| 1 | #!/usr/bin/env python3
|
|---|
| 2 |
|
|---|
| 3 | stopwords = """'ll
|
|---|
| 4 | 'tis
|
|---|
| 5 | 'twas
|
|---|
| 6 | 've
|
|---|
| 7 | 10
|
|---|
| 8 | 39
|
|---|
| 9 | a
|
|---|
| 10 | a's
|
|---|
| 11 | able
|
|---|
| 12 | ableabout
|
|---|
| 13 | about
|
|---|
| 14 | above
|
|---|
| 15 | abroad
|
|---|
| 16 | abst
|
|---|
| 17 | accordance
|
|---|
| 18 | according
|
|---|
| 19 | accordingly
|
|---|
| 20 | across
|
|---|
| 21 | act
|
|---|
| 22 | actually
|
|---|
| 23 | ad
|
|---|
| 24 | added
|
|---|
| 25 | adj
|
|---|
| 26 | adopted
|
|---|
| 27 | ae
|
|---|
| 28 | af
|
|---|
| 29 | affected
|
|---|
| 30 | affecting
|
|---|
| 31 | affects
|
|---|
| 32 | after
|
|---|
| 33 | afterwards
|
|---|
| 34 | ag
|
|---|
| 35 | again
|
|---|
| 36 | against
|
|---|
| 37 | ago
|
|---|
| 38 | ah
|
|---|
| 39 | ahead
|
|---|
| 40 | ai
|
|---|
| 41 | ain't
|
|---|
| 42 | aint
|
|---|
| 43 | al
|
|---|
| 44 | all
|
|---|
| 45 | allow
|
|---|
| 46 | allows
|
|---|
| 47 | almost
|
|---|
| 48 | alone
|
|---|
| 49 | along
|
|---|
| 50 | alongside
|
|---|
| 51 | already
|
|---|
| 52 | also
|
|---|
| 53 | although
|
|---|
| 54 | always
|
|---|
| 55 | am
|
|---|
| 56 | amid
|
|---|
| 57 | amidst
|
|---|
| 58 | among
|
|---|
| 59 | amongst
|
|---|
| 60 | amoungst
|
|---|
| 61 | amount
|
|---|
| 62 | an
|
|---|
| 63 | and
|
|---|
| 64 | announce
|
|---|
| 65 | another
|
|---|
| 66 | any
|
|---|
| 67 | anybody
|
|---|
| 68 | anyhow
|
|---|
| 69 | anymore
|
|---|
| 70 | anyone
|
|---|
| 71 | anything
|
|---|
| 72 | anyway
|
|---|
| 73 | anyways
|
|---|
| 74 | anywhere
|
|---|
| 75 | ao
|
|---|
| 76 | apart
|
|---|
| 77 | apparently
|
|---|
| 78 | appear
|
|---|
| 79 | appreciate
|
|---|
| 80 | appropriate
|
|---|
| 81 | approximately
|
|---|
| 82 | aq
|
|---|
| 83 | ar
|
|---|
| 84 | are
|
|---|
| 85 | area
|
|---|
| 86 | areas
|
|---|
| 87 | aren
|
|---|
| 88 | aren't
|
|---|
| 89 | arent
|
|---|
| 90 | arise
|
|---|
| 91 | around
|
|---|
| 92 | arpa
|
|---|
| 93 | as
|
|---|
| 94 | aside
|
|---|
| 95 | ask
|
|---|
| 96 | asked
|
|---|
| 97 | asking
|
|---|
| 98 | asks
|
|---|
| 99 | associated
|
|---|
| 100 | at
|
|---|
| 101 | au
|
|---|
| 102 | auth
|
|---|
| 103 | available
|
|---|
| 104 | aw
|
|---|
| 105 | away
|
|---|
| 106 | awfully
|
|---|
| 107 | az
|
|---|
| 108 | b
|
|---|
| 109 | ba
|
|---|
| 110 | back
|
|---|
| 111 | backed
|
|---|
| 112 | backing
|
|---|
| 113 | backs
|
|---|
| 114 | backward
|
|---|
| 115 | backwards
|
|---|
| 116 | bb
|
|---|
| 117 | bd
|
|---|
| 118 | be
|
|---|
| 119 | became
|
|---|
| 120 | because
|
|---|
| 121 | become
|
|---|
| 122 | becomes
|
|---|
| 123 | becoming
|
|---|
| 124 | been
|
|---|
| 125 | before
|
|---|
| 126 | beforehand
|
|---|
| 127 | began
|
|---|
| 128 | begin
|
|---|
| 129 | beginning
|
|---|
| 130 | beginnings
|
|---|
| 131 | begins
|
|---|
| 132 | behind
|
|---|
| 133 | being
|
|---|
| 134 | beings
|
|---|
| 135 | believe
|
|---|
| 136 | below
|
|---|
| 137 | beside
|
|---|
| 138 | besides
|
|---|
| 139 | best
|
|---|
| 140 | better
|
|---|
| 141 | between
|
|---|
| 142 | beyond
|
|---|
| 143 | bf
|
|---|
| 144 | bg
|
|---|
| 145 | bh
|
|---|
| 146 | bi
|
|---|
| 147 | big
|
|---|
| 148 | bill
|
|---|
| 149 | billion
|
|---|
| 150 | biol
|
|---|
| 151 | bj
|
|---|
| 152 | bm
|
|---|
| 153 | bn
|
|---|
| 154 | bo
|
|---|
| 155 | both
|
|---|
| 156 | bottom
|
|---|
| 157 | br
|
|---|
| 158 | brief
|
|---|
| 159 | briefly
|
|---|
| 160 | bs
|
|---|
| 161 | bt
|
|---|
| 162 | but
|
|---|
| 163 | buy
|
|---|
| 164 | bv
|
|---|
| 165 | bw
|
|---|
| 166 | by
|
|---|
| 167 | bz
|
|---|
| 168 | c
|
|---|
| 169 | c'mon
|
|---|
| 170 | c's
|
|---|
| 171 | ca
|
|---|
| 172 | call
|
|---|
| 173 | came
|
|---|
| 174 | can
|
|---|
| 175 | can't
|
|---|
| 176 | cannot
|
|---|
| 177 | cant
|
|---|
| 178 | caption
|
|---|
| 179 | case
|
|---|
| 180 | cases
|
|---|
| 181 | cause
|
|---|
| 182 | causes
|
|---|
| 183 | cc
|
|---|
| 184 | cd
|
|---|
| 185 | certain
|
|---|
| 186 | certainly
|
|---|
| 187 | cf
|
|---|
| 188 | cg
|
|---|
| 189 | ch
|
|---|
| 190 | changes
|
|---|
| 191 | ci
|
|---|
| 192 | ck
|
|---|
| 193 | cl
|
|---|
| 194 | clear
|
|---|
| 195 | clearly
|
|---|
| 196 | click
|
|---|
| 197 | cm
|
|---|
| 198 | cmon
|
|---|
| 199 | cn
|
|---|
| 200 | co
|
|---|
| 201 | co.
