Finding if string is concatenation of others - python

I am working on a problem where one must determine if a string is a concatenation of other string (these strings can be repeated in the concatenated strings). I am using backtracking to be as efficient as possible. If the string is a concatenation, it will print the strings it is a concatenation of. If not, it will print NOT POSSIBLE. Here is my python code:
# note: strList has to have been sorted
def findFirstSubstr(strList, substr, start = 0):
index = start
if (index >= len(strList)):
return -1
while (strList[index][:len(substr)] != substr):
index += 1
if (index >= len(strList)):
return -1
return index
def findPossibilities(stringConcat, stringList):
stringList.sort()
i = 0
index = 0
substr = ''
resultDeque = []
indexStack = []
while (i < len(stringConcat)):
substr += stringConcat[i]
index = findFirstSubstr(stringList, substr, index)
if (index < 0):
if (len(resultDeque) == 0):
return 'NOT POSSIBLE'
else:
i -= len(resultDeque.pop())
index = indexStack.pop() + 1
substr = ''
continue
elif (stringList[index] == substr):
resultDeque.append(stringList[index])
indexStack.append(index)
index = 0
substr = ''
i += 1
return ' '.join(resultDeque)
I keep failing the last half of the test cases and can't figure out why. Could someone prompt me in the right direction for any cases that this would fail? Thanks!

First, of all, this code is unnecessary complicated. For example, here is an equivalent but shorter solution:
def findPossibilities(stringConcat, stringList):
if not stringConcat: # if you want exact match, add `and not stringList`
return True
return any(findPossibilities(stringConcat[len(s):],
stringList[:i] + stringList[i+1:]) # assuming non-repeatable match. Otherwise, simply replace with `stringList`
for i, s in enumerate(stringList)
if stringConcat.startswith(s))
Actual answer:
Border condition: remaining part of stringConcat matches some of stringList, search is stopped:
>>> findPossibilities('aaaccbbbccc', ['aaa', 'bb', 'ccb', 'cccc'])
'aaa ccb bb'

Related

Without using built-in functions, a function should reverse a string without changing the '$' position

I need a Python function which gives reversed string with the following conditions.
$ position should not change in the reversed string.
Should not use Python built-in functions.
Function should be an efficient one.
Example : 'pytho$n'
Result : 'nohty$p'
I have already tried with this code:
list = "$asdasdas"
list1 = []
position = ''
for index, i in enumerate(list):
if i == '$':
position = index
elif i != '$':
list1.append(i)
reverse = []
for index, j in enumerate( list1[::-1] ):
if index == position:
reverse.append( '$' )
reverse.append(j)
print reverse
Thanks in advance.
Recognise that it's a variation on the partitioning step of the Quicksort algorithm, using two pointers (array indices) thus:
data = list("foo$barbaz$$")
i, j = 0, len(data) - 1
while i < j:
while i < j and data[i] == "$": i += 1
while i < j and data[j] == "$": j -= 1
data[i], data[j] = data[j], data[i]
i, j = i + 1, j - 1
"".join(data)
'zab$raboof$$'
P.S. it's a travesty to write this in Python!
A Pythonic solution could look like this:
def merge(template, data):
for c in template:
yield c if c == "$" else next(data)
data = "foo$barbaz$$"
"".join(merge(data, reversed([c for c in data if c != "$"])))
'zab$raboof$$'
Wrote this without using any inbuilt functions. Hope it fulfils your criteria -
string = "zytho$n"
def reverse(string):
string_new = string[::-1]
i = 0
position = 0
position_new = 0
for char in string:
if char=="$":
position = i
break
else:
i = i + 1
j = 0
for char in string_new:
if char=="$":
position_new = i
break
else:
j = j + 1
final_string = string_new[:position_new]+string_new[position_new+1:position+1]+"$"+string_new[position+1:]
return(final_string)
string_new = reverse(string)
print(string_new)
The output of this is-
nohty$x
To explain the code to you, first I used [::-1], which is just taking the last position of the string and moving forward so as to reverse the string. Then I found the position of the $ in both the new and the old string. I found the position in the form of an array, in case you have more than one $ present. However, I took for granted that you have just one $ present, and so took the [0] index of the array. Next I stitched back the string using four things - The part of the new string upto the $ sign, the part of the new string from after the dollar sign to the position of the $ sign in the old string, then the $ sign and after that the rest of the new string.

