/* GNU Emacs routines to deal with syntax tables; also word and list parsing.
- Copyright (C) 1985, 1987, 1993, 1994, 1995, 1997, 1998, 1999, 2001,
- 2002, 2003, 2004, 2005, 2006, 2007, 2008, 2009, 2010
+ Copyright (C) 1985, 1987, 1993-1995, 1997-1999, 2001-2011
Free Software Foundation, Inc.
This file is part of GNU Emacs.
#include "syntax.h"
#include "intervals.h"
+#include "category.h"
+
+/* Then there are seven single-bit flags that have the following meanings:
+ 1. This character is the first of a two-character comment-start sequence.
+ 2. This character is the second of a two-character comment-start sequence.
+ 3. This character is the first of a two-character comment-end sequence.
+ 4. This character is the second of a two-character comment-end sequence.
+ 5. This character is a prefix, for backward-prefix-chars.
+ 6. The char is part of a delimiter for comments of style "b".
+ 7. This character is part of a nestable comment sequence.
+ 8. The char is part of a delimiter for comments of style "c".
+ Note that any two-character sequence whose first character has flag 1
+ and whose second character has flag 2 will be interpreted as a comment start.
+
+ bit 6 and 8 are used to discriminate between different comment styles.
+ Languages such as C++ allow two orthogonal syntax start/end pairs
+ and bit 6 is used to determine whether a comment-end or Scommentend
+ ends style a or b. Comment markers can start style a, b, c, or bc.
+ Style a is always the default.
+ For 2-char comment markers, the style b flag is only looked up on the second
+ char of the comment marker and on the first char of the comment ender.
+ For style c (like to for the nested flag), the flag can be placed on any
+ one of the chars.
+ */
+
+/* These macros extract specific flags from an integer
+ that holds the syntax code and the flags. */
+
+#define SYNTAX_FLAGS_COMSTART_FIRST(flags) (((flags) >> 16) & 1)
+
+#define SYNTAX_FLAGS_COMSTART_SECOND(flags) (((flags) >> 17) & 1)
+
+#define SYNTAX_FLAGS_COMEND_FIRST(flags) (((flags) >> 18) & 1)
+
+#define SYNTAX_FLAGS_COMEND_SECOND(flags) (((flags) >> 19) & 1)
+
+#define SYNTAX_FLAGS_PREFIX(flags) (((flags) >> 20) & 1)
+
+#define SYNTAX_FLAGS_COMMENT_STYLEB(flags) (((flags) >> 21) & 1)
+#define SYNTAX_FLAGS_COMMENT_STYLEC(flags) (((flags) >> 22) & 2)
+/* FLAGS should be the flags of the main char of the comment marker, e.g.
+ the second for comstart and the first for comend. */
+#define SYNTAX_FLAGS_COMMENT_STYLE(flags, other_flags) \
+ (SYNTAX_FLAGS_COMMENT_STYLEB (flags) \
+ | SYNTAX_FLAGS_COMMENT_STYLEC (flags) \
+ | SYNTAX_FLAGS_COMMENT_STYLEC (other_flags))
+
+#define SYNTAX_FLAGS_COMMENT_NESTED(flags) (((flags) >> 22) & 1)
+
+/* These macros extract a particular flag for a given character. */
+
+#define SYNTAX_COMEND_FIRST(c) \
+ (SYNTAX_FLAGS_COMEND_FIRST (SYNTAX_WITH_FLAGS (c)))
+#define SYNTAX_PREFIX(c) (SYNTAX_FLAGS_PREFIX (SYNTAX_WITH_FLAGS (c)))
/* We use these constants in place for comment-style and
string-ender-char to distinguish comments/strings started by
#define ST_COMMENT_STYLE (256 + 1)
#define ST_STRING_STYLE (256 + 2)
-#include "category.h"
-Lisp_Object Qsyntax_table_p, Qsyntax_table, Qscan_error;
-
-int words_include_escapes;
-int parse_sexp_lookup_properties;
-
-/* Nonzero means `scan-sexps' treat all multibyte characters as symbol. */
-int multibyte_syntax_as_symbol;
+static Lisp_Object Qsyntax_table_p;
+static Lisp_Object Qsyntax_table, Qscan_error;
+#ifndef __GNUC__
/* Used as a temporary in SYNTAX_ENTRY and other macros in syntax.h,
if not compiled with GCC. No need to mark it, since it is used
only very temporarily. */
Lisp_Object syntax_temp;
-
-/* Non-zero means an open parenthesis in column 0 is always considered
- to be the start of a defun. Zero means an open parenthesis in
- column 0 has no special meaning. */
-
-int open_paren_in_column_0_is_defun_start;
+#endif
/* This is the internal form of the parse state used in parse-partial-sexp. */
static int find_start_modiff;
+static Lisp_Object Fsyntax_table_p (Lisp_Object);
static Lisp_Object skip_chars (int, Lisp_Object, Lisp_Object, int);
static Lisp_Object skip_syntaxes (int, Lisp_Object, Lisp_Object);
static Lisp_Object scan_lists (EMACS_INT, EMACS_INT, EMACS_INT, int);
int, Lisp_Object, int);
static int in_classes (int, Lisp_Object);
\f
+/* Whether the syntax of the character C has the prefix flag set. */
+int syntax_prefix_flag_p (int c)
+{
+ return SYNTAX_PREFIX (c);
+}
struct gl_state_s gl_state; /* Global state of syntax parser. */
-INTERVAL interval_of (int, Lisp_Object);
#define INTERVALS_AT_ONCE 10 /* 1 + max-number of intervals
to scan to property-change. */
start/end of OBJECT. */
void
-update_syntax_table (int charpos, int count, int init, Lisp_Object object)
+update_syntax_table (EMACS_INT charpos, int count, int init,
+ Lisp_Object object)
{
Lisp_Object tmp_table;
- int cnt = 0, invalidate = 1;
+ unsigned cnt = 0;
+ int invalidate = 1;
INTERVAL i;
if (init)
else
{
gl_state.use_global = 0;
- gl_state.current_syntax_table = current_buffer->syntax_table;
+ gl_state.current_syntax_table = BVAR (current_buffer, syntax_table);
}
}
return quoted;
}
-/* Return the bytepos one character after BYTEPOS.
