view src/dynarr.c @ 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 b531bf8658e9
line wrap: on
line source

/* Simple 'n' stupid dynamic-array module.
   Copyright (C) 1993 Sun Microsystems, Inc.
   Copyright (C) 2002 Ben Wing.

This file is part of XEmacs.

XEmacs is free software; you can redistribute it and/or modify it
under the terms of the GNU General Public License as published by the
Free Software Foundation; either version 2, or (at your option) any
later version.

XEmacs is distributed in the hope that it will be useful, but WITHOUT
ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License
for more details.

You should have received a copy of the GNU General Public License
along with XEmacs; see the file COPYING.  If not, write to
the Free Software Foundation, Inc., 59 Temple Place - Suite 330,
Boston, MA 02111-1307, USA.  */

/* Synched up with:  Not in FSF. */

/* Written by Ben Wing, December 1993. */

/*

A "dynamic array" is a contiguous array of fixed-size elements where there
is no upper limit (except available memory) on the number of elements in the
array.  Because the elements are maintained contiguously, space is used
efficiently (no per-element pointers necessary) and random access to a
particular element is in constant time.  At any one point, the block of memory
that holds the array has an upper limit; if this limit is exceeded, the
memory is realloc()ed into a new array that is twice as big.  Assuming that
the time to grow the array is on the order of the new size of the array
block, this scheme has a provably constant amortized time (i.e. average
time over all additions).

When you add elements or retrieve elements, pointers are used.  Note that
the element itself (of whatever size it is), and not the pointer to it,
is stored in the array; thus you do not have to allocate any heap memory
on your own.  Also, returned pointers are only guaranteed to be valid
until the next operation that changes the length of the array.

This is a container object.  Declare a dynamic array of a specific type
as follows:

typedef struct
{
  Dynarr_declare (mytype);
} mytype_dynarr;

Use the following functions/macros:

   void *Dynarr_new(type)
      [MACRO] Create a new dynamic-array object, with each element of the
      specified type.  The return value is cast to (type##_dynarr).
      This requires following the convention that types are declared in
      such a way that this type concatenation works.  In particular, TYPE
      must be a symbol, not an arbitrary C type.

   Dynarr_add(d, el)
      [MACRO] Add an element to the end of a dynamic array.  EL is a pointer
      to the element; the element itself is stored in the array, however.
      No function call is performed unless the array needs to be resized.

   Dynarr_add_many(d, base, len)
      [MACRO] Add LEN elements to the end of the dynamic array.  The elements
      should be contiguous in memory, starting at BASE.  If BASE if NULL,
      just make space for the elements; don't actually add them.

   Dynarr_insert_many_at_start(d, base, len)
      [MACRO] Append LEN elements to the beginning of the dynamic array.
      The elements should be contiguous in memory, starting at BASE.
      If BASE if NULL, just make space for the elements; don't actually
      add them.

   Dynarr_insert_many(d, base, len, start)
      Insert LEN elements to the dynamic array starting at position
      START.  The elements should be contiguous in memory, starting at BASE.
      If BASE if NULL, just make space for the elements; don't actually
      add them.

   Dynarr_delete(d, i)
      [MACRO] Delete an element from the dynamic array at position I.

   Dynarr_delete_many(d, start, len)
      Delete LEN elements from the dynamic array starting at position
      START.

   Dynarr_delete_by_pointer(d, p)
      [MACRO] Delete an element from the dynamic array at pointer P,
      which must point within the block of memory that stores the data.
      P should be obtained using Dynarr_atp().

   int Dynarr_length(d)
      [MACRO] Return the number of elements currently in a dynamic array.

   int Dynarr_largest(d)
      [MACRO] Return the maximum value that Dynarr_length(d) would
      ever have returned.

   type Dynarr_at(d, i)
      [MACRO] Return the element at the specified index (no bounds checking
      done on the index).  The element itself is returned, not a pointer
      to it.

   type *Dynarr_atp(d, i)
      [MACRO] Return a pointer to the element at the specified index (no
      bounds checking done on the index).  The pointer may not be valid
      after an element is added to or removed from the array.

   Dynarr_reset(d)
      [MACRO] Reset the length of a dynamic array to 0.

   Dynarr_free(d)
      Destroy a dynamic array and the memory allocated to it.

