Skip to content

Commit c0280a0

Browse files
lowelowe
committed
scoring unit tests: dictionary entropy
1 parent 67c21de commit c0280a0

1 file changed

Lines changed: 82 additions & 44 deletions

File tree

‎test/test-scoring.coffee‎

Lines changed: 82 additions & 44 deletions
Original file line numberDiff line numberDiff line change
@@ -106,50 +106,6 @@ test 'display time', (t) ->
106106
t.equal scoring.display_time(seconds), display, msg
107107
t.end()
108108

109-
test 'extra uppercase entropy', (t) ->
110-
for [word, extra_entropy] in [
111-
[ '', 0 ]
112-
[ 'a', 0 ]
113-
[ 'A', 1 ]
114-
[ 'abcdef', 0 ]
115-
[ 'Abcdef', 1 ]
116-
[ 'abcdeF', 1 ]
117-
[ 'ABCDEF', 1 ]
118-
[ 'aBcdef', lg(nCk(6,1)) ]
119-
[ 'aBcDef', lg(nCk(6,1) + nCk(6,2)) ]
120-
[ 'ABCDEf', lg(nCk(6,1)) ]
121-
[ 'aBCDEf', lg(nCk(6,1) + nCk(6,2)) ]
122-
[ 'ABCdef', lg(nCk(6,1) + nCk(6,2) + nCk(6,3)) ]
123-
]
124-
msg = "extra uppercase entropy of #{word} is #{extra_entropy}"
125-
t.equal scoring.extra_uppercase_entropy(token: word), extra_entropy, msg
126-
t.end()
127-
128-
test 'extra l33t entropy', (t) ->
129-
match = l33t: false
130-
t.equal scoring.extra_l33t_entropy(match), 0, "0 extra entropy for non-l33t matches"
131-
for [word, extra_entropy, sub] in [
132-
[ '', 0, {} ]
133-
[ 'a', 0, {} ]
134-
[ '4', 1, {'4': 'a'} ]
135-
[ '4pple', 1, {'4': 'a'} ]
136-
[ 'abcet', 0, {} ]
137-
[ '4bcet', 1, {'4': 'a'} ]
138-
[ 'a8cet', 1, {'8': 'b'} ]
139-
[ 'abce+', 1, {'+': 't'} ]
140-
[ '48cet', 2, {'4': 'a', '8': 'b'} ]
141-
[ 'a4a4aa', lg(nCk(6, 2) + nCk(6, 1)), {'4': 'a'} ]
142-
[ '4a4a44', lg(nCk(6, 2) + nCk(6, 1)), {'4': 'a'} ]
143-
[ 'a44att+', lg(nCk(4, 2) + nCk(4, 1)) + lg(nCk(3, 1)), {'4': 'a', '+': 't'} ]
144-
]
145-
match =
146-
token: word
147-
sub: sub
148-
match.l33t = not matching.empty(sub)
149-
msg = "extra l33t entropy of #{word} is #{extra_entropy}"
150-
t.equal scoring.extra_l33t_entropy(match), extra_entropy, msg
151-
t.end()
152-
153109
test 'minimum entropy search', (t) ->
154110
m = (i, j, entropy) ->
155111
i: i
@@ -309,3 +265,85 @@ test 'date entropy', (t) ->
309265
msg += " extra entropy is added for separators and a 4-digit year."
310266
t.equal scoring.date_entropy(match), lg(12 * 31 * scoring.MIN_YEAR_SPACE) + 2 + 1, msg
311267
t.end()
268+
269+
test 'dictionary_entropy', (t) ->
270+
match =
271+
token: 'aaaaa'
272+
rank: 32
273+
msg = "base entropy is the lg of the rank"
274+
t.equal scoring.dictionary_entropy(match), lg(32), msg
275+
276+
match =
277+
token: 'AAAaaa'
278+
rank: 32
279+
msg = "extra entropy is added for capitalization"
280+
t.equal scoring.dictionary_entropy(match), lg(32) + scoring.extra_uppercase_entropy(match), msg
281+
282+
match =
283+
token: 'aaa@@@'
284+
rank: 32
285+
l33t: true
286+
sub: {'@': 'a'}
287+
msg = "extra entropy is added for common l33t substitutions"
288+
t.equal scoring.dictionary_entropy(match), lg(32) + scoring.extra_l33t_entropy(match), msg
289+
290+
match =
291+
token: 'AaA@@@'
292+
rank: 32
293+
l33t: true
294+
sub: {'@': 'a'}
295+
msg = "extra entropy is added for both capitalization and common l33t substitutions"
296+
expected = lg(32) + scoring.extra_l33t_entropy(match) + scoring.extra_uppercase_entropy(match)
297+
t.equal scoring.dictionary_entropy(match), expected, msg
298+
t.end()
299+
300+
test 'extra uppercase entropy', (t) ->
301+
for [word, extra_entropy] in [
302+
[ '', 0 ]
303+
[ 'a', 0 ]
304+
[ 'A', 1 ]
305+
[ 'abcdef', 0 ]
306+
[ 'Abcdef', 1 ]
307+
[ 'abcdeF', 1 ]
308+
[ 'ABCDEF', 1 ]
309+
[ 'aBcdef', lg(nCk(6,1)) ]
310+
[ 'aBcDef', lg(nCk(6,1) + nCk(6,2)) ]
311+
[ 'ABCDEf', lg(nCk(6,1)) ]
312+
[ 'aBCDEf', lg(nCk(6,1) + nCk(6,2)) ]
313+
[ 'ABCdef', lg(nCk(6,1) + nCk(6,2) + nCk(6,3)) ]
314+
]
315+
msg = "extra uppercase entropy of #{word} is #{extra_entropy}"
316+
t.equal scoring.extra_uppercase_entropy(token: word), extra_entropy, msg
317+
t.end()
318+
319+
test 'extra l33t entropy', (t) ->
320+
match = l33t: false
321+
t.equal scoring.extra_l33t_entropy(match), 0, "0 extra entropy for non-l33t matches"
322+
for [word, extra_entropy, sub] in [
323+
[ '', 0, {} ]
324+
[ 'a', 0, {} ]
325+
[ '4', 1, {'4': 'a'} ]
326+
[ '4pple', 1, {'4': 'a'} ]
327+
[ 'abcet', 0, {} ]
328+
[ '4bcet', 1, {'4': 'a'} ]
329+
[ 'a8cet', 1, {'8': 'b'} ]
330+
[ 'abce+', 1, {'+': 't'} ]
331+
[ '48cet', 2, {'4': 'a', '8': 'b'} ]
332+
[ 'a4a4aa', lg(nCk(6, 2) + nCk(6, 1)), {'4': 'a'} ]
333+
[ '4a4a44', lg(nCk(6, 2) + nCk(6, 1)), {'4': 'a'} ]
334+
[ 'a44att+', lg(nCk(4, 2) + nCk(4, 1)) + lg(nCk(3, 1)), {'4': 'a', '+': 't'} ]
335+
]
336+
match =
337+
token: word
338+
sub: sub
339+
l33t: not matching.empty(sub)
340+
msg = "extra l33t entropy of #{word} is #{extra_entropy}"
341+
t.equal scoring.extra_l33t_entropy(match), extra_entropy, msg
342+
match =
343+
token: 'Aa44aA'
344+
l33t: true
345+
sub: {'4': 'a'}
346+
extra_entropy = lg(nCk(6, 2) + nCk(6, 1))
347+
msg = "capitalization doesn't affect extra l33t entropy calc"
348+
t.equal scoring.extra_l33t_entropy(match), extra_entropy, msg
349+
t.end()

0 commit comments

Comments
 (0)