- We assume that BYTEPOS is not at the end of the buffer. */
-
-INLINE EMACS_INT
-inc_bytepos (EMACS_INT bytepos)
-{
- if (NILP (current_buffer->enable_multibyte_characters))
- return bytepos + 1;
-
- INC_POS (bytepos);
- return bytepos;
-}
-
/* Return the bytepos one character before BYTEPOS.
We assume that BYTEPOS is not at the start of the buffer. */
-INLINE EMACS_INT
+static INLINE EMACS_INT
dec_bytepos (EMACS_INT bytepos)
{
- if (NILP (current_buffer->enable_multibyte_characters))
+ if (NILP (BVAR (current_buffer, enable_multibyte_characters)))
return bytepos - 1;
DEC_POS (bytepos);
/* Return the SYNTAX_COMEND_FIRST of the character before POS, POS_BYTE. */
static int
-prev_char_comend_first (int pos, int pos_byte)
+prev_char_comend_first (EMACS_INT pos, EMACS_INT pos_byte)
{
int c, val;
EMACS_INT comment_end = from;
EMACS_INT comment_end_byte = from_byte;
EMACS_INT comstart_pos = 0;
- EMACS_INT comstart_byte;
+ EMACS_INT comstart_byte IF_LINT (= 0);
/* Place where the containing defun starts,
or 0 if we didn't come across it yet. */
EMACS_INT defun_start = 0;
that determines quote parity to the comment-end. */
while (from != stop)
{
- int temp_byte, prev_syntax;
- int com2start, com2end;
+ EMACS_INT temp_byte;
+ int prev_syntax, com2start, com2end;
+ int comstart;
/* Move back and examine a character. */
DEC_BOTH (from, from_byte);
/* Check for 2-char comment markers. */
com2start = (SYNTAX_FLAGS_COMSTART_FIRST (syntax)
&& SYNTAX_FLAGS_COMSTART_SECOND (prev_syntax)
- && comstyle == SYNTAX_FLAGS_COMMENT_STYLE (prev_syntax)
+ && (comstyle
+ == SYNTAX_FLAGS_COMMENT_STYLE (prev_syntax, syntax))
&& (SYNTAX_FLAGS_COMMENT_NESTED (prev_syntax)
|| SYNTAX_FLAGS_COMMENT_NESTED (syntax)) == comnested);
com2end = (SYNTAX_FLAGS_COMEND_FIRST (syntax)
&& SYNTAX_FLAGS_COMEND_SECOND (prev_syntax));
+ comstart = (com2start || code == Scomment);
/* Nasty cases with overlapping 2-char comment markers:
- snmp-mode: -- c -- foo -- c --
/// */
/* If a 2-char comment sequence partly overlaps with another,
- we don't try to be clever. */
- if (from > stop && (com2end || com2start))
+ we don't try to be clever. E.g. |*| in C, or }% in modes that
+ have %..\n and %{..}%. */
+ if (from > stop && (com2end || comstart))
{
- int next = from, next_byte = from_byte, next_c, next_syntax;
+ EMACS_INT next = from, next_byte = from_byte;
+ int next_c, next_syntax;
DEC_BOTH (next, next_byte);
UPDATE_SYNTAX_TABLE_BACKWARD (next);
next_c = FETCH_CHAR_AS_MULTIBYTE (next_byte);
next_syntax = SYNTAX_WITH_FLAGS (next_c);
- if (((com2start || comnested)
+ if (((comstart || comnested)
&& SYNTAX_FLAGS_COMEND_SECOND (syntax)
&& SYNTAX_FLAGS_COMEND_FIRST (next_syntax))
|| ((com2end || comnested)
&& SYNTAX_FLAGS_COMSTART_SECOND (syntax)
- && comstyle == SYNTAX_FLAGS_COMMENT_STYLE (syntax)
+ && (comstyle
+ == SYNTAX_FLAGS_COMMENT_STYLE (syntax, prev_syntax))
&& SYNTAX_FLAGS_COMSTART_FIRST (next_syntax)))
goto lossage;
/* UPDATE_SYNTAX_TABLE_FORWARD (next + 1); */
code = Scomment;
/* Ignore comment starters of a different style. */
else if (code == Scomment
- && (comstyle != SYNTAX_FLAGS_COMMENT_STYLE (syntax)
+ && (comstyle != SYNTAX_FLAGS_COMMENT_STYLE (syntax, 0)
|| SYNTAX_FLAGS_COMMENT_NESTED (syntax) != comnested))
continue;
break;
case Sendcomment:
- if (SYNTAX_FLAGS_COMMENT_STYLE (syntax) == comstyle
+ if (SYNTAX_FLAGS_COMMENT_STYLE (syntax, 0) == comstyle
&& ((com2end && SYNTAX_FLAGS_COMMENT_NESTED (prev_syntax))
|| SYNTAX_FLAGS_COMMENT_NESTED (syntax)) == comnested)
/* This is the same style of comment ender as ours. */
