python Python.DataTypes.Strings
Posted
tags:
篇首语：本文由小常识网(cha138.com)小编为大家整理，主要介绍了python Python.DataTypes.Strings相关的知识，希望对你有一定的参考价值。
CODE = { 'A': '.-', 'B': '-...', 'C': '-.-.',
'D': '-..', 'E': '.', 'F': '..-.',
'G': '--.', 'H': '....', 'I': '..',
'J': '.---', 'K': '-.-', 'L': '.-..',
'M': '--', 'N': '-.', 'O': '---',
'P': '.--.', 'Q': '--.-', 'R': '.-.',
'S': '...', 'T': '-', 'U': '..-',
'V': '...-', 'W': '.--', 'X': '-..-',
'Y': '-.--', 'Z': '--..',
'0': '-----', '1': '.----', '2': '..---',
'3': '...--', '4': '....-', '5': '.....',
'6': '-....', '7': '--...', '8': '---..',
'9': '----.'
}
def dictreverse(mapping):
"""
Function: dictreverse
Description: Swaps values and keys of dictionary
Input: dictionary
Output: dict with swapped key/values
Usage : a = dictreverse(c)
Notes : Returns a new dictionary with keys and values swapped.
>>> dictreverse({1: 2, 3: 4})
{2: 1, 4: 3}
"""
return dict([(value, key) for (key, value) in mapping.items()])
def string_morse(string):
global CODE
outstring = ''
msg = string
for char in msg:
outstring += " " + (CODE[char.upper()])
#print(CODE)
return outstring[1:]
def morse_string(mor):
global CODE
CODEREV = dictreverse(CODE)
outstring = ''
if mor.contains(" "):
msg = mor.split(" ")
for char in msg:
#print(char)
outstring = outstring + (CODEREV[char.upper()])
return outstring
else:
return "Input string not space separated"
def main():
print(string_morse("panagos"))
print(morse_string(string_morse("panagos")))
# print(CODE)
# print("######")
# print(dictreverse(CODE))
# print("######")
# msg = input('MESSAGE: ')
# for char in msg:
# print (CODE[char.upper()], end = '')
if __name__ == "__main__":
main()1. string_filter.py : Filter substring out of string
2. find_index.py : Find the index of specific element
3. count_occur.py : Count occurrences of a character in a string
4. remove_punctuation : Removes all punctuation characters
5. parse_string.py : Parses all non punctuation elements, stores in list
6. randomize_string.py : Randomizes a string (anagram)
7. tokenize_string.py : Tokenizes a string based on delimiter
8. to_octal.py : Converts a string to octal
9. to_dec.py : Converts a string to decimal
10.to_hex.py : Converts a string to hex
11.to_binary.py : Converts a string to binary and back
11.string_padding.py : Pads a string with specified digit, up to length
12.iter_string_sub.py : Iterate over substrings of a string
13.replace_tabs.py : Replace tab with specified number of spaces
14.count_alpha.py : Returns longer string in alphabetic order
15.count_alpha_rev.py : Returns longer string in alphabetic order (reversed)
16.count_string.py : Returns occurrences of a substring in string
17. count_string_no.py : Returns occurrences of substring in string(non overlapping)
18. count_vowels.py : Returns count of vowels in string
19. count_consonants.py : Returns count of consonants in string
20. count_numbers.py : Returns count of numbers in a string
21. count_any_string.py : Returns count of specified characters
22. count_white.py : Returns count of whitespaces in string
23. count_tab.py : Returns count of tab in string
24. count_string(Str len) : Returns total count of string characters
24. stringtotuple : Converts a string to tuple
25. stringtolist : Converts a string to list
26. listtostring : Converts a list into a string
27. tupletostring : Converts a tuple into a string
28. splitbyn : Split string into substrings of specified length
28. stringsubset : Subset strings into gradually increasing digits
29. Validatestring : Various functions for string validation
30. StringtoMorse : Converts a string to Morse code and backdef string_removemid(lista, numberstart, numberend):
'''
Function: list_removemid
Description: Removes from the mid of string
Used as: a = string_removebeg(lista, number)
Notes: Same as list_removebeg. Does not edit in place.
