Current Path: > > opt > > alt > python33 > lib64 > python3.3
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 | - | - | |
collections | Directory | - | - | |
concurrent | Directory | - | - | |
config-3.3m | Directory | - | - | |
ctypes | Directory | - | - | |
curses | Directory | - | - | |
dbm | Directory | - | - | |
distutils | Directory | - | - | |
Directory | - | - | ||
encodings | Directory | - | - | |
html | Directory | - | - | |
http | Directory | - | - | |
idlelib | Directory | - | - | |
importlib | Directory | - | - | |
json | Directory | - | - | |
lib-dynload | Directory | - | - | |
lib2to3 | Directory | - | - | |
logging | Directory | - | - | |
multiprocessing | Directory | - | - | |
plat-linux | Directory | - | - | |
pydoc_data | Directory | - | - | |
site-packages | Directory | - | - | |
sqlite3 | Directory | - | - | |
test | Directory | - | - | |
unittest | Directory | - | - | |
urllib | Directory | - | - | |
venv | Directory | - | - | |
wsgiref | Directory | - | - | |
xml | Directory | - | - | |
xmlrpc | Directory | - | - | |
__future__.py | File | 4584 bytes | April 17 2024 16:58:21. | |
__phello__.foo.py | File | 64 bytes | April 17 2024 16:58:20. | |
_compat_pickle.py | File | 4338 bytes | April 17 2024 16:58:19. | |
_dummy_thread.py | File | 4769 bytes | April 17 2024 16:58:20. | |
_markupbase.py | File | 14598 bytes | April 17 2024 16:58:15. | |
_osx_support.py | File | 18855 bytes | April 17 2024 16:58:20. | |
_pyio.py | File | 72905 bytes | April 17 2024 16:58:17. | |
_strptime.py | File | 21674 bytes | April 17 2024 16:58:20. | |
_sysconfigdata.py | File | 22842 bytes | April 17 2024 16:58:20. | |
_threading_local.py | File | 7410 bytes | April 17 2024 16:58:15. | |
_weakrefset.py | File | 5705 bytes | April 17 2024 16:58:14. | |
abc.py | File | 8057 bytes | April 17 2024 16:58:15. | |
aifc.py | File | 31054 bytes | April 17 2024 16:58:21. | |
antigravity.py | File | 475 bytes | April 17 2024 16:58:16. | |
argparse.py | File | 89069 bytes | April 17 2024 16:58:20. | |
ast.py | File | 12142 bytes | April 17 2024 16:58:20. | |
asynchat.py | File | 11588 bytes | April 17 2024 16:58:19. | |
asyncore.py | File | 20753 bytes | April 17 2024 16:58:21. | |
base64.py | File | 13986 bytes | April 17 2024 16:58:17. | |
bdb.py | File | 21894 bytes | April 17 2024 16:58:19. | |
binhex.py | File | 13708 bytes | April 17 2024 16:58:14. | |
bisect.py | File | 2595 bytes | April 17 2024 16:58:13. | |
bz2.py | File | 18473 bytes | April 17 2024 16:58:20. | |
cProfile.py | File | 6361 bytes | April 17 2024 16:58:14. | |
calendar.py | File | 22940 bytes | April 17 2024 16:58:20. | |
cgi.py | File | 35554 bytes | April 17 2024 16:58:20. | |
cgitb.py | File | 12041 bytes | April 17 2024 16:58:21. | |
chunk.py | File | 5377 bytes | April 17 2024 16:58:17. | |
cmd.py | File | 14860 bytes | April 17 2024 16:58:14. | |
code.py | File | 10030 bytes | April 17 2024 16:58:16. | |
codecs.py | File | 35956 bytes | April 17 2024 16:58:15. | |
codeop.py | File | 5994 bytes | April 17 2024 16:58:14. | |
colorsys.py | File | 3691 bytes | April 17 2024 16:58:15. | |
compileall.py | File | 9743 bytes | April 17 2024 16:58:14. | |
configparser.py | File | 49437 bytes | April 17 2024 16:58:15. | |
contextlib.py | File | 9125 bytes | April 17 2024 16:58:14. | |
copy.py | File | 8991 bytes | April 17 2024 16:58:15. | |
copyreg.py | File | 6611 bytes | April 17 2024 16:58:20. | |
crypt.py | File | 1879 bytes | April 17 2024 16:58:14. | |
csv.py | File | 16185 bytes | April 17 2024 16:58:15. | |
