comparison src/regex.c @ 2367:ecf1ebac70d8

[xemacs-hg @ 2004-11-04 23:05:23 by ben] commit mega-patch configure.in: Turn off -Winline and -Wchar-subscripts. Use the right set of cflags when compiling modules. Rewrite ldap configuration to separate the inclusion of lber (needed in recent Cygwin) from the basic checks for the needed libraries. add a function for MAKE_JUNK_C; initially code was added to generate xemacs.def using this, but it will need to be rewritten. add an rm -f for junk.c to avoid weird Cygwin bug with cp -f onto an existing file. Sort list of auto-detected functions and eliminate unused checks for stpcpy, setlocale and getwd. Add autodetection of Cygwin scanf problems BETA: Rewrite section on configure to indicate what flags are important and what not. digest-doc.c, make-dump-id.c, profile.c, sorted-doc.c: Add proper decls for main(). make-msgfile.c: Document that this is old junk. Move proposal to text.c. make-msgfile.lex: Move proposal to text.c. make-mswin-unicode.pl: Convert error-generating code so that the entire message will be seen as a single unrecognized token. mule/mule-ccl.el: Update docs. lispref/mule.texi: Update CCL docs. ldap/eldap.c: Mule-ize. Use EXTERNAL_LIST_LOOP_2 instead of deleted EXTERNAL_LIST_LOOP. * XEmacs 21.5.18 "chestnut" is released. --------------------------------------------------------------- MULE-RELATED WORK: --------------------------------------------------------------- --------------------------- byte-char conversion --------------------------- buffer.c, buffer.h, insdel.c, text.c: Port FSF algorithm for byte-char conversion, replacing broken previous version. Track the char position of the gap. Add functions to do char-byte conversion downwards as well as upwards. Move comments about algorithm workings to internals manual. --------------------------- work on types --------------------------- alloc.c, console-x-impl.h, dump-data.c, dump-data.h, dumper.c, dialog-msw.c, dired-msw.c, doc.c, editfns.c, esd.c, event-gtk.h, event-msw.c, events.c, file-coding.c, file-coding.h, fns.c, glyphs-eimage.c, glyphs-gtk.c, glyphs-msw.c, glyphs-shared.c, glyphs-x.c, glyphs.c, glyphs.h, gui.c, hpplay.c, imgproc.c, intl-win32.c, lrecord.h, lstream.c, keymap.c, lisp.h, libsst.c, linuxplay.c, miscplay.c, miscplay.h, mule-coding.c, nas.c, nt.c, ntheap.c, ntplay.c, objects-msw.c, objects-tty.c, objects-x.c, print.c, process-nt.c, process.c, redisplay.h, select-common.h, select-gtk.c, select-x.c, sgiplay.c, sound.c, sound.h, sunplay.c, sysfile.h, sysdep.c, syswindows.h, text.c, unexnt.c, win32.c, xgccache.c: Further work on types. This creates a full set of types for all the basic semantics of `char' that I have so far identified, so that its semantics can always be identified for the purposes of proper Mule-safe code, and the raw use of `char' always avoided. (1) More type renaming, for consistency of naming. Char_ASCII -> Ascbyte UChar_ASCII -> UAscbyte Char_Binary -> CBinbyte UChar_Binary -> Binbyte SChar_Binary -> SBinbyte (2) Introduce Rawbyte, CRawbyte, Boolbyte, Chbyte, UChbyte, and Bitbyte and use them. (3) New types Itext, Wexttext and Textcount for separating out the concepts of bytes and textual units (different under UTF-16 and UTF-32, which are potential internal encodings). (4) qxestr*_c -> qxestr*_ascii. lisp.h: New; goes with other qxe() functions. #### Maybe goes in a different section. lisp.h: Group generic int-type defs together with EMACS_INT defs. lisp.h: * lisp.h (WEXTTEXT_IS_WIDE) New defns. lisp.h: New type to replace places where int occurs as a boolean. It's signed because occasionally people may want to use -1 as an error value, and because unsigned ints are viral -- see comments in the internals manual against using them. dynarr.c: int -> Bytecount. --------------------------- Mule-izing --------------------------- device-x.c: Partially Mule-ize. dumper.c, dumper.h: Mule-ize. Use Rawbyte. Use stderr_out not printf. Use wext_*(). sysdep.c, syswindows.h, text.c: New Wexttext API for manipulation of external text that may be Unicode (e.g. startup code under Windows). emacs.c: Mule-ize. Properly deal with argv in external encoding. Use wext_*() and Wexttext. Use Rawbyte. #if 0 some old junk on SCO that is unlikely to be correct. Rewrite allocation code in run-temacs. emacs.c, symsinit.h, win32.c: Rename win32 init function and call it even earlier, to initialize mswindows_9x_p even earlier, for use in startup code (XEUNICODE_P). process.c: Use _wenviron not environ under Windows, to get Unicode environment variables. event-Xt.c: Mule-ize drag-n-drop related stuff. dragdrop.c, dragdrop.h, frame-x.c: Mule-ize. text.h: Add some more stand-in defines for particular kinds of conversion; use in Mule-ization work in frame-x.c etc. --------------------------- Freshening --------------------------- intl-auto-encap-win32.c, intl-auto-encap-win32.h: Regenerate. --------------------------- Unicode-work --------------------------- intl-win32.c, syswindows.h: Factor out common options to MultiByteToWideChar and WideCharToMultiByte. Add convert_unicode_to_multibyte_malloc() and convert_unicode_to_multibyte_dynarr() and use. Add stuff for alloca() conversion of multibyte/unicode. alloc.c: Use dfc_external_data_len() in case of unicode coding system. alloc.c, mule-charset.c: Don't zero out and reinit charset Unicode tables. This fucks up dump-time loading. Anyway, either we load them at dump time or run time, never both. unicode.c: Dump the blank tables as well. --------------------------------------------------------------- DOCUMENTATION, MOSTLY MULE-RELATED: --------------------------------------------------------------- EmacsFrame.c, emodules.c, event-Xt.c, fileio.c, input-method-xlib.c, mule-wnnfns.c, redisplay-gtk.c, redisplay-tty.c, redisplay-x.c, regex.c, sysdep.c: Add comment about Mule work needed. text.h: Add more documentation describing why DFC routines were not written to return their value. Add some other DFC documentation. console-msw.c, console-msw.h: Add pointer to docs in win32.c. emacs.c: Add comments on sources of doc info. text.c, charset.h, unicode.c, intl-win32.c, intl-encap-win32.c, text.h, file-coding.c, mule-coding.c: Collect background comments and related to text matters and internationalization, and proposals for work to be done, in text.c or Internals manual, stuff related to specific textual API's in text.h, and stuff related to internal implementation of Unicode conversion in unicode.c. Put lots of pointers to the comments to make them easier to find. s/mingw32.h, s/win32-common.h, s/win32-native.h, s/windowsnt.h, win32.c: Add bunches of new documentation on the different kinds of builds and environments under Windows and how they work. Collect this info in win32.c. Add pointers to these docs in the relevant s/* files. emacs.c: Document places with long comments. Remove comment about exiting, move to internals manual, put in pointer. event-stream.c: Move docs about event queues and focus to internals manual, put in pointer. events.h: Move docs about event stream callbacks to internals manual, put in pointer. profile.c, redisplay.c, signal.c: Move documentation to the Internals manual. process-nt.c: Add pointer to comment in win32-native.el. lisp.h: Add comments about some comment conventions. lisp.h: Add comment about the second argument. device-msw.c, redisplay-msw.c: @@#### comments are out-of-date. --------------------------------------------------------------- PDUMP WORK (MOTIVATED BY UNICODE CHANGES) --------------------------------------------------------------- alloc.c, buffer.c, bytecode.c, console-impl.h, console.c, device.c, dumper.c, lrecord.h, elhash.c, emodules.h, events.c, extents.c, frame.c, glyphs.c, glyphs.h, mule-charset.c, mule-coding.c, objects.c, profile.c, rangetab.c, redisplay.c, specifier.c, specifier.h, window.c, lstream.c, file-coding.h, file-coding.c: PDUMP: Properly implement dump_add_root_block(), which never worked before, and is necessary for dumping Unicode tables. Pdump name changes for accuracy: XD_STRUCT_PTR -> XD_BLOCK_PTR. XD_STRUCT_ARRAY -> XD_BLOCK_ARRAY. XD_C_STRING -> XD_ASCII_STRING. *_structure_* -> *_block_*. lrecord.h: some comments added about dump_add_root_block() vs dump_add_root_block_ptr(). extents.c: remove incorrect comment about pdump problems with gap array. --------------------------------------------------------------- ALLOCATION --------------------------------------------------------------- abbrev.c, alloc.c, bytecode.c, casefiddle.c, device-msw.c, device-x.c, dired-msw.c, doc.c, doprnt.c, dragdrop.c, editfns.c, emodules.c, file-coding.c, fileio.c, filelock.c, fns.c, glyphs-eimage.c, glyphs-gtk.c, glyphs-msw.c, glyphs-x.c, gui-msw.c, gui-x.c, imgproc.c, intl-win32.c, lread.c, menubar-gtk.c, menubar.c, nt.c, objects-msw.c, objects-x.c, print.c, process-nt.c, process-unix.c, process.c, realpath.c, redisplay.c, search.c, select-common.c, symbols.c, sysdep.c, syswindows.h, text.c, text.h, ui-byhand.c: New macros {alloca,xnew}_{itext,{i,ext,raw,bin,asc}bytes} for more convenient allocation of these commonly requested items. Modify functions to use alloca_ibytes, alloca_array, alloca_extbytes, xnew_ibytes, etc. also XREALLOC_ARRAY, xnew. alloc.c: Rewrite the allocation functions to factor out repeated code. Add assertions for freeing dumped data. lisp.h: Moved down and consolidated with other allocation stuff. lisp.h, dynarr.c: New functions for allocation that's very efficient when mostly in LIFO order. lisp.h, text.c, text.h: Factor out some stuff for general use by alloca()-conversion funs. text.h, lisp.h: Fill out convenience routines for allocating various kinds of bytes and put them in lisp.h. Use them in place of xmalloc(), ALLOCA(). text.h: Fill out the convenience functions so the _MALLOC() kinds match the alloca() kinds. --------------------------------------------------------------- ERROR-CHECKING --------------------------------------------------------------- text.h: Create ASSERT_ASCTEXT_ASCII() and ASSERT_ASCTEXT_ASCII_LEN() from similar Eistring checkers and change the Eistring checkers to use them instead. --------------------------------------------------------------- MACROS IN LISP.H --------------------------------------------------------------- lisp.h: Redo GCPRO declarations. Create a "base" set of functions that can be used to generate any kind of gcpro sets -- regular, ngcpro, nngcpro, private ones used in GC_EXTERNAL_LIST_LOOP_2. buffer.c, callint.c, chartab.c, console-msw.c, device-x.c, dialog-msw.c, dired.c, extents.c, ui-gtk.c, rangetab.c, nt.c, mule-coding.c, minibuf.c, menubar-msw.c, menubar.c, menubar-gtk.c, lread.c, lisp.h, gutter.c, glyphs.c, glyphs-widget.c, fns.c, fileio.c, file-coding.c, specifier.c: Eliminate EXTERNAL_LIST_LOOP, which does not check for circularities. Use EXTERNAL_LIST_LOOP_2 instead or EXTERNAL_LIST_LOOP_3 or EXTERNAL_PROPERTY_LIST_LOOP_3 or GC_EXTERNAL_LIST_LOOP_2 (new macro). Removed/redid comments on EXTERNAL_LIST_LOOP. --------------------------------------------------------------- SPACING FIXES --------------------------------------------------------------- callint.c, hftctl.c, number-gmp.c, process-unix.c: Spacing fixes. --------------------------------------------------------------- FIX FOR GEOMETRY PROBLEM IN FIRST FRAME --------------------------------------------------------------- unicode.c: Add workaround for newlib bug in sscanf() [should be fixed by release 1.5.12 of Cygwin]. toolbar.c: bug fix for problem of initial frame being 77 chars wide on Windows. will be overridden by my other ws. --------------------------------------------------------------- FIX FOR LEAKING