keyphrase 0.1.0

data/lib/keyphrase/stoplist/eng.rb

@@ -0,0 +1,1896 @@
+class Keyphrase
+  module Stoplist
+    class Eng
+      def self.smart
+        @@smart_regex ||= /(?:^|\s)(?:#{smart_words.join('|')})(?:$|\s)/io
+      end
+
+      def self.strict
+        @@strict_regex ||= /(?:^|\s)(?:#{strict_words.join('|')})(?:$|\s)/io
+      end
+
+      def self.smart_words
+        @@smart ||= %w{
+dr
+dra
+mr
+ms
+a
+a's
+able
+about
+above
+according
+accordingly
+across
+actually
+after
+afterwards
+again
+against
+ain't
+all
+allow
+allows
+almost
+alone
+along
+already
+also
+although
+always
+am
+among
+amongst
+an
+and
+another
+any
+anybody
+anyhow
+anyone
+anything
+anyway
+anyways
+anywhere
+apart
+appear
+appreciate
+appropriate
+are
+aren't
+around
+as
+aside
+ask
+asking
+associated
+at
+available
+away
+awfully
+b
+be
+became
+because
+become
+becomes
+becoming
+been
+before
+beforehand
+behind
+being
+believe
+below
+beside
+besides
+best
+better
+between
+beyond
+both
+brief
+but
+by
+c
+c'mon
+c's
+came
+can
+can't
+cannot
+cant
+cause
+causes
+certain
+certainly
+changes
+clearly
+co
+com
+come
+comes
+concerning
+consequently
+consider
+considering
+contain
+containing
+contains
+corresponding
+could
+couldn't
+course
+currently
+d
+definitely
+described
+despite
+did
+didn't
+different
+do
+does
+doesn't
+doing
+don't
+done
+down
+downwards
+during
+e
+each
+edu
+eg
+eight
+either
+else
+elsewhere
+enough
+entirely
+especially
+et
+etc
+even
+ever
+every
+everybody
+everyone
+everything
+everywhere
+ex
+exactly
+example
+except
+f
+far
+few
+fifth
+first
+five
+followed
+following
+follows
+for
+former
+formerly
+forth
+four
+from
+further
+furthermore
+g
+get
+gets
+getting
+given
+gives
+go
+goes
+going
+gone
+got
+gotten
+greetings
+h
+had
+hadn't
+happens
+hardly
+has
+hasn't
+have
+haven't
+having
+he
+he's
+hello
+help
+hence
+her
+here
+here's
+hereafter
+hereby
+herein
+hereupon
+hers
+herself
+hi
+him
+himself
+his
+hither
+hopefully
+how
+howbeit
+however
+i
+i'd
+i'll
+i'm
+i've
+ie
+if
+ignored
+immediate
+in
+inasmuch
+inc
+indeed
+indicate
+indicated
+indicates
+inner
+insofar
+instead
+into
+inward
+is
+isn't
+it
+it'd
+it'll
+it's
+its
+itself
+j
+just
+k
+keep
+keeps
+kept
+know
+knows
+known
+l
+last
+lately
+later
+latter
+latterly
+least
+less
+lest
+let
+let's
+like
+liked
+likely
+little
+look
+looking
+looks
+ltd
+m
+mainly
+many
+may
+maybe
+me
+mean
+meanwhile
+merely
+might
+more
+moreover
+most
+mostly
+much
+must
+my
+myself
+n
+name
+namely
+nd
+near
+nearly
+necessary
+need
+needs
+neither
+never
+nevertheless
+new
+next
+nine
+no
+nobody
+non
+none
+noone
+nor
+normally
+not
+nothing
+novel
+now
+nowhere
+o
+obviously
+of
+off
+often
+oh
+ok
+okay
+old
+on
+once
+one
+ones
+only
+onto
+or
+other
+others
+otherwise
+ought
+our
+ours
+ourselves
+out
+outside
+over
+overall
+own
+p
+particular
+particularly
+per
+perhaps
+placed
+please
+plus
+possible
+presumably
+probably
+provides
+q
+que
+quite
+qv
+r
+rather
+rd
+re
+really
+reasonably
+regarding
+regardless
+regards
+relatively
+respectively
+right
+s
+said
+same
+saw
+say
+saying
+says
+second
+secondly
+see
+seeing
+seem
+seemed
+seeming
+seems
+seen
+self
+selves
+sensible
+sent
+serious
+seriously
+seven
+several
+shall
+she
+should
+shouldn't
+since
+six
+so
+some
+somebody
+somehow
+someone
+something
+sometime
+sometimes
+somewhat
