/
opt
/
alt
/
python33
/
lib64
/
python3.3
/
/opt/alt/python33/lib64/python3.3
mkdir
upload
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/csv.py
(16185B)
""" csv.py - read/write/investigate CSV files """ import re from _csv import Error, __version__, writer, reader, register_dialect, \ unregister_dialect, get_dialect, list_dialects, \ field_size_limit, \ QUOTE_MINIMAL, QUOTE_ALL, QUOTE_NONNUMERIC, QUOTE_NONE, \ __doc__ from _csv import Dialect as _Dialect from io import StringIO __all__ = [ "QUOTE_MINIMAL", "QUOTE_ALL", "QUOTE_NONNUMERIC", "QUOTE_NONE", "Error", "Dialect", "__doc__", "excel", "excel_tab", "field_size_limit", "reader", "writer", "register_dialect", "get_dialect", "list_dialects", "Sniffer", "unregister_dialect", "__version__", "DictReader", "DictWriter" ] class Dialect: """Describe a CSV dialect. This must be subclassed (see csv.excel). Valid attributes are: delimiter, quotechar, escapechar, doublequote, skipinitialspace, lineterminator, quoting. """ _name = "" _valid = False # placeholders delimiter = None quotechar = None escapechar = None doublequote = None skipinitialspace = None lineterminator = None quoting = None def __init__(self): if self.__class__ != Dialect: self._valid = True self._validate() def _validate(self): try: _Dialect(self) except TypeError as e: # We do this for compatibility with py2.3 raise Error(str(e)) class excel(Dialect): """Describe the usual properties of Excel-generated CSV files.""" delimiter = ',' quotechar = '"' doublequote = True skipinitialspace = False lineterminator = '\r\n' quoting = QUOTE_MINIMAL register_dialect("excel", excel) class excel_tab(excel): """Describe the usual properties of Excel-generated TAB-delimited files.""" delimiter = '\t' register_dialect("excel-tab", excel_tab) class unix_dialect(Dialect): """Describe the usual properties of Unix-generated CSV files.""" delimiter = ',' quotechar = '"' doublequote = True skipinitialspace = False lineterminator = '\n' quoting = QUOTE_ALL register_dialect("unix", unix_dialect) class DictReader: def __init__(self, f, fieldnames=None, restkey=None, restval=None, dialect="excel", *args, **kwds): self._fieldnames = fieldnames # list of keys for the dict self.restkey = restkey # key to catch long rows self.restval = restval # default value for short rows self.reader = reader(f, dialect, *args, **kwds) self.dialect = dialect self.line_num = 0 def __iter__(self): return self @property def fieldnames(self): if self._fieldnames is None: try: self._fieldnames = next(self.reader) except StopIteration: pass self.line_num = self.reader.line_num return self._fieldnames @fieldnames.setter def fieldnames(self, value): self._fieldnames = value def __next__(self): if self.line_num == 0: # Used only for its side effect. self.fieldnames row = next(self.reader) self.line_num = self.reader.line_num # unlike the basic reader, we prefer not to return blanks, # because we will typically wind up with a dict full of None # values while row == []: row = next(self.reader) d = dict(zip(self.fieldnames, row)) lf = len(self.fieldnames) lr = len(row) if lf < lr: d[self.restkey] = row[lf:] elif lf > lr: for key in self.fieldnames[lr:]: d[key] = self.restval return d class DictWriter: def __init__(self, f, fieldnames, restval="", extrasaction="raise", dialect="excel", *args, **kwds): self.fieldnames = fieldnames # list of keys for the dict self.restval = restval # for writing short dicts if extrasaction.lower() not in ("raise", "ignore"): raise ValueError("extrasaction (%s) must be 'raise' or 'ignore'" % extrasaction) self.extrasaction = extrasaction self.writer = writer(f, dialect, *args, **kwds) def writeheader(self): header = dict(zip(self.fieldnames, self.fieldnames)) self.writerow(header) def _dict_to_list(self, rowdict): if self.extrasaction == "raise": wrong_fields = [k for k in rowdict if k not in self.fieldnames] if wrong_fields: raise ValueError("dict contains fields not in fieldnames: " + ", ".join([repr(x) for x in wrong_fields])) return [rowdict.get(key, self.restval) for key in self.fieldnames] def writerow(self, rowdict): return self.writer.writerow(self._dict_to_list(rowdict)) def writerows(self, rowdicts): rows = [] for rowdict in rowdicts: rows.append(self._dict_to_list(rowdict)) return self.writer.writerows(rows) # Guard Sniffer's type checking against builds that exclude complex() try: complex except NameError: complex = float class Sniffer: ''' "Sniffs" the format of a CSV file (i.e. delimiter, quotechar) Returns a Dialect object. ''' def __init__(self): # in case there is more than one possible delimiter self.preferred = [',', '\t', ';', ' ', ':'] def sniff(self, sample, delimiters=None): """ Returns a dialect (or None) corresponding to the sample """ quotechar, doublequote, delimiter, skipinitialspace = \ self._guess_quote_and_delimiter(sample, delimiters) if not delimiter: delimiter, skipinitialspace = self._guess_delimiter(sample, delimiters) if not delimiter: raise Error("Could not determine delimiter") class dialect(Dialect): _name = "sniffed" lineterminator = '\r\n' quoting = QUOTE_MINIMAL # escapechar = '' dialect.doublequote = doublequote dialect.delimiter = delimiter # _csv.reader won't accept a quotechar of '' dialect.quotechar = quotechar or '"' dialect.skipinitialspace = skipinitialspace return dialect def _guess_quote_and_delimiter(self, data, delimiters): """ Looks for text enclosed between two identical quotes (the probable quotechar) which are preceded and followed by the same character (the probable delimiter). For example: ,'some text', The quote with the most wins, same with the delimiter. If there is no quotechar the delimiter can't be determined this way. """ matches = [] for restr in ('(?P<delim>[^\w\n"\'])(?P<space> ?)(?P<quote>["\']).*?(?P=quote)(?P=delim)', # ,".*?", '(?:^|\n)(?P<quote>["\']).*?(?P=quote)(?P<delim>[^\w\n"\'])(?P<space> ?)', # ".*?", '(?P<delim>>[^\w\n"\'])(?P<space> ?)(?P<quote>["\']).*?(?P=quote)(?:$|\n)', # ,".*?" '(?:^|\n)(?P<quote>["\']).*?(?P=quote)(?:$|\n)'): # ".*?" (no delim, no space) regexp = re.compile(restr, re.DOTALL | re.MULTILINE) matches = regexp.findall(data) if matches: break if not matches: # (quotechar, doublequote, delimiter, skipinitialspace) return ('', False, None, 0) quotes = {} delims = {} spaces = 0 for m in matches: n = regexp.groupindex['quote'] - 1 key = m[n] if key: quotes[key] = quotes.get(key, 0) + 1 try: n = regexp.groupindex['delim'] - 1 key = m[n] except KeyError: continue if key and (delimiters is None or key in delimiters): delims[key] = delims.get(key, 0) + 1 try: n = regexp.groupindex['space'] - 1 except KeyError: continue if m[n]: spaces += 1 quotechar = max(quotes, key=quotes.get) if delims: delim = max(delims, key=delims.get) skipinitialspace = delims[delim] == spaces if delim == '\n': # most likely a file with a single column delim = '' else: # there is *no* delimiter, it's a single column of quoted data delim = '' skipinitialspace = 0 # if we see an extra quote between delimiters, we've got a # double quoted format dq_regexp = re.compile( r"((%(delim)s)|^)\W*%(quote)s[^%(delim)s\n]*%(quote)s[^%(delim)s\n]*%(quote)s\W*((%(delim)s)|$)" % \ {'delim':re.escape(delim), 'quote':quotechar}, re.MULTILINE) if dq_regexp.search(data): doublequote = True else: doublequote = False return (quotechar, doublequote, delim, skipinitialspace) def _guess_delimiter(self, data, delimiters): """ The delimiter /should/ occur the same number of times on each row. However, due to malformed data, it may not. We don't want an all or nothing approach, so we allow for small variations in this number. 1) build a table of the frequency of each character on every line. 2) build a table of frequencies of this frequency (meta-frequency?), e.g. 