/* 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, 2011, 2012
+ Copyright (C) 1985, 1987, 1993-1995, 1997-1999, 2001-2012
Free Software Foundation, Inc.
This file is part of GNU Emacs.
#include <config.h>
-#include <ctype.h>
+
+#include <sys/types.h>
#include <setjmp.h>
#include "lisp.h"
#include "commands.h"
-#include "buffer.h"
#include "character.h"
+#include "buffer.h"
#include "keymap.h"
#include "regex.h"
#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. */
struct lisp_parse_state
{
- int depth; /* Depth at end of parsing. */
+ EMACS_INT depth; /* Depth at end of parsing. */
int instring; /* -1 if not within string, else desired terminator. */
- int incomment; /* -1 if in unnestable comment else comment nesting */
+ EMACS_INT incomment; /* -1 if in unnestable comment else comment nesting */
int comstyle; /* comment style a=0, or b=1, or ST_COMMENT_STYLE. */
int quoted; /* Nonzero if just after an escape char at end of parsing */
- int mindepth; /* Minimum depth seen while scanning. */
+ EMACS_INT mindepth; /* Minimum depth seen while scanning. */
/* Char number of most recent start-of-expression at current level */
- EMACS_INT thislevelstart;
+ ptrdiff_t thislevelstart;
/* Char number of start of containing expression */
- EMACS_INT prevlevelstart;
- EMACS_INT location; /* Char number at which parsing stopped. */
- EMACS_INT comstr_start; /* Position of last comment/string starter. */
+ ptrdiff_t prevlevelstart;
+ ptrdiff_t location; /* Char number at which parsing stopped. */
+ ptrdiff_t comstr_start; /* Position of last comment/string starter. */
Lisp_Object levelstarts; /* Char numbers of starts-of-expression
of levels (starting from outermost). */
};
find_start_begv is the BEGV value when it was found.
find_start_modiff is the value of MODIFF when it was found. */
-static EMACS_INT find_start_pos;
-static EMACS_INT find_start_value;
-static EMACS_INT find_start_value_byte;
+static ptrdiff_t find_start_pos;
+static ptrdiff_t find_start_value;
+static ptrdiff_t find_start_value_byte;
static struct buffer *find_start_buffer;
-static EMACS_INT find_start_begv;
-static int find_start_modiff;
+static ptrdiff_t find_start_begv;
+static EMACS_INT find_start_modiff;
+
+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);
+static void scan_sexps_forward (struct lisp_parse_state *,
+ ptrdiff_t, ptrdiff_t, ptrdiff_t, EMACS_INT,
+ int, Lisp_Object, int);
+static int in_classes (int, Lisp_Object);
-static Lisp_Object skip_chars P_ ((int, Lisp_Object, Lisp_Object, int));
-static Lisp_Object skip_syntaxes P_ ((int, Lisp_Object, Lisp_Object));
-static Lisp_Object scan_lists P_ ((EMACS_INT, EMACS_INT, EMACS_INT, int));
-static void scan_sexps_forward P_ ((struct lisp_parse_state *,
- EMACS_INT, EMACS_INT, EMACS_INT, int,
- int, Lisp_Object, int));
-static int in_classes P_ ((int, Lisp_Object));
+/* This setter is used only in this file, so it can be private. */
+static inline void
+bset_syntax_table (struct buffer *b, Lisp_Object val)
+{
+ b->INTERNAL_FIELD (syntax_table) = val;
+}
\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 ();
#define INTERVALS_AT_ONCE 10 /* 1 + max-number of intervals
to scan to property-change. */
direction than the intervals - or in an interval. We update the
current syntax-table basing on the property of this interval, and
update the interval to start further than CHARPOS - or be
- NULL_INTERVAL. We also update lim_property to be the next value of
+ NULL. We also update lim_property to be the next value of
charpos to call this subroutine again - or be before/after the
start/end of OBJECT. */
void
-update_syntax_table (charpos, count, init, object)
- int charpos, count, init;
- Lisp_Object object;
+update_syntax_table (ptrdiff_t charpos, EMACS_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)
i = interval_of (charpos, object);
gl_state.backward_i = gl_state.forward_i = i;
invalidate = 0;
- if (NULL_INTERVAL_P (i))
+ if (!i)
return;
/* interval_of updates only ->position of the return value, so
update the parents manually to speed up update_interval. */
/* We are guaranteed to be called with CHARPOS either in i,
or further off. */
- if (NULL_INTERVAL_P (i))
+ if (!i)
error ("Error in syntax_table logic for to-the-end intervals");
else if (charpos < i->position) /* Move left. */
{
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);
}
}
- while (!NULL_INTERVAL_P (i))
+ while (i)
{
if (cnt && !EQ (tmp_table, textget (i->plist, Qsyntax_table)))
{
