From 69e5f771ec1fe89f90d923b4549f98ba3e9b5b5f Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Jos=C3=A9=20Carlos=20Cuevas?= <reset.reboot@gmail.com>
Date: Fri, 3 Jul 2015 10:48:00 +0200
Subject: [PATCH] Initial commit

---
 .gitignore                                    |   3 +
 README.md                                     |   0
 main.go                                       | 208 +++++
 src/tfidf/stop-words/stop-words-arabic.txt    | 162 ++++
 src/tfidf/stop-words/stop-words-catalian.txt  | 126 +++
 src/tfidf/stop-words/stop-words-czech1.txt    | 138 ++++
 src/tfidf/stop-words/stop-words-czech2.txt    | 172 ++++
 src/tfidf/stop-words/stop-words-dutch.txt     |  48 ++
 src/tfidf/stop-words/stop-words-english1.txt  | 635 +++++++++++++++
 src/tfidf/stop-words/stop-words-english2.txt  | 174 ++++
 .../stop-words/stop-words-english3-google.txt |  32 +
 src/tfidf/stop-words/stop-words-english4.txt  | 671 ++++++++++++++++
 src/tfidf/stop-words/stop-words-english5.txt  | 319 ++++++++
 src/tfidf/stop-words/stop-words-finnish.txt   | 747 ++++++++++++++++++
 src/tfidf/stop-words/stop-words-french.txt    | 126 +++
 src/tfidf/stop-words/stop-words-german.txt    | 129 +++
 src/tfidf/stop-words/stop-words-greek.txt     |  79 ++
 src/tfidf/stop-words/stop-words-hungarian.txt |  35 +
 src/tfidf/stop-words/stop-words-italian.txt   | 134 ++++
 src/tfidf/stop-words/stop-words-norwegian.txt | 119 +++
 src/tfidf/stop-words/stop-words-polish1.txt   | 138 ++++
 src/tfidf/stop-words/stop-words-polish2.txt   | 272 +++++++
 src/tfidf/stop-words/stop-words-portugese.txt | 147 ++++
 src/tfidf/stop-words/stop-words-russian.txt   | 421 ++++++++++
 src/tfidf/stop-words/stop-words-slovak.txt    | 173 ++++
 src/tfidf/stop-words/stop-words-slovak2.txt   | 106 +++
 src/tfidf/stop-words/stop-words-spanish.txt   | 181 +++++
 src/tfidf/stop-words/stop-words-swedish.txt   | 386 +++++++++
 src/tfidf/stop-words/stop-words-turkish.txt   | 114 +++
 src/tfidf/tfidf.go                            | 182 +++++
 test.go                                       |  15 +
 31 files changed, 6192 insertions(+)
 create mode 100644 .gitignore
 create mode 100644 README.md
 create mode 100644 main.go
 create mode 100644 src/tfidf/stop-words/stop-words-arabic.txt
 create mode 100644 src/tfidf/stop-words/stop-words-catalian.txt
 create mode 100644 src/tfidf/stop-words/stop-words-czech1.txt
 create mode 100644 src/tfidf/stop-words/stop-words-czech2.txt
 create mode 100644 src/tfidf/stop-words/stop-words-dutch.txt
 create mode 100644 src/tfidf/stop-words/stop-words-english1.txt
 create mode 100644 src/tfidf/stop-words/stop-words-english2.txt
 create mode 100644 src/tfidf/stop-words/stop-words-english3-google.txt
 create mode 100644 src/tfidf/stop-words/stop-words-english4.txt
 create mode 100644 src/tfidf/stop-words/stop-words-english5.txt
 create mode 100644 src/tfidf/stop-words/stop-words-finnish.txt
 create mode 100644 src/tfidf/stop-words/stop-words-french.txt
 create mode 100644 src/tfidf/stop-words/stop-words-german.txt
 create mode 100644 src/tfidf/stop-words/stop-words-greek.txt
 create mode 100644 src/tfidf/stop-words/stop-words-hungarian.txt
 create mode 100644 src/tfidf/stop-words/stop-words-italian.txt
 create mode 100644 src/tfidf/stop-words/stop-words-norwegian.txt
 create mode 100644 src/tfidf/stop-words/stop-words-polish1.txt
 create mode 100644 src/tfidf/stop-words/stop-words-polish2.txt
 create mode 100644 src/tfidf/stop-words/stop-words-portugese.txt
 create mode 100644 src/tfidf/stop-words/stop-words-russian.txt
 create mode 100644 src/tfidf/stop-words/stop-words-slovak.txt
 create mode 100644 src/tfidf/stop-words/stop-words-slovak2.txt
 create mode 100644 src/tfidf/stop-words/stop-words-spanish.txt
 create mode 100644 src/tfidf/stop-words/stop-words-swedish.txt
 create mode 100644 src/tfidf/stop-words/stop-words-turkish.txt
 create mode 100644 src/tfidf/tfidf.go
 create mode 100644 test.go

diff --git a/.gitignore b/.gitignore
new file mode 100644
