diff src/syntax.h @ 826:6728e641994e

[xemacs-hg @ 2002-05-05 11:30:15 by ben] syntax cache, 8-bit-format, lots of code cleanup README.packages: Update info about --package-path. i.c: Create an inheritable event and pass it on to XEmacs, so that ^C can be handled properly. Intercept ^C and signal the event. "Stop Build" in VC++ now works. bytecomp-runtime.el: Doc string changes. compat.el: Some attempts to redo this to make it truly useful and fix the "multiple versions interacting with each other" problem. Not yet done. Currently doesn't work. files.el: Use with-obsolete-variable to avoid warnings in new revert-buffer code. xemacs.mak: Split up CFLAGS into a version without flags specifying the C library. The problem seems to be that minitar depends on zlib, which depends specifically on libc.lib, not on any of the other C libraries. Unless you compile with libc.lib, you get errors -- specifically, no _errno in the other libraries, which must make it something other than an int. (#### But this doesn't seem to obtain in XEmacs, which also uses zlib, and can be linked with any of the C libraries. Maybe zlib is used differently and doesn't need errno, or maybe XEmacs provides an int errno; ... I don't understand. Makefile.in.in: Fix so that packages are around when testing. abbrev.c, alloc.c, buffer.c, buffer.h, bytecode.c, callint.c, casefiddle.c, casetab.c, casetab.h, charset.h, chartab.c, chartab.h, cmds.c, console-msw.h, console-stream.c, console-x.c, console.c, console.h, data.c, device-msw.c, device.c, device.h, dialog-msw.c, dialog-x.c, dired-msw.c, dired.c, doc.c, doprnt.c, dumper.c, editfns.c, elhash.c, emacs.c, eval.c, event-Xt.c, event-gtk.c, event-msw.c, event-stream.c, events.c, events.h, extents.c, extents.h, faces.c, file-coding.c, file-coding.h, fileio.c, fns.c, font-lock.c, frame-gtk.c, frame-msw.c, frame-x.c, frame.c, frame.h, glade.c, glyphs-gtk.c, glyphs-msw.c, glyphs-msw.h, glyphs-x.c, glyphs.c, glyphs.h, gui-msw.c, gui-x.c, gui.h, gutter.h, hash.h, indent.c, insdel.c, intl-win32.c, intl.c, keymap.c, lisp-disunion.h, lisp-union.h, lisp.h, lread.c, lrecord.h, lstream.c, lstream.h, marker.c, menubar-gtk.c, menubar-msw.c, menubar-x.c, menubar.c, minibuf.c, mule-ccl.c, mule-charset.c, mule-coding.c, mule-wnnfns.c, nas.c, objects-msw.c, objects-x.c, opaque.c, postgresql.c, print.c, process-nt.c, process-unix.c, process.c, process.h, profile.c, rangetab.c, redisplay-gtk.c, redisplay-msw.c, redisplay-output.c, redisplay-x.c, redisplay.c, redisplay.h, regex.c, regex.h, scrollbar-msw.c, search.c, select-x.c, specifier.c, specifier.h, symbols.c, symsinit.h, syntax.c, syntax.h, syswindows.h, tests.c, text.c, text.h, tooltalk.c, ui-byhand.c, ui-gtk.c, unicode.c, win32.c, window.c: Another big Ben patch. -- FUNCTIONALITY CHANGES: add partial support for 8-bit-fixed, 16-bit-fixed, and 32-bit-fixed formats. not quite done yet. (in particular, needs functions to actually convert the buffer.) NOTE: lots of changes to regex.c here. also, many new *_fmt() inline funs that take an Internal_Format argument. redo syntax cache code. make the cache per-buffer; keep the cache valid across calls to functions that use it. also keep it valid across insertions/deletions and extent changes, as much as is possible. eliminate the junky regex-reentrancy code by passing in the relevant lisp info to the regex routines as local vars. add general mechanism in extents code for signalling extent changes. fix numerous problems with the case-table implementation; yoshiki never properly transferred many algorithms from old-style to new-style case tables. redo char tables to support a default argument, so that mapping only occurs over changed args. change many chartab functions to accept Lisp_Object instead of Lisp_Char_Table *. comment out the code in font-lock.c by default, because font-lock.el no longer uses it. we should consider eliminating it entirely. Don't output bell as ^G in console-stream when not a TTY. add -mswindows-termination-handle to interface with i.c, so we can properly kill a build. add more error-checking to buffer/string macros. add some additional buffer_or_string_() funs. -- INTERFACE CHANGES AFFECTING MORE CODE: switch