Mercurial > hg > xemacs-beta
view src/syntax.h @ 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 | 223736d75acb |
| children | 943eaba38521 |
line wrap: on
line source
/* Declarations having to do with XEmacs syntax tables. Copyright (C) 1985, 1992, 1993 Free Software Foundation, Inc. This file is part of XEmacs. XEmacs 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. XEmacs 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. */ /* Synched up with: FSF 19.28. */ #ifndef INCLUDED_syntax_h_ #define INCLUDED_syntax_h_ #include "chartab.h" /* A syntax table is a type of char table. The low 7 bits of the integer is a code, as follows. The 8th bit is used as the prefix bit flag (see below). The values in a syntax table are either integers or conses of integers and chars. The lowest 7 bits of the integer are the syntax class. If this is Sinherit, then the actual syntax value needs to be retrieved from the standard syntax table. Since the logic involved in finding the actual integer isn't very complex, you'd think the time required to retrieve it is not a factor. If you thought that, however, you'd be wrong, due to the high number of times (many per character) that the syntax value is accessed in functions such as scan_lists(). To speed this up, we maintain a mirror syntax table that contains the actual integers. We can do this successfully because syntax tables are now an abstract type, where we control all access. */ enum syntaxcode { Swhitespace, /* whitespace character */ Spunct, /* random punctuation character */ Sword, /* word constituent */ Ssymbol, /* symbol constituent but not word constituent */ Sopen, /* a beginning delimiter */ Sclose, /* an ending delimiter */ Squote, /* a prefix character like Lisp ' */ Sstring, /* a string-grouping character like Lisp " */ Smath, /* delimiters like $ in TeX. */ Sescape, /* a character that begins a C-style escape */ Scharquote, /* a character that quotes the following character */ Scomment, /* a comment-starting character */ Sendcomment, /* a comment-ending character */ Sinherit, /* use the standard syntax table for this character */ Scomment_fence, /* Starts/ends comment which is delimited on the other side by a char with the same syntaxcode. */ Sstring_fence, /* Starts/ends string which is delimited on the other side by a char with the same syntaxcode. */ Smax /* Upper bound on codes that are meaningful */ }; enum syntaxcode charset_syntax (struct buffer *buf, Lisp_Object charset, int *multi_p_out); /* Return the syntax code for a particular character and mirror table. */ #define SYNTAX_CODE_UNSAFE(table, c) \ XINT (CHAR_TABLE_VALUE_UNSAFE (table, c)) INLINE_HEADER int SYNTAX_CODE (Lisp_Char_Table *table, Emchar c); INLINE_HEADER int SYNTAX_CODE (Lisp_Char_Table *table, Emchar c) { return SYNTAX_CODE_UNSAFE (table, c); } #define SYNTAX_UNSAFE(table, c) \ ((enum syntaxcode) (SYNTAX_CODE_UNSAFE (table, c) & 0177)) #define SYNTAX_FROM_CODE(code) ((enum syntaxcode) ((code) & 0177)) #define SYNTAX(table, c) SYNTAX_FROM_CODE (SYNTAX_CODE (table, c)) INLINE_HEADER int WORD_SYNTAX_P (Lisp_Char_Table *table, Emchar