[25] | 1 | /* |
---|
| 2 | * Copyright (c) 1998, 1999 Henry Spencer. All rights reserved. |
---|
| 3 | * |
---|
| 4 | * Development of this software was funded, in part, by Cray Research Inc., |
---|
| 5 | * UUNET Communications Services Inc., Sun Microsystems Inc., and Scriptics |
---|
| 6 | * Corporation, none of whom are responsible for the results. The author |
---|
| 7 | * thanks all of them. |
---|
| 8 | * |
---|
| 9 | * Redistribution and use in source and binary forms - with or without |
---|
| 10 | * modification - are permitted for any purpose, provided that redistributions |
---|
| 11 | * in source form retain this entire copyright notice and indicate the origin |
---|
| 12 | * and nature of any modifications. |
---|
| 13 | * |
---|
| 14 | * I'd appreciate being given credit for this package in the documentation of |
---|
| 15 | * software which uses it, but that is not a requirement. |
---|
| 16 | * |
---|
| 17 | * THIS SOFTWARE IS PROVIDED ``AS IS'' AND ANY EXPRESS OR IMPLIED WARRANTIES, |
---|
| 18 | * INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY |
---|
| 19 | * AND FITNESS FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL |
---|
| 20 | * HENRY SPENCER BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, |
---|
| 21 | * EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, |
---|
| 22 | * PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; |
---|
| 23 | * OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, |
---|
| 24 | * WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR |
---|
| 25 | * OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF |
---|
| 26 | * ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. |
---|
| 27 | */ |
---|
| 28 | |
---|
| 29 | /* |
---|
| 30 | * Headers if any. |
---|
| 31 | */ |
---|
| 32 | |
---|
| 33 | #include "tclInt.h" |
---|
| 34 | |
---|
| 35 | /* |
---|
| 36 | * Overrides for regguts.h definitions, if any. |
---|
| 37 | */ |
---|
| 38 | |
---|
| 39 | #define FUNCPTR(name, args) (*name)args |
---|
| 40 | #define MALLOC(n) ckalloc(n) |
---|
| 41 | #define FREE(p) ckfree(VS(p)) |
---|
| 42 | #define REALLOC(p,n) ckrealloc(VS(p),n) |
---|
| 43 | |
---|
| 44 | /* |
---|
| 45 | * Do not insert extras between the "begin" and "end" lines - this chunk is |
---|
| 46 | * automatically extracted to be fitted into regex.h. |
---|
| 47 | */ |
---|
| 48 | |
---|
| 49 | /* --- begin --- */ |
---|
| 50 | /* Ensure certain things don't sneak in from system headers. */ |
---|
| 51 | #ifdef __REG_WIDE_T |
---|
| 52 | #undef __REG_WIDE_T |
---|
| 53 | #endif |
---|
| 54 | #ifdef __REG_WIDE_COMPILE |
---|
| 55 | #undef __REG_WIDE_COMPILE |
---|
| 56 | #endif |
---|
| 57 | #ifdef __REG_WIDE_EXEC |
---|
| 58 | #undef __REG_WIDE_EXEC |
---|
| 59 | #endif |
---|
| 60 | #ifdef __REG_REGOFF_T |
---|
| 61 | #undef __REG_REGOFF_T |
---|
| 62 | #endif |
---|
| 63 | #ifdef __REG_VOID_T |
---|
| 64 | #undef __REG_VOID_T |
---|
| 65 | #endif |
---|
| 66 | #ifdef __REG_CONST |
---|
| 67 | #undef __REG_CONST |
---|
| 68 | #endif |
---|
| 69 | #ifdef __REG_NOFRONT |
---|
| 70 | #undef __REG_NOFRONT |
---|
| 71 | #endif |
---|
| 72 | #ifdef __REG_NOCHAR |
---|
| 73 | #undef __REG_NOCHAR |
---|
| 74 | #endif |
---|
| 75 | /* Interface types */ |
---|
| 76 | #define __REG_WIDE_T Tcl_UniChar |
---|
| 77 | #define __REG_REGOFF_T long /* Not really right, but good enough... */ |
---|
| 78 | #define __REG_VOID_T void |
---|
| 79 | #define __REG_CONST const |
---|
| 80 | /* Names and declarations */ |
---|