Add a start index to a string index generator

I'm currently learning to create generators and to use itertools. So I decided to make a string index generator, but I'd like to add some parameters such as a "start index" allowing to define where to start generating the indexes.
I came up with this ugly solution which can be very long and not efficient with large indexes:
import itertools
import string
class StringIndex(object):
'''
Generator that create string indexes in form:
A, B, C ... Z, AA, AB, AC ... ZZ, AAA, AAB, etc.
Arguments:
- startIndex = string; default = ''; start increment for the generator.
- mode = 'lower' or 'upper'; default = 'upper'; is the output index in
lower or upper case.
'''
def __init__(self, startIndex = '', mode = 'upper'):
if mode == 'lower':
self.letters = string.ascii_lowercase
elif mode == 'upper':
self.letters = string.ascii_uppercase
else:
cmds.error ('Wrong output mode, expected "lower" or "upper", ' +
'got {}'.format(mode))
if startIndex != '':
if not all(i in self.letters for i in startIndex):
cmds.error ('Illegal characters in start index; allowed ' +
'characters are: {}'.format(self.letters))
self.startIndex = startIndex
def getIndex(self):
'''
Returns:
- string; current string index
'''
startIndexOk = False
x = 1
while True:
strIdMaker = itertools.product(self.letters, repeat = x)
for stringList in strIdMaker:
index = ''.join([s for s in stringList])
# Here is the part to simpify
if self.startIndex:
if index == self.startIndex:
startIndexOk = True
if not startIndexOk:
continue
###
yield index
x += 1
Any advice or improvement is welcome. Thank you!
EDIT:
The start index must be a string!
You would have to do the arithmetic (in base 26) yourself to avoid looping over itertools.product. But you can at least set x=len(self.startIndex) or 1!
Old (incorrect) answer
If you would do it without itertools (assuming you start with a single letter), you could do the following:
letters = 'abcdefghijklmnopqrstuvwxyz'
def getIndex(start, case):
lets = list(letters.lower()) if case == 'lower' else list(letters.upper())
# default is 'upper', but can also be an elif
for r in xrange(0,10):
for l in lets[start:]:
if l.lower() == 'z':
start = 0
yield ''.join(lets[:r])+l
I run until max 10 rows of letters are created, but you could ofcourse use an infinite while loop such that it can be called forever.
Correct answer
I found the solution in a different way: I used a base 26 number translator (based on (and fixxed since it didn't work perfectly): http://quora.com/How-do-I-write-a-program-in-Python-that-can-convert-an-integer-from-one-base-to-another)
I uses itertools.count() to count and just loops over all the possibilities.
The code:
import time
from itertools import count
def toAlph(x, letters):
div = 26
r = '' if x > 0 else letters[0]
while x > 0:
r = letters[x % div] + r
if (x // div == 1) and (x % div == 0):
r = letters[0] + r
break
else:
x //= div
return r
def getIndex(start, case='upper'):
alphabet = 'abcdefghijklmnopqrstuvwxyz'
letters = alphabet.upper() if case == 'upper' else alphabet
started = False
for num in count(0,1):
l = toAlph(num, letters)
if l == start:
started = True
if started:
yield l
iterator = getIndex('AA')
for i in iterator:
print(i)
time.sleep(0.1)

Comparing strings and getting the most frequent serie of letters [duplicate]