the arguments of write_c_string and friends to be consistent with write_fmt_string, which must have printcharfun first. change BI_* macros to BYTE_* for increased clarity; similarly for bi_* local vars. change VOID_TO_LISP to be a one-argument function. eliminate no-longer-needed CVOID_TO_LISP. -- char/string macro changes: rename MAKE_CHAR() to make_emchar() for slightly less confusion with make_char(). (The former generates an Emchar, the latter a Lisp object. Conceivably we should rename make_char() -> wrap_char() and similarly for make_int(), make_float().) Similar changes for other *CHAR* macros -- we now consistently use names with `emchar' whenever we are working with Emchars. Any remaining name with just `char' always refers to a Lisp object. rename macros with XSTRING_* to string_* except for those that reference actual fields in the Lisp_String object, following conventions used elsewhere. rename set_string_{data,length} macros (the only ones to work with a Lisp_String_* instead of a Lisp_Object) to set_lispstringp_* to make the difference clear. try to be consistent about caps vs. lowercase in macro/inline-fun names for chars and such, which wasn't the case before. we now reserve caps either for XFOO_ macros that reference object fields (e.g. XSTRING_DATA) or for things that have non-function semantics, e.g. directly modifying an arg (BREAKUP_EMCHAR) or evaluating an arg (any arg) more than once. otherwise, use lowercase. here is a summary of most of the macros/inline funs changed by all of the above changes: BYTE_*_P -> byte_*_p XSTRING_BYTE -> string_byte set_string_data/length -> set_lispstringp_data/length XSTRING_CHAR_LENGTH -> string_char_length XSTRING_CHAR -> string_emchar INTBYTE_FIRST_BYTE_P -> intbyte_first_byte_p INTBYTE_LEADING_BYTE_P -> intbyte_leading_byte_p charptr_copy_char -> charptr_copy_emchar LEADING_BYTE_* -> leading_byte_* CHAR_* -> EMCHAR_* *_CHAR_* -> *_EMCHAR_* *_CHAR -> *_EMCHAR CHARSET_BY_ -> charset_by_* BYTE_SHIFT_JIS* -> byte_shift_jis* BYTE_BIG5* -> byte_big5* REP_BYTES_BY_FIRST_BYTE -> rep_bytes_by_first_byte char_to_unicode -> emchar_to_unicode valid_char_p -> valid_emchar_p Change intbyte_strcmp -> qxestrcmp_c (duplicated functionality). -- INTERFACE CHANGES AFFECTING LESS CODE: use DECLARE_INLINE_HEADER in various places. remove '#ifdef emacs' from XEmacs-only files. eliminate CHAR_TABLE_VALUE(), which duplicated the functionality of get_char_table(). add BUFFER_TEXT_LOOP to simplify iterations over buffer text. define typedefs for signed and unsigned types of fixed sizes (INT_32_BIT, UINT_32_BIT, etc.). create ALIGN_FOR_TYPE as a higher-level interface onto ALIGN_SIZE; fix code to use it. add charptr_emchar_len to return the text length of the character pointed to by a ptr; use it in place of charcount_to_bytecount(..., 1). add emchar_len to return the text length of a given character. add types Bytexpos and Charxpos to generalize Bytebpos/Bytecount and Charbpos/Charcount, in code (particularly, the extents code and redisplay code) that works with either kind of index. rename redisplay struct params with names such as `charbpos' to e.g. `charpos' when they are e.g. a Charxpos, not a Charbpos. eliminate xxDEFUN in place of DEFUN; no longer necessary with changes awhile back to doc.c. split up big ugly combined list of EXFUNs in lisp.h on a file-by-file basis, since other prototypes are similarly split. rewrite some "*_UNSAFE" macros as inline funs and eliminate the _UNSAFE suffix. move most string code from lisp.h to text.h; the string code and text.h code is now intertwined in such a fashion that they need to be in the same place and partially interleaved. (you can't create forward references for inline funs) automated/lisp-tests.el, automated/symbol-tests.el, automated/test-harness.el: Fix test harness to output FAIL messages to stderr when in batch mode. Fix up some problems in lisp-tests/symbol-tests that were causing spurious failures.
author ben
date Sun, 05 May 2002 11:33:57 +0000
parents e38acbeb1cae
children 804517e16990
line wrap: on
line diff
--- a/src/syntax.h	Thu May 02 14:35:32 2002 +0000
+++ b/src/syntax.h	Sun May 05 11:33:57 2002 +0000
@@ -74,25 +74,16 @@
 