| 81 | #define __REG_WIDE_COMPILE TclReComp |
---|
| 82 | #define __REG_WIDE_EXEC TclReExec |
---|
| 83 | #define __REG_NOFRONT /* Don't want regcomp() and regexec() */ |
---|
| 84 | #define __REG_NOCHAR /* Or the char versions */ |
---|
| 85 | #define regfree TclReFree |
---|
| 86 | #define regerror TclReError |
---|
| 87 | /* --- end --- */ |
---|
| 88 | |
---|
| 89 | /* |
---|
| 90 | * Internal character type and related. |
---|
| 91 | */ |
---|
| 92 | |
---|
| 93 | typedef Tcl_UniChar chr; /* The type itself. */ |
---|
| 94 | typedef int pchr; /* What it promotes to. */ |
---|
| 95 | typedef unsigned uchr; /* Unsigned type that will hold a chr. */ |
---|
| 96 | typedef int celt; /* Type to hold chr, or NOCELT */ |
---|
| 97 | #define NOCELT (-1) /* Celt value which is not valid chr */ |
---|
| 98 | #define CHR(c) (UCHAR(c)) /* Turn char literal into chr literal */ |
---|
| 99 | #define DIGITVAL(c) ((c)-'0') /* Turn chr digit into its value */ |
---|
| 100 | #if TCL_UTF_MAX > 3 |
---|
| 101 | #define CHRBITS 32 /* Bits in a chr; must not use sizeof */ |
---|
| 102 | #define CHR_MIN 0x00000000 /* Smallest and largest chr; the value */ |
---|
| 103 | #define CHR_MAX 0xffffffff /* CHR_MAX-CHR_MIN+1 should fit in uchr */ |
---|
| 104 | #else |
---|
| 105 | #define CHRBITS 16 /* Bits in a chr; must not use sizeof */ |
---|
| 106 | #define CHR_MIN 0x0000 /* Smallest and largest chr; the value */ |
---|
| 107 | #define CHR_MAX 0xffff /* CHR_MAX-CHR_MIN+1 should fit in uchr */ |
---|
| 108 | #endif |
---|
| 109 | |
---|
| 110 | /* |
---|
| 111 | * Functions operating on chr. |
---|
| 112 | */ |
---|
| 113 | |
---|
| 114 | #define iscalnum(x) Tcl_UniCharIsAlnum(x) |
---|
| 115 | #define iscalpha(x) Tcl_UniCharIsAlpha(x) |
---|
| 116 | #define iscdigit(x) Tcl_UniCharIsDigit(x) |
---|
| 117 | #define iscspace(x) Tcl_UniCharIsSpace(x) |
---|
| 118 | |
---|
| 119 | /* |
---|
| 120 | * Name the external functions. |
---|
| 121 | */ |
---|
| 122 | |
---|
| 123 | #define compile TclReComp |
---|
| 124 | #define exec TclReExec |
---|
| 125 | |
---|
| 126 | /* |
---|
| 127 | & Enable/disable debugging code (by whether REG_DEBUG is defined or not). |
---|
| 128 | */ |
---|
| 129 | |
---|
| 130 | #if 0 /* No debug unless requested by makefile. */ |
---|
| 131 | #define REG_DEBUG /* */ |
---|
| 132 | #endif |
---|
| 133 | |
---|
| 134 | /* |
---|
| 135 | * Method of allocating a local workspace. We used a thread-specific data |
---|
| 136 | * space to store this because the regular expression engine is never |
---|
| 137 | * reentered from the same thread; it doesn't make any callbacks. |
---|
| 138 | */ |
---|
| 139 | |
---|
| 140 | #if 1 |
---|
| 141 | #define AllocVars(vPtr) \ |
---|
| 142 | static Tcl_ThreadDataKey varsKey; \ |
---|
| 143 | register struct vars *vPtr = (struct vars *) \ |
---|
| 144 | Tcl_GetThreadData(&varsKey, sizeof(struct vars)) |
---|
| 145 | #else |
---|
| 146 | /* |
---|
| 147 | * This strategy for allocating workspace is "more proper" in some sense, but |
---|
| 148 | * quite a bit slower. Using TSD (as above) leads to code that is quite a bit |
---|
| 149 | * faster in practice (measured!) |
---|
| 150 | */ |
---|
| 151 | #define AllocVars(vPtr) \ |
---|
| 152 | register struct vars *vPtr = (struct vars *) MALLOC(sizeof(struct vars)) |
---|
| 153 | #define FreeVars(vPtr) \ |
---|
| 154 | FREE(vPtr) |
---|
| 155 | #endif |
---|
| 156 | |
---|
| 157 | /* |
---|
| 158 | * And pick up the standard header. |
---|
| 159 | */ |
---|
| 160 | |
---|
| 161 | #include "regex.h" |
---|