PROCESS HANDLES: --------------------------------------------------------------- process-nt.c: Fixes for leaking handles. Inspired by work done by Adrian Aichner <adrian@xemacs.org>. --------------------------------------------------------------- FIX FOR CYGWIN BUG (Unicode-related): --------------------------------------------------------------- unicode.c: Add workaround for newlib bug in sscanf() [should be fixed by release 1.5.12 of Cygwin]. --------------------------------------------------------------- WARNING FIXES: --------------------------------------------------------------- console-stream.c: `reinit' is unused. compiler.h, event-msw.c, frame-msw.c, intl-encap-win32.c, text.h: Add stuff to deal with ANSI-aliasing warnings I got. regex.c: Gather includes together to avoid warning. --------------------------------------------------------------- CHANGES TO INITIALIZATION ROUTINES: --------------------------------------------------------------- buffer.c, emacs.c, console.c, debug.c, device-x.c, device.c, dragdrop.c, emodules.c, eval.c, event-Xt.c, event-gtk.c, event-msw.c, event-stream.c, event-tty.c, events.c, extents.c, faces.c, file-coding.c, fileio.c, font-lock.c, frame-msw.c, glyphs-widget.c, glyphs.c, gui-x.c, insdel.c, lread.c, lstream.c, menubar-gtk.c, menubar-x.c, minibuf.c, mule-wnnfns.c, objects-msw.c, objects.c, print.c, scrollbar-x.c, search.c, select-x.c, text.c, undo.c, unicode.c, window.c, symsinit.h: Call reinit_*() functions directly from emacs.c, for clarity. Factor out some redundant init code. Move disallowed stuff that had crept into vars_of_glyphs() into complex_vars_of_glyphs(). Call init_eval_semi_early() from eval.c not in the middle of vars_of_() in emacs.c since there should be no order dependency in the latter calls. --------------------------------------------------------------- ARMAGEDDON: --------------------------------------------------------------- alloc.c, emacs.c, lisp.h, print.c: Rename inhibit_non_essential_printing_operations to inhibit_non_essential_conversion_operations. text.c: Assert on !inhibit_non_essential_conversion_operations. console-msw.c, print.c: Don't do conversion in SetConsoleTitle or FindWindow to avoid problems during armageddon. Put #errors for NON_ASCII_INTERNAL_FORMAT in places where problems would arise. --------------------------------------------------------------- CHANGES TO THE BUILD PROCEDURE: --------------------------------------------------------------- config.h.in, s/cxux.h, s/usg5-4-2.h, m/powerpc.h: Add comment about correct ordering of this file. Rearrange everything to follow this -- put all #undefs together and before the s&m files. Add undefs for HAVE_ALLOCA, C_ALLOCA, BROKEN_ALLOCA_IN_FUNCTION_CALLS, STACK_DIRECTION. Remove unused HAVE_STPCPY, HAVE_GETWD, HAVE_SETLOCALE. m/gec63.h: Deleted; totally broken, not used at all, not in FSF. m/7300.h, m/acorn.h, m/alliant-2800.h, m/alliant.h, m/altos.h, m/amdahl.h, m/apollo.h, m/att3b.h, m/aviion.h, m/celerity.h, m/clipper.h, m/cnvrgnt.h, m/convex.h, m/cydra5.h, m/delta.h, m/delta88k.h, m/dpx2.h, m/elxsi.h, m/ews4800r.h, m/gould.h, m/hp300bsd.h, m/hp800.h, m/hp9000s300.h, m/i860.h, m/ibmps2-aix.h, m/ibmrs6000.h, m/ibmrt-aix.h, m/ibmrt.h, m/intel386.h, m/iris4d.h, m/iris5d.h, m/iris6d.h, m/irist.h, m/isi-ov.h, m/luna88k.h, m/m68k.h, m/masscomp.h, m/mg1.h, m/mips-nec.h, m/mips-siemens.h, m/mips.h, m/news.h, m/nh3000.h, m/nh4000.h, m/ns32000.h, m/orion105.h, m/pfa50.h, m/plexus.h, m/pmax.h, m/powerpc.h, m/pyrmips.h, m/sequent-ptx.h, m/sequent.h, m/sgi-challenge.h, m/symmetry.h, m/tad68k.h, m/tahoe.h, m/targon31.h, m/tekxd88.h, m/template.h, m/tower32.h, m/tower32v3.h, m/ustation.h, m/vax.h, m/wicat.h, m/xps100.h: Delete C_ALLOCA, HAVE_ALLOCA, STACK_DIRECTION, BROKEN_ALLOCA_IN_FUNCTION_CALLS. All of this is auto-detected. When in doubt, I followed recent FSF sources, which also have these things deleted.