This is the one specified by the current buffer. */)
(void)
{
- return current_buffer->syntax_table;
+ return BVAR (current_buffer, syntax_table);
}
DEFUN ("standard-syntax-table", Fstandard_syntax_table,
{
int idx;
check_syntax_table (table);
- current_buffer->syntax_table = table;
+ BVAR (current_buffer, syntax_table) = table;
/* Indicate that this buffer now has a specified syntax table. */
idx = PER_BUFFER_VAR_IDX (syntax_table);
SET_PER_BUFFER_VALUE_P (current_buffer, idx, 1);
case 'n':
val |= 1 << 22;
break;
+
+ case 'c':
+ val |= 1 << 23;
+ break;
}
if (val < XVECTOR (Vsyntax_code_object)->size && NILP (match))
3 means CHAR is the start of a two-char comment end sequence.
4 means CHAR is the second character of such a sequence.
-There can be up to two orthogonal comment sequences. This is to support
+There can be several orthogonal comment sequences. This is to support
language modes such as C++. By default, all comment sequences are of style
a, but you can set the comment sequence style to b (on the second character
-of a comment-start, or the first character of a comment-end sequence) using
-this flag:
+of a comment-start, and the first character of a comment-end sequence) and/or
+c (on any of its chars) using this flag:
b means CHAR is part of comment sequence b.
+ c means CHAR is part of comment sequence c.
n means CHAR is part of a nestable comment sequence.
p means CHAR is a prefix character for `backward-prefix-chars';
CHECK_CHARACTER (c);
if (NILP (syntax_table))
- syntax_table = current_buffer->syntax_table;
+ syntax_table = BVAR (current_buffer, syntax_table);
else
check_syntax_table (syntax_table);
(Lisp_Object syntax)
{
register enum syntaxcode code;
- char desc, start1, start2, end1, end2, prefix, comstyle, comnested;
+ int syntax_code;
+ char desc, start1, start2, end1, end2, prefix,
+ comstyleb, comstylec, comnested;
char str[2];
Lisp_Object first, match_lisp, value = syntax;
return syntax;
}
- code = (enum syntaxcode) (XINT (first) & 0377);
- start1 = (XINT (first) >> 16) & 1;
- start2 = (XINT (first) >> 17) & 1;
- end1 = (XINT (first) >> 18) & 1;
- end2 = (XINT (first) >> 19) & 1;
- prefix = (XINT (first) >> 20) & 1;
- comstyle = (XINT (first) >> 21) & 1;
- comnested = (XINT (first) >> 22) & 1;
+ syntax_code = XINT (first);
+ code = (enum syntaxcode) (syntax_code & 0377);
+ start1 = SYNTAX_FLAGS_COMSTART_FIRST (syntax_code);
+ start2 = SYNTAX_FLAGS_COMSTART_SECOND (syntax_code);;
+ end1 = SYNTAX_FLAGS_COMEND_FIRST (syntax_code);
+ end2 = SYNTAX_FLAGS_COMEND_SECOND (syntax_code);
+ prefix = SYNTAX_FLAGS_PREFIX (syntax_code);
+ comstyleb = SYNTAX_FLAGS_COMMENT_STYLEB (syntax_code);
+ comstylec = SYNTAX_FLAGS_COMMENT_STYLEC (syntax_code);
+ comnested = SYNTAX_FLAGS_COMMENT_NESTED (syntax_code);
if ((int) code < 0 || (int) code >= (int) Smax)
{
if (prefix)
insert ("p", 1);
- if (comstyle)
+ if (comstyleb)
insert ("b", 1);
+ if (comstylec)
+ insert ("c", 1);
if (comnested)
insert ("n", 1);
insert_string (",\n\t is the first character of a comment-end sequence");
if (end2)
insert_string (",\n\t is the second character of a comment-end sequence");
- if (comstyle)
+ if (comstyleb)
insert_string (" (comment style b)");
+ if (comstylec)
+ insert_string (" (comment style c)");
if (comnested)
insert_string (" (nestable)");
return syntax;
}
\f
-int parse_sexp_ignore_comments;
-
-/* Char-table of functions that find the next or previous word
- boundary. */
-Lisp_Object Vfind_word_boundary_function_table;
-
/* Return the position across COUNT words from FROM.