|
|---|
| 202 | com
|
|---|
| 203 | come
|
|---|
| 204 | comes
|
|---|
| 205 | computer
|
|---|
| 206 | con
|
|---|
| 207 | concerning
|
|---|
| 208 | consequently
|
|---|
| 209 | consider
|
|---|
| 210 | considering
|
|---|
| 211 | contain
|
|---|
| 212 | containing
|
|---|
| 213 | contains
|
|---|
| 214 | copy
|
|---|
| 215 | corresponding
|
|---|
| 216 | could
|
|---|
| 217 | could've
|
|---|
| 218 | couldn
|
|---|
| 219 | couldn't
|
|---|
| 220 | couldnt
|
|---|
| 221 | course
|
|---|
| 222 | cr
|
|---|
| 223 | cry
|
|---|
| 224 | cs
|
|---|
| 225 | cu
|
|---|
| 226 | currently
|
|---|
| 227 | cv
|
|---|
| 228 | cx
|
|---|
| 229 | cy
|
|---|
| 230 | cz
|
|---|
| 231 | d
|
|---|
| 232 | dare
|
|---|
| 233 | daren't
|
|---|
| 234 | darent
|
|---|
| 235 | date
|
|---|
| 236 | de
|
|---|
| 237 | dear
|
|---|
| 238 | definitely
|
|---|
| 239 | describe
|
|---|
| 240 | described
|
|---|
| 241 | despite
|
|---|
| 242 | detail
|
|---|
| 243 | did
|
|---|
| 244 | didn
|
|---|
| 245 | didn't
|
|---|
| 246 | didnt
|
|---|
| 247 | differ
|
|---|
| 248 | different
|
|---|
| 249 | differently
|
|---|
| 250 | directly
|
|---|
| 251 | dj
|
|---|
| 252 | dk
|
|---|
| 253 | dm
|
|---|
| 254 | do
|
|---|
| 255 | does
|
|---|
| 256 | doesn
|
|---|
| 257 | doesn't
|
|---|
| 258 | doesnt
|
|---|
| 259 | doing
|
|---|
| 260 | don
|
|---|
| 261 | don't
|
|---|
| 262 | done
|
|---|
| 263 | dont
|
|---|
| 264 | doubtful
|
|---|
| 265 | down
|
|---|
| 266 | downed
|
|---|
| 267 | downing
|
|---|
| 268 | downs
|
|---|
| 269 | downwards
|
|---|
| 270 | due
|
|---|
| 271 | during
|
|---|
| 272 | dz
|
|---|
| 273 | e
|
|---|
| 274 | each
|
|---|
| 275 | early
|
|---|
| 276 | ec
|
|---|
| 277 | ed
|
|---|
| 278 | edu
|
|---|
| 279 | ee
|
|---|
| 280 | effect
|
|---|
| 281 | eg
|
|---|
| 282 | eh
|
|---|
| 283 | eight
|
|---|
| 284 | eighty
|
|---|
| 285 | either
|
|---|
| 286 | eleven
|
|---|
| 287 | else
|
|---|
| 288 | elsewhere
|
|---|
| 289 | empty
|
|---|
| 290 | end
|
|---|
| 291 | ended
|
|---|
| 292 | ending
|
|---|
| 293 | ends
|
|---|
| 294 | enough
|
|---|
| 295 | entirely
|
|---|
| 296 | er
|
|---|
| 297 | es
|
|---|
| 298 | especially
|
|---|
| 299 | et
|
|---|
| 300 | et-al
|
|---|
| 301 | etc
|
|---|
| 302 | even
|
|---|
| 303 | evenly
|
|---|
| 304 | ever
|
|---|
| 305 | evermore
|
|---|
| 306 | every
|
|---|
| 307 | everybody
|
|---|
| 308 | everyone
|
|---|
| 309 | everything
|
|---|
| 310 | everywhere
|
|---|
| 311 | ex
|
|---|
| 312 | exactly
|
|---|
| 313 | example
|
|---|
| 314 | except
|
|---|
| 315 | f
|
|---|
| 316 | face
|
|---|
| 317 | faces
|
|---|
| 318 | fact
|
|---|
| 319 | facts
|
|---|
| 320 | fairly
|
|---|
| 321 | far
|
|---|
| 322 | farther
|
|---|
| 323 | felt
|
|---|
| 324 | few
|
|---|
| 325 | fewer
|
|---|
| 326 | ff
|
|---|
| 327 | fi
|
|---|
| 328 | fifteen
|
|---|
| 329 | fifth
|
|---|
| 330 | fifty
|
|---|
| 331 | fify
|
|---|
| 332 | fill
|
|---|
| 333 | find
|
|---|
| 334 | finds
|
|---|
| 335 | fire
|
|---|
| 336 | first
|
|---|
| 337 | five
|
|---|
| 338 | fix
|
|---|
| 339 | fj
|
|---|
| 340 | fk
|
|---|
| 341 | fm
|
|---|
| 342 | fo
|
|---|
| 343 | followed
|
|---|
| 344 | following
|
|---|
| 345 | follows
|
|---|
| 346 | for
|
|---|
| 347 | forever
|
|---|
| 348 | former
|
|---|
| 349 | formerly
|
|---|
