Mercurial > hg > xemacs-beta
diff src/file-coding.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 | b39c14581166 |
| children | 943eaba38521 |
line wrap: on
line diff
--- a/src/file-coding.c Tue Sep 18 05:06:57 2001 +0000 +++ b/src/file-coding.c Thu Sep 20 06:31:11 2001 +0000 @@ -174,47 +174,47 @@ #ifdef MULE struct detection_state; static int detect_coding_sjis (struct detection_state *st, - const Extbyte *src, Lstream_Data_Count n); + const Extbyte *src, Bytecount n); static void decode_coding_sjis (Lstream *decoding, const Extbyte *src, - unsigned_char_dynarr *dst, Lstream_Data_Count n); -static void encode_coding_sjis (Lstream *encoding, const Bufbyte *src, - unsigned_char_dynarr *dst, Lstream_Data_Count n); + unsigned_char_dynarr *dst, Bytecount n); +static void encode_coding_sjis (Lstream *encoding, const Intbyte *src, + unsigned_char_dynarr *dst, Bytecount n); static int detect_coding_big5 (struct detection_state *st, - const Extbyte *src, Lstream_Data_Count n); + const Extbyte *src, Bytecount n); static void decode_coding_big5 (Lstream *decoding, const Extbyte *src, - unsigned_char_dynarr *dst, Lstream_Data_Count n); -static void encode_coding_big5 (Lstream *encoding, const Bufbyte *src, - unsigned_char_dynarr *dst, Lstream_Data_Count n); + unsigned_char_dynarr *dst, Bytecount n); +static void encode_coding_big5 (Lstream *encoding, const Intbyte *src, + unsigned_char_dynarr *dst, Bytecount n); static int detect_coding_ucs4 (struct detection_state *st, - const Extbyte *src, Lstream_Data_Count n); + const Extbyte *src, Bytecount n); static void decode_coding_ucs4 (Lstream *decoding, const Extbyte *src, - unsigned_char_dynarr *dst, Lstream_Data_Count n); -static void encode_coding_ucs4 (Lstream *encoding, const Bufbyte *src, - unsigned_char_dynarr *dst, Lstream_Data_Count n); + unsigned_char_dynarr *dst, Bytecount n); +static void encode_coding_ucs4 (Lstream *encoding, const Intbyte *src, + unsigned_char_dynarr *dst, Bytecount n); static int detect_coding_utf8 (struct detection_state *st, - const Extbyte *src, Lstream_Data_Count n); + const Extbyte *src, Bytecount n); static void decode_coding_utf8 (Lstream *decoding, const Extbyte *src, - unsigned_char_dynarr *dst, Lstream_Data_Count n); -static void encode_coding_utf8 (Lstream *encoding, const Bufbyte *src, - unsigned_char_dynarr *dst, Lstream_Data_Count n); + unsigned_char_dynarr *dst, Bytecount n); +static void encode_coding_utf8 (Lstream *encoding, const Intbyte *src, + unsigned_char_dynarr *dst, Bytecount n); static int postprocess_iso2022_mask (int mask); static void reset_iso2022 (Lisp_Object coding_system, struct iso2022_decoder *iso); static int detect_coding_iso2022 (struct detection_state *st, - const Extbyte *src, Lstream_Data_Count n); + const Extbyte *src, Bytecount n); static void decode_coding_iso2022 (Lstream *decoding, const Extbyte *src, - unsigned_char_dynarr *dst, Lstream_Data_Count n); -static void encode_coding_iso2022 (Lstream *encoding, const Bufbyte *src, - unsigned_char_dynarr *dst, Lstream_Data_Count n); + unsigned_char_dynarr *dst, Bytecount n); +static void encode_coding_iso2022 (Lstream *encoding, const Intbyte *src, + unsigned_char_dynarr *dst, Bytecount