This repository has been archived by the owner on Nov 19, 2023. It is now read-only.
-
Notifications
You must be signed in to change notification settings - Fork 1
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
- Loading branch information
0 parents
commit a54b644
Showing
11 changed files
with
566,848 additions
and
0 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,21 @@ | ||
MIT License | ||
|
||
Copyright (c) 2019 avandekleut | ||
|
||
Permission is hereby granted, free of charge, to any person obtaining a copy | ||
of this software and associated documentation files (the "Software"), to deal | ||
in the Software without restriction, including without limitation the rights | ||
to use, copy, modify, merge, publish, distribute, sublicense, and/or sell | ||
copies of the Software, and to permit persons to whom the Software is | ||
furnished to do so, subject to the following conditions: | ||
|
||
The above copyright notice and this permission notice shall be included in all | ||
copies or substantial portions of the Software. | ||
|
||
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR | ||
IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, | ||
FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE | ||
AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER | ||
LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, | ||
OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE | ||
SOFTWARE. |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,43 @@ | ||
# anagram-generator | ||
|
||
[![Build Status](https://travis-ci.org/joemccann/dillinger.svg?branch=master)](https://travis-ci.org/joemccann/dillinger) | ||
|
||
`anagram-generator` is a minimal python package that lets you generate multi-word anagrams from any corpus. This package is written in pure python and has no dependencies. See `anagram-generator/writeup/writeup.pdf` to learn how it works (**tries** and clever sorting of partially generated anagrams), or read the source code at `anagram-generator/anagram-generator.py`. Example corpuses are in `anagram-generator/corpuses`. | ||
|
||
### Installation | ||
|
||
Installation is easy using `pip`. | ||
|
||
```sh | ||
$ pip install anagramgen | ||
``` | ||
|
||
### Example | ||
```python | ||
from anagramgen import AnagramGenerator | ||
with open('corpuses/top-5k.txt', 'r') as file: | ||
corpus = [line.strip() for line in file.readlines()] | ||
gen = AnagramGenerator(corpus) | ||
gen.generate("wonderland") | ||
``` | ||
returns | ||
|
||
```python | ||
[['do', 'lend', 'warn'], | ||
['down', 'land', 're'], | ||
['draw', 'lend', 'on'], | ||
['draw', 'lend', 'no'], | ||
['dawn', 'lend', 'or'], | ||
['end', 'old', 'warn'], | ||
['end', 'lawn', 'rod'], | ||
['end', 'land', 'row'], | ||
['lend', 'nod', 'war'], | ||
['lend', 'nod', 'raw'], | ||
['lawn', 'nod', 'red'], | ||
['land', 'wonder'], | ||
['land', 'own', 'red'], | ||
['land', 'now', 'red'], | ||
['land', 'new', 'rod'], | ||
['a', 'drown', 'lend'], | ||
['and', 'lend', 'row']] | ||
``` |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1 @@ | ||
from anagramgen import AnagramGenerator |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,73 @@ | ||
from random import randrange | ||
|
||
class Trie: | ||
def __init__(self): | ||
self.root = {} | ||
|
||
def add(self, word): | ||
self.__add(self.root, word[0], word[1:]) | ||
|
||
def __add(self, node, prefix, suffix): | ||
if prefix not in node: | ||
node[prefix] = {} | ||
if suffix == "": | ||
node[prefix][suffix] = "" | ||
else: | ||
new_prefix = suffix[0] | ||
new_suffix = suffix[1:] | ||
self.__add(node[prefix], new_prefix, new_suffix) | ||
|
||
def __contains__(self, word): | ||
word = list(word) | ||
index_string = "['" + "']['".join(word) + "']" | ||
try: | ||
child_nodes = eval("self.root"+index_string) | ||
if '' in child_nodes: | ||
return True | ||
except KeyError: | ||
pass | ||
return False | ||
|
||
class AnagramGenerator: | ||
def __init__(self, corpus): | ||
self.t = Trie() | ||
for word in corpus: | ||
word = word.rstrip() | ||
self.t.add(word) | ||
|
||
def frequency_dict(self, string): | ||
f = {} | ||
for letter in string: | ||
if letter not in f: | ||
f[letter] = 0 | ||
f[letter] += 1 | ||
return f | ||
|
||
def generate(self, string): | ||
string = string.lower() | ||
for c in string: | ||
if c not in 'abcdefghijklmnopqrstuvwxyz': | ||
string = string.replace(c, "") | ||
|
||
anagrams = [] | ||
f = self.frequency_dict(string) | ||
self.__generate(anagrams, self.t.root, [], "", f) | ||
|
||
return anagrams | ||
|
||
def __generate(self, anagrams, node, partial_anagram, current_word, f): | ||
if '' in node: # if we have just finished generating a word | ||
next_partial_anagram = partial_anagram + [current_word] | ||
if all([f[key] == 0 for key in f]): # if there are no more letters | ||
anagrams.append(next_partial_anagram) # then this is a full phrase anagram | ||
else: | ||
self.__generate(anagrams, self.t.root, next_partial_anagram, "", f) # so loop back to the top of the tree with a new word and add a space to the anagram phrase we are building | ||
|
||
for prefix in f: | ||
if f[prefix] > 0: | ||
if prefix in node: | ||
new_word = current_word+prefix | ||
if len(partial_anagram) == 0 or new_word >= partial_anagram[-1][:len(new_word)]: | ||
f[prefix] -= 1 # since f is shared between function calls we need to subtract from it | ||
self.__generate(anagrams, node[prefix], partial_anagram, current_word+prefix, f) | ||
f[prefix] += 1 # then add back |
Oops, something went wrong.