I'm looking for a Python library for finding the longest common sub-string from a set of strings. There are two ways to solve this problem:
using suffix trees
using dynamic programming.
Method implemented is not important. It is important it can be used for a set of strings (not only two strings).
These paired functions will find the longest common string in any arbitrary array of strings:
def long_substr(data):
substr = ''
if len(data) > 1 and len(data[0]) > 0:
for i in range(len(data[0])):
for j in range(len(data[0])-i+1):
if j > len(substr) and is_substr(data[0][i:i+j], data):
substr = data[0][i:i+j]
return substr
def is_substr(find, data):
if len(data) < 1 and len(find) < 1:
return False
for i in range(len(data)):
if find not in data[i]:
return False
return True
print long_substr(['Oh, hello, my friend.',
'I prefer Jelly Belly beans.',
'When hell freezes over!'])
No doubt the algorithm could be improved and I've not had a lot of exposure to Python, so maybe it could be more efficient syntactically as well, but it should do the job.
EDIT: in-lined the second is_substr function as demonstrated by J.F. Sebastian. Usage remains the same. Note: no change to algorithm.
def long_substr(data):
substr = ''
if len(data) > 1 and len(data[0]) > 0:
for i in range(len(data[0])):
for j in range(len(data[0])-i+1):
if j > len(substr) and all(data[0][i:i+j] in x for x in data):
substr = data[0][i:i+j]
return substr
Hope this helps,
Jason.
This can be done shorter:
def long_substr(data):
substrs = lambda x: {x[i:i+j] for i in range(len(x)) for j in range(len(x) - i + 1)}
s = substrs(data[0])
for val in data[1:]:
s.intersection_update(substrs(val))
return max(s, key=len)
set's are (probably) implemented as hash-maps, which makes this a bit inefficient. If you (1) implement a set datatype as a trie and (2) just store the postfixes in the trie and then force each node to be an endpoint (this would be the equivalent of adding all substrings), THEN in theory I would guess this baby is pretty memory efficient, especially since intersections of tries are super-easy.
Nevertheless, this is short and premature optimization is the root of a significant amount of wasted time.
def common_prefix(strings):
""" Find the longest string that is a prefix of all the strings.
"""
if not strings:
return ''
prefix = strings[0]
for s in strings:
if len(s) < len(prefix):
prefix = prefix[:len(s)]
if not prefix:
return ''
for i in range(len(prefix)):
if prefix[i] != s[i]:
prefix = prefix[:i]
break
return prefix
From http://bitbucket.org/ned/cog/src/tip/cogapp/whiteutils.py
I prefer this for is_substr, as I find it a bit more readable and intuitive:
def is_substr(find, data):
"""
inputs a substring to find, returns True only
if found for each data in data list
"""
if len(find) < 1 or len(data) < 1:
return False # expected input DNE
is_found = True # and-ing to False anywhere in data will return False
for i in data:
print "Looking for substring %s in %s..." % (find, i)
is_found = is_found and find in i
return is_found
# this does not increase asymptotical complexity
# but can still waste more time than it saves. TODO: profile
def shortest_of(strings):
return min(strings, key=len)
def long_substr(strings):
substr = ""
if not strings:
return substr
reference = shortest_of(strings) #strings[0]
length = len(reference)
#find a suitable slice i:j
for i in xrange(length):
#only consider strings long at least len(substr) + 1
for j in xrange(i + len(substr) + 1, length + 1):
candidate = reference[i:j] # ↓ is the slice recalculated every time?
if all(candidate in text for text in strings):
substr = candidate
return substr
