FM / python3.3

/opt/alt/python33/lib64/python3.3

Name	Size	Mode	Actions
collections/	-	0755	rm
concurrent/	-	0755	rm
config-3.3m/	-	0755	rm
ctypes/	-	0755	rm
curses/	-	0755	rm
dbm/	-	0755	rm
distutils/	-	0755	rm
email/	-	0755	rm
encodings/	-	0755	rm
html/	-	0755	rm
http/	-	0755	rm
idlelib/	-	0755	rm
importlib/	-	0755	rm
json/	-	0755	rm
lib-dynload/	-	0755	rm
lib2to3/	-	0755	rm
logging/	-	0755	rm
multiprocessing/	-	0755	rm
plat-linux/	-	0755	rm
pydoc_data/	-	0755	rm
site-packages/	-	0755	rm
sqlite3/	-	0755	rm
test/	-	0755	rm
unittest/	-	0755	rm
urllib/	-	0755	rm
venv/	-	0755	rm
wsgiref/	-	0755	rm
xml/	-	0755	rm
xmlrpc/	-	0755	rm
__pycache__/	-	0755	rm
abc.py	8057	0644	edit dl rm
aifc.py	31054	0644	edit dl rm
antigravity.py	475	0644	edit dl rm
argparse.py	89069	0644	edit dl rm
ast.py	12142	0644	edit dl rm
asynchat.py	11588	0644	edit dl rm
asyncore.py	20753	0644	edit dl rm
base64.py	13986	0755	edit dl rm
bdb.py	21894	0644	edit dl rm
binhex.py	13708	0644	edit dl rm
bisect.py	2595	0644	edit dl rm
bz2.py	18473	0644	edit dl rm
calendar.py	22940	0644	edit dl rm
cgi.py	35554	0755	edit dl rm
cgitb.py	12041	0644	edit dl rm
chunk.py	5377	0644	edit dl rm
cmd.py	14860	0644	edit dl rm
code.py	10030	0644	edit dl rm
codecs.py	35956	0644	edit dl rm
codeop.py	5994	0644	edit dl rm
colorsys.py	3691	0644	edit dl rm
compileall.py	9743	0644	edit dl rm
configparser.py	49437	0644	edit dl rm
contextlib.py	9125	0644	edit dl rm
copy.py	8991	0644	edit dl rm
copyreg.py	6611	0644	edit dl rm
cProfile.py	6361	0755	edit dl rm
crypt.py	1879	0644	edit dl rm
csv.py	16185	0644	edit dl rm
datetime.py	74954	0644	edit dl rm
decimal.py	228558	0644	edit dl rm
difflib.py	82519	0644	edit dl rm
dis.py	10134	0644	edit dl rm
doctest.py	102933	0644	edit dl rm
dummy_threading.py	2815	0644	edit dl rm
filecmp.py	9597	0644	edit dl rm
fileinput.py	14256	0644	edit dl rm
fnmatch.py	3163	0644	edit dl rm
formatter.py	14930	0644	edit dl rm
fractions.py	23033	0644	edit dl rm
ftplib.py	40253	0644	edit dl rm
functools.py	13596	0644	edit dl rm
genericpath.py	3093	0644	edit dl rm
getopt.py	7488	0644	edit dl rm
getpass.py	5793	0644	edit dl rm
gettext.py	20637	0644	edit dl rm
glob.py	2838	0644	edit dl rm
gzip.py	24403	0644	edit dl rm
hashlib.py	6193	0644	edit dl rm
heapq.py	17997	0644	edit dl rm
hmac.py	4440	0644	edit dl rm
imaplib.py	50111	0644	edit dl rm
imghdr.py	3528	0644	edit dl rm
imp.py	9727	0644	edit dl rm
inspect.py	78960	0644	edit dl rm
io.py	3280	0644	edit dl rm
ipaddress.py	70303	0644	edit dl rm
keyword.py	2060	0755	edit dl rm
linecache.py	3864	0644	edit dl rm
locale.py	93215	0644	edit dl rm
lzma.py	17454	0644	edit dl rm
macpath.py	5617	0644	edit dl rm
macurl2path.py	2732	0644	edit dl rm
mailbox.py	79093	0644	edit dl rm
mailcap.py	7437	0644	edit dl rm
mimetypes.py	20735	0644	edit dl rm
modulefinder.py	23198	0644	edit dl rm
netrc.py	5747	0644	edit dl rm
nntplib.py	42786	0644	edit dl rm
ntpath.py	20437	0644	edit dl rm