/* e_property at EOB is not set to ZV but to ZV+1, so that
we can do INC(from);UPDATE_SYNTAX_TABLE_FORWARD without
having to check eob between the two. */
- + (NULL_INTERVAL_P (next_interval (i)) ? 1 : 0);
+ + (next_interval (i) ? 0 : 1);
gl_state.forward_i = i;
}
else
cnt++;
i = count > 0 ? next_interval (i) : previous_interval (i);
}
- eassert (NULL_INTERVAL_P (i)); /* This property goes to the end. */
+ eassert (i == NULL); /* This property goes to the end. */
if (count > 0)
gl_state.e_property = gl_state.stop;
else
or after. On return global syntax data is good for lookup at CHARPOS. */
static int
-char_quoted (EMACS_INT charpos, EMACS_INT bytepos)
+char_quoted (ptrdiff_t charpos, ptrdiff_t bytepos)
{
register enum syntaxcode code;
- register EMACS_INT beg = BEGV;
+ register ptrdiff_t beg = BEGV;
register int quoted = 0;
- EMACS_INT orig = charpos;
+ ptrdiff_t orig = charpos;
while (charpos > beg)
{
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 (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
-dec_bytepos (bytepos)
- EMACS_INT bytepos;
+static inline ptrdiff_t
+dec_bytepos (ptrdiff_t bytepos)
{
- if (NILP (current_buffer->enable_multibyte_characters))
+ if (NILP (BVAR (current_buffer, enable_multibyte_characters)))
return bytepos - 1;
DEC_POS (bytepos);
valid on return from the subroutine, so the caller should explicitly
update the global data. */
-static EMACS_INT
-find_defun_start (pos, pos_byte)
- EMACS_INT pos, pos_byte;
+static ptrdiff_t
+find_defun_start (ptrdiff_t pos, ptrdiff_t pos_byte)
{
- EMACS_INT opoint = PT, opoint_byte = PT_BYTE;
+ ptrdiff_t opoint = PT, opoint_byte = PT_BYTE;
if (!open_paren_in_column_0_is_defun_start)
{
/* We optimize syntax-table lookup for rare updates. Thus we accept
only those `^\s(' which are good in global _and_ text-property
syntax-tables. */
- gl_state.current_syntax_table = current_buffer->syntax_table;
- gl_state.use_global = 0;
+ SETUP_BUFFER_SYNTAX_TABLE ();
while (PT > BEGV)
{
int c;
if (SYNTAX (c) == Sopen)
break;
/* Now fallback to the default value. */
- gl_state.current_syntax_table = current_buffer->syntax_table;
- gl_state.use_global = 0;
+ SETUP_BUFFER_SYNTAX_TABLE ();
}
/* Move to beg of previous line. */
scan_newline (PT, PT_BYTE, BEGV, BEGV_BYTE, -2, 1);
/* Return the SYNTAX_COMEND_FIRST of the character before POS, POS_BYTE. */
static int
-prev_char_comend_first (pos, pos_byte)
- int pos, pos_byte;
+prev_char_comend_first (ptrdiff_t pos, ptrdiff_t pos_byte)
{
int c, val;
the returned value (or at FROM, if the search was not successful). */
static int
-back_comment (from, from_byte, stop, comnested, comstyle, charpos_ptr, bytepos_ptr)
- EMACS_INT from, from_byte, stop;
- int comnested, comstyle;
- EMACS_INT *charpos_ptr, *bytepos_ptr;
+back_comment (ptrdiff_t from, ptrdiff_t from_byte, ptrdiff_t stop, int comnested, int comstyle, ptrdiff_t *charpos_ptr, ptrdiff_t *bytepos_ptr)
{
/* Look back, counting the parity of string-quotes,
and recording the comment-starters seen.
inside another comment).
Test case: { a (* b } c (* d *) */
int comment_lossage = 0;
- EMACS_INT comment_end = from;
- EMACS_INT comment_end_byte = from_byte;
- EMACS_INT comstart_pos = 0;
- EMACS_INT comstart_byte;
+ ptrdiff_t comment_end = from;
+ ptrdiff_t comment_end_byte = from_byte;
+ ptrdiff_t comstart_pos = 0;
+ ptrdiff_t 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;
- EMACS_INT defun_start_byte = 0;
+ ptrdiff_t defun_start = 0;
+ ptrdiff_t defun_start_byte = 0;
register enum syntaxcode code;
int nesting = 1; /* current comment nesting */
int c;
that determines quote parity to the comment-end. */
while (from != stop)
{
- int temp_byte, prev_syntax;
- int com2start, com2end;
+ ptrdiff_t temp_byte;
+ int prev_syntax, com2start, com2end;
int comstart;
/* Move back and examine a character. */
/* 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 --
--- c --
have %..\n and %{..}%. */
if (from > stop && (com2end || comstart))
{
- int next = from, next_byte = from_byte, next_c, next_syntax;
+ ptrdiff_t 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);
&& 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. */
{
scan_sexps_forward (&state,
defun_start, defun_start_byte,
- comment_end, -10000, 0, Qnil, 0);
+ comment_end, TYPE_MINIMUM (EMACS_INT),
+ 0, Qnil, 0);
defun_start = comment_end;
if (state.incomment == (comnested ? 1 : -1)
&& state.comstyle == comstyle)
DEFUN ("syntax-table-p", Fsyntax_table_p, Ssyntax_table_p, 1, 1, 0,
doc: /* Return t if OBJECT is a syntax table.
Currently, any char-table counts as a syntax table. */)
- (object)
- Lisp_Object object;
+ (Lisp_Object object)
{
if (CHAR_TABLE_P (object)
&& EQ (XCHAR_TABLE (object)->purpose, Qsyntax_table))
}
static void
-check_syntax_table (obj)
- Lisp_Object obj;
+check_syntax_table (Lisp_Object obj)
{
CHECK_TYPE (CHAR_TABLE_P (obj) && EQ (XCHAR_TABLE (obj)->purpose, Qsyntax_table),
Qsyntax_table_p, obj);
DEFUN ("syntax-table", Fsyntax_table, Ssyntax_table, 0, 0, 0,
doc: /* Return the current syntax table.
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,
Sstandard_syntax_table, 0, 0, 0,
doc: /* Return the standard syntax table.
This is the one used for new buffers. */)
- ()
+ (void)
{
return Vstandard_syntax_table;
}
DEFUN ("copy-syntax-table", Fcopy_syntax_table, Scopy_syntax_table, 0, 1, 0,
doc: /* Construct a new syntax table and return it.
It is a copy of the TABLE, which defaults to the standard syntax table. */)
- (table)
- Lisp_Object table;
+ (Lisp_Object table)
{
Lisp_Object copy;
/* Only the standard syntax table should have a default element.
Other syntax tables should inherit from parents instead. */
- XCHAR_TABLE (copy)->defalt = Qnil;
+ set_char_table_defalt (copy, Qnil);
/* Copied syntax tables should all have parents.
If we copied one with no parent, such as the standard syntax table,
DEFUN ("set-syntax-table", Fset_syntax_table, Sset_syntax_table, 1, 1, 0,
doc: /* Select a new syntax table for the current buffer.
One argument, a syntax table. */)
- (table)
- Lisp_Object table;
+ (Lisp_Object table)
{
int idx;
check_syntax_table (table);
- current_buffer->syntax_table = table;
+ bset_syntax_table (current_buffer, 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);
character `w' (119) is returned.
The characters that correspond to various syntax codes
are listed in the documentation of `modify-syntax-entry'. */)
- (character)
- Lisp_Object character;
+ (Lisp_Object character)
{
int char_int;
- gl_state.current_syntax_table = current_buffer->syntax_table;
-
- gl_state.use_global = 0;
- CHECK_NUMBER (character);
+ CHECK_CHARACTER (character);
char_int = XINT (character);
+ SETUP_BUFFER_SYNTAX_TABLE ();
return make_number (syntax_code_spec[(int) SYNTAX (char_int)]);
}
DEFUN ("matching-paren", Fmatching_paren, Smatching_paren, 1, 1, 0,
doc: /* Return the matching parenthesis of CHARACTER, or nil if none. */)
- (character)
- Lisp_Object character;
+ (Lisp_Object character)
{
int char_int, code;
- gl_state.current_syntax_table = current_buffer->syntax_table;
- gl_state.use_global = 0;
CHECK_NUMBER (character);
char_int = XINT (character);
+ SETUP_BUFFER_SYNTAX_TABLE ();
code = SYNTAX (char_int);
if (code == Sopen || code == Sclose)
return SYNTAX_MATCH (char_int);
`modify-syntax-entry'. Value is the equivalent cons cell
\(CODE . MATCHING-CHAR) that can be used as value of a `syntax-table'
text property. */)
- (string)
- Lisp_Object string;
+ (Lisp_Object string)
{
register const unsigned char *p;
register enum syntaxcode code;
case 'n':
val |= 1 << 22;
break;
+
+ case 'c':
+ val |= 1 << 23;
+ break;
}
- if (val < XVECTOR_SIZE (Vsyntax_code_object) && NILP (match))
- return XVECTOR (Vsyntax_code_object)->contents[val];
+ if (val < ASIZE (Vsyntax_code_object) && NILP (match))
+ return AREF (Vsyntax_code_object, val);
else
/* Since we can't use a shared object, let's make a new one. */
return Fcons (make_number (val), match);
" string quote. \\ escape.
$ paired delimiter. ' expression quote or prefix operator.
< comment starter. > comment ender.
- / character-quote. @ inherit from `standard-syntax-table'.
+ / character-quote. @ inherit from parent table.
| generic string fence. ! generic comment fence.
Only single-character comment start and end sequences are represented thus.
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';
such characters are treated as whitespace when they occur
between expressions.
usage: (modify-syntax-entry CHAR NEWENTRY &optional SYNTAX-TABLE) */)
- (c, newentry, syntax_table)
- Lisp_Object c, newentry, syntax_table;
+ (Lisp_Object c, Lisp_Object newentry, Lisp_Object syntax_table)
{
if (CONSP (c))
{
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);
DEFUN ("internal-describe-syntax-value", Finternal_describe_syntax_value,
Sinternal_describe_syntax_value, 1, 1, 0,
doc: /* Insert a description of the internal syntax description SYNTAX at point. */)
- (syntax)
- Lisp_Object syntax;
+ (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;
first = XCAR (value);
match_lisp = XCDR (value);
- if (!INTEGERP (first) || !(NILP (match_lisp) || INTEGERP (match_lisp)))
+ if (!INTEGERP (first) || !(NILP (match_lisp) || CHARACTERP (match_lisp)))
{
insert_string ("invalid");
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) & INT_MAX;
+ 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 ("\twhich means: ");
- switch (SWITCH_ENUM_CAST (code))
+ switch (code)
{
case Swhitespace:
insert_string ("whitespace"); break;
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 (from, count)
- register int from, count;
+ptrdiff_t
+scan_words (register ptrdiff_t from, register EMACS_INT count)
{
- register int beg = BEGV;
- register int end = ZV;
- register int from_byte = CHAR_TO_BYTE (from);
+ register ptrdiff_t beg = BEGV;
+ register ptrdiff_t end = ZV;
+ register ptrdiff_t 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;
if (! NILP (Ffboundp (func)))
{
pos = call2 (func, make_number (from - 1), make_number (end));
- if (INTEGERP (pos) && XINT (pos) > from)
+ if (INTEGERP (pos) && from < XINT (pos) && XINT (pos) <= ZV)
{
from = XINT (pos);
from_byte = CHAR_TO_BYTE (from);
}
else
{
- script = CHAR_TABLE_REF (Vchar_script_table, ch0);
while (1)
{
if (from == end) break;
if (! NILP (Ffboundp (func)))
{
pos = call2 (func, make_number (from), make_number (beg));
- if (INTEGERP (pos) && XINT (pos) < from)
+ if (INTEGERP (pos) && BEGV <= XINT (pos) && XINT (pos) < from)
{
from = XINT (pos);
from_byte = CHAR_TO_BYTE (from);
}
else
{
- script = CHAR_TABLE_REF (Vchar_script_table, ch1);
while (1)
{
if (from == beg)
If an edge of the buffer or a field boundary is reached, point is left there
and the function returns nil. Field boundaries are not noticed if
`inhibit-field-text-motion' is non-nil. */)
- (arg)
- Lisp_Object arg;
+ (Lisp_Object arg)
{
Lisp_Object tmp;
- int orig_val, val;
+ ptrdiff_t orig_val, val;
if (NILP (arg))
XSETFASTINT (arg, 1);
return val == orig_val ? Qt : Qnil;
}
\f
-Lisp_Object skip_chars ();
-
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
Char classes, e.g. `[:alpha:]', are supported.
Returns the distance traveled, either zero or positive. */)
- (string, lim)
- Lisp_Object string, lim;
+ (Lisp_Object string, Lisp_Object lim)
{
return skip_chars (1, string, lim, 1);
}
doc: /* Move point backward, stopping after a char not in STRING, or at pos LIM.
See `skip-chars-forward' for details.
Returns the distance traveled, either zero or negative. */)
- (string, lim)
- Lisp_Object string, lim;
+ (Lisp_Object string, Lisp_Object lim)
{
return skip_chars (0, string, lim, 1);
}
Stop before a char whose syntax is not in SYNTAX, or at position LIM.
If SYNTAX starts with ^, skip characters whose syntax is NOT in SYNTAX.
This function returns the distance traveled, either zero or positive. */)
- (syntax, lim)
- Lisp_Object syntax, lim;
+ (Lisp_Object syntax, Lisp_Object lim)
{
return skip_syntaxes (1, syntax, lim);
}
Stop on reaching a char whose syntax is not in SYNTAX, or at position LIM.
If SYNTAX starts with ^, skip characters whose syntax is NOT in SYNTAX.
