Пример #1
0
 def fixup(literal, flags=flags):
     return _sre.getlower(literal, flags)
Пример #2
0
 def fixup(literal, flags=flags):
     return _sre.getlower(literal, flags)
Пример #3
0
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
    for op, av in pattern:
        if op in LITERAL_CODES:
            if flags & SRE_FLAG_IGNORECASE:
                emit(OPCODES[OP_IGNORE[op]])
                emit(_sre.getlower(av, flags))
            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 = _identityfunction
            skip = _len(code); emit(0)
            _compile_charset(av, flags, code, fixup)
            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
        else:
            raise ValueError("unsupported operand type", op)
Пример #4
0
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
    for op, av in pattern:
        if op in LITERAL_CODES:
            if flags & SRE_FLAG_IGNORECASE:
                emit(OPCODES[OP_IGNORE[op]])
                emit(_sre.getlower(av, flags))
            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 = _identityfunction
            skip = _len(code)
            emit(0)
            _compile_charset(av, flags, code, fixup)
            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
        else:
            raise ValueError("unsupported operand type", op)