Notes
Notes - notes.io |
x8 = '"(' + b + '|' + c + '|' + d + '|' + e + '|' + f + '|' + g + '|' + h + '|' + i + ')":"([^"|^:]*?)"'
find = r'' + x8 + ',"' + a + '":"([^"|^:]*?)",' + x8 + ',' + x8 + ',' + x8 + ',' + x8 + ',' + x8 + ',' + x8 + ',' + x8
replace = '"' + a + '":"' + r'3","' + r'1":"' + r'2","' + r'4":"' + r'5","' + r'6":"' + r'7","' + r'8":"' + r'9","' + r'10":"' + r'11","' + r'12":"' + r'13","' + r'14":"' + r'15","' + r'16":"' + r'17"'
line = re.sub(find, replace, line)
find = r'' + x8 + ',' + x8 + ',"' + a + '":"([^"|^:]*?)",' + x8 + ',' + x8 + ',' + x8 + ',' + x8 + ',' + x8 + ',' + x8
replace = '"' + a + '":"' + r'5","' + r'1":"' + r'2","' + r'3":"' + r'4","' + r'6":"' + r'7","' + r'8":"' + r'9","' + r'10":"' + r'11","' + r'12":"' + r'13","' + r'14":"'+ r'15","' + r'16":"' + r'17"'
line = re.sub(find, replace, line)
find = r'' + x8 + ',' + x8 + ',' + x8 + ',"' + a + '":"([^"|^:]*?)",' + x8 + ',' + x8 + ',' + x8 + ',' + x8 + ',' + x8
replace = '"' + a + '":"' + r'7","' + r'1":"' + r'2","' + r'3":"' + r'4","' + r'5":"' + r'6","' + r'8":"' + r'9","' + r'10":"' + r'11","' + r'12":"' + r'13","' + r'14":"' + r'15","' + r'16":"' + r'17"'
line = re.sub(find, replace, line)
find = r'' + x8 + ',' + x8 + ',' + x8 + ',' + x8 + ',"' + a + '":"([^"|^:]*?)",' + x8 + ',' + x8 + ',' + x8 + ',' + x8
replace = '"' + a + '":"' + r'9","' + r'1":"' + r'2","' + r'3":"' + r'4","' + r'5":"' + r'6","' + r'7":"' + r'8","' + r'10":"' + r'11","' + r'12":"' + r'13","' + r'14":"' + r'15","' + r'16":"' + r'17"'
line = re.sub(find, replace, line)
find = r'' + x8 + ',' + x8 + ',' + x8 + ',' + x8 + ',' + x8 + ',"' + a + '":"([^"|^:]*?)",' + x8 + ',' + x8 + ',' + x8
replace = '"' + a + '":"' + r'11","' + r'1":"' + r'2","' + r'3":"' + r'4","' + r'5":"' + r'6","' + r'7":"' + r'8","' + r'9":"' + r'10","' + r'12":"' + r'13","' + r'14":"' + r'15","' + r'16":"' + r'17"'
line = re.sub(find, replace, line)
find = r'' + x8 + ',' + x8 + ',' + x8 + ',' + x8 + ',' + x8 + ',' + x8 + ',"' + a + '":"([^"|^:]*?)",' + ',' + x8 + ',' + x8
replace = '"' + a + '":"' + r'13","' + r'1":"' + r'2","' + r'3":"' + r'4","' + r'5":"' + r'6","' + r'7":"' + r'8","' + r'9":"' + r'10","' + r'11":"' + r'12","' + r'14":"' + r'15","' + r'16":"' + r'17"'
line = re.sub(find, replace, line)
find = r'' + x8 + ',' + x8 + ',' + x8 + ',' + x8 + ',' + x8 + ',' + x8 + ',' + x8 + ',"' + a + '":"([^"|^:]*?)",' + x8
replace = '"' + a + '":"' + r'15","' + r'1":"' + r'2","' + r'3":"' + r'4","' + r'5":"' + r'6","' + r'7":"' + r'8","' + r'9":"' + r'10","' + r'11":"' + r'12","' + r'13":"' + r'14","' + r'16":"' + r'17"'
line = re.sub(find, replace, line)
find = r'' + x8 + ',' + x8 + ',' + x8 + ',' + x8 + ',' + x8 + ',' + x8 + ',' + x8 + ',' + x8 + ',"' + a + '":"([^"|^:]*?)"'