index 0000000..0be49ff
--- /dev/null
+++ b/.gitignore
@@ -0,0 +1,3 @@
+*.swp
+main
+websites.txt
diff --git a/README.md b/README.md
new file mode 100644
index 0000000..e69de29
diff --git a/main.go b/main.go
new file mode 100644
index 0000000..463dc99
--- /dev/null
+++ b/main.go
@@ -0,0 +1,208 @@
+package main
+
+import (
+	"fmt"
+	"io/ioutil"
+	"net/http"
+	"regexp"
+	"strings"
+    "os"
+	"tfidf"
+)
+
+func getLinks(text, mainUrl string) []string {
+	result := make([]string, 0)
+	hrefLocator, _ := regexp.Compile("href=(\"|').*?(\"|')")
+
+	elems := hrefLocator.FindAllString(text, -1)
+
+	for _, link := range elems {
+		temp := strings.Replace(link, "href=", "", -1)
+		temp = strings.Replace(temp, "\"", "", -1)
+		temp = strings.Replace(temp, "'", "", -1)
+
+		switch {
+		case strings.Contains(temp, ".png"):
+			continue
+		case strings.Contains(temp, ".jpg"):
+			continue
+		case strings.Contains(temp, ".gif"):
+			continue
+		case strings.Contains(temp, ".xml"):
+			continue
+		case strings.Contains(temp, ".css"):
+			continue
+		case strings.Contains(temp, ".js"):
+			continue
+		case !strings.Contains(temp, mainUrl):
+			continue
+		default:
+			result = append(result, temp)
+		}
+
+	}
+
+	return result
+}
+
+func fetchAndGetLinks(url string, output chan []string) {
+	result := make([]string, 0)
+
+	resp, err := http.Get(url)
+
+	if err != nil {
+		output <- result
+		return
+	}
+
+	body, err := ioutil.ReadAll(resp.Body)
+
+	defer resp.Body.Close()
+
+	if err != nil {
+		output <- result
+		return
+	}
+
+	links := getLinks(string(body), url)
+	output <- links
+
+}
+
+func fetchText(url string, output chan []string) {
+	resp, err := http.Get(url)
+	if err != nil {
+		output <- nil
+		return
+	}
+
+	defer resp.Body.Close()
+
+	body, err := ioutil.ReadAll(resp.Body)
+	if err != nil {
+		output <- nil
+		return
+	}
+
+	if strings.Contains(string(body), "<html") && strings.Contains(string(body), "<body") {
+		output <- []string{url, tfidf.ClearHtml(string(body))}
+	} else {
+		output <- nil
+	}
+}
+
+func getDocuments(websites []string) ([]string, []string) {
+	allDocsUris := make([]string, 0)               // Initial, empty
+	allDocsUris = append(allDocsUris, websites...) // The index page IS a document
+	results := make([]string, 0)
+	sites := make([]string, 0)
+	webChannel := make(chan []string, 10)
+	textChannel := make(chan []string, 10)
+
+	fmt.Println("Initial link parsing...")
+
+	for _, url := range websites {
+		fmt.Printf("Fetching: %s\n", url)
+		go fetchAndGetLinks(url, webChannel)
+	}
+
+	for count := 0; count < len(websites); count++ {
+		links := <-webChannel
+		fmt.Printf("Received %d links...\n", len(links))
+		allDocsUris = append(allDocsUris, links...)
+	}
+
+	fmt.Printf("Now fetching texts from %d urls\n", len(allDocsUris))
+
+	for count, url := range allDocsUris {
+		fmt.Printf("%d of %d - Fetching: %s\n", count, len(allDocsUris), url)
+		go fetchText(url, textChannel)
+	}
+
+	for count := 0; count < len(allDocsUris); count++ {
+		fmt.Printf("Received %d web pages.\n", count)
+		text := <-textChannel
+		if text != nil {
+			sites = append(sites, text[0])
+			results = append(results, text[1])
+		}
+	}
+
+	return results, sites
+}
+
+func loadWebsites(filename string) []string {
+    content, err := ioutil.ReadFile(filename)
+    if err != nil {
+        fmt.Println(err)
+        return nil
+    }
+
+    elements := strings.Fields(string(content))
+    fmt.Printf("Loaded %d websites", len(elements))
+
+    return elements
+}
+
+func getCommandLineArgument(option, defaultValue string) string {
+    result := defaultValue
+    if len(os.Args) > 1 {
+        for count := 1; count < len(os.Args); count++ {
+            if strings.Contains(os.Args[count], option) {
+                result = os.Args[count]
+                result = strings.Replace(result, option, "", -1)
+                result = strings.TrimSpace(result)
+
+                if result == "" {
+                    result = os.Args[count + 1]