n); #endif /* MULE */ static void decode_coding_no_conversion (Lstream *decoding, const Extbyte *src, - unsigned_char_dynarr *dst, Lstream_Data_Count n); -static void encode_coding_no_conversion (Lstream *encoding, const Bufbyte *src, - unsigned_char_dynarr *dst, Lstream_Data_Count n); + unsigned_char_dynarr *dst, Bytecount n); +static void encode_coding_no_conversion (Lstream *encoding, const Intbyte *src, + unsigned_char_dynarr *dst, Bytecount n); static void mule_decode (Lstream *decoding, const Extbyte *src, - unsigned_char_dynarr *dst, Lstream_Data_Count n); -static void mule_encode (Lstream *encoding, const Bufbyte *src, - unsigned_char_dynarr *dst, Lstream_Data_Count n); + unsigned_char_dynarr *dst, Bytecount n); +static void mule_encode (Lstream *encoding, const Intbyte *src, + unsigned_char_dynarr *dst, Bytecount n); typedef struct codesys_prop codesys_prop; struct codesys_prop @@ -1617,7 +1617,7 @@ static eol_type_t detect_eol_type (struct detection_state *st, const Extbyte *src, - Lstream_Data_Count n) + Bytecount n) { while (n--) { @@ -1660,7 +1660,7 @@ static int detect_coding_type (struct detection_state *st, const Extbyte *src, - Lstream_Data_Count n, int just_do_eol) + Bytecount n, int just_do_eol) { if (st->eol_type == EOL_AUTODETECT) st->eol_type = detect_eol_type (st, src, n); @@ -1791,7 +1791,7 @@ Extbyte buf[4096]; Lisp_Object coding_system = Qnil; Extbyte *p; - Lstream_Data_Count nread = Lstream_read (stream, buf, sizeof (buf)); + Bytecount nread = Lstream_read (stream, buf, sizeof (buf)); Extbyte *scan_end; /* Look for initial "-*-"; mode line prefix */ @@ -1907,7 +1907,7 @@ { Lisp_Object val = Qnil; struct buffer *buf = decode_buffer (buffer, 0); - Bufpos b, e; + Charbpos b, e; Lisp_Object instream, lb_instream; Lstream *istr, *lb_istr; struct detection_state decst; @@ -1925,7 +1925,7 @@ while (1) { Extbyte random_buffer[4096]; - Lstream_Data_Count nread = Lstream_read (istr, random_buffer, sizeof (random_buffer)); + Bytecount nread = Lstream_read (istr, random_buffer, sizeof (random_buffer)); if (!nread) break; @@ -2092,10 +2092,10 @@ struct detection_state decst; }; -static Lstream_Data_Count decoding_reader (Lstream *stream, - unsigned char *data, Lstream_Data_Count size); -static Lstream_Data_Count decoding_writer (Lstream *stream, - const unsigned char *data, Lstream_Data_Count size); +static Bytecount decoding_reader (Lstream *stream, + unsigned char *data, Bytecount size); +static Bytecount decoding_writer (Lstream *stream, + const unsigned char *data, Bytecount size); static int decoding_rewinder (Lstream *stream); static int decoding_seekable_p (Lstream *stream); static int decoding_flusher (Lstream *stream); @@ -2127,12 +2127,12 @@ /* Read SIZE bytes of data and store it into DATA. We are a decoding stream so we read data from the other end, decode it, and store it into DATA. */ -static Lstream_Data_Count -decoding_reader (Lstream *stream, unsigned char *data, Lstream_Data_Count size) +static Bytecount +decoding_reader (Lstream *stream, unsigned char *data, Bytecount size) { struct decoding_stream *str = DECODING_STREAM_DATA (stream); unsigned char *orig_data = data; - Lstream_Data_Count read_size; + Bytecount