Works on list, tuples, strings.
'''
output_list = lista[:numberstart] + lista[numberend+1:]
return output_list
a = 'panagosasdasdasd'
b = [ 1, 2, 3, 4, "x", 5, 3, 2, 7, 6 ]
c = ( 1, 2, 3, 6, 4, 3, 2,)
print (list_removemid(b, 1, 4))
print (list_removemid(a, 1, 3))
print (list_removemid(c, 2, 5))def string_removeend(lista, number):
'''
Function: list_removeend
Description: Removes from the end of string
Used as: a = string_removebeg(lista, number)
Notes: Same as list_removebeg. Does not edit in place.
Works on list, tuples, strings.
'''
lengthof = len(lista)
calc = lengthof - number
output_list = lista[:calc]
return output_list
a = 'panagosasdasdasd'
b = [ 1, 2, 3, 4, "x", 5, 3, 2, 7, 6 ]
c = ( 1, 2, 3, 6, 4, 3, 2,)
#print (list_removeend(a, 1))
#print (list_removeend(b, 2))
#print (list_removeend(c, 1))
def string_removebeg(lista, number):
'''
Function: string_removebeg
Description: Removes from the beginning of string
Used as: a = string_removebeg(lista, number)
Notes: Same as list_removebeg. Does not edit in place.
Works on list, tuples, strings.
'''
output_list = lista[number:]
return output_list
a = 'panagosasdasdasd'
b = [ 1, 2, 3, 4, "x", 5, 3, 2, 7, 6 ]
c = ( 1, 2, 3, 6, 4, 3, 2,)
#print (list_removebeg(a, 2))
#print (list_removebeg(b, 3))
#print (list_removebeg(c, 1))def checklength(string_in):
'''
Function: checklength
Description: Checks the length of the script
Input: string
Output: Boolean
Usage: if checklength(string):
Notes: Simple validation
'''
if len(string_in) <> 29:
return False
else:
return Truedef tooct(string1):
'''
Function : Converts a string to oct
Called as : tohex(string1)
Notes : Translates everything including special characters, newlines
'''
strout = ''
for i in string1:
strout += str(oct(ord(i)))
return strout
#print (strout)def tohex(string1):
'''
Function : Converts a string to hex
Called as : tohex(string1)
Notes : Translates everything including special characters, newlines
'''
strout = ''
for i in string1:
strout += str(hex(ord(i)))
return strout
#print (strout)def tobinary(str):
#to_conv = bytes(str, "ascii")
#print(' '.join(["{0:b}".format(x) for x in to_conv]))
b = ''.join(format(ord(x), 'b') for x in str)
return b
print (tobinary("panagos"))
print (tobinary("hello world"))
def bintoascii(stri):
a = ''.join(chr(int(stri[i:i+8], 2)) for i in range(0, len(str(stri)), 8))
return a
print (bintoascii("1101000110010111011001101100110111110000011101111101111111001011011001100100"))
def tobits(s):
result = []
string = ''
for c in s:
bits = bin(ord(c))[2:]
bits = '00000000'[len(bits):] + bits
result.extend([int(b) for b in bits])
for j in result:
string += str(j)
return (result, string)
def frombits(bits):
chars = []
for b in range(int(len(bits) / 8)):
byte = bits[b*8:(b+1)*8]
chars.append(chr(int(''.join([str(bit) for bit in byte]), 2)))
return ''.join(chars)
print (tobits("panagos")[1])
b = tobits("panagos")[1]
print (frombits(b))
def strtotuple(string):
out = ()
for s in string:
out = out + (s,)
return out
print (strtotuple(b))def stringsubsets(string1):
'''
Name: String Subsets
Function: stringsubsets(string)
Input: string, or string variable
Output: list
Usage: a = stringsubsets(string1)
Notes: Used anywhere, no modules required
'''
i = 0
output = []
for j in range(1, len(string1) + 1, 1):
output.append(string1[:j])
return output
print (stringsubsets("panagos"))def anagram(string):
'''
Function: anagram
Description: Makes an anagram out of a string
Input: string
Output: anagrammed string
Usage: a = anagram(string)
Notes: Does not edit in place, requires random module
'''
import random
lista = []
outLista = []
outstring = ''
x = 0
# Convert to list
for i in string:
lista.append(i)
for i in (range(len(lista))):
x = random.randint(0,(len(lista)-1))
outLista.append(lista[x])
del lista[x]
for i in outLista:
outstring = outstring + str(i)
return outstring
print (anagram('panos'))##################################
#Composing together this function and the split method from the previous section makes a useful combination — we’ll clean out the punctuation, and split will clean out the newlines and tabs while turning the string into a list of words:
