Find common substring between two strings - python

I'd like to compare 2 strings and keep the matched, splitting off where the comparison fails.
So if I have 2 strings:
string1 = "apples"
string2 = "appleses"
answer = "apples"
Another example, as the string could have more than one word:
string1 = "apple pie available"
string2 = "apple pies"
answer = "apple pie"
I'm sure there is a simple Python way of doing this but I can't work it out, any help and explanation appreciated.

For completeness, difflib in the standard-library provides loads of sequence-comparison utilities. For instance find_longest_match which finds the longest common substring when used on strings. Example use:
from difflib import SequenceMatcher
string1 = "apple pie available"
string2 = "come have some apple pies"
match = SequenceMatcher(None, string1, string2).find_longest_match()
print(match) # -> Match(a=0, b=15, size=9)
print(string1[match.a:match.a + match.size]) # -> apple pie
print(string2[match.b:match.b + match.size]) # -> apple pie
If you're using a version older than 3.9, you'need to call find_longest_match() with the following arguments:
SequenceMatcher(None, string1, string2).find_longest_match(0, len(string1), 0, len(string2))

One might also consider os.path.commonprefix that works on characters and thus can be used for any strings.
import os
common = os.path.commonprefix(['apple pie available', 'apple pies'])
assert common == 'apple pie'
As the function name indicates, this only considers the common prefix of two strings.

def common_start(sa, sb):
""" returns the longest common substring from the beginning of sa and sb """
def _iter():
for a, b in zip(sa, sb):
if a == b:
yield a
else:
return
return ''.join(_iter())
>>> common_start("apple pie available", "apple pies")
'apple pie'
Or a slightly stranger way:
def stop_iter():
"""An easy way to break out of a generator"""
raise StopIteration
def common_start(sa, sb):
return ''.join(a if a == b else stop_iter() for a, b in zip(sa, sb))
Which might be more readable as
def terminating(cond):
"""An easy way to break out of a generator"""
if cond:
return True
raise StopIteration
def common_start(sa, sb):
return ''.join(a for a, b in zip(sa, sb) if terminating(a == b))

Its called Longest Common Substring problem. Here I present a simple, easy to understand but inefficient solution. It will take a long time to produce correct output for large strings, as the complexity of this algorithm is O(N^2).
def longestSubstringFinder(string1, string2):
answer = ""
len1, len2 = len(string1), len(string2)
for i in range(len1):
match = ""
for j in range(len2):
if (i + j < len1 and string1[i + j] == string2[j]):
match += string2[j]
else:
if (len(match) > len(answer)): answer = match
match = ""
return answer
print(longestSubstringFinder("apple pie available", "apple pies"))
print(longestSubstringFinder("apples", "appleses"))
print(longestSubstringFinder("bapples", "cappleses"))
Output
apple pie
apples
apples

Fix bugs with the first's answer:
def longestSubstringFinder(string1, string2):
answer = ""
len1, len2 = len(string1), len(string2)
for i in range(len1):
for j in range(len2):
lcs_temp = 0
match = ''
while ((i+lcs_temp < len1) and (j+lcs_temp<len2) and string1[i+lcs_temp] == string2[j+lcs_temp]):
match += string2[j+lcs_temp]
lcs_temp += 1
if len(match) > len(answer):
answer = match
return answer
print(longestSubstringFinder("dd apple pie available", "apple pies"))
print(longestSubstringFinder("cov_basic_as_cov_x_gt_y_rna_genes_w1000000", "cov_rna15pcs_as_cov_x_gt_y_rna_genes_w1000000")
print(longestSubstringFinder("bapples", "cappleses"))
print(longestSubstringFinder("apples", "apples"))

The same as Evo's, but with arbitrary number of strings to compare:
def common_start(*strings):
""" Returns the longest common substring
from the beginning of the `strings`
"""
def _iter():
for z in zip(*strings):
if z.count(z[0]) == len(z): # check all elements in `z` are the same
yield z[0]
else:
return
return ''.join(_iter())

The fastest way I've found is to use suffix_trees package:
from suffix_trees import STree
a = ["xxxabcxxx", "adsaabc"]
st = STree.STree(a)
print(st.lcs()) # "abc"

This script requests you the minimum common substring length and gives all common substrings in two strings. Also, it eliminates shorter substrings that longer substrings include already.
def common_substrings(str1,str2):
len1,len2=len(str1),len(str2)
if len1 > len2:
str1,str2=str2,str1
len1,len2=len2,len1
#short string=str1 and long string=str2
min_com = int(input('Please enter the minumum common substring length:'))
cs_array=[]
for i in range(len1,min_com-1,-1):
for k in range(len1-i+1):
if (str1[k:i+k] in str2):
flag=1
for m in range(len(cs_array)):
if str1[k:i+k] in cs_array[m]:
#print(str1[k:i+k])
flag=0
break
if flag==1:
cs_array.append(str1[k:i+k])
if len(cs_array):
print(cs_array)
else:
print('There is no any common substring according to the parametres given')
common_substrings('ciguliuana','ciguana')
common_substrings('apples','appleses')
common_substrings('apple pie available','apple pies')

Try:
import itertools as it
''.join(el[0] for el in it.takewhile(lambda t: t[0] == t[1], zip(string1, string2)))
It does the comparison from the beginning of both strings.

