sre_parse.py

来自「mallet是自然语言处理、机器学习领域的一个开源项目。」· Python 代码 · 共 739 行 · 第 1/2 页

    subpattern = SubPattern(state)

    while 1:

        if source.next in ("|", ")"):
            break # end of subpattern
        this = source.get()
        if this is None:
            break # end of pattern

        if state.flags & SRE_FLAG_VERBOSE:
            # skip whitespace and comments
            if this in WHITESPACE:
                continue
            if this == "#":
                while 1:
                    this = source.get()
                    if this in (None, "\n"):
                        break
                continue

        if this and this[0] not in SPECIAL_CHARS:
            subpattern.append((LITERAL, ord(this)))

        elif this == "[":
            # character set
            set = []
##          if source.match(":"):
##              pass # handle character classes
            if source.match("^"):
                set.append((NEGATE, None))
            # check remaining characters
            start = set[:]
            while 1:
                this = source.get()
                if this == "]" and set != start:
                    break
                elif this and this[0] == "\\":
                    code1 = _class_escape(source, this)
                elif this:
                    code1 = LITERAL, ord(this)
                else:
                    raise error, "unexpected end of regular expression"
                if source.match("-"):
                    # potential range
                    this = source.get()
                    if this == "]":
                        if code1[0] is IN:
                            code1 = code1[1][0]
                        set.append(code1)
                        set.append((LITERAL, ord("-")))
                        break
                    else:
                        if this[0] == "\\":
                            code2 = _class_escape(source, this)
                        else:
                            code2 = LITERAL, ord(this)
                        if code1[0] != LITERAL or code2[0] != LITERAL:
                            raise error, "bad character range"
                        lo = code1[1]
                        hi = code2[1]
                        if hi < lo:
                            raise error, "bad character range"
                        set.append((RANGE, (lo, hi)))
                else:
                    if code1[0] is IN:
                        code1 = code1[1][0]
                    set.append(code1)

            # XXX: <fl> should move set optimization to compiler!
            if len(set)==1 and set[0][0] is LITERAL:
                subpattern.append(set[0]) # optimization
            elif len(set)==2 and set[0][0] is NEGATE and set[1][0] is LITERAL:
                subpattern.append((NOT_LITERAL, set[1][1])) # optimization
            else:
                # XXX: <fl> should add charmap optimization here
                subpattern.append((IN, set))

        elif this and this[0] in REPEAT_CHARS:
            # repeat previous item
            if this == "?":
                min, max = 0, 1
            elif this == "*":
                min, max = 0, MAXREPEAT

            elif this == "+":
                min, max = 1, MAXREPEAT
            elif this == "{":
                here = source.tell()
                min, max = 0, MAXREPEAT
                lo = hi = ""
                while source.next in DIGITS:
                    lo = lo + source.get()
                if source.match(","):
                    while source.next in DIGITS:
                        hi = hi + source.get()
                else:
                    hi = lo
                if not source.match("}"):
                    subpattern.append((LITERAL, ord(this)))
                    source.seek(here)
                    continue
                if lo:
                    min = atoi(lo)
                if hi:
                    max = atoi(hi)
                if max < min:
                    raise error, "bad repeat interval"
            else:
                raise error, "not supported"
            # figure out which item to repeat
            if subpattern:
                item = subpattern[-1:]
            else:
                item = None
            if not item or (len(item) == 1 and item[0][0] == AT):
                raise error, "nothing to repeat"
            if item[0][0] in (MIN_REPEAT, MAX_REPEAT):
                raise error, "multiple repeat"
            if source.match("?"):
                subpattern[-1] = (MIN_REPEAT, (min, max, item))
            else:
                subpattern[-1] = (MAX_REPEAT, (min, max, item))

        elif this == ".":
            subpattern.append((ANY, None))