# Needs the remove punctuation function!!!!!!
my_story = """
Pythons are constrictors, which means that they will 'squeeze' the life
out of their prey. They coil themselves around their prey and with
each breath the creature takes the snake will squeeze a little tighter
until they stop breathing completely. Once the heart stops the prey
is swallowed whole. The entire animal is digested in the snake's
stomach except for fur or feathers. What do you think happens to the fur,
feathers, beaks, and eggshells? The 'extra stuff' gets passed out as ---
you guessed it --- snake POOP! """
wds = remove_punctuation(my_story).split()
print(wds)
#The output:
#['Pythons', 'are', 'constrictors', ... , 'it', 'snake', 'POOP']
def parse_string(s):
'''
Function: parse_string
Description: Parse given string to words, sort in array
Input: string
Output: Array of words
Usage: b = parse_string(s)
Notes: Will split on single whitespace
'''
def remove_punctuation(s):
punctuation = "!\"#$%&'()*+,-./:;<=>?@[\\]^_`{|}~"
s_sans_punct = ""
for letter in s:
if letter not in punctuation:
s_sans_punct += letter
return s_sans_punct
temp = remove_punctuation(s).split()
return temp
my_story = """
Pythons are constrictors, which means that they will 'squeeze' the life
out of their prey. They coil themselves around their prey and with
each breath the creature takes
"""
#wds = remove_punctuation(my_story).split()
wds = (parse_string(my_story))
print(wds)def padstring(str,target,padding, position = 1):
'''
Function: padstring
Description: Pads a string with specified padding up to target
Input: string, target number (ie 30), padding (ie 'O'), position = 1 or 0
Output: string with padding to the left or right
Usage: a = padstring(string, 30, '0', 1)
Notes: Does not edit string in place
Notes2: Position(1) = Left padding / Position(2) = Right Padding
'''
outstring = ''
length = len(str)
if target < length:
return False
elif target == length:
return str
else:
# Calc dif
diffdigit = target - length
tempstring = (padding)*(int(diffdigit))
if position == 1:
outstring = tempstring + str
return outstring
else:
outstring = str + tempstring
return outstring
a = 'abcdsdfsdfd'
print (padright(a, 15, '0', 0))def listtostr(list):
out = ''
for s in list:
out += str(s)
return outdef iter_slices(string, slice_length):
"""
Function: iter_slices
Description: Iterates over specified substrings of a string
Input: string, slice_length
Output: slice_length pieces of string
Notes: Iterate over slices of a string.
Usage: See below.
"""
pos = 0
while pos < len(string):
yield string[pos:pos + slice_length]
pos += slice_length
if __name__ == '__main__':
s = "abcdefg"
for i in iter_slices(s, 2):
print i
#result:
#ab
#cd
#ef
#g
def find(strng, ch):
'''
Function: find_index
Description: Find and return the index of ch in strng. Return -1 if ch does not occur in strng.
Input: string, character
Output: index of character in string, or -1
Usage: print (find(str,char))
'''
ix = 0
while ix < len(strng):
if strng[ix] == ch:
return ix
ix += 1
return -1
test(find("Compsci", "p") == 3)
test(find("Compsci", "C") == 0)
test(find("Compsci", "i") == 6)
test(find("Compsci", "x") == -1)
############33
def find2(strng, ch, start):
'''
Function: find2
Description: Find and return the index of ch in strng. Return -1 if ch does not occur in strng.