replace = '"' + a + '":"' + r'17","' + r'1":"' + r'2","' + r'3":"' + r'4","' + r'5":"' + r'6","' + r'7":"' + r'8","' + r'9":"' + r'10","' + r'11":"' + r'12","' + r'13":"' + r'14","' + r'15":"' + r'16"'
line = re.sub(find, replace, line)
return inOrder_8(line, b, c, d, e, f, g, h, i)
def inOrder_10(line, a, b, c, d, e, f, g, h, i, j):
x9 = '"(' + b + '|' + c + '|' + d + '|' + e + '|' + f + '|' + g + '|' + h + '|' + i + '|' + j + ')":"([^"|^:]*?)"'
find = r'' + x9 + ',"' + a + '":"([^"|^:]*?)",' + x9 + ',' + x9 + ',' + x9 + ',' + x9 + ',' + x9 + ',' + x9 + ',' + x9 + ',' + x9
replace = '"' + a + '":"' + r'3","' + r'1":"' + r'2","' + r'4":"' + r'5","' + r'6":"' + r'7","' + r'8":"' + r'9","' + r'10":"' + r'11","' + r'12":"' + r'13","' + r'14":"' + r'15","' + r'16":"' + r'17","' + r'18":"' + r'19"'
line = re.sub(find, replace, line)
find = r'' + x9 + ',' + x9 + ',"' + a + '":"([^"|^:]*?)",' + x9 + ',' + x9 + ',' + x9 + ',' + x9 + ',' + x9 + ',' + x9 + ',' + x9
replace = '"' + a + '":"' + r'5","' + r'1":"' + r'2","' + r'3":"' + r'4","' + r'6":"' + r'7","' + r'8":"' + r'9","' + r'10":"' + r'11","' + r'12":"' + r'13","' + r'14":"' + r'15","' + r'16":"' + r'17","' + r'18":"' + r'19"'
line = re.sub(find, replace, line)
find = r'' + x9 + ',' + x9 + ',' + x9 + ',"' + a + '":"([^"|^:]*?)",' + x9 + ',' + x9 + ',' + x9 + ',' + x9 + ',' + x9 + ',' + x9
replace = '"' + a + '":"' + r'7","' + r'1":"' + r'2","' + r'3":"' + r'4","' + r'5":"' + r'6","' + r'8":"' + r'9","' + r'10":"' + r'11","' + r'12":"' + r'13","' + r'14":"' + r'15","' + r'16":"' + r'17","' + r'18":"' + r'19"'
line = re.sub(find, replace, line)
find = r'' + x9 + ',' + x9 + ',' + x9 + ',' + x9 + ',"' + a + '":"([^"|^:]*?)",' + x9 + ',' + x9 + ',' + x9 + ',' + x9 + ',' + x9
replace = '"' + a + '":"' + r'9","' + r'1":"' + r'2","' + r'3":"' + r'4","' + r'5":"' + r'6","' + r'7":"' + r'8","' + r'10":"' + r'11","' + r'12":"' + r'13","' + r'14":"' + r'15","' + r'16":"' + r'17","' + r'18":"' + r'19"'
line = re.sub(find, replace, line)
find = r'' + x9 + ',' + x9 + ',' + x9 + ',' + x9 + ',' + x9 + ',"' + a + '":"([^"|^:]*?)",' + x9 + ',' + x9 + ',' + x9 + ',' + x9
replace = '"' + a + '":"' + r'11","' + r'1":"' + r'2","' + r'3":"' + r'4","' + r'5":"' + r'6","' + r'7":"' + r'8","' + r'9":"' + r'10","' + r'12":"' + r'13","' + r'14":"' + r'15","' + r'16":"' + r'17","' + r'18":"' + r'19"'
line = re.sub(find, replace, line)
find = r'' + x9 + ',' + x9 + ',' + x9 + ',' + x9 + ',' + x9 + ',' + x9 + ',"' + a + '":"([^"|^:]*?)",' + x9 + ',' + x9 + ',' + x9
replace = '"' + a + '":"' + r'13","' + r'1":"' + r'2","' + r'3":"' + r'4","' + r'5":"' + r'6","' + r'7":"' + r'8","' + r'9":"' + r'10","' + r'11":"' + r'12","' + r'14":"' + r'15","' + r'16":"' + r'17","' + r'18":"' + r'19"'
line = re.sub(find, replace, line)
