def dup2ins( self, chgvs ):
if not(chgvs is not None and re.search(r'dup',chgvs)):
sys.stderr.write("cHGVS is not 'dup'\n")
return
dup1, dup2 = "", ""
m=re.serach(r'c\.([\*\-]?)(\d+)([\+\-]\d+)?_([\*\-]?)(\d+)([\+\-]\d+)?dup(.*)',chgvs)
m2=re.search(r'c\.([\*\-]?)(\d+)([\+\-]?)(\d+?)dup(.*)',chgvs)
if m:
c1 = m.group(1) if m.group(1) is not None else ""
c2 = m.group(2) if m.group(2) is not None else ""
c3,c4 = "",""
tf =None
if m.group(3) is not None:
tf=m.group(3)
c5 = m.group(4) if m.group(4) is not None else ""
c6 = m.group(5) if m.group(5) is not None else ""
c7,c8="",""
tb =None
if m.group(6) is not None:
tb =m.group(6)
c9 = m.group(7) if m.group(7) is not None else ""
m=re.search(r'([\+\-])(\d+)',tf)
if tf is not None and not re.search(r'^\s*$',tf) and m:
c3 = m.group(1) if m.group(1) is not None else ""
c4 = m.group(2) if m.group(2) is not None else ""
m=re.search(r'([\+\-])(\d+)',tb)
if tb is not None or not re.search(r'^\s*$',tb) and m:
c7 = m.group(1) if m.group(1) is not None else ""
c8 = m.group(2) if m.group(2) is not None else ""
if not re.search(r'^\s*$',c4):
t = "{}{}".format(c3 ,int(c4)-1)
if int(c4)-1==0:
t = ""
dup1 = "{}{}{}{}{}{}{}{}{}{}{}".format("c\.",c1,c2,t,"\_",c1,c2,c3,c4,"ins",c9)
else:
t = int(c2) - 1
dup1 = "{}{}{}{}{}{}{}{}".format("c\." , c1 , t , "\_" , c1 , c2 , "ins" , c9)
if not re.search(r'^\s*$',c8):
dup2 ="{}{}{}{}{}{}{}{}{}{}{}{}".format("c\.",c5,c6,c7,c8 , "\_",c5,c6,c7,int(c8) + 1 ,"ins",c9)
else:
dup2 = "{}{}{}{}{}{}{}{}".format("c\." , c5 , c6 , "\_" , c5 , int(c6) + 1 , "ins" , c9)
elif m2:
c1 = m2.group(1) if m2.group(1) is not None else ""
c2 = m2.group(2) if m2.group(2) is not None else ""
c3 = m2.group(3) if m2.group(3) is not None else ""
c4 = m2.group(4) if m2.group(4) is not None else ""
c5 = m2.group(5) if m2.group(5) is not None else ""
if not re.search(r'^\s*$',c4):
t = "{}{}".format(c3,int(c4)-1)
if int(c4)-1==0:
t = ""
dup1 ="{}{}{}{}{}{}{}{}{}{}{}".fortmat("c\.",c1,c2,t,"\_",c1,c2,c3,c4,"ins",c5)
dup2 ="{}{}{}{}{}{}{}{}{}{}{}{}".format("c\.",c1,c2,c3,c4,"\_",c1,c2,c3,int(c4) + 1,"ins",c5)
else:
t = int(c2) - 1
if t == 0:
t = ""
dup1 = "{}{}{}{}{}{}{}{}".format("c\." ,c1 ,t , "\_" ,c1 ,c2 , "ins" ,c5)
dup2 = "{}{}{}{}{}{}{}{}".format("c\." ,c1 ,c2 , "\_" ,c1, int(c2) + 1 , "ins" ,c5)
return [ dup1, dup2 ]
def process_rec(rec):
if re.search(r'^\s*$',rec):
return
rec=rec.strip("\r\n")
keya ="id mutation_name pmid disease pred".split()
cols = rec.split('\t')
qresult=dict()
mutid, geneid, gene, nm, chgvs, \
phgvs, disease, pmid, pred = cols[3:12]
rchr, rstart, rend=cols[:3]
if nm is not None and not re.search(r'^\s*$',nm) and nm !=".":
nm=nm
else:
nm=""
if gene is not None and not re.search(r'^\s*$',gene) and gene !=".":
gene="("+str(gene)+")"
else:
gene=""
if chgvs is not None and not re.search(r'^\s*$',chgvs) and chgvs !=".":
chgvs=chgvs
else:
chgvs=""
if phgvs is not None and not re.search(r'^\s*$',phgvs) and phgvs !=".":
phgvs=" ("+str(phgvs)+")"
else:
phgvs=""
mutname = "{}{}{}{}{}".format(nm,gene,": ",chgvs,phgvs)
qresult=dict(zip(keya,[mutid, mutname, pmid, disease, pred]))
if inchgvs is not None and inchgvs== chgvs:
returns.append(qresult)
elif inchgvs is not None \