Input: string, character, start digit
Output: index of character in string, or -1
Usage: print (find2(str,char))
Notes: Search after specific index in string (Start)
'''
ix = start
while ix < len(strng):
if strng[ix] == ch:
return ix
ix += 1
return -1
test(find2("banana", "a", 2) == 3)
##############
def findimpr(strng, ch, start=0):
'''
Function: findimpr
Description: Find and return the index of ch in strng. Return -1 if ch does not occur in strng.
Input: string, character, start digit
Output: index of character in string, or -1
Usage: print (find(str,char))
Notes: Search after specific index in string (Start)
Notes: Same as above, but default start equals to zero
'''
ix = start
while ix < len(strng):
if strng[ix] == ch:
return ix
ix += 1
return -1
###############
def find(strng, ch, start=0, end=None):
ix = start
if end is None:
end = len(strng)
while ix < end:
if strng[ix] == ch:
return ix
ix += 1
return -1
# ########################
# Function : countwhite
# Usage : countconso(string)
# Example : print countconso(string)
# Output : Counts the amount of whitespace
# Note : Pre declared consonants, all.
# Method : Iterates over letters in string, checks if each letter exists "in" the
# provided list, and if it does it increments the num_conso.
#
# Define Function
def countwhite(string):
# initialize variable
num_numbers=0
# iterate over string
for char in string:
# iterate over list of characters
if char in " ":
num_numbers += 1
return num_numbers
# count = str(countwhite(s))
# print ( "Number of Vowels : " + count )# ########################
# Function : countvowel
# Usage : countvowel(string)
# Example : print countvowel(string,'bob')
# Output : Counts the amout of vowels
# Note : Pre declared vowels, all.
# Method : Uses "asdasd".count(pattern) method.
#
# Define Function
def countvowel(string):
# initialize variable
num_vowels=0
# iterate over string
for char in string.lower:
# iterate over list of characters
if char in "aeiouyw":
num_vowels += 1
return num_vowels
# count = str(countvowel(s))
# print ( "Number of Vowels : " + count )
# ##
## ########################
# Function : countwhite
# Usage : countconso(string)
# Example : print countconso(string)
# Output : Counts the amount of whitespace
# Note : Pre declared consonants, all.
# Method : Iterates over letters in string, checks if each letter exists "in" the
# provided list, and if it does it increments the num_conso.
#
# Define Function
def countwhite(string):
# initialize variable
num_numbers=0
# iterate over string
for char in string:
# iterate over list of characters
if char in "\t":
num_numbers += 1
return num_numbers
# count = str(countwhite(s))
# print ( "Number of Vowels : " + count )
print ("Count tab is : " + str(countwhite("pana\t\t\t")))# ########################
# Function : countnonoverlap
# Usage : countnonoverlap(string,pattern,casesensitive=True/False)
# Example : print countnonoverlap(string,'bob')
# Output : Counts the count of occurences of 'pattern' in a string
# Note : Counts non overlapping occurences
# Method : Uses "asdasd".count(pattern) method.
#
# Define Function
def countnonoverlap(string,pattern,casesensitive=True):
# Check for case sensitivity
if casesensitive != True:
string = string.lower()
pattern = string.lower()
# Set the length of the pattern to l
l = len(pattern)
# Initialize a counter at zero
ct = 0
return string.count(pattern)
# DEBUG
#test = 'my maaather lies over the oceaaan'
#print (test)
#print (countnonoverlap(test,'a'))
#print (countnonoverlap(test,'aa'))
#print (countnonoverlap(test,'aaa'))
# ##
#def countchar(string1):
'''
Name: countchar
Function: countchar(string1)
Input: string
Output: integer
Usage: print (countchar("Panagos 341234 ####$$ 111"))
Notes: Any string can be passed
'''
counter = 0
for j in string1:
counter += 1
return counter
print (countchar("Panagos 341234 ####$$ 111"))def count_a(text,chara):
'''
Function: count_a
Description: Counts occurrences of character, in text
Input: String, character
Output: Number of encountered instances
Usage: test(count_a("banana") == 3)
Usage: print (count_a(text1,chara))
'''
count = 0
for c in text:
if c == str(chara):
count += 1
return(count)