c); INLINE_HEADER int WORD_SYNTAX_P (Lisp_Char_Table *table, Emchar c) { return SYNTAX (table, c) == Sword; } /* OK, here's a graphic diagram of the format of the syntax values: Bit number: [ 3 3 2 2 2 2 2 2 2 2 2 2 1 1 1 1 1 1 1 1 1 1 0 0 0 0 0 0 0 0 0 0 ] [ 1 0 9 8 7 6 5 4 3 2 1 0 9 8 7 6 5 4 3 2 1 0 9 8 7 6 5 4 3 2 1 0 ] <-----> <-----> <-------------> <-------------> ^ <-----------> ELisp unused |comment bits | unused | syntax code tag | | | | | | | | | stuff | | | | | | | | | | | | | | | | | | | | | | | | | | `--> prefix flag | | | | | | | | | | | | | | | `--> comment end style B, second char | | | | | | `----> comment end style A, second char | | | | | `------> comment end style B, first char | | | | `--------> comment end style A, first char | | | `----------> comment start style B, second char | | `------------> comment start style A, second char | `--------------> comment start style B, first char `----------------> comment start style A, first char In a 64-bit integer, there would be 32 more unused bits between the tag and the comment bits. Clearly, such a scheme will not work for Mule, because the matching paren could be any character and as such requires 19 bits, which we don't got. Remember that under Mule we use char tables instead of vectors. So what we do is use another char table for the matching paren and store a pointer to it in the first char table. (This frees code from having to worry about passing two tables around.) */ /* The prefix flag bit for backward-prefix-chars is now put into bit 7. */ #define SYNTAX_PREFIX_UNSAFE(table, c) \ ((SYNTAX_CODE_UNSAFE (table, c) >> 7) & 1) #define SYNTAX_PREFIX(table, c) \ ((SYNTAX_CODE (table, c) >> 7) & 1) /* Bits 23-16 are used to implement up to two comment styles in a single buffer. They have the following meanings: 1. first of a one or two character comment-start sequence of style a. 2. first of a one or two character comment-start sequence of style b. 3. second of a two-character comment-start sequence of style a. 4. second of a two-character comment-start sequence of style b. 5. first of a one or two character comment-end sequence of style a. 6. first of a one or two character comment-end sequence of style b. 7. second of a two-character comment-end sequence of style a. 8. second of a two-character comment-end sequence of style b. */ #define SYNTAX_COMMENT_BITS(table, c) \ ((SYNTAX_CODE (table, c) >> 16) &0xff) #define SYNTAX_FIRST_OF_START_A 0x80 #define SYNTAX_FIRST_OF_START_B 0x40 #define SYNTAX_SECOND_OF_START_A 0x20 #define SYNTAX_SECOND_OF_START_B 0x10 #define SYNTAX_FIRST_OF_END_A 0x08 #define SYNTAX_FIRST_OF_END_B 0x04 #define SYNTAX_SECOND_OF_END_A 0x02 #define SYNTAX_SECOND_OF_END_B 0x01 #define SYNTAX_COMMENT_STYLE_A 0xaa #define SYNTAX_COMMENT_STYLE_B 0x55 #define SYNTAX_FIRST_CHAR_START 0xc0 #define SYNTAX_FIRST_CHAR_END 0x0c #define SYNTAX_FIRST_CHAR 0xcc #define SYNTAX_SECOND_CHAR_START 0x30 #define SYNTAX_SECOND_CHAR_END 0x03 #define SYNTAX_SECOND_CHAR 0x33 /* #### These are now more or less equivalent to SYNTAX_COMMENT_MATCH_START ...