/* GNU Emacs routines to deal with syntax tables; also word and list parsing.
- Copyright (C) 1985, 87, 93, 94, 95, 97, 1998, 1999 Free Software Foundation, Inc.
+ Copyright (C) 1985, 1987, 1993, 1994, 1995, 1997, 1998, 1999, 2002,
+ 2003, 2004, 2005, 2006 Free Software Foundation, Inc.
This file is part of GNU Emacs.
You should have received a copy of the GNU General Public License
along with GNU Emacs; see the file COPYING. If not, write to
-the Free Software Foundation, Inc., 59 Temple Place - Suite 330,
-Boston, MA 02111-1307, USA. */
+the Free Software Foundation, Inc., 51 Franklin Street, Fifth Floor,
+Boston, MA 02110-1301, USA. */
#include <config.h>
#include "buffer.h"
#include "charset.h"
#include "keymap.h"
+#include "regex.h"
/* Make syntax table lookup grant data in gl_state. */
#define SYNTAX_ENTRY_VIA_PROPERTY
static int find_defun_start P_ ((int, int));
static int back_comment P_ ((int, int, int, int, int, int *, int *));
static int char_quoted P_ ((int, int));
-static Lisp_Object skip_chars P_ ((int, int, Lisp_Object, Lisp_Object));
+static Lisp_Object skip_chars P_ ((int, int, Lisp_Object, Lisp_Object, int));
static Lisp_Object scan_lists P_ ((int, int, int, int));
static void scan_sexps_forward P_ ((struct lisp_parse_state *,
int, int, int, int,
int, Lisp_Object, int));
+static int in_classes P_ ((int, Lisp_Object));
\f
struct gl_state_s gl_state; /* Global state of syntax parser. */
{
Lisp_Object tmp_table;
int cnt = 0, invalidate = 1;
- INTERVAL i, oldi;
+ INTERVAL i;
if (init)
{
gl_state.e_property = INTERVAL_LAST_POS (i) - gl_state.offset;
goto update;
}
- oldi = i = count > 0 ? gl_state.forward_i : gl_state.backward_i;
+ i = count > 0 ? gl_state.forward_i : gl_state.backward_i;
/* We are guaranteed to be called with CHARPOS either in i,
or further off. */
if (invalidate)
invalidate = !EQ (tmp_table, gl_state.old_prop); /* Need to invalidate? */
-
+
if (invalidate) /* Did not get to adjacent interval. */
{ /* with the same table => */
/* invalidate the old range. */
if (EQ (Fsyntax_table_p (tmp_table), Qt))
{
gl_state.use_global = 0;
- }
+ }
else if (CONSP (tmp_table))
{
gl_state.use_global = 1;
gl_state.global_code = tmp_table;
}
- else
+ else
{
gl_state.use_global = 0;
gl_state.current_syntax_table = current_buffer->syntax_table;
}
else
{
- gl_state.b_property = i->position + LENGTH (i) - gl_state.offset;
+ gl_state.b_property
+ = i->position + LENGTH (i) - gl_state.offset;
gl_state.backward_i = i;
}
return;
}
- else if (cnt == INTERVALS_AT_ONCE)
+ else if (cnt == INTERVALS_AT_ONCE)
{
if (count > 0)
{
- gl_state.e_property = i->position + LENGTH (i) - gl_state.offset;
+ gl_state.e_property
+ = i->position + LENGTH (i) - gl_state.offset
+ /* 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);
gl_state.forward_i = i;
}
else
DEC_BOTH (charpos, bytepos);
- while (bytepos >= beg)
+ while (charpos >= beg)
{
+ int c;
+
UPDATE_SYNTAX_TABLE_BACKWARD (charpos);
- code = SYNTAX (FETCH_CHAR (bytepos));
+ c = FETCH_CHAR (bytepos);
+ code = SYNTAX (c);
if (! (code == Scharquote || code == Sescape))
break;
It should be the last one before POS, or nearly the last.
When open_paren_in_column_0_is_defun_start is nonzero,
- the beginning of every line is treated as a defun-start.
+ only the beginning of the buffer is treated as a defun-start.
We record the information about where the scan started
and what its result was, so that another call in the same area
{
int opoint = PT, opoint_byte = PT_BYTE;
+ if (!open_paren_in_column_0_is_defun_start)
+ {
+ find_start_value_byte = BEGV_BYTE;
+ return BEGV;
+ }
+
/* Use previous finding, if it's valid and applies to this inquiry. */
if (current_buffer == find_start_buffer
/* Reuse the defun-start even if POS is a little farther on.
syntax-tables. */
gl_state.current_syntax_table = current_buffer->syntax_table;
gl_state.use_global = 0;
- if (open_paren_in_column_0_is_defun_start)
+ while (PT > BEGV)
{
- while (PT > BEGV)
+ int c;
+
+ /* Open-paren at start of line means we may have found our
+ defun-start. */
+ c = FETCH_CHAR (PT_BYTE);
+ if (SYNTAX (c) == Sopen)
{
- /* Open-paren at start of line means we may have found our
- defun-start. */
- if (SYNTAX (FETCH_CHAR (PT_BYTE)) == Sopen)
- {
- SETUP_SYNTAX_TABLE (PT + 1, -1); /* Try again... */
- if (SYNTAX (FETCH_CHAR (PT_BYTE)) == Sopen)
- break;
- /* Now fallback to the default value. */
- gl_state.current_syntax_table = current_buffer->syntax_table;
- gl_state.use_global = 0;
- }
- /* Move to beg of previous line. */
- scan_newline (PT, PT_BYTE, BEGV, BEGV_BYTE, -2, 1);
+ SETUP_SYNTAX_TABLE (PT + 1, -1); /* Try again... */
+ c = FETCH_CHAR (PT_BYTE);
+ 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;
}
+ /* Move to beg of previous line. */
+ scan_newline (PT, PT_BYTE, BEGV, BEGV_BYTE, -2, 1);
}
/* Record what we found, for the next try. */
* int pos, pos_byte;
* {
* int c, val;
- *
+ *
* DEC_BOTH (pos, pos_byte);
* UPDATE_SYNTAX_TABLE_BACKWARD (pos);
* c = FETCH_CHAR (pos_byte);
int string_style = -1; /* Presumed outside of any string. */
int string_lossage = 0;
/* Not a real lossage: indicates that we have passed a matching comment
- starter plus an non-matching comment-ender, meaning that any matching
+ starter plus a non-matching comment-ender, meaning that any matching
comment-starter we might see later could be a false positive (hidden
inside another comment).
