Current Path: > > opt > alt > python312 > lib64 > > python3.12 >
Operation : Linux premium131.web-hosting.com 4.18.0-553.44.1.lve.el8.x86_64 #1 SMP Thu Mar 13 14:29:12 UTC 2025 x86_64 Software : Apache Server IP : 162.0.232.56 | Your IP: 216.73.216.111 Domains : 1034 Domain(s) Permission : [ 0755 ]
| Name | Type | Size | Last Modified | Actions |
|---|---|---|---|---|
| __pycache__ | Directory | - | - | |
| asyncio | Directory | - | - | |
| collections | Directory | - | - | |
| concurrent | Directory | - | - | |
| config-3.12-x86_64-linux-gnu | Directory | - | - | |
| ctypes | Directory | - | - | |
| curses | Directory | - | - | |
| dbm | Directory | - | - | |
| Directory | - | - | ||
| encodings | Directory | - | - | |
| ensurepip | Directory | - | - | |
| html | Directory | - | - | |
| http | Directory | - | - | |
| importlib | Directory | - | - | |
| json | Directory | - | - | |
| lib-dynload | Directory | - | - | |
| lib2to3 | Directory | - | - | |
| logging | Directory | - | - | |
| multiprocessing | Directory | - | - | |
| pydoc_data | Directory | - | - | |
| re | Directory | - | - | |
| site-packages | Directory | - | - | |
| sqlite3 | Directory | - | - | |
| tomllib | Directory | - | - | |
| unittest | Directory | - | - | |
| urllib | Directory | - | - | |
| venv | Directory | - | - | |
| wsgiref | Directory | - | - | |
| xml | Directory | - | - | |
| xmlrpc | Directory | - | - | |
| zipfile | Directory | - | - | |
| zoneinfo | Directory | - | - | |
| LICENSE.txt | File | 13936 bytes | June 03 2025 15:41:47. | |
| __future__.py | File | 5218 bytes | June 23 2025 13:48:52. | |
| __hello__.py | File | 227 bytes | June 23 2025 13:48:52. | |
| _aix_support.py | File | 4021 bytes | June 23 2025 13:48:49. | |
| _collections_abc.py | File | 32089 bytes | June 23 2025 13:48:37. | |
| _compat_pickle.py | File | 8761 bytes | June 23 2025 13:48:48. | |
| _compression.py | File | 5681 bytes | June 23 2025 13:48:37. | |
| _markupbase.py | File | 14653 bytes | June 23 2025 13:48:37. | |
| _osx_support.py | File | 22023 bytes | June 23 2025 13:48:50. | |
| _py_abc.py | File | 6189 bytes | June 23 2025 13:48:51. | |
| _pydatetime.py | File | 92087 bytes | June 23 2025 13:48:51. | |
| _pydecimal.py | File | 227283 bytes | June 23 2025 13:48:36. | |
| _pyio.py | File | 93593 bytes | June 23 2025 13:48:37. | |
| _pylong.py | File | 10790 bytes | June 23 2025 13:48:37. | |
| _sitebuiltins.py | File | 3128 bytes | June 23 2025 13:48:37. | |
| _strptime.py | File | 28393 bytes | June 23 2025 13:48:51. | |
| _sysconfigdata__linux_x86_64-linux-gnu.py | File | 76553 bytes | June 23 2025 13:58:24. | |
| _sysconfigdata_d_linux_x86_64-linux-gnu.py | File | 76549 bytes | June 23 2025 13:51:17. | |
| _threading_local.py | File | 7220 bytes | June 23 2025 13:48:37. | |
| _weakrefset.py | File | 5893 bytes | June 23 2025 13:48:36. | |
| abc.py | File | 6538 bytes | June 23 2025 13:48:37. | |
| aifc.py | File | 34211 bytes | June 23 2025 13:48:51. | |
| antigravity.py | File | 500 bytes | June 23 2025 13:48:37. | |
| argparse.py | File | 101155 bytes | June 23 2025 13:48:49. | |
| ast.py | File | 64452 bytes | June 23 2025 13:48:50. | |
| base64.py | File | 20648 bytes | June 23 2025 13:48:37. | |
| bdb.py | File | 33573 bytes | June 23 2025 13:48:48. | |
| bisect.py | File | 3423 bytes | June 23 2025 13:48:36. | |
| bz2.py | File | 11847 bytes | June 23 2025 13:48:50. | |
| cProfile.py | File | 6569 bytes | June 23 2025 13:48:36. | |
| calendar.py | File | 25864 bytes | June 23 2025 13:48:49. | |
| cgi.py | File | 34432 bytes | June 23 2025 13:48:50. | |
| cgitb.py | File | 12421 bytes | June 23 2025 13:48:52. | |
| chunk.py | File | 5500 bytes | June 23 2025 13:48:37. | |
| cmd.py | File | 14873 bytes | June 23 2025 13:48:36. | |
| code.py | File | 10962 bytes | June 23 2025 13:48:37. | |
| codecs.py | File | 36870 bytes | June 23 2025 13:48:37. | |
| codeop.py | File | 5908 bytes | June 23 2025 13:48:36. | |
| colorsys.py | File | 4062 bytes | June 23 2025 13:48:37. | |
| compileall.py | File | 20507 bytes | June 23 2025 13:48:36. | |
| configparser.py | File | 53789 bytes | June 23 2025 13:48:37. | |
| contextlib.py | File | 27637 bytes | June 23 2025 13:48:36. | |
| contextvars.py | File | 129 bytes | June 23 2025 13:48:48. | |
| copy.py | File | 8412 bytes | June 23 2025 13:48:37. | |
| copyreg.py | File | 7614 bytes | June 23 2025 13:48:50. | |
| crypt.py | File | 3913 bytes | June 23 2025 13:48:37. | |
| csv.py | File | 16386 bytes | June 23 2025 13:48:37. | |
| dataclasses.py | File | 62085 bytes | June 23 2025 13:48:50. | |
| datetime.py | File | 268 bytes | June 23 2025 13:48:52. | |
| decimal.py | File | 2805 bytes | June 23 2025 13:48:49. | |
| difflib.py | File | 83368 bytes | June 23 2025 13:48:37. | |
| dis.py | File | 30227 bytes | June 23 2025 13:48:37. | |
| doctest.py | File | 106749 bytes | June 23 2025 13:48:37. | |
| enum.py | File | 81540 bytes | June 23 2025 13:48:37. | |
| filecmp.py | File | 10381 bytes | June 23 2025 13:48:37. | |
| fileinput.py | File | 15714 bytes | June 23 2025 13:48:37. | |
| fnmatch.py | File | 5999 bytes | June 23 2025 13:48:37. | |
| fractions.py | File | 38147 bytes | June 23 2025 13:48:36. | |
| ftplib.py | File | 34735 bytes | June 23 2025 13:48:37. | |
| functools.py | File | 37940 bytes | June 23 2025 13:48:52. | |
| genericpath.py | File | 5572 bytes | June 23 2025 13:48:52. | |
| getopt.py | File | 7488 bytes | June 23 2025 13:48:50. | |
| getpass.py | File | 5990 bytes | June 23 2025 13:48:36. | |
| gettext.py | File | 21320 bytes | June 23 2025 13:48:50. | |
| glob.py | File | 8732 bytes | June 23 2025 13:48:36. | |
| graphlib.py | File | 9648 bytes | June 23 2025 13:48:36. | |
| gzip.py | File | 25402 bytes | June 23 2025 13:48:50. | |
| hashlib.py | File | 9349 bytes | June 23 2025 13:48:51. | |
| heapq.py | File | 23024 bytes | June 23 2025 13:48:36. | |
| hmac.py | File | 7716 bytes | June 23 2025 13:48:37. | |
| imaplib.py | File | 54040 bytes | June 23 2025 13:48:49. | |
| imghdr.py | File | 4398 bytes | June 23 2025 13:48:50. | |
| inspect.py | File | 127125 bytes | June 23 2025 13:48:48. | |
| io.py | File | 3582 bytes | June 23 2025 13:48:37. | |
| ipaddress.py | File | 81414 bytes | June 23 2025 13:48:49. | |
| keyword.py | File | 1073 bytes | June 23 2025 13:48:50. | |
| linecache.py | File | 5800 bytes | June 23 2025 13:48:37. | |
| locale.py | File | 78599 bytes | June 23 2025 13:48:48. | |
| lzma.py | File | 13277 bytes | June 23 2025 13:48:51. | |
| mailbox.py | File | 78911 bytes | June 23 2025 13:48:48. | |
| mailcap.py | File | 9333 bytes | June 23 2025 13:48:36. | |
| mimetypes.py | File | 23037 bytes | June 23 2025 13:48:48. | |
| modulefinder.py | File | 23699 bytes | June 23 2025 13:48:37. | |
| netrc.py | File | 6922 bytes | June 23 2025 13:48:37. | |
| nntplib.py | File | 41087 bytes | June 23 2025 13:48:36. | |
| ntpath.py | File | 32324 bytes | June 23 2025 13:48:36. | |
| nturl2path.py | File | 2374 bytes | June 23 2025 13:48:50. | |
| numbers.py | File | 11467 bytes | June 23 2025 13:48:51. | |
| opcode.py | File | 13174 bytes | June 23 2025 13:48:52. | |
| operator.py | File | 10965 bytes | June 23 2025 13:48:48. | |
| optparse.py | File | 60369 bytes | June 23 2025 13:48:50. | |
| os.py | File | 40821 bytes | June 23 2025 13:48:36. | |
| pathlib.py | File | 51052 bytes | June 23 2025 13:48:49. | |
| pdb.py | File | 70311 bytes | June 23 2025 13:48:37. | |
| pickle.py | File | 66911 bytes | June 23 2025 13:48:37. | |
| pickletools.py | File | 94052 bytes | June 23 2025 13:48:37. | |
| pipes.py | File | 8978 bytes | June 23 2025 13:48:50. | |
| pkgutil.py | File | 18281 bytes | June 23 2025 13:48:37. | |
| platform.py | File | 43402 bytes | June 23 2025 13:48:37. | |
| plistlib.py | File | 28342 bytes | June 23 2025 13:48:36. | |
| poplib.py | File | 14619 bytes | June 23 2025 13:48:36. | |
| posixpath.py | File | 17483 bytes | June 23 2025 13:48:37. | |
| pprint.py | File | 24158 bytes | June 23 2025 13:48:37. | |
| profile.py | File | 23106 bytes | June 23 2025 13:48:37. | |
| pstats.py | File | 29289 bytes | June 23 2025 13:48:37. | |
| pty.py | File | 6137 bytes | June 23 2025 13:48:36. | |
| py_compile.py | File | 7837 bytes | June 23 2025 13:48:49. | |
| pyclbr.py | File | 11396 bytes | June 23 2025 13:48:36. | |
| pydoc.py | File | 113522 bytes | June 23 2025 13:48:37. | |
| queue.py | File | 11496 bytes | June 23 2025 13:48:50. | |
| quopri.py | File | 7197 bytes | June 23 2025 13:48:50. | |
| random.py | File | 34689 bytes | June 23 2025 13:48:36. | |
| reprlib.py | File | 7148 bytes | June 23 2025 13:48:37. | |
| rlcompleter.py | File | 7827 bytes | June 23 2025 13:48:52. | |
| runpy.py | File | 12885 bytes | June 23 2025 13:48:36. | |
| sched.py | File | 6351 bytes | June 23 2025 13:48:49. | |
| secrets.py | File | 1984 bytes | June 23 2025 13:48:37. | |
| selectors.py | File | 19671 bytes | June 23 2025 13:48:37. | |
| shelve.py | File | 8560 bytes | June 23 2025 13:48:49. | |
| shlex.py | File | 13353 bytes | June 23 2025 13:48:51. | |
| shutil.py | File | 56762 bytes | June 23 2025 13:48:49. | |
| signal.py | File | 2495 bytes | June 23 2025 13:48:49. | |
| site.py | File | 23198 bytes | June 23 2025 13:48:48. | |
| smtplib.py | File | 43545 bytes | June 23 2025 13:48:37. | |
| sndhdr.py | File | 7448 bytes | June 23 2025 13:48:50. | |
| socket.py | File | 37815 bytes | June 23 2025 13:48:51. | |
| socketserver.py | File | 28065 bytes | June 23 2025 13:48:52. | |
| sre_compile.py | File | 231 bytes | June 23 2025 13:48:37. | |
| sre_constants.py | File | 232 bytes | June 23 2025 13:48:36. | |
| sre_parse.py | File | 229 bytes | June 23 2025 13:48:37. | |
| ssl.py | File | 50904 bytes | June 23 2025 13:48:48. | |
| stat.py | File | 5485 bytes | June 23 2025 13:48:49. | |
| statistics.py | File | 50227 bytes | June 23 2025 13:48:37. | |
| string.py | File | 11786 bytes | June 23 2025 13:48:50. | |
| stringprep.py | File | 12917 bytes | June 23 2025 13:48:37. | |
| struct.py | File | 257 bytes | June 23 2025 13:48:37. | |
| subprocess.py | File | 88747 bytes | June 23 2025 13:48:36. | |
| sunau.py | File | 18478 bytes | June 23 2025 13:48:37. | |
| symtable.py | File | 12477 bytes | June 23 2025 13:48:50. | |
| sysconfig.py | File | 31850 bytes | June 23 2025 13:48:49. | |
| tabnanny.py | File | 11545 bytes | June 23 2025 13:48:50. | |
| tarfile.py | File | 112458 bytes | June 23 2025 13:48:37. | |
| telnetlib.py | File | 23334 bytes | June 23 2025 13:48:37. | |
| tempfile.py | File | 32386 bytes | June 23 2025 13:48:36. | |
| textwrap.py | File | 19718 bytes | June 23 2025 13:48:36. | |
| this.py | File | 1003 bytes | June 23 2025 13:48:37. | |
| threading.py | File | 60200 bytes | June 23 2025 13:48:49. | |
| timeit.py | File | 13477 bytes | June 23 2025 13:48:37. | |
| token.py | File | 2511 bytes | June 23 2025 13:48:36. | |
| tokenize.py | File | 21570 bytes | June 23 2025 13:48:49. | |
| trace.py | File | 29366 bytes | June 23 2025 13:48:36. | |
| traceback.py | File | 46393 bytes | June 23 2025 13:48:49. | |
| tracemalloc.py | File | 18047 bytes | June 23 2025 13:48:50. | |
| tty.py | File | 2035 bytes | June 23 2025 13:48:36. | |
| types.py | File | 10993 bytes | June 23 2025 13:48:36. | |
| typing.py | File | 118836 bytes | June 23 2025 13:48:50. | |
| uu.py | File | 7341 bytes | June 23 2025 13:59:33. | |
| uuid.py | File | 29656 bytes | June 23 2025 13:48:37. | |
| warnings.py | File | 21909 bytes | June 23 2025 13:48:37. | |
| wave.py | File | 22769 bytes | June 23 2025 13:48:37. | |
| weakref.py | File | 21513 bytes | June 23 2025 13:48:49. | |
| webbrowser.py | File | 23746 bytes | June 23 2025 13:48:50. | |
| xdrlib.py | File | 5942 bytes | June 23 2025 13:48:52. | |
| zipapp.py | File | 7543 bytes | June 23 2025 13:48:37. | |
| zipimport.py | File | 27840 bytes | June 23 2025 13:48:49. |
"""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
SILENT KILLER Tool