Disclaimer This adds very little to jtjacques' answer. However, hopefully, this should be more readable and faster and it didn't fit in a comment, hence why I'm posting this in an answer. I'm not satisfied about shortest_of, to be honest.
If someone is looking for a generalized version that can also take a list of sequences of arbitrary objects:
def get_longest_common_subseq(data):
substr = []
if len(data) > 1 and len(data[0]) > 0:
for i in range(len(data[0])):
for j in range(len(data[0])-i+1):
if j > len(substr) and is_subseq_of_any(data[0][i:i+j], data):
substr = data[0][i:i+j]
return substr
def is_subseq_of_any(find, data):
if len(data) < 1 and len(find) < 1:
return False
for i in range(len(data)):
if not is_subseq(find, data[i]):
return False
return True
# Will also return True if possible_subseq == seq.
def is_subseq(possible_subseq, seq):
if len(possible_subseq) > len(seq):
return False
def get_length_n_slices(n):
for i in xrange(len(seq) + 1 - n):
yield seq[i:i+n]
for slyce in get_length_n_slices(len(possible_subseq)):
if slyce == possible_subseq:
return True
return False
print get_longest_common_subseq([[1, 2, 3, 4, 5], [2, 3, 4, 5, 6]])
print get_longest_common_subseq(['Oh, hello, my friend.',
'I prefer Jelly Belly beans.',
'When hell freezes over!'])
My answer, pretty slow, but very easy to understand. Working on a file with 100 strings of 1 kb each takes about two seconds, returns any one longest substring if there are more than one
ls = list()
ls.sort(key=len)
s1 = ls.pop(0)
maxl = len(s1)
#1 create a list of all substrings backwards sorted by length. Thus we don't have to check the whole list.
subs = [s1[i:j] for i in range(maxl) for j in range(maxl,i,-1)]
subs.sort(key=len, reverse=True)
#2 Check a substring with the next shortest then the next etc. if is not in an any next shortest string then break the cycle, it's not common. If it passes all checks, it is the longest one by default, break the cycle.
def isasub(subs, ls):
for sub in subs:
for st in ls:
if sub not in st:
break
else:
return sub
break
print('the longest common substring is: ',isasub(subs,ls))
Caveman solution that will give you a dataframe with the top most frequent substring in a string base on the substring length you pass as a list:
import pandas as pd
lista = ['How much wood would a woodchuck',' chuck if a woodchuck could chuck wood?']
string = ''
for i in lista:
string = string + ' ' + str(i)
string = string.lower()
characters_you_would_like_to_remove_from_string = [' ','-','_']
for i in charecters_you_would_like_to_remove_from_string:
string = string.replace(i,'')
substring_length_you_want_to_check = [3,4,5,6,7,8]
results_list = []
for string_length in substring_length_you_want_to_check:
for i in range(len(string)):
checking_str = string[i:i+string_length]
if len(checking_str) == string_length:
number_of_times_appears = (len(string) - len(string.replace(checking_str,'')))/string_length
results_list = results_list+[[checking_str,number_of_times_appears]]
df = pd.DataFrame(data=results_list,columns=['string','freq'])
df['freq'] = df['freq'].astype('int64')
df = df.drop_duplicates()
df = df.sort_values(by='freq',ascending=False)
display(df[:10])
result is:
string freq
78 huck 4
63 wood 4
77 chuc 4
132 chuck 4
8 ood 4
7 woo 4
21 chu 4
23 uck 4
22 huc 4
20 dch 3
The addition of a single 'break' speeds up jtjacques's answer significantly on my machine (1000X or so for 16K files):
def long_substr(data):
substr = ''
if len(data) > 1 and len(data[0]) > 0:
for i in range(len(data[0])):
for j in range(len(substr)+1, len(data[0])-i+1):
if all(data[0][i:i+j] in x for x in data[1:]):
substr = data[0][i:i+j]
else:
break
return substr
You could use the SuffixTree module that is a wrapper based on an ANSI C implementation of generalised suffix trees. The module is easy to handle....
Take a look at: here