If that many words cannot be found before the end of the buffer, return 0.
COUNT negative means scan backward and stop at word beginning. */
-int
-scan_words (register int from, register int count)
+EMACS_INT
+scan_words (register EMACS_INT from, register EMACS_INT count)
{
- register int beg = BEGV;
- register int end = ZV;
- register int from_byte = CHAR_TO_BYTE (from);
+ register EMACS_INT beg = BEGV;
+ register EMACS_INT end = ZV;
+ register EMACS_INT from_byte = CHAR_TO_BYTE (from);
register enum syntaxcode code;
int ch0, ch1;
- Lisp_Object func, script, pos;
+ Lisp_Object func, pos;
immediate_quit = 1;
QUIT;
}
else
{
- script = CHAR_TABLE_REF (Vchar_script_table, ch0);
while (1)
{
if (from == end) break;
}
else
{
- script = CHAR_TABLE_REF (Vchar_script_table, ch1);
while (1)
{
if (from == beg)
return val == orig_val ? Qt : Qnil;
}
\f
-Lisp_Object skip_chars (int, Lisp_Object, Lisp_Object, int);
-
DEFUN ("skip-chars-forward", Fskip_chars_forward, Sskip_chars_forward, 1, 2, 0,
doc: /* Move point forward, stopping before a char not in STRING, or at pos LIM.
STRING is like the inside of a `[...]' in a regular expression
register unsigned int c;
unsigned char fastmap[0400];
/* Store the ranges of non-ASCII characters. */
- int *char_ranges;
+ int *char_ranges IF_LINT (= NULL);
int n_char_ranges = 0;
int negate = 0;
- register int i, i_byte;
+ register EMACS_INT i, i_byte;
/* Set to 1 if the current buffer is multibyte and the region
contains non-ASCII chars. */
int multibyte;
/* Set to 1 if STRING is multibyte and it contains non-ASCII
chars. */
int string_multibyte;
- int size_byte;
+ EMACS_INT size_byte;
const unsigned char *str;
int len;
Lisp_Object iso_classes;
if (XINT (lim) < BEGV)
XSETFASTINT (lim, BEGV);
- multibyte = (!NILP (current_buffer->enable_multibyte_characters)
+ multibyte = (!NILP (BVAR (current_buffer, enable_multibyte_characters))
&& (XINT (lim) - PT != CHAR_TO_BYTE (XINT (lim)) - PT_BYTE));
string_multibyte = SBYTES (string) > SCHARS (string);
if (c <= c2)
{
- while (c <= c2)
+ unsigned lim2 = c2 + 1;
+ while (c < lim2)
fastmap[c++] = 1;
if (! ASCII_CHAR_P (c2))
string_has_eight_bit = 1;
}
if (! ASCII_CHAR_P (c))
{
- while (leading_code <= leading_code2)
+ unsigned lim2 = leading_code2 + 1;
+ while (leading_code < lim2)
fastmap[leading_code++] = 1;
if (c <= c2)
{
for (i = 0; i < n_char_ranges; i += 2)
{
int c1 = char_ranges[i];
- int c2 = char_ranges[i + 1];
+ unsigned lim2 = char_ranges[i + 1] + 1;
- for (; c1 <= c2; c1++)
+ for (; c1 < lim2; c1++)
{
int b = CHAR_TO_BYTE_SAFE (c1);
if (b >= 0)
}
{
- int start_point = PT;
- int pos = PT;
- int pos_byte = PT_BYTE;
+ EMACS_INT start_point = PT;
+ EMACS_INT pos = PT;
+ EMACS_INT pos_byte = PT_BYTE;
unsigned char *p = PT_ADDR, *endp, *stop;
if (forwardp)
register unsigned int c;
unsigned char fastmap[0400];
int negate = 0;
- register int i, i_byte;
+ register EMACS_INT i, i_byte;
int multibyte;
- int size_byte;
+ EMACS_INT size_byte;
unsigned char *str;
CHECK_STRING (string);
if (forwardp ? (PT >= XFASTINT (lim)) : (PT <= XFASTINT (lim)))
return make_number (0);
- multibyte = (!NILP (current_buffer->enable_multibyte_characters)
+ multibyte = (!NILP (BVAR (current_buffer, enable_multibyte_characters))
&& (XINT (lim) - PT != CHAR_TO_BYTE (XINT (lim)) - PT_BYTE));
memset (fastmap, 0, sizeof fastmap);
fastmap[i] ^= 1;
{
- int start_point = PT;
- int pos = PT;
- int pos_byte = PT_BYTE;
+ EMACS_INT start_point = PT;
+ EMACS_INT pos = PT;
+ EMACS_INT pos_byte = PT_BYTE;
unsigned char *p = PT_ADDR, *endp, *stop;
if (forwardp)
FROM_BYTE is the bytepos corresponding to FROM.