def matchingString(x,y):
match=''
for i in range(0,len(x)):
for j in range(0,len(y)):
k=1
# now applying while condition untill we find a substring match and length of substring is less than length of x and y
while (i+k <= len(x) and j+k <= len(y) and x[i:i+k]==y[j:j+k]):
if len(match) <= len(x[i:i+k]):
match = x[i:i+k]
k=k+1
return match
print matchingString('apple','ale') #le
print matchingString('apple pie available','apple pies') #apple pie

A Trie data structure would work the best, better than DP.
Here is the code.
class TrieNode:
def __init__(self):
self.child = [None]*26
self.endWord = False
class Trie:
def __init__(self):
self.root = self.getNewNode()
def getNewNode(self):
return TrieNode()
def insert(self,value):
root = self.root
for i,character in enumerate(value):
index = ord(character) - ord('a')
if not root.child[index]:
root.child[index] = self.getNewNode()
root = root.child[index]
root.endWord = True
def search(self,value):
root = self.root
for i,character in enumerate(value):
index = ord(character) - ord('a')
if not root.child[index]:
return False
root = root.child[index]
return root.endWord
def main():
# Input keys (use only 'a' through 'z' and lower case)
keys = ["the","anaswe"]
output = ["Not present in trie",
"Present in trie"]
# Trie object
t = Trie()
# Construct trie
for key in keys:
t.insert(key)
# Search for different keys
print("{} ---- {}".format("the",output[t.search("the")]))
print("{} ---- {}".format("these",output[t.search("these")]))
print("{} ---- {}".format("their",output[t.search("their")]))
print("{} ---- {}".format("thaw",output[t.search("thaw")]))
if __name__ == '__main__':
main()
Let me know in case of doubts.

In case we have a list of words that we need to find all common substrings I check some of the codes above and the best was https://stackoverflow.com/a/42882629/8520109 but it has some bugs for example 'histhome' and 'homehist'. In this case, we should have 'hist' and 'home' as a result. Furthermore, it differs if the order of arguments is changed. So I change the code to find every block of substring and it results a set of common substrings:
main = input().split(" ") #a string of words separated by space
def longestSubstringFinder(string1, string2):
'''Find the longest matching word'''
answer = ""
len1, len2 = len(string1), len(string2)
for i in range(len1):
for j in range(len2):
lcs_temp=0
match=''
while ((i+lcs_temp < len1) and (j+lcs_temp<len2) and string1[i+lcs_temp] == string2[j+lcs_temp]):
match += string2[j+lcs_temp]
lcs_temp+=1
if (len(match) > len(answer)):
answer = match
return answer
def listCheck(main):
'''control the input for finding substring in a list of words'''
string1 = main[0]
result = []
for i in range(1, len(main)):
string2 = main[i]
res1 = longestSubstringFinder(string1, string2)
res2 = longestSubstringFinder(string2, string1)
result.append(res1)
result.append(res2)
result.sort()
return result
first_answer = listCheck(main)
final_answer = []
for item1 in first_answer: #to remove some incorrect match
string1 = item1
double_check = True
for item2 in main:
string2 = item2
if longestSubstringFinder(string1, string2) != string1:
double_check = False
if double_check:
final_answer.append(string1)
print(set(final_answer))
main = 'ABACDAQ BACDAQA ACDAQAW XYZCDAQ' #>>> {'CDAQ'}
main = 'homehist histhome' #>>> {'hist', 'home'}

def LongestSubString(s1,s2):
if len(s1)<len(s2) :
s1,s2 = s2,s1
maxsub =''
for i in range(len(s2)):
for j in range(len(s2),i,-1):
if s2[i:j] in s1 and j-i>len(maxsub):
return s2[i:j]

Returns the first longest common substring:
def compareTwoStrings(string1, string2):
list1 = list(string1)
list2 = list(string2)
match = []
output = ""
length = 0
for i in range(0, len(list1)):
if list1[i] in list2:
match.append(list1[i])
for j in range(i + 1, len(list1)):
if ''.join(list1[i:j]) in string2:
match.append(''.join(list1[i:j]))
else:
continue
else:
continue
for string in match:
if length < len(list(string)):
length = len(list(string))
output = string
else:
continue
return output

**Return the comman longest substring**
def longestSubString(str1, str2):
longestString = ""
maxLength = 0
for i in range(0, len(str1)):
if str1[i] in str2:
for j in range(i + 1, len(str1)):
if str1[i:j] in str2:
if(len(str1[i:j]) > maxLength):
maxLength = len(str1[i:j])
longestString = str1[i:j]
return longestString

This is the classroom problem called 'Longest sequence finder'. I have given some simple code that worked for me, also my inputs are lists of a sequence which can also be a string:
def longest_substring(list1,list2):
both=[]
if len(list1)>len(list2):
small=list2
big=list1
else:
small=list1
big=list2
removes=0
stop=0
for i in small:
for j in big:
if i!=j:
removes+=1
if stop==1:
break
elif i==j:
both.append(i)
for q in range(removes+1):
big.pop(0)
stop=1
break
removes=0
return both