| 350 | forth
|
|---|
| 351 | forty
|
|---|
| 352 | forward
|
|---|
| 353 | found
|
|---|
| 354 | four
|
|---|
| 355 | fr
|
|---|
| 356 | free
|
|---|
| 357 | from
|
|---|
| 358 | front
|
|---|
| 359 | full
|
|---|
| 360 | fully
|
|---|
| 361 | further
|
|---|
| 362 | furthered
|
|---|
| 363 | furthering
|
|---|
| 364 | furthermore
|
|---|
| 365 | furthers
|
|---|
| 366 | fx
|
|---|
| 367 | g
|
|---|
| 368 | ga
|
|---|
| 369 | gave
|
|---|
| 370 | gb
|
|---|
| 371 | gd
|
|---|
| 372 | ge
|
|---|
| 373 | general
|
|---|
| 374 | generally
|
|---|
| 375 | get
|
|---|
| 376 | gets
|
|---|
| 377 | getting
|
|---|
| 378 | gf
|
|---|
| 379 | gg
|
|---|
| 380 | gh
|
|---|
| 381 | gi
|
|---|
| 382 | give
|
|---|
| 383 | given
|
|---|
| 384 | gives
|
|---|
| 385 | giving
|
|---|
| 386 | gl
|
|---|
| 387 | gm
|
|---|
| 388 | gmt
|
|---|
| 389 | gn
|
|---|
| 390 | go
|
|---|
| 391 | goes
|
|---|
| 392 | going
|
|---|
| 393 | gone
|
|---|
| 394 | good
|
|---|
| 395 | goods
|
|---|
| 396 | got
|
|---|
| 397 | gotten
|
|---|
| 398 | gov
|
|---|
| 399 | gp
|
|---|
| 400 | gq
|
|---|
| 401 | gr
|
|---|
| 402 | great
|
|---|
| 403 | greater
|
|---|
| 404 | greatest
|
|---|
| 405 | greetings
|
|---|
| 406 | group
|
|---|
| 407 | grouped
|
|---|
| 408 | grouping
|
|---|
| 409 | groups
|
|---|
| 410 | gs
|
|---|
| 411 | gt
|
|---|
| 412 | gu
|
|---|
| 413 | gw
|
|---|
| 414 | gy
|
|---|
| 415 | h
|
|---|
| 416 | had
|
|---|
| 417 | hadn't
|
|---|
| 418 | hadnt
|
|---|
| 419 | half
|
|---|
| 420 | happens
|
|---|
| 421 | hardly
|
|---|
| 422 | has
|
|---|
| 423 | hasn
|
|---|
| 424 | hasn't
|
|---|
| 425 | hasnt
|
|---|
| 426 | have
|
|---|
| 427 | haven
|
|---|
| 428 | haven't
|
|---|
| 429 | havent
|
|---|
| 430 | having
|
|---|
| 431 | he
|
|---|
| 432 | he'd
|
|---|
| 433 | he'll
|
|---|
| 434 | he's
|
|---|
| 435 | hed
|
|---|
| 436 | hell
|
|---|
| 437 | hello
|
|---|
| 438 | help
|
|---|
| 439 | hence
|
|---|
| 440 | her
|
|---|
| 441 | here
|
|---|
| 442 | here's
|
|---|
| 443 | hereafter
|
|---|
| 444 | hereby
|
|---|
| 445 | herein
|
|---|
| 446 | heres
|
|---|
| 447 | hereupon
|
|---|
| 448 | hers
|
|---|
| 449 | herself
|
|---|
| 450 | herse”
|
|---|
| 451 | hes
|
|---|
| 452 | hi
|
|---|
| 453 | hid
|
|---|
| 454 | high
|
|---|
| 455 | higher
|
|---|
| 456 | highest
|
|---|
| 457 | him
|
|---|
| 458 | himself
|
|---|
| 459 | himse”
|
|---|
| 460 | his
|
|---|
| 461 | hither
|
|---|
| 462 | hk
|
|---|
| 463 | hm
|
|---|
| 464 | hn
|
|---|
| 465 | home
|
|---|
| 466 | homepage
|
|---|
| 467 | hopefully
|
|---|
| 468 | how
|
|---|
| 469 | how'd
|
|---|
| 470 | how'll
|
|---|
| 471 | how's
|
|---|
| 472 | howbeit
|
|---|
| 473 | however
|
|---|
| 474 | hr
|
|---|
| 475 | ht
|
|---|
| 476 | htm
|
|---|
| 477 | html
|
|---|
| 478 | http
|
|---|
| 479 | hu
|
|---|
| 480 | hundred
|
|---|
| 481 | i
|
|---|
| 482 | i'd
|
|---|
| 483 | i'll
|
|---|
| 484 | i'm
|
|---|
| 485 | i've
|
|---|
| 486 | i.e.
|
|---|
| 487 | id
|
|---|
| 488 | ie
|
|---|
| 489 | if
|
|---|
| 490 | ignored
|
|---|
| 491 | ii
|
|---|
| 492 | il
|
|---|
| 493 | ill
|
|---|
| 494 | im
|
|---|
| 495 | immediate
|
|---|
| 496 | immediately
|
|---|
| 497 | importance
|
|---|
| 498 | important
|
|---|
| 499 | in
|
|---|
| 500 | inasmuch
|
|---|
| 501 | inc
|
|---|
| 502 | inc.
|
|---|
| 503 | indeed
|
|---|
| 504 | index
|
|---|
| 505 | indicate
|
|---|
| 506 | indicated
|
|---|
| 507 | indicates
|
|---|
| 508 | information
|
|---|
| 509 | inner
|
|---|
| 510 | inside
|
|---|
| 511 | insofar
|
|---|
| 512 | instead
|
|---|
| 513 | int
|
|---|
| 514 | interest
|
|---|
| 515 | interested
|
|---|
| 516 | interesting
|
|---|
| 517 | interests
|
|---|
| 518 | into
|
|---|
| 519 | invention
|
|---|
| 520 | inward
|
|---|
| 521 | io
|
|---|
| 522 | iq
|
|---|
| 523 | ir
|
|---|
| 524 | is
|
|---|
| 525 | isn
|
|---|
| 526 | isn't
|
|---|
| 527 | isnt
|
|---|
| 528 | it
|
|---|
| 529 | it'd
|
|---|
| 530 | it'll
|
|---|
| 531 | it's
|
|---|
| 532 | itd
|
|---|
| 533 | itll
|
|---|
| 534 | its
|
|---|
| 535 | itself
|
|---|
| 536 | itse”
|
|---|
| 537 | ive
|
|---|
| 538 | j
|
|---|
| 539 | je
|
|---|
| 540 | jm
|
|---|
| 541 | jo
|
|---|
| 542 | join
|
|---|
| 543 | jp
|
|---|
| 544 | just
|
|---|
| 545 | k
|
|---|
| 546 | ke
|
|---|
| 547 | keep
|
|---|
| 548 | keeps
|
|---|
| 549 | kept
|
|---|
| 550 | keys
|
|---|
| 551 | kg
|
|---|
| 552 | kh
|
|---|
| 553 | ki
|
|---|
| 554 | kind
|
|---|
| 555 | km
|
|---|
| 556 | kn
|
|---|
| 557 | knew
|
|---|
| 558 | know
|
|---|
| 559 | known
|
|---|
| 560 | knows
|
|---|
| 561 | kp
|
|---|
| 562 | kr
|
|---|
| 563 | kw
|
|---|
| 564 | ky
|
|---|
| 565 | kz
|
|---|
| 566 | l
|
|---|
| 567 | la
|
|---|
| 568 | large
|
|---|
| 569 | largely
|
|---|
| 570 | last
|
|---|
| 571 | lately
|
|---|
| 572 | later
|
|---|
| 573 | latest
|
|---|
| 574 | latter
|
|---|
| 575 | latterly
|
|---|
| 576 | lb
|
|---|
| 577 | lc
|
|---|
| 578 | least
|
|---|
| 579 | length
|
|---|
| 580 | less
|
|---|
| 581 | lest
|
|---|
| 582 | let
|
|---|
| 583 | let's
|
|---|
| 584 | lets
|
|---|
| 585 | li
|
|---|
| 586 | like
|
|---|
| 587 | liked
|
|---|
| 588 | likely
|
|---|
| 589 | likewise
|
|---|
| 590 | line
|
|---|
| 591 | little
|
|---|
| 592 | lk
|
|---|
| 593 | ll
|
|---|
| 594 | long
|
|---|
| 595 | longer
|
|---|
| 596 | longest
|
|---|
| 597 | look
|
|---|
| 598 | looking
|
|---|
| 599 | looks
|
|---|
| 600 | low
|
|---|
| 601 | lower
|
|---|
| 602 | lr
|
|---|
| 603 | ls
|
|---|
| 604 | lt
|
|---|
| 605 | ltd
|
|---|
| 606 | lu
|
|---|
| 607 | lv
|
|---|
| 608 | ly
|
|---|
| 609 | m
|
|---|
| 610 | ma
|
|---|
| 611 | made
|
|---|
| 612 | mainly
|
|---|
| 613 | make
|
|---|
| 614 | makes
|
|---|
| 615 | making
|
|---|
| 616 | man
|
|---|
| 617 | many
|
|---|
| 618 | may
|
|---|
| 619 | maybe
|
|---|
| 620 | mayn't
|
|---|
| 621 | maynt
|
|---|
| 622 | mc
|
|---|
| 623 | md
|
|---|
| 624 | me
|
|---|
| 625 | mean
|
|---|
| 626 | means
|
|---|
| 627 | meantime
|
|---|
| 628 | meanwhile
|
|---|
| 629 | member
|
|---|
| 630 | members
|
|---|
| 631 | men
|
|---|
| 632 | merely
|
|---|
| 633 | mg
|
|---|
| 634 | mh
|
|---|
| 635 | microsoft
|
|---|
| 636 | might
|
|---|
| 637 | might've
|
|---|
| 638 | mightn't
|
|---|
| 639 | mightnt
|
|---|
| 640 | mil
|
|---|
| 641 | mill
|
|---|
| 642 | million
|
|---|
| 643 | mine
|
|---|
| 644 | minus
|
|---|
| 645 | miss
|
|---|
| 646 | mk
|
|---|
| 647 | ml
|
|---|
| 648 | mm
|
|---|
| 649 | mn
|
|---|
| 650 | mo
|
|---|
| 651 | more
|
|---|
| 652 | moreover
|
|---|
| 653 | most
|
|---|
| 654 | mostly
|
|---|
| 655 | move
|
|---|
| 656 | mp
|
|---|
| 657 | mq
|
|---|
| 658 | mr
|
|---|
| 659 | mrs
|
|---|
| 660 | ms
|
|---|
| 661 | msie
|
|---|
| 662 | mt
|
|---|
| 663 | mu
|
|---|
| 664 | much
|
|---|
| 665 | mug
|
|---|
| 666 | must
|
|---|
| 667 | must've
|
|---|
| 668 | mustn't
|
|---|
| 669 | mustnt
|
|---|
| 670 | mv
|
|---|
| 671 | mw
|
|---|
| 672 | mx
|
|---|
| 673 | my
|
|---|
| 674 | myself
|
|---|
| 675 | myse”
|
|---|
| 676 | mz
|
|---|
| 677 | n
|
|---|
| 678 | na
|
|---|
| 679 | name
|
|---|
| 680 | namely
|
|---|
| 681 | nay
|
|---|
| 682 | nc
|
|---|
| 683 | nd
|
|---|
| 684 | ne
|
|---|
| 685 | near
|
|---|
| 686 | nearly
|
|---|
| 687 | necessarily
|
|---|
| 688 | necessary
|
|---|
| 689 | need
|
|---|
| 690 | needed
|
|---|
| 691 | needing
|
|---|
| 692 | needn't
|
|---|
| 693 | neednt
|
|---|
| 694 | needs
|
|---|
| 695 | neither
|
|---|
| 696 | net
|
|---|
| 697 | netscape
|
|---|
| 698 | never
|
|---|
| 699 | neverf
|
|---|
| 700 | neverless
|
|---|
| 701 | nevertheless
|
|---|
| 702 | new
|
|---|
| 703 | newer
|
|---|
| 704 | newest
|
|---|
| 705 | next
|
|---|
| 706 | nf
|
|---|
| 707 | ng
|
|---|
| 708 | ni
|
|---|
| 709 | nine
|
|---|
| 710 | ninety
|
|---|
| 711 | nl
|
|---|
| 712 | no
|
|---|
| 713 | no-one
|
|---|
| 714 | nobody
|
|---|
| 715 | non
|
|---|
| 716 | none
|
|---|
| 717 | nonetheless
|
|---|
| 718 | noone
|
|---|
| 719 | nor
|
|---|
| 720 | normally
|
|---|
| 721 | nos
|
|---|
| 722 | not
|
|---|
| 723 | noted
|
|---|
| 724 | nothing
|
|---|
| 725 | notwithstanding
|
|---|
| 726 | novel
|
|---|
| 727 | now
|
|---|
| 728 | nowhere
|
|---|
| 729 | np
|
|---|
| 730 | nr
|
|---|
| 731 | nu
|
|---|
| 732 | null
|
|---|
| 733 | number
|
|---|
| 734 | numbers
|
|---|
| 735 | nz
|
|---|
| 736 | o
|
|---|
| 737 | obtain
|
|---|
| 738 | obtained
|
|---|
| 739 | obviously
|
|---|
| 740 | of
|
|---|
| 741 | off
|
|---|
| 742 | often
|
|---|
| 743 | oh
|
|---|
| 744 | ok
|
|---|
| 745 | okay
|
|---|
| 746 | old
|
|---|
| 747 | older
|
|---|
| 748 | oldest
|
|---|
| 749 | om
|
|---|
| 750 | omitted
|
|---|
| 751 | on
|
|---|
| 752 | once
|
|---|
| 753 | one
|
|---|
| 754 | one's
|
|---|
| 755 | ones
|
|---|
| 756 | only
|
|---|
| 757 | onto
|
|---|
| 758 | open
|
|---|
| 759 | opened
|
|---|
| 760 | opening
|
|---|
| 761 | opens
|
|---|
| 762 | opposite
|
|---|
| 763 | or
|
|---|
| 764 | ord
|
|---|
| 765 | order
|
|---|
| 766 | ordered
|
|---|
| 767 | ordering
|
|---|
| 768 | orders
|
|---|
| 769 | org
|
|---|
| 770 | other
|
|---|
| 771 | others
|
|---|
| 772 | otherwise
|
|---|
| 773 | ought
|
|---|
| 774 | oughtn't
|
|---|
| 775 | oughtnt
|
|---|
| 776 | our
|
|---|
| 777 | ours
|
|---|
| 778 | ourselves
|
|---|
| 779 | out
|
|---|
| 780 | outside
|
|---|
| 781 | over
|
|---|
| 782 | overall
|
|---|
| 783 | owing
|
|---|
| 784 | own
|
|---|
| 785 | p
|
|---|
| 786 | pa
|
|---|
| 787 | page
|
|---|
| 788 | pages
|
|---|
| 789 | part
|
|---|
| 790 | parted
|
|---|
| 791 | particular
|
|---|
| 792 | particularly
|
|---|
| 793 | parting
|
|---|
| 794 | parts
|
|---|
| 795 | past
|
|---|
| 796 | pe
|
|---|
| 797 | per
|
|---|
| 798 | perhaps
|
|---|
| 799 | pf
|
|---|
| 800 | pg
|
|---|
| 801 | ph
|
|---|
| 802 | pk
|
|---|
| 803 | pl
|
|---|
| 804 | place
|
|---|
| 805 | placed
|
|---|
| 806 | places
|
|---|
| 807 | please
|
|---|
| 808 | plus
|
|---|
| 809 | pm
|
|---|
| 810 | pmid
|
|---|
| 811 | pn
|
|---|
| 812 | point
|
|---|
| 813 | pointed
|
|---|
| 814 | pointing
|
|---|
| 815 | points
|
|---|
| 816 | poorly
|
|---|
| 817 | possible
|
|---|
| 818 | possibly
|
|---|
| 819 | potentially
|
|---|
| 820 | pp
|
|---|
| 821 | pr
|
|---|
| 822 | predominantly
|
|---|
| 823 | present
|
|---|
| 824 | presented
|
|---|
| 825 | presenting
|
|---|
| 826 | presents
|
|---|
| 827 | presumably
|
|---|
| 828 | previously
|
|---|
| 829 | primarily
|
|---|
| 830 | probably
|
|---|
| 831 | problem
|
|---|
| 832 | problems
|
|---|
| 833 | promptly
|
|---|
| 834 | proud
|
|---|
| 835 | provided
|
|---|
| 836 | provides
|
|---|
| 837 | pt
|
|---|
| 838 | put
|
|---|
| 839 | puts
|
|---|
| 840 | pw
|
|---|
| 841 | py
|
|---|
| 842 | q
|
|---|
| 843 | qa
|
|---|
| 844 | que
|
|---|
| 845 | quickly
|
|---|
| 846 | quite
|
|---|
| 847 | qv
|
|---|
| 848 | r
|
|---|
| 849 | ran
|
|---|
| 850 | rather
|
|---|
| 851 | rd
|
|---|
| 852 | re
|
|---|
| 853 | readily
|
|---|
| 854 | really
|
|---|
| 855 | reasonably
|
|---|
| 856 | recent
|
|---|
| 857 | recently
|
|---|
| 858 | ref
|
|---|
| 859 | refs
|
|---|
| 860 | regarding
|
|---|