+                    result = strings.Replace(result, option, "", -1)
+                    result = strings.TrimSpace(result)
+                }
+                break
+            }
+        }
+    }
+
+    return result
+}
+
+func getWebsitesArgument() string {
+    return getCommandLineArgument("-w", "websites.txt")
+}
+
+func getStopWordsArgument() string {
+    return getCommandLineArgument("-s", "english1")
+}
+
+func main() {
+	var searchTerm string
+	var matrix tfidf.TfIdfMatrix
+
+	fmt.Println("Init the TfIdf with stopwords")
+
+    stopwordsLanguage := getStopWordsArgument()
+	matrix.LoadStopWords(fmt.Sprintf("./src/tfidf/stop-words/stop-words-%s.txt", stopwordsLanguage))
+
+	websites := loadWebsites(getWebsitesArgument())
+
+	input, sites := getDocuments(websites)
+
+	matrix.TfIdf(input)
+
+	running := true
+
+	for running {
+		fmt.Println("Introduzca término de búsqueda o q para salir:")
+		fmt.Scanf("%s", &searchTerm)
+
+		if searchTerm != "q" {
+			results, percentages := matrix.SearchDocumentsByWord(searchTerm)
+			fmt.Println("Resultados:")
+			for c, value := range results {
+				fmt.Printf("%d: %.2f%% - %s\n", c, percentages[c] * 10.0, sites[value])
+			}
+		} else {
+			running = false
+		}
+	}
+}
diff --git a/src/tfidf/stop-words/stop-words-arabic.txt b/src/tfidf/stop-words/stop-words-arabic.txt
new file mode 100644
index 0000000..c547d07
--- /dev/null
+++ b/src/tfidf/stop-words/stop-words-arabic.txt
@@ -0,0 +1,162 @@
+فى
+في
+كل
+لم
+لن
+له
+من
+هو
+هي
+قوة
+كما
+لها
+منذ
+وقد
+ولا
+نفسه
+لقاء
+مقابل
+هناك
+وقال
+وكان
+نهاية
+وقالت
+وكانت
+للامم
+فيه
+كلم
+لكن
+وفي
+وقف
+ولم
+ومن
+وهو
+وهي
+يوم
+فيها
+منها
+مليار
+لوكالة
+يكون
+يمكن
+مليون
+حيث
+اكد
+الا
+اما
+امس
+السابق
+التى
+التي
+اكثر
+ايار
+ايضا
+ثلاثة
+الذاتي
+الاخيرة
+الثاني
+الثانية
+الذى
+الذي
+الان
+امام
+ايام
+خلال
+حوالى
+الذين
+الاول
+الاولى
+بين
+ذلك
+دون
+حول
+حين
+الف
+الى
+انه
+اول
+ضمن
+انها
+جميع
+الماضي
+الوقت
+المقبل
+اليوم
+ـ
+ف
+و
+و6
+قد
+لا
+ما
+مع
+مساء
+هذا
+واحد
+واضاف
+واضافت
+فان
+قبل
+قال
+كان
+لدى
+نحو
+هذه
+وان
+واكد
+كانت
+واوضح
+مايو
+ب
+ا
+أ
+،
+عشر
+عدد
+عدة
+عشرة
+عدم
+عام
+عاما
+عن
+عند
+عندما
+على
+عليه
+عليها
+زيارة
+سنة
+سنوات
+تم
+ضد
+بعد
+بعض
+اعادة
+اعلنت
+بسبب
+حتى
+اذا
+احد
+اثر
+برس
+باسم
+غدا
+شخصا
+صباح
+اطار
+اربعة
+اخرى
+بان
+اجل
+غير
+بشكل
+حاليا
+بن
+به
+ثم
+اف
+ان
+او
+اي
+بها
+صفر
diff --git a/src/tfidf/stop-words/stop-words-catalian.txt b/src/tfidf/stop-words/stop-words-catalian.txt
new file mode 100644
index 0000000..7479f08
--- /dev/null
+++ b/src/tfidf/stop-words/stop-words-catalian.txt
@@ -0,0 +1,126 @@
+a
+abans
+algun
+alguna
+algunes
+alguns
+altre
+amb
+ambdós
+anar
+ans
+aquell
+aquelles
+aquells
+aquí
+bastant
+bé
+cada
+com
+consegueixo
+conseguim
+conseguir
+consigueix
+consigueixen
+consigueixes
+dalt
+de
+des de
+dins
+el
+elles
+ells
+els
+en
+ens
+entre
+era
+erem
+eren
+eres
+es
+és
+éssent
+està
+estan
+estat
+estava
+estem
+esteu
+estic
+ets
+fa
+faig
+fan
+fas
+fem
+fer
+feu
+fi
+haver
+i
+inclòs
+jo
+la
+les
+llarg
+llavors
+mentre
+meu
+mode
+molt
+molts
+nosaltres
+o
+on
+per
+per
+per que
+però
+perquè
+podem
+poden
+poder
+podeu
+potser
+primer
+puc
+quan
+quant
+qui
+sabem
+saben
+saber
+sabeu
+sap
+saps
+sense
+ser
+seu
+seus
+si
+soc
+solament
+sols
+som
+sota
+també
+te
+tene
+tenim
+tenir
+teniu
+teu
+tinc
+tot
+últim
+un
+un
+una
+unes
+uns
+ús
+va
+vaig
+van
+vosaltres
diff --git a/src/tfidf/stop-words/stop-words-czech1.txt b/src/tfidf/stop-words/stop-words-czech1.txt
new file mode 100644
index 0000000..6582cd9
--- /dev/null
+++ b/src/tfidf/stop-words/stop-words-czech1.txt
@@ -0,0 +1,138 @@
+aby
+aj
+ale
+ani
+asi
+az
+bez
+bude
+budem
+budes
+by
+byl
+byla
+byli
+bylo
+byt
+ci
+clanek
+clanku
+clanky
+co
+coz
+cz
+dalsi
+design
+dnes
+do
+email
+ho
+jak
+jako
+je
+jeho
+jej
+jeji
+jejich
+jen
+jeste
+ji
+jine
+jiz
+jsem
+jses
+jsme
+jsou
+jste
+kam
+kde
+kdo
+kdyz
+ke
+ktera
+ktere
+kteri
+kterou
+ktery
+ma
+mate
+mezi
+mi
+mit
+muj