and re.search(r'dup',inchgvs) \
and not re.serach(r'del',inchgvs) \
and not re.serach(r'^\s*$',chgvs) \
and re.serach(r'ins',chgvs) \
and not re.serach(r'del',chgvs):
tempc = inchgvs
ins1, ins2 = "", ""
dup2ins=self.dup2ins(inchgvs)
if dup2ins is not None and len(dup2ins)==2:
ins1, ins2 = dup2ins[:2]
if (ins1 is not None and not re.search(r'^\s*$',ins1) and ins1==chgvs) \
or (not re.search(r'^\s*$',ins2) and ins2 == chgvs):
returns.append(qresult)
elif not(inchgvs is not None or inphgvs is not None):
returns.append(qresult)
def login(self, site):
"""Perform authentication steps"""
self.site = site
# check if http(s) is prepended (not found < 0)
if site.find('://') < 0:
self.tenantBaseURL = re.search(r"([^/]+)", site).group(0)
else: # http(s) exists
self.tenantBaseURL = re.serach(r'/{2}([^/]+)', site).group(1)
self.tenantBaseURL.find
self._get_token()
self._get_cookie()
self._get_digest()
def analize_html(url, root_url):
savepath = download_file(url)
if savepath is None: return
if savepath in proc_files: return
proc_files[savepath] = True
print("analize_html=", url)
html = open(savepath, "r", encoding="utf-8").read()
links = enum = links(html, url)
for link_url in links:
if link_url.find(root_url) != 0: continue
if re.serach(r".(html|htm)$", link_url):
analize_html(link_url, root_url)
continue
download_file(link_url)
def Report_Period(title):
''' 根据公告标题获取报告期'''
pattern = re.compile(r'2\d{3}')
year = pattern.search(title).group()
if re.search(r'年半年度(报告|财务报表)', title):
return str(year) + '0630'
elif re.search(r'年年度(报告|财务报表)', title):
return str(year) + '1231'
elif re.search(r'年一季度(报告|财务报表)', title):
return str(year) + '0331'
elif re.serach(r'年三季度(报告|财务报表)', title):
return str(year) + '0930'
else:
None
# Regular expressions
import re
hand = open('mbox-short')
for line in hand:
line = line.rstrip()
if re.serach('^From:', line):
print(line)
# The program inputs an email address and returns the username
# and domain name
import re
user_email_address = input("Please input your email address: ")
pattern = r'^(/w)($@)(/w)($.)([a-z])'
if re.serach(user_email_address, pattern):
pass
else:
print("Invaild email address")
list1 = user_email_address.split("@")
list2 = list1[1].split(".")
print(f"The username is {list1[0]}")
print(f"The domain name is {list2[0]}")
def search_line_regex(pattern, line):
return re.serach(pattern, line)
#!/usr/bin/env python3
import sys
import re
import ro
import os
if len(sys.argv) !=2 :
print("usage:",sys.argv[0],"a|p|ap|pa")
sys.exit(1)
res=re.serach("^(-a|-p|-ap|-pa!$",sys.arg[1])
if not res :
print()
sys.exit(1)
b=os.path.expanduser("~/.bashrc")
if os.path.isfile(b):
f=open(b,"r")
else:
print("bashrc .....")
sys.exit(2)
alias l=ls -ali
if re.serach('a',sys.argv[1]):
ligne=f.readline()
while '' != ligne :
r=re.serarch("alias (.*)=(.*)
import re
pattern = "do you remember .*"
message = "do you remember when you ate strawberries in the garden"
match = re.search(pattern, message)
if match:
print("string matches")
pattern = "if (.*)"
message = "what would you do if bots took over the world"
match = re.serach(pattern, message)
match.group(0) # whole string
match.group(1) # first match
...