 /* Return the syntax code for a particular character and mirror table. */
 
-#define SYNTAX_CODE_UNSAFE(table, c) \
-   XINT (CHAR_TABLE_VALUE_UNSAFE (table, c))
-
-INLINE_HEADER int SYNTAX_CODE (Lisp_Char_Table *table, Emchar c);
-INLINE_HEADER int
-SYNTAX_CODE (Lisp_Char_Table *table, Emchar c)
-{
-  return SYNTAX_CODE_UNSAFE (table, c);
-}
-
-#define SYNTAX_UNSAFE(table, c) \
-  ((enum syntaxcode) (SYNTAX_CODE_UNSAFE (table, c) & 0177))
+#define SYNTAX_CODE(table, c) XINT (get_char_table (c, table))
 
 #define SYNTAX_FROM_CODE(code) ((enum syntaxcode) ((code) & 0177))
+
 #define SYNTAX(table, c) SYNTAX_FROM_CODE (SYNTAX_CODE (table, c))
 
-INLINE_HEADER int WORD_SYNTAX_P (Lisp_Char_Table *table, Emchar c);
-INLINE_HEADER int
-WORD_SYNTAX_P (Lisp_Char_Table *table, Emchar c)
+DECLARE_INLINE_HEADER (
+int
+WORD_SYNTAX_P (Lisp_Object table, Emchar c)
+)
 {
   return SYNTAX (table, c) == Sword;
 }
@@ -136,8 +127,6 @@
 
 /* The prefix flag bit for backward-prefix-chars is now put into bit 7. */
 
-#define SYNTAX_PREFIX_UNSAFE(table, c) \
-  ((SYNTAX_CODE_UNSAFE (table, c) >> 7) & 1)
 #define SYNTAX_PREFIX(table, c) \
   ((SYNTAX_CODE (table, c) >> 7) & 1)
 
@@ -175,6 +164,9 @@
 #define SYNTAX_SECOND_CHAR_END   0x03
 #define SYNTAX_SECOND_CHAR       0x33
 
+#if 0
+
+/* #### Entirely unused.  Should they be deleted? */
 
 /* #### These are now more or less equivalent to
    SYNTAX_COMMENT_MATCH_START ...*/
@@ -232,12 +224,7 @@
       ? SYNTAX_COMMENT_STYLE_B					\
 	 : 0)))
 
-EXFUN (Fchar_syntax, 2);
-EXFUN (Fforward_word, 2);
-
-/* The standard syntax table is stored where it will automatically
-   be used in all new buffers.  */
-extern Lisp_Object Vstandard_syntax_table;
+#endif /* 0 */
 
 /* This array, indexed by a character, contains the syntax code which
    that character signifies (as a char).
@@ -258,161 +245,113 @@
 Lisp_Object syntax_match (Lisp_Object table, Emchar ch);
 
 extern int no_quit_in_re_search;
-extern struct buffer *regex_emacs_buffer;
+
+void update_syntax_table (Lisp_Object table);
 
-/* This is the string or buffer in which we are matching.  It is used
-   for looking up syntax properties.  */
-extern Lisp_Object regex_match_object;
-
-void update_syntax_table (Lisp_Char_Table *ct);
-
-#ifdef emacs
+
+/****************************** syntax caches ********************************/
 
 extern int lookup_syntax_properties;
 
+/* Now that the `syntax-table' property exists, and can override the syntax
+   table or directly specify the syntax, we cache the last place we
+   retrieved the syntax-table property.  This is because, when moving
+   linearly through text (e.g. in the regex routines or the scanning
+   routines in syntax.c), we only need to recalculate at the next place the
+   syntax-table property changes (i.e. not every position), and when we do
+   need to recalculate, we can update the info from the previous info
+   faster than if we did the whole calculation from scratch. */
 struct syntax_cache
 {
-  int use_code;				/* Whether to use syntax_code
-					   or current_syntax_table. */
-  struct buffer* buffer;		/* The buffer the current syntax cache
-					   applies to. */
+  int use_code;				/* Whether to use syntax_code or
+					   current_syntax_table.  This is
+					   set depending on whether the
+					   syntax-table property is a
+					   syntax table or a syntax
+					   code. */
+  int no_syntax_table_prop;		/* If non-zero, there was no
+					   `syntax-table' property on the
+					   current range, and so we're
+					   using the buffer's syntax table.
+					   This is important to note because
+					   sometimes the buffer's syntax
+					   table can be changed. */
   Lisp_Object object;			/* The buffer or string the current
-					   syntax cache applies to. */
+					   syntax cache applies to, or
+					   Qnil for a string of text not
+					   coming from a buffer or string. */
+  struct buffer *buffer;		/* The buffer that supplies the
+					   syntax tables, or 0 for the
+					   standard syntax table.  If
+					   OBJECT is a buffer, this will
+					   always be the same buffer. */
   int syntax_code;			/* Syntax code of current char. */
   Lisp_Object current_syntax_table;	/* Syntax table for current pos. */
-  Lisp_Object old_prop;			/* Syntax-table prop at prev pos. */
-
-  Charbpos next_change;			/* Position of the next extent
+  Lisp_Object start, end;		/* Markers to keep track of the
+					   known region in a buffer.
+					   Formerly we used an internal
+					   extent, but it seems that having
+					   an extent over the entire buffer
+					   causes serious slowdowns in
+					   extent operations!  Yuck! */
+  Charxpos next_change;			/* Position of the next extent
                                            change. */
-  Charbpos prev_change;			/* Position of the previous
-                                           extent change. */
+  Charxpos prev_change;			/* Position of the previous extent
+					   change. */
 };
-extern struct syntax_cache syntax_cache;
+
+/* Note that the external interface to the syntax-cache uses charpos's, but
+   intnernally we use bytepos's, for speed. */
 
-void update_syntax_cache (int pos, int count, int init);
+void update_syntax_cache (struct syntax_cache *cache, Charxpos pos, int count);
+struct syntax_cache *setup_syntax_cache (struct syntax_cache *cache,
+					 Lisp_Object object,
+					 struct buffer *buffer,
+					 Charxpos from, int count);
+struct syntax_cache *setup_buffer_syntax_cache (struct buffer *buffer,
+						Charxpos from, int count);
 
 /* Make syntax cache state good for CHARPOS, assuming it is
    currently good for a position before CHARPOS.  */
-#define UPDATE_SYNTAX_CACHE_FORWARD(pos)	\
-   (lookup_syntax_properties			\
-    ? (update_syntax_cache ((pos), 1, 0), 1)	\
-    : 0)
+DECLARE_INLINE_HEADER (
+void
+UPDATE_SYNTAX_CACHE_FORWARD (struct syntax_cache *cache, Charxpos pos)
+)
+{
+  if (!(pos >= cache->prev_change && pos < cache->next_change))
+    update_syntax_cache (cache, pos, 1);
+}
 
 /* Make syntax cache state good for CHARPOS, assuming it is
    currently good for a position after CHARPOS.  */
-#define UPDATE_SYNTAX_CACHE_BACKWARD(pos)	\
-   (lookup_syntax_properties			\
-    ? (update_syntax_cache ((pos), -1, 0), 1)	\
-    : 0)
+DECLARE_INLINE_HEADER (
+void
+UPDATE_SYNTAX_CACHE_BACKWARD (struct syntax_cache *cache, Charxpos pos)
+)
+{
+  if (!(pos >= cache->prev_change && pos < cache->next_change))
+    update_syntax_cache (cache, pos, -1);
+}
 
