phrasify 0.0.1
Sign up to get free protection for your applications and to get access to all the features.
- data/.gitignore +4 -0
- data/.rspec +1 -0
- data/.rvmrc +1 -0
- data/Gemfile +16 -0
- data/Guardfile +6 -0
- data/Rakefile +1 -0
- data/lib/phrasify.rb +7 -0
- data/lib/phrasify/common_words.rb +1006 -0
- data/lib/phrasify/phrase.rb +14 -0
- data/lib/phrasify/text.rb +63 -0
- data/lib/phrasify/version.rb +3 -0
- data/phrasify.gemspec +23 -0
- data/spec/phrasify_spec.rb +1 -0
- data/spec/spec_helper.rb +1 -0
- data/spec/text_spec.rb +92 -0
- metadata +87 -0
data/.gitignore
ADDED
data/.rspec
ADDED
@@ -0,0 +1 @@
|
|
1
|
+
--color
|
data/.rvmrc
ADDED
@@ -0,0 +1 @@
|
|
1
|
+
rvm use 1.9.3-rc1@phrasify --create
|
data/Gemfile
ADDED
@@ -0,0 +1,16 @@
|
|
1
|
+
source "http://rubygems.org"
|
2
|
+
|
3
|
+
# Specify your gem's dependencies in phrasify.gemspec
|
4
|
+
gemspec
|
5
|
+
|
6
|
+
|
7
|
+
gem 'rake'
|
8
|
+
|
9
|
+
require 'rbconfig'
|
10
|
+
|
11
|
+
if RbConfig::CONFIG['target_os'] =~ /darwin/i
|
12
|
+
gem 'rb-fsevent', '>= 0.4.0', :require => false
|
13
|
+
gem 'growl_notify', :require => false
|
14
|
+
gem 'guard', '~> 0.6.0', :require => false
|
15
|
+
gem 'guard-rspec', '~> 0.4.0', :require => false
|
16
|
+
end
|
data/Guardfile
ADDED
data/Rakefile
ADDED
@@ -0,0 +1 @@
|
|
1
|
+
require "bundler/gem_tasks"
|
data/lib/phrasify.rb
ADDED
@@ -0,0 +1,1006 @@
|
|
1
|
+
module Phrasify
|
2
|
+
|
3
|
+
# http://giwersworld.org/computers/linux/common-words.phtml
|
4
|
+
COMMON_WORDS = %w{
|
5
|
+
a
|
6
|
+
able
|
7
|
+
about
|
8
|
+
above
|
9
|
+
according
|
10
|
+
account
|
11
|
+
across
|
12
|
+
act
|
13
|
+
action
|
14
|
+
activities
|
15
|
+
activity
|
16
|
+
actually
|
17
|
+
added
|
18
|
+
addition
|
19
|
+
additional
|
20
|
+
administration
|
21
|
+
after
|
22
|
+
again
|
23
|
+
against
|
24
|
+
age
|
25
|
+
ago
|
26
|
+
ahead
|
27
|
+
aid
|
28
|
+
air
|
29
|
+
all
|
30
|
+
almost
|
31
|
+
alone
|
32
|
+
along
|
33
|
+
already
|
34
|
+
also
|
35
|
+
although
|
36
|
+
always
|
37
|
+
am
|
38
|
+
america
|
39
|
+
american
|
40
|
+
among
|
41
|
+
amount
|
42
|
+
an
|
43
|
+
analysis
|
44
|
+
and
|
45
|
+
another
|
46
|
+
answer
|
47
|
+
anti
|
48
|
+
any
|
49
|
+
anyone
|
50
|
+
anything
|
51
|
+
apparently
|
52
|
+
appear
|
53
|
+
appeared
|
54
|
+
approach
|
55
|
+
are
|
56
|
+
area
|
57
|
+
areas
|
58
|
+
arms
|
59
|
+
army
|
60
|
+
around
|
61
|
+
art
|
62
|
+
as
|
63
|
+
ask
|
64
|
+
asked
|
65
|
+
association
|
66
|
+
at
|
67
|
+
attack
|
68
|
+
attention
|
69
|
+
audience
|
70
|
+
available
|
71
|
+
average
|
72
|
+
away
|
73
|
+
b
|
74
|
+
back
|
75
|
+
bad
|
76
|
+
ball
|
77
|
+
based
|
78
|
+
basic
|
79
|
+
basis
|
80
|
+
be
|
81
|
+
beautiful
|
82
|
+
became
|
83
|
+
because
|
84
|
+
become
|
85
|
+
bed
|
86
|
+
been
|
87
|
+
before
|
88
|
+
began
|
89
|
+
beginning
|
90
|
+
behind
|
91
|
+
being
|
92
|
+
believe
|
93
|
+
below
|
94
|
+
best
|
95
|
+
better
|
96
|
+
between
|
97
|
+
beyond
|
98
|
+
big
|
99
|
+
bill
|
100
|
+
black
|
101
|
+
blood
|
102
|
+
blue
|
103
|
+
board
|
104