Finding the length of longest repeating?

I have tried plenty of different methods to achieve this, and I don't know what I'm doing wrong.
reps=[]
len_charac=0
def longest_charac(strng)
for i in range(len(strng)):
if strng[i] == strng[i+1]:
if strng[i] in reps:
reps.append(strng[i])
len_charac=len(reps)
return len_charac
Remember in Python counting loops and indexing strings aren't usually needed. There is also a builtin max function:
def longest(s):
maximum = count = 0
current = ''
for c in s:
if c == current:
count += 1
else:
count = 1
current = c
maximum = max(count,maximum)
return maximum
Output:
>>> longest('')
0
>>> longest('aab')
2
>>> longest('a')
1
>>> longest('abb')
2
>>> longest('aabccdddeffh')
3
>>> longest('aaabcaaddddefgh')
4
Simple solution:
def longest_substring(strng):
len_substring=0
longest=0
for i in range(len(strng)):
if i > 0:
if strng[i] != strng[i-1]:
len_substring = 0
len_substring += 1
if len_substring > longest:
longest = len_substring
return longest
Iterates through the characters in the string and checks against the previous one. If they are different then the count of repeating characters is reset to zero, then the count is incremented. If the current count beats the current record (stored in longest) then it becomes the new longest.
Compare two things and there is one relation between them:
'a' == 'a'
True
Compare three things, and there are two relations:
'a' == 'a' == 'b'
True False
Combine these ideas - repeatedly compare things with the things next to them, and the chain gets shorter each time:
'a' == 'a' == 'b'
True == False
False
It takes one reduction for the 'b' comparison to be False, because there was one 'b'; two reductions for the 'a' comparison to be False because there were two 'a'. Keep repeating until the relations are all all False, and that is how many consecutive equal characters there were.
def f(s):
repetitions = 0
while any(s):
repetitions += 1
s = [ s[i] and s[i] == s[i+1] for i in range(len(s)-1) ]
return repetitions
>>> f('aaabcaaddddefgh')
4
NB. matching characters at the start become True, only care about comparing the Trues with anything, and stop when all the Trues are gone and the list is all Falses.
It can also be squished into a recursive version, passing the depth in as an optional parameter:
def f(s, depth=1):
s = [ s[i] and s[i]==s[i+1] for i in range(len(s)-1) ]
return f(s, depth+1) if any(s) else depth
>>> f('aaabcaaddddefgh')
4
I stumbled on this while trying for something else, but it's quite pleasing.
You can use itertools.groupby to solve this pretty quickly, it will group characters together, and then you can sort the resulting list by length and get the last entry in the list as follows:
from itertools import groupby
print(sorted([list(g) for k, g in groupby('aaabcaaddddefgh')],key=len)[-1])
This should give you:
['d', 'd', 'd', 'd']
This works:
def longestRun(s):
if len(s) == 0: return 0
runs = ''.join('*' if x == y else ' ' for x,y in zip(s,s[1:]))
starStrings = runs.split()
if len(starStrings) == 0: return 1
return 1 + max(len(stars) for stars in starStrings)
Output:
>>> longestRun("aaabcaaddddefgh")
4
First off, Python is not my primary language, but I can still try to help.
1) you look like you are exceeding the bounds of the array. On the last iteration, you check the last character against the character beyond the last character. This normally leads to undefined behavior.
2) you start off with an empty reps[] array and compare every character to see if it's in it. Clearly, that check will fail every time and your append is within that if statement.
def longest_charac(string):
longest = 0
if string:
flag = string[0]
tmp_len = 0
for item in string:
if item == flag:
tmp_len += 1
else:
flag = item
tmp_len = 1
if tmp_len > longest:
longest = tmp_len
return longest
This is my solution. Maybe it will help you.
Just for context, here is a recursive approach that avoids dealing with loops:
def max_rep(prev, text, reps, rep=1):
"""Recursively consume all characters in text and find longest repetition.
Args
prev: string of previous character
text: string of remaining text
reps: list of ints of all reptitions observed
rep: int of current repetition observed
"""
if text == '': return max(reps)
if prev == text[0]:
rep += 1
else:
rep = 1
return max_rep(text[0], text[1:], reps + [rep], rep)
Tests:
>>> max_rep('', 'aaabcaaddddefgh', [])
4
>>> max_rep('', 'aaaaaabcaadddddefggghhhhhhh', [])
7