Test case: { a (* b } c (* d *) */
There's no way to grok this scanning backwards. */
string_lossage = 1;
break;
-
+
case Scomment:
/* We've already checked that it is the relevant comstyle. */
if (string_style != -1 || comment_lossage || string_lossage)
case Sendcomment:
if (SYNTAX_FLAGS_COMMENT_STYLE (syntax) == comstyle
- && (SYNTAX_FLAGS_COMMENT_NESTED (prev_syntax)
+ && ((com2end && SYNTAX_FLAGS_COMMENT_NESTED (prev_syntax))
|| SYNTAX_FLAGS_COMMENT_NESTED (syntax)) == comnested)
/* This is the same style of comment ender as ours. */
{
{
from = comstart_pos;
from_byte = comstart_byte;
- /* Globals are correct now. */
+ UPDATE_SYNTAX_TABLE_FORWARD (from - 1);
}
else
{
from_byte = CHAR_TO_BYTE (from);
UPDATE_SYNTAX_TABLE_FORWARD (from - 1);
}
-
+
done:
*charpos_ptr = from;
*bytepos_ptr = from_byte;
if (!(CHAR_TABLE_P (obj)
&& EQ (XCHAR_TABLE (obj)->purpose, Qsyntax_table)))
wrong_type_argument (Qsyntax_table_p, obj);
-}
+}
DEFUN ("syntax-table", Fsyntax_table, Ssyntax_table, 0, 0, 0,
doc: /* Return the current syntax table.
gl_state.current_syntax_table = current_buffer->syntax_table;
gl_state.use_global = 0;
- CHECK_NUMBER (character, 0);
+ CHECK_NUMBER (character);
char_int = XINT (character);
return make_number (syntax_code_spec[(int) SYNTAX (char_int)]);
}
int char_int, code;
gl_state.current_syntax_table = current_buffer->syntax_table;
gl_state.use_global = 0;
- CHECK_NUMBER (character, 0);
+ CHECK_NUMBER (character);
char_int = XINT (character);
code = SYNTAX (char_int);
if (code == Sopen || code == Sclose)
(string)
Lisp_Object string;
{
- register unsigned char *p;
+ register const unsigned char *p;
register enum syntaxcode code;
int val;
Lisp_Object match;
- CHECK_STRING (string, 0);
+ CHECK_STRING (string);
- p = XSTRING (string)->data;
+ p = SDATA (string);
code = (enum syntaxcode) syntax_spec_code[*p++];
if (((int) code & 0377) == 0377)
- error ("invalid syntax description letter: %c", p[-1]);
+ error ("Invalid syntax description letter: %c", p[-1]);
if (code == Sinherit)
return Qnil;
{
int len;
int character = (STRING_CHAR_AND_LENGTH
- (p, STRING_BYTES (XSTRING (string)) - 1, len));
+ (p, SBYTES (string) - 1, len));
XSETINT (match, character);
if (XFASTINT (match) == ' ')
match = Qnil;
val |= 1 << 22;
break;
}
-
+
if (val < XVECTOR (Vsyntax_code_object)->size && NILP (match))
return XVECTOR (Vsyntax_code_object)->contents[val];
else
}
/* I really don't know why this is interactive
- help-form should at least be made useful whilst reading the second arg
-*/
-DEFUN ("modify-syntax-entry", Fmodify_syntax_entry, Smodify_syntax_entry, 2, 3,
+ help-form should at least be made useful whilst reading the second arg. */
+DEFUN ("modify-syntax-entry", Fmodify_syntax_entry, Smodify_syntax_entry, 2, 3,
"cSet syntax for character: \nsSet syntax for %s to: ",
- doc: /* Set syntax for character C according to string NEWENTRY.
-The syntax is changed only for table SYNTAX_TABLE, which defaults to
+ doc: /* Set syntax for character CHAR according to string NEWENTRY.
+The syntax is changed only for table SYNTAX-TABLE, which defaults to
the current buffer's syntax table.
The first character of NEWENTRY should be one of the following:
Space or - whitespace syntax. w word constituent.
used only if the first character is `(' or `)'.
Any additional characters are flags.
Defined flags are the characters 1, 2, 3, 4, b, p, and n.
- 1 means C is the start of a two-char comment start sequence.
- 2 means C is the second character of such a sequence.
- 3 means C is the start of a two-char comment end sequence.
- 4 means C is the second character of such a sequence.
+ 1 means CHAR is the start of a two-char comment start sequence.
+ 2 means CHAR is the second character of such a sequence.
+ 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
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:
- b means C is part of comment sequence b.
- n means C is part of a nestable comment sequence.
+ b means CHAR is part of comment sequence b.
+ n means CHAR is part of a nestable comment sequence.
- p means C is a prefix character for `backward-prefix-chars';
+ p means CHAR is a prefix character for `backward-prefix-chars';
such characters are treated as whitespace when they occur
- between expressions. */)
+ between expressions.
