Skip to content

Commit

Permalink
Returning Index instead of boolean in knuth_morris_pratt (kmp) functi…
Browse files Browse the repository at this point in the history
…on, making it compatible with str.find(). (TheAlgorithms#9083)

* Update knuth_morris_pratt.py - changed Boolean to Index

* Update knuth_morris_pratt.py

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

* Update knuth_morris_pratt.py

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

* Update knuth_morris_pratt.py

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

* Update back_propagation_neural_network.py

* Update back_propagation_neural_network.py

* Update strings/knuth_morris_pratt.py

* Update knuth_morris_pratt.py

* Update knuth_morris_pratt.py

---------

Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
Co-authored-by: Christian Clauss <[email protected]>
  • Loading branch information
3 people authored Sep 28, 2023
1 parent 38c2b83 commit 35dd529
Showing 1 changed file with 25 additions and 8 deletions.
33 changes: 25 additions & 8 deletions strings/knuth_morris_pratt.py
Original file line number Diff line number Diff line change
@@ -1,7 +1,7 @@
from __future__ import annotations


def kmp(pattern: str, text: str) -> bool:
def knuth_morris_pratt(text: str, pattern: str) -> int:
"""
The Knuth-Morris-Pratt Algorithm for finding a pattern within a piece of text
with complexity O(n + m)
Expand All @@ -14,6 +14,12 @@ def kmp(pattern: str, text: str) -> bool:
2) Step through the text one character at a time and compare it to a character in
the pattern updating our location within the pattern if necessary
>>> kmp = "knuth_morris_pratt"
>>> all(
... knuth_morris_pratt(kmp, s) == kmp.find(s)
... for s in ("kn", "h_m", "rr", "tt", "not there")
... )
True
"""

# 1) Construct the failure array
Expand All @@ -24,7 +30,7 @@ def kmp(pattern: str, text: str) -> bool:
while i < len(text):
if pattern[j] == text[i]:
if j == (len(pattern) - 1):
return True
return i - j
j += 1

# if this is a prefix in our pattern
Expand All @@ -33,7 +39,7 @@ def kmp(pattern: str, text: str) -> bool:
j = failure[j - 1]
continue
i += 1
return False
return -1


def get_failure_array(pattern: str) -> list[int]:
Expand All @@ -57,27 +63,38 @@ def get_failure_array(pattern: str) -> list[int]:


if __name__ == "__main__":
import doctest

doctest.testmod()

# Test 1)
pattern = "abc1abc12"
text1 = "alskfjaldsabc1abc1abc12k23adsfabcabc"
text2 = "alskfjaldsk23adsfabcabc"
assert kmp(pattern, text1) and not kmp(pattern, text2)
assert knuth_morris_pratt(text1, pattern) and knuth_morris_pratt(text2, pattern)

# Test 2)
pattern = "ABABX"
text = "ABABZABABYABABX"
assert kmp(pattern, text)
assert knuth_morris_pratt(text, pattern)

# Test 3)
pattern = "AAAB"
text = "ABAAAAAB"
assert kmp(pattern, text)
assert knuth_morris_pratt(text, pattern)

# Test 4)
pattern = "abcdabcy"
text = "abcxabcdabxabcdabcdabcy"
assert kmp(pattern, text)
assert knuth_morris_pratt(text, pattern)

# Test 5) -> Doctests
kmp = "knuth_morris_pratt"
assert all(
knuth_morris_pratt(kmp, s) == kmp.find(s)
for s in ("kn", "h_m", "rr", "tt", "not there")
)

# Test 5)
# Test 6)
pattern = "aabaabaaa"
assert get_failure_array(pattern) == [0, 1, 0, 1, 2, 3, 4, 5, 2]

0 comments on commit 35dd529

Please sign in to comment.