Finding longest substring in alphabetical order

EDIT: I am aware that a question with similar task was already asked in SO but I'm interested to find out the problem in this specific piece of code. I am also aware that this problem can be solved without using recursion.
The task is to write a program which will find (and print) the longest sub-string in which the letters occur in alphabetical order. If more than 1 equally long sequences were found, then the first one should be printed. For example, the output for a string abczabcd will be abcz.
I have solved this problem with recursion which seemed to pass my manual tests. However when I run an automated tests set which generate random strings, I have noticed that in some cases, the output is incorrect. For example:
if s = 'hixwluvyhzzzdgd', the output is hix instead of luvy
if s = 'eseoojlsuai', the output is eoo instead of jlsu
if s = 'drurotsxjehlwfwgygygxz', the output is dru instead of ehlw
After some time struggling, I couldn't figure out what is so special about these strings that causes the bug.
This is my code:
pos = 0
maxLen = 0
startPos = 0
endPos = 0
def last_pos(pos):
if pos < (len(s) - 1):
if s[pos + 1] >= s[pos]:
pos += 1
if pos == len(s)-1:
return len(s)
else:
return last_pos(pos)
return pos
for i in range(len(s)):
if last_pos(i+1) != None:
diff = last_pos(i) - i
if diff - 1 > maxLen:
maxLen = diff
startPos = i
endPos = startPos + diff
print s[startPos:endPos+1]
There are many things to improve in your code but making minimum changes so as to make it work. The problem is you should have if last_pos(i) != None: in your for loop (i instead of i+1) and you should compare diff (not diff - 1) against maxLen. Please read other answers to learn how to do it better.
for i in range(len(s)):
if last_pos(i) != None:
diff = last_pos(i) - i + 1
if diff > maxLen:
maxLen = diff
startPos = i
endPos = startPos + diff - 1
Here. This does what you want. One pass, no need for recursion.
def find_longest_substring_in_alphabetical_order(s):
groups = []
cur_longest = ''
prev_char = ''
for c in s.lower():
if prev_char and c < prev_char:
groups.append(cur_longest)
cur_longest = c
else:
cur_longest += c
prev_char = c
return max(groups, key=len) if groups else s
Using it:
>>> find_longest_substring_in_alphabetical_order('hixwluvyhzzzdgd')
'luvy'
>>> find_longest_substring_in_alphabetical_order('eseoojlsuai')
'jlsu'
>>> find_longest_substring_in_alphabetical_order('drurotsxjehlwfwgygygxz')
'ehlw'
Note: It will probably break on strange characters, has only been tested with the inputs you suggested. Since this is a "homework" question, I will leave you with the solution as is, though there is still some optimization to be done, I wanted to leave it a little bit understandable.
You can use nested for loops, slicing and sorted. If the string is not all lower-case then you can convert the sub-strings to lower-case before comparing using str.lower:
def solve(strs):
maxx = ''
for i in xrange(len(strs)):
for j in xrange(i+1, len(strs)):
s = strs[i:j+1]
if ''.join(sorted(s)) == s:
maxx = max(maxx, s, key=len)
else:
break
return maxx
Output:
>>> solve('hixwluvyhzzzdgd')
'luvy'
>>> solve('eseoojlsuai')
'jlsu'
>>> solve('drurotsxjehlwfwgygygxz')
'ehlw'
Python has a powerful builtin package itertools and a wonderful function within groupby
An intuitive use of the Key function can give immense mileage.
In this particular case, you just have to keep a track of order change and group the sequence accordingly. The only exception is the boundary case which you have to handle separately
Code
def find_long_cons_sub(s):
class Key(object):
'''
The Key function returns
1: For Increasing Sequence
0: For Decreasing Sequence
'''
def __init__(self):
self.last_char = None
def __call__(self, char):
resp = True
if self.last_char:
resp = self.last_char < char
self.last_char = char
return resp
def find_substring(groups):
'''
The Boundary Case is when an increasing sequence
starts just after the Decresing Sequence. This causes