+somewhere
+soon
+sorry
+specified
+specify
+specifying
+still
+sub
+such
+sup
+sure
+t
+t's
+take
+taken
+tell
+tends
+th
+than
+thank
+thanks
+thanx
+that
+that's
+thats
+the
+their
+theirs
+them
+themselves
+then
+thence
+there
+there's
+thereafter
+thereby
+therefore
+therein
+theres
+thereupon
+these
+they
+they'd
+they'll
+they're
+they've
+think
+third
+this
+thorough
+thoroughly
+those
+though
+three
+through
+throughout
+thru
+thus
+to
+together
+too
+took
+toward
+towards
+tried
+tries
+truly
+try
+trying
+twice
+two
+u
+un
+under
+unfortunately
+unless
+unlikely
+until
+unto
+up
+upon
+us
+use
+used
+useful
+uses
+using
+usually
+uucp
+v
+value
+various
+very
+via
+viz
+vs
+w
+want
+wants
+was
+wasn't
+way
+we
+we'd
+we'll
+we're
+we've
+welcome
+well
+went
+were
+weren't
+what
+what's
+whatever
+when
+whence
+whenever
+where
+where's
+whereafter
+whereas
+whereby
+wherein
+whereupon
+wherever
+whether
+which
+while
+whither
+who
+who's
+whoever
+whole
+whom
+whose
+why
+will
+willing
+wish
+with
+within
+without
+won't
+wonder
+would
+would
+wouldn't
+x
+y
+yes
+yet
+you
+you'd
+you'll
+you're
+you've
+your
+yours
+yourself
+yourselves
+z
+zero
+        }
+      end
+
+      def self.strict_words
+        @@strict ||= %w{
+  'll
+    'tis
+    'twas
+    've
+    10
+    39
+    a
+    a's
+    able
+    ableabout
+    about
+    above
+    abroad
+    abst
+    accordance
+    according
+    accordingly
+    across
+    act
+    actually
+    ad
+    added
+    adj
+    adopted
+    ae
+    af
+    affected
+    affecting
+    affects
+    after
+    afterwards
+    ag
+    again
+    against
+    ago
+    ah
+    ahead
+    ai
+    ain't
+    aint
+    al
+    all
+    allow
+    allows
+    almost
+    alone
+    along
+    alongside
+    already
+    also
+    although
+    always
+    am
+    amid
+    amidst
+    among
+    amongst
+    amoungst
+    amount
+    an
+    and
+    announce
+    another
+    any
+    anybody
+    anyhow
+    anymore
+    anyone
+    anything
+    anyway
+    anyways
+    anywhere
+    ao
+    apart
+    apparently
+    appear
+    appreciate
+    appropriate
+    approximately
+    aq
+    ar
+    are
+    area
+    areas
+    aren
+    aren't
+    arent
+    arise
+    around
+    arpa
+    as
+    aside
+    ask
+    asked
+    asking
+    asks
+    associated
+    at
+    au
+    auth
+    available
+    aw
+    away
+    awfully
+    az
+    b
+    ba
+    back
+    backed
+    backing
+    backs
+    backward
+    backwards
+    bb
+    bd
+    be
+    became
+    because
+    become
+    becomes
+    becoming
+    been
+    before
+    beforehand
+    began
+    begin
+    beginning
+    beginnings
+    begins
+    behind
+    being
+    beings
+    believe
+    below
+    beside
+    besides
+    best
+    better
+    between
+    beyond
+    bf
+    bg
+    bh
+    bi
+    big
+    bill
+    billion
+    biol
+    bj
+    bm
+    bn
+    bo
+    both
+    bottom
+    br
+    brief
+    briefly
+    bs
+    bt
+    but
+    buy
+    bv
+    bw
+    by
+    bz
+    c
+    c'mon
+    c's
+    ca
+    call
+    came
+    can
+    can't
+    cannot
+    cant
+    caption
+    case
+    cases
+    cause
+    causes
+    cc
+    cd
+    certain
+    certainly
+    cf
+    cg
+    ch
+    changes
+    ci
+    ck
+    cl
+    clear
+    clearly
+    click
+    cm
+    cmon
+    cn
+    co
+    co.