author ben
date Thu, 04 Nov 2004 23:08:28 +0000
parents ba4677f54a05
children ab71ad6ff3dd
comparison
equal deleted inserted replaced
2366:2a392e0c390a 2367:ecf1ebac70d8
26 26
27 #ifdef HAVE_CONFIG_H 27 #ifdef HAVE_CONFIG_H
28 #include <config.h> 28 #include <config.h>
29 #endif 29 #endif
30 30
31 #ifndef REGISTER /* Rigidly enforced as of 20.3 */
32 #define REGISTER
33 #endif
34
35 #ifndef _GNU_SOURCE 31 #ifndef _GNU_SOURCE
36 #define _GNU_SOURCE 1 32 #define _GNU_SOURCE 1
37 #endif 33 #endif
38 34
39 /* We assume non-Mule if emacs isn't defined. */ 35 /* We assume non-Mule if emacs isn't defined. */
40 #ifndef emacs 36 #ifndef emacs
41 #undef MULE 37 #undef MULE
42 #endif 38 #endif
43
44 /* We need this for `regex.h', and perhaps for the Emacs include files. */
45 #include <sys/types.h>
46 #include <stddef.h> /* needed for ptrdiff_t under Solaris */
47 39
48 /* XEmacs addition */ 40 /* XEmacs addition */
49 #ifdef REL_ALLOC 41 #ifdef REL_ALLOC
50 #define REGEX_REL_ALLOC /* may be undefined below */ 42 #define REGEX_REL_ALLOC /* may be undefined below */
51 #endif 43 #endif
81 #define PTR_TO_OFFSET(d) (MATCHING_IN_FIRST_STRING \ 73 #define PTR_TO_OFFSET(d) (MATCHING_IN_FIRST_STRING \
82 ? (d) - string1 : (d) - (string2 - size1)) 74 ? (d) - string1 : (d) - (string2 - size1))
83 75
84 #else /* not emacs */ 76 #else /* not emacs */
85 77
78 #include <stdlib.h>
79 #include <sys/types.h>
80 #include <stddef.h> /* needed for ptrdiff_t under Solaris */
81 #include <string.h>
82
86 #include "compiler.h" /* Get compiler-specific definitions like UNUSED */ 83 #include "compiler.h" /* Get compiler-specific definitions like UNUSED */
87 84
88 /* If we are not linking with Emacs proper, 85 /* If we are not linking with Emacs proper,
89 we can't use the relocating allocator 86 we can't use the relocating allocator
90 even if config.h says that we can. */ 87 even if config.h says that we can. */
94 #ifdef REGEX_MALLOC 91 #ifdef REGEX_MALLOC
95 #ifndef DECLARE_NOTHING 92 #ifndef DECLARE_NOTHING
96 #define DECLARE_NOTHING struct nosuchstruct 93 #define DECLARE_NOTHING struct nosuchstruct
97 #endif 94 #endif
98 #endif 95 #endif
99
100 #include <stdlib.h>
101 96
102 #define itext_ichar(str) ((Ichar) (str)[0]) 97 #define itext_ichar(str) ((Ichar) (str)[0])
103 #define itext_ichar_fmt(str, fmt, object) ((Ichar) (str)[0]) 98 #define itext_ichar_fmt(str, fmt, object) ((Ichar) (str)[0])
104 #define itext_ichar_ascii_fmt(str, fmt, object) ((Ichar) (str)[0]) 99 #define itext_ichar_ascii_fmt(str, fmt, object) ((Ichar) (str)[0])
105 100
115 #define INC_IBYTEPTR_FMT(p, fmt) ((p)++) 110 #define INC_IBYTEPTR_FMT(p, fmt) ((p)++)
116 #define DEC_IBYTEPTR(p) ((p)--) 111 #define DEC_IBYTEPTR(p) ((p)--)
117 #define DEC_IBYTEPTR_FMT(p, fmt) ((p)--) 112 #define DEC_IBYTEPTR_FMT(p, fmt) ((p)--)
118 #define itext_ichar_len(ptr) 1 113 #define itext_ichar_len(ptr) 1
119 #define itext_ichar_len_fmt(ptr, fmt) 1 114 #define itext_ichar_len_fmt(ptr, fmt) 1
120
121 #include <string.h>
122 115
123 /* Define the syntax stuff for \<, \>, etc. */ 116 /* Define the syntax stuff for \<, \>, etc. */
124 117
125 /* This must be nonzero for the wordchar and notwordchar pattern 118 /* This must be nonzero for the wordchar and notwordchar pattern
126 commands in re_match_2. */ 119 commands in re_match_2. */
343 336
344 #endif /* not alloca */ 337 #endif /* not alloca */
345 338
346 #define REGEX_ALLOCATE ALLOCA 339 #define REGEX_ALLOCATE ALLOCA
347 340
341 /* !!#### Needs review */
348 /* Assumes a `char *destination' variable. */ 342 /* Assumes a `char *destination' variable. */
349 #define REGEX_REALLOCATE(source, osize, nsize) \ 343 #define REGEX_REALLOCATE(source, osize, nsize) \
350 (destination = (char *) ALLOCA (nsize), \ 344 (destination = (char *) ALLOCA (nsize), \
351 memmove (destination, source, osize), \ 345 memmove (destination, source, osize), \
352 destination) 346 destination)