diff --git a/Modules/reopmodule.c b/Modules/reopmodule.c deleted file mode 100644 index 6c671c898ac..00000000000 --- a/Modules/reopmodule.c +++ /dev/null @@ -1,1053 +0,0 @@ -/*********************************************************** -Copyright 1991-1995 by Stichting Mathematisch Centrum, Amsterdam, -The Netherlands. - - All Rights Reserved - -Permission to use, copy, modify, and distribute this software and its -documentation for any purpose and without fee is hereby granted, -provided that the above copyright notice appear in all copies and that -both that copyright notice and this permission notice appear in -supporting documentation, and that the names of Stichting Mathematisch -Centrum or CWI or Corporation for National Research Initiatives or -CNRI not be used in advertising or publicity pertaining to -distribution of the software without specific, written prior -permission. - -While CWI is the initial source for this software, a modified version -is made available by the Corporation for National Research Initiatives -(CNRI) at the Internet address ftp://ftp.python.org. - -STICHTING MATHEMATISCH CENTRUM AND CNRI DISCLAIM ALL WARRANTIES WITH -REGARD TO THIS SOFTWARE, INCLUDING ALL IMPLIED WARRANTIES OF -MERCHANTABILITY AND FITNESS, IN NO EVENT SHALL STICHTING MATHEMATISCH -CENTRUM OR CNRI BE LIABLE FOR ANY SPECIAL, INDIRECT OR CONSEQUENTIAL -DAMAGES OR ANY DAMAGES WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR -PROFITS, WHETHER IN AN ACTION OF CONTRACT, NEGLIGENCE OR OTHER -TORTIOUS ACTION, ARISING OUT OF OR IN CONNECTION WITH THE USE OR -PERFORMANCE OF THIS SOFTWARE. - -******************************************************************/ - -/* $Id$ */ - -/* Regular expression objects */ -/* This uses Tatu Ylonen's copyleft-free reimplementation of - GNU regular expressions */ - -#include "Python.h" - -#include - -#include "regexpr.h" - -static PyObject *ReopError; /* Exception */ - -#define IGNORECASE 0x01 -#define MULTILINE 0x02 -#define DOTALL 0x04 -#define VERBOSE 0x08 - -#define NORMAL 0 -#define CHARCLASS 1 -#define REPLACEMENT 2 - -#define CHAR 0 -#define MEMORY_REFERENCE 1 -#define SYNTAX 2 -#define NOT_SYNTAX 3 -#define SET 4 -#define WORD_BOUNDARY 5 -#define NOT_WORD_BOUNDARY 6 -#define BEGINNING_OF_BUFFER 7 -#define END_OF_BUFFER 8 - -static PyObject * -makeresult(regs, num_regs) - struct re_registers *regs; - int num_regs; -{ - PyObject *v; - int i; - static PyObject *filler = NULL; - - if (filler == NULL) { - filler = Py_BuildValue("(ii)", -1, -1); - if (filler == NULL) - return NULL; - } - v = PyTuple_New(num_regs); - if (v == NULL) - return NULL; - - for (i = 0; i < num_regs; i++) { - int lo = regs->start[i]; - int hi = regs->end[i]; - PyObject *w; - if (lo == -1 && hi == -1) { - w = filler; - Py_INCREF(w); - } - else - w = Py_BuildValue("(ii)", lo, hi); - if (w == NULL || PyTuple_SetItem(v, i, w) < 0) { - Py_DECREF(v); - return NULL; - } - } - return v; -} - -static PyObject * -reop_match(self, args) - PyObject *self; - PyObject *args; -{ - unsigned char *string; - int fastmaplen, stringlen; - int can_be_null, anchor, i; - int flags, pos, result; - struct re_pattern_buffer bufp; - struct re_registers re_regs; - PyObject *modules = NULL; - PyObject *reopmodule = NULL; - PyObject *reopdict = NULL; - PyObject *casefold = NULL; - - if (!PyArg_Parse(args, "(s#iiis#is#i)", - &(bufp.buffer), &(bufp.allocated), - &(bufp.num_registers), &flags, &can_be_null, - &(bufp.fastmap), &fastmaplen, - &anchor, - &string, &stringlen, - &pos)) - return NULL; - - /* XXX sanity-check the input data */ - bufp.used=bufp.allocated; - if (flags & IGNORECASE) - { - if ((modules = PyImport_GetModuleDict()) == NULL) - return NULL; - - if ((reopmodule = PyDict_GetItemString(modules, - "reop")) == NULL) - return NULL; - - if ((reopdict = PyModule_GetDict(reopmodule)) == NULL) - return NULL; - - if ((casefold = PyDict_GetItemString(reopdict, - "casefold")) == NULL) - return NULL; - - bufp.translate = (unsigned char*)PyString_AsString(casefold); - } - else - bufp.translate=NULL; - bufp.fastmap_accurate=1; - bufp.can_be_null=can_be_null; - bufp.uses_registers=1; - bufp.anchor=anchor; - - for(i=0; i", which will be - passed to eval() */ - string[0]=string[length+3]='"'; - string[1]='\\'; - string[length+4]='\0'; - memcpy(string+2, pattern+index-1, length+1); - v=PyRun_String((char *)string, Py_eval_input, - PyEval_GetGlobals(), PyEval_GetLocals()); - free(string); - /* The evaluation raised an exception */ - if (v==NULL) return NULL; - result=Py_BuildValue("iOi", CHAR, v, end); - Py_DECREF(v); - return result; - } - break; - - case('b'): - if (context!=NORMAL) - return Py_BuildValue("ici", CHAR, (char)8, index); - else - { - unsigned char empty_string[1]; - empty_string[0]='\0'; - return Py_BuildValue("isi", WORD_BOUNDARY, empty_string, index); - } - break; - case('B'): - if (context!=NORMAL) - return Py_BuildValue("ici", CHAR, 'B', index); - else - { - unsigned char empty_string[1]; - empty_string[0]='\0'; - return Py_BuildValue("isi", NOT_WORD_BOUNDARY, empty_string, index); - } - break; - case('A'): - if (context!=NORMAL) - return Py_BuildValue("ici", CHAR, 'A', index); - else - { - unsigned char empty_string[1]; - empty_string[0]='\0'; - return Py_BuildValue("isi", BEGINNING_OF_BUFFER, empty_string, index); - } - break; - case('Z'): - if (context!=NORMAL) - return Py_BuildValue("ici", CHAR, 'Z', index); - else - { - unsigned char empty_string[1]; - empty_string[0]='\0'; - return Py_BuildValue("isi", END_OF_BUFFER, empty_string, index); - } - break; - case('E'): case('G'): case('L'): case('Q'): - case('U'): case('l'): case('u'): - { - char message[50]; - sprintf(message, "\\%c is not allowed", c); - PyErr_SetString(ReopError, message); - return NULL; - } - - case ('w'): - if (context==NORMAL) - return Py_BuildValue("iii", SYNTAX, Sword, index); - if (context!=CHARCLASS) - return Py_BuildValue("ici", CHAR, 'w', index); - { - /* context==CHARCLASS */ - unsigned char set[256]; - int i, j; - for(i=j=0; i<256; i++) - if (re_syntax_table[i] & Sword) - { - set[j++] = i; - } - return Py_BuildValue("is#i", SET, set, j, index); - } - break; - case ('W'): - if (context==NORMAL) - return Py_BuildValue("iii", NOT_SYNTAX, Sword, index); - if (context!=CHARCLASS) - return Py_BuildValue("ici", CHAR, 'W', index); - { - /* context==CHARCLASS */ - unsigned char set[256]; - int i, j; - for(i=j=0; i<256; i++) - if (! (re_syntax_table[i] & Sword)) - { - set[j++] = i; - } - return Py_BuildValue("is#i", SET, set, j, index); - } - break; - case ('s'): - if (context==NORMAL) - return Py_BuildValue("iii", SYNTAX, Swhitespace, index); - if (context!=CHARCLASS) - return Py_BuildValue("ici", CHAR, 's', index); - { - /* context==CHARCLASS */ - unsigned char set[256]; - int i, j; - for(i=j=0; i<256; i++) - if (re_syntax_table[i] & Swhitespace) - { - set[j++] = i; - } - return Py_BuildValue("is#i", SET, set, j, index); - } - break; - case ('S'): - if (context==NORMAL) - return Py_BuildValue("iii", NOT_SYNTAX, Swhitespace, index); - if (context!=CHARCLASS) - return Py_BuildValue("ici", CHAR, 'S', index); - { - /* context==CHARCLASS */ - unsigned char set[256]; - int i, j; - for(i=j=0; i<256; i++) - if (! (re_syntax_table[i] & Swhitespace) ) - { - set[j++] = i; - } - return Py_BuildValue("is#i", SET, set, j, index); - } - break; - - case ('d'): - if (context==NORMAL) - return Py_BuildValue("iii", SYNTAX, Sdigit, index); - if (context!=CHARCLASS) - return Py_BuildValue("ici", CHAR, 'd', index); - { - /* context==CHARCLASS */ - unsigned char set[256]; - int i, j; - for(i=j=0; i<256; i++) - if (re_syntax_table[i] & Sdigit) - { - set[j++] = i; - } - return Py_BuildValue("is#i", SET, set, j, index); - } - break; - case ('D'): - if (context==NORMAL) - return Py_BuildValue("iii", NOT_SYNTAX, Sdigit, index); - if (context!