datetime.py | File | 74954 bytes | April 17 2024 16:58:21. | |
decimal.py | File | 228558 bytes | April 17 2024 16:58:19. | |
difflib.py | File | 82519 bytes | April 17 2024 16:58:17. | |
dis.py | File | 10134 bytes | April 17 2024 16:58:15. | |
doctest.py | File | 102933 bytes | April 17 2024 16:58:15. | |
dummy_threading.py | File | 2815 bytes | April 17 2024 16:58:14. | |
filecmp.py | File | 9597 bytes | April 17 2024 16:58:15. | |
fileinput.py | File | 14256 bytes | April 17 2024 16:58:17. | |
fnmatch.py | File | 3163 bytes | April 17 2024 16:58:15. | |
formatter.py | File | 14930 bytes | April 17 2024 16:58:15. | |
fractions.py | File | 23033 bytes | April 17 2024 16:58:14. | |
ftplib.py | File | 40253 bytes | April 17 2024 16:58:15. | |
functools.py | File | 13596 bytes | April 17 2024 16:58:21. | |
genericpath.py | File | 3093 bytes | April 17 2024 16:58:21. | |
getopt.py | File | 7488 bytes | April 17 2024 16:58:20. | |
getpass.py | File | 5793 bytes | April 17 2024 16:58:14. | |
gettext.py | File | 20637 bytes | April 17 2024 16:58:20. | |
glob.py | File | 2838 bytes | April 17 2024 16:58:14. | |
gzip.py | File | 24403 bytes | April 17 2024 16:58:20. | |
hashlib.py | File | 6193 bytes | April 17 2024 16:58:21. | |
heapq.py | File | 17997 bytes | April 17 2024 16:58:13. | |
hmac.py | File | 4440 bytes | April 17 2024 16:58:17. | |
imaplib.py | File | 50111 bytes | April 17 2024 16:58:20. | |
imghdr.py | File | 3528 bytes | April 17 2024 16:58:20. | |
imp.py | File | 9727 bytes | April 17 2024 16:58:15. | |
inspect.py | File | 78960 bytes | April 17 2024 16:58:19. | |
io.py | File | 3280 bytes | April 17 2024 16:58:15. | |
ipaddress.py | File | 70303 bytes | April 17 2024 16:58:20. | |
keyword.py | File | 2060 bytes | April 17 2024 16:58:20. | |
linecache.py | File | 3864 bytes | April 17 2024 16:58:16. | |
locale.py | File | 93215 bytes | April 17 2024 16:58:19. | |
lzma.py | File | 17454 bytes | April 17 2024 16:58:20. | |
macpath.py | File | 5617 bytes | April 17 2024 16:58:15. | |
macurl2path.py | File | 2732 bytes | April 17 2024 16:58:15. | |
mailbox.py | File | 79093 bytes | April 17 2024 16:58:19. | |
mailcap.py | File | 7437 bytes | April 17 2024 16:58:14. | |
mimetypes.py | File | 20735 bytes | April 17 2024 16:58:19. | |
modulefinder.py | File | 23198 bytes | April 17 2024 16:58:14. | |
netrc.py | File | 5747 bytes | April 17 2024 16:58:17. | |
nntplib.py | File | 42786 bytes | April 17 2024 16:58:13. | |
ntpath.py | File | 20437 bytes | April 17 2024 16:58:14. | |
nturl2path.py | File | 2396 bytes | April 17 2024 16:58:20. | |
numbers.py | File | 10398 bytes | April 17 2024 16:58:20. | |
opcode.py | File | 5098 bytes | April 17 2024 16:58:21. | |
optparse.py | File | 60346 bytes | April 17 2024 16:58:20. | |
os.py | File | 34779 bytes | April 17 2024 16:58:14. | |
os2emxpath.py | File | 4659 bytes | April 17 2024 16:58:15. | |
pdb.py | File | 60653 bytes | April 17 2024 16:58:16. | |
pickle.py | File | 47858 bytes | April 17 2024 16:58:17. | |
pickletools.py | File | 81349 bytes | April 17 2024 16:58:15. | |
pipes.py | File | 8916 bytes | April 17 2024 16:58:20. | |
pkgutil.py | File | 21539 bytes | April 17 2024 16:58:15. | |
platform.py | File | 50742 bytes | April 17 2024 16:58:15. | |
plistlib.py | File | 14777 bytes | April 17 2024 16:58:13. | |
poplib.py | File | 11372 bytes | April 17 2024 16:58:13. | |
posixpath.py | File | 14254 bytes | April 17 2024 16:58:16. | |
pprint.py | File | 12700 bytes | April 17 2024 16:58:15. | |
profile.py | File | 21448 bytes | April 17 2024 16:58:17. | |
