cpython/Lib/html/parser.py

"""A parser for HTML and XHTML."""

# This file is based on sgmllib.py, but the API is slightly different.

# 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).


import re
import warnings
import _markupbase

from html import unescape


__all__ = ['HTMLParser']

# Regular expressions used for parsing

interesting_normal = re.compile('[&<]')
incomplete = re.compile('&[a-zA-Z#]')

entityref = re.compile('&([a-zA-Z][-.a-zA-Z0-9]*)[^a-zA-Z0-9]')
charref = re.compile('&#(?:[0-9]+|[xX][0-9a-fA-F]+)[^0-9a-fA-F]')

starttagopen = re.compile('<[a-zA-Z]')
piclose = re.compile('>')
commentclose = re.compile(r'--\s*>')
# Note:
#  1) the strict attrfind isn't really strict, but we can't make it
#     correctly strict without breaking backward compatibility;
#  2) if you change tagfind/attrfind remember to update locatestarttagend too;
#  3) if you change tagfind/attrfind and/or locatestarttagend the parser will
#     explode, so don't do it.
tagfind = re.compile('([a-zA-Z][-.a-zA-Z0-9:_]*)(?:\s|/(?!>))*')
# see http://www.w3.org/TR/html5/tokenization.html#tag-open-state
# and http://www.w3.org/TR/html5/tokenization.html#tag-name-state
tagfind_tolerant = re.compile('([a-zA-Z][^\t\n\r\f />\x00]*)(?:\s|/(?!>))*')
attrfind = re.compile(
    r'\s*([a-zA-Z_][-.:a-zA-Z_0-9]*)(\s*=\s*'
    r'(\'[^\']*\'|"[^"]*"|[^\s"\'=<>`]*))?')
attrfind_tolerant = re.compile(
    r'((?<=[\'"\s/])[^\s/>][^\s/=>]*)(\s*=+\s*'
    r'(\'[^\']*\'|"[^"]*"|(?![\'"])[^>\s]*))?(?:\s|/(?!>))*')
locatestarttagend = re.compile(r"""
  <[a-zA-Z][-.a-zA-Z0-9:_]*          # tag name
  (?:\s+                             # whitespace before attribute name
    (?:[a-zA-Z_][-.:a-zA-Z0-9_]*     # attribute name
      (?:\s*=\s*                     # value indicator
        (?:'[^']*'                   # LITA-enclosed value
          |\"[^\"]*\"                # LIT-enclosed value
          |[^'\">\s]+                # bare value
         )
       )?
     )
   )*
  \s*                                # trailing whitespace
""", re.VERBOSE)
locatestarttagend_tolerant = re.compile(r"""
  <[a-zA-Z][^\t\n\r\f />\x00]*       # tag name
  (?:[\s/]*                          # optional whitespace before attribute name
    (?:(?<=['"\s/])[^\s/>][^\s/=>]*  # attribute name
      (?:\s*=+\s*                    # value indicator
        (?:'[^']*'                   # LITA-enclosed value
          |"[^"]*"                   # LIT-enclosed value
          |(?!['"])[^>\s]*           # bare value
         )
         (?:\s*,)*                   # possibly followed by a comma
       )?(?:\s|/(?!>))*
     )*
   )?
  \s*                                # trailing whitespace
""", re.VERBOSE)
endendtag = re.compile('>')
# the HTML 5 spec, section 8.1.2.2, doesn't allow spaces between
# </ and the tag name, so maybe this should be fixed
endtagfind = re.compile('</\s*([a-zA-Z][-.a-zA-Z0-9:_]*)\s*>')


class HTMLParseError(Exception):
    """Exception raised for all parse errors."""

    def __init__(self, msg, position=(None, None)):
        assert msg
        self.msg = msg
        self.lineno = position[0]
        self.offset = position[1]

    def __str__(self):
        result = self.msg
        if self.lineno is not None:
            result = result + ", at line %d" % self.lineno
        if self.offset is not None:
            result = result + ", column %d" % (self.offset + 1)
        return result


_default_sentinel = object()

class HTMLParser(_markupbase.ParserBase):
    """Find tags and other markup and call handler functions.

    Usage:
        p = HTMLParser()
        p.feed(data)
        ...
        p.close()

    Start tags are handled by calling self.handle_starttag() or
    self.handle_startendtag(); end tags by self.handle_endtag().  The
    data between tags is passed from the parser to the derived class
    by calling self.handle_data() with the data as argument (the data
    may be split up in arbitrary chunks).  If convert_charrefs is
    True the character references are converted automatically to the
    corresponding Unicode character (and self.handle_data() is no
    longer split in chunks), otherwise they are passed by calling
    self.handle_entityref() or self.handle_charref() with the string
    containing respectively the named or numeric reference as the
    argument.
    """

    CDATA_CONTENT_ELEMENTS = ("script", "style")

    def __init__(self, strict=_default_sentinel, *,
                 convert_charrefs=_default_sentinel):
        """Initialize and reset this instance.