*/ /* a and b must be first and second start chars for a common type */ #define SYNTAX_START_P(table, a, b) \ (((SYNTAX_COMMENT_BITS (table, a) & SYNTAX_FIRST_CHAR_START) >> 2) \ & (SYNTAX_COMMENT_BITS (table, b) & SYNTAX_SECOND_CHAR_START)) /* ... and SYNTAX_COMMENT_MATCH_END */ /* a and b must be first and second end chars for a common type */ #define SYNTAX_END_P(table, a, b) \ (((SYNTAX_COMMENT_BITS (table, a) & SYNTAX_FIRST_CHAR_END) >> 2) \ & (SYNTAX_COMMENT_BITS (table, b) & SYNTAX_SECOND_CHAR_END)) #define SYNTAX_STYLES_MATCH_START_P(table, a, b, mask) \ ((SYNTAX_COMMENT_BITS (table, a) & SYNTAX_FIRST_CHAR_START & (mask)) \ && (SYNTAX_COMMENT_BITS (table, b) & SYNTAX_SECOND_CHAR_START & (mask))) #define SYNTAX_STYLES_MATCH_END_P(table, a, b, mask) \ ((SYNTAX_COMMENT_BITS (table, a) & SYNTAX_FIRST_CHAR_END & (mask)) \ && (SYNTAX_COMMENT_BITS (table, b) & SYNTAX_SECOND_CHAR_END & (mask))) #define SYNTAX_STYLES_MATCH_1CHAR_P(table, a, mask) \ ((SYNTAX_COMMENT_BITS (table, a) & (mask))) #define STYLE_FOUND_P(table, a, b, startp, style) \ ((SYNTAX_COMMENT_BITS (table, a) & \ ((startp) ? SYNTAX_FIRST_CHAR_START : \ SYNTAX_FIRST_CHAR_END) & (style)) \ && (SYNTAX_COMMENT_BITS (table, b) & \ ((startp) ? SYNTAX_SECOND_CHAR_START : \ SYNTAX_SECOND_CHAR_END) & (style))) #define SYNTAX_COMMENT_MASK_START(table, a, b) \ ((STYLE_FOUND_P (table, a, b, 1, SYNTAX_COMMENT_STYLE_A) \ ? SYNTAX_COMMENT_STYLE_A \ : (STYLE_FOUND_P (table, a, b, 1, SYNTAX_COMMENT_STYLE_B) \ ? SYNTAX_COMMENT_STYLE_B \ : 0))) #define SYNTAX_COMMENT_MASK_END(table, a, b) \ ((STYLE_FOUND_P (table, a, b, 0, SYNTAX_COMMENT_STYLE_A) \ ? SYNTAX_COMMENT_STYLE_A \ : (STYLE_FOUND_P (table, a, b, 0, SYNTAX_COMMENT_STYLE_B) \ ? SYNTAX_COMMENT_STYLE_B \ : 0))) #define STYLE_FOUND_1CHAR_P(table, a, style) \ ((SYNTAX_COMMENT_BITS (table, a) & (style))) #define SYNTAX_COMMENT_1CHAR_MASK(table, a) \ ((STYLE_FOUND_1CHAR_P (table, a, SYNTAX_COMMENT_STYLE_A) \ ? SYNTAX_COMMENT_STYLE_A \ : (STYLE_FOUND_1CHAR_P (table, a, SYNTAX_COMMENT_STYLE_B) \ ? SYNTAX_COMMENT_STYLE_B \ : 0))) EXFUN (Fchar_syntax, 2); EXFUN (Fforward_word, 2); /* The standard syntax table is stored where it will automatically be used in all new buffers. */ extern Lisp_Object Vstandard_syntax_table; /* This array, indexed by a character, contains the syntax code which that character signifies (as a char). For example, (enum syntaxcode) syntax_spec_code['w'] is Sword. */ extern const unsigned char syntax_spec_code[0400]; /* Indexed by syntax code, give the letter that describes it. */ extern const unsigned char syntax_code_spec[]; Lisp_Object scan_lists (struct buffer *buf, Charbpos from, int count, int depth, int sexpflag, int no_error); int char_quoted (struct buffer *buf, Charbpos pos); /* NOTE: This does not refer to the mirror table, but to the syntax table itself. */ Lisp_Object syntax_match (Lisp_Object table, Emchar ch); extern int no_quit_in_re_search; extern struct buffer *regex_emacs_buffer; /* This is the string or buffer in which we are matching. It is used for looking up syntax properties. */ extern Lisp_Object regex_match_object; void update_syntax_table (Lisp_Char_Table *ct); #ifdef emacs extern int lookup_syntax_properties; struct syntax_cache { int use_code; /* Whether to use syntax_code or current_syntax_table. */ struct buffer* buffer; /* The buffer the current syntax cache applies to. */ Lisp_Object object; /* The buffer or string the current syntax cache applies to. */ int syntax_code; /* Syntax code of current char. */ Lisp_Object current_syntax_table; /* Syntax table for current pos. */ Lisp_Object old_prop; /* Syntax-table prop at prev pos. */ Charbpos next_change; /* Position of the next extent change. */ Charbpos prev_change; /* Position of the previous extent change. */ }; extern struct syntax_cache syntax_cache; void update_syntax_cache (int pos, int count, int init); /* Make syntax cache state good for CHARPOS, assuming it is currently good for a position before CHARPOS. */ #define UPDATE_SYNTAX_CACHE_FORWARD(pos) \ (lookup_syntax_properties \ ? (update_syntax_cache ((pos), 1, 0), 1) \ : 0) /* Make syntax cache state good for CHARPOS, assuming it is currently good for a position after CHARPOS. */ #define UPDATE_SYNTAX_CACHE_BACKWARD(pos) \ (lookup_syntax_properties \ ? (update_syntax_cache ((pos), -1, 0), 1) \ : 0) /* Make syntax cache state good for CHARPOS */ #define UPDATE_SYNTAX_CACHE(pos) \ (lookup_syntax_properties \ ? (update_syntax_cache ((pos), 0, 0), 1) \ : 0) #define SYNTAX_FROM_CACHE(table, c) \ SYNTAX_FROM_CODE (SYNTAX_CODE_FROM_CACHE (table, c)) #define SYNTAX_CODE_FROM_CACHE(table, c) \ ( syntax_cache.use_code \ ? syntax_cache.syntax_code \ : SYNTAX_CODE (XCHAR_TABLE (syntax_cache.current_syntax_table), \ c) \ ) /* Convert the byte offset BYTEPOS into a character position, for the object recorded in syntax_cache with SETUP_SYNTAX_TABLE_FOR_OBJECT. The value is meant for use in the UPDATE_SYNTAX_TABLE... macros. These macros do nothing when parse_sexp_lookup_properties is 0, so we return 0 in that case, for speed. */ #define SYNTAX_CACHE_BYTE_TO_CHAR(bytepos) \ (! lookup_syntax_properties \ ? 0 \ : STRINGP (syntax_cache.object) \ ? bytecount_to_charcount (XSTRING_DATA (syntax_cache.object), bytepos) \ : (BUFFERP (syntax_cache.object) || NILP (syntax_cache.object)) \ ? bytebpos_to_charbpos (syntax_cache.buffer, \ bytepos + BI_BUF_BEGV (syntax_cache.buffer)) \ : (bytepos)) #define SYNTAX_CACHE_OBJECT_BYTE_TO_CHAR(obj, buf, bytepos) \ (! lookup_syntax_properties \ ? 0 \ : STRINGP (obj) \ ? bytecount_to_charcount (XSTRING_DATA (obj), bytepos) \ : (BUFFERP (obj) || NILP (obj)) \ ? bytebpos_to_charbpos (buf, bytepos + BI_BUF_BEGV (buf)) \ : (bytepos)) #else /* not emacs */ #define update_syntax_cache(pos, count, init) #define UPDATE_SYNTAX_CACHE_FORWARD(pos) #define UPDATE_SYNTAX_CACHE_BACKWARD(pos) #define UPDATE_SYNTAX_CACHE(pos) #define SYNTAX_FROM_CACHE SYNTAX #define SYNTAX_CODE_FROM_CACHE SYNTAX_CODE #endif /* emacs */ #define SETUP_SYNTAX_CACHE(FROM, COUNT) \ do { \ syntax_cache.buffer = current_buffer; \ syntax_cache.object = Qnil; \ syntax_cache.current_syntax_table \ = current_buffer->mirror_syntax_table; \ syntax_cache.use_code = 0; \ if (lookup_syntax_properties) \ update_syntax_cache ((COUNT) > 0 ? (FROM) : (FROM) - 1, \ (COUNT), 1); \ } while (0) #define SETUP_SYNTAX_CACHE_FOR_BUFFER(BUFFER, FROM, COUNT) \ do { \ syntax_cache.buffer = (BUFFER); \ syntax_cache.object = Qnil; \ syntax_cache.current_syntax_table = \ syntax_cache.buffer->mirror_syntax_table; \ syntax_cache.use_code = 0; \ if (lookup_syntax_properties) \ update_syntax_cache ((FROM) + ((COUNT) > 0 ? 