+muze
+na
+nad
+nam
+napiste
+nas
+nasi
+ne
+nebo
+nejsou
+neni
+nez
+nic
+nove
+novy
+od
+pak
+po
+pod
+podle
+pokud
+pouze
+prave
+pred
+pres
+pri
+pro
+proc
+proto
+protoze
+prvni
+pta
+re
+si
+strana
+sve
+svych
+svym
+svymi
+ta
+tak
+take
+takze
+tato
+tedy
+tema
+ten
+tento
+teto
+tim
+timto
+tipy
+to
+tohle
+toho
+tohoto
+tom
+tomto
+tomuto
+tu
+tuto
+ty
+tyto
+uz
+vam
+vas
+vase
+ve
+vice
+vsak
+za
+zda
+zde
+ze
+zpet
+zpravy
diff --git a/src/tfidf/stop-words/stop-words-czech2.txt b/src/tfidf/stop-words/stop-words-czech2.txt
new file mode 100644
index 0000000..809e9fe
--- /dev/null
+++ b/src/tfidf/stop-words/stop-words-czech2.txt
@@ -0,0 +1,172 @@
+a
+aby
+aj
+ale
+ani
+aniž
+ano
+asi
+až
+bez
+bude
+budem
+budeš
+by
+byl
+byla
+byli
+bylo
+být
+co
+což
+cz
+či
+článek
+článku
+články
+další
+dnes
+do
+ho
+i
+já
+jak
+jako
+je
+jeho
+jej
+její
+jejich
+jen
+jenž
+ještě
+ji
+jiné
+již
+jsem
+jseš
+jsme
+jsou
+jšte
+k
+kam
+každý
+kde
+kdo
+když
+ke
+která
+které
+kterou
+který
+kteři
+ku
+ma
+máte
+me
+mě
+mezi
+mi
+mít
+mně
+mnou
+můj
+může
+my
+na
+ná
+nad
+nám
+napište
+náš
+naši
+ne
+nebo
+nechť
+nejsou
+není
+než
+ní
+nic
+nové
+nový
+o
+od
+ode
+on
+pak
+po
+pod
+podle
+pokud
+pouze
+práve
+pro
+proč
+proto
+protože
+první
+před
+přede
+přes
+při
+pta
+re
+s
+se
+si
+sice
+strana
+své
+svůj
+svých
+svým
+svými
+ta
+tak
+také
+takže
+tato
+te
+tě
+tedy
+těma
+ten
+tento
+této 
+tím
+tímto
+tipy
+to
+to
+tohle
+toho
+tohoto
+tom
+tomto
+tomuto
+toto
+tu
+tuto
+tvůj
+ty
+tyto
+u
+už
+v
+vám
+váš
+vaše
+ve
+více
+však
+všechen
+vy
+z
+za
+zda
+zde
+ze
+zpět
+zprávy
+že
diff --git a/src/tfidf/stop-words/stop-words-dutch.txt b/src/tfidf/stop-words/stop-words-dutch.txt
new file mode 100644
index 0000000..37c2ba9
--- /dev/null
+++ b/src/tfidf/stop-words/stop-words-dutch.txt
@@ -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
diff --git a/src/tfidf/stop-words/stop-words-english1.txt b/src/tfidf/stop-words/stop-words-english1.txt
new file mode 100644
index 0000000..6e8c2fb
--- /dev/null
+++ b/src/tfidf/stop-words/stop-words-english1.txt
@@ -0,0 +1,635 @@
+able
+about
+above
+abroad
+according
+accordingly
+across
+actually
+adj
+after
+afterwards
+again
+against
+ago
+ahead
+ain't
+all
+allow
+allows
+almost
+alone
+along
+alongside
+already
+also
+although
+always
+am
+amid
+amidst
+among
+amongst
+an
+and
+another
+any
+anybody
+anyhow
+anyone
+anything
+anyway
+anyways
+anywhere
+apart
+appear
+appreciate
+appropriate
+are
+aren't
+around
+as
+a's
+aside
+ask
+asking
+associated
+at
+available
+away
+awfully
+back
+backward
+backwards
+be
+became
+because
+become
+becomes
+becoming
+been
+before
+beforehand
+begin
+behind
+being
+believe
+below
+beside
+besides
+best
+better
+between
+beyond
+both
+brief
+but
+by
+came
+can
+cannot
+cant
+can't
+caption
+cause
+causes
+certain
+certainly
+changes
+clearly
+c'mon
+co
+co.
+com
+come
+comes
+concerning
+consequently
+consider
+considering
+contain
+containing
+contains
+corresponding
+could
+couldn't
+course
+c's
+currently
+dare
+daren't
+definitely
+described
+despite
+did
+didn't
+different
+directly
+do
+does
+doesn't
+doing
+done
+don't
+down
+downwards
+during
+each
+edu
+eg
+eight
+eighty
+either
+else
+elsewhere
+end
+ending
+enough
+entirely
+especially
+et
+etc
+even
+ever
+evermore
+every
+everybody
+everyone
+everything
+everywhere
+ex
+exactly
+example
+except
+fairly
+far
+farther
+few
+fewer
+fifth
+first
+five
+followed
+following
+follows
+for
+forever
+former
+formerly
+forth
+forward
+found
+four
+from
+further
+furthermore
+get
+gets
+getting
+given
+gives
+go
+goes
+going
+gone
+got
+gotten
+greetings
+had
+hadn't
+half
+happens
+hardly
+has
+hasn't
+have
+haven't
+having
+he
+he'd
+he'll
+hello
+help
+hence
+her
+here
+hereafter
+hereby
+herein
+here's
+hereupon
+hers
+herself
+he's
+hi
+him
+himself
+his
+hither
+hopefully
+how
+howbeit
+however
+hundred
+i'd
+ie
+if
+ignored
+i'll
+i'm
+immediate
+in
+inasmuch
+inc
+inc.
