projects
/
cipher-tools.git
/ blobdiff
commit
grep
author
committer
pickaxe
?
search:
re
summary
|
shortlog
|
log
|
commit
|
commitdiff
|
tree
raw
|
inline
| side by side
Moved cracking files into directories
[cipher-tools.git]
/
language_models.py
diff --git
a/language_models.py
b/language_models.py
index 1b90ac2ca425c1a246b410ac2f7a588931105f00..5a35b38ec32867dbe00f6fe6e99ada066e858c8e 100644
(file)
--- a/
language_models.py
+++ b/
language_models.py
@@
-5,6
+5,9
@@
import collections
import unicodedata
import itertools
from math import log10
import unicodedata
import itertools
from math import log10
+import os
+
+unaccent_specials = ''.maketrans({"’": "'"})
def letters(text):
"""Remove all non-alphabetic characters from a text
def letters(text):
"""Remove all non-alphabetic characters from a text
@@
-31,7
+34,8
@@
def unaccent(text):
>>> unaccent('HÉLLÖ')
'HELLO'
"""
>>> unaccent('HÉLLÖ')
'HELLO'
"""
- return unicodedata.normalize('NFKD', text).\
+ translated_text = text.translate(unaccent_specials)
+ return unicodedata.normalize('NFKD', translated_text).\
encode('ascii', 'ignore').\
decode('utf-8')
encode('ascii', 'ignore').\
decode('utf-8')
@@
-53,7
+57,7
@@
def sanitise(text):
def datafile(name, sep='\t'):
"""Read key,value pairs from file.
"""
def datafile(name, sep='\t'):
"""Read key,value pairs from file.
"""
- with open(
name
, 'r') as f:
+ with open(
os.path.join(os.path.dirname(os.path.realpath(__file__)), name)
, 'r') as f:
for line in f:
splits = line.split(sep)
yield [splits[0], int(splits[1])]
for line in f:
splits = line.split(sep)
yield [splits[0], int(splits[1])]
@@
-67,7
+71,7
@@
normalised_english_bigram_counts = norms.normalise(english_bigram_counts)
english_trigram_counts = collections.Counter(dict(datafile('count_3l.txt')))
normalised_english_trigram_counts = norms.normalise(english_trigram_counts)
english_trigram_counts = collections.Counter(dict(datafile('count_3l.txt')))
normalised_english_trigram_counts = norms.normalise(english_trigram_counts)
-with open(
'words.txt'
, 'r') as f:
+with open(
os.path.join(os.path.dirname(os.path.realpath(__file__)), 'words.txt')
, 'r') as f:
keywords = [line.rstrip() for line in f]
keywords = [line.rstrip() for line in f]
@@
-121,7
+125,7
@@
def log_probability_of_unknown_word(key, N):
Pw = Pdist(datafile('count_1w.txt'), log_probability_of_unknown_word)
Pl = Pdist(datafile('count_1l.txt'), lambda _k, _N: 0)
Pw = Pdist(datafile('count_1w.txt'), log_probability_of_unknown_word)
Pl = Pdist(datafile('count_1l.txt'), lambda _k, _N: 0)
-P
l2
= Pdist(datafile('count_2l.txt'), lambda _k, _N: 0)
+P
2l
= Pdist(datafile('count_2l.txt'), lambda _k, _N: 0)
def Pwords(words):
"""The Naive Bayes log probability of a sequence of words.
def Pwords(words):
"""The Naive Bayes log probability of a sequence of words.