Do not move past STOP (a charpos).
The comment over which we have to jump is of style STYLE
- (either SYNTAX_COMMENT_STYLE(foo) or ST_COMMENT_STYLE).
+ (either SYNTAX_FLAGS_COMMENT_STYLE(foo) or ST_COMMENT_STYLE).
NESTING should be positive to indicate the nesting at the beginning
for nested comments and should be zero or negative else.
ST_COMMENT_STYLE cannot be nested.
{
register int c, c1;
register enum syntaxcode code;
- register int syntax;
+ register int syntax, other_syntax;
if (nesting <= 0) nesting = -1;
syntax = SYNTAX_WITH_FLAGS (c);
code = syntax & 0xff;
if (code == Sendcomment
- && SYNTAX_FLAGS_COMMENT_STYLE (syntax) == style
+ && SYNTAX_FLAGS_COMMENT_STYLE (syntax, 0) == style
&& (SYNTAX_FLAGS_COMMENT_NESTED (syntax) ?
(nesting > 0 && --nesting == 0) : nesting < 0))
/* we have encountered a comment end of the same style
if (nesting > 0
&& code == Scomment
&& SYNTAX_FLAGS_COMMENT_NESTED (syntax)
- && SYNTAX_FLAGS_COMMENT_STYLE (syntax) == style)
+ && SYNTAX_FLAGS_COMMENT_STYLE (syntax, 0) == style)
/* we have encountered a nested comment of the same style
as the comment sequence which began this comment section */
nesting++;
forw_incomment:
if (from < stop && SYNTAX_FLAGS_COMEND_FIRST (syntax)
- && SYNTAX_FLAGS_COMMENT_STYLE (syntax) == style
&& (c1 = FETCH_CHAR_AS_MULTIBYTE (from_byte),
- SYNTAX_COMEND_SECOND (c1))
+ other_syntax = SYNTAX_WITH_FLAGS (c1),
+ SYNTAX_FLAGS_COMEND_SECOND (other_syntax))
+ && SYNTAX_FLAGS_COMMENT_STYLE (syntax, other_syntax) == style
&& ((SYNTAX_FLAGS_COMMENT_NESTED (syntax) ||
- SYNTAX_COMMENT_NESTED (c1)) ? nesting > 0 : nesting < 0))
+ SYNTAX_FLAGS_COMMENT_NESTED (other_syntax))
+ ? nesting > 0 : nesting < 0))
{
if (--nesting <= 0)
/* we have encountered a comment end of the same style
&& from < stop
&& SYNTAX_FLAGS_COMSTART_FIRST (syntax)
&& (c1 = FETCH_CHAR_AS_MULTIBYTE (from_byte),
- SYNTAX_COMMENT_STYLE (c1) == style
- && SYNTAX_COMSTART_SECOND (c1))
+ other_syntax = SYNTAX_WITH_FLAGS (c1),
+ SYNTAX_FLAGS_COMMENT_STYLE (other_syntax, syntax) == style
+ && SYNTAX_FLAGS_COMSTART_SECOND (other_syntax))
&& (SYNTAX_FLAGS_COMMENT_NESTED (syntax) ||
- SYNTAX_COMMENT_NESTED (c1)))
+ SYNTAX_FLAGS_COMMENT_NESTED (other_syntax)))
/* we have encountered a nested comment of the same style
as the comment sequence which began this comment
section */
{
do
{
- int comstart_first;
+ int comstart_first, syntax, other_syntax;
if (from == stop)
{
return Qnil;
}
c = FETCH_CHAR_AS_MULTIBYTE (from_byte);
+ syntax = SYNTAX_WITH_FLAGS (c);
code = SYNTAX (c);
- comstart_first = SYNTAX_COMSTART_FIRST (c);
- comnested = SYNTAX_COMMENT_NESTED (c);
- comstyle = SYNTAX_COMMENT_STYLE (c);
+ comstart_first = SYNTAX_FLAGS_COMSTART_FIRST (syntax);
+ comnested = SYNTAX_FLAGS_COMMENT_NESTED (syntax);
+ comstyle = SYNTAX_FLAGS_COMMENT_STYLE (syntax, 0);
INC_BOTH (from, from_byte);
UPDATE_SYNTAX_TABLE_FORWARD (from);
if (from < stop && comstart_first
&& (c1 = FETCH_CHAR_AS_MULTIBYTE (from_byte),
- SYNTAX_COMSTART_SECOND (c1)))
+ other_syntax = SYNTAX_WITH_FLAGS (c1),
+ SYNTAX_FLAGS_COMSTART_SECOND (other_syntax)))
{
/* We have encountered a comment start sequence and we
are ignoring all text inside comments. We must record
only a comment end of the same style actually ends
the comment section. */
code = Scomment;
- comstyle = SYNTAX_COMMENT_STYLE (c1);
- comnested = comnested || SYNTAX_COMMENT_NESTED (c1);
+ comstyle = SYNTAX_FLAGS_COMMENT_STYLE (other_syntax, syntax);
+ comnested
+ = comnested || SYNTAX_FLAGS_COMMENT_NESTED (other_syntax);