+indeed
+indicate
+indicated
+indicates
+inner
+inside
+insofar
+instead
+into
+inward
+is
+isn't
+it
+it'd
+it'll
+its
+it's
+itself
+i've
+just
+k
+keep
+keeps
+kept
+know
+known
+knows
+last
+lately
+later
+latter
+latterly
+least
+less
+lest
+let
+let's
+like
+liked
+likely
+likewise
+little
+look
+looking
+looks
+low
+lower
+ltd
+made
+mainly
+make
+makes
+many
+may
+maybe
+mayn't
+me
+mean
+meantime
+meanwhile
+merely
+might
+mightn't
+mine
+minus
+miss
+more
+moreover
+most
+mostly
+mr
+mrs
+much
+must
+mustn't
+my
+myself
+name
+namely
+nd
+near
+nearly
+necessary
+need
+needn't
+needs
+neither
+never
+neverf
+neverless
+nevertheless
+new
+next
+nine
+ninety
+no
+nobody
+non
+none
+nonetheless
+noone
+no-one
+nor
+normally
+not
+nothing
+notwithstanding
+novel
+now
+nowhere
+obviously
+of
+off
+often
+oh
+ok
+okay
+old
+on
+once
+one
+ones
+one's
+only
+onto
+opposite
+or
+other
+others
+otherwise
+ought
+oughtn't
+our
+ours
+ourselves
+out
+outside
+over
+overall
+own
+particular
+particularly
+past
+per
+perhaps
+placed
+please
+plus
+possible
+presumably
+probably
+provided
+provides
+que
+quite
+qv
+rather
+rd
+re
+really
+reasonably
+recent
+recently
+regarding
+regardless
+regards
+relatively
+respectively
+right
+round
+said
+same
+saw
+say
+saying
+says
+second
+secondly
+see
+seeing
+seem
+seemed
+seeming
+seems
+seen
+self
+selves
+sensible
+sent
+serious
+seriously
+seven
+several
+shall
+shan't
+she
+she'd
+she'll
+she's
+should
+shouldn't
+since
+six
+so
+some
+somebody
+someday
+somehow
+someone
+something
+sometime
+sometimes
+somewhat
+somewhere
+soon
+sorry
+specified
+specify
+specifying
+still
+sub
+such
+sup
+sure
+take
+taken
+taking
+tell
+tends
+th
+than
+thank
+thanks
+thanx
+that
+that'll
+thats
+that's
+that've
+the
+their
+theirs
+them
+themselves
+then
+thence
+there
+thereafter
+thereby
+there'd
+therefore
+therein
+there'll
+there're
+theres
+there's
+thereupon
+there've
+these
+they
+they'd
+they'll
+they're
+they've
+thing
+things
+think
+third
+thirty
+this
+thorough
+thoroughly
+those
+though
+three
+through
+throughout
+thru
+thus
+till
+to
+together
+too
+took
+toward
+towards
+tried
+tries
+truly
+try
+trying
+t's
+twice
+two
+un
+under
+underneath
+undoing
+unfortunately
+unless
+unlike
+unlikely
+until
+unto
+up
+upon
+upwards
+us
+use
+used
+useful
+uses
+using
+usually
+v
+value
+various
+versus
+very
+via
+viz
+vs
+want
+wants
+was
+wasn't
+way
+we
+we'd
+welcome
+well
+we'll
+went
+were
+we're
+weren't
+we've
+what
+whatever
+what'll
+what's
+what've
+when
+whence
+whenever
+where
+whereafter
+whereas
+whereby
+wherein
+where's
+whereupon
+wherever
+whether
+which
+whichever
+while
+whilst
+whither
+who
+who'd
+whoever
+whole
+who'll
+whom
+whomever
+who's
+whose
+why
+will
+willing
+wish
+with
+within
+without
+wonder
+won't
+would
+wouldn't
+yes
+yet
+you
+you'd
+you'll
+your
+you're
+yours
+yourself
+yourselves
+you've
+zero
diff --git a/src/tfidf/stop-words/stop-words-english2.txt b/src/tfidf/stop-words/stop-words-english2.txt
new file mode 100644
index 0000000..2a674a0
--- /dev/null
+++ b/src/tfidf/stop-words/stop-words-english2.txt
@@ -0,0 +1,174 @@
+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'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
diff --git a/src/tfidf/stop-words/stop-words-english3-google.txt b/src/tfidf/stop-words/stop-words-english3-google.txt
new file mode 100644
index 0000000..b8c36dd
--- /dev/null
+++ b/src/tfidf/stop-words/stop-words-english3-google.txt
@@ -0,0 +1,32 @@
+I
+a
+about
+an
+are
+as
+at
+be
+by
+com
+for
+from
+how
+in
+is
+it
+of
+on
+or
+that
+the
+this
+to
+was
+what
+when
+where
+who
+will
+with
+the
+www
diff --git a/src/tfidf/stop-words/stop-words-english4.txt b/src/tfidf/stop-words/stop-words-english4.txt
new file mode 100644
index 0000000..699306a
--- /dev/null