the first character to be in the previous group.
If you do not want to handle the Boundary Case
seperately, you have to mak the Key function a bit
complicated to flag the start of increasing sequence'''
yield next(groups)
try:
while True:
yield next(groups)[-1:] + next(groups)
except StopIteration:
pass
groups = (list(g) for k, g in groupby(s, key = Key()) if k)
#Just determine the maximum sequence based on length
return ''.join(max(find_substring(groups), key = len))
Result
>>> find_long_cons_sub('drurotsxjehlwfwgygygxz')
'ehlw'
>>> find_long_cons_sub('eseoojlsuai')
'jlsu'
>>> find_long_cons_sub('hixwluvyhzzzdgd')
'luvy'
Simple and easy.
Code :
s = 'hixwluvyhzzzdgd'
r,p,t = '','',''
for c in s:
if p <= c:
t += c
p = c
else:
if len(t) > len(r):
r = t
t,p = c,c
if len(t) > len(r):
r = t
print 'Longest substring in alphabetical order is: ' + r
Output :
Longest substring in alphabetical order which appeared first: luvy
Here is a single pass solution with a fast loop. It reads each character only once. Inside the loop operations are limited to
1 string comparison (1 char x 1 char)
1 integer increment
2 integer subtractions
1 integer comparison
1 to 3 integer assignments
1 string assignment
No containers are used. No function calls are made. The empty string is handled without special-case code. All character codes, including chr(0), are properly handled. If there is a tie for the longest alphabetical substring, the function returns the first winning substring it encountered. Case is ignored for purposes of alphabetization, but case is preserved in the output substring.
def longest_alphabetical_substring(string):
start, end = 0, 0 # range of current alphabetical string
START, END = 0, 0 # range of longest alphabetical string yet found
prev = chr(0) # previous character
for char in string.lower(): # scan string ignoring case
if char < prev: # is character out of alphabetical order?
start = end # if so, start a new substring
end += 1 # either way, increment substring length
if end - start > END - START: # found new longest?
START, END = start, end # if so, update longest
prev = char # remember previous character
return string[START : END] # return longest alphabetical substring
Result
>>> longest_alphabetical_substring('drurotsxjehlwfwgygygxz')
'ehlw'
>>> longest_alphabetical_substring('eseoojlsuai')
'jlsu'
>>> longest_alphabetical_substring('hixwluvyhzzzdgd')
'luvy'
>>>
a lot more looping, but it gets the job done
s = raw_input("Enter string")
fin=""
s_pos =0
while s_pos < len(s):
n=1
lng=" "
for c in s[s_pos:]:
if c >= lng[n-1]:
lng+=c
n+=1
else :
break
if len(lng) > len(fin):
fin= lng`enter code here`
s_pos+=1
print "Longest string: " + fin
def find_longest_order():
`enter code here`arr = []
`enter code here`now_long = ''
prev_char = ''
for char in s.lower():
if prev_char and char < prev_char:
arr.append(now_long)
now_long = char
else:
now_long += char
prev_char = char
if len(now_long) == len(s):
return now_long
else:
return max(arr, key=len)
def main():
print 'Longest substring in alphabetical order is: ' + find_longest_order()
main()
Simple and easy to understand:
s = "abcbcd" #The original string
l = len(s) #The length of the original string
maxlenstr = s[0] #maximum length sub-string, taking the first letter of original string as value.
curlenstr = s[0] #current length sub-string, taking the first letter of original string as value.
for i in range(1,l): #in range, the l is not counted.
if s[i] >= s[i-1]: #If current letter is greater or equal to previous letter,
curlenstr += s[i] #add the current letter to current length sub-string
else:
curlenstr = s[i] #otherwise, take the current letter as current length sub-string
if len(curlenstr) > len(maxlenstr): #if current cub-string's length is greater than max one,
maxlenstr = curlenstr; #take current one as max one.
print("Longest substring in alphabetical order is:", maxlenstr)
s = input("insert some string: ")
start = 0
end = 0
temp = ""
while end+1 <len(s):