+    com
+    come
+    comes
+    computer
+    con
+    concerning
+    consequently
+    consider
+    considering
+    contain
+    containing
+    contains
+    copy
+    corresponding
+    could
+    could've
+    couldn
+    couldn't
+    couldnt
+    course
+    cr
+    cry
+    cs
+    cu
+    currently
+    cv
+    cx
+    cy
+    cz
+    d
+    dare
+    daren't
+    darent
+    date
+    de
+    dear
+    definitely
+    describe
+    described
+    despite
+    detail
+    did
+    didn
+    didn't
+    didnt
+    differ
+    different
+    differently
+    directly
+    dj
+    dk
+    dm
+    do
+    does
+    doesn
+    doesn't
+    doesnt
+    doing
+    don
+    don't
+    done
+    dont
+    doubtful
+    down
+    downed
+    downing
+    downs
+    downwards
+    due
+    during
+    dz
+    e
+    each
+    early
+    ec
+    ed
+    edu
+    ee
+    effect
+    eg
+    eh
+    eight
+    eighty
+    either
+    eleven
+    else
+    elsewhere
+    empty
+    end
+    ended
+    ending
+    ends
+    enough
+    entirely
+    er
+    es
+    especially
+    et
+    et-al
+    etc
+    even
+    evenly
+    ever
+    evermore
+    every
+    everybody
+    everyone
+    everything
+    everywhere
+    ex
+    exactly
+    example
+    except
+    f
+    face
+    faces
+    fact
+    facts
+    fairly
+    far
+    farther
+    felt
+    few
+    fewer
+    ff
+    fi
+    fifteen
+    fifth
+    fifty
+    fify
+    fill
+    find
+    finds
+    fire
+    first
+    five
+    fix
+    fj
+    fk
+    fm
+    fo
+    followed
+    following
+    follows
+    for
+    forever
+    former
+    formerly
+    forth
+    forty
+    forward
+    found
+    four
+    fr
+    free
+    from
+    front
+    full
+    fully
+    further
+    furthered
+    furthering
+    furthermore
+    furthers
+    fx
+    g
+    ga
+    gave
+    gb
+    gd
+    ge
+    general
+    generally
+    get
+    gets
+    getting
+    gf
+    gg
+    gh
+    gi
+    give
+    given
+    gives
+    giving
+    gl
+    gm
+    gmt
+    gn
+    go
+    goes
+    going
+    gone
+    good
+    goods
+    got
+    gotten
+    gov
+    gp
+    gq
+    gr
+    great
+    greater
+    greatest
+    greetings
+    group
+    grouped
+    grouping
+    groups
+    gs
+    gt
+    gu
+    gw
+    gy
+    h
+    had
+    hadn't
+    hadnt
+    half
+    happens
+    hardly
+    has
+    hasn
+    hasn't
+    hasnt
+    have
+    haven
+    haven't
+    havent
+    having
+    he
+    he'd
+    he'll
+    he's
+    hed
+    hell
+    hello
+    help
+    hence
+    her
+    here
+    here's
+    hereafter
+    hereby
+    herein
+    heres
+    hereupon
+    hers
+    herself
+    herse”
+    hes
+    hi
+    hid
+    high
+    higher
+    highest
+    him
+    himself
+    himse”
+    his
+    hither
+    hk
+    hm
+    hn
+    home
+    homepage
+    hopefully
+    how
+    how'd
+    how'll
+    how's
+    howbeit
+    however
+    hr
+    ht
+    htm
+    html
+    http
+    hu
+    hundred
+    i
+    i'd
+    i'll
+    i'm
+    i've
+    i.e.
+    id
+    ie
+    if
+    ignored
+    ii
+    il
+    ill
+    im
+    immediate
+    immediately
+    importance
+    important
+    in
+    inasmuch
+    inc
+    inc.