        elif this == "(":
            group = 1
            name = None
            if source.match("?"):
                group = 0
                # options
                if source.match("P"):
                    # python extensions
                    if source.match("<"):
                        # named group: skip forward to end of name
                        name = ""
                        while 1:
                            char = source.get()
                            if char is None:
                                raise error, "unterminated name"
                            if char == ">":
                                break
                            name = name + char
                        group = 1
                        if not isname(name):
                            raise error, "bad character in group name"
                    elif source.match("="):
                        # named backreference
                        name = ""
                        while 1:
                            char = source.get()
                            if char is None:
                                raise error, "unterminated name"
                            if char == ")":
                                break
                            name = name + char
                        if not isname(name):
                            raise error, "bad character in group name"
                        gid = state.groupdict.get(name)
                        if gid is None:
                            raise error, "unknown group name"
                        subpattern.append((GROUPREF, gid))
                        continue
                    else:
                        char = source.get()
                        if char is None:
                            raise error, "unexpected end of pattern"
                        raise error, "unknown specifier: ?P%s" % char
                elif source.match(":"):
                    # non-capturing group
                    group = 2
                elif source.match("#"):
                    # comment
                    while 1:
                        if source.next is None or source.next == ")":
                            break
                        source.get()
                    if not source.match(")"):
                        raise error, "unbalanced parenthesis"
                    continue
                elif source.next in ("=", "!", "<"):
                    # lookahead assertions
                    char = source.get()
                    dir = 1
                    if char == "<":
                        if source.next not in ("=", "!"):
                            raise error, "syntax error"
                        dir = -1 # lookbehind
                        char = source.get()
                    p = _parse_sub(source, state)
                    if not source.match(")"):
                        raise error, "unbalanced parenthesis"
                    if char == "=":
                        subpattern.append((ASSERT, (dir, p)))
                    else:
                        subpattern.append((ASSERT_NOT, (dir, p)))
                    continue
                else:
                    # flags
                    if not FLAGS.has_key(source.next):
                        raise error, "unexpected end of pattern"
                    while FLAGS.has_key(source.next):
                        state.flags = state.flags | FLAGS[source.get()]
            if group:
                # parse group contents
                if group == 2:
                    # anonymous group
                    group = None
                else:
                    group = state.opengroup(name)
                p = _parse_sub(source, state)
                if not source.match(")"):
                    raise error, "unbalanced parenthesis"
                if group is not None:
                    state.closegroup(group)
                subpattern.append((SUBPATTERN, (group, p)))
            else:
                while 1:
                    char = source.get()
                    if char is None:
                        raise error, "unexpected end of pattern"
                    if char == ")":
                        break
                    raise error, "unknown extension"

        elif this == "^":
            subpattern.append((AT, AT_BEGINNING))

        elif this == "$":
            subpattern.append((AT, AT_END))

        elif this and this[0] == "\\":
            code = _escape(source, this, state)
            subpattern.append(code)

        else:
            raise error, "parser error"

    return subpattern

def parse(str, flags=0, pattern=None):
    # parse 're' pattern into list of (opcode, argument) tuples

    source = Tokenizer(str)

    if pattern is None:
        pattern = Pattern()
    pattern.flags = flags
    pattern.str = str

    p = _parse_sub(source, pattern, 0)

    tail = source.get()
    if tail == ")":
        raise error, "unbalanced parenthesis"
    elif tail:
        raise error, "bogus characters at end of regular expression"

    if flags & SRE_FLAG_DEBUG:
        p.dump()

    if not (flags & SRE_FLAG_VERBOSE) and p.pattern.flags & SRE_FLAG_VERBOSE:
        # the VERBOSE flag was switched on inside the pattern.  to be
        # on the safe side, we'll parse the whole thing again...
        return parse(str, p.pattern.flags)

    return p

def parse_template(source, pattern):
    # parse 're' replacement string into list of literals and
    # group references
    s = Tokenizer(source)
    p = []
    a = p.append
    def literal(literal, p=p):
        if p and p[-1][0] is LITERAL:
            p[-1] = LITERAL, p[-1][1] + literal
        else:
            p.append((LITERAL, literal))
    sep = source[:0]
    if type(sep) is type(""):
        makechar = chr
    else:
        makechar = unichr
    while 1:
        this = s.get()
        if this is None:
            break # end of replacement string
        if this and this[0] == "\\":
            # group
            if this == "\\g":
                name = ""
                if s.match("<"):
                    while 1:
                        char = s.get()
                        if char is None:
                            raise error, "unterminated group name"
                        if char == ">":
                            break
                        name = name + char
                if not name:
                    raise error, "bad group name"
                try:
                    index = atoi(name)
                except ValueError:
                    if not isname(name):
                        raise error, "bad character in group name"
                    try:
                        index = pattern.groupindex[name]
                    except KeyError:
                        raise IndexError, "unknown group name"
                a((MARK, index))
            elif len(this) > 1 and this[1] in DIGITS:
                code = None
                while 1:
                    group = _group(this, pattern.groups+1)
                    if group:
                        if (s.next not in DIGITS or
                            not _group(this + s.next, pattern.groups+1)):
                            code = MARK, group
                            break
                    elif s.next in OCTDIGITS:
                        this = this + s.get()
                    else:
                        break
                if not code:
                    this = this[1:]
                    code = LITERAL, makechar(atoi(this[-6:], 8) & 0xff)
                if code[0] is LITERAL:
                    literal(code[1])
                else:
                    a(code)
            else:
                try:
                    this = makechar(ESCAPES[this][1])
                except KeyError:
                    pass
                literal(this)
        else:
            literal(this)
    # convert template to groups and literals lists
    i = 0
    groups = []
    literals = []
    for c, s in p:
        if c is MARK:
            groups.append((i, s))
            literals.append(None)
        else:
            literals.append(s)
        i = i + 1
    return groups, literals

def expand_template(template, match):
    g = match.group
    sep = match.string[:0]
    groups, literals = template
    literals = literals[:]
    try:
        for index, group in groups:
            literals[index] = s = g(group)
            if s is None:
                raise IndexError
    except IndexError:
        raise error, "empty group"
    return string.join(literals, sep)