nturl2path.py	2396	0644	edit dl rm
numbers.py	10398	0644	edit dl rm
opcode.py	5098	0644	edit dl rm
optparse.py	60346	0644	edit dl rm
os.py	34779	0644	edit dl rm
os2emxpath.py	4659	0644	edit dl rm
pdb.py	60653	0755	edit dl rm
pickle.py	47858	0644	edit dl rm
pickletools.py	81349	0644	edit dl rm
pipes.py	8916	0644	edit dl rm
pkgutil.py	21539	0644	edit dl rm
platform.py	50742	0755	edit dl rm
plistlib.py	14777	0644	edit dl rm
poplib.py	11372	0644	edit dl rm
posixpath.py	14254	0644	edit dl rm
pprint.py	12700	0644	edit dl rm
profile.py	21448	0755	edit dl rm
pstats.py	26372	0644	edit dl rm
pty.py	5055	0644	edit dl rm
pyclbr.py	13438	0644	edit dl rm
pydoc.py	101644	0755	edit dl rm
py_compile.py	6717	0644	edit dl rm
queue.py	8835	0644	edit dl rm
quopri.py	7315	0755	edit dl rm
random.py	25660	0644	edit dl rm
re.py	14973	0644	edit dl rm
reprlib.py	5110	0644	edit dl rm
rlcompleter.py	5526	0644	edit dl rm
runpy.py	10413	0644	edit dl rm
sched.py	6399	0644	edit dl rm
shelve.py	8243	0644	edit dl rm
shlex.py	11502	0644	edit dl rm
shutil.py	39147	0644	edit dl rm
site.py	21971	0644	edit dl rm
smtpd.py	30207	0755	edit dl rm
smtplib.py	38021	0755	edit dl rm
sndhdr.py	6219	0644	edit dl rm
socket.py	14913	0644	edit dl rm
socketserver.py	24196	0644	edit dl rm
sre_compile.py	16345	0644	edit dl rm
sre_constants.py	7231	0644	edit dl rm
sre_parse.py	30212	0644	edit dl rm
ssl.py	24478	0644	edit dl rm
stat.py	4304	0644	edit dl rm
string.py	9410	0644	edit dl rm
stringprep.py	12917	0644	edit dl rm
struct.py	238	0644	edit dl rm
subprocess.py	67578	0644	edit dl rm
sunau.py	17523	0644	edit dl rm
symbol.py	2051	0755	edit dl rm
symtable.py	7383	0644	edit dl rm
sysconfig.py	25174	0644	edit dl rm
tabnanny.py	11410	0755	edit dl rm
tarfile.py	88864	0755	edit dl rm
telnetlib.py	27349	0644	edit dl rm
tempfile.py	23013	0644	edit dl rm
textwrap.py	16488	0644	edit dl rm
this.py	1003	0644	edit dl rm
threading.py	45641	0644	edit dl rm
timeit.py	12395	0755	edit dl rm
token.py	3034	0644	edit dl rm
tokenize.py	24876	0644	edit dl rm
trace.py	31487	0755	edit dl rm
traceback.py	11982	0644	edit dl rm
tty.py	879	0644	edit dl rm
types.py	3167	0644	edit dl rm
uu.py	6766	0755	edit dl rm
uuid.py	22349	0644	edit dl rm
warnings.py	13825	0644	edit dl rm
wave.py	18579	0644	edit dl rm
weakref.py	11495	0644	edit dl rm
webbrowser.py	22913	0755	edit dl rm
xdrlib.py	5381	0644	edit dl rm
zipfile.py	66424	0644	edit dl rm
_compat_pickle.py	4338	0644	edit dl rm
_dummy_thread.py	4769	0644	edit dl rm
_markupbase.py	14598	0644	edit dl rm
_osx_support.py	18855	0644	edit dl rm
_pyio.py	72905	0644	edit dl rm
_strptime.py	21674	0644	edit dl rm
_sysconfigdata.py	21056	0644	edit dl rm
_threading_local.py	7410	0644	edit dl rm
_weakrefset.py	5705	0644	edit dl rm
__future__.py	4584	0644	edit dl rm
__phello__.foo.py	64	0644	edit dl rm

Edit: /opt/alt/python33/lib64/python3.3/_markupbase.py (14598B)

"""Shared support for scanning document type declarations in HTML and XHTML.