+++ b/src/tfidf/stop-words/stop-words-english4.txt
@@ -0,0 +1,671 @@
+a
+able
+about
+above
+abst
+accordance
+according
+accordingly
+across
+act
+actually
+added
+adj
+adopted
+affected
+affecting
+affects
+after
+afterwards
+again
+against
+ah
+all
+almost
+alone
+along
+already
+also
+although
+always
+am
+among
+amongst
+an
+and
+announce
+another
+any
+anybody
+anyhow
+anymore
+anyone
+anything
+anyway
+anyways
+anywhere
+apparently
+approximately
+are
+aren
+arent
+arise
+around
+as
+aside
+ask
+asking
+at
+auth
+available
+away
+awfully
+b
+back
+be
+became
+because
+become
+becomes
+becoming
+been
+before
+beforehand
+begin
+beginning
+beginnings
+begins
+behind
+being
+believe
+below
+beside
+besides
+between
+beyond
+biol
+both
+brief
+briefly
+but
+by
+c
+ca
+came
+can
+cannot
+can't
+cause
+causes
+certain
+certainly
+co
+com
+come
+comes
+contain
+containing
+contains
+could
+couldnt
+d
+date
+did
+didn't
+different
+do
+does
+doesn't
+doing
+done
+don't
+down
+downwards
+due
+during
+e
+each
+ed
+edu
+effect
+eg
+eight
+eighty
+either
+else
+elsewhere
+end
+ending
+enough
+especially
+et
+et-al
+etc
+even
+ever
+every
+everybody
+everyone
+everything
+everywhere
+ex
+except
+f
+far
+few
+ff
+fifth
+first
+five
+fix
+followed
+following
+follows
+for
+former
+formerly
+forth
+found
+four
+from
+further
+furthermore
+g
+gave
+get
+gets
+getting
+give
+given
+gives
+giving
+go
+goes
+gone
+got
+gotten
+h
+had
+happens
+hardly
+has
+hasn't
+have
+haven't
+having
+he
+hed
+hence
+her
+here
+hereafter
+hereby
+herein
+heres
+hereupon
+hers
+herself
+hes
+hi
+hid
+him
+himself
+his
+hither
+home
+how
+howbeit
+however
+hundred
+i
+id
+ie
+if
+i'll
+im
+immediate
+immediately
+importance
+important
+in
+inc
+indeed
+index
+information
+instead
+into
+invention
+inward
+is
+isn't
+it
+itd
+it'll
+its
+itself
+i've
+j
+just
+k
+keep
+keeps
+kept
+keys
+kg
+km
+know
+known
+knows
+l
+largely
+last
+lately
+later
+latter
+latterly
+least
+less
+lest
+let
+lets
+like
+liked
+likely
+line
+little
+'ll
+look
+looking
+looks
+ltd
+m
+made
+mainly
+make
+makes
+many
+may
+maybe
+me
+mean
+means
+meantime
+meanwhile
+merely
+mg
+might
+million
+miss
+ml
+more
+moreover
+most
+mostly
+mr
+mrs
+much
+mug
+must
+my
+myself
+n
+na
+name
+namely
+nay
+nd
+near
+nearly
+necessarily
+necessary
+need
+needs
+neither
+never
+nevertheless
+new
+next
+nine
+ninety
+no
+nobody
+non
+none
+nonetheless
+noone
+nor
+normally
+nos
+not
+noted
+nothing
+now
+nowhere
+o
+obtain
+obtained
+obviously
+of
+off
+often
+oh
+ok
+okay
+old
+omitted
+on
+once
+one
+ones
+only
+onto
+or
+ord
+other
+others
+otherwise
+ought
+our
+ours
+ourselves
+out
+outside
+over
+overall
+owing
+own
+p
+page
+pages
+part
+particular
+particularly
+past
+per
+perhaps
+placed
+please
+plus
+poorly
+possible
+possibly
+potentially
+pp
+predominantly
+present
+previously
+primarily
+probably
+promptly
+proud
+provides
+put
+q
+que
+quickly
+quite
+qv
+r
+ran
+rather
+rd
+re
+readily
+really
+recent
+recently
+ref
+refs
+regarding
+regardless
+regards
+related
+relatively
+research
+respectively
+resulted
+resulting
+results
+right
+run
+s
+said
+same
+saw
+say
+saying
+says
+sec
+section
+see
+seeing
+seem
+seemed
+seeming
+seems
+seen
+self
+selves
+sent
+seven
+several
+shall
+she
+shed
+she'll
+shes
+should
+shouldn't
+show
+showed
+shown
+showns
+shows
+significant
+significantly
+similar
+similarly
+since
+six
+slightly
+so
+some
+somebody
+somehow
+someone
+somethan
+something
+sometime
+sometimes
+somewhat
+somewhere
+soon
+sorry
+specifically
+specified
+specify
+specifying
+state
+states
+still
+stop
+strongly
+sub
+substantially
+successfully
+such
+sufficiently
+suggest
+sup
+sure
+t
+take
+taken
+taking
+tell
+tends
+th
+than
+thank
+thanks
+thanx
+that
+that'll
+thats
+that've
+the
+their
+theirs
+them
+themselves
+then
+thence
+there
+thereafter