        If convert_charrefs is True (default: False), all character references
        are automatically converted to the corresponding Unicode characters.
        If strict is set to False (the default) the parser will parse invalid
        markup, otherwise it will raise an error.  Note that the strict mode
        and argument are deprecated.
        """
        if strict is not _default_sentinel:
            warnings.warn("The strict argument and mode are deprecated.",
                          DeprecationWarning, stacklevel=2)
        else:
            strict = False  # default
        self.strict = strict
        if convert_charrefs is _default_sentinel:
            convert_charrefs = False  # default
            warnings.warn("The value of convert_charrefs will become True in "
                          "3.5. You are encouraged to set the value explicitly.",
                          DeprecationWarning, stacklevel=2)
        self.convert_charrefs = convert_charrefs
        self.reset()

    def reset(self):
        """Reset this instance.  Loses all unprocessed data."""
        self.rawdata = ''
        self.lasttag = '???'
        self.interesting = interesting_normal
        self.cdata_elem = None
        _markupbase.ParserBase.reset(self)

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

        Call this as often as you want, with as little or as much text
        as you want (may include '\n').
        """
        self.rawdata = self.rawdata + data
        self.goahead(0)

    def close(self):
        """Handle any buffered data."""
        self.goahead(1)

    def error(self, message):
        warnings.warn("The 'error' method is deprecated.",
                      DeprecationWarning, stacklevel=2)
        raise HTMLParseError(message, self.getpos())

    __starttag_text = None

    def get_starttag_text(self):
        """Return full source of start tag: '<...>'."""
        return self.__starttag_text

    def set_cdata_mode(self, elem):
        self.cdata_elem = elem.lower()
        self.interesting = re.compile(r'</\s*%s\s*>' % self.cdata_elem, re.I)

    def clear_cdata_mode(self):
        self.interesting = interesting_normal
        self.cdata_elem = None

    # 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.convert_charrefs and not self.cdata_elem:
                j = rawdata.find('<', i)
                if j < 0:
                    if not end:
                        break  # wait till we get all the text
                    j = n
            else:
                match = self.interesting.search(rawdata, i)  # < or &
                if match:
                    j = match.start()
                else:
                    if self.cdata_elem:
                        break
                    j = n
            if i < j:
                if self.convert_charrefs and not self.cdata_elem:
                    self.handle_data(unescape(rawdata[i:j]))
                else:
                    self.handle_data(rawdata[i:j])
            i = self.updatepos(i, j)
            if i == n: break
            startswith = rawdata.startswith
            if startswith('<', i):
                if starttagopen.match(rawdata, i): # < + letter
                    k = self.parse_starttag(i)
                elif startswith("</", i):
                    k = self.parse_endtag(i)
                elif startswith("<!--", i):
                    k = self.parse_comment(i)
                elif startswith("<?", i):
                    k = self.parse_pi(i)
                elif startswith("<!", i):
                    if self.strict:
                        k = self.parse_declaration(i)
                    else:
                        k = self.parse_html_declaration(i)
                elif (i + 1) < n:
                    self.handle_data("<")
                    k = i + 1
                else:
                    break
                if k < 0:
                    if not end:
                        break
                    if self.strict:
                        self.error("EOF in middle of construct")
                    k = rawdata.find('>', i + 1)
                    if k < 0:
                        k = rawdata.find('<', i + 1)
                        if k < 0:
                            k = i + 1
                    else:
                        k += 1
                    if self.convert_charrefs and not self.cdata_elem:
                        self.handle_data(unescape(rawdata[i:k]))
                    else:
                        self.handle_data(rawdata[i:k])
                i = self.updatepos(i, k)
            elif startswith("&#", i):
                match = charref.match(rawdata, i)
                if match:
                    name = match.group()[2:-1]
                    self.handle_charref(name)
                    k = match.end()
                    if not startswith(';', k-1):
                        k = k - 1
                    i = self.updatepos(i, k)
                    continue
                else:
                    if ";" in rawdata[i:]:  # bail by consuming &#
                        self.handle_data(rawdata[i:i+2])
                        i = self.updatepos(i, i+2)
                    break
            elif startswith('&', i):
                match = entityref.match(rawdata, i)
                if match:
                    name = match.group(1)
                    self.handle_entityref(name)
                    k = match.end()
                    if not startswith(';', k-1):
                        k = k - 1
                    i = self.updatepos(i, k)
                    continue
                match = incomplete.match(rawdata, i)
                if match:
                    # match.group() will contain at least 2 chars
                    if end and match.group() == rawdata[i:]:
                        if self.strict:
                            self.error("EOF in middle of entity or char ref")
                        else:
                            k = match.end()
                            if k <= i:
                                k = n
                            i = self.updatepos(i, i + 1)
                    # incomplete
                    break
                elif (i + 1) < n:
                    # not the end of the buffer, and can't be confused
                    # with some other construct
                    self.handle_data("&")
                    i = self.updatepos(i, i + 1)
                else:
                    break
            else:
                assert 0, "interesting.search() lied"
        # end while
        if end and i < n and not self.cdata_elem:
            if self.convert_charrefs and not self.cdata_elem:
                self.handle_data(unescape(rawdata[i:n]))
            else:
                self.handle_data(rawdata[i:n])
            i = self.updatepos(i, n)
        self.rawdata = rawdata[i:]