| 861 | regardless
|
|---|
| 862 | regards
|
|---|
| 863 | related
|
|---|
| 864 | relatively
|
|---|
| 865 | research
|
|---|
| 866 | reserved
|
|---|
| 867 | respectively
|
|---|
| 868 | resulted
|
|---|
| 869 | resulting
|
|---|
| 870 | results
|
|---|
| 871 | right
|
|---|
| 872 | ring
|
|---|
| 873 | ro
|
|---|
| 874 | room
|
|---|
| 875 | rooms
|
|---|
| 876 | round
|
|---|
| 877 | ru
|
|---|
| 878 | run
|
|---|
| 879 | rw
|
|---|
| 880 | s
|
|---|
| 881 | sa
|
|---|
| 882 | said
|
|---|
| 883 | same
|
|---|
| 884 | saw
|
|---|
| 885 | say
|
|---|
| 886 | saying
|
|---|
| 887 | says
|
|---|
| 888 | sb
|
|---|
| 889 | sc
|
|---|
| 890 | sd
|
|---|
| 891 | se
|
|---|
| 892 | sec
|
|---|
| 893 | second
|
|---|
| 894 | secondly
|
|---|
| 895 | seconds
|
|---|
| 896 | section
|
|---|
| 897 | see
|
|---|
| 898 | seeing
|
|---|
| 899 | seem
|
|---|
| 900 | seemed
|
|---|
| 901 | seeming
|
|---|
| 902 | seems
|
|---|
| 903 | seen
|
|---|
| 904 | sees
|
|---|
| 905 | self
|
|---|
| 906 | selves
|
|---|
| 907 | sensible
|
|---|
| 908 | sent
|
|---|
| 909 | serious
|
|---|
| 910 | seriously
|
|---|
| 911 | seven
|
|---|
| 912 | seventy
|
|---|
| 913 | several
|
|---|
| 914 | sg
|
|---|
| 915 | sh
|
|---|
| 916 | shall
|
|---|
| 917 | shan't
|
|---|
| 918 | shant
|
|---|
| 919 | she
|
|---|
| 920 | she'd
|
|---|
| 921 | she'll
|
|---|
| 922 | she's
|
|---|
| 923 | shed
|
|---|
| 924 | shell
|
|---|
| 925 | shes
|
|---|
| 926 | should
|
|---|
| 927 | should've
|
|---|
| 928 | shouldn
|
|---|
| 929 | shouldn't
|
|---|
| 930 | shouldnt
|
|---|
| 931 | show
|
|---|
| 932 | showed
|
|---|
| 933 | showing
|
|---|
| 934 | shown
|
|---|
| 935 | showns
|
|---|
| 936 | shows
|
|---|
| 937 | si
|
|---|
| 938 | side
|
|---|
| 939 | sides
|
|---|
| 940 | significant
|
|---|
| 941 | significantly
|
|---|
| 942 | similar
|
|---|
| 943 | similarly
|
|---|
| 944 | since
|
|---|
| 945 | sincere
|
|---|
| 946 | site
|
|---|
| 947 | six
|
|---|
| 948 | sixty
|
|---|
| 949 | sj
|
|---|
| 950 | sk
|
|---|
| 951 | sl
|
|---|
| 952 | slightly
|
|---|
| 953 | sm
|
|---|
| 954 | small
|
|---|
| 955 | smaller
|
|---|
| 956 | smallest
|
|---|
| 957 | sn
|
|---|
| 958 | so
|
|---|
| 959 | some
|
|---|
| 960 | somebody
|
|---|
| 961 | someday
|
|---|
| 962 | somehow
|
|---|
| 963 | someone
|
|---|
| 964 | somethan
|
|---|
| 965 | something
|
|---|
| 966 | sometime
|
|---|
| 967 | sometimes
|
|---|
| 968 | somewhat
|
|---|
| 969 | somewhere
|
|---|
| 970 | soon
|
|---|
| 971 | sorry
|
|---|
| 972 | specifically
|
|---|
| 973 | specified
|
|---|
| 974 | specify
|
|---|
| 975 | specifying
|
|---|
| 976 | sr
|
|---|
| 977 | st
|
|---|
| 978 | state
|
|---|
| 979 | states
|
|---|
| 980 | still
|
|---|
| 981 | stop
|
|---|
| 982 | strongly
|
|---|
| 983 | su
|
|---|
| 984 | sub
|
|---|
| 985 | substantially
|
|---|
| 986 | successfully
|
|---|
| 987 | such
|
|---|
| 988 | sufficiently
|
|---|
| 989 | suggest
|
|---|
| 990 | sup
|
|---|
| 991 | sure
|
|---|
| 992 | sv
|
|---|
| 993 | sy
|
|---|
| 994 | system
|
|---|
| 995 | sz
|
|---|
| 996 | t
|
|---|
| 997 | t's
|
|---|
| 998 | take
|
|---|
| 999 | taken
|
|---|
| 1000 | taking
|
|---|
| 1001 | tc
|
|---|
| 1002 | td
|
|---|
| 1003 | tell
|
|---|
| 1004 | ten
|
|---|
| 1005 | tends
|
|---|
| 1006 | test
|
|---|
| 1007 | text
|
|---|
| 1008 | tf
|
|---|
| 1009 | tg
|
|---|
| 1010 | th
|
|---|
| 1011 | than
|
|---|
| 1012 | thank
|
|---|
| 1013 | thanks
|
|---|
| 1014 | thanx
|
|---|
| 1015 | that
|
|---|
| 1016 | that'll
|
|---|
| 1017 | that's
|
|---|
| 1018 | that've
|
|---|
| 1019 | thatll
|
|---|
| 1020 | thats
|
|---|
| 1021 | thatve
|
|---|
| 1022 | the
|
|---|
| 1023 | their
|
|---|
| 1024 | theirs
|
|---|
| 1025 | them
|
|---|
| 1026 | themselves
|
|---|
| 1027 | then
|
|---|
| 1028 | thence
|
|---|
| 1029 | there
|
|---|
| 1030 | there'd
|
|---|
| 1031 | there'll
|
|---|
| 1032 | there're
|
|---|