=CHARCLASS) - return Py_BuildValue("ici", CHAR, 'D', index); - { - /* context==CHARCLASS */ - unsigned char set[256]; - int i, j; - for(i=j=0; i<256; i++) - if ( !(re_syntax_table[i] & Sdigit) ) - { - set[j++] = i; - } - return Py_BuildValue("is#i", SET, set, j, index); - } - break; - - case('g'): - { - int end, valid, i; - if (context!=REPLACEMENT) - return Py_BuildValue("ici", CHAR, 'g', index); - if (pattern_len<=index) - { - PyErr_SetString(ReopError, "unfinished symbolic reference"); - return NULL; - } - if (pattern[index]!='<') - { - PyErr_SetString(ReopError, "missing < in symbolic reference"); - return NULL; - } - index++; - end=index; - while (end255) - { - PyErr_SetString(ReopError, "octal value out of range"); - return NULL; - } - return Py_BuildValue("ici", CHAR, (unsigned char)octval, i); - } - break; - case('1'): case('2'): case('3'): case('4'): - case('5'): case('6'): case('7'): case('8'): - case('9'): - { - /* Handle \?, where ? is from 1 through 9 */ - int value=0; - index--; - /* If it's at least a two-digit reference, like \34, it might - either be a 3-digit octal escape (\123) or a 2-digit - decimal memory reference (\34) */ - - if ( (index+1) 255) - { - PyErr_SetString(ReopError, "octal value out of range"); - return NULL; - } - return Py_BuildValue("ici", CHAR, (unsigned char)value, index+3); - } - else - { - /* 2-digit form, so it's a memory reference */ - if (context==CHARCLASS) - { - PyErr_SetString(ReopError, - "cannot reference a register from inside a character class"); - return NULL; - } - value= 10*(pattern[index ]-'0') + - (pattern[index+1]-'0'); - if (value<1 || RE_NREGS<=value) - { - PyErr_SetString(ReopError, "memory reference out of range"); - return NULL; - } - return Py_BuildValue("iii", MEMORY_REFERENCE, - value, index+2); - } - } - else - { - /* Single-digit form, like \2, so it's a memory reference */ - if (context==CHARCLASS) - { - PyErr_SetString(ReopError, - "cannot reference a register from inside a character class"); - return NULL; - } - return Py_BuildValue("iii", MEMORY_REFERENCE, - pattern[index]-'0', index+1); - } - } - break; - - default: - return Py_BuildValue("ici", CHAR, c, index); - break; - } -} - -static PyObject * -reop__expand(self, args) - PyObject *self; - PyObject *args; -{ - PyObject *results, *match_obj; - PyObject *repl_obj, *newstring; - unsigned char *repl; - int size, total_len, i, start, pos; - - if (!PyArg_ParseTuple(args, "OS", &match_obj, &repl_obj)) - return NULL; - - repl=(unsigned char *)PyString_AsString(repl_obj); - size=PyString_Size(repl_obj); - results=PyList_New(0); - if (results==NULL) return NULL; - for(start=total_len=i=0; ire_patbuf, - start, length, next, length-next, - &pattern->re_regs); - if (result < -1) - { /* Erk... an error happened during the reop search */ - Py_DECREF(newlist); - PyErr_SetString(ReopError, "match failure"); - return NULL; - } - if (next<=result) - { - int match_start=pattern->re_regs.start[0]; - int oldmatch_end=match_end; - match_end=pattern->re_regs.end[0]; - - if (match_start==match_end) - { /* A zero-length match; increment to the next position */ - next=result+1; - match_end=oldmatch_end; - continue; - } - - /* Append the string up to the start of the match */ - s=PyString_FromStringAndSize(start+oldmatch_end, match_start-oldmatch_end); - if (!s) - { - Py_DECREF(newlist); - return NULL; - } - PyList_Append(newlist, s); - Py_DECREF(s); - - if (retain) - { - /* Append a string containing whatever matched */ - s=PyString_FromStringAndSize(start+match_start, match_end-match_start); - if (!s) - { - Py_DECREF(newlist); - return NULL; - } - PyList_Append(newlist, s); - Py_DECREF(s); - } - /* Update the pointer, and increment the count of splits */ - next=match_end; count++; - } - } while (result!=-1 && !(maxsplit && maxsplit==count) && - next