As if this question doesn't have enough answers, here's another option:
from collections import defaultdict
def LongestCommonSubstring(string1, string2):
match = ""
matches = defaultdict(list)
str1, str2 = sorted([string1, string2], key=lambda x: len(x))
for i in range(len(str1)):
for k in range(i, len(str1)):
cur = match + str1[k]
if cur in str2:
match = cur
else:
match = ""
if match:
matches[len(match)].append(match)
if not matches:
return ""
longest_match = max(matches.keys())
return matches[longest_match][0]
Some example cases:
LongestCommonSubstring("whose car?", "this is my car")
> ' car'
LongestCommonSubstring("apple pies", "apple? forget apple pie!")
> 'apple pie'

This isn't the most efficient way to do it but it's what I could come up with and it works. If anyone can improve it, please do. What it does is it makes a matrix and puts 1 where the characters match. Then it scans the matrix to find the longest diagonal of 1s, keeping track of where it starts and ends. Then it returns the substring of the input string with the start and end positions as arguments.
Note: This only finds one longest common substring. If there's more than one, you could make an array to store the results in and return that Also, it's case sensitive so (Apple pie, apple pie) will return pple pie.
def longestSubstringFinder(str1, str2):
answer = ""
if len(str1) == len(str2):
if str1==str2:
return str1
else:
longer=str1
shorter=str2
elif (len(str1) == 0 or len(str2) == 0):
return ""
elif len(str1)>len(str2):
longer=str1
shorter=str2
else:
longer=str2
shorter=str1
matrix = numpy.zeros((len(shorter), len(longer)))
for i in range(len(shorter)):
for j in range(len(longer)):
if shorter[i]== longer[j]:
matrix[i][j]=1
longest=0
start=[-1,-1]
end=[-1,-1]
for i in range(len(shorter)-1, -1, -1):
for j in range(len(longer)):
count=0
begin = [i,j]
while matrix[i][j]==1:
finish=[i,j]
count=count+1
if j==len(longer)-1 or i==len(shorter)-1:
break
else:
j=j+1
i=i+1
i = i-count
if count>longest:
longest=count
start=begin
end=finish
break
answer=shorter[int(start[0]): int(end[0])+1]
return answer

First a helper function adapted from the itertools pairwise recipe to produce substrings.
import itertools
def n_wise(iterable, n = 2):
'''n = 2 -> (s0,s1), (s1,s2), (s2, s3), ...
n = 3 -> (s0,s1, s2), (s1,s2, s3), (s2, s3, s4), ...'''
a = itertools.tee(iterable, n)
for x, thing in enumerate(a[1:]):
for _ in range(x+1):
next(thing, None)
return zip(*a)
Then a function the iterates over substrings, longest first, and tests for membership. (efficiency not considered)
def foo(s1, s2):
'''Finds the longest matching substring
'''
# the longest matching substring can only be as long as the shortest string
#which string is shortest?
shortest, longest = sorted([s1, s2], key = len)
#iterate over substrings, longest substrings first
for n in range(len(shortest)+1, 2, -1):
for sub in n_wise(shortest, n):
sub = ''.join(sub)
if sub in longest:
#return the first one found, it should be the longest
return sub
s = "fdomainster"
t = "exdomainid"
print(foo(s,t))
>>>
domain
>>>

def LongestSubString(s1,s2):
left = 0
right =len(s2)
while(left<right):
if(s2[left] not in s1):
left = left+1
else:
if(s2[left:right] not in s1):
right = right - 1
else:
return(s2[left:right])
s1 = "pineapple"
s2 = "applc"
print(LongestSubString(s1,s2))

Related

Count number of occurences of certain character in two strings with Python

I want to count the number of times both a occurs, and b occurs in both strings together, using recursion in Python.
For example if the input was ('aabb', 'bbba'), the output would be (3,5) because there are three a's and five b's total.
What I have tried:
def counting(string1, string2):
if not string1:
return 0
elif string1[0]=='a':
return 1+counting(string[1:],string2)
else:
return counting(string[1:],string2)
Your mistake is referencing an invalid variable. You tried to access the variable string in this line:
return counting(string[1:],string2)
... where it should have been string1. You can fix it like so:
return counting(string1[1:],string2)
Via recursion:
NOTE: If you merge both the strings before then you can further simplify this algorithm
def counting(s, v):
if not s:
return 0
elif s[0] == v:
return 1+counting(s[1:], v)
else:
return counting(s[1:], v)
def count(s1, s2):
return (counting(s1, 'a') + counting(s1, 'b')), (counting(s2, 'a') + counting(s2, 'b'))
count('aaab','bba') # will print (4,3)
Via Counter:
You can merge both the string and then count value:
from collections import Counter
print(Counter(''.join(('aabb', 'bbba'))).values()) #[3,5]
updated function:
def counting(string1, string2):
return Counter(string1+string2).values()
counting('aab','bbb')
UPDATE
Considering your specifiaction in the comments, I came up with this:
def counting(string1: str, string2: str) -> tuple[int, int]:
if not string1 and not string2:
return 0, 0
if not string1:
str1a = str1b = 0
elif string1[0] == "a":
str1a, str1b = 1, 0
else:
str1a, str1b = 0, 1
if not string2:
str2a = str2b = 0
elif string2[0] == "a":
str2a, str2b = 1, 0
else:
str2a, str2b = 0, 1
next_round = counting(string1[1:], string2[1:])
return next_round[0] + str1a + str2a, next_round[1] + str1b + str2b
print(counting("aabb", "bbba"))
>> (3, 5)
Old answer:
Your recursive function is working pretty well, however keeping track of two variables with two letters each can become quite hard with recursion. I would suggest that you use your recursive function for counting the occurrence of one letter in one word at a time and then adding up the results.
In order to make it more extensible in the future (more/other words, more/other letters to count) you could create a function like this:
# You only count the occurrence of one letter in one word.
def counting(string: str, letter: str) -> int:
if not string:
return 0
elif string[0] == letter:
return 1 + counting(string[1:], letter)
else:
return counting(string[1:], letter)
# here you add up the results
def get_all_occurrences(word_list: list[str], letter_list: list[str]) -> tuple[int]:
letters_profile = []
for letter in letter_list:
letter_occurrences = 0
for word in word_list:
letter_occurrences += counting(word, letter)
letters_profile.append(letter_occurrences)
return tuple(letters_profile)
words = ["aabb", "abbb"]
letters = ["a", "b"]
occurrences = get_all_occurrences(words, letters)
print(occurrences)