| 1033 | there's
|
|---|
| 1034 | there've
|
|---|
| 1035 | thereafter
|
|---|
| 1036 | thereby
|
|---|
| 1037 | thered
|
|---|
| 1038 | therefore
|
|---|
| 1039 | therein
|
|---|
| 1040 | therell
|
|---|
| 1041 | thereof
|
|---|
| 1042 | therere
|
|---|
| 1043 | theres
|
|---|
| 1044 | thereto
|
|---|
| 1045 | thereupon
|
|---|
| 1046 | thereve
|
|---|
| 1047 | these
|
|---|
| 1048 | they
|
|---|
| 1049 | they'd
|
|---|
| 1050 | they'll
|
|---|
| 1051 | they're
|
|---|
| 1052 | they've
|
|---|
| 1053 | theyd
|
|---|
| 1054 | theyll
|
|---|
| 1055 | theyre
|
|---|
| 1056 | theyve
|
|---|
| 1057 | thick
|
|---|
| 1058 | thin
|
|---|
| 1059 | thing
|
|---|
| 1060 | things
|
|---|
| 1061 | think
|
|---|
| 1062 | thinks
|
|---|
| 1063 | third
|
|---|
| 1064 | thirty
|
|---|
| 1065 | this
|
|---|
| 1066 | thorough
|
|---|
| 1067 | thoroughly
|
|---|
| 1068 | those
|
|---|
| 1069 | thou
|
|---|
| 1070 | though
|
|---|
| 1071 | thoughh
|
|---|
| 1072 | thought
|
|---|
| 1073 | thoughts
|
|---|
| 1074 | thousand
|
|---|
| 1075 | three
|
|---|
| 1076 | throug
|
|---|
| 1077 | through
|
|---|
| 1078 | throughout
|
|---|
| 1079 | thru
|
|---|
| 1080 | thus
|
|---|
| 1081 | til
|
|---|
| 1082 | till
|
|---|
| 1083 | tip
|
|---|
| 1084 | tis
|
|---|
| 1085 | tj
|
|---|
| 1086 | tk
|
|---|
| 1087 | tm
|
|---|
| 1088 | tn
|
|---|
| 1089 | to
|
|---|
| 1090 | today
|
|---|
| 1091 | together
|
|---|
| 1092 | too
|
|---|
| 1093 | took
|
|---|
| 1094 | top
|
|---|
| 1095 | toward
|
|---|
| 1096 | towards
|
|---|
| 1097 | tp
|
|---|
| 1098 | tr
|
|---|
| 1099 | tried
|
|---|
| 1100 | tries
|
|---|
| 1101 | trillion
|
|---|
| 1102 | truly
|
|---|
| 1103 | try
|
|---|
| 1104 | trying
|
|---|
| 1105 | ts
|
|---|
| 1106 | tt
|
|---|
| 1107 | turn
|
|---|
| 1108 | turned
|
|---|
| 1109 | turning
|
|---|
| 1110 | turns
|
|---|
| 1111 | tv
|
|---|
| 1112 | tw
|
|---|
| 1113 | twas
|
|---|
| 1114 | twelve
|
|---|
| 1115 | twenty
|
|---|
| 1116 | twice
|
|---|
| 1117 | two
|
|---|
| 1118 | tz
|
|---|
| 1119 | u
|
|---|
| 1120 | ua
|
|---|
| 1121 | ug
|
|---|
| 1122 | uk
|
|---|
| 1123 | um
|
|---|
| 1124 | un
|
|---|
| 1125 | under
|
|---|
| 1126 | underneath
|
|---|
| 1127 | undoing
|
|---|
| 1128 | unfortunately
|
|---|
| 1129 | unless
|
|---|
| 1130 | unlike
|
|---|
| 1131 | unlikely
|
|---|
| 1132 | until
|
|---|
| 1133 | unto
|
|---|
| 1134 | up
|
|---|
| 1135 | upon
|
|---|
| 1136 | ups
|
|---|
| 1137 | upwards
|
|---|
| 1138 | us
|
|---|
| 1139 | use
|
|---|
| 1140 | used
|
|---|
| 1141 | useful
|
|---|
| 1142 | usefully
|
|---|
| 1143 | usefulness
|
|---|
| 1144 | uses
|
|---|
| 1145 | using
|
|---|
| 1146 | usually
|
|---|
| 1147 | uucp
|
|---|
| 1148 | uy
|
|---|
| 1149 | uz
|
|---|
| 1150 | v
|
|---|
| 1151 | va
|
|---|
| 1152 | value
|
|---|
| 1153 | various
|
|---|
| 1154 | vc
|
|---|
| 1155 | ve
|
|---|
| 1156 | versus
|
|---|
| 1157 | very
|
|---|
| 1158 | vg
|
|---|
| 1159 | vi
|
|---|
| 1160 | via
|
|---|
| 1161 | viz
|
|---|
| 1162 | vn
|
|---|
| 1163 | vol
|
|---|
| 1164 | vols
|
|---|
| 1165 | vs
|
|---|
| 1166 | vu
|
|---|
| 1167 | w
|
|---|
| 1168 | want
|
|---|
| 1169 | wanted
|
|---|
| 1170 | wanting
|
|---|
| 1171 | wants
|
|---|
| 1172 | was
|
|---|
| 1173 | wasn
|
|---|
| 1174 | wasn't
|
|---|
| 1175 | wasnt
|
|---|
| 1176 | way
|
|---|
| 1177 | ways
|
|---|
| 1178 | we
|
|---|
| 1179 | we'd
|
|---|
| 1180 | we'll
|
|---|
| 1181 | we're
|
|---|
| 1182 | we've
|
|---|
| 1183 | web
|
|---|
| 1184 | webpage
|
|---|
| 1185 | website
|
|---|
| 1186 | wed
|
|---|
| 1187 | welcome
|
|---|
| 1188 | well
|
|---|
| 1189 | wells
|
|---|
| 1190 | went
|
|---|
| 1191 | were
|
|---|
| 1192 | weren
|
|---|
| 1193 | weren't
|
|---|
| 1194 | werent
|
|---|
| 1195 | weve
|
|---|
| 1196 | wf
|
|---|
| 1197 | what
|
|---|
| 1198 | what'd
|
|---|
| 1199 | what'll
|
|---|
| 1200 | what's
|
|---|
| 1201 | what've
|
|---|
| 1202 | whatever
|
|---|