# ########################
# Function : countconso
# Usage : countconso(string)
# Example : print countconso(string,'bob')
# Output : Counts the amount of consonants
# Note : Pre declared consonants, all.
# Method : Iterates over letters in string, checks if each letter exists "in" the
# provided list, and if it does it increments the num_conso.
#
# Define Function
def countnumbers(string):
# initialize variable
num_numbers=0
# iterate over string
for char in string:
# iterate over list of characters
if char in "1234567890":
num_numbers += 1
return num_numbers
# count = str(countvowel(s))
# print ( "Number of Vowels : " + count )# ########################
# Function : countconso
# Usage : countconso(string)
# Example : print countconso(string,'bob')
# Output : Counts the amount of consonants
# Note : Pre declared consonants, all.
# Method : Iterates over letters in string, checks if each letter exists "in" the
# provided list, and if it does it increments the num_conso.
#
# Define Function
def countconso(string):
# initialize variable
num_conso=0
# iterate over string
for char in string.lower:
# iterate over list of characters
if char in "qrtpsdfghjklzxcvbnm":
num_conso += 1
return num_conso
# count = str(countconso(s))
# print ( "Number of Consonants : " + count )
# ##
## ########################
# Function : countany
# Usage : countany(string,letters)
# Example : print countconso(string,'bhf')
# Output : Counts the amount of all letters supplies in "letters"
# Note : Letters must be passed encased in " "
# Method : Iterates over letters in string, checks if each letter exists "in" the
# provided list, and if it does it increments the num_conso.
#
# Define Function
def countany(string,letters):
# initialize variable
num_letters=0
# iterate over string
for char in string:
# iterate over list of characters
if char in letters:
num_letters += 1
return num_letters
# count = str(countany(s,'brutal'))
# print ( "Number of Vowels : " + count )
# ##
## ###################
# Function : countalpharev
# Usage : countalpha(s) -> s = string
# Example : print (countalpha(panagos)
# Output : Longest string in reverse alphabetic order
# Note : Counts overlapping occurences
# Method : Iterates over each letter, and compares it to the next
# if the next is lexically smaller, then it sets currentsub to the concatenation
# of the two. If not it sets currentsub to the character in check and continues.
# The moment it finds a string longer than currentsub it assigns to massub.
#
# Define a new function
def countalpharev(s):
# Initialize variables for max substring, current, and previous char
maxSub = ''
currentSub = ''
previousChar = ''
# Iterate over every char and check with the previous
for char in s:
# If current is bigger than previous, then the currentsub is the concatenation
if char <= previousChar:
currentSub = currentSub + char
# If the length of current sub is greater than the max, assign
if len(currentSub) > len(maxSub):