while end+1 <len(s) and s[end+1] >= s[end]:
end += 1
if len(s[start:end+1]) > len(temp):
temp = s[start:end+1]
end +=1
start = end
print("longest ordered part is: "+temp)
I suppose this is problem set question for CS6.00.1x on EDX. Here is what I came up with.
s = raw_input("Enter the string: ")
longest_sub = ""
last_longest = ""
for i in range(len(s)):
if len(last_longest) > 0:
if last_longest[-1] <= s[i]:
last_longest += s[i]
else:
last_longest = s[i]
else:
last_longest = s[i]
if len(last_longest) > len(longest_sub):
longest_sub = last_longest
print(longest_sub)
I came up with this solution
def longest_sorted_string(s):
max_string = ''
for i in range(len(s)):
for j in range(i+1, len(s)+1):
string = s[i:j]
arr = list(string)
if sorted(string) == arr and len(max_string) < len(string):
max_string = string
return max_string
Assuming this is from Edx course:
till this question, we haven't taught anything about strings and their advanced operations in python
So, I would simply go through the looping and conditional statements
string ="" #taking a plain string to represent the then generated string
present ="" #the present/current longest string
for i in range(len(s)): #not len(s)-1 because that totally skips last value
j = i+1
if j>= len(s):
j=i #using s[i+1] simply throws an error of not having index
if s[i] <= s[j]: #comparing the now and next value
string += s[i] #concatinating string if above condition is satisied
elif len(string) != 0 and s[i] > s[j]: #don't want to lose the last value
string += s[i] #now since s[i] > s[j] #last one will be printed
if len(string) > len(present): #1 > 0 so from there we get to store many values
present = string #swapping to largest string
string = ""
if len(string) > len(present): #to swap from if statement
present = string
if present == s[len(s)-1]: #if no alphabet is in order then first one is to be the output
present = s[0]
print('Longest substring in alphabetical order is:' + present)
I agree with #Abhijit about the power of itertools.groupby() but I took a simpler approach to (ab)using it and avoided the boundary case problems:
from itertools import groupby
LENGTH, LETTERS = 0, 1
def longest_sorted(string):
longest_length, longest_letters = 0, []
key, previous_letter = 0, chr(0)
def keyfunc(letter):
nonlocal key, previous_letter
if letter < previous_letter:
key += 1
previous_letter = letter
return key
for _, group in groupby(string, keyfunc):
letters = list(group)
length = len(letters)
if length > longest_length:
longest_length, longest_letters = length, letters
return ''.join(longest_letters)
print(longest_sorted('hixwluvyhzzzdgd'))
print(longest_sorted('eseoojlsuai'))
print(longest_sorted('drurotsxjehlwfwgygygxz'))
print(longest_sorted('abcdefghijklmnopqrstuvwxyz'))
OUTPUT
> python3 test.py
luvy
jlsu
ehlw
abcdefghijklmnopqrstuvwxyz
>
s = 'azcbobobegghakl'
i=1
subs=s[0]
subs2=s[0]
while(i<len(s)):
j=i
while(j<len(s)):
if(s[j]>=s[j-1]):
subs+=s[j]
j+=1
else:
subs=subs.replace(subs[:len(subs)],s[i])
break
if(len(subs)>len(subs2)):
subs2=subs2.replace(subs2[:len(subs2)], subs[:len(subs)])
subs=subs.replace(subs[:len(subs)],s[i])
i+=1
print("Longest substring in alphabetical order is:",subs2)
s = 'gkuencgybsbezzilbfg'
x = s.lower()
y = ''
z = [] #creating an empty listing which will get filled
for i in range(0,len(x)):
if i == len(x)-1:
y = y + str(x[i])
z.append(y)
break
a = x[i] <= x[i+1]
if a == True:
y = y + str(x[i])
else:
y = y + str(x[i])
z.append(y) # fill the list
y = ''
# search of 1st longest string
L = len(max(z,key=len)) # key=len takes length in consideration
for i in range(0,len(z)):
a = len(z[i])
if a == L:
print 'Longest substring in alphabetical order is:' + str(z[i])
break
first_seq=s[0]
break_seq=s[0]
current = s[0]
for i in range(0,len(s)-1):
if s[i]<=s[i+1]:
first_seq = first_seq + s[i+1]
if len(first_seq) > len(current):
current = first_seq
else:
first_seq = s[i+1]
break_seq = first_seq
print("Longest substring in alphabetical order is: ", current)

Categories

Resources