 /* Make syntax cache state good for CHARPOS */
-#define UPDATE_SYNTAX_CACHE(pos)		\
-   (lookup_syntax_properties			\
-    ? (update_syntax_cache ((pos), 0, 0), 1)	\
-    : 0)
-
-#define SYNTAX_FROM_CACHE(table, c)			\
-   SYNTAX_FROM_CODE (SYNTAX_CODE_FROM_CACHE (table, c))
-
-#define SYNTAX_CODE_FROM_CACHE(table, c)				\
-  ( syntax_cache.use_code						\
-      ? syntax_cache.syntax_code					\
-      : SYNTAX_CODE (XCHAR_TABLE (syntax_cache.current_syntax_table),	\
-		     c)							\
- )
-
-/* Convert the byte offset BYTEPOS into a character position,
-   for the object recorded in syntax_cache with SETUP_SYNTAX_TABLE_FOR_OBJECT.
-
-   The value is meant for use in the UPDATE_SYNTAX_TABLE... macros.
-   These macros do nothing when parse_sexp_lookup_properties is 0,
-   so we return 0 in that case, for speed.  */
-#define SYNTAX_CACHE_BYTE_TO_CHAR(bytepos)				\
-  (! lookup_syntax_properties						\
-   ? 0									\
-   : STRINGP (syntax_cache.object)					\
-   ? string_index_byte_to_char (syntax_cache.object, bytepos)		\
-   : (BUFFERP (syntax_cache.object) || NILP (syntax_cache.object))	\
-   ? bytebpos_to_charbpos (syntax_cache.buffer,				\
-		       bytepos + BI_BUF_BEGV (syntax_cache.buffer))	\
-   : (bytepos))
-
-#define SYNTAX_CACHE_OBJECT_BYTE_TO_CHAR(obj, buf, bytepos)	\
-  (! lookup_syntax_properties					\
-   ? 0								\
-   : STRINGP (obj)						\
-   ? string_index_byte_to_char (obj, bytepos)			\
-   : (BUFFERP (obj) || NILP (obj))				\
-   ? bytebpos_to_charbpos (buf, bytepos + BI_BUF_BEGV (buf))	\
-   : (bytepos))
-
-#else  /* not emacs */
-
-#define update_syntax_cache(pos, count, init)
-#define UPDATE_SYNTAX_CACHE_FORWARD(pos)
-#define UPDATE_SYNTAX_CACHE_BACKWARD(pos)
-#define UPDATE_SYNTAX_CACHE(pos)
-#define SYNTAX_FROM_CACHE SYNTAX
-#define SYNTAX_CODE_FROM_CACHE SYNTAX_CODE
-
-#endif /* emacs */
+DECLARE_INLINE_HEADER (
+void
+UPDATE_SYNTAX_CACHE (struct syntax_cache *cache, Charxpos pos)
+)
+{
+  if (!(pos >= cache->prev_change && pos < cache->next_change))
+    update_syntax_cache (cache, pos, 0);
+}
 
-#define SETUP_SYNTAX_CACHE(FROM, COUNT)				\
-  do {								\
-    syntax_cache.buffer = current_buffer;			\
-    syntax_cache.object = Qnil;					\
-    syntax_cache.current_syntax_table				\
-      = current_buffer->mirror_syntax_table;			\
-    syntax_cache.use_code = 0;					\
-    if (lookup_syntax_properties)				\
-      update_syntax_cache ((COUNT) > 0 ? (FROM) : (FROM) - 1,	\
-			   (COUNT), 1);				\
-  } while (0)
-
-#define SETUP_SYNTAX_CACHE_FOR_BUFFER(BUFFER, FROM, COUNT)	\
-  do {								\
-    syntax_cache.buffer = (BUFFER);				\
-    syntax_cache.object = Qnil;					\
-    syntax_cache.current_syntax_table =				\
-      syntax_cache.buffer->mirror_syntax_table;			\
-    syntax_cache.use_code = 0;					\
-    if (lookup_syntax_properties)				\
-      update_syntax_cache ((FROM) + ((COUNT) > 0 ? 0 : -1),	\
-			   (COUNT), 1);				\
-  } while (0)
+#define SYNTAX_FROM_CACHE(cache, c)			\
+   SYNTAX_FROM_CODE (SYNTAX_CODE_FROM_CACHE (cache, c))
 
-#define SETUP_SYNTAX_CACHE_FOR_OBJECT(OBJECT, BUFFER, FROM, COUNT)	\
-  do {									\
-    syntax_cache.buffer = (BUFFER);					\
-    syntax_cache.object = (OBJECT);					\
-    if (NILP (syntax_cache.object))					\
-      {									\
-        /* do nothing */;						\
-      }									\
-    else if (EQ (syntax_cache.object, Qt))				\
-      {									\
-        /* do nothing */;						\
-      }									\
-    else if (STRINGP (syntax_cache.object))				\
-      {									\
-        /* do nothing */;						\
-      }									\
-    else if (BUFFERP (syntax_cache.object))				\
-      {									\
-        syntax_cache.buffer = XBUFFER (syntax_cache.object);		\
-      }									\
-    else								\
-      {									\
-        /* OBJECT must be buffer/string/t/nil */			\
-        assert(0);							\
-      }									\
-    syntax_cache.current_syntax_table					\
-      = syntax_cache.buffer->mirror_syntax_table;			\
-    syntax_cache.use_code = 0;						\
-    if (lookup_syntax_properties)					\
-      update_syntax_cache ((FROM) + ((COUNT) > 0 ? 0 : -1),		\
-			   (COUNT), 1);					\
-  } while (0)
+#define SYNTAX_CODE_FROM_CACHE(cache, c)				\
+  ((cache)->use_code ? (cache)->syntax_code				\
+   : SYNTAX_CODE ((cache)->current_syntax_table, c))
+
+
+/***************************** syntax code macros ****************************/
 
 #define SYNTAX_CODE_PREFIX(c) \
   ((c >> 7) & 1)