'''

T._detect( b'\x1b'*1) ### {'encoding': None, 'confidence': 0.0, 'language': None}

_detect 可能返回 {'encoding': None, 'confidence': None}

'''

r=_detect(abytes)

if r['encoding'] in ['Windows-1254' ]:

try:

if abytes.decode('utf-8').encode('utf-8')==abytes:

return 'utf-8'

except Exception as e:

pass

if r['encoding'] in ['gb2312','GB2312' ]:

try:

if abytes.decode('gb18030').encode('gb18030')==abytes:

return 'gb18030'

except Exception as e:

pass

if r['confidence'] and r['confidence']>confidence:return r['encoding']

else:

if default:return default

# raise Exception

return py.No(abytes,r,msg=

'T.detect encoding {1} confidence {2} less then {3} {0}'.format(

import uncurl

U,T,N,F=py.importUTNF()

if not sc:sc=U.cbg()

rs=uncurl.parse(sc)

global U,T,N,F

U,T,N,F=py.importUTNF()

row=[]

for k,v in ka.items():

if py.len(k)<2:raise py.NotImplementedError()

n=py.int(k[1:])

row.append(U.StrRepr(v,size=n))

'''C:\test\github\TradingView-Machine-Learning-GUI\requirements.txt

'''

global U,T,N,F

U,T,N,F=py.importUTNF()

d={}

for line in F.readlines(f):

line=line.strip()

if not line:continue

if '==' in line:

name,v=line.split('==')

else:

name,v=line,None

d[name]=v

# r.append(line)

import email,io

message=email.message_from_file(io.StringIO(t))

'''

[[0, '__class__', requests_toolbelt.multipart.decoder.BodyPart],

[1, '__delattr__', <method-wrapper '__delattr__' of BodyPart object at 0x000002B990690EC8>],

[2, '__dict__', {'encoding': 'utf-8', 'content': b'8000000', 'headers': {b'Content-Disposition': b'form-data; name="MAX_FILE_SIZE"'}}],

[3, '__dir__', <function BodyPart.__dir__()>],

[4,

'__doc__',

'\n\n The ``BodyPart`` object is a ``Response``-like interface to an individual\n subpart of a multipart response. It is expected that these will\n generally be created by objects of the ``MultipartDecoder`` class.\n\n Like ``Response``, there is a ``CaseInsensitiveDict`` object named headers,\n ``content`` to access bytes, ``text`` to access unicode, and ``encoding``\n to access the unicode codec.\n\n '],

....

[26, 'content', b'8000000'],

[27, 'encoding', 'utf-8'],

[28, 'headers', {b'Content-Disposition': b'form-data; name="MAX_FILE_SIZE"'}],

[29, 'text', '8000000']]

'''

from requests_toolbelt.multipart import decoder

# a = b"--ce560532019a77d83195f9e9873e16a1\r\nContent-Disposition: form-data; name=\"author\"\r\n\r\nJohn Smith\r\n--ce560532019a77d83195f9e9873e16a1\r\nContent-Disposition: form-data; name=\"file\"; filename=\"example2.txt\"\r\nContent-Type: text/plain\r\nExpires: 0\r\n\r\nHello World\r\n--ce560532019a77d83195f9e9873e16a1--\r\n"

# content_type = "multipart/form-data; boundary=ce560532019a77d83195f9e9873e16a1"

# content_type = 'multipart/form-data; boundary=----WebKitFormBoundaryZXuC4Jc1YZng6box'

if py.istr(a):

a=a.encode()

if not content_type:

h=a.splitlines()[0].decode().strip()[2:]

content_type= fr'multipart/form-data; boundary={h}'

r=[]

for part in decoder.MultipartDecoder(a, content_type).parts:

print(part.text)

r.append(part)

# return a,content_type,r

if py.len(a)==1 and not py.isint(a[0]):

a=a[0]

if py.len(a)==1 and a[0]> 0x110000:

s=py.hex(a[0])[2:]

ms=py.len(s)

if ms%2!=0:raise py.ArgumentError('0xAABBCC long a % 2 ! 0 ')

ta=[]

for i in py.range(0,ms,2):

i=py.int('0x' s[i:i 2],16)

ta.append(i)

a=ta

s=''

for i in a:

s =py.chr(i)

global U,T,N,F

U,T,N,F=py.importUTNF()

r=[]

for c in s:

i=py.ord(c)

if hex:

i=U.IntRepr(i,repr=_0x py.hex(i)[2:].upper(),)

r.append(i)

import unicodedata

r=[]

for i in c:

r.append(unicodedata.name(c))

if py.len(c)==1:

return r[0]

else:

r''' pip install PyPDF2

AttributeError: function/symbol 'ARC4_stream_init' not found in library 'C:\QGB\Anaconda3\lib\site-packages\Crypto\Util\..\Cipher\_ARC4.cp37-win_amd64.pyd': error 0x7f

https://github.com/py-pdf/PyPDF2/issues/1192

'''

if '://' in filename_or_url:

U,T,N,F=py.importUTNF()

filename=N.HTTP.get_bytes(filename_or_url,return_only_filename=True,skip_if_exist=True,print_req=True,**ka) #if file exist, no print_req

else:

filename=filename_or_url

import PyPDF2

reader=PyPDF2.PdfReader(filename)

# text = ""

for page in reader.pages:

# text = page.extract_text() "\n"

yield page.extract_text() # page_splitor

''' zh-cn 大陆简体; zh-tw 台灣正體; zh-hk 香港繁體

u'元旦快樂'

'''

from zhconv import convert

''' one str list return {}

'''

from difflib import SequenceMatcher

substring_counts={}

for i,s in py.enumerate(names):

for j in range(i 1,len(names)):

string1 = names[i]

string2 = names[j]

match = SequenceMatcher(None, string1, string2).find_longest_match(0, len(string1), 0, len(string2))

matching_substring=string1[match.a:match.a match.size]

if(matching_substring not in substring_counts):

substring_counts[matching_substring]=1

else:

substring_counts[matching_substring] =1

U,T,N,F=py.importUTNF()

r=[[],[],[],[]] #十位 个位 a b

if b:mb=py.len(b)

else:mb=0

w10=0

for n,c in py.enumerate(a):

if (n 1)%line_max==0:

r

# r[2].append('\n'*4)

if escape_eol and c in escape_eol:

c=py.repr(c)[1:-1]

w=T.wcswidth(c)

else:

w=T.wcswidth(c)

w10 =w

r[1].append(T._09[n] ' '*(w-1))

if n==9:

s10=py.str(n//10)

r[0].append(s10 ' '*(w10-py.len(s10)))

w10=0

r[2].append(c)

if n<mb:

r[3].append(b[n])

r= '\n'.join([''.join(row) for row in r])

if p:U.pln(r)

''' '''

import difflib

seq = difflib.SequenceMatcher(isjunk=isjunk_function, a=a,b=b)

ratio = seq.ratio()

repr=a.encode("unicode_escape").decode('ascii')

# if StrRepr:

U,T,N,F=py.importUTNF()

return U.StrRepr(a,repr=repr)

# else:

''' '''

T

RE_VAR

'''

pandas.read_html first argument "io" : str, path object or file-like object

A URL, a file-like object, or a raw string containing HTML. Note that

lxml only accepts the http, ftp and file url protocols. If you have a

URL that starts with ``'https'`` you might try removing the ``'s'``.

'''

U,T,N,F=py.importUTNF()

if html_or_url.startswith('https://'):

html_or_url=N.HTTP.get(html_or_url)

import pandas

''' '''

U,T,N,F=py.importUTNF()

u=T.regex_match_all(a,T.RE_GIT)[0]

us=u.split('/')

user,repo=us[-2],us[-1]

U,T,N,F=py.importUTNF()

r=[]

row_lens=U.len(*a)

maxs=[0]* py.max(row_lens)

U,T,N,F=py.importUTNF()

r={}

max_k,max_v=0,0

id0=0

id_1=0

def fk(a,*aa,**ka):

nonlocal max_k

# py.pdb()()

# U.get_or_set('fk',[]).append([a,py.id(a)])

r=T.padding(py.repr(a._qgb_obj),size=max_k)

if py.id(a._qgb_obj)==id0:

r="\n" r

return r

def fv(a):

nonlocal max_v

# U.get_or_set('fv',[]).append([a,py.id(a._qgb_obj)])

r=T.padding(py.repr(a._qgb_obj),size=max_v)

if py.id(a._qgb_obj)==id_1:

r=r ",\n\n" #TODO '一个\n 在IPython 中显示不出来。'

return r

for n,(k,v) in py.enumerate(d.items()):

s=py.repr(k)

nk=T.wcswidth(s)

if nk>max_k:

max_k=nk

sv=py.repr(v)

nv=T.wcswidth(sv)

if nv>max_v:

max_v=nv

if n==0:

id0=py.id(k)

# print('id0:',id0)

r[U.object_custom_repr(k,repr=fk)]=U.object_custom_repr(v,repr=fv)

else:#只有break后才不执行else

id_1=py.id(v)