read_size; int error_occurred = 0; /* We need to interface to mule_decode(), which expects to take some @@ -2148,7 +2148,7 @@ most SIZE bytes, and delete the data from the runoff. */ if (Dynarr_length (str->runoff) > 0) { - Lstream_Data_Count chunk = min (size, (Lstream_Data_Count) Dynarr_length (str->runoff)); + Bytecount chunk = min (size, (Bytecount) Dynarr_length (str->runoff)); memcpy (data, Dynarr_atp (str->runoff, 0), chunk); Dynarr_delete_many (str->runoff, 0, chunk); data += chunk; @@ -2189,11 +2189,11 @@ return data - orig_data; } -static Lstream_Data_Count -decoding_writer (Lstream *stream, const unsigned char *data, Lstream_Data_Count size) +static Bytecount +decoding_writer (Lstream *stream, const unsigned char *data, Bytecount size) { struct decoding_stream *str = DECODING_STREAM_DATA (stream); - Lstream_Data_Count retval; + Bytecount retval; /* Decode all our data into the runoff, and then attempt to write it all out to the other end. Remove whatever chunk we succeeded @@ -2351,7 +2351,7 @@ static void mule_decode (Lstream *decoding, const Extbyte *src, - unsigned_char_dynarr *dst, Lstream_Data_Count n) + unsigned_char_dynarr *dst, Bytecount n) { struct decoding_stream *str = DECODING_STREAM_DATA (decoding); @@ -2439,7 +2439,7 @@ */ (start, end, coding_system, buffer)) { - Bufpos b, e; + Charbpos b, e; struct buffer *buf = decode_buffer (buffer, 0); Lisp_Object instream, lb_outstream, de_outstream, outstream; Lstream *istr, *ostr; @@ -2471,9 +2471,9 @@ while (1) { char tempbuf[1024]; /* some random amount */ - Bufpos newpos, even_newer_pos; - Bufpos oldpos = lisp_buffer_stream_startpos (istr); - Lstream_Data_Count size_in_bytes = Lstream_read (istr, tempbuf, sizeof (tempbuf)); + Charbpos newpos, even_newer_pos; + Charbpos oldpos = lisp_buffer_stream_startpos (istr); + Bytecount size_in_bytes = Lstream_read (istr, tempbuf, sizeof (tempbuf)); if (!size_in_bytes) break; @@ -2558,9 +2558,9 @@ #endif /* MULE */ }; -static Lstream_Data_Count encoding_reader (Lstream *stream, unsigned char *data, Lstream_Data_Count size); -static Lstream_Data_Count encoding_writer (Lstream *stream, const unsigned char *data, - Lstream_Data_Count size); +static Bytecount encoding_reader (Lstream *stream, unsigned char *data, Bytecount size); +static Bytecount encoding_writer (Lstream *stream, const unsigned char *data, + Bytecount size); static int encoding_rewinder (Lstream *stream); static int encoding_seekable_p (Lstream *stream); static int encoding_flusher (Lstream *stream); @@ -2592,12 +2592,12 @@ /* Read SIZE bytes of data and store it into DATA. We are a encoding stream so we read data from the other end, encode it, and store it into DATA. */ -static Lstream_Data_Count -encoding_reader (Lstream *stream, unsigned char *data, Lstream_Data_Count size) +static Bytecount +encoding_reader (Lstream *stream, unsigned char *data, Bytecount size) { struct encoding_stream *str = ENCODING_STREAM_DATA (stream); unsigned char *orig_data = data; - Lstream_Data_Count read_size; + Bytecount read_size; int error_occurred = 0; /* We need to interface to mule_encode(), which expects to take some @@ -2654,11 +2654,11 @@ return data - orig_data; } -static Lstream_Data_Count -encoding_writer (Lstream *stream, const unsigned char *data, Lstream_Data_Count size) +static Bytecount +encoding_writer (Lstream *stream, const unsigned char *data, Bytecount size) { struct encoding_stream *str = ENCODING_STREAM_DATA (stream); - Lstream_Data_Count retval; + Bytecount retval; /* Encode all our data into the runoff, and then attempt to write it all out to the other end. Remove whatever chunk we succeeded @@ -2797,8 +2797,8 @@ Store the encoded data into DST. */ static void -mule_encode (Lstream *encoding, const Bufbyte *src, - unsigned_char_dynarr *dst, Lstream_Data_Count n) +mule_encode (Lstream *encoding, const Intbyte *src, + unsigned_char_dynarr *dst, Bytecount n) { struct encoding_stream *str = ENCODING_STREAM_DATA (encoding); @@ -2852,7 +2852,7 @@ */ (start, end, coding_system, buffer)) { - Bufpos b, e; + Charbpos b, e; struct buffer *buf = decode_buffer (buffer, 0); Lisp_Object instream, lb_outstream, de_outstream, outstream; Lstream *istr, *ostr; @@ -2882,9 +2882,9 @@ while (1) { char tempbuf[1024]; /* some random amount */ - Bufpos newpos, even_newer_pos; - Bufpos oldpos = lisp_buffer_stream_startpos (istr); - Lstream_Data_Count size_in_bytes = Lstream_read (istr, tempbuf, sizeof (tempbuf)); + Charbpos newpos, even_newer_pos; + Charbpos oldpos = lisp_buffer_stream_startpos (istr); + Bytecount size_in_bytes = Lstream_read (istr, tempbuf, sizeof (tempbuf)); if (!size_in_bytes) break; @@ -2947,7 +2947,7 @@ ((c) >= 0xA1 && (c) <= 0xDF) static int -detect_coding_sjis (struct detection_state *st, const Extbyte *src, Lstream_Data_Count n) +detect_coding_sjis (struct detection_state *st, const Extbyte *src, Bytecount n) { while (n--) { @@ -2970,7 +2970,7 @@ static void decode_coding_sjis (Lstream *decoding, const Extbyte *src, - unsigned_char_dynarr *dst, Lstream_Data_Count n) + unsigned_char_dynarr *dst, Bytecount n) { struct decoding_stream *str = DECODING_STREAM_DATA (decoding); unsigned int flags = str->flags; @@ -3025,8 +3025,8 @@ /* Convert internally-formatted data to Shift-JIS. */ static void -encode_coding_sjis (Lstream *encoding, const Bufbyte *src, - unsigned_char_dynarr *dst, Lstream_Data_Count n) +encode_coding_sjis (Lstream *encoding, const Intbyte *src, + unsigned_char_dynarr *dst, Bytecount n) { struct encoding_stream *str = ENCODING_STREAM_DATA (encoding); unsigned int flags = str->flags; @@ -3035,7 +3035,7 @@ while (n--) { - Bufbyte c = *src++; + Intbyte c = *src++; if (c == '\n') { if (eol_type != EOL_LF && eol_type != EOL_AUTODETECT) @@ -3049,7 +3049,7 @@ Dynarr_add (dst, c); ch = 0; } - else if (BUFBYTE_LEADING_BYTE_P (c)) + else if (INTBYTE_LEADING_BYTE_P (c)) ch = (c == LEADING_BYTE_KATAKANA_JISX0201 || c == LEADING_BYTE_JAPANESE_JISX0208_1978 || c == LEADING_BYTE_JAPANESE_JISX0208) ? c : 0; @@ -3228,7 +3228,7 @@ } while (0) static int -detect_coding_big5 (struct detection_state *st, const Extbyte *src, Lstream_Data_Count n) +detect_coding_big5 (struct detection_state *st, const Extbyte *src, Bytecount n) { while (n--) { @@ -3252,7 +3252,7 @@ static void decode_coding_big5 (Lstream *decoding, const Extbyte *src, - unsigned_char_dynarr *dst, Lstream_Data_Count n) + unsigned_char_dynarr *dst, Bytecount n) { struct decoding_stream *str = DECODING_STREAM_DATA (decoding); unsigned int flags = str->flags; @@ -3300,8 +3300,8 @@ /* Convert internally-formatted data to Big5. */ static void -encode_coding_big5 (Lstream *encoding, const Bufbyte *src, - unsigned_char_dynarr *dst, Lstream_Data_Count n) +encode_coding_big5 (Lstream *encoding, const Intbyte *src, + unsigned_char_dynarr *dst, Bytecount n) { unsigned char c; struct encoding_stream *str = ENCODING_STREAM_DATA (encoding); @@ -3324,7 +3324,7 @@ /* ASCII. */ Dynarr_add (dst, c); } - else if (BUFBYTE_LEADING_BYTE_P (c)) + else if (INTBYTE_LEADING_BYTE_P (c)) { if (c == LEADING_BYTE_CHINESE_BIG5_1 || c == LEADING_BYTE_CHINESE_BIG5_2) @@ -3505,7 +3505,7 @@ if (! NILP (chr)) { - Bufbyte work[MAX_EMCHAR_LEN]; + Intbyte work[MAX_EMCHAR_LEN]; int len; ch = XCHAR (chr); @@ -3567,7 +3567,7 @@ } static int -detect_coding_ucs4 (struct detection_state *st, const Extbyte *src, Lstream_Data_Count n) +detect_coding_ucs4 (struct detection_state *st, const Extbyte *src, Bytecount n) { while (n--) { @@ -3592,7 +3592,7 @@ static void decode_coding_ucs4 (Lstream *decoding, const Extbyte *src, - unsigned_char_dynarr *dst, Lstream_Data_Count n) + unsigned_char_dynarr *dst, Bytecount n) { struct decoding_stream *str = DECODING_STREAM_DATA (decoding); unsigned int flags = str->flags; @@ -3627,8 +3627,8 @@ } static void -encode_coding_ucs4 (Lstream *encoding, const Bufbyte *src, - unsigned_char_dynarr *dst, Lstream_Data_Count n) +encode_coding_ucs4 (Lstream *encoding, const Intbyte *src, + unsigned_char_dynarr *dst, Bytecount n) { struct encoding_stream *str = ENCODING_STREAM_DATA (encoding); unsigned int flags = str->flags; @@ -3639,7 +3639,7 @@ #ifdef ENABLE_COMPOSITE_CHARS /* flags for handling composite chars. We do a little switcharoo on the source while we're outputting the composite char. */ - Lstream_Data_Count saved_n = 0; + Bytecount saved_n = 0; const unsigned char *saved_src = NULL; int in_composite = 0; @@ -3656,7 +3656,7 @@ encode_ucs4 (Vcharset_ascii, c, 0, dst); char_boundary = 1; } - else if (BUFBYTE_LEADING_BYTE_P (c) || BUFBYTE_LEADING_BYTE_P (ch)) + else if (INTBYTE_LEADING_BYTE_P (c) || INTBYTE_LEADING_BYTE_P (ch)) { /* Processing Leading Byte */ ch = 0; charset = CHARSET_BY_LEADING_BYTE (c); @@ -3766,7 +3766,7 @@ /************************************************************************/ static int -detect_coding_utf8 (struct detection_state *st, const Extbyte *src, Lstream_Data_Count n) +detect_coding_utf8 (struct detection_state *st, const Extbyte *src, Bytecount n) { while (n--) { @@ -3801,7 +3801,7 @@ static void decode_coding_utf8 (Lstream *decoding, const Extbyte *src, - unsigned_char_dynarr *dst, Lstream_Data_Count n) + unsigned_char_dynarr *dst, Bytecount n) { struct decoding_stream *str = DECODING_STREAM_DATA (decoding); unsigned int flags = str->flags; @@ -3914,8 +3914,8 @@ } static void -encode_coding_utf8 (Lstream *encoding, const Bufbyte *src, - unsigned_char_dynarr *dst, Lstream_Data_Count n) +encode_coding_utf8 (Lstream *encoding, const Intbyte *src, + unsigned_char_dynarr *dst, Bytecount n) { struct encoding_stream *str = ENCODING_STREAM_DATA (encoding); unsigned int flags = str->flags; @@ -3927,7 +3927,7 @@ #ifdef ENABLE_COMPOSITE_CHARS /* flags for handling composite chars. We do a little switcharoo on the source while we're outputting the composite char. */ - Lstream_Data_Count saved_n = 0; + Bytecount saved_n = 0; const unsigned char *saved_src = NULL; int in_composite = 0; @@ -3952,7 +3952,7 @@ encode_utf8 (Vcharset_ascii, c, 0, dst); char_boundary = 1; } - else if (BUFBYTE_LEADING_BYTE_P (c) || BUFBYTE_LEADING_BYTE_P (ch)) + else if (INTBYTE_LEADING_BYTE_P (c) || INTBYTE_LEADING_BYTE_P (ch)) { /* Processing Leading Byte */ ch = 0; charset = CHARSET_BY_LEADING_BYTE (c); @@ -4674,7 +4674,7 @@ } static int -detect_coding_iso2022 (struct detection_state *st, const Extbyte *src, Lstream_Data_Count n) +detect_coding_iso2022 (struct detection_state *st, const Extbyte *src, Bytecount n) { int mask; @@ -4865,7 +4865,7 @@ static void decode_coding_iso2022 (Lstream *decoding, const Extbyte *src, - unsigned_char_dynarr *dst, Lstream_Data_Count n) + unsigned_char_dynarr *dst, Bytecount n) { struct decoding_stream *str = DECODING_STREAM_DATA (decoding); unsigned int flags = str->flags; @@ -4905,7 +4905,7 @@ break; case ISO_ESC_END_COMPOSITE: { - Bufbyte comstr[MAX_EMCHAR_LEN]; + Intbyte comstr[MAX_EMCHAR_LEN]; Bytecount len; Emchar emch = lookup_composite_char (Dynarr_atp (dst, 0), Dynarr_length (dst)); @@ -5190,8 +5190,8 @@ /* Convert internally-formatted data to ISO2022 format. */ static void -encode_coding_iso2022 (Lstream *encoding, const Bufbyte *src, - unsigned_char_dynarr *dst, Lstream_Data_Count n) +encode_coding_iso2022 (Lstream *encoding, const Intbyte *src, + unsigned_char_dynarr *dst, Bytecount n) { unsigned char charmask, c; unsigned char char_boundary; @@ -5207,7 +5207,7 @@ #ifdef ENABLE_COMPOSITE_CHARS /* flags for handling composite chars. We do a little switcharoo on the source while we're outputting the composite char. */ - Lstream_Data_Count saved_n = 0; + Bytecount saved_n = 0; const unsigned char *saved_src = NULL; int in_composite = 0; #endif /* ENABLE_COMPOSITE_CHARS */ @@ -5270,7 +5270,7 @@ char_boundary = 1; } - else if (BUFBYTE_LEADING_BYTE_P (c) || BUFBYTE_LEADING_BYTE_P (ch)) + else if (INTBYTE_LEADING_BYTE_P (c) || INTBYTE_LEADING_BYTE_P (ch)) { /* Processing Leading Byte */ ch = 0; charset = CHARSET_BY_LEADING_BYTE (c); @@ -5500,7 +5500,7 @@ interpreted as being in any particular decoding. */ static void decode_coding_no_conversion (Lstream *decoding, const Extbyte *src, - unsigned_char_dynarr *dst, Lstream_Data_Count n) + unsigned_char_dynarr *dst, Bytecount n) { struct decoding_stream *str = DECODING_STREAM_DATA (decoding); unsigned int flags = str->flags; @@ -5523,8 +5523,8 @@ } static void -encode_coding_no_conversion (Lstream *encoding, const Bufbyte *src, - unsigned_char_dynarr *dst, Lstream_Data_Count n) +encode_coding_no_conversion (Lstream *encoding, const Intbyte *src, + unsigned_char_dynarr *dst, Bytecount n) { unsigned char c; struct encoding_stream *str = ENCODING_STREAM_DATA (encoding); @@ -5548,7 +5548,7 @@ assert (ch == 0); Dynarr_add (dst, c); } - else if (BUFBYTE_LEADING_BYTE_P (c)) + else if (INTBYTE_LEADING_BYTE_P (c)) { assert (ch == 0); if (c == LEADING_BYTE_LATIN_ISO8859_1 ||