FM / python3.10

/snap/core22/2411/usr/lib/python3.10

Name	Size	Mode	Actions
asyncio/	-	0755	rm
collections/	-	0755	rm
concurrent/	-	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
importlib/	-	0755	rm
json/	-	0755	rm
lib-dynload/	-	0755	rm
lib2to3/	-	0755	rm
logging/	-	0755	rm
multiprocessing/	-	0755	rm
pydoc_data/	-	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
zoneinfo/	-	0755	rm
__pycache__/	-	0755	rm
abc.py	6522	0644	edit dl rm
aifc.py	32605	0644	edit dl rm
antigravity.py	500	0644	edit dl rm
argparse.py	98839	0644	edit dl rm
ast.py	59900	0644	edit dl rm
asynchat.py	11520	0644	edit dl rm
asyncore.py	20268	0644	edit dl rm
base64.py	20846	0755	edit dl rm
bdb.py	32396	0644	edit dl rm
binhex.py	14784	0644	edit dl rm
bisect.py	3135	0644	edit dl rm
bz2.py	11847	0644	edit dl rm
calendar.py	24575	0644	edit dl rm
cgi.py	34099	0755	edit dl rm
cgitb.py	12096	0644	edit dl rm
chunk.py	5435	0644	edit dl rm
cmd.py	14860	0644	edit dl rm
code.py	10622	0644	edit dl rm
codecs.py	36714	0644	edit dl rm
codeop.py	5609	0644	edit dl rm
colorsys.py	4017	0644	edit dl rm
compileall.py	20252	0644	edit dl rm
configparser.py	54612	0644	edit dl rm
contextlib.py	25882	0644	edit dl rm
contextvars.py	129	0644	edit dl rm
copy.py	8681	0644	edit dl rm
copyreg.py	7426	0644	edit dl rm
cProfile.py	6347	0755	edit dl rm
crypt.py	3848	0644	edit dl rm
csv.py	16030	0644	edit dl rm
dataclasses.py	56390	0644	edit dl rm
datetime.py	88086	0644	edit dl rm
decimal.py	320	0644	edit dl rm
difflib.py	83308	0644	edit dl rm
dis.py	20020	0644	edit dl rm
doctest.py	105143	0644	edit dl rm
enum.py	39831	0644	edit dl rm
filecmp.py	10178	0644	edit dl rm
fileinput.py	16442	0644	edit dl rm
fnmatch.py	6713	0644	edit dl rm
fractions.py	28242	0644	edit dl rm
ftplib.py	35496	0644	edit dl rm
functools.py	38076	0644	edit dl rm
genericpath.py	4975	0644	edit dl rm
getopt.py	7489	0644	edit dl rm
getpass.py	5990	0644	edit dl rm
gettext.py	27693	0644	edit dl rm
glob.py	7888	0644	edit dl rm
graphlib.py	9573	0644	edit dl rm
gzip.py	21849	0644	edit dl rm
hashlib.py	10229	0644	edit dl rm
heapq.py	22877	0644	edit dl rm
hmac.py	7717	0644	edit dl rm
imaplib.py	55035	0644	edit dl rm
imghdr.py	3808	0644	edit dl rm
imp.py	10591	0644	edit dl rm
inspect.py	124378	0644	edit dl rm
io.py	4196	0644	edit dl rm
ipaddress.py	77780	0644	edit dl rm
keyword.py	1061	0644	edit dl rm
LICENSE.txt	13936	0644	edit dl rm
linecache.py	5690	0644	edit dl rm
locale.py	78128	0644	edit dl rm
lzma.py	13277	0644	edit dl rm
mailbox.py	78794	0644	edit dl rm
mailcap.py	9116	0644	edit dl rm
mimetypes.py	22539	0644	edit dl rm
modulefinder.py	24401	0644	edit dl rm
netrc.py	5747	0644	edit dl rm
nntplib.py	41023	0644	edit dl rm
ntpath.py	27561	0644	edit dl rm
nturl2path.py	2887	0644	edit dl rm
numbers.py	10348	0644	edit dl rm
opcode.py	5902	0644	edit dl rm
operator.py	10751	0644	edit dl rm
optparse.py	60369	0644	edit dl rm
os.py	39557	0644	edit dl rm
pathlib.py	49575	0644	edit dl rm
pdb.py	63225	0755	edit dl rm
pickle.py	64949	0644	edit dl rm
pickletools.py	93486	0644	edit dl rm
pipes.py	8914	0644	edit dl rm
pkgutil.py	24576	0644	edit dl rm
platform.py	42022	0755	edit dl rm
plistlib.py	28592	0644	edit dl rm
poplib.py	15321	0644	edit dl rm
posixpath.py	16123	0644	edit dl rm
pprint.py	24444	0644	edit dl rm
profile.py	22883	0755	edit dl rm
pstats.py	29326	0644	edit dl rm
pty.py	5213	0644	edit dl rm
pyclbr.py	11396	0644	edit dl rm
pydoc.py	109884	0755	edit dl rm
py_compile.py	7878	0644	edit dl rm
queue.py	11496	0644	edit dl rm
quopri.py	7267	0755	edit dl rm
random.py	33221	0644	edit dl rm
re.py	15860	0644	edit dl rm
reprlib.py	5267	0644	edit dl rm
rlcompleter.py	7817	0644	edit dl rm
runpy.py	13111	0644	edit dl rm
sched.py	6351	0644	edit dl rm
secrets.py	2036	0644	edit dl rm
selectors.py	19536	0644	edit dl rm
shelve.py	8560	0644	edit dl rm
shlex.py	13501	0644	edit dl rm
shutil.py	54572	0644	edit dl rm
signal.py	2438	0644	edit dl rm
site.py	23667	0644	edit dl rm
sitecustomize.py	155	0644	edit dl rm
smtpd.py	35165	0755	edit dl rm
smtplib.py	45418	0755	edit dl rm
sndhdr.py	7099	0644	edit dl rm
socket.py	36785	0644	edit dl rm
socketserver.py	27296	0644	edit dl rm
sre_compile.py	27973	0644	edit dl rm
sre_constants.py	7177	0644	edit dl rm
sre_parse.py	40779	0644	edit dl rm
ssl.py	53725	0644	edit dl rm
stat.py	5485	0644	edit dl rm
statistics.py	43205	0644	edit dl rm
string.py	10566	0644	edit dl rm
stringprep.py	12917	0644	edit dl rm
struct.py	257	0644	edit dl rm
subprocess.py	84917	0644	edit dl rm
sunau.py	18158	0644	edit dl rm
symtable.py	10217	0644	edit dl rm
sysconfig.py	29398	0644	edit dl rm
tabnanny.py	11299	0755	edit dl rm
tarfile.py	107453	0755	edit dl rm
telnetlib.py	23254	0644	edit dl rm
tempfile.py	34567	0644	edit dl rm
textwrap.py	19772	0644	edit dl rm
this.py	1003	0644	edit dl rm
threading.py	57200	0644	edit dl rm
timeit.py	13495	0755	edit dl rm
token.py	2386	0644	edit dl rm
tokenize.py	25921	0644	edit dl rm
trace.py	29215	0755	edit dl rm
traceback.py	26222	0644	edit dl rm
tracemalloc.py	18047	0644	edit dl rm
tty.py	879	0644	edit dl rm
turtle.py	143760	0644	edit dl rm
types.py	10117	0644	edit dl rm
typing.py	92557	0644	edit dl rm
uu.py	7300	0755	edit dl rm
uuid.py	27500	0644	edit dl rm
warnings.py	19688	0644	edit dl rm
wave.py	18004	0644	edit dl rm
weakref.py	21560	0644	edit dl rm
webbrowser.py	24245	0755	edit dl rm
xdrlib.py	5913	0644	edit dl rm
zipapp.py	7535	0644	edit dl rm
zipfile.py	90851	0644	edit dl rm
zipimport.py	30891	0644	edit dl rm
_aix_support.py	3270	0644	edit dl rm
_bootsubprocess.py	2675	0644	edit dl rm
_collections_abc.py	32284	0644	edit dl rm
_compat_pickle.py	8749	0644	edit dl rm
_compression.py	5681	0644	edit dl rm
_distutils_system_mod.py	6312	0644	edit dl rm
_markupbase.py	14653	0644	edit dl rm
_osx_support.py	21787	0644	edit dl rm
_pydecimal.py	228676	0644	edit dl rm
_pyio.py	94467	0644	edit dl rm
_py_abc.py	6189	0644	edit dl rm
_sitebuiltins.py	3128	0644	edit dl rm
_strptime.py	25277	0644	edit dl rm
_sysconfigdata__linux_x86_64-linux-gnu.py	27484	0644	edit dl rm
_sysconfigdata__x86_64-linux-gnu.py	27484	0644	edit dl rm
_threading_local.py	7220	0644	edit dl rm
_weakrefset.py	5923	0644	edit dl rm
__future__.py	5155	0644	edit dl rm
__phello__.foo.py	64	0644	edit dl rm

Edit: /snap/core22/2411/usr/lib/python3.10/_markupbase.py (14653B)

"""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 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
                    raise AssertionError("unsupported '[' char in %s declaration" % decltype)
                else:
                    raise AssertionError("unexpected '[' char in declaration")
            else:
                raise AssertionError("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:
            raise AssertionError(
                '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] != '<!--':
            raise AssertionError('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)
                    raise AssertionError(
                        "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)
                    raise AssertionError(
                        "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)
                    raise AssertionError("unexpected char after internal subset")
                else:
                    return -1
            elif c.isspace():
                j = j + 1
            else:
                self.updatepos(declstartpos, j)
                raise AssertionError("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)
            raise AssertionError(
                "expected name token at %r" % rawdata[declstartpos:declstartpos+20]
            )

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

cmd: