RubyGems - wordlist - Versions diffs - 0.1.1 → 1.0.0 - Mend

wordlist 0.1.1 → 1.0.0

Files changed (148) hide show

checksums.yaml +7 -0
data/.github/workflows/ruby.yml +27 -0
data/.gitignore +6 -3
data/ChangeLog.md +45 -1
data/Gemfile +13 -0
data/LICENSE.txt +1 -3
data/README.md +266 -61
data/Rakefile +7 -32
data/benchmarks.rb +115 -0
data/bin/wordlist +4 -7
data/data/stop_words/ar.txt +104 -0
data/data/stop_words/bg.txt +259 -0
data/data/stop_words/bn.txt +363 -0
data/data/stop_words/ca.txt +126 -0
data/data/stop_words/cs.txt +138 -0
data/data/stop_words/da.txt +101 -0
data/data/stop_words/de.txt +129 -0
data/data/stop_words/el.txt +79 -0
data/data/stop_words/en.txt +175 -0
data/data/stop_words/es.txt +178 -0
data/data/stop_words/eu.txt +98 -0
data/data/stop_words/fa.txt +332 -0
data/data/stop_words/fi.txt +747 -0
data/data/stop_words/fr.txt +116 -0
data/data/stop_words/ga.txt +109 -0
data/data/stop_words/gl.txt +160 -0
data/data/stop_words/he.txt +499 -0
data/data/stop_words/hi.txt +97 -0
data/data/stop_words/hr.txt +179 -0
data/data/stop_words/hu.txt +35 -0
data/data/stop_words/hy.txt +45 -0
data/data/stop_words/id.txt +357 -0
data/data/stop_words/it.txt +134 -0
data/data/stop_words/ja.txt +44 -0
data/data/stop_words/ko.txt +677 -0
data/data/stop_words/ku.txt +63 -0
data/data/stop_words/lt.txt +507 -0
data/data/stop_words/lv.txt +163 -0
data/data/stop_words/mr.txt +99 -0
data/data/stop_words/nl.txt +48 -0
data/data/stop_words/no.txt +172 -0
data/data/stop_words/pl.txt +138 -0
data/data/stop_words/pt.txt +147 -0
data/data/stop_words/ro.txt +281 -0
data/data/stop_words/ru.txt +421 -0
data/data/stop_words/sk.txt +173 -0
data/data/stop_words/sv.txt +386 -0
data/data/stop_words/th.txt +115 -0
data/data/stop_words/tr.txt +114 -0
data/data/stop_words/uk.txt +28 -0
data/data/stop_words/ur.txt +513 -0
data/data/stop_words/zh.txt +125 -0
data/gemspec.yml +4 -10
data/lib/wordlist/abstract_wordlist.rb +24 -0
data/lib/wordlist/builder.rb +170 -138
data/lib/wordlist/cli.rb +458 -0
data/lib/wordlist/compression/reader.rb +72 -0
data/lib/wordlist/compression/writer.rb +80 -0
data/lib/wordlist/exceptions.rb +31 -0
data/lib/wordlist/file.rb +176 -0
data/lib/wordlist/format.rb +38 -0
data/lib/wordlist/lexer/lang.rb +32 -0
data/lib/wordlist/lexer/stop_words.rb +68 -0
data/lib/wordlist/lexer.rb +218 -0
data/lib/wordlist/list_methods.rb +462 -0
data/lib/wordlist/modifiers/capitalize.rb +45 -0
data/lib/wordlist/modifiers/downcase.rb +45 -0
data/lib/wordlist/modifiers/gsub.rb +51 -0
data/lib/wordlist/modifiers/modifier.rb +44 -0
data/lib/wordlist/modifiers/mutate.rb +133 -0
data/lib/wordlist/modifiers/mutate_case.rb +25 -0
data/lib/wordlist/modifiers/sub.rb +97 -0
data/lib/wordlist/modifiers/tr.rb +71 -0
data/lib/wordlist/modifiers/upcase.rb +45 -0
data/lib/wordlist/modifiers.rb +8 -0
data/lib/wordlist/operators/binary_operator.rb +38 -0
data/lib/wordlist/operators/concat.rb +47 -0
data/lib/wordlist/operators/intersect.rb +55 -0
data/lib/wordlist/operators/operator.rb +29 -0
data/lib/wordlist/operators/power.rb +72 -0
data/lib/wordlist/operators/product.rb +50 -0
data/lib/wordlist/operators/subtract.rb +54 -0
data/lib/wordlist/operators/unary_operator.rb +29 -0
data/lib/wordlist/operators/union.rb +61 -0
data/lib/wordlist/operators/unique.rb +52 -0
data/lib/wordlist/operators.rb +7 -0
data/lib/wordlist/unique_filter.rb +40 -61
data/lib/wordlist/version.rb +1 -1
data/lib/wordlist/words.rb +71 -0
data/lib/wordlist.rb +103 -2
data/spec/abstract_list_spec.rb +18 -0
data/spec/builder_spec.rb +220 -76
data/spec/cli_spec.rb +801 -0
data/spec/compression/reader_spec.rb +137 -0
data/spec/compression/writer_spec.rb +194 -0
data/spec/file_spec.rb +258 -0
data/spec/fixtures/wordlist.txt +15 -0
data/spec/fixtures/wordlist.txt.bz2 +0 -0
data/spec/fixtures/wordlist.txt.gz +0 -0
data/spec/fixtures/wordlist.txt.xz +0 -0
data/spec/fixtures/wordlist_with_ambiguous_format +3 -0
data/spec/fixtures/wordlist_with_comments.txt +19 -0
data/spec/fixtures/wordlist_with_empty_lines.txt +19 -0
data/spec/format_spec.rb +50 -0
data/spec/helpers/text.rb +3 -3
data/spec/helpers/wordlist.rb +2 -2
data/spec/lexer/lang_spec.rb +70 -0
data/spec/lexer/stop_words_spec.rb +77 -0
data/spec/lexer_spec.rb +652 -0
data/spec/list_methods_spec.rb +181 -0
data/spec/modifiers/capitalize_spec.rb +27 -0
data/spec/modifiers/downcase_spec.rb +27 -0
data/spec/modifiers/gsub_spec.rb +59 -0
data/spec/modifiers/modifier_spec.rb +20 -0
data/spec/modifiers/mutate_case_spec.rb +46 -0
data/spec/modifiers/mutate_spec.rb +39 -0
data/spec/modifiers/sub_spec.rb +98 -0
data/spec/modifiers/tr_spec.rb +46 -0
data/spec/modifiers/upcase_spec.rb +27 -0
data/spec/operators/binary_operator_spec.rb +19 -0
data/spec/operators/concat_spec.rb +26 -0
data/spec/operators/intersect_spec.rb +37 -0
data/spec/operators/operator_spec.rb +16 -0
data/spec/operators/power_spec.rb +57 -0
data/spec/operators/product_spec.rb +39 -0
data/spec/operators/subtract_spec.rb +37 -0
data/spec/operators/union_spec.rb +37 -0
data/spec/operators/unique_spec.rb +25 -0
data/spec/spec_helper.rb +2 -1
data/spec/unique_filter_spec.rb +108 -18
data/spec/wordlist_spec.rb +55 -3
data/spec/words_spec.rb +41 -0
metadata +183 -120
data/lib/wordlist/builders/website.rb +0 -216
data/lib/wordlist/builders.rb +0 -1
data/lib/wordlist/flat_file.rb +0 -47
data/lib/wordlist/list.rb +0 -162
data/lib/wordlist/mutator.rb +0 -113
data/lib/wordlist/parsers.rb +0 -74
data/lib/wordlist/runners/list.rb +0 -116
data/lib/wordlist/runners/runner.rb +0 -67
data/lib/wordlist/runners.rb +0 -2
data/scripts/benchmark +0 -59
data/scripts/text/comedy_of_errors.txt +0 -4011
data/spec/flat_file_spec.rb +0 -25
data/spec/list_spec.rb +0 -58
data/spec/mutator_spec.rb +0 -43
data/spec/parsers_spec.rb +0 -118

data/data/stop_words/ca.txt ADDED Viewed

@@ -0,0 +1,126 @@
+de
+es
+i
+a
+o
+un
+una
+unes
+uns
+un
+tot
+també
+altre
+algun
+alguna
+alguns
+algunes
+ser
+és
+soc
+ets
+som
+estic
+està
+estem
+esteu
+estan
+com
+en
+per
+perquè
+per que
+estat
+estava
+ans
+abans
+éssent
+ambdós
+però
+per
+poder
+potser
+puc
+podem
+podeu
+poden
+vaig
+va
+van
+fer
+faig
+fa
+fem
+feu
+fan
+cada
+fi
+inclòs
+primer
+des de
+conseguir
+consegueixo
+consigueix
+consigueixes
+conseguim
+consigueixen
+anar
+haver
+tenir
+tinc
+te
+tenim
+teniu
+tene
+el
+la
+les
+els
+seu
+aquí
+meu
+teu
+ells
+elles
+ens
+nosaltres
+vosaltres
+si
+dins
+sols
+solament
+saber
+saps
+sap
+sabem
+sabeu
+saben
+últim
+llarg
+bastant
+fas
+molts
+aquells
+aquelles
+seus
+llavors
+sota
+dalt
+ús
+molt
+era
+eres
+erem
+eren
+mode
+bé
+quant
+quan
+on
+mentre
+qui
+amb
+entre
+sense
+jo
+aquell

data/data/stop_words/cs.txt ADDED Viewed

@@ -0,0 +1,138 @@
+dnes
+cz
+timto
+budes
+budem
+byli
+jses
+muj
+svym
+ta
+tomto
+tohle
+tuto
+tyto
+jej
+zda
+proc
+mate
+tato
+kam
+tohoto
+kdo
+kteri
+mi
+nam
+tom
+tomuto
+mit
+nic
+proto
+kterou
+byla
+toho
+protoze
+asi
+ho
+nasi
+napiste
+re
+coz
+tim
+takze
+svych
+jeji
+svymi
+jste
+aj
+tu
+tedy
+teto
+bylo
+kde
+ke
+prave
+ji
+nad
+nejsou
+ci
+pod
+tema
+mezi
+pres
+ty
+pak
+vam
+ani
+kdyz
+vsak
+ne
+jsem
+tento
+clanku
+clanky
+aby
+jsme
+pred
+pta
+jejich
+byl
+jeste
+az
+bez
+take
+pouze
+prvni
+vase
+ktera
+nas
+novy
+tipy
+pokud
+muze
+design
+strana
+jeho
+sve
+jine
+zpravy
+nove
+neni
+vas
+jen
+podle
+zde
+clanek
+uz
+email
+byt
+vice
+bude
+jiz
+nez
+ktery
+by
+ktere
+co
+nebo
+ten
+tak
+ma
+pri
+od
+po
+jsou
+jak
+dalsi
+ale
+si
+ve
+to
+jako
+za
+zpet
+ze
+do
+pro
+je
+na

data/data/stop_words/da.txt ADDED Viewed

@@ -0,0 +1,101 @@
+af
+alle
+andet
+andre
+at
+begge
+da
+de
+den
+denne
+der
+deres
+det
+dette
+dig
+din
+dog
+du
+ej
+eller
+en
+end
+ene
+eneste
+enhver
+et
+fem
+fire
+flere
+fleste
+for
+fordi
+forrige
+fra
+få
+før
+god
+han
+hans
+har
+hendes
+her
+hun
+hvad
+hvem
+hver
+hvilken
+hvis
+hvor
+hvordan
+hvorfor
+hvornår
+i
+ikke
+ind
+ingen
+intet
+jeg
+jeres
+kan
+kom
+kommer
+lav
+lidt
+lille
+man
+mand
+mange
+med
+meget
+men
+mens
+mere
+mig
+ned
+ni
+nogen
+noget
+ny
+nyt
+nær
+næste
+næsten
+og
+op
+otte
+over
+på
+se
+seks
+ses
+som
+stor
+store
+syv
+ti
+til
+to
+tre
+ud
+var

data/data/stop_words/de.txt ADDED Viewed

@@ -0,0 +1,129 @@
+aber
+als
+am
+an
+auch
+auf
+aus
+bei
+bin
+bis
+bist
+da
+dadurch
+daher
+darum
+das
+daß
+dass
+dein
+deine
+dem
+den
+der
+des
+dessen
+deshalb
+die
+dies
+dieser
+dieses
+doch
+dort
+du
+durch
+ein
+eine
+einem
+einen
+einer
+eines
+er
+es
+euer
+eure
+für
+hatte
+hatten
+hattest
+hattet
+hier
+hinter
+ich
+ihr
+ihre
+im
+in
+ist
+ja
+jede
+jedem
+jeden
+jeder
+jedes
+jener
+jenes
+jetzt
+kann
+kannst
+können
+könnt
+machen
+mein
+meine
+mit
+muß
+mußt
+musst
+müssen
+müßt
+nach
+nachdem
+nein
+nicht
+nun
+oder
+seid
+sein
+seine
+sich
+sie
+sind
+soll
+sollen
+sollst
+sollt
+sonst
+soweit
+sowie
+und
+unser
+unsere
+unter
+vom
+von
+vor
+wann
+warum
+was
+weiter
+weitere
+wenn
+wer
+werde
+werden
+werdet
+weshalb
+wie
+wieder
+wieso
+wir
+wird
+wirst
+wo
+woher
+wohin
+zu
+zum
+zur
+über

data/data/stop_words/el.txt ADDED Viewed

@@ -0,0 +1,79 @@
+μή
+ἑαυτοῦ
+ἄν
+ἀλλ’
+ἀλλά
+ἄλλοσ
+ἀπό
+ἄρα
+αὐτόσ
+δ’
+δέ
+δή
+διά
+δαί
+δαίσ
+ἔτι
+ἐγώ
+ἐκ
+ἐμόσ
+ἐν
+ἐπί
+εἰ
+εἰμί
+εἴμι
+εἰσ
+γάρ
+γε
+γα^
+ἡ
+ἤ
+καί
+κατά
+μέν
+μετά
+μή
+ὁ
+ὅδε
+ὅσ
+ὅστισ
+ὅτι
+οὕτωσ
+οὗτοσ
+οὔτε
+οὖν
+οὐδείσ
+οἱ
+οὐ
+οὐδέ
+οὐκ
+περί
+πρόσ
+σύ
+σύν
+τά
+τε
+τήν
+τῆσ
+τῇ
+τι
+τί
+τισ
+τίσ
+τό
+τοί
+τοιοῦτοσ
+τόν
+τούσ
+τοῦ
+τῶν
+τῷ
+ὑμόσ
+ὑπέρ
+ὑπό
+ὡσ
+ὦ
+ὥστε
+ἐάν
+παρά
+σόσ

data/data/stop_words/en.txt ADDED Viewed

@@ -0,0 +1,175 @@
+a
+about
+above
+after
+again
+against
+all
+am
+an
+and
+any
+are
+aren't
+as
+at
+be
+because
+been
+before
+being
+below
+between
+both
+but
+by
+can
+can't
+cannot
+could
+couldn't
+did
+didn't
+do
+does
+doesn't
+doing
+don't
+down
+during
+each
+few
+for
+from
+further
+had
+hadn't
+has
+hasn't
+have
+haven't
+having
+he
+he'd
+he'll
+he's
+her
+here
+here's
+hers
+herself
+him
+himself
+his
+how
+how's
+i
+i'd
+i'll
+i'm
+i've
+if
+in
+into
+is
+isn't
+it
+it's
+its
+itself
+let's
+me
+more
+most
+mustn't
+my
+myself
+no
+nor
+not
+of
+off
+on
+once
+only
+or
+other
+ought
+our
+ours
+ourselves
+out
+over
+own
+same
+shan't
+she
+she'd
+she'll
+she's
+should
+shouldn't
+so
+some
+such
+than
+that
+that's
+the
+their
+theirs
+them
+themselves
+then
+there
+there's
+these
+they
+they'd
+they'll
+they're
+they've
+this
+those
+through
+to
+too
+under
+until
+up
+very
+was
+wasn't
+we
+we'd
+we'll
+we're
+we've
+were
+weren't
+what
+what's
+when
+when's
+where
+where's
+which
+while
+who
+who's
+whom
+why
+why's
+with
+won't
+would
+wouldn't
+you
+you'd
+you'll
+you're
+you've
+your
+yours
+yourself
+yourselves