+thereby
+thered
+therefore
+therein
+there'll
+thereof
+therere
+theres
+thereto
+thereupon
+there've
+these
+they
+theyd
+they'll
+theyre
+they've
+think
+this
+those
+thou
+though
+thoughh
+thousand
+throug
+through
+throughout
+thru
+thus
+til
+tip
+to
+together
+too
+took
+toward
+towards
+tried
+tries
+truly
+try
+trying
+ts
+twice
+two
+u
+un
+under
+unfortunately
+unless
+unlike
+unlikely
+until
+unto
+up
+upon
+ups
+us
+use
+used
+useful
+usefully
+usefulness
+uses
+using
+usually
+v
+value
+various
+'ve
+very
+via
+viz
+vol
+vols
+vs
+w
+want
+wants
+was
+wasn't
+way
+we
+wed
+welcome
+we'll
+went
+were
+weren't
+we've
+what
+whatever
+what'll
+whats
+when
+whence
+whenever
+where
+whereafter
+whereas
+whereby
+wherein
+wheres
+whereupon
+wherever
+whether
+which
+while
+whim
+whither
+who
+whod
+whoever
+whole
+who'll
+whom
+whomever
+whos
+whose
+why
+widely
+willing
+wish
+with
+within
+without
+won't
+words
+world
+would
+wouldn't
+www
+x
+y
+yes
+yet
+you
+youd
+you'll
+your
+youre
+yours
+yourself
+yourselves
+you've
+z
+zero
diff --git a/src/tfidf/stop-words/stop-words-english5.txt b/src/tfidf/stop-words/stop-words-english5.txt
new file mode 100644
index 0000000..b8ad594
--- /dev/null
+++ b/src/tfidf/stop-words/stop-words-english5.txt
@@ -0,0 +1,319 @@
+a
+about
+above
+across
+after
+afterwards
+again
+against
+all
+almost
+alone
+along
+already
+also
+although
+always
+am
+among
+amongst
+amoungst
+amount
+an
+and
+another
+any
+anyhow
+anyone
+anything
+anyway
+anywhere
+are
+around
+as
+at
+back
+be
+became
+because
+become
+becomes
+becoming
+been
+before
+beforehand
+behind
+being
+below
+beside
+besides
+between
+beyond
+bill
+both
+bottom
+but
+by
+call
+can
+cannot
+cant
+co
+computer
+con
+could
+couldnt
+cry
+de
+describe
+detail
+do
+done
+down
+due
+during
+each
+eg
+eight
+either
+eleven
+else
+elsewhere
+empty
+enough
+etc
+even
+ever
+every
+everyone
+everything
+everywhere
+except
+few
+fifteen
+fify
+fill
+find
+fire
+first
+five
+for
+former
+formerly
+forty
+found
+four
+from
+front
+full
+further
+get
+give
+go
+had
+has
+hasnt
+have
+he
+hence
+her
+here
+hereafter
+hereby
+herein
+hereupon
+hers
+herse”
+him
+himse”
+his
+how
+however
+hundred
+i
+ie
+if
+in
+inc
+indeed
+interest
+into
+is
+it
+its
+itse”
+keep
+last
+latter
+latterly
+least
+less
+ltd
+made
+many
+may
+me
+meanwhile
+might
+mill
+mine
+more
+moreover
+most
+mostly
+move
+much
+must
+my
+myse”
+name
+namely
+neither
+never
+nevertheless
+next
+nine
+no
+nobody
+none
+noone
+nor
+not
+nothing
+now
+nowhere
+of
+off
+often
+on
+once
+one
+only
+onto
+or
+other
+others
+otherwise
+our
+ours
+ourselves
+out
+over
+own
+part
+per
+perhaps
+please
+put
+rather
+re
+same
+see
+seem
+seemed
+seeming
+seems
+serious
+several
+she
+should
+show
+side
+since
+sincere
+six
+sixty
+so
+some
+somehow
+someone
+something
+sometime
+sometimes
+somewhere
+still
+such
+system
+take
+ten
+than
+that
+the
+their
+them
+themselves
+then
+thence
+there
+thereafter
+thereby
+therefore
+therein
+thereupon
+these
+they
+thick
+thin
+third
+this
+those
+though
+three
+through
+throughout
+thru
+thus
+to
+together
+too
+top
+toward
+towards
+twelve
+twenty
+two
+un
+under
+until
+up
+upon
+us
+very
+via
+was
+we
+well
+were
+what
+whatever
+when
+whence
+whenever
+where
+whereafter
+whereas
+whereby
+wherein
+whereupon
+wherever
+whether
+which
+while
+whither
+who
+whoever
+whole
+whom
+whose
+why
+will
+with
+within
+without
+would
+yet
+you
+your
+yours
+yourself
+yourselves
diff --git a/src/tfidf/stop-words/stop-words-finnish.txt b/src/tfidf/stop-words/stop-words-finnish.txt
new file mode 100644
index 0000000..7f5742e
--- /dev/null
+++ b/src/tfidf/stop-words/stop-words-finnish.txt
@@ -0,0 +1,747 @@
+aiemmin
+aika
+aikaa
+aikaan
+aikaisemmin
+aikaisin
+aikajen
+aikana
+aikoina
+aikoo
+aikovat
+aina
+ainakaan