    # Internal -- parse html declarations, return length or -1 if not terminated
    # See w3.org/TR/html5/tokenization.html#markup-declaration-open-state
    # See also parse_declaration in _markupbase
    def parse_html_declaration(self, i):
        rawdata = self.rawdata
        assert rawdata[i:i+2] == '<!', ('unexpected call to '
                                        'parse_html_declaration()')
        if rawdata[i:i+4] == '<!--':
            # this case is actually already handled in goahead()
            return self.parse_comment(i)
        elif rawdata[i:i+3] == '<![':
            return self.parse_marked_section(i)
        elif rawdata[i:i+9].lower() == '<!doctype':
            # find the closing >
            gtpos = rawdata.find('>', i+9)
            if gtpos == -1:
                return -1
            self.handle_decl(rawdata[i+2:gtpos])
            return gtpos+1
        else:
            return self.parse_bogus_comment(i)

    # Internal -- parse bogus comment, return length or -1 if not terminated
    # see http://www.w3.org/TR/html5/tokenization.html#bogus-comment-state
    def parse_bogus_comment(self, i, report=1):
        rawdata = self.rawdata
        assert rawdata[i:i+2] in ('<!', '</'), ('unexpected call to '
                                                'parse_comment()')
        pos = rawdata.find('>', i+2)
        if pos == -1:
            return -1
        if report:
            self.handle_comment(rawdata[i+2:pos])
        return pos + 1

    # Internal -- parse processing instr, return end or -1 if not terminated
    def parse_pi(self, i):
        rawdata = self.rawdata
        assert rawdata[i:i+2] == '<?', 'unexpected call to parse_pi()'
        match = piclose.search(rawdata, i+2) # >
        if not match:
            return -1
        j = match.start()
        self.handle_pi(rawdata[i+2: j])
        j = match.end()
        return j

    # Internal -- handle starttag, return end or -1 if not terminated
    def parse_starttag(self, i):
        self.__starttag_text = None
        endpos = self.check_for_whole_start_tag(i)
        if endpos < 0:
            return endpos
        rawdata = self.rawdata
        self.__starttag_text = rawdata[i:endpos]

        # Now parse the data between i+1 and j into a tag and attrs
        attrs = []
        if self.strict:
            match = tagfind.match(rawdata, i+1)
        else:
            match = tagfind_tolerant.match(rawdata, i+1)
        assert match, 'unexpected call to parse_starttag()'
        k = match.end()
        self.lasttag = tag = match.group(1).lower()
        while k < endpos:
            if self.strict:
                m = attrfind.match(rawdata, k)
            else:
                m = attrfind_tolerant.match(rawdata, k)
            if not m:
                break
            attrname, rest, attrvalue = m.group(1, 2, 3)
            if not rest:
                attrvalue = None
            elif attrvalue[:1] == '\'' == attrvalue[-1:] or \
                 attrvalue[:1] == '"' == attrvalue[-1:]:
                attrvalue = attrvalue[1:-1]
            if attrvalue:
                attrvalue = unescape(attrvalue)
            attrs.append((attrname.lower(), attrvalue))
            k = m.end()

        end = rawdata[k:endpos].strip()
        if end not in (">", "/>"):
            lineno, offset = self.getpos()
            if "\n" in self.__starttag_text:
                lineno = lineno + self.__starttag_text.count("\n")
                offset = len(self.__starttag_text) \
                         - self.__starttag_text.rfind("\n")
            else:
                offset = offset + len(self.__starttag_text)
            if self.strict:
                self.error("junk characters in start tag: %r"
                           % (rawdata[k:endpos][:20],))
            self.handle_data(rawdata[i:endpos])
            return endpos
        if end.endswith('/>'):
            # XHTML-style empty tag: <span attr="value" />
            self.handle_startendtag(tag, attrs)
        else:
            self.handle_starttag(tag, attrs)
            if tag in self.CDATA_CONTENT_ELEMENTS:
                self.set_cdata_mode(tag)
        return endpos