INC_BOTH (from, from_byte);
UPDATE_SYNTAX_TABLE_FORWARD (from);
}
{
while (1)
{
- int quoted;
+ int quoted, syntax;
if (from <= stop)
{
/* char_quoted does UPDATE_SYNTAX_TABLE_BACKWARD (from). */
quoted = char_quoted (from, from_byte);
c = FETCH_CHAR_AS_MULTIBYTE (from_byte);
+ syntax = SYNTAX_WITH_FLAGS (c);
code = SYNTAX (c);
comstyle = 0;
- comnested = SYNTAX_COMMENT_NESTED (c);
+ comnested = SYNTAX_FLAGS_COMMENT_NESTED (syntax);
if (code == Sendcomment)
- comstyle = SYNTAX_COMMENT_STYLE (c);
- if (from > stop && SYNTAX_COMEND_SECOND (c)
+ comstyle = SYNTAX_FLAGS_COMMENT_STYLE (syntax, 0);
+ if (from > stop && SYNTAX_FLAGS_COMEND_SECOND (syntax)
&& prev_char_comend_first (from, from_byte)
&& !char_quoted (from - 1, dec_bytepos (from_byte)))
{
+ int other_syntax;
/* We must record the comment style encountered so that
later, we can match only the proper comment begin
sequence of the same style. */
/* Calling char_quoted, above, set up global syntax position
at the new value of FROM. */
c1 = FETCH_CHAR_AS_MULTIBYTE (from_byte);
- comstyle = SYNTAX_COMMENT_STYLE (c1);
- comnested = comnested || SYNTAX_COMMENT_NESTED (c1);
+ other_syntax = SYNTAX_WITH_FLAGS (c1);
+ comstyle = SYNTAX_FLAGS_COMMENT_STYLE (other_syntax, syntax);
+ comnested
+ = comnested || SYNTAX_FLAGS_COMMENT_NESTED (other_syntax);
}
if (code == Scomment_fence)
{
/* Skip until first preceding unquoted comment_fence. */
- int found = 0, ini = from, ini_byte = from_byte;
+ int fence_found = 0;
+ EMACS_INT ini = from, ini_byte = from_byte;
while (1)
{
if (SYNTAX (c) == Scomment_fence
&& !char_quoted (from, from_byte))
{
- found = 1;
+ fence_found = 1;
break;
}
else if (from == stop)
break;
}
- if (found == 0)
+ if (fence_found == 0)
{
from = ini; /* Set point to ini + 1. */
from_byte = ini_byte;
{
/* Failure: we should go back to the end of this
not-quite-endcomment. */
- if (SYNTAX(c) != code)
+ if (SYNTAX (c) != code)
/* It was a two-char Sendcomment. */
INC_BOTH (from, from_byte);
goto leave;
{
while (from < stop)
{
- int comstart_first, prefix;
+ int comstart_first, prefix, syntax, other_syntax;
UPDATE_SYNTAX_TABLE_FORWARD (from);
c = FETCH_CHAR_AS_MULTIBYTE (from_byte);
+ syntax = SYNTAX_WITH_FLAGS (c);
code = SYNTAX_WITH_MULTIBYTE_CHECK (c);
- comstart_first = SYNTAX_COMSTART_FIRST (c);
- comnested = SYNTAX_COMMENT_NESTED (c);
- comstyle = SYNTAX_COMMENT_STYLE (c);
- prefix = SYNTAX_PREFIX (c);
+ comstart_first = SYNTAX_FLAGS_COMSTART_FIRST (syntax);
+ comnested = SYNTAX_FLAGS_COMMENT_NESTED (syntax);
+ comstyle = SYNTAX_FLAGS_COMMENT_STYLE (syntax, 0);
+ prefix = SYNTAX_FLAGS_PREFIX (syntax);
if (depth == min_depth)
last_good = from;
INC_BOTH (from, from_byte);
UPDATE_SYNTAX_TABLE_FORWARD (from);
if (from < stop && comstart_first
&& (c = FETCH_CHAR_AS_MULTIBYTE (from_byte),
- SYNTAX_COMSTART_SECOND (c))
+ other_syntax = SYNTAX_WITH_FLAGS (c),
+ SYNTAX_FLAGS_COMSTART_SECOND (other_syntax))
&& parse_sexp_ignore_comments)
{
/* we have encountered a comment start sequence and we
only a comment end of the same style actually ends
the comment section */
code = Scomment;
- c1 = FETCH_CHAR_AS_MULTIBYTE (from_byte);
- comstyle = SYNTAX_COMMENT_STYLE (c1);
- comnested = comnested || SYNTAX_COMMENT_NESTED (c1);
+ comstyle = SYNTAX_FLAGS_COMMENT_STYLE (other_syntax, syntax);
+ comnested
+ = comnested || SYNTAX_FLAGS_COMMENT_NESTED (other_syntax);
INC_BOTH (from, from_byte);
UPDATE_SYNTAX_TABLE_FORWARD (from);
}
{
while (from > stop)
{