How to find the longest common substring between two strings using Python?

I want to write a Python code that computes the longest common substring between two strings from the input.
Example:
word1 = input('Give 1. word: xlaqseabcitt')
word2 = input('Give 2. word: peoritabcpeor')
Wanted output:
abc
I have code like this so far:
word1 = input("Give 1. word: ")
word2 = input("Give 2. word: ")
longestSegment = ""
tempSegment = ""
for i in range(len(word1)):
if word1[i] == word2[i]:
tempSegment += word1[i]
else:
tempSegment = ""
if len(tempSegment) > len(longestSegment):
longestSegment = tempSegment
print(longestSegment)
I end up with IndexError when word2 is shorter than word1, and it does not give me the common substring.
EDIT: I found this solution:
string1 = input('Give 1. word: ')
string2 = input('Give 2. word: ')
answer = ""
len1, len2 = len(string1), len(string2)
for i in range(len1):
for j in range(len2):
lcs_temp=0
match=''
while ((i+lcs_temp < len1) and (j+lcs_temp<len2) and string1[i+lcs_temp] == string2[j+lcs_temp]):
match += string2[j+lcs_temp]
lcs_temp+=1
if (len(match) > len(answer)):
answer = match
print(answer)
However, I would like to see a library function call that could be used to compute the longest common substring between two strings.
Alternatively, please suggest a more concise code to achieve the same.
You can build a dictionary from the first string containing the positions of each character, keyed on the characters. Then go through the second string and compare the substring of each character with the rest of the second string at that position:
# extract common prefix
def common(A,B) :
firstDiff = (i for i,(a,b) in enumerate(zip(A,B)) if a!=b) # 1st difference
commonLen = next(firstDiff,min(len(A),len(B))) # common length
return A[:commonLen]
word1 = "xlaqseabcitt"
word2 = "peoritabcpeor"
# position(s) of each character in word1
sub1 = dict()
for i,c in enumerate(word1): sub1.setdefault(c,[]).append(i)
# maximum (by length) of common prefixes from matching first characters
maxSub = max((common(word2[i:],word1[j:])
for i,c in enumerate(word2)
for j in sub1.get(c,[])),key=len)
print(maxSub) # abc
For me, looks like the solution that works is using the suffix_trees package:
from suffix_trees import STree
a = ["xxx ABC xxx", "adsa abc"]
st = STree.STree(a)
print(st.lcs()) # "abc"
Here is an answer if you later want to compute any number of strings. It should return the longest common substring. It work with the different test i gave it. (as long as you don't use the '§' character)
It is not a library but you can still import the functions in your code just like a library. You can use the same logic with your own code (only for two strings.) Do so as follows (put both files in the same directory for the sake of simplicity). I am supposing you will call the file findmatch.py.
import findmatch
longest_substring = findmatch.prep(['list', 'of', 'strings'])
Here is the code that should be in 'findmatch.py'.
def main(words,first):
nextreference = first
reference = first
for word in words:
foundsub = False
print('reference : ',reference)
print('word : ', word)
num_of_substring = 0
length_longest_substring = 0
for i in range(len(word)):
print('nextreference : ', nextreference)
letter = word[i]
print('letter : ', letter)
if word[i] in reference:
foundsub = True
num_of_substring += 1
locals()['substring'+str(num_of_substring)] = word[i]
print('substring : ', locals()['substring'+str(num_of_substring)])
for j in range(len(reference)-i):
if word[i:i+j+1] in reference:
locals()['substring'+str(num_of_substring) ]= word[i:i+j+1]
print('long_sub : ',locals()['substring'+str(num_of_substring)])
print('new : ',len(locals()['substring'+str(num_of_substring)]))
print('next : ',len(nextreference))
print('ref : ', len(reference))
longer = (len(reference)<len(locals()['substring'+str(num_of_substring)]))
longer2 = (len(nextreference)<len(locals()['substring'+str(num_of_substring)]))
if (num_of_substring==1) or longer or longer2:
nextreference = locals()['substring'+str(num_of_substring)]
if not foundsub:
for i in range(len(words)):
words[i] = words[i].replace(reference, '§')
#§ should not be used in any of the strings, put a character you don't use here
print(words)
try:
nextreference = main(words, first)
except Exception as e:
return None
reference = nextreference
return reference
def prep(words):
first = words[0]
words.remove(first)
answer = main(words, first)
return answer
if __name__ == '__main__':
words = ['azerty','azertydqse','fghertqdfqf','ert','sazjjjjjjjjjjjert']
#just some absurd examples any word in here
substring = prep(words)
print('answer : ',substring)
It is basically creating your own library.
I hope this aswers helps someone.
Here is a recursive solution :
def lcs(X, Y, m, n):
if m == 0 or n == 0:
return 0
elif X[m - 1] == Y[n - 1]:
return 1 + lcs(X, Y, m - 1, n - 1);
else:
return max(lcs(X, Y, m, n - 1), lcs(X, Y, m - 1, n));
Since someone asked for a multiple-word solution, here's one:
def multi_lcs(words):
words.sort(key=lambda x:len(x))
search = words.pop(0)
s_len = len(search)
for ln in range(s_len, 0, -1):
for start in range(0, s_len-ln+1):
cand = search[start:start+ln]
for word in words:
if cand not in word:
break
else:
return cand
return False
>>> multi_lcs(['xlaqseabcitt', 'peoritabcpeor'])
'abc'
>>> multi_lcs(['xlaqseabcitt', 'peoritabcpeor', 'visontatlasrab'])
'ab'
for small strings, copy this into a file in your project, let's say string_utils.py
def find_longest_common_substring(string1, string2):
s1 = string1
s2 = string2
longest_substring = ""
longest_substring_i1 = None
longest_substring_i2 = None
# iterate through every index (i1) of s1
for i1, c1 in enumerate(s1):
# for each index (i2) of s2 that matches s1[i1]
for i2, c2 in enumerate(s2):
# if start of substring
if c1 == c2:
delta = 1
# make sure we aren't running past the end of either string
while i1 + delta < len(s1) and i2 + delta < len(s2):
# if end of substring
if s2[i2 + delta] != s1[i1 + delta]:
break
# still matching characters move to the next character in both strings
delta += 1
substring = s1[i1:(i1 + delta)]
# print(f'substring candidate: {substring}')
# replace longest_substring if newly found substring is longer
if len(substring) > len(longest_substring):
longest_substring = substring
longest_substring_i1 = i1
longest_substring_i2 = i2
return (longest_substring, longest_substring_i1, longest_substring_i2)
Then it can be used as follows:
import string_utils
print(f"""(longest substring, index of string1, index of string2):
{ string_utils.find_longest_common_substring("stackoverflow.com", "tackerflow")}""")
For any that are curious the print statement when uncommented prints:
substring candidate: tack
substring candidate: ack
substring candidate: ck
substring candidate: o
substring candidate: erflow
substring candidate: rflow
substring candidate: flow
substring candidate: low
substring candidate: ow
substring candidate: w
substring candidate: c
substring candidate: o
(longest substring, index of string1, index of string2):
('erflow', 7, 4)
Here is a naive solution in terms of time complexity but simple enough to understand:
def longest_common_substring(a, b):
"""Find longest common substring between two strings A and B."""
if len(a) > len(b):
a, b = b, a
for i in range(len(a), 0, -1):
for j in range(len(a) - i + 1):
if a[j:j + i] in b:
return a[j:j + i]
return ''
A super fast library is available for Python: pylcs
It can find the indices of the longest common substring (LCS) between 2 strings, and can do some other related tasks as well.
A function to return the LCS using this library consists of 2 lines:
import pylcs
def find_LCS(s1, s2):
res = pylcs.lcs_string_idx(s1, s2)
return ''.join([s2[i] for i in res if i != -1])
Example:
s1 = 'bbbaaabaa'
s2 = 'abaabaab'
print(find_LCS(s1, s2))
aabaa
Explanation:
In this example res is:
[-1, -1, -1, -1, 2, 3, 4, 5, 6]
It is a mapping of all characters in s1 - to the indices of characters in s2 of the LCS.
-1 indicates that the character of s1 is NOT part of the LCS.
The reasons behind the speed and efficiency of this library are that it's implemented in C++ and uses dynamic programming.

