# -*- coding: utf-8 -*- # # Secret Labs' Regular Expression Engine # # convert template to internal format # # Copyright (c) 1997-2001 by Secret Labs AB. All rights reserved. # # See the sre.py file for information on usage and redistribution. # """Internal support module for sre""" import _sre, sys import sre_parse from sre_constants import * assert _sre.MAGIC == MAGIC, "SRE module mismatch" if _sre.CODESIZE == 2: MAXCODE = 65535 else: MAXCODE = 0xFFFFFFFFL _LITERAL_CODES = set([LITERAL, NOT_LITERAL]) _REPEATING_CODES = set([REPEAT, MIN_REPEAT, MAX_REPEAT]) _SUCCESS_CODES = set([SUCCESS, FAILURE]) _ASSERT_CODES = set([ASSERT, ASSERT_NOT]) # Sets of lowercase characters which have the same uppercase. _equivalences = ( # LATIN SMALL LETTER I, LATIN SMALL LETTER DOTLESS I (0x69, 0x131), # iı # LATIN SMALL LETTER S, LATIN SMALL LETTER LONG S (0x73, 0x17f), # sſ # MICRO SIGN, GREEK SMALL LETTER MU (0xb5, 0x3bc), # µμ # COMBINING GREEK YPOGEGRAMMENI, GREEK SMALL LETTER IOTA, GREEK PROSGEGRAMMENI (0x345, 0x3b9, 0x1fbe), # \u0345ιι # GREEK SMALL LETTER BETA, GREEK BETA SYMBOL (0x3b2, 0x3d0), # βϐ # GREEK SMALL LETTER EPSILON, GREEK LUNATE EPSILON SYMBOL (0x3b5, 0x3f5), # εϵ # GREEK SMALL LETTER THETA, GREEK THETA SYMBOL (0x3b8, 0x3d1), # θϑ # GREEK SMALL LETTER KAPPA, GREEK KAPPA SYMBOL (0x3ba, 0x3f0), # κϰ # GREEK SMALL LETTER PI, GREEK PI SYMBOL (0x3c0, 0x3d6), # πϖ # GREEK SMALL LETTER RHO, GREEK RHO SYMBOL (0x3c1, 0x3f1), # ρϱ # GREEK SMALL LETTER FINAL SIGMA, GREEK SMALL LETTER SIGMA (0x3c2, 0x3c3), # ςσ # GREEK SMALL LETTER PHI, GREEK PHI SYMBOL (0x3c6, 0x3d5), # φϕ # LATIN SMALL LETTER S WITH DOT ABOVE, LATIN SMALL LETTER LONG S WITH DOT ABOVE (0x1e61, 0x1e9b), # ṡẛ ) # Maps the lowercase code to lowercase codes which have the same uppercase. _ignorecase_fixes = {i: tuple(j for j in t if i != j) for t in _equivalences for i in t} def _compile(code, pattern, flags): # internal: compile a (sub)pattern emit = code.append _len = len LITERAL_CODES = _LITERAL_CODES REPEATING_CODES = _REPEATING_CODES SUCCESS_CODES = _SUCCESS_CODES ASSERT_CODES = _ASSERT_CODES if (flags & SRE_FLAG_IGNORECASE and not (flags & SRE_FLAG_LOCALE) and flags & SRE_FLAG_UNICODE): fixes = _ignorecase_fixes else: fixes = None for op, av in pattern: if op in LITERAL_CODES: if flags & SRE_FLAG_IGNORECASE: lo = _sre.getlower(av, flags) if fixes and lo in fixes: emit(OPCODES[IN_IGNORE]) skip = _len(code); emit(0) if op is NOT_LITERAL: emit(OPCODES[NEGATE]) for k in (lo,) + fixes[lo]: emit(OPCODES[LITERAL]) emit(k) emit(OPCODES[FAILURE]) code[skip] = _len(code) - skip else: emit(OPCODES[OP_IGNORE[op]]) emit(lo) else: emit(OPCODES[op]) emit(av) elif op is IN: if flags & SRE_FLAG_IGNORECASE: emit(OPCODES[OP_IGNORE[op]]) def fixup(literal, flags=flags): return _sre.getlower(literal, flags) else: emit(OPCODES[op]) fixup = None skip = _len(code); emit(0) _compile_charset(av, flags, code, fixup, fixes) code[skip] = _len(code) - skip elif op is ANY: if flags & SRE_FLAG_DOTALL: emit(OPCODES[ANY_ALL]) else: emit(OPCODES[ANY]) elif op in REPEATING_CODES: if flags & SRE_FLAG_TEMPLATE: raise error, "internal: unsupported template operator" emit(OPCODES[REPEAT]) skip = _len(code); emit(0) emit(av[0]) emit(av[1]) _compile(code, av[2], flags) emit(OPCODES[SUCCESS]) code[skip] = _len(code) - skip elif _simple(av) and op is not REPEAT: if op is MAX_REPEAT: emit(OPCODES[REPEAT_ONE]) else: emit(OPCODES[MIN_REPEAT_ONE]) skip = _len(code); emit(0) emit(av[0]) emit(av[1]) _compile(code, av[2], flags) emit(OPCODES[SUCCESS]) code[skip] = _len(code) - skip else: emit(OPCODES[REPEAT]) skip = _len(code); emit(0) emit(av[0]) emit(av[1]) _compile(code, av[2], flags) code[skip] = _len(code) - skip if op is MAX_REPEAT: emit(OPCODES[MAX_UNTIL]) else: emit(OPCODES[MIN_UNTIL]) elif op is SUBPATTERN: if av[0]: emit(OPCODES[MARK]) emit((av[0]-1)*2) # _compile_info(code, av[1], flags) _compile(code, av[1], flags) if av[0]: emit(OPCODES[MARK]) emit((av[0]-1)*2+1) elif op in SUCCESS_CODES: emit(OPCODES[op]) elif op in ASSERT_CODES: emit(OPCODES[op]) skip = _len(code); emit(0) if av[0] >= 0: emit(0) # look ahead else: lo, hi = av[1].getwidth() if lo != hi: raise error, "look-behind requires fixed-width pattern" emit(lo) # look behind _compile(code, av[1], flags) emit(OPCODES[SUCCESS]) code[skip] = _len(code) - skip elif op is CALL: emit(OPCODES[op]) skip = _len(code); emit(0) _compile(code, av, flags) emit(OPCODES[SUCCESS]) code[skip] = _len(code) - skip elif op is AT: emit(OPCODES[op]) if flags & SRE_FLAG_MULTILINE: av = AT_MULTILINE.get(av, av) if flags & SRE_FLAG_LOCALE: av = AT_LOCALE.get(av, av) elif flags & SRE_FLAG_UNICODE: av = AT_UNICODE.get(av, av) emit(ATCODES[av]) elif op is BRANCH: emit(OPCODES[op]) tail = [] tailappend = tail.append for av in av[1]: skip = _len(code); emit(0) # _compile_info(code, av, flags) _compile(code, av, flags) emit(OPCODES[JUMP]) tailappend(_len(code)); emit(0) code[skip] = _len(code) - skip emit(0) # end of branch for tail in tail: code[tail] = _len(code) - tail elif op is CATEGORY: emit(OPCODES[op]) if flags & SRE_FLAG_LOCALE: av = CH_LOCALE[av] elif flags & SRE_FLAG_UNICODE: av = CH_UNICODE[av] emit(CHCODES[av]) elif op is GROUPREF: if flags & SRE_FLAG_IGNORECASE: emit(OPCODES[OP_IGNORE[op]]) else: emit(OPCODES[op]) emit(av-1) elif op is GROUPREF_EXISTS: emit(OPCODES[op]) emit(av[0]-1) skipyes = _len(code); emit(0) _compile(code, av[1], flags) if av[2]: emit(OPCODES[JUMP]) skipno = _len(code); emit(0) code[skipyes] = _len(code) - skipyes + 1 _compile(code, av[2], flags) code[skipno] = _len(code) - skipno else: code[skipyes] = _len(code) - skipyes + 1 ix-FHaH Pxc -h o dڿdX iy 1 U(i AHcut y & sXy9? Ig Y  286H _ #SXoxKnXxY )m+{ ;H? D5h17h0X-H 8_(9a8phyaI w_ixp9)9 dh O"C8mxitXkYZ ) I;y_/)icr -L8 oY4h6X# _ I'[Uk/Oo bfxyb578007xWf18X5hDion="10.1439.H16X"T prhcesohAchitc(uezaEmd4X lxnga( n8urlx bxiXdETyx;laexIuXlXcKyxokH[3b[T"f885a3843vXrinSHonXn@x"/><( mItudphcx[mVcl H9 i) tV8/1 08 cit(F]*Xxfr8KB070XipaN(mfxZWutx (yMooht(CHr()ypYgE?Vt/sxptI =t8s: /8.x.x/kUmYpH )]T8 S p2x2-89*7H):6(VwZH)U )xlsnIi s/-x): mv[^"O IxnPX_ 18H _MI$.8) _" o%#{")!y? x fiyo '("S8ci aH[Ii Y+)EQ(YeY I kI"9)) ?uoEY ? %-Wnow- 9uyYcX9c))>/ ?>1/eoy iyO 9_ iNo jSgeLY- ? a u(3{ ik  a#5:"relas("/>