maxSub = currentSub
# If its not, then assign the value of char to currentsub
else: currentSub = char
# Assign char to previous char to proceed with iteration
previousChar = char
return maxSub
# DEBUG
# print (countalpharev(panagos)
# ##
## ###################
# Function : countalpha
# Usage : countalpha(s) -> s = string
# Example : print (countalpha(panagos)
# Output : Longest string in alphabetic order
# Note : Counts overlapping occurences
# Method : Iterates over each letter, and compares it to the next
# if the next is lexically bigger, then it sets currentsub to the concatenation
# of the two. If not it sets currentsub to the character in check and continues.
# The moment it finds a string longer than currentsub it assigns to massub.
#
# Define a new function
def countalpha(s):
# Initialize variables for max substring, current, and previous char
maxSub = ''
currentSub = ''
previousChar = ''
# Iterate over every char and check with the previous
for char in s:
# If current is bigger than previous, then the currentsub is the concatenation
if char >= previousChar:
currentSub = currentSub + char
# If the length of current sub is greater than the max, assign
if len(currentSub) > len(maxSub):
maxSub = currentSub
# If its not, then assign the value of char to currentsub
else: currentSub = char
# Assign char to previous char to proceed with iteration
previousChar = char
return maxSub
# DEBUG
# print (countalpha(panagos)def tupletostr(tuple):
'''
Name: tupletostr
Function: Tuple to string
Input: tuple
Output: string
Usage: b = tupletostr(tuple1)
Notes: Any tuple can be passed
'''
out = ''
for x in tuple:
out = out + str(x)
return out input = 'John,Doe,1984,4,1,male'
a = 'a;b;g;c;d'
def tokenize_string(str,delim):
'''
Function: tokenize_string
Description: Tokenizes a string based on spec. delimiter
Input: string, delimiter
Output: List of tokens
Usage: a = tokenize_string(string, 'delimiter')
Notes: Parses strings
'''
tokens = str.split(delim)
outlist = []
for j in tokens:
outlist.append(j)
return outlist
print (tokenize_string(a,';'))
print (tokenize_string(a,'a'))
print (tokenize_string(a,','))def todec(string1):
'''
Function : Converts a string to oct
Called as : tohex(string1)
Notes : Translates everything including special characters, newlines
Notes: Converts to ASCII
'''
strout = ''
for i in string1:
strout += str((ord(i)))
return strout
#print (strout)def strtolist(string):
out = []
for s in string:
out.append(s)
return outdef splitbyn(str, n):
'''
Function: splitbyn
Description: Splits a string into substrings of n length
Input: String, length of string
Output: string
Usage: print (splitbyn("panagos", 3))
'''
output = ''
while str:
output = output + str[:n] + ' '
str = str[n:]
return output
print (splitbyn("panagos", 3))def replace_tab(s, tabstop = 4):
result = str()
for c in s:
if c == '\t':
while (len(result) % tabstop != 0):
result += ' ';
else:
result += c
return resultpunctuation = "!\"#$%&'()*+,-./:;<=>?@[\\]^_`{|}~"
def remove_punctuation(s):
'''
Function: remove_punctuation
Description: Removes all punctuation elements from string
Input: String with punctuation
Output: String with out punctuation
Usage: newstr = remove_punctuation(oldstr)
Notes: Does not edit in place
'''
punctuation = "!\"#$%&'()*+,-./:;<=>?@[\\]^_`{|}~"
s_sans_punct = ""
for letter in s:
if letter not in punctuation:
s_sans_punct += letter
return s_sans_punct
###############################3
def remove_punctuation(s):
'''
Function: remove_punctuation
Description: Removes all punctuation elements from string
Input: String with punctuation
Output: String with out punctuation
Usage: newstr = remove_punctuation(oldstr)
Notes: Does not edit in place, uses import string
'''
import string
s_without_punct = ""
for letter in s:
if letter not in string.punctuation:
s_without_punct += letter
return s_without_punct
test(remove_punctuation('"Well, I never did!", said Alice.') ==
"Well I never did said Alice")
test(remove_punctuation("Are you very, very, sure?") ==
"Are you very very sure")
##################################
#Composing together this function and the split method from the previous section makes a useful combination — we’ll clean out the punctuation, and split will clean out the newlines and tabs while turning the string into a list of words:
my_story = """
Pythons are constrictors, which means that they will 'squeeze' the life
out of their prey. They coil themselves around their prey and with
each breath the creature takes the snake will squeeze a little tighter
until they stop breathing completely. Once the heart stops the prey
is swallowed whole. The entire animal is digested in the snake's
stomach except for fur or feathers. What do you think happens to the fur,
feathers, beaks, and eggshells? The 'extra stuff' gets passed out as ---
you guessed it --- snake POOP! """
wds = remove_punctuation(my_story).split()
print(wds)
#The output:
#['Pythons', 'are', 'constrictors', ... , 'it', 'snake', 'POOP']def removesub(x,substr):
'''
Function: removesub
Description : Removes first occurrence fo substring from string
Input: x (string)
substr (substring)
Output: String with removed substring
Usage: print (removesub("tralala","lala"))
'''
sublen = len(substr)
strlen = len(x)
loop = 0
while loop+sublen < strlen:
loop = loop +1;
if x[loop:loop+sublen] == substr:
return x[0:loop]+x[loop+sublen:strlen]
#print subsub('tototalalatolatalala','talala')以上是关于python Python.DataTypes.Strings的主要内容，如果未能解决你的问题，请参考以下文章