ordered word perminuations in python

So my question is simple, and half of it is already working.
I need help with generating ordered word-permutations.
My code:
from os.path import isfile
from string import printable
def loadRuleSet(fileLocation):
rules = {}
assert isfile(fileLocation)
for x in open(fileLocation).read().split('\n'):
if not len(x) == 0:
data = x.split(':')
if not len(data[0]) == 0 or not len(data[1]) == 0:
rules[data[0]] = data[1]
return rules
class deform:
def __init__(self, ruleSet):
assert type(ruleSet) == dict
self.ruleSet = ruleSet
def walker(self, string):
spot = []
cnt = 0
for x in string:
spot.append((x, cnt))
cnt += 1
return spot
def replace_exact(self, word, position, new):
cnt = 0
newword = ''
for x in word:
if cnt == position:
newword += new
else:
newword += x
cnt+= 1
return newword
def first_iter(self, word):
data = []
pos = self.walker(word)
for x in pos:
if x[0] in self.ruleSet:
for y in self.ruleSet[x[0]]:
data.append(self.replace_exact(word, x[1], y))
return data
print deform({'a':'#A'}).first_iter('abac')
My current code does half of the job, but I've reached a "writer's block"
>>>deform({'a':'#'}).first_iter('aaa')
['#aa', 'a#a', 'aa#']
Here's the results from my currently made script.
What code is supposed to do is - take the word, and reorder it with other characters in the replacement. I've successfully made it do it with one character, but I need help with making all the results. For example:
['#aa', 'a#a', 'aa#', '##a', 'a##', '#a#']
In your case you can use permutations function which could return all possible orderings, no repeated elements.
from itertools import permutations
from operator import itemgetter
perm_one = sorted(set([''.join(x) for x in permutations('#aa')]))
perm_two = sorted(set([''.join(x) for x in permutations('##a')]), key=itemgetter(1))
print perm_one + perm_two
I divided it into two collections because they differ number of # and a characters.