    # Internal -- check to see if we have a complete starttag; return end
    # or -1 if incomplete.
    def check_for_whole_start_tag(self, i):
        rawdata = self.rawdata
        if self.strict:
            m = locatestarttagend.match(rawdata, i)
        else:
            m = locatestarttagend_tolerant.match(rawdata, i)
        if m:
            j = m.end()
            next = rawdata[j:j+1]
            if next == ">":
                return j + 1
            if next == "/":
                if rawdata.startswith("/>", j):
                    return j + 2
                if rawdata.startswith("/", j):
                    # buffer boundary
                    return -1
                # else bogus input
                if self.strict:
                    self.updatepos(i, j + 1)
                    self.error("malformed empty start tag")
                if j > i:
                    return j
                else:
                    return i + 1
            if next == "":
                # end of input
                return -1
            if next in ("abcdefghijklmnopqrstuvwxyz=/"
                        "ABCDEFGHIJKLMNOPQRSTUVWXYZ"):
                # end of input in or before attribute value, or we have the
                # '/' from a '/>' ending
                return -1
            if self.strict:
                self.updatepos(i, j)
                self.error("malformed start tag")
            if j > i:
                return j
            else:
                return i + 1
        raise AssertionError("we should not get here!")

    # Internal -- parse endtag, return end or -1 if incomplete
    def parse_endtag(self, i):
        rawdata = self.rawdata
        assert rawdata[i:i+2] == "</", "unexpected call to parse_endtag"
        match = endendtag.search(rawdata, i+1) # >
        if not match:
            return -1
        gtpos = match.end()
        match = endtagfind.match(rawdata, i) # </ + tag + >
        if not match:
            if self.cdata_elem is not None:
                self.handle_data(rawdata[i:gtpos])
                return gtpos
            if self.strict:
                self.error("bad end tag: %r" % (rawdata[i:gtpos],))
            # find the name: w3.org/TR/html5/tokenization.html#tag-name-state
            namematch = tagfind_tolerant.match(rawdata, i+2)
            if not namematch:
                # w3.org/TR/html5/tokenization.html#end-tag-open-state
                if rawdata[i:i+3] == '</>':
                    return i+3
                else:
                    return self.parse_bogus_comment(i)
            tagname = namematch.group(1).lower()
            # consume and ignore other stuff between the name and the >
            # Note: this is not 100% correct, since we might have things like
            # </tag attr=">">, but looking for > after tha name should cover
            # most of the cases and is much simpler
            gtpos = rawdata.find('>', namematch.end())
            self.handle_endtag(tagname)
            return gtpos+1

        elem = match.group(1).lower() # script or style
        if self.cdata_elem is not None:
            if elem != self.cdata_elem:
                self.handle_data(rawdata[i:gtpos])
                return gtpos

        self.handle_endtag(elem.lower())
        self.clear_cdata_mode()
        return gtpos

    # Overridable -- finish processing of start+end tag: <tag.../>
    def handle_startendtag(self, tag, attrs):
        self.handle_starttag(tag, attrs)
        self.handle_endtag(tag)

    # Overridable -- handle start tag
    def handle_starttag(self, tag, attrs):
        pass

    # Overridable -- handle end tag
    def handle_endtag(self, tag):
        pass

    # Overridable -- handle character reference
    def handle_charref(self, name):
        pass

    # Overridable -- handle entity reference
    def handle_entityref(self, name):
        pass

    # Overridable -- handle data
    def handle_data(self, data):
        pass

    # Overridable -- handle comment
    def handle_comment(self, data):
        pass

    # Overridable -- handle declaration
    def handle_decl(self, decl):
        pass

    # Overridable -- handle processing instruction
    def handle_pi(self, data):
        pass

    def unknown_decl(self, data):
        if self.strict:
            self.error("unknown declaration: %r" % (data,))

    # Internal -- helper to remove special character quoting
    def unescape(self, s):
        warnings.warn('The unescape method is deprecated and will be removed '
                      'in 3.5, use html.unescape() instead.',
                      DeprecationWarning, stacklevel=2)
        return unescape(s)