+    indeed
+    index
+    indicate
+    indicated
+    indicates
+    information
+    inner
+    inside
+    insofar
+    instead
+    int
+    interest
+    interested
+    interesting
+    interests
+    into
+    invention
+    inward
+    io
+    iq
+    ir
+    is
+    isn
+    isn't
+    isnt
+    it
+    it'd
+    it'll
+    it's
+    itd
+    itll
+    its
+    itself
+    itse”
+    ive
+    j
+    je
+    jm
+    jo
+    join
+    jp
+    just
+    k
+    ke
+    keep
+    keeps
+    kept
+    keys
+    kg
+    kh
+    ki
+    kind
+    km
+    kn
+    knew
+    know
+    known
+    knows
+    kp
+    kr
+    kw
+    ky
+    kz
+    l
+    la
+    large
+    largely
+    last
+    lately
+    later
+    latest
+    latter
+    latterly
+    lb
+    lc
+    least
+    length
+    less
+    lest
+    let
+    let's
+    lets
+    li
+    like
+    liked
+    likely
+    likewise
+    line
+    little
+    lk
+    ll
+    long
+    longer
+    longest
+    look
+    looking
+    looks
+    low
+    lower
+    lr
+    ls
+    lt
+    ltd
+    lu
+    lv
+    ly
+    m
+    ma
+    made
+    mainly
+    make
+    makes
+    making
+    man
+    many
+    may
+    maybe
+    mayn't
+    maynt
+    mc
+    md
+    me
+    mean
+    means
+    meantime
+    meanwhile
+    member
+    members
+    men
+    merely
+    mg
+    mh
+    microsoft
+    might
+    might've
+    mightn't
+    mightnt
+    mil
+    mill
+    million
+    mine
+    minus
+    miss
+    mk
+    ml
+    mm
+    mn
+    mo
+    more
+    moreover
+    most
+    mostly
+    move
+    mp
+    mq
+    mr
+    mrs
+    ms
+    msie
+    mt
+    mu
+    much
+    mug
+    must
+    must've
+    mustn't
+    mustnt
+    mv
+    mw
+    mx
+    my
+    myself
+    myse”
+    mz
+    n
+    na
+    name
+    namely
+    nay
+    nc
+    nd
+    ne
+    near
+    nearly
+    necessarily
+    necessary
+    need
+    needed
+    needing
+    needn't
+    neednt
+    needs
+    neither
+    net
+    netscape
+    never
+    neverf
+    neverless
+    nevertheless
+    new
+    newer
+    newest
+    next
+    nf
+    ng
+    ni
+    nine
+    ninety
+    nl
+    no
+    no-one
+    nobody
+    non
+    none
+    nonetheless
+    noone
+    nor
+    normally
+    nos
+    not
+    noted
+    nothing
+    notwithstanding
+    novel
+    now
+    nowhere
+    np
+    nr
+    nu
+    null
+    number
+    numbers
+    nz
+    o
+    obtain
+    obtained
+    obviously
+    of
+    off
+    often
+    oh
+    ok
+    okay
+    old
+    older
+    oldest
+    om
+    omitted
+    on
+    once
+    one
+    one's
+    ones
+    only
+    onto
+    open
+    opened
+    opening
+    opens
+    opposite
+    or
+    ord
+    order
+    ordered
+    ordering
+    orders
+    org
+    other
+    others
+    otherwise
+    ought
+    oughtn't
+    oughtnt
+    our
+    ours
+    ourselves
+    out
+    outside
+    over
+    overall
+    owing
+    own
+    p
+    pa
+    page
+    pages
+    part
+    parted
+    particular
+    particularly
+    parting
+    parts
+    past
+    pe
+    per
+    perhaps
+    pf
+    pg
+    ph
+    pk
+    pl
+    place
+    placed
+    places
+    please
+    plus
+    pm
+    pmid
+    pn
+    point
+    pointed
+    pointing
+    points
+    poorly
+    possible
+    possibly
+    potentially
+    pp
+    pr
+    predominantly
+    present
+    presented
+    presenting
+    presents
+    presumably
+    previously
+    primarily
+    probably
+    problem
+    problems
+    promptly
+    proud
+    provided
+    provides
+    pt
+    put
+    puts
+    pw
+    py
+    q
+    qa
+    que
+    quickly
+    quite
+    qv
+    r
+    ran
+    rather
+    rd
+    re
+    readily
+    really
+    reasonably
+    recent
+    recently
+    ref
+    refs
+    regarding
+    regardless
+    regards
+    related
+    relatively
+    research
+    reserved
+    respectively
+    resulted
+    resulting
+    results
+    right
+    ring
+    ro
+    room
+    rooms
+    round
+    ru
+    run
+    rw
+    s
+    sa
+    said
+    same
+    saw
+    say
+    saying
+    says
+    sb
+    sc
+    sd
+    se
+    sec
+    second
+    secondly
+    seconds
+    section
+    see
+    seeing
+    seem
+    seemed
+    seeming
+    seems
+    seen
+    sees
+    self
+    selves
+    sensible
+    sent
+    serious
+    seriously
+    seven
+    seventy
+    several
+    sg
+    sh
+    shall
+    shan't
+    shant
+    she
+    she'd
+    she'll
+    she's
+    shed
+    shell
+    shes
+    should
+    should've
+    shouldn
+    shouldn't
+    shouldnt
+    show
+    showed
+    showing
+    shown
+    showns
+    shows
+    si
+    side
+    sides
+    significant
+    significantly
+    similar
+    similarly
+    since
+    sincere
+    site
+    six
+    sixty
+    sj
+    sk
+    sl
+    slightly
+    sm
+    small
+    smaller
+    smallest
+    sn
+    so
+    some
+    somebody
+    someday
+    somehow
+    someone
+    somethan
+    something
+    sometime
+    sometimes
+    somewhat
+    somewhere
+    soon
+    sorry
+    specifically
+    specified
+    specify
+    specifying
+    sr
+    st
+    state
+    states
+    still
+    stop
+    strongly
+    su
+    sub
+    substantially
+    successfully
+    such
+    sufficiently
+    suggest
+    sup
+    sure
+    sv
+    sy
+    system
+    sz
+    t
+    t's
+    take
+    taken
+    taking
+    tc
+    td
+    tell
+    ten
+    tends
+    test
+    text
+    tf
+    tg
+    th
+    than
+    thank
+    thanks
+    thanx
+    that
+    that'll
+    that's
+    that've
+    thatll
+    thats
+    thatve
+    the
+    their
+    theirs
+    them
+    themselves
+    then
+    thence
+    there
+    there'd
+    there'll
+    there're
+    there's
+    there've
+    thereafter
+    thereby
+    thered
+    therefore
+    therein
+    therell
+    thereof
+    therere
+    theres
+    thereto
+    thereupon
+    thereve
+    these
+    they
+    they'd
+    they'll
+    they're
+    they've
+    theyd
+    theyll
+    theyre
+    theyve
+    thick
+    thin
+    thing
+    things
+    think
+    thinks
+    third
+    thirty
+    this
+    thorough
+    thoroughly
+    those
+    thou
+    though
+    thoughh
+    thought
+    thoughts
+    thousand
+    three
+    throug
+    through
+    throughout
+    thru
+    thus
+    til
+    till
+    tip
+    tis
+    tj
+    tk
+    tm
+    tn
+    to
+    today
+    together
+    too
+    took
+    top
+    toward
+    towards
+    tp
+    tr
+    tried
+    tries
+    trillion
+    truly
+    try
+    trying
+    ts
+    tt
+    turn
+    turned
+    turning
+    turns
+    tv
+    tw
+    twas
+    twelve
+    twenty
+    twice
+    two
+    tz
+    u
+    ua
+    ug
+    uk
+    um
+    un
+    under
+    underneath
+    undoing
+    unfortunately
+    unless
+    unlike
+    unlikely
+    until
+    unto
+    up
+    upon
+    ups
+    upwards
+    us
+    use
+    used
+    useful
+    usefully
+    usefulness
+    uses
+    using
+    usually
+    uucp
+    uy
+    uz
+    v
+    va
+    value
+    various
+    vc
+    ve
+    versus
+    very
+    vg
+    vi
+    via
+    viz
+    vn
+    vol
+    vols
+    vs
+    vu
+    w
+    want
+    wanted
+    wanting
+    wants
+    was
+    wasn
+    wasn't
+    wasnt
+    way
+    ways
+    we
+    we'd
+    we'll
+    we're
+    we've
+    web
+    webpage
+    website
+    wed
+    welcome
+    well
+    wells
+    went
+    were
+    weren
+    weren't
+    werent
+    weve
+    wf
+    what
+    what'd
+    what'll
+    what's
+    what've
+    whatever
+    whatll
+    whats
+    whatve
+    when
+    when'd
+    when'll
+    when's
+    whence
+    whenever
+    where
+    where'd
+    where'll
+    where's
+    whereafter
+    whereas
+    whereby
+    wherein
+    wheres
+    whereupon
+    wherever
+    whether
+    which
+    whichever
+    while
+    whilst
+    whim
+    whither
+    who
+    who'd
+    who'll
+    who's
+    whod
+    whoever
+    whole
+    wholl
+    whom
+    whomever
+    whos
+    whose
+    why
+    why'd
+    why'll
+    why's
+    widely
+    width
+    will
+    willing
+    wish
+    with
+    within
+    without
+    won
+    won't
+    wonder
+    wont
+    words
+    work
+    worked
+    working
+    works
+    world
+    would
+    would've
+    wouldn
+    wouldn't
+    wouldnt
+    ws
+    www
+    x
+    y
+    ye
+    year
+    years
+    yes
+    yet
+    you
+    you'd
+    you'll
+    you're
+    you've
+    youd
+    youll
+    young
+    younger
+    youngest
+    your
+    youre
+    yours
+    yourself
+    yourselves
+    youve
+    yt
+    yu
+    z
+    za
+    zero
+    zm
+    zr
+        }
+        end
+    end
+  end
+end