Anagram check in Python

I am trying to write a program that will compare two lists of words and check the words to see if they are anagrams.
eg.,
input : ['cinema','host','aab','train'], ['iceman', 'shot', 'bab', 'rain']
I am using the below code:
#!/usr/bin/env python
anagram_dict = {}
def anagram_solver(first_words,second_words):
for word in first_words:
first_word = list(word)
second_word = list(second_words[first_words.index(word)])
first_copy = first_word
second_copy = second-word
if len(first_word) != len(second_word):
anagram_dict[first_words.index(word)] = 0
else:
for char in first_word:
second_word = second_copy
if char in second_word:
first_copy.remove(char)
second_copy.remove(char)
else:
pass
if len(first_copy) == len(second_copy):
print first_copy
print second_copy
anagram_dict[first_words.index(word)] = 1
else:
anagram_dict[first_words.index(word)] = 0
for k,v in anagram_dict.items():
print "%d : %d" %(k,v)
if __name__ == "__main__":
anagram_solver(['cinema','host','aab','train'],['iceman','shot','bab','rain'])
When I execute this script, in the for loop for char in first_word: the loop is skipped, by one list item. for example, if it is processing the list ['c','i','n','e','m','a']
it only processes 'c','n','m' and ignores the other items. If I remove the list.remove(), then it doesn't skip the items.
One can execute this script to better understand, what I am trying to explain here.
Just wondering why is this behavior and how to overcome this ?
You can simply sort the words and check if they are equal:
def anagram_solver(first_words, second_words):
result = []
for i in xrange(len(first_words)):
a = list(first_words[i])
b = list(second_words[i])
a.sort()
b.sort()
result.append(a == b)
return result
Example:
>>> a = ['cinema','host','aab','train']
>>> b = ['iceman', 'shot', 'bab', 'rain']
>>> anagram_solver(a, b)
[True, True, False, False]
Python handles lists by reference, so when you set first_copy = first_word, you're actually just making first_copy and first_word point to the same list. You can overcome this behavior (actually copy the list) using
first_copy = first_word[:]
second_copy = second_word[:]
To answer to your question according to its title: "Anagram check in Python"
You can do that in one three lines:
first_words = ['cinema','host','aab','train']
second_words = ['iceman', 'shot', 'bab', 'rain']
print [sorted(a) == sorted(b) for (a,b) in zip(first_words,second_words)]
Producing:
[True, True, False, False]
You can use enumerate with sorted:
[sorted(a[ind]) == sorted(ele) for ind, ele in enumerate(b)]
There are two ways to do this. One is pretty easy and other one is a bit complicated but is Optimal.
First Method
def anagram1(s1,s2):
# We need to get rid of the empty spaces and
# lower case the string
s1 = s1.replace(' ', '').lower()
s2 = s2.replace(' ', '').lower()
# Now we will return boolean for sorted match.
return sorted(s1) == sorted(s2)
The next Method is bit longer:
def anagram2(s1, s2):
# We will remove spaces and will lower case the string
s1 = s1.replace(' ', '').lower()
s2 = s2.replace(' ', '').lower()
# We will do the edge case to check if both strings have same number of letters
if len(s1) != len(s2):
return False
# will creat an empty dictionary.
count = {}
for letter in s1:
if letter in count:
# We are assigning value 1 for every letter in s1
count[letter] += 1
# if it is the start of loop u just want to assign one into it.
else:
count[letter] = 1
for s2 we will do the opposite.
for letter in s2:
if letter in count:
# We are making every value of the letters from 1 to zero
count[letter] -= 1
else:
count[letter] = 1
for k in count:
if count[k] != 0:
return False
# other wise just return true
return True
def anagram(string_one, string_two):
string_one = string_one.replace(' ', '').lower()
string_two = string_two.replace(' ', '').lower()
string_list_one = []
string_list_two = []
for letters in string_one:
string_list_one.append(letters)
for letters_t in string_two:
string_list_two.append(letters_t)
string_list_one.sort()
string_list_two.sort()
if(string_list_one == string_list_two):
return True
else:
return False

How to find all occurrences of a substring?

