) %w day of week (0..6) %W week number of year with Monday as first day of week (00..53) %x locale's date representation (mm/dd/yy) %y last two digits of year (00..99) %Y year (1970...) David MacKenzie <djm@gnu.ai.mit.edu> */ #ifdef HAVE_CONFIG_H #include <config.h> #include "lisp.h" #endif #include <stdio.h> #include <sys/types.h> #if defined(TM_IN_SYS_TIME) || (!defined(HAVE_TM_ZONE) && !defined(HAVE_TZNAME)) #include <sys/time.h> #else #include <time.h> #endif #ifndef STDC_HEADERS time_t mktime (); #endif #if defined(WIN32_NATIVE) || defined(CYGWIN) #include <time.h> #else #if defined(HAVE_TZNAME) extern char *tzname[2]; #endif #endif /* WIN32_NATIVE */ #ifdef emacs #define strftime emacs_strftime #endif /* Types of padding for numbers in date and time. */ enum padding { none, blank, zero }; static char const* const days[] = { "Sunday", "Monday", "Tuesday", "Wednesday", "Thursday", "Friday", "Saturday" }; static char const * const months[] = { "January", "February", "March", "April", "May", "June", "July", "August", "September", "October", "November", "December" }; /* Add character C to STRING and increment LENGTH, unless LENGTH would exceed MAX. */ #define add_char(c) do \ { \ if (length + 1 <= max) \ string[length++] = (c); \ } while (0) /* Add a 2 digit number to STRING, padding if specified. Return the number of characters added, up to MAX. */ static int add_num2 (char *string, int num, int max, enum padding pad) { int top = num / 10; int length = 0; if (top == 0 && pad == blank) add_char (' '); else if (top != 0 || pad == zero) add_char (top + '0'); add_char (num % 10 + '0'); return length; } /* Add a 3 digit number to STRING, padding if specified. Return the number of characters added, up to MAX. */ static int add_num3 (char *string, int num, int max, enum padding pad) { int top = num / 100; int mid = (num - top * 100) / 10; int length = 0; if (top == 0 && pad == blank) add_char (' '); else if (top != 0 || pad == zero) add_char (top + '0'); if (mid == 0 && top == 0 && pad == blank) add_char (' '); else if (mid != 0 || top != 0 || pad == zero) add_char (mid + '0'); add_char (num % 10 + '0'); return length; } /* Like strncpy except return the number of characters copied. */ static int add_str (char *to, const char *from, int max) { int i; for (i = 0; from[i] && i <= max; ++i) to[i] = from[i]; return i; } static int add_num_time_t (char *string, int max, time_t num) { /* This buffer is large enough to hold the character representation (including the trailing NUL) of any unsigned decimal quantity whose binary representation fits in 128 bits. */ char buf[40]; int length; if (sizeof (num) > 16) abort (); sprintf (buf, "%lu", (unsigned long) num); length = add_str (string, buf, max); return length; } /* Return the week in the year of the time in TM, with the weeks starting on Sundays. */ static int sun_week (const struct tm *tm) { int dl; /* Set `dl' to the day in the year of the last day of the week previous to the one containing the day specified in TM. If the day specified in TM is in the first week of the year, `dl' will be negative or 0. Otherwise, calculate the number of complete weeks before our week (dl / 7) and add any partial week at the start of the year (dl % 7). */ dl = tm->tm_yday - tm->tm_wday; return dl <= 0 ? 0 : dl / 7 + (dl % 7 != 0); } /* Return the week in the year of the time in TM, with the weeks starting on Mondays. */ static int mon_week (const struct tm *tm) { int dl, wday; if (tm->tm_wday == 0) wday = 6; else wday = tm->tm_wday - 1; dl = tm->tm_yday - wday; return dl <= 0 ? 