RubyGems - wordlist - Versions diffs - 0.1.1 → 1.0.1 - Mend

wordlist 0.1.1 → 1.0.1

Files changed (152) hide show

checksums.yaml +7 -0
data/.github/workflows/ruby.yml +28 -0
data/.gitignore +6 -3
data/ChangeLog.md +55 -1
data/Gemfile +15 -0
data/LICENSE.txt +1 -3
data/README.md +301 -60
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 +13 -12
data/lib/wordlist/abstract_wordlist.rb +25 -0
data/lib/wordlist/builder.rb +172 -138
data/lib/wordlist/cli.rb +459 -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 +177 -0
data/lib/wordlist/format.rb +39 -0
data/lib/wordlist/lexer/lang.rb +34 -0
data/lib/wordlist/lexer/stop_words.rb +69 -0
data/lib/wordlist/lexer.rb +221 -0
data/lib/wordlist/list_methods.rb +462 -0
data/lib/wordlist/modifiers/capitalize.rb +46 -0
data/lib/wordlist/modifiers/downcase.rb +46 -0
data/lib/wordlist/modifiers/gsub.rb +52 -0
data/lib/wordlist/modifiers/modifier.rb +44 -0
data/lib/wordlist/modifiers/mutate.rb +134 -0
data/lib/wordlist/modifiers/mutate_case.rb +26 -0
data/lib/wordlist/modifiers/sub.rb +98 -0
data/lib/wordlist/modifiers/tr.rb +72 -0
data/lib/wordlist/modifiers/upcase.rb +46 -0
data/lib/wordlist/modifiers.rb +9 -0
data/lib/wordlist/operators/binary_operator.rb +39 -0
data/lib/wordlist/operators/concat.rb +48 -0
data/lib/wordlist/operators/intersect.rb +56 -0
data/lib/wordlist/operators/operator.rb +29 -0
data/lib/wordlist/operators/power.rb +73 -0
data/lib/wordlist/operators/product.rb +51 -0
data/lib/wordlist/operators/subtract.rb +55 -0
data/lib/wordlist/operators/unary_operator.rb +30 -0
data/lib/wordlist/operators/union.rb +62 -0
data/lib/wordlist/operators/unique.rb +53 -0
data/lib/wordlist/operators.rb +8 -0
data/lib/wordlist/unique_filter.rb +41 -61
data/lib/wordlist/version.rb +4 -2
data/lib/wordlist/words.rb +72 -0
data/lib/wordlist.rb +104 -2
data/spec/abstract_list_spec.rb +18 -0
data/spec/builder_spec.rb +220 -76
data/spec/cli_spec.rb +802 -0
data/spec/compression/reader_spec.rb +137 -0
data/spec/compression/writer_spec.rb +194 -0
data/spec/file_spec.rb +269 -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 +718 -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/unary_operator_spec.rb +14 -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
data/wordlist.gemspec +1 -0
metadata +164 -126
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/classes/parser_class.rb +0 -7
data/spec/classes/test_list.rb +0 -9
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/mr.txt ADDED Viewed

@@ -0,0 +1,99 @@
+आहे
+या
+आणि
+व
+नाही
+आहेत
+यानी
+हे
+तर
+ते
+असे
+होते
+केली
+हा
+ही
+पण
+करणयात
+काही
+केले
+एक
+केला
+अशी
+मात्र
+त्यानी
+सुरू
+करून
+होती
+असून
+आले
+त्यामुळे
+झाली
+होता
+दोन
+झाले
+मुबी
+होत
+त्या
+आता
+असा
+याच्या
+त्याच्या
+ता
+आली
+की
+पम
+तो
+झाला
+त्री
+तरी
+म्हणून
+त्याना
+अनेक
+काम
+माहिती
+हजार
+सागित्ले
+दिली
+आला
+आज
+ती
+तसेच
+एका
+याची
+येथील
+सर्व
+न
+डॉ
+तीन
+येथे
+पाटील
+असलयाचे
+त्याची
+काय
+आपल्या
+म्हणजे
+याना
+म्हणाले
+त्याचा
+असलेल्या
+मी
+गेल्या
+याचा
+येत
+म
+लाख
+कमी
+जात
+टा
+होणार
+किवा
+का
+अधिक
+घेऊन
+परयतन
+कोटी
+झालेल्या
+निर्ण्य
+येणार
+व्यकत

data/data/stop_words/nl.txt ADDED Viewed

@@ -0,0 +1,48 @@
+aan
+af
+al
+als
+bij
+dan
+dat
+die
+dit
+een
+en
+er
+had
+heb
+hem
+het
+hij
+hoe
+hun
+ik
+in
+is
+je
+kan
+me
+men
+met
+mij
+nog
+nu
+of
+ons
+ook
+te
+tot
+uit
+van
+was
+wat
+we
+wel
+wij
+zal
+ze
+zei
+zij
+zo
+zou

data/data/stop_words/no.txt ADDED Viewed

@@ -0,0 +1,172 @@
+å
+alle
+at
+av
+både
+båe
+bare
+begge
+ble
+blei
+bli
+blir
+blitt
+då
+da
+de
+deg
+dei
+deim
+deira
+deires
+dem
+den
+denne
+der
+dere
+deres
+det
+dette
+di
+din
+disse
+ditt
+du
+dykk
+dykkar
+eg
+ein
+eit
+eitt
+eller
+elles
+en
+enn
+er
+et
+ett
+etter
+før
+for
+fordi
+fra
+ha
+hadde
+han
+hans
+har
+hennar
+henne
+hennes
+her
+hjå
+ho
+hoe
+honom
+hoss
+hossen
+hun
+hva
+hvem
+hver
+hvilke
+hvilken
+hvis
+hvor
+hvordan
+hvorfor
+i
+ikke
+ikkje
+ingen
+ingi
+inkje
+inn
+inni
+ja
+jeg
+kan
+kom
+korleis
+korso
+kun
+kunne
+kva
+kvar
+kvarhelst
+kven
+kvi
+kvifor
+man
+mange
+me
+med
+medan
+meg
+meget
+mellom
+men
+mi
+min
+mine
+mitt
+mot
+mykje
+nå
+når
+ned
+no
+noe
+noen
+noka
+noko
+nokon
+nokor
+nokre
+og
+også
+om
+opp
+oss
+over
+på
+så
+sånn
+samme
+seg
+selv
+si
+sia
+sidan
+siden
+sin
+sine
+sitt
+sjøl
+skal
+skulle
+slik
+so
+som
+somme
+somt
+til
+um
+upp
+ut
+uten
+vår
+være
+vært
+var
+vart
+varte
+ved
+vere
+verte
+vi
+vil
+ville
+vore
+vors
+vort

data/data/stop_words/pl.txt ADDED Viewed

@@ -0,0 +1,138 @@
+ach
+aj
+albo
+bardzo
+bez
+bo
+być
+ci
+cię
+ciebie
+co
+czy
+daleko
+dla
+dlaczego
+dlatego
+do
+dobrze
+dokąd
+dość
+dużo
+dwa
+dwaj
+dwie
+dwoje
+dziś
+dzisiaj
+gdyby
+gdzie
+go
+ich
+ile
+im
+inny
+ja
+ją
+jak
+jakby
+jaki
+je
+jeden
+jedna
+jedno
+jego
+jej
+jemu
+jeśli
+jest
+jestem
+jeżeli
+już
+każdy
+kiedy
+kierunku
+kto
+ku
+lub
+ma
+mają
+mam
+mi
+mną
+mnie
+moi
+mój
+moja
+moje
+może
+mu
+my
+na
+nam
+nami
+nas
+nasi
+nasz
+nasza
+nasze
+natychmiast
+nią
+nic
+nich
+nie
+niego
+niej
+niemu
+nigdy
+nim
+nimi
+niż
+obok
+od
+około
+on
+ona
+one
+oni
+ono
+owszem
+po
+pod
+ponieważ
+przed
+przedtem
+są
+sam
+sama
+się
+skąd
+tak
+taki
+tam
+ten
+to
+tobą
+tobie
+tu
+tutaj
+twoi
+twój
+twoja
+twoje
+ty
+wam
+wami
+was
+wasi
+wasz
+wasza
+wasze
+we
+więc
+wszystko
+wtedy
+wy
+żaden
+zawsze
+że

data/data/stop_words/pt.txt ADDED Viewed

@@ -0,0 +1,147 @@
+último
+é
+acerca
+agora
+algmas
+alguns
+ali
+ambos
+antes
+apontar
+aquela
+aquelas
+aquele
+aqueles
+aqui
+atrás
+bem
+bom
+cada
+caminho
+cima
+com
+como
+comprido
+conhecido
+corrente
+das
+debaixo
+dentro
+desde
+desligado
+deve
+devem
+deverá
+direita
+diz
+dizer
+dois
+dos
+e
+ela
+ele
+eles
+em
+enquanto
+então
+está
+estão
+estado
+estar
+estará
+este
+estes
+esteve
+estive
+estivemos
+estiveram
+eu
+fará
+faz
+fazer
+fazia
+fez
+fim
+foi
+fora
+horas
+iniciar
+inicio
+ir
+irá
+ista
+iste
+isto
+ligado
+maioria
+maiorias
+mais
+mas
+mesmo
+meu
+muito
+muitos
+nós
+não
+nome
+nosso
+novo
+o
+onde
+os
+ou
+outro
+para
+parte
+pegar
+pelo
+pessoas
+pode
+poderá
+podia
+por
+porque
+povo
+promeiro
+quê
+qual
+qualquer
+quando
+quem
+quieto
+são
+saber
+sem
+ser
+seu
+somente
+têm
+tal
+também
+tem
+tempo
+tenho
+tentar
+tentaram
+tente
+tentei
+teu
+teve
+tipo
+tive
+todos
+trabalhar
+trabalho
+tu
+um
+uma
+umas
+uns
+usa
+usar
+valor
+veja
+ver
+verdade
+verdadeiro
+você