+usage: (modify-syntax-entry CHAR NEWENTRY &optional SYNTAX-TABLE) */)
(c, newentry, syntax_table)
Lisp_Object c, newentry, syntax_table;
{
- CHECK_NUMBER (c, 0);
+ CHECK_NUMBER (c);
if (NILP (syntax_table))
syntax_table = current_buffer->syntax_table;
\f
/* Dump syntax table to buffer in human-readable format */
-static void
-describe_syntax (value)
- Lisp_Object value;
+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;
{
register enum syntaxcode code;
char desc, start1, start2, end1, end2, prefix, comstyle, comnested;
char str[2];
- Lisp_Object first, match_lisp;
-
- Findent_to (make_number (16), make_number (1));
+ Lisp_Object first, match_lisp, value = syntax;
if (NILP (value))
{
- insert_string ("default\n");
- return;
+ insert_string ("default");
+ return syntax;
}
if (CHAR_TABLE_P (value))
{
- insert_string ("deeper char-table ...\n");
- return;
+ insert_string ("deeper char-table ...");
+ return syntax;
}
if (!CONSP (value))
{
- insert_string ("invalid\n");
- return;
+ insert_string ("invalid");
+ return syntax;
}
first = XCAR (value);
if (!INTEGERP (first) || !(NILP (match_lisp) || INTEGERP (match_lisp)))
{
- insert_string ("invalid\n");
- return;
+ insert_string ("invalid");
+ return syntax;
}
code = (enum syntaxcode) (XINT (first) & 0377);
if ((int) code < 0 || (int) code >= (int) Smax)
{
insert_string ("invalid");
- return;
+ return syntax;
}
desc = syntax_code_spec[(int) code];
insert_string ("string fence"); break;
default:
insert_string ("invalid");
- return;
+ return syntax;
}
if (!NILP (match_lisp))
if (prefix)
insert_string (",\n\t is a prefix character for `backward-prefix-chars'");
- insert_string ("\n");
-}
-
-static Lisp_Object
-describe_syntax_1 (vector)
- Lisp_Object vector;
-{
- struct buffer *old = current_buffer;
- set_buffer_internal (XBUFFER (Vstandard_output));
- describe_vector (vector, Qnil, describe_syntax, 0, Qnil, Qnil, (int *) 0, 0);
- while (! NILP (XCHAR_TABLE (vector)->parent))
- {
- vector = XCHAR_TABLE (vector)->parent;
- insert_string ("\nThe parent syntax table is:");
- describe_vector (vector, Qnil, describe_syntax, 0, Qnil, Qnil,
- (int *) 0, 0);
- }
-
- call0 (intern ("help-mode"));
- set_buffer_internal (old);
- return Qnil;
-}
-
-DEFUN ("describe-syntax", Fdescribe_syntax, Sdescribe_syntax, 0, 0, "",
- doc: /* Describe the syntax specifications in the syntax table.
-The descriptions are inserted in a buffer, which is then displayed. */)
- ()
-{
- internal_with_output_to_temp_buffer
- ("*Help*", describe_syntax_1, current_buffer->syntax_table);
-
- return Qnil;
+ return syntax;
}
\f
int parse_sexp_ignore_comments;
return from;
}
-DEFUN ("forward-word", Fforward_word, Sforward_word, 1, 1, "p",
+DEFUN ("forward-word", Fforward_word, Sforward_word, 0, 1, "p",
doc: /* Move point forward ARG words (backward if ARG is negative).
Normally returns t.
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. */)
- (count)
- Lisp_Object count;
+ (arg)
+ Lisp_Object arg;
{
+ Lisp_Object tmp;
int orig_val, val;
- CHECK_NUMBER (count, 0);
- val = orig_val = scan_words (PT, XINT (count));
+ if (NILP (arg))
+ XSETFASTINT (arg, 1);
+ else
+ CHECK_NUMBER (arg);
+
+ val = orig_val = scan_words (PT, XINT (arg));
if (! orig_val)
- val = XINT (count) > 0 ? ZV : BEGV;
+ val = XINT (arg) > 0 ? ZV : BEGV;
/* Avoid jumping out of an input field. */
- val = XFASTINT (Fconstrain_to_field (make_number (val), make_number (PT),
- Qt, Qnil, Qnil));
-
+ tmp = Fconstrain_to_field (make_number (val), make_number (PT),
+ Qt, Qnil, Qnil);
+ val = XFASTINT (tmp);
+
SET_PT (val);
return val == orig_val ? Qt : Qnil;
}
(but not as the end of a range; quoting is never needed there).
Thus, with arg "a-zA-Z", this skips letters stopping before first nonletter.
With arg "^a-zA-Z", skips nonletters stopping before first letter.
+Char classes, e.g. `[:alpha:]', are supported.
+
Returns the distance traveled, either zero or positive. */)
(string, lim)
Lisp_Object string, lim;
{
- return skip_chars (1, 0, string, lim);
+ return skip_chars (1, 0, string, lim, 1);
}
DEFUN ("skip-chars-backward", Fskip_chars_backward, Sskip_chars_backward, 1, 2, 0,
(string, lim)
Lisp_Object string, lim;
{
- return skip_chars (0, 0, string, lim);
+ return skip_chars (0, 0, string, lim, 1);
}
DEFUN ("skip-syntax-forward", Fskip_syntax_forward, Sskip_syntax_forward, 1, 2, 0,
(syntax, lim)
Lisp_Object syntax, lim;
{
- return skip_chars (1, 1, syntax, lim);
+ return skip_chars (1, 1, syntax, lim, 0);
}
DEFUN ("skip-syntax-backward", Fskip_syntax_backward, Sskip_syntax_backward, 1, 2, 0,
(syntax, lim)
Lisp_Object syntax, lim;
{
- return skip_chars (0, 1, syntax, lim);
+ return skip_chars (0, 1, syntax, lim, 0);
}
static Lisp_Object
-skip_chars (forwardp, syntaxp, string, lim)
+skip_chars (forwardp, syntaxp, string, lim, handle_iso_classes)
int forwardp, syntaxp;
Lisp_Object string, lim;
+ int handle_iso_classes;
{
register unsigned int c;
unsigned char fastmap[0400];
int multibyte = !NILP (current_buffer->enable_multibyte_characters);
int string_multibyte;
int size_byte;
- unsigned char *str;
+ const unsigned char *str;
int len;
+ Lisp_Object iso_classes;
- CHECK_STRING (string, 0);
- char_ranges = (int *) alloca (XSTRING (string)->size * (sizeof (int)) * 2);
+ CHECK_STRING (string);
+ char_ranges = (int *) alloca (SCHARS (string) * (sizeof (int)) * 2);
string_multibyte = STRING_MULTIBYTE (string);
- str = XSTRING (string)->data;
- size_byte = STRING_BYTES (XSTRING (string));
+ str = SDATA (string);
+ size_byte = SBYTES (string);
+ iso_classes = Qnil;
/* Adjust the multibyteness of the string to that of the buffer. */
if (multibyte != string_multibyte)
int nbytes;
if (multibyte)
- nbytes = count_size_as_multibyte (XSTRING (string)->data,
- XSTRING (string)->size);
+ nbytes = count_size_as_multibyte (SDATA (string),
+ SCHARS (string));
else
- nbytes = XSTRING (string)->size;
+ nbytes = SCHARS (string);
if (nbytes != size_byte)
{
- str = (unsigned char *) alloca (nbytes);
- copy_text (XSTRING (string)->data, str, size_byte,
+ unsigned char *tmp = (unsigned char *) alloca (nbytes);
+ copy_text (SDATA (string), tmp, size_byte,
string_multibyte, multibyte);
size_byte = nbytes;
+ str = tmp;
}
}
if (NILP (lim))
XSETINT (lim, forwardp ? ZV : BEGV);
else
- CHECK_NUMBER_COERCE_MARKER (lim, 0);
+ CHECK_NUMBER_COERCE_MARKER (lim);
/* In any case, don't allow scan outside bounds of buffer. */
if (XINT (lim) > ZV)
i_byte = 0;
if (i_byte < size_byte
- && XSTRING (string)->data[0] == '^')
+ && SREF (string, 0) == '^')
{
negate = 1; i_byte++;
}
fastmap[syntax_spec_code[c & 0377]] = 1;
else
{
+ if (handle_iso_classes && c == '['
+ && i_byte < size_byte
+ && STRING_CHAR (str + i_byte, size_byte - i_byte) == ':')
+ {
+ const unsigned char *class_beg = str + i_byte + 1;
+ const unsigned char *class_end = class_beg;
+ const unsigned char *class_limit = str + size_byte - 2;
+ /* Leave room for the null. */
+ unsigned char class_name[CHAR_CLASS_MAX_LENGTH + 1];
+ re_wctype_t cc;
+
+ if (class_limit - class_beg > CHAR_CLASS_MAX_LENGTH)
+ class_limit = class_beg + CHAR_CLASS_MAX_LENGTH;
+
+ while (class_end < class_limit
+ && *class_end >= 'a' && *class_end <= 'z')
+ class_end++;
+
+ if (class_end == class_beg
+ || *class_end != ':' || class_end[1] != ']')
+ goto not_a_class_name;
+
+ bcopy (class_beg, class_name, class_end - class_beg);
+ class_name[class_end - class_beg] = 0;
+
+ cc = re_wctype (class_name);
+ if (cc == 0)
+ error ("Invalid ISO C character class");
+
+ iso_classes = Fcons (make_number (cc), iso_classes);
+
+ i_byte = class_end + 2 - str;
+ continue;
+ }
+
+ not_a_class_name:
if (c == '\\')
{
if (i_byte == size_byte)
break;
- c = STRING_CHAR_AND_LENGTH (str+i_byte, size_byte-i_byte, len);
+ c = STRING_CHAR_AND_LENGTH (str + i_byte,
+ size_byte - i_byte, len);
i_byte += len;
}
- if (i_byte < size_byte
+ /* Treat `-' as range character only if another character
+ follows. */
+ if (i_byte + 1 < size_byte
&& str[i_byte] == '-')
{
unsigned int c2;
/* Skip over the dash. */
i_byte++;
- if (i_byte == size_byte)