0 : dl / 7 + (dl % 7 != 0); } #if !defined(HAVE_TM_ZONE) && !defined(HAVE_TZNAME) char *zone_name (const struct tm *tp); char * zone_name (const struct tm *tp) { char *timezone (); struct timeval tv; struct timezone tz; gettimeofday (&tv, &tz); return timezone (tz.tz_minuteswest, tp->tm_isdst); } #endif /* Format the time given in TM according to FORMAT, and put the results in STRING. Return the number of characters (not including terminating null) that were put into STRING, or 0 if the length would have exceeded MAX. */ size_t strftime (char *string, size_t max, const char *format, const struct tm *tm); size_t strftime (char *string, size_t max, const char *format, const struct tm *tm) { enum padding pad; /* Type of padding to apply. */ size_t length = 0; /* Characters put in STRING so far. */ for (; *format && length < max; ++format) { if (*format != '%') add_char (*format); else { ++format; /* Modifiers: */ if (*format == '-') { pad = none; ++format; } else if (*format == '_') { pad = blank; ++format; } else pad = zero; switch (*format) { /* Literal character fields: */ case 0: case '%': add_char ('%'); break; case 'n': add_char ('\n'); break; case 't': add_char ('\t'); break; default: add_char (*format); break; /* Time fields: */ case 'H': case 'k': length += add_num2 (&string[length], tm->tm_hour, max - length, *format == 'H' ? pad : blank); break; case 'I': case 'l': { int hour12; if (tm->tm_hour == 0) hour12 = 12; else if (tm->tm_hour > 12) hour12 = tm->tm_hour - 12; else hour12 = tm->tm_hour; length += add_num2 (&string[length], hour12, max - length, *format == 'I' ? pad : blank); } break; case 'M': length += add_num2 (&string[length], tm->tm_min, max - length, pad); break; case 'p': if (tm->tm_hour < 12) add_char ('A'); else add_char ('P'); add_char ('M'); break; case 'r': length += strftime (&string[length], max - length, "%I:%M:%S %p", tm); break; case 'R': length += strftime (&string[length], max - length, "%H:%M", tm); break; case 's': { struct tm writable_tm; writable_tm = *tm; length += add_num_time_t (&string[length], max - length, mktime (&writable_tm)); } break; case 'S': length += add_num2 (&string[length], tm->tm_sec, max - length, pad); break; case 'T': length += strftime (&string[length], max - length, "%H:%M:%S", tm); break; case 'X': length += strftime (&string[length], max - length, "%H:%M:%S", tm); break; case 'Z': #ifdef HAVE_TM_ZONE length += add_str (&string[length], tm->tm_zone, max - length); #else #ifdef HAVE_TZNAME if (tm->tm_isdst && tzname[1] && *tzname[1]) length += add_str (&string[length], tzname[1], max - length); else length += add_str (&string[length], tzname[0], max - length); #else length += add_str (&string[length], zone_name (tm), max - length); #endif #endif break; /* Date fields: */ case 'a': add_char (days[tm->tm_wday][0]); add_char (days[tm->tm_wday][1]); add_char (days[tm->tm_wday][2]); break; case 'A': length += add_str (&string[length], days[tm->tm_wday], max - length); break; case 'b': case 'h': add_char (months[tm->tm_mon][0]); add_char (months[tm->tm_mon][1]); add_char (months[tm->tm_mon][2]); break; case 'B': length += add_str (&string[length], months[tm->tm_mon], max - length); break; case 'c': length += strftime (&string[length], max - length, "%a %b %d %H:%M:%S %Z %Y", tm); break; case 'C': length += add_num2 (&string[length], (tm->tm_year + 1900) / 100, max - length, pad); break; case 'd': length += add_num2 (&string[length], tm->tm_mday, max - length, pad); break; case 'e': length += add_num2 (&string[length], tm->tm_mday, max - length, blank); break; case 'D': length += strftime (&string[length], max - length, "%m/%d/%y", tm); break; case 'j': length += add_num3 (&string[length], tm->tm_yday + 1, max - length, pad); break; case 'm': length += add_num2 (&string[length], tm->tm_mon + 1, max - length, pad); break; case 'U': length += add_num2 (&string[length], sun_week (tm), max - length, pad); break; case 'w': add_char (tm->tm_wday + '0'); break; case 'W': length += add_num2 (&string[length], mon_week (tm), max - length, pad); break; case 'x': length += strftime (&string[length], max - length, "%m/%d/%y", tm); break; case 'y': length += add_num2 (&string[length], tm->tm_year % 100, max - length, pad); break; case 'Y': add_char ((tm->tm_year + 1900) / 1000 + '0'); length += add_num3 (&string[length], (1900 + tm->tm_year) % 1000, max - length, zero); break; } } } add_char (0); return length - 1; }