|
+
body
|
105
|
+
book
|
106
|
+
born
|
107
|
+
both
|
108
|
+
boy
|
109
|
+
boys
|
110
|
+
bring
|
111
|
+
british
|
112
|
+
brought
|
113
|
+
brown
|
114
|
+
building
|
115
|
+
built
|
116
|
+
business
|
117
|
+
but
|
118
|
+
by
|
119
|
+
c
|
120
|
+
call
|
121
|
+
called
|
122
|
+
came
|
123
|
+
can
|
124
|
+
cannot
|
125
|
+
cant
|
126
|
+
car
|
127
|
+
care
|
128
|
+
carried
|
129
|
+
cars
|
130
|
+
case
|
131
|
+
cases
|
132
|
+
cause
|
133
|
+
cent
|
134
|
+
center
|
135
|
+
central
|
136
|
+
century
|
137
|
+
certain
|
138
|
+
certainly
|
139
|
+
chance
|
140
|
+
change
|
141
|
+
changes
|
142
|
+
character
|
143
|
+
charge
|
144
|
+
chief
|
145
|
+
child
|
146
|
+
children
|
147
|
+
choice
|
148
|
+
christian
|
149
|
+
church
|
150
|
+
city
|
151
|
+
class
|
152
|
+
clear
|
153
|
+
clearly
|
154
|
+
close
|
155
|
+
closed
|
156
|
+
club
|
157
|
+
co
|
158
|
+
cold
|
159
|
+
college
|
160
|
+
color
|
161
|
+
come
|
162
|
+
comes
|
163
|
+
coming
|
164
|
+
committee
|
165
|
+
common
|
166
|
+
communist
|
167
|
+
community
|
168
|
+
company
|
169
|
+
complete
|
170
|
+
completely
|
171
|
+
concerned
|
172
|
+
conditions
|
173
|
+
congress
|
174
|
+
consider
|
175
|
+
considered
|
176
|
+
continued
|
177
|
+
control
|
178
|
+
corner
|
179
|
+
corps
|
180
|
+
cost
|
181
|
+
costs
|
182
|
+
could
|
183
|
+
couldnt
|
184
|
+
countries
|
185
|
+
country
|
186
|
+
county
|
187
|
+
couple
|
188
|
+
course
|
189
|
+
court
|
190
|
+
covered
|
191
|
+
cut
|
192
|
+
d
|
193
|
+
daily
|
194
|
+
dark
|
195
|
+
data
|
196
|
+
day
|
197
|
+
days
|
198
|
+
de
|
199
|
+
dead
|
200
|
+
deal
|
201
|
+
death
|
202
|
+
decided
|
203
|
+
decision
|
204
|
+
deep
|
205
|
+
defense
|
206
|
+
degree
|
207
|
+
democratic
|
208
|
+
department
|
209
|
+
described
|
210
|
+
design
|
211
|
+
designed
|
212
|
+
determined
|
213
|
+
developed
|
214
|
+
development
|
215
|
+
did
|
216
|
+
didnt
|
217
|
+
difference
|
218
|
+
different
|
219
|
+
difficult
|
220
|
+
direct
|
221
|
+
direction
|
222
|
+
directly
|
223
|
+
distance
|
224
|
+
district
|
225
|
+
do
|
226
|
+
does
|
227
|
+
doing
|
228
|
+
done
|
229
|
+
dont
|
230
|
+
door
|
231
|
+
doubt
|
232
|
+
down
|
233
|
+
dr
|
234
|
+
drive
|
235
|
+
due
|
236
|
+
during
|
237
|
+
e
|
238
|
+
each
|
239
|
+
earlier
|
240
|
+
early
|
241
|
+
earth
|
242
|
+
east
|
243
|
+
easy
|
244
|
+
economic
|
245
|
+
education
|
246
|
+
effect
|
247
|
+
effective
|
248
|
+
effects
|
249
|
+
effort
|
250
|
+
efforts
|
251
|
+
eight
|
252
|
+
either
|
253
|
+
elements
|
254
|
+
else
|
255
|
+
end
|
256
|
+
england
|
257
|
+
english
|
258
|
+
enough
|
259
|
+
entire
|
260
|
+
equipment
|
261
|
+
especially
|
262
|
+
established
|
263
|
+
europe
|
264
|
+
even
|
265
|
+
evening
|
266
|
+
ever
|
267
|
+
every
|
268
|
+
everything
|
269
|
+
evidence
|
270
|
+
example
|
271
|
+
except
|
272
|
+
existence
|
273
|
+
expect
|
274
|
+
expected
|
275
|
+
experience
|
276
|
+
extent
|
277
|
+
eye
|
278
|
+
eyes
|
279
|
+
f
|
280
|
+
face
|
281
|
+
fact
|
282
|
+
faith
|
283
|
+
fall
|
284
|
+
family
|
285
|
+
far
|
286
|
+
farm
|
287
|
+
father
|
288
|
+
fear
|
289
|
+
federal
|
290
|
+
feed
|
291
|
+
feel
|
292
|
+
feeling
|
293
|
+
feet
|
294
|
+
felt
|
295
|
+
few
|
296
|
+
field
|
297
|
+
figure
|
298
|
+
figures
|
299
|
+
filled
|
300
|
+
final
|
301
|
+
finally
|
302
|
+
find
|
303
|
+
fine
|
304
|
+
fire
|
305
|
+
firm
|
306
|
+
first
|
307
|
+
fiscal
|
308
|
+
five
|
309
|
+
floor
|
310
|
+
followed
|
311
|
+
following
|
312
|
+
food
|
313
|
+
foot
|
314
|
+
for
|
315
|
+
force
|
316
|
+
forces
|
317
|
+
foreign
|
318
|
+
form
|
319
|
+
former
|
320
|
+
forms
|
321
|
+
forward
|
322
|
+
found
|
323
|
+
four
|
324
|
+
free
|
325
|
+
freedom
|
326
|
+
french
|
327
|
+
friend
|
328
|
+
friends
|
329
|
+
from
|
330
|
+
front
|
331
|
+
full
|
332
|
+
function
|
333
|
+
further
|
334
|
+
future
|
335
|
+
g
|
336
|
+
game
|
337
|
+
gave
|
338
|
+
general
|
339
|
+
generally
|
340
|
+
george
|
341
|
+
get
|
342
|
+
getting
|
343
|
+
girl
|
344
|
+
girls
|
345
|
+
give
|
346
|
+
given
|
347
|
+
gives
|
348
|
+
glass
|
349
|
+
go
|
350
|
+
god
|
351
|
+
going
|
352
|
+
gone
|
353
|
+
good
|
354
|
+
got
|
355
|
+
government
|
356
|
+
great
|
357
|
+
greater
|
358
|
+
green
|
359
|
+
ground
|
360
|
+
group
|
361
|
+
groups
|
362
|
+
growing
|
363
|
+
growth
|
364
|
+
gun
|
365
|
+
h
|
366
|
+
had
|
367
|
+
hair
|
368
|
+
half
|
369
|
+
hall
|
370
|
+
hand
|
371
|
+
hands
|
372
|
+
happened
|
373
|
+
hard
|
374
|
+
has
|
375
|
+
have
|
376
|
+
having
|
377
|
+
he
|
378
|
+
head
|
379
|
+
hear
|
380
|
+
heard
|
381
|
+
heart
|
382
|
+
heavy
|
383
|
+
held
|
384
|
+
hell
|
385
|
+
help
|
386
|
+
her
|
387
|
+
here
|
388
|
+
herself
|
389
|
+
hes
|
390
|
+
high
|
391
|
+
higher
|
392
|
+
him
|
393
|
+
himself
|
394
|
+
his
|
395
|
+
history
|
396
|
+
hit
|
397
|
+
hold
|
398
|
+
home
|
399
|
+
hope
|
400
|
+
horse
|
401
|
+
hospital
|
402
|
+
hot
|
403
|
+
hotel
|
404
|
+
hour
|
405
|
+
hours
|
406
|
+
house
|
407
|
+
how
|
408
|
+
however
|
409
|
+
human
|
410
|
+
hundred
|
411
|
+
husband
|
412
|
+
i
|
413
|
+
idea
|
414
|
+
ideas
|
415
|
+
if
|
416
|
+
ill
|
417
|
+
im
|
418
|
+
image
|
419
|
+
immediately
|
420
|
+
important
|
421
|
+
in
|
422
|
+
include
|
423
|
+
including
|
424
|
+
income
|
425
|
+
increase
|
426
|
+
increased
|
427
|
+
indeed
|
428
|
+
individual
|
429
|
+
industrial
|
430
|
+
industry
|
431
|
+
influence
|
432
|
+
information
|
433
|
+
inside
|
434
|
+
instead
|
435
|
+
interest
|
436
|
+
international
|
437
|
+
into
|
438
|
+
involved
|
439
|
+
is
|
440
|
+
island
|
441
|
+
issue
|
442
|
+
it
|
443
|
+
its
|
444
|
+
itself
|
445
|
+
ive
|
446
|
+
j
|
447
|
+
job
|
448
|
+
john
|
449
|
+
just
|
450
|
+
justice
|
451
|
+
keep
|
452
|
+
kennedy
|
453
|
+
kept
|
454
|
+
kind
|
455
|
+
knew
|
456
|
+
know
|
457
|
+
knowledge
|
458
|
+
known
|
459
|
+
l
|
460
|
+
labor
|
461
|
+
lack
|
462
|
+
land
|
463
|
+
language
|
464
|
+
large
|
465
|
+
larger
|
466
|
+
last
|
467
|
+
late
|
468
|
+
later
|
469
|
+
latter
|
470
|
+
law
|
471
|
+
lay
|
472
|
+
lead
|
473
|
+
leaders
|
474
|
+
learned
|
475
|
+
least
|
476
|
+
leave
|
477
|
+
led
|
478
|
+
left
|
479
|
+
length
|
480
|
+
less
|
481
|
+
let
|
482
|
+
letter
|
483
|
+
letters
|
484
|
+
level
|
485
|
+
life
|
486
|
+
light
|
487
|
+
like
|
488
|
+
likely
|
489
|
+
line
|
490
|
+
lines
|
491
|
+
list
|
492
|
+
literature
|
493
|
+
little
|
494
|
+
live
|
495
|
+
lived
|
496
|
+
living
|
497
|
+
local
|
498
|
+
long
|
499
|
+
longer
|
500
|
+
look
|
501
|
+
looked
|
502
|
+
looking
|
503
|
+
lost
|
504
|
+
lot
|
505
|
+
love
|
506
|
+
low
|
507
|
+
lower
|
508
|
+
m
|
509
|
+
made
|
510
|
+
main
|
511
|
+
major
|
512
|
+
make
|
513
|
+
makes
|
514
|
+
making
|
515
|
+
man
|
516
|
+
manner
|
517
|
+
mans
|
518
|
+
many
|
519
|
+
march
|
520
|
+
market
|
521
|
+
married
|
522
|
+
mass
|
523
|
+
material
|
524
|
+
matter
|
525
|
+
may
|
526
|
+
maybe
|
527
|
+
me
|
528
|
+
mean
|
529
|
+
meaning
|
530
|
+
means
|
531
|
+
medical
|
532
|
+
meet
|
533
|
+
meeting
|
534
|
+
member
|
535
|
+
members
|
536
|
+
men
|
537
|
+
merely
|
538
|
+
met
|
539
|
+
method
|
540
|
+
methods
|
541
|
+
middle
|
542
|
+
might
|
543
|
+
miles
|
544
|
+
military
|
545
|
+
million
|
546
|
+
mind
|
547
|
+
minutes
|
548
|
+
miss
|
549
|
+
modern
|
550
|
+
moment
|
551
|
+
money
|
552
|
+
month
|
553
|
+
months
|
554
|
+
moral
|
555
|
+
more
|
556
|
+
morning
|
557
|
+
most
|
558
|
+
mother
|
559
|
+
move
|
560
|
+
moved
|
561
|
+
movement
|
562
|
+
moving
|
563
|
+
mr
|
564
|
+
mrs
|
565
|
+
much
|
566
|
+
music
|
567
|
+
must
|
568
|
+
my
|
569
|
+
myself
|
570
|
+
n
|
571
|
+
name
|
572
|
+
nation
|
573
|
+
national
|
574
|
+
nations
|
575
|
+
natural
|
576
|
+
nature
|
577
|
+
near
|
578
|
+
nearly
|
579
|
+
necessary
|
580
|
+
need
|
581
|
+
needed
|
582
|
+
needs
|
583
|
+
negro
|
584
|
+
neither
|
585
|
+
never
|
586
|
+
new
|
587
|
+
next
|
588
|
+
night
|
589
|
+
no
|
590
|
+
non
|
591
|
+
nor
|
592
|
+
normal
|
593
|
+
north
|
594
|
+
not
|
595
|
+
note
|
596
|
+
nothing
|
597
|
+
now
|
598
|
+
nuclear
|
599
|
+
number
|
600
|
+
numbers
|
601
|
+
obtained
|
602
|
+
obviously
|
603
|
+
of
|
604
|
+
off
|
605
|
+
office
|
606
|
+
often
|
607
|
+
oh
|
608
|
+
old
|
609
|
+
on
|
610
|
+
once
|
611
|
+
one
|
612
|
+
ones
|
613
|
+
only
|
614
|
+
open
|
615
|
+
opened
|
616
|
+
operation
|
617
|
+
opportunity
|
618
|
+
or
|
619
|
+
order
|
620
|
+
organization
|
621
|
+
other
|
622
|
+
others
|
623
|
+
our
|
624
|
+
out
|
625
|
+
outside
|
626
|
+
over
|
627
|
+
own
|
628
|
+
p
|
629
|
+
paid
|
630
|
+
paper
|
631
|
+
part
|
632
|
+
particular
|
633
|
+
particularly
|
634
|
+
parts
|
635
|
+
party
|
636
|
+
passed
|
637
|
+
past
|
638
|
+
pattern
|
639
|
+
pay
|
640
|
+
peace
|
641
|
+
people
|
642
|
+
per
|
643
|
+
performance
|
644
|
+
perhaps
|
645
|
+
period
|
646
|
+
person
|
647
|
+
personal
|
648
|
+
persons
|
649
|
+
physical
|
650
|
+
picture
|
651
|
+
piece
|
652
|
+
place
|
653
|
+
placed
|
654
|
+
plan
|
655
|
+
plane
|
656
|
+
planning
|
657
|
+
plans
|
658
|
+
plant
|
659
|
+
play
|
660
|
+
point
|
661
|
+
points
|
662
|
+
police
|
663
|
+
policy
|
664
|
+
political
|
665
|
+
pool
|
666
|
+
poor
|
667
|
+
population
|
668
|
+
position
|
669
|
+
possible
|
670
|
+
post
|
671
|
+
power
|
672
|
+
present
|
673
|
+
president
|
674
|
+
press
|
675
|
+
pressure
|
676
|
+
price
|
677
|
+
principle
|
678
|
+
private
|
679
|
+
probably
|
680
|
+
problem
|
681
|
+
problems
|
682
|
+
process
|
683
|
+
production
|
684
|
+
products
|
685
|
+
program
|
686
|
+
programs
|
687
|
+
progress
|
688
|
+
property
|
689
|
+
provide
|
690
|
+
provided
|
691
|
+
public
|
692
|
+
purpose
|
693
|
+
put
|
694
|
+
quality
|
695
|
+
question
|
696
|
+
questions
|
697
|
+
quite
|
698
|
+
r
|
699
|
+
race
|
700
|
+
radio
|
701
|
+
ran
|
702
|
+
range
|
703
|
+
rate
|
704
|
+
rather
|
705
|
+
reached
|
706
|
+
reaction
|
707
|
+
read
|
708
|
+
reading
|
709
|
+
ready
|
710
|
+
real
|
711
|
+
really
|
712
|
+
reason
|
713
|
+
received
|
714
|
+
recent
|
715
|
+
recently
|
716
|
+
record
|
717
|
+
red
|
718
|
+
religion
|
719
|
+
religious
|
720
|
+
remember
|
721
|
+
report
|
722
|
+
reported
|
723
|
+
required
|
724
|
+
research
|
725
|
+
respect
|
726
|
+
responsibility
|
727
|
+
rest
|
728
|
+
result
|
729
|
+
results
|
730
|
+
return
|
731
|
+
returned
|
732
|
+
right
|
733
|
+
river
|
734
|
+
road
|
735
|
+
room
|
736
|
+
run
|
737
|
+
running
|
738
|
+
s
|
739
|
+
said
|
740
|
+
sales
|
741
|
+
same
|
742
|
+
sat
|
743
|
+
saw
|
744
|
+
say
|
745
|
+
saying
|
746
|
+
says
|
747
|
+
school
|
748
|
+
schools
|
749
|
+
science
|
750
|
+
season
|
751
|
+
second
|
752
|
+
secretary
|
753
|
+
section
|
754
|
+
see
|
755
|
+
seem
|
756
|
+
seemed
|
757
|
+
seems
|
758
|
+
seen
|
759
|
+
self
|
760
|
+
sense
|
761
|
+
sent
|
762
|
+
series
|
763
|
+
serious
|
764
|
+
served
|
765
|
+
service
|
766
|
+
services
|
767
|
+
set
|
768
|
+
seven
|
769
|
+
several
|
770
|
+
shall
|
771
|
+
she
|
772
|
+
short
|
773
|
+
shot
|
774
|
+
should
|
775
|
+
show
|
776
|
+
showed
|
777
|
+
shown
|
778
|
+
side
|
779
|
+
similar
|
780
|
+
simple
|
781
|
+
simply
|
782
|
+
since
|
783
|
+
single
|
784
|
+
situation
|
785
|
+
six
|
786
|
+
size
|
787
|
+
slowly
|
788
|
+
small
|
789
|
+
so
|
790
|
+
social
|
791
|
+
society
|
792
|
+
some
|
793
|
+
something
|
794
|
+
sometimes
|
795
|
+
somewhat
|
796
|
+
son
|
797
|
+
soon
|
798
|
+
sort
|
799
|
+
sound
|
800
|
+
south
|
801
|
+
southern
|
802
|
+
soviet
|
803
|
+
space
|
804
|
+
speak
|
805
|
+
special
|
806
|
+
specific
|
807
|
+
spirit
|
808
|
+
spring
|
809
|
+
square
|
810
|
+
st
|
811
|
+
staff
|
812
|
+
stage
|
813
|
+
stand
|
814
|
+
standard
|
815
|
+
start
|
816
|
+
started
|
817
|
+
state
|
818
|
+
statements
|
819
|
+
states
|
820
|
+
stay
|
821
|
+
step
|
822
|
+
steps
|
823
|
+
still
|
824
|
+
stock
|
825
|
+
stood
|
826
|
+
stop
|
827
|
+
stopped
|
828
|
+
story
|
829
|
+
straight
|
830
|
+
street
|
831
|
+
strength
|
832
|
+
strong
|
833
|
+
student
|
834
|
+
students
|
835
|
+
study
|
836
|
+
subject
|
837
|
+
such
|
838
|
+
suddenly
|
839
|
+
summer
|
840
|
+
sun
|
841
|
+
support
|
842
|
+
sure
|
843
|
+
surface
|
844
|
+
system
|
845
|
+
systems
|
846
|
+
t
|
847
|
+
table
|
848
|
+
take
|
849
|
+
taken
|
850
|
+
taking
|
851
|
+
talk
|
852
|
+
tax
|
853
|
+
technical
|
854
|
+
tell
|
855
|
+
temperature
|
856
|
+
ten
|
857
|
+
term
|
858
|
+
terms
|
859
|
+
test
|
860
|
+
th
|
861
|
+
than
|
862
|
+
that
|
863
|
+
thats
|
864
|
+
the
|
865
|
+
their
|
866
|
+
them
|
867
|
+
themselves
|
868
|
+
then
|
869
|
+
theory
|
870
|
+
there
|
871
|
+
therefore
|
872
|
+
theres
|
873
|
+
these
|
874
|
+
they
|
875
|
+
thing
|
876
|
+
things
|
877
|
+
think
|
878
|
+
thinking
|
879
|
+
third
|
880
|
+
thirty
|
881
|
+
this
|
882
|
+
those
|
883
|
+
thought
|
884
|
+
three
|
885
|
+
through
|
886
|
+
through
|
887
|
+
throughout
|
888
|
+
thus
|
889
|
+
time
|
890
|
+
times
|
891
|
+
to
|
892
|
+
today
|
893
|
+
together
|
894
|
+
told
|
895
|
+
too
|
896
|
+
took
|
897
|
+
top
|
898
|
+
total
|
899
|
+
toward
|
900
|
+
town
|
901
|
+
trade
|
902
|
+
training
|
903
|
+
treatment
|
904
|
+
trial
|
905
|
+
tried
|
906
|
+
trouble
|
907
|
+
true
|
908
|
+
truth
|
909
|
+
try
|
910
|
+
trying
|
911
|
+
turn
|
912
|
+
turned
|
913
|
+
twenty
|
914
|
+
two
|
915
|
+
type
|
916
|
+
types
|
917
|
+
u
|
918
|
+
under
|
919
|
+
understand
|
920
|
+
understanding
|
921
|
+
union
|
922
|
+
united
|
923
|
+
university
|
924
|
+
until
|
925
|
+
up
|
926
|
+
upon
|
927
|
+
us
|
928
|
+
use
|
929
|
+
used
|
930
|
+
using
|
931
|
+
usually
|
932
|
+
value
|
933
|
+
values
|
934
|
+
various
|
935
|
+
very
|
936
|
+
view
|
937
|
+
voice
|
938
|
+
volume
|
939
|
+
waiting
|
940
|
+
walked
|
941
|
+
wall
|
942
|
+
want
|
943
|
+
wanted
|
944
|
+
war
|
945
|
+
was
|
946
|
+
washington
|
947
|
+
wasnt
|
948
|
+
water
|
949
|
+
way
|
950
|
+
ways
|
951
|
+
we
|
952
|
+
week
|
953
|
+
weeks
|
954
|
+
well
|
955
|
+
went
|
956
|
+
were
|
957
|
+
west
|
958
|
+
western
|
959
|
+
what
|
960
|
+
whatever
|
961
|
+
when
|
962
|
+
where
|
963
|
+
whether
|
964
|
+
which
|
965
|
+
while
|
966
|
+
white
|
967
|
+
who
|
968
|
+
whole
|
969
|
+
whom
|
970
|
+
whose
|
971
|
+
why
|
972
|
+
wide
|
973
|
+
wife
|
974
|
+
will
|
975
|
+
william
|
976
|
+
window
|
977
|
+
wish
|
978
|
+
with
|
979
|
+
within
|
980
|
+
without
|
981
|
+
woman
|
982
|
+
women
|
983
|
+
word
|
984
|
+
words
|
985
|
+
work
|
986
|
+
worked
|
987
|
+
working
|
988
|
+
works
|
989
|
+
world
|
990
|
+
would
|
991
|
+
wouldnt
|
992
|
+
writing
|
993
|
+
written
|
994
|
+
wrong
|
995
|
+
wrote
|
996
|
+
year
|
997
|
+
years
|
998
|
+
yes
|
999
|
+
yet
|
1000
|
+
york
|
1001
|
+
you
|
1002
|
+
young
|
1003
|
+
your
|
1004
|
+
youre
|
1005
|
+
}
|
1006
|
+
end
|
@@ -0,0 +1,63 @@
|
|
1
|
+
module Phrasify
|
2
|
+
class Text < ::String
|
3
|
+
|
4
|
+
##
|
5
|
+
#
|
6
|
+
#
|
7
|
+
# @param [String] string The string you want to match phrases against
|
8
|
+
# @param [#search] phrase_klass A class that responds to search with an array
|
9
|
+
# of strings
|
10
|
+
# @return [Phrasify::Text]
|
11
|
+
def initialize(string, phrase_klass = Phrase)
|
12
|
+
@phrase_klass = phrase_klass
|
13
|
+
super(string)
|
14
|
+
end
|
15
|
+
|
16
|
+
##
|
17
|
+
#
|
18
|
+
#
|
19
|
+
# @return [Phrasify::Text]
|
20
|
+
def parse
|
21
|
+
phrases.inject(self) do |string, phrase|
|
22
|
+
|
23
|
+
string = string.split(":phrasify:").inject("") do |new_string, part|
|
24
|
+
|
25
|
+
# If this part of the string has already been matched we won't try
|
26
|
+
# and match it again.
|
27
|
+
if part.include?(":matched:")
|
28
|
+
new_string += part
|
29
|
+
else
|
30
|
+
new_string += part.gsub(
|
31
|
+
phrase.match,
|
32
|
+
":phrasify::matched:#{phrase.replace}:matched::phrasify:"
|
33
|
+
)
|
34
|
+
end
|
35
|
+
end
|
36
|
+
end.gsub(":matched:", "").gsub(":phrasify:", "")
|
37
|
+
end
|
38
|
+
|
39
|
+
##
|
40
|
+
# Text broken down into words with all punctuation removed
|
41
|
+
#
|
42
|
+
# @return [Array<String>]
|
43
|
+
def words
|
44
|
+
gsub(/[^A-Za-z0-9_-|\s]/, '').downcase.split(" ").uniq
|
45
|
+
end
|
46
|
+
|
47
|
+
##
|
48
|
+
# Unique list of words that could have a matching phrase
|
49
|
+
#
|
50
|
+
# @return [Array<String>]
|
51
|
+
def phraseable_words
|
52
|
+
words - COMMON_WORDS
|
53
|
+
end
|
54
|
+
|
55
|
+
##
|
56
|
+
# Phrases that could match text
|
57
|
+
#
|
58
|
+
# @return [Array[<Phrase>]]
|
59
|
+
def phrases
|
60
|
+
@phrase_klass.search(phraseable_words)
|
61
|
+
end
|
62
|
+
end
|
63
|
+
end
|
data/phrasify.gemspec
ADDED
@@ -0,0 +1,23 @@
|
|
1
|
+
# -*- encoding: utf-8 -*-
|
2
|
+
$:.push File.expand_path("../lib", __FILE__)
|
3
|
+
require "phrasify/version"
|
4
|
+
|
5
|
+
Gem::Specification.new do |s|
|
6
|
+
s.name = "phrasify"
|
7
|
+
s.version = Phrasify::VERSION
|
8
|
+
s.authors = ["Robert Williams"]
|
9
|
+
s.email = ["rob@r-williams.com"]
|
10
|
+
s.homepage = ""
|
11
|
+
s.summary = %q{Match phrases in text and replace them}
|
12
|
+
s.description = %q{Match phrases in text and replace them efficiently across thousands of different terms.}
|
13
|
+
|
14
|
+
s.rubyforge_project = "phrasify"
|
15
|
+
|
16
|
+
s.files = `git ls-files`.split("\n")
|
17
|
+
s.test_files = `git ls-files -- {test,spec,features}/*`.split("\n")
|
18
|
+
s.executables = `git ls-files -- bin/*`.split("\n").map{ |f| File.basename(f) }
|
19
|
+
s.require_paths = ["lib"]
|
20
|
+
|
21
|
+
s.add_development_dependency('rspec', '~> 2.6.0')
|
22
|
+
s.add_development_dependency('yard')
|
23
|
+
end
|
@@ -0,0 +1 @@
|
|
1
|
+
require_relative './spec_helper'
|
data/spec/spec_helper.rb
ADDED
@@ -0,0 +1 @@
|
|
1
|
+
require_relative '../lib/phrasify'
|
data/spec/text_spec.rb
ADDED
@@ -0,0 +1,92 @@
|
|
1
|
+
require_relative './spec_helper'
|
2
|
+
|
3
|
+
describe Phrasify::Text do
|
4
|
+
|
5
|
+
let(:text) {
|
6
|
+
Phrasify::Text.new(%q(
|
7
|
+
The quick brown fox jumps over the lazy dog.
|
8
|
+
It's inevitable.
|
9
|
+
and and and
|
10
|
+
))
|
11
|
+
}
|
12
|
+
|
13
|
+
describe "#words" do
|
14
|
+
|
15
|
+
it "should return an Array" do
|
16
|
+
text.words.should be_a(Array)
|
17
|
+
end
|
18
|
+
|
19
|
+
it "should not have any duplicate words" do
|
20
|
+
text.words.should eql(text.words.uniq)
|
21
|
+
end
|
22
|
+
|
23
|
+
it "should not contain any strings with apostrophes" do
|
24
|
+
text.words.join.should_not include("it's")
|
25
|
+
end
|
26
|
+
|
27
|
+
it "should only have lowercase characters" do
|
28
|
+
text.words.join.should_not match(/[A-Z].+/)
|
29
|
+
end
|
30
|
+
end
|
31
|
+
|
32
|
+
describe "#phraseable_words" do
|
33
|
+
let(:phraseable_words) {
|
34
|
+
text.phraseable_words
|
35
|
+
}
|
36
|
+
|
37
|
+
it "should not contain any common words" do
|
38
|
+
phraseable_words.should eql(phraseable_words - Phrasify::COMMON_WORDS)
|
39
|
+
end
|
40
|
+
end
|
41
|
+
|
42
|
+
describe "#parse" do
|
43
|
+
|
44
|
+
before do
|
45
|
+
@phrases = [
|
46
|
+
Phrasify::Phrase.new("brown fox", "yellow rabbit"),
|
47
|
+
Phrasify::Phrase.new("lazy", "laid back")
|
48
|
+
]
|
49
|
+
Phrasify::Phrase.stub!(:search).and_return(@phrases)
|
50
|
+
end
|
51
|
+
|
52
|
+
it "should replace the contents of the string" do
|
53
|
+
@phrases.each do |phrase|
|
54
|
+
text.parse.should include(phrase.replace)
|
55
|
+
end
|
56
|
+
end
|
57
|
+
end
|
58
|
+
|
59
|
+
describe "#parse", "with phrases that match replacements" do
|
60
|
+
|
61
|
+
before do
|
62
|
+
@phrases = [
|
63
|
+
Phrasify::Phrase.new("brown fox", "yellow rabbit"),
|
64
|
+
Phrasify::Phrase.new("yellow rabbit", "purple kangaroo")
|
65
|
+
]
|
66
|
+
Phrasify::Phrase.stub!(:search).and_return(@phrases)
|
67
|
+
end
|
68
|
+
|
69
|
+
it "should only replace phrases that have not already been matched" do
|
70
|
+
text.parse.should include("yellow rabbit")
|
71
|
+
text.parse.should_not include("purple kangaroo")
|
72
|
+
end
|
73
|
+
end
|
74
|
+
|
75
|
+
describe "#parse", "with phrases that target the same term" do
|
76
|
+
|
77
|
+
before do
|
78
|
+
@phrases = [
|
79
|
+
Phrasify::Phrase.new("brown fox", "orange hippo"),
|
80
|
+
Phrasify::Phrase.new("brown", "purple kangaroo")
|
81
|
+
]
|
82
|
+
Phrasify::Phrase.stub!(:search).and_return(@phrases)
|
83
|
+
end
|
84
|
+
|
85
|
+
it "should only replace phrase once" do
|
86
|
+
text.parse.should include("orange hippo")
|
87
|
+
text.parse.should_not include("purple kangaroo")
|
88
|
+
end
|
89
|
+
end
|
90
|
+
|
91
|
+
|
92
|
+
end
|
metadata
ADDED
@@ -0,0 +1,87 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: phrasify
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
version: 0.0.1
|
5
|
+
prerelease:
|
6
|
+
platform: ruby
|
7
|
+
authors:
|
8
|
+
- Robert Williams
|
9
|
+
autorequire:
|
10
|
+
bindir: bin
|
11
|
+
cert_chain: []
|
12
|
+
date: 2011-10-20 00:00:00.000000000 Z
|
13
|
+
dependencies:
|
14
|
+
- !ruby/object:Gem::Dependency
|
15
|
+
name: rspec
|
16
|
+
requirement: &70274532775880 !ruby/object:Gem::Requirement
|
17
|
+
none: false
|
18
|
+
requirements:
|
19
|
+
- - ~>
|
20
|
+
- !ruby/object:Gem::Version
|
21
|
+
version: 2.6.0
|
22
|
+
type: :development
|
23
|
+
prerelease: false
|
24
|
+
version_requirements: *70274532775880
|
25
|
+
- !ruby/object:Gem::Dependency
|
26
|
+
name: yard
|
27
|
+
requirement: &70274532775400 !ruby/object:Gem::Requirement
|
28
|
+
none: false
|
29
|
+
requirements:
|
30
|
+
- - ! '>='
|
31
|
+
- !ruby/object:Gem::Version
|
32
|
+
version: '0'
|
33
|
+
type: :development
|
34
|
+
prerelease: false
|
35
|
+
version_requirements: *70274532775400
|
36
|
+
description: Match phrases in text and replace them efficiently across thousands of
|
37
|
+
different terms.
|
38
|
+
email:
|
39
|
+
- rob@r-williams.com
|
40
|
+
executables: []
|
41
|
+
extensions: []
|
42
|
+
extra_rdoc_files: []
|
43
|
+
files:
|
44
|
+
- .gitignore
|
45
|
+
- .rspec
|
46
|
+
- .rvmrc
|
47
|
+
- Gemfile
|
48
|
+
- Guardfile
|
49
|
+
- Rakefile
|
50
|
+
- lib/phrasify.rb
|
51
|
+
- lib/phrasify/common_words.rb
|
52
|
+
- lib/phrasify/phrase.rb
|
53
|
+
- lib/phrasify/text.rb
|
54
|
+
- lib/phrasify/version.rb
|
55
|
+
- phrasify.gemspec
|
56
|
+
- spec/phrasify_spec.rb
|
57
|
+
- spec/spec_helper.rb
|
58
|
+
- spec/text_spec.rb
|
59
|
+
homepage: ''
|
60
|
+
licenses: []
|
61
|
+
post_install_message:
|
62
|
+
rdoc_options: []
|
63
|
+
require_paths:
|
64
|
+
- lib
|
65
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
66
|
+
none: false
|
67
|
+
requirements:
|
68
|
+
- - ! '>='
|
69
|
+
- !ruby/object:Gem::Version
|
70
|
+
version: '0'
|
71
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
72
|
+
none: false
|
73
|
+
requirements:
|
74
|
+
- - ! '>='
|
75
|
+
- !ruby/object:Gem::Version
|
76
|
+
version: '0'
|
77
|
+
requirements: []
|
78
|
+
rubyforge_project: phrasify
|
79
|
+
rubygems_version: 1.8.6
|
80
|
+
signing_key:
|
81
|
+
specification_version: 3
|
82
|
+
summary: Match phrases in text and replace them
|
83
|
+
test_files:
|
84
|
+
- spec/phrasify_spec.rb
|
85
|
+
- spec/spec_helper.rb
|
86
|
+
- spec/text_spec.rb
|
87
|
+
has_rdoc:
|