This function returns the distance traveled, either zero or negative. */)
- (syntax, lim)
- Lisp_Object syntax, lim;
+ (Lisp_Object syntax, Lisp_Object lim)
{
return skip_syntaxes (0, syntax, lim);
}
static Lisp_Object
-skip_chars (forwardp, string, lim, handle_iso_classes)
- int forwardp;
- Lisp_Object string, lim;
- int handle_iso_classes;
+skip_chars (int forwardp, Lisp_Object string, Lisp_Object lim, int handle_iso_classes)
{
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 ptrdiff_t 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;
+ ptrdiff_t 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);
- bzero (fastmap, sizeof fastmap);
+ memset (fastmap, 0, sizeof fastmap);
str = SDATA (string);
size_byte = SBYTES (string);
|| *class_end != ':' || class_end[1] != ']')
goto not_a_class_name;
- bcopy (class_beg, class_name, class_end - class_beg);
+ memcpy (class_name, class_beg, class_end - class_beg);
class_name[class_end - class_beg] = 0;
cc = re_wctype (class_name);
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;
unsigned char fastmap2[0400];
int range_start_byte, range_start_char;
- bcopy (fastmap2 + 0200, fastmap + 0200, 0200);
- bzero (fastmap + 0200, 0200);
+ memcpy (fastmap + 0200, fastmap2 + 0200, 0200);
+ memset (fastmap + 0200, 0, 0200);
/* We are sure that this loop stops. */
for (i = 0200; ! fastmap2[i]; i++);
c = BYTE8_TO_CHAR (i);
fastmap[CHAR_LEADING_CODE (c)] = 1;
range_start_byte = i;
range_start_char = c;
- char_ranges = (int *) alloca (sizeof (int) * 128 * 2);
+ char_ranges = alloca (sizeof *char_ranges * 128 * 2);
for (i = 129; i < 0400; i++)
{
c = BYTE8_TO_CHAR (i);
}
else /* STRING is multibyte */
{
- char_ranges = (int *) alloca (sizeof (int) * SCHARS (string) * 2);
+ char_ranges = alloca (sizeof *char_ranges * SCHARS (string) * 2);
while (i_byte < size_byte)
{
|| *class_end != ':' || class_end[1] != ']')
goto not_a_class_name_multibyte;
- bcopy (class_beg, class_name, class_end - class_beg);
+ memcpy (class_name, class_beg, class_end - class_beg);
class_name[class_end - class_beg] = 0;
cc = re_wctype (class_name);
}
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)
{
if (! multibyte && n_char_ranges > 0)
{
- bzero (fastmap + 0200, 0200);
+ memset (fastmap + 0200, 0, 0200);
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;
+ ptrdiff_t start_point = PT;
+ ptrdiff_t pos = PT;
+ ptrdiff_t pos_byte = PT_BYTE;
unsigned char *p = PT_ADDR, *endp, *stop;
if (forwardp)
let's initialize it manually.
We ignore syntax-table text-properties for now, since that's
what we've done in the past. */
- SETUP_SYNTAX_TABLE (BEGV, 0);
+ SETUP_BUFFER_SYNTAX_TABLE ();
if (forwardp)
{
if (multibyte)
static Lisp_Object
-skip_syntaxes (forwardp, string, lim)
- int forwardp;
- Lisp_Object string, lim;
+skip_syntaxes (int forwardp, Lisp_Object string, Lisp_Object lim)
{
register unsigned int c;
unsigned char fastmap[0400];
int negate = 0;
- register int i, i_byte;
+ register ptrdiff_t i, i_byte;
int multibyte;
- int size_byte;
+ ptrdiff_t 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));
- bzero (fastmap, sizeof fastmap);
+ memset (fastmap, 0, sizeof fastmap);
if (SBYTES (string) > SCHARS (string))
/* As this is very rare case (syntax spec is ASCII only), don't
fastmap[i] ^= 1;
{
- int start_point = PT;
- int pos = PT;
- int pos_byte = PT_BYTE;
+ ptrdiff_t start_point = PT;
+ ptrdiff_t pos = PT;
+ ptrdiff_t pos_byte = PT_BYTE;
unsigned char *p = PT_ADDR, *endp, *stop;
if (forwardp)
integer which is its type according to re_wctype. */
static int
-in_classes (c, iso_classes)
- int c;
- Lisp_Object iso_classes;
+in_classes (int c, Lisp_Object iso_classes)
{
int fits_class = 0;
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.
remains valid for forward search starting at the returned position. */
static int
-forw_comment (from, from_byte, stop, nesting, style, prev_syntax,
- charpos_ptr, bytepos_ptr, incomment_ptr)
- EMACS_INT from, from_byte, stop;
- int nesting, style, prev_syntax;
- EMACS_INT *charpos_ptr, *bytepos_ptr;
- int *incomment_ptr;
+forw_comment (ptrdiff_t from, ptrdiff_t from_byte, ptrdiff_t stop,
+ EMACS_INT nesting, int style, int prev_syntax,
+ ptrdiff_t *charpos_ptr, ptrdiff_t *bytepos_ptr,
+ EMACS_INT *incomment_ptr)
{
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 */
Set point to where scanning stops.
If COUNT comments are found as expected, with nothing except whitespace
between them, return t; otherwise return nil. */)
- (count)
- Lisp_Object count;
+ (Lisp_Object count)
{
- register EMACS_INT from;
- EMACS_INT from_byte;
- register EMACS_INT stop;
+ register ptrdiff_t from;
+ ptrdiff_t from_byte;
+ register ptrdiff_t stop;
register int c, c1;
register enum syntaxcode code;
int comstyle = 0; /* style of comment encountered */
int comnested = 0; /* whether the comment is nestable or not */
int found;
EMACS_INT count1;
- EMACS_INT out_charpos, out_bytepos;
- int dummy;
+ ptrdiff_t out_charpos, out_bytepos;
+ EMACS_INT dummy;
CHECK_NUMBER (count);
count1 = XINT (count);
{
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;
+ ptrdiff_t 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;
? SYNTAX (c) : Ssymbol)
static Lisp_Object
-scan_lists (from, count, depth, sexpflag)
- register EMACS_INT from;
- EMACS_INT count, depth;
- int sexpflag;
+scan_lists (register EMACS_INT from, EMACS_INT count, EMACS_INT depth, int sexpflag)
{
Lisp_Object val;
- register EMACS_INT stop = count > 0 ? ZV : BEGV;
+ register ptrdiff_t stop = count > 0 ? ZV : BEGV;
register int c, c1;
int stringterm;
int quoted;
int mathexit = 0;
register enum syntaxcode code, temp_code;
- int min_depth = depth; /* Err out if depth gets less than this. */
+ EMACS_INT min_depth = depth; /* Err out if depth gets less than this. */
int comstyle = 0; /* style of comment encountered */
int comnested = 0; /* whether the comment is nestable or not */
- EMACS_INT temp_pos;
+ ptrdiff_t temp_pos;
EMACS_INT last_good = from;
int found;
- EMACS_INT from_byte;
- EMACS_INT out_bytepos, out_charpos;
- int temp, dummy;
+ ptrdiff_t from_byte;
+ ptrdiff_t out_bytepos, out_charpos;
+ int temp;
+ EMACS_INT dummy;
int multibyte_symbol_p = sexpflag && multibyte_syntax_as_symbol;
if (depth > 0) min_depth = 0;
{
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);
}
if (prefix)
continue;
- switch (SWITCH_ENUM_CAST (code))
+ switch (code)
{
case Sescape:
case Scharquote:
{
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))
+ switch (code)
{
case Sword:
case Ssymbol:
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--;
DEFUN ("scan-lists", Fscan_lists, Sscan_lists, 3, 3, 0,
doc: /* Scan from character number FROM by COUNT lists.
-Returns the character number of the position thus found.
+Scan forward if COUNT is positive, backward if COUNT is negative.
+Return the character number of the position thus found.
+
+A \"list", in this context, refers to a balanced parenthetical
+grouping, as determined by the syntax table.
-If DEPTH is nonzero, paren depth begins counting from that value,
-only places where the depth in parentheses becomes zero
-are candidates for stopping; COUNT such places are counted.
-Thus, a positive value for DEPTH means go out levels.
+If DEPTH is nonzero, treat that as the nesting depth of the starting
+point (i.e. the starting point is DEPTH parentheses deep). This
+function scans over parentheses until the depth goes to zero COUNT
+times. Hence, positive DEPTH moves out that number of levels of
+parentheses, while negative DEPTH moves to a deeper level.
Comments are ignored if `parse-sexp-ignore-comments' is non-nil.
-If the beginning or end of (the accessible part of) the buffer is reached
-and the depth is wrong, an error is signaled.
-If the depth is right but the count is not used up, nil is returned. */)
- (from, count, depth)
- Lisp_Object from, count, depth;
+If we reach the beginning or end of the accessible part of the buffer
+before we have scanned over COUNT lists, return nil if the depth at
+that point is zero, and signal a error if the depth is nonzero. */)
+ (Lisp_Object from, Lisp_Object count, Lisp_Object depth)
{
CHECK_NUMBER (from);
CHECK_NUMBER (count);
in the middle of a parenthetical grouping, an error is signaled.
If the beginning or end is reached between groupings
but before count is used up, nil is returned. */)
- (from, count)
- Lisp_Object from, count;
+ (Lisp_Object from, Lisp_Object count)
{
CHECK_NUMBER (from);
CHECK_NUMBER (count);
0, 0, 0,
doc: /* Move point backward over any number of chars with prefix syntax.
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;
+ ptrdiff_t beg = BEGV;
+ ptrdiff_t opoint = PT;
+ ptrdiff_t opoint_byte = PT_BYTE;
+ ptrdiff_t pos = PT;
+ ptrdiff_t pos_byte = PT_BYTE;
int c;
if (pos <= beg)
after the beginning of a string, or after the end of a string. */
static void
-scan_sexps_forward (stateptr, from, from_byte, end, targetdepth,
- stopbefore, oldstate, commentstop)
- struct lisp_parse_state *stateptr;
- register EMACS_INT from;
- EMACS_INT from_byte, end;
- int targetdepth, stopbefore;
- Lisp_Object oldstate;
- int commentstop;
+scan_sexps_forward (struct lisp_parse_state *stateptr,
+ ptrdiff_t from, ptrdiff_t from_byte, ptrdiff_t end,
+ EMACS_INT targetdepth, int stopbefore,
+ Lisp_Object oldstate, int commentstop)
{
struct lisp_parse_state state;
register enum syntaxcode code;
int c1;
int comnested;
- struct level { int last, prev; };
+ struct level { ptrdiff_t last, prev; };
struct level levelstart[100];
register struct level *curlevel = levelstart;
struct level *endlevel = levelstart + 100;
- register int depth; /* Paren depth of current scanning location.
+ register EMACS_INT depth; /* Paren depth of current scanning location.
level - levelstart equals this except
when the depth becomes negative. */
- int mindepth; /* Lowest DEPTH value seen. */
+ EMACS_INT mindepth; /* Lowest DEPTH value seen. */
int start_quoted = 0; /* Nonzero means starting after a char quote */
Lisp_Object tem;
- EMACS_INT prev_from; /* Keep one character before FROM. */
- EMACS_INT prev_from_byte;
+ ptrdiff_t prev_from; /* Keep one character before FROM. */
+ ptrdiff_t prev_from_byte;
int prev_from_syntax;
int boundary_stop = commentstop == -1;
int nofence;
int found;
- EMACS_INT out_bytepos, out_charpos;
+ ptrdiff_t out_bytepos, out_charpos;
int temp;
prev_from = from;
tem = Fcar (oldstate);
/* Check whether we are inside string_fence-style string: */
state.instring = (!NILP (tem)
- ? (INTEGERP (tem) ? XINT (tem) : ST_STRING_STYLE)
+ ? (CHARACTERP (tem) ? XFASTINT (tem) : ST_STRING_STYLE)
: -1);
oldstate = Fcdr (oldstate);
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
+ : (RANGED_INTEGERP (0, tem, ST_COMMENT_STYLE)
+ ? XINT (tem)
+ : ST_COMMENT_STYLE));
oldstate = Fcdr (oldstate);
tem = Fcar (oldstate);
- state.comstr_start = NILP (tem) ? -1 : XINT (tem) ;
+ state.comstr_start =
+ RANGED_INTEGERP (PTRDIFF_MIN, tem, PTRDIFF_MAX) ? XINT (tem) : -1;
oldstate = Fcdr (oldstate);
tem = Fcar (oldstate);
while (!NILP (tem)) /* >= second enclosing sexps. */
{
- /* curlevel++->last ran into compiler bug on Apollo */
- curlevel->last = XINT (Fcar (tem));
+ Lisp_Object temhd = Fcar (tem);
+ if (RANGED_INTEGERP (PTRDIFF_MIN, temhd, PTRDIFF_MAX))
+ curlevel->last = XINT (temhd);
if (++curlevel == endlevel)
curlevel--; /* error ("Nesting too deep for parser"); */
curlevel->prev = -1;
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;
if (SYNTAX_FLAGS_PREFIX (prev_from_syntax))
continue;
- switch (SWITCH_ENUM_CAST (code))
+ switch (code)
{
case Sescape:
case Scharquote:
= (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
any character that starts a sexp.
Fifth arg OLDSTATE is a list like what this function returns.
It is used to initialize the state of the parse. Elements number 1, 2, 6
- and 8 are ignored.
+ are ignored.
Sixth arg COMMENTSTOP non-nil means stop at the start of a comment.
If it is symbol `syntax-table', stop after the start of a comment or a
string, or after end of a comment or a string. */)
- (from, to, targetdepth, stopbefore, oldstate, commentstop)
- Lisp_Object from, to, targetdepth, stopbefore, oldstate, commentstop;
+ (Lisp_Object from, Lisp_Object to, Lisp_Object targetdepth, Lisp_Object stopbefore, Lisp_Object oldstate, Lisp_Object commentstop)
{
struct lisp_parse_state state;
- int target;
+ EMACS_INT target;
if (!NILP (targetdepth))
{
target = XINT (targetdepth);
}
else
- target = -100000; /* We won't reach this depth */
+ target = TYPE_MINIMUM (EMACS_INT); /* We won't reach this depth */
validate_region (&from, &to);
scan_sexps_forward (&state, XINT (from), CHAR_TO_BYTE (XINT (from)),
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)
}
\f
void
-init_syntax_once ()
+init_syntax_once (void)
{
register int i, c;
Lisp_Object temp;
/* This has to be done here, before we call Fmake_char_table. */
- Qsyntax_table = intern_c_string ("syntax-table");
- staticpro (&Qsyntax_table);
+ DEFSYM (Qsyntax_table, "syntax-table");
/* Intern_C_String this now in case it isn't already done.
Setting this variable twice is harmless.
/* Create objects which can be shared among syntax tables. */
Vsyntax_code_object = Fmake_vector (make_number (Smax), Qnil);
- for (i = 0; i < XVECTOR_SIZE (Vsyntax_code_object); i++)
- XVECTOR (Vsyntax_code_object)->contents[i]
- = Fcons (make_number (i), Qnil);
+ for (i = 0; i < ASIZE (Vsyntax_code_object); i++)
+ ASET (Vsyntax_code_object, i, Fcons (make_number (i), Qnil));
/* Now we are ready to set up this property, so we can
create syntax tables. */
Fput (Qsyntax_table, Qchar_table_extra_slots, make_number (0));
- temp = XVECTOR (Vsyntax_code_object)->contents[(int) Swhitespace];
+ temp = AREF (Vsyntax_code_object, (int) Swhitespace);
Vstandard_syntax_table = Fmake_char_table (Qsyntax_table, temp);
/* Control characters should not be whitespace. */
- temp = XVECTOR (Vsyntax_code_object)->contents[(int) Spunct];
+ temp = AREF (Vsyntax_code_object, (int) Spunct);
for (i = 0; i <= ' ' - 1; i++)
SET_RAW_SYNTAX_ENTRY (Vstandard_syntax_table, i, temp);
SET_RAW_SYNTAX_ENTRY (Vstandard_syntax_table, 0177, temp);
/* Except that a few really are whitespace. */
- temp = XVECTOR (Vsyntax_code_object)->contents[(int) Swhitespace];
+ temp = AREF (Vsyntax_code_object, (int) Swhitespace);
SET_RAW_SYNTAX_ENTRY (Vstandard_syntax_table, ' ', temp);
SET_RAW_SYNTAX_ENTRY (Vstandard_syntax_table, '\t', temp);
SET_RAW_SYNTAX_ENTRY (Vstandard_syntax_table, '\n', temp);
SET_RAW_SYNTAX_ENTRY (Vstandard_syntax_table, 015, temp);
SET_RAW_SYNTAX_ENTRY (Vstandard_syntax_table, 014, temp);
- temp = XVECTOR (Vsyntax_code_object)->contents[(int) Sword];
+ temp = AREF (Vsyntax_code_object, (int) Sword);
for (i = 'a'; i <= 'z'; i++)
SET_RAW_SYNTAX_ENTRY (Vstandard_syntax_table, i, temp);
for (i = 'A'; i <= 'Z'; i++)
SET_RAW_SYNTAX_ENTRY (Vstandard_syntax_table, '\\',
Fcons (make_number ((int) Sescape), Qnil));
- temp = XVECTOR (Vsyntax_code_object)->contents[(int) Ssymbol];
+ temp = AREF (Vsyntax_code_object, (int) Ssymbol);
for (i = 0; i < 10; i++)
{
c = "_-+*/&|<>="[i];
SET_RAW_SYNTAX_ENTRY (Vstandard_syntax_table, c, temp);
}
- temp = XVECTOR (Vsyntax_code_object)->contents[(int) Spunct];
+ temp = AREF (Vsyntax_code_object, (int) Spunct);
for (i = 0; i < 12; i++)
{
c = ".,;:?!#@~^'`"[i];
}
/* All multibyte characters have syntax `word' by default. */
- temp = XVECTOR (Vsyntax_code_object)->contents[(int) Sword];
+ temp = AREF (Vsyntax_code_object, (int) Sword);
char_table_set_range (Vstandard_syntax_table, 0x80, MAX_CHAR, temp);
}
void
-syms_of_syntax ()
+syms_of_syntax (void)
{
- Qsyntax_table_p = intern_c_string ("syntax-table-p");
- staticpro (&Qsyntax_table_p);
+ DEFSYM (Qsyntax_table_p, "syntax-table-p");
staticpro (&Vsyntax_code_object);
/* Defined in regex.c */
staticpro (&re_match_object);
- Qscan_error = intern_c_string ("scan-error");
- staticpro (&Qscan_error);
+ DEFSYM (Qscan_error, "scan-error");
Fput (Qscan_error, Qerror_conditions,
- pure_cons (Qscan_error, pure_cons (Qerror, Qnil)));
+ listn (CONSTYPE_PURE, 2, Qscan_error, Qerror));
Fput (Qscan_error, Qerror_message,
- make_pure_c_string ("Scan error"));
+ build_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,
- doc: /* *Non-nil means an open paren in column 0 denotes the start of a defun. */);
+ 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) */
HCoop / bpt / emacs.git / blobdiff