Python has string.find() and string.rfind() to get the index of a substring in a string.
I'm wondering whether there is something like string.find_all() which can return all found indexes (not only the first from the beginning or the first from the end).
For example:
string = "test test test test"
print string.find('test') # 0
print string.rfind('test') # 15
#this is the goal
print string.find_all('test') # [0,5,10,15]
For counting the occurrences, see Count number of occurrences of a substring in a string.
There is no simple built-in string function that does what you're looking for, but you could use the more powerful regular expressions:
import re
[m.start() for m in re.finditer('test', 'test test test test')]
#[0, 5, 10, 15]
If you want to find overlapping matches, lookahead will do that:
[m.start() for m in re.finditer('(?=tt)', 'ttt')]
#[0, 1]
If you want a reverse find-all without overlaps, you can combine positive and negative lookahead into an expression like this:
search = 'tt'
[m.start() for m in re.finditer('(?=%s)(?!.{1,%d}%s)' % (search, len(search)-1, search), 'ttt')]
#[1]
re.finditer returns a generator, so you could change the [] in the above to () to get a generator instead of a list which will be more efficient if you're only iterating through the results once.
>>> help(str.find)
Help on method_descriptor:
find(...)
S.find(sub [,start [,end]]) -> int
Thus, we can build it ourselves:
def find_all(a_str, sub):
start = 0
while True:
start = a_str.find(sub, start)
if start == -1: return
yield start
start += len(sub) # use start += 1 to find overlapping matches
list(find_all('spam spam spam spam', 'spam')) # [0, 5, 10, 15]
No temporary strings or regexes required.
Here's a (very inefficient) way to get all (i.e. even overlapping) matches:
>>> string = "test test test test"
>>> [i for i in range(len(string)) if string.startswith('test', i)]
[0, 5, 10, 15]
Use re.finditer:
import re
sentence = input("Give me a sentence ")
word = input("What word would you like to find ")
for match in re.finditer(word, sentence):
print (match.start(), match.end())
For word = "this" and sentence = "this is a sentence this this" this will yield the output:
(0, 4)
(19, 23)
(24, 28)
Again, old thread, but here's my solution using a generator and plain str.find.
def findall(p, s):
'''Yields all the positions of
the pattern p in the string s.'''
i = s.find(p)
while i != -1:
yield i
i = s.find(p, i+1)
Example
x = 'banananassantana'
[(i, x[i:i+2]) for i in findall('na', x)]
returns
[(2, 'na'), (4, 'na'), (6, 'na'), (14, 'na')]
You can use re.finditer() for non-overlapping matches.
>>> import re
>>> aString = 'this is a string where the substring "is" is repeated several times'
>>> print [(a.start(), a.end()) for a in list(re.finditer('is', aString))]
[(2, 4), (5, 7), (38, 40), (42, 44)]
but won't work for:
In [1]: aString="ababa"
In [2]: print [(a.start(), a.end()) for a in list(re.finditer('aba', aString))]
Output: [(0, 3)]
Come, let us recurse together.
def locations_of_substring(string, substring):
"""Return a list of locations of a substring."""
substring_length = len(substring)
def recurse(locations_found, start):
location = string.find(substring, start)
if location != -1:
return recurse(locations_found + [location], location+substring_length)
else:
return locations_found
return recurse([], 0)
print(locations_of_substring('this is a test for finding this and this', 'this'))
# prints [0, 27, 36]
No need for regular expressions this way.
If you're just looking for a single character, this would work:
string = "dooobiedoobiedoobie"
match = 'o'
reduce(lambda count, char: count + 1 if char == match else count, string, 0)
# produces 7
Also,
string = "test test test test"
match = "test"
len(string.split(match)) - 1
# produces 4
My hunch is that neither of these (especially #2) is terribly performant.
this is an old thread but i got interested and wanted to share my solution.
def find_all(a_string, sub):
result = []
k = 0
while k < len(a_string):
k = a_string.find(sub, k)
if k == -1:
return result
else:
result.append(k)
k += 1 #change to k += len(sub) to not search overlapping results
return result
It should return a list of positions where the substring was found.
Please comment if you see an error or room for improvment.
This does the trick for me using re.finditer
import re
text = 'This is sample text to test if this pythonic '\
'program can serve as an indexing platform for '\
'finding words in a paragraph. It can give '\
'values as to where the word is located with the '\
'different examples as stated'
# find all occurances of the word 'as' in the above text
find_the_word = re.finditer('as', text)
for match in find_the_word:
print('start {}, end {}, search string \'{}\''.
format(match.start(), match.end(), match.group()))
This thread is a little old but this worked for me:
numberString = "onetwothreefourfivesixseveneightninefiveten"
testString = "five"
marker = 0
while marker < len(numberString):
try:
print(numberString.index("five",marker))
marker = numberString.index("five", marker) + 1
except ValueError:
print("String not found")
marker = len(numberString)
You can try :
>>> string = "test test test test"
>>> for index,value in enumerate(string):
if string[index:index+(len("test"))] == "test":
print index
0
5
10
15
You can try :
import re
str1 = "This dress looks good; you have good taste in clothes."
substr = "good"
result = [_.start() for _ in re.finditer(substr, str1)]
# result = [17, 32]
When looking for a large amount of key words in a document, use flashtext
from flashtext import KeywordProcessor
words = ['test', 'exam', 'quiz']
txt = 'this is a test'
kwp = KeywordProcessor()
kwp.add_keywords_from_list(words)
result = kwp.extract_keywords(txt, span_info=True)
Flashtext runs faster than regex on large list of search words.
This function does not look at all positions inside the string, it does not waste compute resources. My try:
def findAll(string,word):
all_positions=[]