# print(n,k,v,id_1)

# r[U.StrRepr(k,repr=s)]=U.StrRepr(v,repr=T.padding(1,size=3))

T=py.importT()

dc={}

for n,l in py.enumerate(s.split(';')):

l=l.strip()

name=T.sub(l,'','=')

v=l[len(name) 1:]

if name in dc:raise py.Exception('cookie name conflict?',name)

dc[name]=v

#print(l)

# print(n,name,v)

#break

r=[]

for s in a:

r.extend(s.splitlines())

'''

numpy.loadtxt("myfile.txt")[:, 1]

fname : file, str, or pathlib.Path

File, filename, or generator to read. If the filename extension is

``.gz`` or ``.bz2``, the file is first decompressed. Note that

generators should return byte strings for Python 3k.

'1\r\n2\r\n4'.splitlines()

['1', '2', '4']

'1\n2\r\n4'.splitlines()

['1', '2', '4']

'''

U=py.importU()

if py.islist(text):

rs=text

elif row in ['\n','\r\n']:

rs=text.splitlines()

else:

rs=text.split(row)

r=[]

for i,v in py.enumerate(rs):

if strip:v=v.strip()

if skip_empty_line and not v:continue

cs=re.split(col,v)

if StrRepr:

StrRepr_ka={}

if py.isint(StrRepr) and StrRepr>1:

StrRepr_ka['size']=StrRepr

row=[U.StrRepr(i,**StrRepr_ka) for i in cs]

else:

row=cs

r.append(row)

return r

# import numpy as np

# np.loadtxt("myfile.txt")[:, 1]

try:

return target in text

except Exception as e:

''' not only for str '''

if py.isinstance(start,py.slice):

if stop==None and step==1:

start,stop,step=start.start,start.stop,start.step

else:

raise py.ArgumentError('conflict',start,stop,step)

if not py.isint(start):

len=py.len(start)

if len==1:start=start[0]

if len==2 and stop==None:start,stop=start

if len==2 and stop==None and step==1:

start,stop,step=start

try:

return a[start:stop:step]

except Exception as e:

U=py.importU()

a=U.get_duplicated_kargs(ka,'A',default=a)

b=U.get_duplicated_kargs(ka,'B',default=b)

c=U.get_duplicated_kargs(ka,'C',default=c)

return_target=U.get_duplicated_kargs(ka,'return_target','return_t','t','target',default=return_target)

c_StrRepr=U.get_duplicated_kargs(ka,'c_StrRepr','crepr','cstrrepr',default=c_StrRepr)

case_sensitive=U.get_duplicated_kargs(ka,'cs','case','upper','caseSensitive',default=case_sensitive)

return_dict=U.get_duplicated_kargs(ka,'d','return_dict','rd','dict',default=return_dict)

index=U.get_duplicated_kargs(ka,'index','i','n',default=index)

r=[]

d={}

def _append(t,i,sub=''):

if return_dict:

if sub:

U.dict_add_value_list(d,t,(i,sub))

else :U.dict_add_value_list(d,t,i)

else:

row=[i]

if sub:

row.append( sub)

if return_target:

row.insert(0,t)

if index:

row.insert(0,py.len(r))

r.append(row)

len_text_digits=py.len(str(py.len(text))) #不是digitals

c_isint=py.isint(c)

c_len_2= U.len(c)==2

for t in py.set(targets):

i=0

# re.finditer(re.escape)

while True:

i=text.find(t,i)

if i==-1:break

else:

if a or b or c:

c0=py.max(i-a,0)

c1=i py.len(t) b

if c:

if c_isint:

c0=py.max(i-c,0)

c1=i py.len(t) c

elif c_len_2:

c0=text.rfind(c[0],0,i)

c1=text.find(c[1],i)

if c0==-1 or c0-i>default_c_size:c0=i-(default_c_size//2)

if c1==-1 or i-c1>default_c_size:c1=i-(default_c_size//2)

c0 =1

else:

raise py.ArgumentUnsupported(c)

if c_StrRepr:

_append( t,U.IntRepr(i,size=len_text_digits 1),U.StrRepr(text[c0:c1],size=default_c_size) )

else:

_append( t,i,text[c0:c1] )

else:

_append(t,i,)

i =1 # 不然 死循环

if merge_sub and c_len_2 and r:

dt={}

for row in r:

head=row[:-1]

if py.len(head)==1:head=head[0]

U.dict_add_value_list(dt,row[-1],head)

r=py.list(dt.items())

if r:return r

if d:return d

s=''

last='' # alphan:a oherchar:c

for c in chars:

if c in alphanumeric:

if not last:

c=quote c

if last=='c':

c=' ' quote c

last='a'

else:

c=chr_func(c)

if not last:pass

if last=='a':

c=quote ' ' c

if last=='c':

c=' ' c

last='c'

s =c

if last=='a':s =quote

U=py.importU()

'''rjust() 返回一个原字符串右对齐, 在左边填充

'''

# from wcwidth import wcswidth

from wcwidth import wcwidth

width = 0

for n,c in py.enumerate(s):

wcw = wcwidth(c)

if width>=size:

break

if wcw < 0:

width = 0

else:

width = wcw

"""

Given a unicode string, return its printable length on a terminal.