0 : -1), \ (COUNT), 1); \ } while (0) #define SETUP_SYNTAX_CACHE_FOR_OBJECT(OBJECT, BUFFER, FROM, COUNT) \ do { \ syntax_cache.buffer = (BUFFER); \ syntax_cache.object = (OBJECT); \ if (NILP (syntax_cache.object)) \ { \ /* do nothing */; \ } \ else if (EQ (syntax_cache.object, Qt)) \ { \ /* do nothing */; \ } \ else if (STRINGP (syntax_cache.object)) \ { \ /* do nothing */; \ } \ else if (BUFFERP (syntax_cache.object)) \ { \ syntax_cache.buffer = XBUFFER (syntax_cache.object); \ } \ else \ { \ /* OBJECT must be buffer/string/t/nil */ \ assert(0); \ } \ syntax_cache.current_syntax_table \ = syntax_cache.buffer->mirror_syntax_table; \ syntax_cache.use_code = 0; \ if (lookup_syntax_properties) \ update_syntax_cache ((FROM) + ((COUNT) > 0 ? 0 : -1), \ (COUNT), 1); \ } while (0) #define SYNTAX_CODE_PREFIX(c) \ ((c >> 7) & 1) #define SYNTAX_CODE_COMMENT_BITS(c) \ ((c >> 16) &0xff) #define SYNTAX_CODES_START_P(a, b) \ (((SYNTAX_CODE_COMMENT_BITS (a) & SYNTAX_FIRST_CHAR_START) >> 2) \ & (SYNTAX_CODE_COMMENT_BITS (b) & SYNTAX_SECOND_CHAR_START)) #define SYNTAX_CODES_END_P(a, b) \ (((SYNTAX_CODE_COMMENT_BITS (a) & SYNTAX_FIRST_CHAR_END) >> 2) \ & (SYNTAX_CODE_COMMENT_BITS (b) & SYNTAX_SECOND_CHAR_END)) #define SYNTAX_CODES_COMMENT_MASK_START(a, b) \ (SYNTAX_CODES_MATCH_START_P (a, b, SYNTAX_COMMENT_STYLE_A) \ ? SYNTAX_COMMENT_STYLE_A \ : (SYNTAX_CODES_MATCH_START_P (a, b, SYNTAX_COMMENT_STYLE_B) \ ? SYNTAX_COMMENT_STYLE_B \ : 0)) #define SYNTAX_CODES_COMMENT_MASK_END(a, b) \ (SYNTAX_CODES_MATCH_END_P (a, b, SYNTAX_COMMENT_STYLE_A) \ ? SYNTAX_COMMENT_STYLE_A \ : (SYNTAX_CODES_MATCH_END_P (a, b, SYNTAX_COMMENT_STYLE_B) \ ? SYNTAX_COMMENT_STYLE_B \ : 0)) #define SYNTAX_CODE_START_FIRST_P(a) \ (SYNTAX_CODE_COMMENT_BITS (a) & SYNTAX_FIRST_CHAR_START) #define SYNTAX_CODE_START_SECOND_P(a) \ (SYNTAX_CODE_COMMENT_BITS (a) & SYNTAX_SECOND_CHAR_START) #define SYNTAX_CODE_END_FIRST_P(a) \ (SYNTAX_CODE_COMMENT_BITS (a) & SYNTAX_FIRST_CHAR_END) #define SYNTAX_CODE_END_SECOND_P(a) \ (SYNTAX_CODE_COMMENT_BITS (a) & SYNTAX_SECOND_CHAR_END) #define SYNTAX_CODES_MATCH_START_P(a, b, mask) \ ((SYNTAX_CODE_COMMENT_BITS (a) & SYNTAX_FIRST_CHAR_START & (mask)) \ && (SYNTAX_CODE_COMMENT_BITS (b) \ & SYNTAX_SECOND_CHAR_START & (mask))) #define SYNTAX_CODES_MATCH_END_P(a, b, mask) \ ((SYNTAX_CODE_COMMENT_BITS (a) & SYNTAX_FIRST_CHAR_END & (mask)) \ && (SYNTAX_CODE_COMMENT_BITS (b) & SYNTAX_SECOND_CHAR_END & (mask))) #define SYNTAX_CODE_MATCHES_1CHAR_P(a, mask) \ ((SYNTAX_CODE_COMMENT_BITS (a) & (mask))) #define SYNTAX_CODE_COMMENT_1CHAR_MASK(a) \ ((SYNTAX_CODE_MATCHES_1CHAR_P (a, SYNTAX_COMMENT_STYLE_A) \ ? SYNTAX_COMMENT_STYLE_A \ : (SYNTAX_CODE_MATCHES_1CHAR_P (a, SYNTAX_COMMENT_STYLE_B) \ ? SYNTAX_COMMENT_STYLE_B \ : 0))) #endif /* INCLUDED_syntax_h_ */