+ int syntax;
DEC_BOTH (from, from_byte);
UPDATE_SYNTAX_TABLE_BACKWARD (from);
c = FETCH_CHAR_AS_MULTIBYTE (from_byte);
+ syntax= SYNTAX_WITH_FLAGS (c);
code = SYNTAX_WITH_MULTIBYTE_CHECK (c);
if (depth == min_depth)
last_good = from;
comstyle = 0;
- comnested = SYNTAX_COMMENT_NESTED (c);
+ comnested = SYNTAX_FLAGS_COMMENT_NESTED (syntax);
if (code == Sendcomment)
- comstyle = SYNTAX_COMMENT_STYLE (c);
- if (from > stop && SYNTAX_COMEND_SECOND (c)
+ comstyle = SYNTAX_FLAGS_COMMENT_STYLE (syntax, 0);
+ if (from > stop && SYNTAX_FLAGS_COMEND_SECOND (syntax)
&& prev_char_comend_first (from, from_byte)
&& parse_sexp_ignore_comments)
{
/* We must record the comment style encountered so that
later, we can match only the proper comment begin
sequence of the same style. */
+ int c2, other_syntax;
DEC_BOTH (from, from_byte);
UPDATE_SYNTAX_TABLE_BACKWARD (from);
code = Sendcomment;
- c1 = FETCH_CHAR_AS_MULTIBYTE (from_byte);
- comstyle = SYNTAX_COMMENT_STYLE (c1);
- comnested = comnested || SYNTAX_COMMENT_NESTED (c1);
+ c2 = FETCH_CHAR_AS_MULTIBYTE (from_byte);
+ other_syntax = SYNTAX_WITH_FLAGS (c2);
+ comstyle = SYNTAX_FLAGS_COMMENT_STYLE (other_syntax, syntax);
+ comnested
+ = comnested || SYNTAX_FLAGS_COMMENT_NESTED (other_syntax);
}
/* Quoting turns anything except a comment-ender
DEC_BOTH (from, from_byte);
code = Sword;
}
- else if (SYNTAX_PREFIX (c))
+ else if (SYNTAX_FLAGS_PREFIX (syntax))
continue;
switch (SWITCH_ENUM_CAST (code))
while (from > stop)
{
temp_pos = from_byte;
- if (! NILP (current_buffer->enable_multibyte_characters))
+ if (! NILP (BVAR (current_buffer, enable_multibyte_characters)))
DEC_POS (temp_pos);
else
temp_pos--;
This includes chars with "quote" or "prefix" syntax (' or p). */)
(void)
{
- int beg = BEGV;
- int opoint = PT;
- int opoint_byte = PT_BYTE;
- int pos = PT;
- int pos_byte = PT_BYTE;
+ EMACS_INT beg = BEGV;
+ EMACS_INT opoint = PT;
+ EMACS_INT opoint_byte = PT_BYTE;
+ EMACS_INT pos = PT;
+ EMACS_INT pos_byte = PT_BYTE;
int c;
if (pos <= beg)
oldstate = Fcdr (oldstate);
oldstate = Fcdr (oldstate);
tem = Fcar (oldstate);
- state.comstyle = NILP (tem) ? 0 : (EQ (tem, Qsyntax_table)
- ? ST_COMMENT_STYLE : 1);
+ state.comstyle = (NILP (tem)
+ ? 0
+ : (EQ (tem, Qsyntax_table)
+ ? ST_COMMENT_STYLE
+ : INTEGERP (tem) ? XINT (tem) : 1));
oldstate = Fcdr (oldstate);
tem = Fcar (oldstate);
while (from < end)
{
+ int syntax;
INC_FROM;
code = prev_from_syntax & 0xff;
if (from < end
&& SYNTAX_FLAGS_COMSTART_FIRST (prev_from_syntax)
&& (c1 = FETCH_CHAR (from_byte),
- SYNTAX_COMSTART_SECOND (c1)))
+ syntax = SYNTAX_WITH_FLAGS (c1),
+ SYNTAX_FLAGS_COMSTART_SECOND (syntax)))
/* Duplicate code to avoid a complex if-expression
which causes trouble for the SGI compiler. */
{
/* Record the comment style we have entered so that only
the comment-end sequence of the same style actually
terminates the comment section. */
- state.comstyle = SYNTAX_COMMENT_STYLE (c1);
+ state.comstyle
+ = SYNTAX_FLAGS_COMMENT_STYLE (syntax, prev_from_syntax);
comnested = SYNTAX_FLAGS_COMMENT_NESTED (prev_from_syntax);
- comnested = comnested || SYNTAX_COMMENT_NESTED (c1);
+ comnested = comnested || SYNTAX_FLAGS_COMMENT_NESTED (syntax);
state.incomment = comnested ? 1 : -1;
state.comstr_start = prev_from;
INC_FROM;
}
else if (code == Scomment)
{
- state.comstyle = SYNTAX_FLAGS_COMMENT_STYLE (prev_from_syntax);
+ state.comstyle = SYNTAX_FLAGS_COMMENT_STYLE (prev_from_syntax, 0);
state.incomment = (SYNTAX_FLAGS_COMMENT_NESTED (prev_from_syntax) ?