pstats.py | File | 26372 bytes | April 17 2024 16:58:14. | |
pty.py | File | 5055 bytes | April 17 2024 16:58:14. | |
py_compile.py | File | 6717 bytes | April 17 2024 16:58:19. | |
pyclbr.py | File | 13438 bytes | April 17 2024 16:58:13. | |
pydoc.py | File | 101644 bytes | April 17 2024 16:58:15. | |
queue.py | File | 8835 bytes | April 17 2024 16:58:20. | |
quopri.py | File | 7315 bytes | April 17 2024 16:58:20. | |
random.py | File | 25660 bytes | April 17 2024 16:58:14. | |
re.py | File | 14973 bytes | April 17 2024 16:58:17. | |
reprlib.py | File | 5110 bytes | April 17 2024 16:58:15. | |
rlcompleter.py | File | 5526 bytes | April 17 2024 16:58:21. | |
runpy.py | File | 10413 bytes | April 17 2024 16:58:14. | |
sched.py | File | 6399 bytes | April 17 2024 16:58:19. | |
shelve.py | File | 8243 bytes | April 17 2024 16:58:20. | |
shlex.py | File | 11502 bytes | April 17 2024 16:58:21. | |
shutil.py | File | 39147 bytes | April 17 2024 16:58:20. | |
site.py | File | 21971 bytes | April 17 2024 16:58:19. | |
smtpd.py | File | 30207 bytes | April 17 2024 16:58:16. | |
smtplib.py | File | 38021 bytes | April 17 2024 16:58:14. | |
sndhdr.py | File | 6219 bytes | April 17 2024 16:58:20. | |
socket.py | File | 14913 bytes | April 17 2024 16:58:20. | |
socketserver.py | File | 24196 bytes | April 17 2024 16:58:21. | |
sre_compile.py | File | 16345 bytes | April 17 2024 16:58:14. | |
sre_constants.py | File | 7231 bytes | April 17 2024 16:58:14. | |
sre_parse.py | File | 30212 bytes | April 17 2024 16:58:16. | |
ssl.py | File | 24478 bytes | April 17 2024 16:58:19. | |
stat.py | File | 4304 bytes | April 17 2024 16:58:19. | |
string.py | File | 9410 bytes | April 17 2024 16:58:20. | |
stringprep.py | File | 12917 bytes | April 17 2024 16:58:17. | |
struct.py | File | 238 bytes | April 17 2024 16:58:16. | |
subprocess.py | File | 67578 bytes | April 17 2024 16:58:14. | |
sunau.py | File | 17523 bytes | April 17 2024 16:58:15. | |
symbol.py | File | 2051 bytes | April 17 2024 16:58:14. | |
symtable.py | File | 7383 bytes | April 17 2024 16:58:20. | |
sysconfig.py | File | 25174 bytes | April 17 2024 16:58:20. | |
tabnanny.py | File | 11410 bytes | April 17 2024 16:58:20. | |
tarfile.py | File | 88864 bytes | April 17 2024 16:58:15. | |
telnetlib.py | File | 27349 bytes | April 17 2024 16:58:15. | |
tempfile.py | File | 23013 bytes | April 17 2024 16:58:14. | |
textwrap.py | File | 16488 bytes | April 17 2024 16:58:14. | |
this.py | File | 1003 bytes | April 17 2024 16:58:17. | |
threading.py | File | 45641 bytes | April 17 2024 16:58:19. | |
timeit.py | File | 12395 bytes | April 17 2024 16:58:15. | |
token.py | File | 3034 bytes | April 17 2024 16:58:14. | |
tokenize.py | File | 24876 bytes | April 17 2024 16:58:20. | |
trace.py | File | 31487 bytes | April 17 2024 16:58:13. | |
traceback.py | File | 11982 bytes | April 17 2024 16:58:20. | |
tty.py | File | 879 bytes | April 17 2024 16:58:13. | |
types.py | File | 3167 bytes | April 17 2024 16:58:14. | |
uu.py | File | 6766 bytes | April 17 2024 16:58:14. | |
uuid.py | File | 22349 bytes | April 17 2024 16:58:15. | |
warnings.py | File | 13825 bytes | April 17 2024 16:58:15. | |
wave.py | File | 18579 bytes | April 17 2024 16:58:15. | |
weakref.py | File | 11495 bytes | April 17 2024 16:58:19. | |
webbrowser.py | File | 22913 bytes | April 17 2024 16:58:20. | |
xdrlib.py | File | 5381 bytes | April 17 2024 16:58:21. | |
zipfile.py | File | 66424 bytes | April 17 2024 16:58:21. |
""" 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
SILENT KILLER Tool