| 1203 | whatll
|
|---|
| 1204 | whats
|
|---|
| 1205 | whatve
|
|---|
| 1206 | when
|
|---|
| 1207 | when'd
|
|---|
| 1208 | when'll
|
|---|
| 1209 | when's
|
|---|
| 1210 | whence
|
|---|
| 1211 | whenever
|
|---|
| 1212 | where
|
|---|
| 1213 | where'd
|
|---|
| 1214 | where'll
|
|---|
| 1215 | where's
|
|---|
| 1216 | whereafter
|
|---|
| 1217 | whereas
|
|---|
| 1218 | whereby
|
|---|
| 1219 | wherein
|
|---|
| 1220 | wheres
|
|---|
| 1221 | whereupon
|
|---|
| 1222 | wherever
|
|---|
| 1223 | whether
|
|---|
| 1224 | which
|
|---|
| 1225 | whichever
|
|---|
| 1226 | while
|
|---|
| 1227 | whilst
|
|---|
| 1228 | whim
|
|---|
| 1229 | whither
|
|---|
| 1230 | who
|
|---|
| 1231 | who'd
|
|---|
| 1232 | who'll
|
|---|
| 1233 | who's
|
|---|
| 1234 | whod
|
|---|
| 1235 | whoever
|
|---|
| 1236 | whole
|
|---|
| 1237 | wholl
|
|---|
| 1238 | whom
|
|---|
| 1239 | whomever
|
|---|
| 1240 | whos
|
|---|
| 1241 | whose
|
|---|
| 1242 | why
|
|---|
| 1243 | why'd
|
|---|
| 1244 | why'll
|
|---|
| 1245 | why's
|
|---|
| 1246 | widely
|
|---|
| 1247 | width
|
|---|
| 1248 | will
|
|---|
| 1249 | willing
|
|---|
| 1250 | wish
|
|---|
| 1251 | with
|
|---|
| 1252 | within
|
|---|
| 1253 | without
|
|---|
| 1254 | won
|
|---|
| 1255 | won't
|
|---|
| 1256 | wonder
|
|---|
| 1257 | wont
|
|---|
| 1258 | words
|
|---|
| 1259 | work
|
|---|
| 1260 | worked
|
|---|
| 1261 | working
|
|---|
| 1262 | works
|
|---|
| 1263 | world
|
|---|
| 1264 | would
|
|---|
| 1265 | would've
|
|---|
| 1266 | wouldn
|
|---|
| 1267 | wouldn't
|
|---|
| 1268 | wouldnt
|
|---|
| 1269 | ws
|
|---|
| 1270 | www
|
|---|
| 1271 | x
|
|---|
| 1272 | y
|
|---|
| 1273 | ye
|
|---|
| 1274 | year
|
|---|
| 1275 | years
|
|---|
| 1276 | yes
|
|---|
| 1277 | yet
|
|---|
| 1278 | you
|
|---|
| 1279 | you'd
|
|---|
| 1280 | you'll
|
|---|
| 1281 | you're
|
|---|
| 1282 | you've
|
|---|
| 1283 | youd
|
|---|
| 1284 | youll
|
|---|
| 1285 | young
|
|---|
| 1286 | younger
|
|---|
| 1287 | youngest
|
|---|
| 1288 | your
|
|---|
| 1289 | youre
|
|---|
| 1290 | yours
|
|---|
| 1291 | yourself
|
|---|
| 1292 | yourselves
|
|---|
| 1293 | youve
|
|---|
| 1294 | yt
|
|---|
| 1295 | yu
|
|---|
| 1296 | z
|
|---|
| 1297 | za
|
|---|
| 1298 | zero
|
|---|
| 1299 | zm
|
|---|
| 1300 | zr
|
|---|
| 1301 | """
|
|---|
| 1302 |
|
|---|
| 1303 | import xapian
|
|---|
| 1304 | db = xapian.WritableDatabase("test.xapiandb.tmp", xapian.DB_CREATE_OR_OVERWRITE | xapian.DB_NO_TERMLIST)
|
|---|
| 1305 | db.set_metadata("valuesmap", "title:0;targetPath:1")
|
|---|
| 1306 | db.set_metadata("kind", "title")
|
|---|
| 1307 | db.set_metadata("data", "fullPath")
|
|---|
| 1308 | db.set_metadata("language", "en")
|
|---|
| 1309 | db.set_metadata("stopwords", stopwords)
|
|---|
| 1310 | stemmer = xapian.Stem("en")
|
|---|
| 1311 | indexer = xapian.TermGenerator()
|
|---|
| 1312 | indexer.set_max_word_length(240)
|
|---|
| 1313 | indexer.set_flags(indexer.FLAG_CJK_NGRAM)
|
|---|
| 1314 | indexer.set_stemmer(stemmer)
|
|---|
| 1315 | indexer.set_stemming_strategy(indexer.STEM_SOME)
|
|---|
| 1316 | doc = xapian.Document()
|
|---|
| 1317 | doc.clear_values()
|
|---|
| 1318 | doc.set_data("C/p")
|
|---|
| 1319 | indexer.set_document(doc)
|
|---|
| 1320 | doc.add_value(0, "awordthatis240characterslonggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggg awordthatis240characterslonggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggg")
|
|---|
| 1321 | doc.add_value(1, "p")
|
|---|
| 1322 | indexer.index_text("0posanchor awordthatis240characterslonggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggg awordthatis240characterslonggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggg", 1)
|
|---|
| 1323 | db.add_document(doc)
|
|---|
| 1324 | db.commit()
|
|---|
| 1325 | db.compact("test.xapiandb", xapian.DBCOMPACT_SINGLE_FILE|xapian.Compactor.FULLER)
|
|---|
| 1326 | db.close()
|
|---|