'x occurred 5 times in 10 rows, 6 times in 1000 rows, 7 times in 2 rows' 3) use the mode of the meta-frequency to determine the /expected/ frequency for that character 4) find out how often the character actually meets that goal 5) the character that best meets its goal is the delimiter For performance reasons, the data is evaluated in chunks, so it can try and evaluate the smallest portion of the data possible, evaluating additional chunks as necessary. """ data = list(filter(None, data.split('\n'))) ascii = [chr(c) for c in range(127)] # 7-bit ASCII # build frequency tables chunkLength = min(10, len(data)) iteration = 0 charFrequency = {} modes = {} delims = {} start, end = 0, min(chunkLength, len(data)) while start < len(data): iteration += 1 for line in data[start:end]: for char in ascii: metaFrequency = charFrequency.get(char, {}) # must count even if frequency is 0 freq = line.count(char) # value is the mode metaFrequency[freq] = metaFrequency.get(freq, 0) + 1 charFrequency[char] = metaFrequency for char in charFrequency.keys(): items = list(charFrequency[char].items()) if len(items) == 1 and items[0][0] == 0: continue # get the mode of the frequencies if len(items) > 1: modes[char] = max(items, key=lambda x: x[1]) # adjust the mode - subtract the sum of all # other frequencies items.remove(modes[char]) modes[char] = (modes[char][0], modes[char][1] - sum(item[1] for item in items)) else: modes[char] = items[0] # build a list of possible delimiters modeList = modes.items() total = float(chunkLength * iteration) # (rows of consistent data) / (number of rows) = 100% consistency = 1.0 # minimum consistency threshold threshold = 0.9 while len(delims) == 0 and consistency >= threshold: for k, v in modeList: if v[0] > 0 and v[1] > 0: if ((v[1]/total) >= consistency and (delimiters is None or k in delimiters)): delims[k] = v consistency -= 0.01 if len(delims) == 1: delim = list(delims.keys())[0] skipinitialspace = (data[0].count(delim) == data[0].count("%c " % delim)) return (delim, skipinitialspace) # analyze another chunkLength lines start = end end += chunkLength if not delims: return ('', 0) # if there's more than one, fall back to a 'preferred' list if len(delims) > 1: for d in self.preferred: if d in delims.keys(): skipinitialspace = (data[0].count(d) == data[0].count("%c " % d)) return (d, skipinitialspace) # nothing else indicates a preference, pick the character that # dominates(?) items = [(v,k) for (k,v) in delims.items()] items.sort() delim = items[-1][1] skipinitialspace = (data[0].count(delim) == data[0].count("%c " % delim)) return (delim, skipinitialspace) def has_header(self, sample): # Creates a dictionary of types of data in each column. If any # column is of a single type (say, integers), *except* for the first # row, then the first row is presumed to be labels. If the type # can't be determined, it is assumed to be a string in which case # the length of the string is the determining factor: if all of the # rows except for the first are the same length, it's a header. # Finally, a 'vote' is taken at the end for each column, adding or # subtracting from the likelihood of the first row being a header. rdr = reader(StringIO(sample), self.sniff(sample)) header = next(rdr) # assume first row is header columns = len(header) columnTypes = {} for i in range(columns): columnTypes[i] = None checked = 0 for row in rdr: # arbitrary number of rows to check, to keep it sane if checked > 20: break checked += 1 if len(row) != columns: continue # skip rows that have irregular number of columns for col in list(columnTypes.keys()): for thisType in [int, float, complex]: try: thisType(row[col]) break except (ValueError, OverflowError): pass else: # fallback to length of string thisType = len(row[col]) if thisType != columnTypes[col]: if columnTypes[col] is None: # add new column type columnTypes[col] = thisType else: # type is inconsistent, remove column from # consideration del columnTypes[col] # finally, compare results against first row and "vote" # on whether it's a header hasHeader = 0 for col, colType in columnTypes.items(): if type(colType) == type(0): # it's a length if len(header[col]) != colType: hasHeader += 1 else: hasHeader -= 1 else: # attempt typecast try: colType(header[col]) except (ValueError, TypeError): hasHeader += 1 else: hasHeader -= 1 return hasHeader > 0
Save
cmd:
run