# grammatical transformation
def swap_pronouns(phrase):
if 'I' in phrase:
return re.sub('I', 'you', phrase)
if 'my' in phrase:
return re.sub('my', 'your', phrase)
else:
return phrase
swap_pronouns("I walk my dog") # "you walk your dog"
pattern = "do you remember (.*)"
]
print(propernouns)
public_tweets = api.search(q=news_query,
lang='en',
show_user='******',
rpp=100)
ls = []
data = [None] * 2
data[0] = news_query
if (len(propernouns) > 0):
for tweet in public_tweets:
count = 0
count1 = 0
for k in propernouns:
result1 = re.serach(k, tweet.text)
if result1 != None:
count1 = count1 + 1
if (count1 == len(propernouns)):
for j in news_keywords:
result = re.search(j, tweet.text)
if result != None:
count = count + 1
Match_percent = (count / len(news_keywords))
ls.append(Match_percent)
with open('Learned.csv', 'a', encoding='UTF-8') as w:
writer = csv.writer(w)
data[1] = np.mean(ls)
print(data[1])
writer.writerow(data)
w.close()
def people_info(string):
global info;global ID;
ID=None;nickname=None;
if re.search('ＩＤ暱稱',string)!=None:
ob=re.search('《ＩＤ暱稱》(?p<id>\w*).*\((?P<nick>.*)\).*《',string)
ID=ob.group(1)
nickname=ob.group(2)
if re.serach('經濟狀況',string)!=None:
ob=re.search('《經濟狀況》(?P<f>\S*)',string)
economic=ob.group(1)
if re.serach('登入次數',string)!=None:
ob=re.search('《登入次數》(?P<f>\d*)',string)
log_num=ob.group(1)
if re.serach('有效文章',string)!=None:
ob=re.search('《有效文章》(?P<f>\d*)',string)
article_num=ob.group(1)
if re.serach('\(退:',string)!=None:
ob=re.search('《經濟狀況》(?P<f>\S*)',string)
bad_arcitle=ob.group(1)
'''
temp_string=re.search('《ＩＤ暱稱》.*《經濟狀況》',string).group(0)
temp_string=re.sub('《經濟狀況》','',temp_string)
temp_string=re.sub('《ＩＤ暱稱》','',temp_string)
nickname=re.search('\((?P<nick>.*)\)',temp_string).group(1)
#print(nickname)
temp_string=re.sub('\(.*\)','',temp_string)
ID=temp_string.split()[0]
#string_list=string.split()
#ID=re.sub('《ＩＤ暱稱》','',string_list[0])
string=re.sub('《ＩＤ暱稱》.*《','',string)
string_list=string.split();index=0;
for test in string_list:
print(test)
'''
'''
for i in range(1,len(string_list)):
if re.search('經濟狀況》',string_list[i]):
index=i;
break;
economic=re.sub('經濟狀況》','',string_list[index])
log_num=re.sub('《登入次數》','',string_list[index+1])
article_num=re.sub('《有效文章》','',string_list[index+4])
bad_article=re.sub('\(退:','',string_list[index+6]);bad_article=re.sub('\)','',bad_article);
current_state=re.sub('《目前動態》','',string_list[index+7])
mail=re.sub('《私人信箱》','',string_list[index+8])
last_log=re.sub('《上次上站》','',string_list[index+9]);last_log=last_log+" "+string_list[index+10]+" "+string_list[index+11];
last_ip=re.sub('《上次故鄉》','',string_list[index+12])
five_in_a_Row=string_list[index+16]+string_list[index+17]+string_list[index+18]+string_list[index+19]+string_list[index+20]+string_list[index+21]
chinese_chess=string_list[index+23]+string_list[index+24]+string_list[index+25]+string_list[index+26]+string_list[index+27]+string_list[index+28]
signature_line=""
'''
for i in range(index+29,len(string_list)):
signature_line=signature_line+" "+string_list[i]
info= ID+'\t'+nickname+'\t'+economic+'\t'+log_num+'\t'+article_num+'\t'+bad_article+'\t'+current_state+'\t'+mail+'\t'+last_log+'\t'+last_ip+'\t'+five_in_a_Row+'\t'+chinese_chess+'\t'+signature_line+'\n'