- break;
-
/* Get the end of the range. */
- c2 =STRING_CHAR_AND_LENGTH (str+i_byte, size_byte-i_byte, len);
+ c2 = STRING_CHAR_AND_LENGTH (str + i_byte,
+ size_byte - i_byte, len);
i_byte += len;
if (SINGLE_BYTE_CHAR_P (c))
int start_point = PT;
int pos = PT;
int pos_byte = PT_BYTE;
+ unsigned char *p = PT_ADDR, *endp, *stop;
+
+ if (forwardp)
+ {
+ endp = (XINT (lim) == GPT) ? GPT_ADDR : CHAR_POS_ADDR (XINT (lim));
+ stop = (pos < GPT && GPT < XINT (lim)) ? GPT_ADDR : endp;
+ }
+ else
+ {
+ endp = CHAR_POS_ADDR (XINT (lim));
+ stop = (pos >= GPT && GPT > XINT (lim)) ? GAP_END_ADDR : endp;
+ }
immediate_quit = 1;
if (syntaxp)
if (forwardp)
{
if (multibyte)
- {
- if (pos < XINT (lim))
- while (fastmap[(int) SYNTAX (FETCH_CHAR (pos_byte))])
+ while (1)
+ {
+ int nbytes;
+
+ if (p >= stop)
{
- /* Since we already checked for multibyteness,
- avoid using INC_BOTH which checks again. */
- INC_POS (pos_byte);
- pos++;
- if (pos >= XINT (lim))
- break;
- UPDATE_SYNTAX_TABLE_FORWARD (pos);
+ if (p >= endp)
+ break;
+ p = GAP_END_ADDR;
+ stop = endp;
}
- }
+ c = STRING_CHAR_AND_LENGTH (p, MAX_MULTIBYTE_LENGTH, nbytes);
+ if (! fastmap[(int) SYNTAX (c)])
+ break;
+ p += nbytes, pos++, pos_byte += nbytes;
+ UPDATE_SYNTAX_TABLE_FORWARD (pos);
+ }
else
- {
- while (pos < XINT (lim)
- && fastmap[(int) SYNTAX (FETCH_BYTE (pos))])
- {
- pos++;
- UPDATE_SYNTAX_TABLE_FORWARD (pos);
- }
- }
+ while (1)
+ {
+ if (p >= stop)
+ {
+ if (p >= endp)
+ break;
+ p = GAP_END_ADDR;
+ stop = endp;
+ }
+ if (! fastmap[(int) SYNTAX (*p)])
+ break;
+ p++, pos++;
+ UPDATE_SYNTAX_TABLE_FORWARD (pos);
+ }
}
else
{
if (multibyte)
- {
- while (pos > XINT (lim))
- {
- int savepos = pos_byte;
- /* Since we already checked for multibyteness,
- avoid using DEC_BOTH which checks again. */
- pos--;
- DEC_POS (pos_byte);
- UPDATE_SYNTAX_TABLE_BACKWARD (pos);
- if (!fastmap[(int) SYNTAX (FETCH_CHAR (pos_byte))])
- {
- pos++;
- pos_byte = savepos;
+ while (1)
+ {
+ unsigned char *prev_p;
+ int nbytes;
+
+ if (p <= stop)
+ {
+ if (p <= endp)
break;
- }
- }
- }
+ p = GPT_ADDR;
+ stop = endp;
+ }
+ prev_p = p;
+ while (--p >= stop && ! CHAR_HEAD_P (*p));
+ PARSE_MULTIBYTE_SEQ (p, MAX_MULTIBYTE_LENGTH, nbytes);
+ if (prev_p - p > nbytes)
+ p = prev_p - 1, c = *p, nbytes = 1;
+ else
+ c = STRING_CHAR (p, MAX_MULTIBYTE_LENGTH);
+ pos--, pos_byte -= nbytes;
+ UPDATE_SYNTAX_TABLE_BACKWARD (pos);
+ if (! fastmap[(int) SYNTAX (c)])
+ {
+ pos++;
+ pos_byte += nbytes;
+ break;
+ }
+ }
else
- {
- if (pos > XINT (lim))
- while (fastmap[(int) SYNTAX (FETCH_BYTE (pos - 1))])
+ while (1)
+ {
+ if (p <= stop)
{
- pos--;
- if (pos <= XINT (lim))
+ if (p <= endp)
break;
- UPDATE_SYNTAX_TABLE_BACKWARD (pos - 1);
+ p = GPT_ADDR;
+ stop = endp;
}
- }
+ if (! fastmap[(int) SYNTAX (p[-1])])
+ break;
+ p--, pos--;
+ UPDATE_SYNTAX_TABLE_BACKWARD (pos - 1);
+ }
}
}
else
if (forwardp)
{
if (multibyte)
- while (pos < XINT (lim))
+ while (1)
{
- c = FETCH_MULTIBYTE_CHAR (pos_byte);
+ int nbytes;
+
+ if (p >= stop)
+ {
+ if (p >= endp)
+ break;
+ p = GAP_END_ADDR;
+ stop = endp;
+ }
+ c = STRING_CHAR_AND_LENGTH (p, MAX_MULTIBYTE_LENGTH, nbytes);
+
+ if (! NILP (iso_classes) && in_classes (c, iso_classes))
+ {
+ if (negate)
+ break;
+ else
+ goto fwd_ok;
+ }
+
if (SINGLE_BYTE_CHAR_P (c))
{
if (!fastmap[c])
if (!(negate ^ (i < n_char_ranges)))
break;
}
- INC_BOTH (pos, pos_byte);
+ fwd_ok:
+ p += nbytes, pos++, pos_byte += nbytes;
}
else
- while (pos < XINT (lim) && fastmap[FETCH_BYTE (pos)])
- pos++;
+ while (1)
+ {
+ if (p >= stop)
+ {
+ if (p >= endp)
+ break;
+ p = GAP_END_ADDR;
+ stop = endp;
+ }
+
+ if (!NILP (iso_classes) && in_classes (*p, iso_classes))
+ {
+ if (negate)
+ break;
+ else
+ goto fwd_unibyte_ok;
+ }
+
+ if (!fastmap[*p])
+ break;
+ fwd_unibyte_ok:
+ p++, pos++;
+ }
}
else
{
if (multibyte)
- while (pos > XINT (lim))
+ while (1)
{
- int prev_pos_byte = pos_byte;
+ unsigned char *prev_p;
+ int nbytes;
+
+ if (p <= stop)
+ {
+ if (p <= endp)
+ break;
+ p = GPT_ADDR;
+ stop = endp;
+ }
+ prev_p = p;
+ while (--p >= stop && ! CHAR_HEAD_P (*p));
+ PARSE_MULTIBYTE_SEQ (p, MAX_MULTIBYTE_LENGTH, nbytes);
+ if (prev_p - p > nbytes)
+ p = prev_p - 1, c = *p, nbytes = 1;
+ else
+ c = STRING_CHAR (p, MAX_MULTIBYTE_LENGTH);
+
+ if (! NILP (iso_classes) && in_classes (c, iso_classes))
+ {
+ if (negate)
+ break;
+ else
+ goto back_ok;
+ }
- DEC_POS (prev_pos_byte);
- c = FETCH_MULTIBYTE_CHAR (prev_pos_byte);
if (SINGLE_BYTE_CHAR_P (c))
{
if (!fastmap[c])
if (!(negate ^ (i < n_char_ranges)))
break;
}
- pos--;
- pos_byte = prev_pos_byte;
+ back_ok:
+ pos--, pos_byte -= nbytes;
}
else
- while (pos > XINT (lim) && fastmap[FETCH_BYTE (pos - 1)])
- pos--;
+ while (1)
+ {
+ if (p <= stop)
+ {
+ if (p <= endp)
+ break;
+ p = GPT_ADDR;
+ stop = endp;
+ }
+
+ if (! NILP (iso_classes) && in_classes (p[-1], iso_classes))
+ {
+ if (negate)
+ break;
+ else
+ goto back_unibyte_ok;
+ }
+
+ if (!fastmap[p[-1]])
+ break;
+ back_unibyte_ok:
+ p--, pos--;
+ }
}
}
return make_number (PT - start_point);
}
}
+
+/* Return 1 if character C belongs to one of the ISO classes
+ in the list ISO_CLASSES. Each class is represented by an
+ integer which is its type according to re_wctype. */
+
+static int
+in_classes (c, iso_classes)
+ int c;
+ Lisp_Object iso_classes;
+{
+ int fits_class = 0;
+
+ while (! NILP (iso_classes))
+ {
+ Lisp_Object elt;
+ elt = XCAR (iso_classes);
+ iso_classes = XCDR (iso_classes);
+
+ if (re_iswctype (c, XFASTINT (elt)))
+ fits_class = 1;
+ }
+
+ return fits_class;
+}
\f
/* Jump over a comment, assuming we are at the beginning of one.
FROM is the current position.
nesting++;
INC_BOTH (from, from_byte);
UPDATE_SYNTAX_TABLE_FORWARD (from);
-
+
forw_incomment:
if (from < stop && SYNTAX_FLAGS_COMEND_FIRST (syntax)
&& SYNTAX_FLAGS_COMMENT_STYLE (syntax) == style
}
DEFUN ("forward-comment", Fforward_comment, Sforward_comment, 1, 1, 0,
- doc: /* Move forward across up to N comments. If N is negative, move backward.
+ doc: /*
+Move forward across up to COUNT comments. If COUNT is negative, move backward.
Stop scanning if we find something other than a comment or whitespace.
Set point to where scanning stops.
-If N comments are found as expected, with nothing except whitespace
+If COUNT comments are found as expected, with nothing except whitespace
between them, return t; otherwise return nil. */)
(count)
Lisp_Object count;
int out_charpos, out_bytepos;
int dummy;
- CHECK_NUMBER (count, 0);
+ CHECK_NUMBER (count);
count1 = XINT (count);
stop = count1 > 0 ? ZV : BEGV;
&& (c1 = FETCH_CHAR (from_byte),
SYNTAX_COMSTART_SECOND (c1)))
{
- /* We have encountered a comment start sequence and we
+ /* We have encountered a comment start sequence and we
are ignoring all text inside comments. We must record
the comment style this sequence begins so that later,
only a comment end of the same style actually ends
{
/* Skip until first preceding unquoted comment_fence. */
int found = 0, ini = from, ini_byte = from_byte;
-
+
while (1)
{
DEC_BOTH (from, from_byte);
- if (from == stop)
- break;
UPDATE_SYNTAX_TABLE_BACKWARD (from);
c = FETCH_CHAR (from_byte);
if (SYNTAX (c) == Scomment_fence
- && !char_quoted (from, from_byte))
+ && !char_quoted (from, from_byte))
{
- found = 1;
+ found = 1;
break;
}
+ else if (from == stop)
+ break;
}
if (found == 0)
{
from_byte = ini_byte;
goto leave;
}
+ else
+ /* We have skipped one comment. */
+ break;
}
else if (code == Sendcomment)
{
INC_BOTH (from, from_byte);
UPDATE_SYNTAX_TABLE_FORWARD (from);
if (from < stop && comstart_first
- && SYNTAX_COMSTART_SECOND (FETCH_CHAR (from_byte))
+ && (c = FETCH_CHAR (from_byte), SYNTAX_COMSTART_SECOND (c))
&& parse_sexp_ignore_comments)
{
- /* we have encountered a comment start sequence and we
+ /* we have encountered a comment start sequence and we
are ignoring all text inside comments. We must record
the comment style this sequence begins so that later,
only a comment end of the same style actually ends
INC_BOTH (from, from_byte);
UPDATE_SYNTAX_TABLE_FORWARD (from);
}
-
+
if (prefix)
continue;
INC_BOTH (from, from_byte);
if (!depth && sexpflag) goto done;
break;
+ default:
+ /* Ignore whitespace, punctuation, quote, endcomment. */
+ break;
}
}
comstyle = SYNTAX_COMMENT_STYLE (c1);
comnested = comnested || SYNTAX_COMMENT_NESTED (c1);
}
-
+
/* Quoting turns anything except a comment-ender
into a word character. Note that this cannot be true
if we decremented FROM in the if-statement above. */
if (code != Sendcomment && char_quoted (from, from_byte))
- code = Sword;
+ {
+ DEC_BOTH (from, from_byte);
+ code = Sword;
+ }
else if (SYNTAX_PREFIX (c))
continue;
case Sstring_fence:
while (1)
{
- DEC_BOTH (from, from_byte);
if (from == stop) goto lose;
+ DEC_BOTH (from, from_byte);
UPDATE_SYNTAX_TABLE_BACKWARD (from);
- if (!char_quoted (from, from_byte)
+ if (!char_quoted (from, from_byte)
&& (c = FETCH_CHAR (from_byte),
SYNTAX_WITH_MULTIBYTE_CHECK (c) == code))
break;
}
if (code == Sstring_fence && !depth && sexpflag) goto done2;
break;
-
+
case Sstring:
stringterm = FETCH_CHAR (from_byte);
while (1)
{
if (from == stop) goto lose;
- temp_pos = from_byte;
- if (! NILP (current_buffer->enable_multibyte_characters))
- DEC_POS (temp_pos);
- else
- temp_pos--;
- UPDATE_SYNTAX_TABLE_BACKWARD (from - 1);
- if (!char_quoted (from - 1, temp_pos)
- && stringterm == (c = FETCH_CHAR (temp_pos))
+ DEC_BOTH (from, from_byte);
+ UPDATE_SYNTAX_TABLE_BACKWARD (from);
+ if (!char_quoted (from, from_byte)
+ && stringterm == (c = FETCH_CHAR (from_byte))
&& SYNTAX_WITH_MULTIBYTE_CHECK (c) == Sstring)
break;
- DEC_BOTH (from, from_byte);
}
- DEC_BOTH (from, from_byte);
if (!depth && sexpflag) goto done2;
break;
+ default:
+ /* Ignore whitespace, punctuation, quote, endcomment. */
+ break;
}
}
Fcons (build_string ("Unbalanced parentheses"),
Fcons (make_number (last_good),
Fcons (make_number (from), Qnil))));
-
+ abort ();
/* NOTREACHED */
}
(from, count, depth)
Lisp_Object from, count, depth;
{
- CHECK_NUMBER (from, 0);
- CHECK_NUMBER (count, 1);
- CHECK_NUMBER (depth, 2);
+ CHECK_NUMBER (from);
+ CHECK_NUMBER (count);
+ CHECK_NUMBER (depth);
return scan_lists (XINT (from), XINT (count), XINT (depth), 0);
}
(from, count)
Lisp_Object from, count;
{
- CHECK_NUMBER (from, 0);
- CHECK_NUMBER (count, 1);
+ CHECK_NUMBER (from);
+ CHECK_NUMBER (count);
return scan_lists (XINT (from), XINT (count), 0, 1);
}
int pos_byte = PT_BYTE;
int c;
- if (pos <= beg)
+ if (pos <= beg)
{
SET_PT_BOTH (opoint, opoint_byte);
stopbefore, oldstate, commentstop)
struct lisp_parse_state *stateptr;
register int from;
- int end, targetdepth, stopbefore;
+ int end, targetdepth, stopbefore, from_byte;
Lisp_Object oldstate;
int commentstop;
{
#define INC_FROM \
do { prev_from = from; \
prev_from_byte = from_byte; \
- prev_from_syntax \
- = SYNTAX_WITH_FLAGS (FETCH_CHAR (prev_from_byte)); \
+ temp = FETCH_CHAR (prev_from_byte); \
+ prev_from_syntax = SYNTAX_WITH_FLAGS (temp); \
INC_BOTH (from, from_byte); \
- UPDATE_SYNTAX_TABLE_FORWARD (from); \
+ if (from < end) \
+ UPDATE_SYNTAX_TABLE_FORWARD (from); \
} while (0)
immediate_quit = 1;
oldstate = Fcdr (oldstate);
tem = Fcar (oldstate);
/* Check whether we are inside string_fence-style string: */
- state.instring = (!NILP (tem)
- ? (INTEGERP (tem) ? XINT (tem) : ST_STRING_STYLE)
+ state.instring = (!NILP (tem)
+ ? (INTEGERP (tem) ? XINT (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)
+ state.comstyle = NILP (tem) ? 0 : (EQ (tem, Qsyntax_table)
? ST_COMMENT_STYLE : 1);
oldstate = Fcdr (oldstate);
curlevel->last = -1;
SETUP_SYNTAX_TABLE (prev_from, 1);
- prev_from_syntax = SYNTAX_WITH_FLAGS (FETCH_CHAR (prev_from_byte));
+ temp = FETCH_CHAR (prev_from_byte);
+ prev_from_syntax = SYNTAX_WITH_FLAGS (temp);
UPDATE_SYNTAX_TABLE_FORWARD (from);
/* Enter the loop at a place appropriate for initial state. */
else if (start_quoted)
goto startquoted;
-#if 0 /* This seems to be redundant with the identical code above. */
- SETUP_SYNTAX_TABLE (prev_from, 1);
- prev_from_syntax = SYNTAX_WITH_FLAGS (FETCH_CHAR (prev_from_byte));
- UPDATE_SYNTAX_TABLE_FORWARD (from);
-#endif
-
while (from < end)
{
INC_FROM;
code = prev_from_syntax & 0xff;
- if (code == Scomment)
+ if (from < end
+ && SYNTAX_FLAGS_COMSTART_FIRST (prev_from_syntax)
+ && (c1 = FETCH_CHAR (from_byte),
+ SYNTAX_COMSTART_SECOND (c1)))
+ /* Duplicate code to avoid a complex if-expression
+ which causes trouble for the SGI compiler. */
{
- state.comstyle = SYNTAX_FLAGS_COMMENT_STYLE (prev_from_syntax);
- state.incomment = (SYNTAX_FLAGS_COMMENT_NESTED (prev_from_syntax) ?
