lib-python.2.7.sgmllib.py Maven / Gradle / Ivy

Show more of this group Show more artifacts with this name
Show all versions of jython Show documentation
Jython is an implementation of the high-level, dynamic, object-oriented language Python written in 100% Pure Java, and seamlessly integrated with the Java platform. It thus allows you to run Python on any Java platform.
There is a newer version: 2.7.4
Show newest version
"""A parser for SGML, using the derived class as a static DTD."""

# XXX This only supports those SGML features used by HTML.

# XXX There should be a way to distinguish between PCDATA (parsed
# character data -- the normal case), RCDATA (replaceable character
# data -- only char and entity references and end tags are special)
# and CDATA (character data -- only end tags are special).  RCDATA is
# not supported at all.


from warnings import warnpy3k
warnpy3k("the sgmllib module has been removed in Python 3.0",
         stacklevel=2)
del warnpy3k

import markupbase
import re

__all__ = ["SGMLParser", "SGMLParseError"]

# Regular expressions used for parsing

interesting = re.compile('[&<]')
incomplete = re.compile('&([a-zA-Z][a-zA-Z0-9]*|#[0-9]*)?|'
                           '<([a-zA-Z][^<>]*|'
                              '/([a-zA-Z][^<>]*)?|'
                              '![^<>]*)?')

entityref = re.compile('&([a-zA-Z][-.a-zA-Z0-9]*)[^a-zA-Z0-9]')
charref = re.compile('&#([0-9]+)[^0-9]')

starttagopen = re.compile('<[>a-zA-Z]')
shorttagopen = re.compile('<[a-zA-Z][-.a-zA-Z0-9]*/')
shorttag = re.compile('<([a-zA-Z][-.a-zA-Z0-9]*)/([^/]*)/')
piclose = re.compile('>')
endbracket = re.compile('[<>]')
tagfind = re.compile('[a-zA-Z][-_.a-zA-Z0-9]*')
attrfind = re.compile(
    r'\s*([a-zA-Z_][-:.a-zA-Z_0-9]*)(\s*=\s*'
    r'(\'[^\']*\'|"[^"]*"|[][\-a-zA-Z0-9./,:;+*%?!&$\(\)_#=~\'"@]*))?')


class SGMLParseError(RuntimeError):
    """Exception raised for all parse errors."""
    pass


# SGML parser base class -- find tags and call handler functions.
# Usage: p = SGMLParser(); p.feed(data); ...; p.close().
# The dtd is defined by deriving a class which defines methods
# with special names to handle tags: start_foo and end_foo to handle
#  and , respectively, or do_foo to handle  by itself.
# (Tags are converted to lower case for this purpose.)  The data
# between tags is passed to the parser by calling self.handle_data()
# with some data as argument (the data may be split up in arbitrary
# chunks).  Entity references are passed by calling
# self.handle_entityref() with the entity reference as argument.

class SGMLParser(markupbase.ParserBase):
    # Definition of entities -- derived classes may override
    entity_or_charref = re.compile('&(?:'
      '([a-zA-Z][-.a-zA-Z0-9]*)|#([0-9]+)'
      ')(;?)')

    def __init__(self, verbose=0):
        """Initialize and reset this instance."""
        self.verbose = verbose
        self.reset()

    def reset(self):
        """Reset this instance. Loses all unprocessed data."""
        self.__starttag_text = None
        self.rawdata = ''
        self.stack = []
        self.lasttag = '???'
        self.nomoretags = 0
        self.literal = 0
        markupbase.ParserBase.reset(self)

    def setnomoretags(self):
        """Enter literal mode (CDATA) till EOF.

        Intended for derived classes only.
        """
        self.nomoretags = self.literal = 1

    def setliteral(self, *args):
        """Enter literal mode (CDATA).

        Intended for derived classes only.
        """
        self.literal = 1

    def feed(self, data):
        """Feed some data to the parser.

        Call this as often as you want, with as little or as much text
        as you want (may include '\n').  (This just saves the text,
        all the processing is done by goahead().)
        """

        self.rawdata = self.rawdata + data
        self.goahead(0)

    def close(self):
        """Handle the remaining data."""
        self.goahead(1)

    def error(self, message):
        raise SGMLParseError(message)

    # Internal -- handle data as far as reasonable.  May leave state
    # and data to be processed by a subsequent call.  If 'end' is
    # true, force handling all data as if followed by EOF marker.
    def goahead(self, end):
        rawdata = self.rawdata
        i = 0
        n = len(rawdata)
        while i < n:
            if self.nomoretags:
                self.handle_data(rawdata[i:n])
                i = n
                break
            match = interesting.search(rawdata, i)
            if match: j = match.start()
            else: j = n
            if i < j:
                self.handle_data(rawdata[i:j])
            i = j
            if i == n: break
            if rawdata[i] == '<':
                if starttagopen.match(rawdata, i):
                    if self.literal:
                        self.handle_data(rawdata[i])
                        i = i+1
                        continue
                    k = self.parse_starttag(i)
                    if k < 0: break
                    i = k
                    continue
                if rawdata.startswith(" (i + 1):
                        self.handle_data("<")
                        i = i+1
                    else:
                        # incomplete
                        break
                    continue
                if rawdata.startswith("