This module is used as a foundation for the html.parser module.  It has no
documented public API and should not be used directly.

"""

import re

_declname_match = re.compile(r'[a-zA-Z][-_.a-zA-Z0-9]*\s*').match
_declstringlit_match = re.compile(r'(\'[^\']*\'|"[^"]*")\s*').match
_commentclose = re.compile(r'--\s*>')
_markedsectionclose = re.compile(r']\s*]\s*>')

# An analysis of the MS-Word extensions is available at
# http://www.planetpublish.com/xmlarena/xap/Thursday/WordtoXML.pdf

_msmarkedsectionclose = re.compile(r']\s*>')

del re

class ParserBase:
    """Parser base class which provides some common support methods used
    by the SGML/HTML and XHTML parsers."""

def __init__(self):
        if self.__class__ is ParserBase:
            raise RuntimeError(
                "_markupbase.ParserBase must be subclassed")

def error(self, message):
        raise NotImplementedError(
            "subclasses of ParserBase must override error()")

def reset(self):
        self.lineno = 1
        self.offset = 0

def getpos(self):
        """Return current line number and offset."""
        return self.lineno, self.offset

# Internal -- update line number and offset.  This should be
    # called for each piece of data exactly once, in order -- in other
    # words the concatenation of all the input strings to this
    # function should be exactly the entire input.
    def updatepos(self, i, j):
        if i >= j:
            return j
        rawdata = self.rawdata
        nlines = rawdata.count("\n", i, j)
        if nlines:
            self.lineno = self.lineno + nlines
            pos = rawdata.rindex("\n", i, j) # Should not fail
            self.offset = j-(pos+1)
        else:
            self.offset = self.offset + j-i
        return j

_decl_otherchars = ''

# Internal -- parse declaration (for use by subclasses).
    def parse_declaration(self, i):
        # This is some sort of declaration; in "HTML as
        # deployed," this should only be the document type
        # declaration ("<!DOCTYPE html...>").
        # ISO 8879:1986, however, has more complex
        # declaration syntax for elements in <!...>, including:
        # --comment--
        # [marked section]
        # name in the following list: ENTITY, DOCTYPE, ELEMENT,
        # ATTLIST, NOTATION, SHORTREF, USEMAP,
        # LINKTYPE, LINK, IDLINK, USELINK, SYSTEM
        rawdata = self.rawdata
        j = i + 2
        assert rawdata[i:j] == "<!", "unexpected call to parse_declaration"
        if rawdata[j:j+1] == ">":
            # the empty comment <!>
            return j + 1
        if rawdata[j:j+1] in ("-", ""):
            # Start of comment followed by buffer boundary,
            # or just a buffer boundary.
            return -1
        # A simple, practical version could look like: ((name|stringlit) S*) + '>'
        n = len(rawdata)
        if rawdata[j:j+2] == '--': #comment
            # Locate --.*-- as the body of the comment
            return self.parse_comment(i)
        elif rawdata[j] == '[': #marked section
            # Locate [statusWord [...arbitrary SGML...]] as the body of the marked section
            # Where statusWord is one of TEMP, CDATA, IGNORE, INCLUDE, RCDATA
            # Note that this is extended by Microsoft Office "Save as Web" function
            # to include [if...] and [endif].
            return self.parse_marked_section(i)
        else: #all other declaration elements
            decltype, j = self._scan_name(j, i)
        if j < 0:
            return j
        if decltype == "doctype":
            self._decl_otherchars = ''
        while j < n:
            c = rawdata[j]
            if c == ">":
                # end of declaration syntax
                data = rawdata[i+2:j]
                if decltype == "doctype":
                    self.handle_decl(data)
                else:
                    # According to the HTML5 specs sections "8.2.4.44 Bogus
                    # comment state" and "8.2.4.45 Markup declaration open
                    # state", a comment token should be emitted.
                    # Calling unknown_decl provides more flexibility though.
                    self.unknown_decl(data)
                return j + 1
            if c in "\"'":
                m = _declstringlit_match(rawdata, j)
                if not m:
                    return -1 # incomplete
                j = m.end()
            elif c in "abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ":
                name, j = self._scan_name(j, i)
            elif c in self._decl_otherchars:
                j = j + 1
            elif c == "[":
                # this could be handled in a separate doctype parser
                if decltype == "doctype":
                    j = self._parse_doctype_subset(j + 1, i)
                elif decltype in {"attlist", "linktype", "link", "element"}:
                    # must tolerate []'d groups in a content model in an element declaration
                    # also in data attribute specifications of attlist declaration
                    # also link type declaration subsets in linktype declarations
                    # also link attribute specification lists in link declarations
                    self.error("unsupported '[' char in %s declaration" % decltype)
                else:
                    self.error("unexpected '[' char in declaration")
            else:
                self.error(
                    "unexpected %r char in declaration" % rawdata[j])
            if j < 0:
                return j
        return -1 # incomplete