find = r'' + x9 + ',' + x9 + ',' + x9 + ',' + x9 + ',' + x9 + ',' + x9 + ',' + x9 + ',"' + a + '":"([^"|^:]*?)",' + x9 + ',' + x9
replace = '"' + a + '":"' + r'15","' + r'1":"' + r'2","' + r'3":"' + r'4","' + r'5":"' + r'6","' + r'7":"' + r'8","' + r'9":"' + r'10","' + r'11":"' + r'12","' + r'13":"' + r'14","' + r'16":"' + r'17","' + r'18":"' + r'19"'
line = re.sub(find, replace, line)
find = r'' + x9 + ',' + x9 + ',' + x9 + ',' + x9 + ',' + x9 + ',' + x9 + ',' + x9 + ',' + x9 + ',"' + a + '":"([^"|^:]*?)",' + x9
replace = '"' + a + '":"' + r'17","' + r'1":"' + r'2","' + r'3":"' + r'4","' + r'5":"' + r'6","' + r'7":"' + r'8","' + r'9":"' + r'10","' + r'11":"' + r'12","' + r'13":"' + r'14","' + r'15":"' + r'16","' + r'18":"' + r'19"'
line = re.sub(find, replace, line)
find = r'' + x9 + ',' + x9 + ',' + x9 + ',' + x9 + ',' + x9 + ',' + x9 + ',' + x9 + ',' + x9 + ',' + x9 + ',"' + a + '":"([^"|^:]*?)"'
replace = '"' + a + '":"' + r'19","' + r'1":"' + r'2","' + r'3":"' + r'4","' + r'5":"' + r'6","' + r'7":"' + r'8","' + r'9":"' + r'10","' + r'11":"' + r'12","' + r'13":"' + r'14","' + r'15":"' + r'16","' + r'17":"' + r'18"'
line = re.sub(find, replace, line)
return inOrder_9(line, b, c, d, e, f, g, h, i, j)
if os.path.isfile("json1File.json"):
os.remove("json1File.json")
# ####################################
# # Process on XML files
# ####################################
with open('json1File.json', 'a') as fo:
#convert each xml to json
for line in open(sys.argv[1]):
#print(line.rstrip())
try:
retcode = subprocess.Popen('xsltr.exe ..\'+ sys.argv[2]+'\'+ line.rstrip() + ' xml2json.xsl output.json', shell=True).wait()
if retcode < 0:
print("Child was terminated by signal", -retcode, file=sys.stderr)
exit(1)
except OSError as e:
print("Execution failed:", e, file=sys.stderr)
#make each json as one line file
with open('new.json', 'w+') as fnew:
for line in open('output.json', 'r'):
line = line.rstrip("n")
fnew.write(line)
fnew.write("n")
#append output.json to one file
for line in open('new.json', 'r'):
line = line.replace(" ", "").lower()
# remove "edgarSubmission" : .... {"headerdata" : , "formdata" and matching braces
braceNum = re.search(r'{"edgarsubmission":{.*?"headerdata":', line).group(0).count("{")
# remove last } that is with {"EdgarSubmission"
line=rreplace(line, "}", "", braceNum)
line = re.sub(r'{"edgarsubmission":{.*?"headerdata":', '', line)
line = line.replace(',"formdata":', '')
#remove redundunt brace
line = re.sub(r'({)([^,|^:]+?)(})', r'2', line)
line = re.sub(r'[{("[a-z]*?":[^:|^,]*?)}]', r'{1}', line)
line = re.sub(r'[([a-z|-]*?)]', r'1', line)
#Iteration to the max nest level, repeat till line==line
x = True
while x:
newLine = line
# line = re.sub(r'[{(^([{)+?)}]', r'{1}', newLine)
line = re.sub(r'[{(.+?)}]', r'{1}', newLine)
x = (newLine != line)
# remove quote on flag
line = line.replace('"false"', 'false')
line = line.replace('"true"', 'true')