Return the width, in cells, necessary to display the first ``n``

characters of the unicode string ``pwcs``. When ``n`` is None (default),

return the length of the entire string.

if a non-printable character is encountered. 0 width added

#TODO :

T.wcswidth('Stack Overflow на русском')==25 # should be 34

"""

# pylint: disable=C0103

# Invalid argument name "n"

from wcwidth import wcwidth

end = len(pwcs) if n is None else n

idx = py.slice(0, end)

width = 0

for char in pwcs[idx]:

wcw = wcwidth(char)

if wcw < 0:

width = 0

else:

width = wcw

T=py.importT()

start='async function {}('.format(function_name)

end='}}//end {}'.format(function_name)

#format string '}}'表示一个 },否则 ValueError: Single '}' encountered in format string

r=T.sub(source,start,end)

if not r:

start='function {}('.format(function_name)

r=T.sub(source,start,end)

if not r:

return py.No('not found function {} in js source'.format(function_name),source,start,end)

return start r end

from lxml import etree

h= etree.tostring(e, pretty_print=True).decode()

if '&#' in h:

h=html_decode(h)

''' xpath(astr<optional > ,xpath,file=''<only_optional_ka> ):

'''

from lxml import etree

U=py.importU()

sa_err='ArgumentError: You must provide (either astr or file<only_optional_ka>) and xpath , '

# print(len(a))

if len(a)>2:

return py.No(sa_err 'but got len(a)==%s'% len(a),a,ka)

astr=U.get_duplicated_kargs(ka,'a','ast','astr','s','st','t','text','txt','h','html')

file=U.get_duplicated_kargs(ka,'file','f','FILE','fileName','filename')#last

xpath=U.get_duplicated_kargs(ka,'xpath','x','XPath','xp')

if not xpath:

if len(a) == 1:

if not astr and not file:

return py.No(sa_err 'but only got 1 argument',a)

xpath=a[0]

elif len(a)==2:

if astr:return py.No(sa_err 'but got duplicated [astr]')

astr =a[0]

xpath=a[1]

if file:

if astr or len(a)!=1:

return py.No(sa_err 'not both. len(a)==%s>1'%len(a))

F=py.importF()

file=F.auto_path(file)

e= etree.parse(file, etree.HTMLParser())

else:

e= etree.fromstring(astr, etree.HTMLParser())

'''textwrap.wrap(text, width=70, **kwargs)

47: zhuanlan code max len

'''

U=py.importU()

replace_whitespace=U.get_duplicated_kargs(ka,'replace_whitespace','remove_old_eol','del_eol','del_old')

import textwrap

if not eol:

if '\r\n' in s:

eol='\r\n'

else:

eol='\n'

return eol.join(

textwrap.wrap(s, width=width, replace_whitespace=replace_whitespace)

import re

IDCARD_REGEX = '[1-9][0-9]{14}([0-9]{2}[0-9X])?'

if isinstance(idcard, int):

idcard = str(idcard)

if not re.match(IDCARD_REGEX, idcard):

return py.No('IDCARD_REGEX not match',idcard)

items = [int(item) for item in idcard[:-1]]

## 加权因子表

factors = (7, 9, 10, 5, 8, 4, 2, 1, 6, 3, 7, 9, 10, 5, 8, 4, 2)

## 计算17位数字各位数字与对应的加权因子的乘积

copulas = sum([a * b for a, b in zip(factors, items)])

## 校验码表

ckcodes = ('1', '0', 'X', '9', '8', '7', '6', '5', '4', '3', '2')

''' 144 break line in default Win R Cmd window

'''

# from IPython.utils.text import columnize as _columnize

if not py.iterable(iterable):return py.repr(iterable)

U,T,N,F=py.importUTNF()

width=U.get_duplicated_kargs(ka,'size','width','row_width',default=width)

import IPython.utils.text

#TODO dict columnize

# { k1:v

# k2:[small list]

# k3:[long,list,

# auto ident

# and columnize]

# k4:and recursively

# }

if py.isdict(iterable):

return pformat( iterable )