# Internal -- parse a marked section
    # Override this to handle MS-word extension syntax <![if word]>content<![endif]>
    def parse_marked_section(self, i, report=1):
        rawdata= self.rawdata
        assert rawdata[i:i+3] == '<![', "unexpected call to parse_marked_section()"
        sectName, j = self._scan_name( i+3, i )
        if j < 0:
            return j
        if sectName in {"temp", "cdata", "ignore", "include", "rcdata"}:
            # look for standard ]]> ending
            match= _markedsectionclose.search(rawdata, i+3)
        elif sectName in {"if", "else", "endif"}:
            # look for MS Office ]> ending
            match= _msmarkedsectionclose.search(rawdata, i+3)
        else:
            self.error('unknown status keyword %r in marked section' % rawdata[i+3:j])
        if not match:
            return -1
        if report:
            j = match.start(0)
            self.unknown_decl(rawdata[i+3: j])
        return match.end(0)

# Internal -- parse comment, return length or -1 if not terminated
    def parse_comment(self, i, report=1):
        rawdata = self.rawdata
        if rawdata[i:i+4] != '<!--':
            self.error('unexpected call to parse_comment()')
        match = _commentclose.search(rawdata, i+4)
        if not match:
            return -1
        if report:
            j = match.start(0)
            self.handle_comment(rawdata[i+4: j])
        return match.end(0)

# Internal -- scan past the internal subset in a <!DOCTYPE declaration,
    # returning the index just past any whitespace following the trailing ']'.
    def _parse_doctype_subset(self, i, declstartpos):
        rawdata = self.rawdata
        n = len(rawdata)
        j = i
        while j < n:
            c = rawdata[j]
            if c == "<":
                s = rawdata[j:j+2]
                if s == "<":
                    # end of buffer; incomplete
                    return -1
                if s != "<!":
                    self.updatepos(declstartpos, j + 1)
                    self.error("unexpected char in internal subset (in %r)" % s)
                if (j + 2) == n:
                    # end of buffer; incomplete
                    return -1
                if (j + 4) > n:
                    # end of buffer; incomplete
                    return -1
                if rawdata[j:j+4] == "<!--":
                    j = self.parse_comment(j, report=0)
                    if j < 0:
                        return j
                    continue
                name, j = self._scan_name(j + 2, declstartpos)
                if j == -1:
                    return -1
                if name not in {"attlist", "element", "entity", "notation"}:
                    self.updatepos(declstartpos, j + 2)
                    self.error(
                        "unknown declaration %r in internal subset" % name)
                # handle the individual names
                meth = getattr(self, "_parse_doctype_" + name)
                j = meth(j, declstartpos)
                if j < 0:
                    return j
            elif c == "%":
                # parameter entity reference
                if (j + 1) == n:
                    # end of buffer; incomplete
                    return -1
                s, j = self._scan_name(j + 1, declstartpos)
                if j < 0:
                    return j
                if rawdata[j] == ";":
                    j = j + 1
            elif c == "]":
                j = j + 1
                while j < n and rawdata[j].isspace():
                    j = j + 1
                if j < n:
                    if rawdata[j] == ">":
                        return j
                    self.updatepos(declstartpos, j)
                    self.error("unexpected char after internal subset")
                else:
                    return -1
            elif c.isspace():
                j = j + 1
            else:
                self.updatepos(declstartpos, j)
                self.error("unexpected char %r in internal subset" % c)
        # end of buffer reached
        return -1

# Internal -- scan past <!ELEMENT declarations
    def _parse_doctype_element(self, i, declstartpos):
        name, j = self._scan_name(i, declstartpos)
        if j == -1:
            return -1
        # style content model; just skip until '>'
        rawdata = self.rawdata
        if '>' in rawdata[j:]:
            return rawdata.find(">", j) + 1
        return -1

# Internal -- scan past <!ATTLIST declarations
    def _parse_doctype_attlist(self, i, declstartpos):
        rawdata = self.rawdata
        name, j = self._scan_name(i, declstartpos)
        c = rawdata[j:j+1]
        if c == "":
            return -1
        if c == ">":
            return j + 1
        while 1:
            # scan a series of attribute descriptions; simplified:
            #   name type [value] [#constraint]
            name, j = self._scan_name(j, declstartpos)
            if j < 0:
                return j
            c = rawdata[j:j+1]
            if c == "":
                return -1
            if c == "(":
                # an enumerated type; look for ')'
                if ")" in rawdata[j:]:
                    j = rawdata.find(")", j) + 1
                else:
                    return -1
                while rawdata[j:j+1].isspace():
                    j = j + 1
                if not rawdata[j:]:
                    # end of buffer, incomplete
                    return -1
            else:
                name, j = self._scan_name(j, declstartpos)
            c = rawdata[j:j+1]
            if not c:
                return -1
            if c in "'\"":
                m = _declstringlit_match(rawdata, j)
                if m:
                    j = m.end()
                else:
                    return -1
                c = rawdata[j:j+1]
                if not c:
                    return -1
            if c == "#":
                if rawdata[j:] == "#":
                    # end of buffer
                    return -1
                name, j = self._scan_name(j + 1, declstartpos)
                if j < 0:
                    return j
                c = rawdata[j:j+1]
                if not c:
                    return -1
            if c == '>':
                # all done
                return j + 1

# Internal -- scan past <!NOTATION declarations
    def _parse_doctype_notation(self, i, declstartpos):
        name, j = self._scan_name(i, declstartpos)
        if j < 0:
            return j
        rawdata = self.rawdata
        while 1:
            c = rawdata[j:j+1]
            if not c:
                # end of buffer; incomplete
                return -1
            if c == '>':
                return j + 1
            if c in "'\"":
                m = _declstringlit_match(rawdata, j)
                if not m:
                    return -1
                j = m.end()
            else:
                name, j = self._scan_name(j, declstartpos)
                if j < 0:
                    return j

# Internal -- scan past <!ENTITY declarations
    def _parse_doctype_entity(self, i, declstartpos):
        rawdata = self.rawdata
        if rawdata[i:i+1] == "%":
            j = i + 1
            while 1:
                c = rawdata[j:j+1]
                if not c:
                    return -1
                if c.isspace():
                    j = j + 1
                else:
                    break
        else:
            j = i
        name, j = self._scan_name(j, declstartpos)
        if j < 0:
            return j
        while 1:
            c = self.rawdata[j:j+1]
            if not c:
                return -1
            if c in "'\"":
                m = _declstringlit_match(rawdata, j)
                if m:
                    j = m.end()
                else:
                    return -1    # incomplete
            elif c == ">":
                return j + 1
            else:
                name, j = self._scan_name(j, declstartpos)
                if j < 0:
                    return j

# Internal -- scan a name token and the new position and the token, or
    # return -1 if we've reached the end of the buffer.
    def _scan_name(self, i, declstartpos):
        rawdata = self.rawdata
        n = len(rawdata)
        if i == n:
            return None, -1
        m = _declname_match(rawdata, i)
        if m:
            s = m.group()
            name = s.strip()
            if (i + len(s)) == n:
                return None, -1  # end of buffer
            return name.lower(), m.end()
        else:
            self.updatepos(declstartpos, i)
            self.error("expected name token at %r"
                       % rawdata[declstartpos:declstartpos+20])

# To be overridden -- handlers for unknown objects
    def unknown_decl(self, data):
        pass

cmd: