OXIESEC PANEL
- Current Dir:
/
/
snap
/
core
/
17200
/
usr
/
lib
/
python3.5
Server IP: 139.59.38.164
Upload:
Create Dir:
Name
Size
Modified
Perms
📁
..
-
06/06/2024 02:31:58 PM
rwxr-xr-x
📄
LICENSE.txt
12.47 KB
11/22/2023 03:35:02 PM
rw-r--r--
📄
__future__.py
4.73 KB
11/22/2023 03:35:00 PM
rw-r--r--
📄
__phello__.foo.py
64 bytes
11/22/2023 03:35:00 PM
rw-r--r--
📁
__pycache__
-
02/18/2024 07:58:21 PM
rwxr-xr-x
📄
_bootlocale.py
1.27 KB
11/22/2023 03:35:00 PM
rw-r--r--
📄
_collections_abc.py
24.13 KB
11/22/2023 03:35:00 PM
rw-r--r--
📄
_compat_pickle.py
8.36 KB
11/22/2023 03:35:00 PM
rw-r--r--
📄
_compression.py
5.21 KB
11/22/2023 03:35:00 PM
rw-r--r--
📄
_dummy_thread.py
5 KB
11/22/2023 03:35:00 PM
rw-r--r--
📄
_markupbase.py
14.26 KB
11/22/2023 03:35:00 PM
rw-r--r--
📄
_osx_support.py
18.66 KB
11/22/2023 03:35:00 PM
rw-r--r--
📄
_pydecimal.py
222.46 KB
11/22/2023 03:35:00 PM
rw-r--r--
📄
_pyio.py
85.91 KB
11/22/2023 03:35:00 PM
rw-r--r--
📄
_sitebuiltins.py
3.04 KB
11/22/2023 03:35:00 PM
rw-r--r--
📄
_strptime.py
21.67 KB
11/22/2023 03:35:00 PM
rw-r--r--
📄
_sysconfigdata.py
126 bytes
11/23/2013 12:09:48 PM
rw-r--r--
📄
_threading_local.py
7.24 KB
11/22/2023 03:35:00 PM
rw-r--r--
📄
_weakrefset.py
5.57 KB
11/22/2023 03:35:00 PM
rw-r--r--
📄
abc.py
8.43 KB
11/22/2023 03:35:00 PM
rw-r--r--
📄
aifc.py
30.84 KB
11/22/2023 03:35:00 PM
rw-r--r--
📄
antigravity.py
475 bytes
11/22/2023 03:35:00 PM
rw-r--r--
📄
argparse.py
88.21 KB
11/22/2023 03:35:00 PM
rw-r--r--
📄
ast.py
11.72 KB
11/22/2023 03:35:00 PM
rw-r--r--
📄
asynchat.py
11.69 KB
11/22/2023 03:35:00 PM
rw-r--r--
📁
asyncio
-
02/18/2024 07:58:21 PM
rwxr-xr-x
📄
asyncore.py
19.63 KB
11/22/2023 03:35:00 PM
rw-r--r--
📄
base64.py
19.96 KB
11/22/2023 03:35:15 PM
rwxr-xr-x
📄
bdb.py
22.81 KB
11/22/2023 03:35:00 PM
rw-r--r--
📄
binhex.py
13.63 KB
11/22/2023 03:35:00 PM
rw-r--r--
📄
bisect.py
2.53 KB
11/22/2023 03:35:00 PM
rw-r--r--
📄
bz2.py
12.13 KB
11/22/2023 03:35:00 PM
rw-r--r--
📄
cProfile.py
5.19 KB
11/22/2023 03:35:25 PM
rwxr-xr-x
📄
calendar.py
22.4 KB
11/22/2023 03:35:00 PM
rw-r--r--
📄
cgi.py
35.19 KB
11/22/2023 03:35:28 PM
rwxr-xr-x
📄
cgitb.py
11.74 KB
11/22/2023 03:35:00 PM
rw-r--r--
📄
chunk.py
5.3 KB
11/22/2023 03:35:00 PM
rw-r--r--
📄
cmd.py
14.51 KB
11/22/2023 03:35:00 PM
rw-r--r--
📄
code.py
9.88 KB
11/22/2023 03:35:00 PM
rw-r--r--
📄
codecs.py
35.38 KB
11/22/2023 03:35:00 PM
rw-r--r--
📄
codeop.py
5.85 KB
11/22/2023 03:35:00 PM
rw-r--r--
📁
collections
-
02/18/2024 07:58:21 PM
rwxr-xr-x
📄
colorsys.py
3.97 KB
11/22/2023 03:35:00 PM
rw-r--r--
📄
compileall.py
11.42 KB
11/22/2023 03:35:00 PM
rw-r--r--
📁
concurrent
-
02/18/2024 07:58:20 PM
rwxr-xr-x
📄
configparser.py
52.2 KB
11/22/2023 03:35:00 PM
rw-r--r--
📄
contextlib.py
11.97 KB
11/22/2023 03:35:00 PM
rw-r--r--
📄
copy.py
8.74 KB
11/22/2023 03:35:00 PM
rw-r--r--
📄
copyreg.py
6.67 KB
11/22/2023 03:35:00 PM
rw-r--r--
📄
crypt.py
1.83 KB
11/22/2023 03:35:00 PM
rw-r--r--
📄
csv.py
15.75 KB
11/22/2023 03:35:00 PM
rw-r--r--
📁
ctypes
-
02/18/2024 07:58:20 PM
rwxr-xr-x
📁
curses
-
02/18/2024 07:58:21 PM
rwxr-xr-x
📄
datetime.py
74.12 KB
11/22/2023 03:35:01 PM
rw-r--r--
📁
dbm
-
02/18/2024 07:58:21 PM
rwxr-xr-x
📄
decimal.py
320 bytes
11/22/2023 03:35:01 PM
rw-r--r--
📄
difflib.py
82.23 KB
11/22/2023 03:35:01 PM
rw-r--r--
📄
dis.py
16.94 KB
11/22/2023 03:35:01 PM
rw-r--r--
📁
distutils
-
02/18/2024 07:58:21 PM
rwxr-xr-x
📄
doctest.py
101.6 KB
11/22/2023 03:35:01 PM
rw-r--r--
📄
dummy_threading.py
2.75 KB
11/22/2023 03:35:01 PM
rw-r--r--
📁
email
-
02/18/2024 07:58:21 PM
rwxr-xr-x
📁
encodings
-
02/18/2024 07:58:21 PM
rwxr-xr-x
📄
enum.py
21.71 KB
11/22/2023 03:35:01 PM
rw-r--r--
📄
filecmp.py
9.6 KB
11/22/2023 03:35:01 PM
rw-r--r--
📄
fileinput.py
13.92 KB
11/22/2023 03:35:01 PM
rw-r--r--
📄
fnmatch.py
3.09 KB
11/22/2023 03:35:01 PM
rw-r--r--
📄
formatter.py
14.79 KB
11/22/2023 03:35:01 PM
rw-r--r--
📄
fractions.py
23.82 KB
11/22/2023 03:35:01 PM
rw-r--r--
📄
ftplib.py
34.36 KB
11/22/2023 03:35:01 PM
rw-r--r--
📄
functools.py
28.1 KB
11/22/2023 03:35:01 PM
rw-r--r--
📄
genericpath.py
4.26 KB
11/22/2023 03:35:01 PM
rw-r--r--
📄
getopt.py
7.31 KB
11/22/2023 03:35:01 PM
rw-r--r--
📄
getpass.py
5.91 KB
11/22/2023 03:35:01 PM
rw-r--r--
📄
gettext.py
18.18 KB
11/22/2023 03:35:01 PM
rw-r--r--
📄
glob.py
4.95 KB
11/22/2023 03:35:01 PM
rw-r--r--
📄
gzip.py
19.79 KB
11/22/2023 03:35:01 PM
rw-r--r--
📄
hashlib.py
7.79 KB
11/22/2023 03:35:01 PM
rw-r--r--
📄
heapq.py
22.39 KB
11/22/2023 03:35:01 PM
rw-r--r--
📄
hmac.py
4.94 KB
11/22/2023 03:35:01 PM
rw-r--r--
📁
html
-
02/18/2024 07:58:21 PM
rwxr-xr-x
📁
http
-
02/18/2024 07:58:21 PM
rwxr-xr-x
📁
idlelib
-
02/18/2024 07:58:21 PM
rwxr-xr-x
📄
imaplib.py
50.75 KB
11/22/2023 03:35:01 PM
rw-r--r--
📄
imghdr.py
3.67 KB
11/22/2023 03:35:01 PM
rw-r--r--
📄
imp.py
10.38 KB
11/22/2023 03:35:01 PM
rw-r--r--
📁
importlib
-
02/18/2024 07:58:20 PM
rwxr-xr-x
📄
inspect.py
110.66 KB
11/22/2023 03:35:01 PM
rw-r--r--
📄
io.py
3.32 KB
11/22/2023 03:35:01 PM
rw-r--r--
📄
ipaddress.py
73.83 KB
11/22/2023 03:35:01 PM
rw-r--r--
📁
json
-
02/18/2024 07:58:21 PM
rwxr-xr-x
📄
keyword.py
2.16 KB
11/22/2023 03:35:15 PM
rwxr-xr-x
📁
lib-dynload
-
02/18/2024 07:58:21 PM
rwxr-xr-x
📁
lib2to3
-
02/18/2024 07:58:21 PM
rwxr-xr-x
📄
linecache.py
5.19 KB
11/22/2023 03:35:01 PM
rw-r--r--
📄
locale.py
72.97 KB
11/22/2023 03:35:01 PM
rw-r--r--
📁
logging
-
02/18/2024 07:58:20 PM
rwxr-xr-x
📄
lzma.py
12.62 KB
11/22/2023 03:35:01 PM
rw-r--r--
📄
macpath.py
5.77 KB
11/22/2023 03:35:01 PM
rw-r--r--
📄
macurl2path.py
2.67 KB
11/22/2023 03:35:01 PM
rw-r--r--
📄
mailbox.py
76.58 KB
11/22/2023 03:35:01 PM
rw-r--r--
📄
mailcap.py
8.21 KB
11/22/2023 03:35:01 PM
rw-r--r--
📄
mimetypes.py
20.36 KB
11/22/2023 03:35:01 PM
rw-r--r--
📄
modulefinder.py
22.54 KB
11/22/2023 03:35:01 PM
rw-r--r--
📁
multiprocessing
-
02/18/2024 07:58:21 PM
rwxr-xr-x
📄
netrc.py
5.61 KB
11/22/2023 03:35:01 PM
rw-r--r--
📄
nntplib.py
42.07 KB
11/22/2023 03:35:01 PM
rw-r--r--
📄
ntpath.py
22.26 KB
11/22/2023 03:35:01 PM
rw-r--r--
📄
nturl2path.py
2.39 KB
11/22/2023 03:35:01 PM
rw-r--r--
📄
numbers.py
10 KB
11/22/2023 03:35:01 PM
rw-r--r--
📄
opcode.py
5.75 KB
11/22/2023 03:35:01 PM
rw-r--r--
📄
operator.py
10.61 KB
11/22/2023 03:35:01 PM
rw-r--r--
📄
optparse.py
58.93 KB
11/22/2023 03:35:01 PM
rw-r--r--
📄
os.py
36.1 KB
11/22/2023 03:35:01 PM
rw-r--r--
📄
pathlib.py
45.89 KB
11/22/2023 03:35:01 PM
rw-r--r--
📄
pdb.py
59.56 KB
11/22/2023 03:35:24 PM
rwxr-xr-x
📄
pickle.py
54.54 KB
11/22/2023 03:35:01 PM
rw-r--r--
📄
pickletools.py
89.61 KB
11/22/2023 03:35:01 PM
rw-r--r--
📄
pipes.py
8.71 KB
11/22/2023 03:35:01 PM
rw-r--r--
📄
pkgutil.py
20.71 KB
11/22/2023 03:35:01 PM
rw-r--r--
📁
plat-x86_64-linux-gnu
-
02/18/2024 07:58:21 PM
rwxr-xr-x
📄
platform.py
47.91 KB
11/22/2023 03:35:15 PM
rwxr-xr-x
📄
plistlib.py
32 KB
11/22/2023 03:35:01 PM
rw-r--r--
📄
poplib.py
14.17 KB
11/22/2023 03:35:01 PM
rw-r--r--
📄
posixpath.py
14.53 KB
11/22/2023 03:35:01 PM
rw-r--r--
📄
pprint.py
20.37 KB
11/22/2023 03:35:01 PM
rw-r--r--
📄
profile.py
21.5 KB
11/22/2023 03:35:24 PM
rwxr-xr-x
📄
pstats.py
25.7 KB
11/22/2023 03:35:01 PM
rw-r--r--
📄
pty.py
4.65 KB
11/22/2023 03:35:01 PM
rw-r--r--
📄
py_compile.py
7.01 KB
11/22/2023 03:35:01 PM
rw-r--r--
📄
pyclbr.py
13.25 KB
11/22/2023 03:35:01 PM
rw-r--r--
📄
pydoc.py
100.38 KB
11/22/2023 03:35:24 PM
rwxr-xr-x
📁
pydoc_data
-
02/18/2024 07:58:21 PM
rwxr-xr-x
📄
queue.py
8.57 KB
11/22/2023 03:35:01 PM
rw-r--r--
📄
quopri.py
7.08 KB
11/22/2023 03:35:29 PM
rwxr-xr-x
📄
random.py
25.48 KB
11/22/2023 03:35:01 PM
rw-r--r--
📄
re.py
15.14 KB
11/22/2023 03:35:01 PM
rw-r--r--
📄
reprlib.py
5.21 KB
11/22/2023 03:35:01 PM
rw-r--r--
📄
rlcompleter.py
6.16 KB
11/22/2023 03:35:01 PM
rw-r--r--
📄
runpy.py
11.13 KB
11/22/2023 03:35:01 PM
rw-r--r--
📄
sched.py
6.07 KB
11/22/2023 03:35:01 PM
rw-r--r--
📄
selectors.py
18.72 KB
11/22/2023 03:35:01 PM
rw-r--r--
📄
shelve.py
8.33 KB
11/22/2023 03:35:01 PM
rw-r--r--
📄
shlex.py
11.15 KB
11/22/2023 03:35:01 PM
rw-r--r--
📄
shutil.py
38.93 KB
11/22/2023 03:35:01 PM
rw-r--r--
📄
signal.py
2.07 KB
11/22/2023 03:35:01 PM
rw-r--r--
📄
site.py
21.74 KB
11/22/2023 03:35:01 PM
rw-r--r--
📄
sitecustomize.py
0 bytes
01/01/1970 12:00:00 AM
---------
📄
smtpd.py
34.53 KB
11/22/2023 03:35:28 PM
rwxr-xr-x
📄
smtplib.py
42.57 KB
11/22/2023 03:35:26 PM
rwxr-xr-x
📄
sndhdr.py
6.27 KB
11/22/2023 03:35:01 PM
rw-r--r--
📄
socket.py
26.46 KB
11/22/2023 03:35:01 PM
rw-r--r--
📄
socketserver.py
24.09 KB
11/22/2023 03:35:01 PM
rw-r--r--
📁
sqlite3
-
02/18/2024 07:58:20 PM
rwxr-xr-x
📄
sre_compile.py
17.98 KB
11/22/2023 03:35:01 PM
rw-r--r--
📄
sre_constants.py
6.3 KB
11/22/2023 03:35:01 PM
rw-r--r--
📄
sre_parse.py
34.14 KB
11/22/2023 03:35:01 PM
rw-r--r--
📄
ssl.py
42.54 KB
11/22/2023 03:35:01 PM
rw-r--r--
📄
stat.py
4.92 KB
11/22/2023 03:35:01 PM
rw-r--r--
📄
statistics.py
19.08 KB
11/22/2023 03:35:01 PM
rw-r--r--
📄
string.py
11.58 KB
11/22/2023 03:35:01 PM
rw-r--r--
📄
stringprep.py
12.61 KB
11/22/2023 03:35:01 PM
rw-r--r--
📄
struct.py
257 bytes
11/22/2023 03:35:01 PM
rw-r--r--
📄
subprocess.py
66.8 KB
11/22/2023 03:35:01 PM
rw-r--r--
📄
sunau.py
17.67 KB
11/22/2023 03:35:01 PM
rw-r--r--
📄
symbol.py
2.04 KB
11/22/2023 03:35:24 PM
rwxr-xr-x
📄
symtable.py
7.02 KB
11/22/2023 03:35:01 PM
rw-r--r--
📄
sysconfig.py
24.07 KB
11/22/2023 03:35:01 PM
rw-r--r--
📄
tabnanny.py
11.13 KB
11/22/2023 03:35:29 PM
rwxr-xr-x
📄
tarfile.py
90.83 KB
11/22/2023 03:35:26 PM
rwxr-xr-x
📄
telnetlib.py
22.48 KB
11/22/2023 03:35:01 PM
rw-r--r--
📄
tempfile.py
30.98 KB
11/22/2023 03:35:01 PM
rw-r--r--
📁
test
-
02/18/2024 07:58:21 PM
rwxr-xr-x
📄
textwrap.py
19.19 KB
11/22/2023 03:35:01 PM
rw-r--r--
📄
this.py
1003 bytes
11/22/2023 03:35:01 PM
rw-r--r--
📄
threading.py
47.77 KB
11/22/2023 03:35:01 PM
rw-r--r--
📄
timeit.py
12.1 KB
11/22/2023 03:35:25 PM
rwxr-xr-x
📁
tkinter
-
02/18/2024 07:58:21 PM
rwxr-xr-x
📄
token.py
3 KB
11/22/2023 03:35:01 PM
rw-r--r--
📄
tokenize.py
27.14 KB
11/22/2023 03:35:01 PM
rw-r--r--
📄
trace.py
30.8 KB
11/22/2023 03:35:29 PM
rwxr-xr-x
📄
traceback.py
21.67 KB
11/22/2023 03:35:01 PM
rw-r--r--
📄
tracemalloc.py
15.27 KB
11/22/2023 03:35:01 PM
rw-r--r--
📄
tty.py
879 bytes
11/22/2023 03:35:01 PM
rw-r--r--
📄
turtle.py
140.14 KB
11/22/2023 03:35:01 PM
rw-r--r--
📄
types.py
8.59 KB
11/22/2023 03:35:01 PM
rw-r--r--
📄
typing.py
58.12 KB
11/22/2023 03:35:01 PM
rw-r--r--
📁
unittest
-
02/18/2024 07:58:21 PM
rwxr-xr-x
📁
urllib
-
02/18/2024 07:58:21 PM
rwxr-xr-x
📄
uu.py
6.59 KB
11/22/2023 03:35:24 PM
rwxr-xr-x
📄
uuid.py
22.72 KB
11/22/2023 03:35:01 PM
rw-r--r--
📁
venv
-
02/18/2024 07:58:21 PM
rwxr-xr-x
📄
warnings.py
15.48 KB
11/22/2023 03:35:01 PM
rw-r--r--
📄
wave.py
17.27 KB
11/22/2023 03:35:01 PM
rw-r--r--
📄
weakref.py
18.95 KB
11/22/2023 03:35:01 PM
rw-r--r--
📄
webbrowser.py
20.92 KB
11/22/2023 03:35:26 PM
rwxr-xr-x
📁
wsgiref
-
02/18/2024 07:58:21 PM
rwxr-xr-x
📄
xdrlib.py
5.77 KB
11/22/2023 03:35:01 PM
rw-r--r--
📁
xml
-
02/18/2024 07:58:20 PM
rwxr-xr-x
📁
xmlrpc
-
02/18/2024 07:58:21 PM
rwxr-xr-x
📄
zipapp.py
6.99 KB
11/22/2023 03:35:01 PM
rw-r--r--
📄
zipfile.py
71.95 KB
11/22/2023 03:35:01 PM
rw-r--r--
Editing: _markupbase.py
Close
"""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