- 1 : -1);
+ /* 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);
+ comnested = SYNTAX_FLAGS_COMMENT_NESTED (prev_from_syntax);
+ comnested = comnested || SYNTAX_COMMENT_NESTED (c1);
+ state.incomment = comnested ? 1 : -1;
state.comstr_start = prev_from;
+ INC_FROM;
+ code = Scomment;
}
else if (code == Scomment_fence)
{
state.comstr_start = prev_from;
code = Scomment;
}
- else if (from < end)
- if (SYNTAX_FLAGS_COMSTART_FIRST (prev_from_syntax))
- if (c1 = FETCH_CHAR (from_byte),
- SYNTAX_COMSTART_SECOND (c1))
- /* 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 (FETCH_CHAR (from_byte));
- comnested = SYNTAX_FLAGS_COMMENT_NESTED (prev_from_syntax);
- comnested = comnested || SYNTAX_COMMENT_NESTED (c1);
- state.incomment = comnested ? 1 : -1;
- state.comstr_start = prev_from;
- INC_FROM;
- code = Scomment;
- }
+ else if (code == Scomment)
+ {
+ state.comstyle = SYNTAX_FLAGS_COMMENT_STYLE (prev_from_syntax);
+ state.incomment = (SYNTAX_FLAGS_COMMENT_NESTED (prev_from_syntax) ?
+ 1 : -1);
+ state.comstr_start = prev_from;
+ }
if (SYNTAX_FLAGS_PREFIX (prev_from_syntax))
continue;
while (from < end)
{
/* Some compilers can't handle this inside the switch. */
- temp = SYNTAX (FETCH_CHAR (from_byte));
+ temp = FETCH_CHAR (from_byte);
+ temp = SYNTAX (temp);
switch (temp)
{
case Scharquote:
curlevel->prev = curlevel->last;
break;
+ case Scomment_fence: /* Can't happen because it's handled above. */
case Scomment:
if (commentstop || boundary_stop) goto done;
startincomment:
state.comstr_start = from - 1;
if (stopbefore) goto stop; /* this arg means stop at sexp start */
curlevel->last = prev_from;
- state.instring = (code == Sstring
+ state.instring = (code == Sstring
? (FETCH_CHAR (prev_from_byte))
: ST_STRING_STYLE);
if (boundary_stop) goto done;
startinstring:
{
nofence = state.instring != ST_STRING_STYLE;
-
+
while (1)
{
int c;
break;
case Smath:
+ /* FIXME: We should do something with it. */
+ break;
+ default:
+ /* Ignore whitespace, punctuation, quote, endcomment. */
break;
}
}
point is set to where parsing stops.
If fifth arg OLDSTATE is omitted or nil,
parsing assumes that FROM is the beginning of a function.
-Value is a list of ten elements describing final state of parsing:
+Value is a list of elements describing final state of parsing:
0. depth in parens.
1. character address of start of innermost containing list; nil if none.
2. character address of start of last complete sexp terminated.
3. non-nil if inside a string.
(it is the character that will terminate the string,
or t if the string should be terminated by a generic string delimiter.)
- 4. nil if outside a comment, t if inside a non-nestable comment,
+ 4. nil if outside a comment, t if inside a non-nestable comment,
else an integer (the current comment nesting).
5. t if following a quote character.
6. the minimum paren-depth encountered during this scan.
in parentheses becomes equal to TARGETDEPTH.
Fourth arg STOPBEFORE non-nil means stop when come to
any character that starts a sexp.
-Fifth arg OLDSTATE is a nine-element list like what this function returns.
+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; you can leave off element 8 (the last) entirely.
Sixth arg COMMENTSTOP non-nil means stop at the start of a comment.
if (!NILP (targetdepth))
{
- CHECK_NUMBER (targetdepth, 3);
+ CHECK_NUMBER (targetdepth);
target = XINT (targetdepth);
}
else
scan_sexps_forward (&state, XINT (from), CHAR_TO_BYTE (XINT (from)),
XINT (to),
target, !NILP (stopbefore), oldstate,
- (NILP (commentstop)
+ (NILP (commentstop)
? 0 : (EQ (commentstop, Qsyntax_table) ? -1 : 1)));
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.instring >= 0
- ? (state.instring == ST_STRING_STYLE
+ Fcons (state.instring >= 0
+ ? (state.instring == ST_STRING_STYLE
? Qt : make_number (state.instring)) : Qnil,
Fcons (state.incomment < 0 ? Qt :
(state.incomment == 0 ? Qnil :
make_number (state.incomment)),
Fcons (state.quoted ? Qt : Qnil,
Fcons (make_number (state.mindepth),
- Fcons ((state.comstyle
+ Fcons ((state.comstyle
? (state.comstyle == ST_COMMENT_STYLE
? Qsyntax_table : Qt) :
Qnil),
staticpro (&Vsyntax_code_object);
+ staticpro (&gl_state.object);
+ staticpro (&gl_state.global_code);
+ staticpro (&gl_state.current_syntax_table);
+ staticpro (&gl_state.old_prop);
+
+ /* Defined in regex.c */
+ staticpro (&re_match_object);
+
Qscan_error = intern ("scan-error");
staticpro (&Qscan_error);
Fput (Qscan_error, Qerror_conditions,
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. */);
+ 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;
defsubr (&Ssyntax_table_p);
defsubr (&Smatching_paren);
defsubr (&Sstring_to_syntax);
defsubr (&Smodify_syntax_entry);
- defsubr (&Sdescribe_syntax);
+ defsubr (&Sinternal_describe_syntax_value);
defsubr (&Sforward_word);
defsubr (&Sbackward_prefix_chars);
defsubr (&Sparse_partial_sexp);
}
+
+/* arch-tag: 3e297b9f-088e-4b64-8f4c-fb0b3443e412
+ (do not change this comment) */