# return pformat( {k:pformat(v) for k,v in iterable.items() } )

r= IPython.utils.text.columnize([pformat(i) for i in iterable],

row_first=True, separator=' , ', displaywidth=width)

''' ljust() 方法返回一个原字符串左对齐,并使用空格填充右边至指定长度的新字符串。

#当提供size 参数时，小心 ModuleNotFoundError: No module named 'wcwidth' # 已经fix部分情况

rpcServer [U.StrRepr(T.az,size=26)]没有错误详情， repr(U.StrRepr(T.az,size=26)) 就有出错详情

'''

s= string(s)

if size<1:

return s

# raise py.ArgumentError('size must > 0',size)

if not method:

try:

from wcwidth import wcwidth

method=wc_ljust

except Exception as e:

method='ljust'

if py.istr(method):

if cut and len(s)>=size:

return s[:size]

return py.getattr(s,method)(size,char) #

if py.callable(method):

if cut and wcswidth(s)>=size:

return wc_cut(s,size)

return method(s,size,char) #TODO 统一参数

'''

codecs.encode(obj, encoding='utf-8', errors='strict')

'''

def return_error(e):

U,T,N,F=py.importUTNF()

return U.StrRepr('')

return py.No(e)

try:

return s.encode(encoding)

except LookupError:

import codecs

try:

return codecs.encode(s,encoding=encoding)

except Exception as e:

return return_error(e)

except Exception as e:

all_args=py.importU().getArgsDict()

U=py.importU();F=py.importF()

sp=F.mkdir(diff_bytes.__name__)

rf=[]

for k,v in all_args.items():

# print(k,v)

if not py.isbytes(v):continue

f=F.write('{}{}={}'.format(sp,filename_legalized(k),len(v), ) ,v)

rf.append(f)

if py.isbytes(b1):b1=b1.splitlines()

if py.isbytes(b2):b2=b2.splitlines()

import difflib

context = difflib.context_diff

r=difflib.diff_bytes(context, b1 ,b2 )

r=b''.join(r)

if p:

print(r)

else:

rf.insert(0,' '*33)

rf.insert(0,r)

import difflib

U,T,N,F=py.importUTNF()

enumerate=U.get_duplicated_kargs(ka,'n','index',default=enumerate)

def tolist(a):

r=[]

if enumerate:

for i,c in py.enumerate(a):

if eol:

r.append('{}:{}\n'.format(i,c))

else:

r.append('{}:{}'.format(i,c))

else:

if eol:

r=[c '\n' for c in a]

else:

r=py.list(a)

return r

expected=tolist(expected)

actual=tolist(actual)

# diff=difflib.unified_diff(enumerate(expected), enumerate(actual))

diff=difflib.unified_diff(expected, actual)

r=''.join(diff)

if p:

print(r,'\n diff_len:%s'%len(r))

return U.StrRepr(r,repr='#T.diff(p=1) result,len:%s'%py.len(r))

else:

"""https://docs.python.org/zh-cn/3/library/difflib.html

Compare two sequences of lines; generate the delta as a unified diff.

Helper function. Returns a string containing the unified diff of two multiline strings.

s.splitlines(keepends=False)

"""

import difflib

U,T,N,F=py.importUTNF()

if pformat:

pformat=T.pformat

try:

pformat=py.from_qgb_import('ipy').pformat

except:pass

if not py.istr(expected):

expected=pformat(expected)

if not py.istr(actual):

actual=pformat(actual)

expected=expected.splitlines(True)

actual=actual.splitlines(True)

diff=difflib.unified_diff(expected, actual)

r=''.join(diff)

if p:

print(r,'\n diff_len:%s'%len(r))

return U.StrRepr(r,repr='#T.diff(p=1) result,len:%s'%py.len(r))

else:

if py.istr(iter):

return iter

else:

si=py.str(_layer)

if prepend_layer:

return s.join([recursive_join(si s,i,_layer=_layer 1,

prepend_layer=True,append_layer=append_layer,format_layer=format_layer

) for i in iter])

if append_layer:

return s.join([recursive_join(s si,i,_layer=_layer 1,

prepend_layer=prepend_layer,append_layer=True,format_layer=format_layer

) for i in iter])

if format_layer:

return s.join([recursive_join(s.format(_layer),i,_layer=_layer 1,

prepend_layer=prepend_layer,append_layer=append_layer,format_layer=True

) for i in iter])

'''T.join( ###<py.No )==''

In [1612]: T.join(1)