################### adjust the sibling order to the same as xsd-avsc
# '...name...' attribute can have ',' in it.
for x in attributes_2[:]:
line = inOrder_2(line, x[0], x[1])
for x in attributes_3[:]:
line = inOrder_3(line, x[0], x[1], x[2])
for x in attributes_4[:]:
line = inOrder_4(line, x[0], x[1], x[2], x[3])
for x in attributes_6[:]:
line = inOrder_6(line, x[0], x[1], x[2], x[3], x[4], x[5])
for x in attributes_10[:]:
line = inOrder_10(line, x[0], x[1], x[2], x[3], x[4], x[5], x[6], x[7], x[8], x[9])
fo.write(line)
if os.path.isfile("avro_reformat.json"):
os.remove("avro_reformat.json")
####################################
# Process on Avro query result
####################################
# remove the file name,
# with open('avro_queryOrdered.txt', 'r') as f:
# content = f.read()
# content(r'[0-9]+.*.XMLD.DOCUMTn', '', content, re.MSI)
print("avro query reformatting ...")
with open('avro_queryOrdered.txt', 'r') as faaa, open('avro_reformat.json', 'a') as ftmp:
#with open('3Sample.txt', 'r') as faaa, open('avro_reformat.json', 'a') as ftmp:
for line in faaa:
# remove filename and single space
line = re.sub(r'.*?{"submissiontype":', '{"submissiontype":', line)
line = line.replace(" ", "").replace("t", "").lower()
# remove null and [] value
line = re.sub(r'"[a-z]+?":[],', '', line)
line = re.sub(r',"[a-z]+?":[]', '', line)
line = re.sub(r'"[a-z0-9]+?":null,', '', line)
line = re.sub(r',"[a-z0-9]+?":null', '', line)
# remove redundunt brace
line = re.sub(r'[{("[a-z]*?":[^:|^,]*?)}]', r'{1}', line)
line = re.sub(r'[("[^:|^,]+?")]', r'1', line)
line = re.sub(r'[([a-z|-]*?)]', r'1', line)
# Iteration to the max nest level, repeat till line==line
x = True
while x:
newLine = line
#line = re.sub(r'[{(^([{)+?)}]', r'{1}', newLine)
line = re.sub(r'[{(.+?)}]', r'{1}', newLine)
x = (newLine != line )
ftmp.write(line)
print("Done")
print("avro_reformat.json compare to json1File.json returned: ", filecmp.cmp('avro_reformat.json','json1File.json', shallow=False))
|
Notes.io is a web-based application for taking notes. You can take your notes and share with others people. If you like taking long notes, notes.io is designed for you. To date, over 8,000,000,000 notes created and continuing...
With notes.io;
- * You can take a note from anywhere and any device with internet connection.
- * You can share the notes in social platforms (YouTube, Facebook, Twitter, instagram etc.).
- * You can quickly share your contents without website, blog and e-mail.
- * You don't need to create any Account to share a note. As you wish you can use quick, easy and best shortened notes with sms, websites, e-mail, or messaging services (WhatsApp, iMessage, Telegram, Signal).
- * Notes.io has fabulous infrastructure design for a short link and allows you to share the note as an easy and understandable link.
Fast: Notes.io is built for speed and performance. You can take a notes quickly and browse your archive.
Easy: Notes.io doesn’t require installation. Just write and share note!
Short: Notes.io’s url just 8 character. You’ll get shorten link of your note when you want to share. (Ex: notes.io/q )
Free: Notes.io works for 12 years and has been free since the day it was started.
You immediately create your first note and start sharing with the ones you wish. If you want to contact us, you can use the following communication channels;
Email: [email protected]
Twitter: http://twitter.com/notesio
Instagram: http://instagram.com/notes.io
Facebook: http://facebook.com/notesio
Regards;
Notes.io Team