Use the following global variable:

   Dynarr_min_size
      Minimum allowable size for a dynamic array when it is resized.

*/

#include <config.h>
#include "lisp.h"

static int Dynarr_min_size = 8;

static void
Dynarr_realloc (Dynarr *dy, int new_size)
{
  if (DUMPEDP (dy->base))
    {
      void *new_base = malloc (new_size);
      memcpy (new_base, dy->base, dy->max > new_size ? dy->max : new_size);
      dy->base = new_base;
    }
  else
    dy->base = xrealloc (dy->base, new_size);
}

void *
Dynarr_newf (int elsize)
{
  Dynarr *d = xnew_and_zero (Dynarr);
  d->elsize = elsize;

  return d;
}

void
Dynarr_resize (void *d, int size)
{
  int newsize;
  double multiplier;
  Dynarr *dy = (Dynarr *) d;

  if (dy->max <= 8)
    multiplier = 2;
  else
    multiplier = 1.5;

  for (newsize = dy->max; newsize < size;)
    newsize = max (Dynarr_min_size, (int) (multiplier * newsize));

  /* Don't do anything if the array is already big enough. */
  if (newsize > dy->max)
    {
      Dynarr_realloc (dy, newsize*dy->elsize);
      dy->max = newsize;
    }
}

/* Add a number of contiguous elements to the array starting at START. */
void
Dynarr_insert_many (void *d, const void *el, int len, int start)
{
  Dynarr *dy = (Dynarr *) Dynarr_verify (d);
  
  Dynarr_resize (dy, dy->cur+len);
  /* Silently adjust start to be valid. */
  if (start > dy->cur)
    start = dy->cur;
  else if (start < 0)
    start = 0;

  if (start != dy->cur)
    {
      memmove ((char *) dy->base + (start + len)*dy->elsize,
	       (char *) dy->base + start*dy->elsize,
	       (dy->cur - start)*dy->elsize);
    }
  if (el)
    memcpy ((char *) dy->base + start*dy->elsize, el, len*dy->elsize);
  dy->cur += len;

  if (dy->cur > dy->largest)
    dy->largest = dy->cur;
}

void
Dynarr_delete_many (void *d, int start, int len)
{
  Dynarr *dy = (Dynarr *) d;

  assert (start >= 0 && len >= 0 && start + len <= dy->cur);
  memmove ((char *) dy->base + start*dy->elsize,
	   (char *) dy->base + (start + len)*dy->elsize,
	   (dy->cur - start - len)*dy->elsize);
  dy->cur -= len;
}

void
Dynarr_free (void *d)
{
  Dynarr *dy = (Dynarr *) d;

  if (dy->base && !DUMPEDP (dy->base))
    xfree (dy->base);
  if(!DUMPEDP (dy))
    xfree (dy);
}

#ifdef MEMORY_USAGE_STATS

/* Return memory usage for Dynarr D.  The returned value is the total
   amount of bytes actually being used for the Dynarr, including all
   overhead.  The extra amount of space in the Dynarr that is
   allocated beyond what was requested is returned in DYNARR_OVERHEAD
   in STATS.  The extra amount of space that malloc() allocates beyond
   what was requested of it is returned in MALLOC_OVERHEAD in STATS.
   See the comment above the definition of this structure. */

Bytecount
Dynarr_memory_usage (void *d, struct overhead_stats *stats)
{
  Bytecount total = 0;
  Dynarr *dy = (Dynarr *) d;

  /* We have to be a bit tricky here because not all of the
     memory that malloc() will claim as "requested" was actually
     requested. */

  if (dy->base)
    {
      Bytecount malloc_used = malloced_storage_size (dy->base,
						  dy->elsize * dy->max, 0);
      /* #### This may or may not be correct.  Some Dynarrs would
	 prefer that we use dy->cur instead of dy->largest here. */
      int was_requested = dy->elsize * dy->largest;
      int dynarr_overhead = dy->elsize * (dy->max - dy->largest);

      total += malloc_used;
      stats->was_requested += was_requested;
      stats->dynarr_overhead += dynarr_overhead;
      /* And the remainder must be malloc overhead. */
      stats->malloc_overhead +=
	malloc_used - was_requested - dynarr_overhead;
    }

  total += malloced_storage_size (d, sizeof (*dy), stats);

  return total;
}

#endif /* MEMORY_USAGE_STATS */