1 : -1);
state.comstr_start = prev_from;
= (curlevel == levelstart) ? -1 : (curlevel - 1)->last;
state.location = from;
state.levelstarts = Qnil;
- while (--curlevel >= levelstart)
- state.levelstarts = Fcons (make_number (curlevel->last),
- state.levelstarts);
+ while (curlevel > levelstart)
+ state.levelstarts = Fcons (make_number ((--curlevel)->last),
+ state.levelstarts);
immediate_quit = 0;
*stateptr = state;
else an integer (the current comment nesting).
5. t if following a quote character.
6. the minimum paren-depth encountered during this scan.
- 7. t if in a comment of style b; symbol `syntax-table' if the comment
- should be terminated by a generic comment delimiter.
+ 7. style of comment, if any.
8. character address of start of comment or string; nil if not in one.
9. Intermediate data for continuation of parsing (subject to change).
If third arg TARGETDEPTH is non-nil, parsing stops if the depth
SET_PT (state.location);
return Fcons (make_number (state.depth),
- Fcons (state.prevlevelstart < 0 ? Qnil : make_number (state.prevlevelstart),
- Fcons (state.thislevelstart < 0 ? Qnil : make_number (state.thislevelstart),
+ Fcons (state.prevlevelstart < 0
+ ? Qnil : make_number (state.prevlevelstart),
+ Fcons (state.thislevelstart < 0
+ ? Qnil : make_number (state.thislevelstart),
Fcons (state.instring >= 0
? (state.instring == ST_STRING_STYLE
? Qt : make_number (state.instring)) : Qnil,
Fcons (make_number (state.mindepth),
Fcons ((state.comstyle
? (state.comstyle == ST_COMMENT_STYLE
- ? Qsyntax_table : Qt) :
- Qnil),
+ ? Qsyntax_table
+ : make_number (state.comstyle))
+ : Qnil),
Fcons (((state.incomment
|| (state.instring >= 0))
? make_number (state.comstr_start)
Fput (Qscan_error, Qerror_message,
make_pure_c_string ("Scan error"));
- DEFVAR_BOOL ("parse-sexp-ignore-comments", &parse_sexp_ignore_comments,
+ DEFVAR_BOOL ("parse-sexp-ignore-comments", parse_sexp_ignore_comments,
doc: /* Non-nil means `forward-sexp', etc., should treat comments as whitespace. */);
- DEFVAR_BOOL ("parse-sexp-lookup-properties", &parse_sexp_lookup_properties,
+ DEFVAR_BOOL ("parse-sexp-lookup-properties", parse_sexp_lookup_properties,
doc: /* Non-nil means `forward-sexp', etc., obey `syntax-table' property.
Otherwise, that text property is simply ignored.
See the info node `(elisp)Syntax Properties' for a description of the
`syntax-table' property. */);
words_include_escapes = 0;
- DEFVAR_BOOL ("words-include-escapes", &words_include_escapes,
+ DEFVAR_BOOL ("words-include-escapes", words_include_escapes,
doc: /* Non-nil means `forward-word', etc., should treat escape chars part of words. */);
- DEFVAR_BOOL ("multibyte-syntax-as-symbol", &multibyte_syntax_as_symbol,
+ DEFVAR_BOOL ("multibyte-syntax-as-symbol", multibyte_syntax_as_symbol,
doc: /* Non-nil means `scan-sexps' treats all multibyte characters as symbol. */);
multibyte_syntax_as_symbol = 0;
DEFVAR_BOOL ("open-paren-in-column-0-is-defun-start",
- &open_paren_in_column_0_is_defun_start,
+ open_paren_in_column_0_is_defun_start,
doc: /* *Non-nil means an open paren in column 0 denotes the start of a defun. */);
open_paren_in_column_0_is_defun_start = 1;
DEFVAR_LISP ("find-word-boundary-function-table",
- &Vfind_word_boundary_function_table,
+ Vfind_word_boundary_function_table,
doc: /*
Char table of functions to search for the word boundary.
Each function is called with two arguments; POS and LIMIT.
defsubr (&Sbackward_prefix_chars);
defsubr (&Sparse_partial_sexp);
}
-
-/* arch-tag: 3e297b9f-088e-4b64-8f4c-fb0b3443e412
- (do not change this comment) */