next_pos=-1
while True:
next_pos=string.find(word,next_pos+1)
if(next_pos<0):
break
all_positions.append(next_pos)
return all_positions
to use it call it like this:
result=findAll('this word is a big word man how many words are there?','word')
src = input() # we will find substring in this string
sub = input() # substring
res = []
pos = src.find(sub)
while pos != -1:
res.append(pos)
pos = src.find(sub, pos + 1)
Whatever the solutions provided by others are completely based on the available method find() or any available methods.
What is the core basic algorithm to find all the occurrences of a
substring in a string?
def find_all(string,substring):
"""
Function: Returning all the index of substring in a string
Arguments: String and the search string
Return:Returning a list
"""
length = len(substring)
c=0
indexes = []
while c < len(string):
if string[c:c+length] == substring:
indexes.append(c)
c=c+1
return indexes
You can also inherit str class to new class and can use this function
below.
class newstr(str):
def find_all(string,substring):
"""
Function: Returning all the index of substring in a string
Arguments: String and the search string
Return:Returning a list
"""
length = len(substring)
c=0
indexes = []
while c < len(string):
if string[c:c+length] == substring:
indexes.append(c)
c=c+1
return indexes
Calling the method
newstr.find_all('Do you find this answer helpful? then upvote
this!','this')
This is solution of a similar question from hackerrank. I hope this could help you.
import re
a = input()
b = input()
if b not in a:
print((-1,-1))
else:
#create two list as
start_indc = [m.start() for m in re.finditer('(?=' + b + ')', a)]
for i in range(len(start_indc)):
print((start_indc[i], start_indc[i]+len(b)-1))
Output:
aaadaa
aa
(0, 1)
(1, 2)
(4, 5)
Here's a solution that I came up with, using assignment expression (new feature since Python 3.8):
string = "test test test test"
phrase = "test"
start = -1
result = [(start := string.find(phrase, start + 1)) for _ in range(string.count(phrase))]
Output:
[0, 5, 10, 15]
I think the most clean way of solution is without libraries and yields:
def find_all_occurrences(string, sub):
index_of_occurrences = []
current_index = 0
while True:
current_index = string.find(sub, current_index)
if current_index == -1:
return index_of_occurrences
else:
index_of_occurrences.append(current_index)
current_index += len(sub)
find_all_occurrences(string, substr)
Note: find() method returns -1 when it can't find anything
The pythonic way would be:
mystring = 'Hello World, this should work!'
find_all = lambda c,s: [x for x in range(c.find(s), len(c)) if c[x] == s]
# s represents the search string
# c represents the character string
find_all(mystring,'o') # will return all positions of 'o'
[4, 7, 20, 26]
>>>
if you only want to use numpy here is a solution
import numpy as np
S= "test test test test"
S2 = 'test'
inds = np.cumsum([len(k)+len(S2) for k in S.split(S2)[:-1]])- len(S2)
print(inds)
if you want to use without re(regex) then:
find_all = lambda _str,_w : [ i for i in range(len(_str)) if _str.startswith(_w,i) ]
string = "test test test test"
print( find_all(string, 'test') ) # >>> [0, 5, 10, 15]
please look at below code
#!/usr/bin/env python
# coding:utf-8
'''黄哥Python'''
def get_substring_indices(text, s):
result = [i for i in range(len(text)) if text.startswith(s, i)]
return result
if __name__ == '__main__':
text = "How much wood would a wood chuck chuck if a wood chuck could chuck wood?"
s = 'wood'
print get_substring_indices(text, s)
def find_index(string, let):
enumerated = [place for place, letter in enumerate(string) if letter == let]
return enumerated
for example :
find_index("hey doode find d", "d")
returns:
[4, 7, 13, 15]
Not exactly what OP asked but you could also use the split function to get a list of where all the substrings don't occur. OP didn't specify the end goal of the code but if your goal is to remove the substrings anyways then this could be a simple one-liner. There are probably more efficient ways to do this with larger strings; regular expressions would be preferable in that case
# Extract all non-substrings
s = "an-example-string"
s_no_dash = s.split('-')
# >>> s_no_dash
# ['an', 'example', 'string']
# Or extract and join them into a sentence
s_no_dash2 = ' '.join(s.split('-'))
# >>> s_no_dash2
# 'an example string'
Did a brief skim of other answers so apologies if this is already up there.
def count_substring(string, sub_string):
c=0
for i in range(0,len(string)-2):
if string[i:i+len(sub_string)] == sub_string:
c+=1
return c
if __name__ == '__main__':
string = input().strip()
sub_string = input().strip()
count = count_substring(string, sub_string)
print(count)
I runned in the same problem and did this:
hw = 'Hello oh World!'
list_hw = list(hw)
o_in_hw = []
while True:
o = hw.find('o')
if o != -1:
o_in_hw.append(o)
list_hw[o] = ' '
hw = ''.join(list_hw)
else:
print(o_in_hw)
break
Im pretty new at coding so you can probably simplify it (and if planned to used continuously of course make it a function).
All and all it works as intended for what i was doing.
Edit: Please consider this is for single characters only, and it will change your variable, so you have to create a copy of the string in a new variable to save it, i didnt put it in the code cause its easy and its only to show how i made it work.
By slicing we find all the combinations possible and append them in a list and find the number of times it occurs using count function
s=input()
n=len(s)
l=[]
f=input()
print(s[0])
for i in range(0,n):
for j in range(1,n+1):
l.append(s[i:j])
if f in l:
print(l.count(f))
To find all the occurence of a character in a give string and return as a dictionary
eg: hello
result :
{'h':1, 'e':1, 'l':2, 'o':1}
def count(string):
result = {}
if(string):
for i in string:
result[i] = string.count(i)
return result
return {}
or else you do like this
from collections import Counter
def count(string):
return Counter(string)

Categories