+ainakin
+ainoa
+ainoat
+aiomme
+aion
+aiotte
+aist
+aivan
+ajan
+älä
+alas
+alemmas
+älköön
+alkuisin
+alkuun
+alla
+alle
+aloitamme
+aloitan
+aloitat
+aloitatte
+aloitattivat
+aloitettava
+aloitettevaksi
+aloitettu
+aloitimme
+aloitin
+aloitit
+aloititte
+aloittaa
+aloittamatta
+aloitti
+aloittivat
+alta
+aluksi
+alussa
+alusta
+annettavaksi
+annetteva
+annettu
+antaa
+antamatta
+antoi
+aoua
+apu
+asia
+asiaa
+asian
+asiasta
+asiat
+asioiden
+asioihin
+asioita
+asti
+avuksi
+avulla
+avun
+avutta
+edellä
+edelle
+edelleen
+edeltä
+edemmäs
+edes
+edessä
+edestä
+ehkä
+ei
+eikä
+eilen
+eivät
+eli
+ellei
+elleivät
+ellemme
+ellen
+ellet
+ellette
+emme
+en
+enää
+enemmän
+eniten
+ennen
+ensi
+ensimmäinen
+ensimmäiseksi
+ensimmäisen
+ensimmäisenä
+ensimmäiset
+ensimmäisiä
+ensimmäisiksi
+ensimmäisinä
+ensimmäistä
+ensin
+entinen
+entisen
+entisiä
+entistä
+entisten
+eräät
+eräiden
+eräs
+eri
+erittäin
+erityisesti
+esi
+esiin
+esillä
+esimerkiksi
+et
+eteen
+etenkin
+että
+ette
+ettei
+halua
+haluaa
+haluamatta
+haluamme
+haluan
+haluat
+haluatte
+haluavat
+halunnut
+halusi
+halusimme
+halusin
+halusit
+halusitte
+halusivat
+halutessa
+haluton
+hän
+häneen
+hänellä
+hänelle
+häneltä
+hänen
+hänessä
+hänestä
+hänet
+he
+hei
+heidän
+heihin
+heille
+heiltä
+heissä
+heistä
+heitä
+helposti
+heti
+hetkellä
+hieman
+huolimatta
+huomenna
+hyvä
+hyvää
+hyvät
+hyviä
+hyvien
+hyviin
+hyviksi
+hyville
+hyviltä
+hyvin
+hyvinä
+hyvissä
+hyvistä
+ihan
+ilman
+ilmeisesti
+itse
+itseään
+itsensä
+ja
+jää
+jälkeen
+jälleen
+jo
+johon
+joiden
+joihin
+joiksi
+joilla
+joille
+joilta
+joissa
+joista
+joita
+joka
+jokainen
+jokin
+joko
+joku
+jolla
+jolle
+jolloin
+jolta
+jompikumpi
+jonka
+jonkin
+jonne
+joo
+jopa
+jos
+joskus
+jossa
+josta
+jota
+jotain
+joten
+jotenkin
+jotenkuten
+jotka
+jotta
+jouduimme
+jouduin
+jouduit
+jouduitte
+joudumme
+joudun
+joudutte
+joukkoon
+joukossa
+joukosta
+joutua
+joutui
+joutuivat
+joutumaan
+joutuu
+joutuvat
+juuri
+kahdeksan
+kahdeksannen
+kahdella
+kahdelle
+kahdelta
+kahden
+kahdessa
+kahdesta
+kahta
+kahteen
+kai
+kaiken
+kaikille
+kaikilta
+kaikkea
+kaikki
+kaikkia
+kaikkiaan
+kaikkialla
+kaikkialle
+kaikkialta
+kaikkien
+kaikkin
+kaksi
+kannalta
+kannattaa
+kanssa
+kanssaan
+kanssamme
+kanssani
+kanssanne
+kanssasi
+kauan
+kauemmas
+kautta
+kehen
+keiden
+keihin
+keiksi
+keillä
+keille
+keiltä
+keinä
+keissä
+keistä
+keitä
+keittä
+keitten
+keneen
+keneksi
+kenellä
+kenelle
+keneltä
+kenen
+kenenä
+kenessä
+kenestä
+kenet
+kenettä
+kennessästä
+kerran
+kerta
+kertaa
+kesken
+keskimäärin
+ketä
+ketkä
+kiitos
+kohti
+koko
+kokonaan
+kolmas
+kolme
+kolmen
+kolmesti
+koska
+koskaan
+kovin
+kuin
+kuinka
+kuitenkaan
+kuitenkin
+kuka
+kukaan
+kukin
+kumpainen
+kumpainenkaan
+kumpi
+kumpikaan
+kumpikin
+kun
+kuten
+kuuden
+kuusi
+kuutta
+kyllä
+kymmenen
+kyse
+lähekkäin
+lähellä
+lähelle
+läheltä
+lähemmäs
+lähes
+lähinnä
+lähtien
+läpi
+liian
+liki
+lisää
+lisäksi
+luo
+mahdollisimman
+mahdollista
+me
+meidän
+meillä
+meille
+melkein
+melko
+menee
+meneet
+menemme
+menen
+menet
+menette
+menevät
+meni
+menimme
+menin
+menit
+menivät
+mennessä
+mennyt
+menossa
+mihin
+mikä
+mikään
+mikäli
+mikin
+miksi
+milloin
+minä
+minne
+minun
+minut
+missä
+mistä
+mitä
+mitään
+miten
+moi
+molemmat
+mones
+monesti
+monet
+moni
+moniaalla
+moniaalle
+moniaalta
+monta
+muassa
+muiden
+muita
+muka
+mukaan
+mukaansa
+mukana
+mutta
+muu
+muualla
+muualle
+muualta
+muuanne
+muulloin
+muun
+muut
+muuta
+muutama
+muutaman
+muuten
+myöhemmin
+myös
+myöskään
+myöskin
+myötä
+näiden
+näin
+näissä
+näissähin
+näissälle
+näissältä
+näissästä
+näitä
+nämä
+ne
+neljä
+neljää
+neljän
+niiden
+niin
+niistä
+niitä
+noin
+nopeammin
+nopeasti
+nopeiten
+nro
+nuo
+nyt
+ohi
+oikein
+ole
+olemme
+olen
+olet
+olette
+oleva
+olevan
+olevat
+oli
+olimme
+olin
+olisi
+olisimme
+olisin
+olisit
+olisitte
+olisivat
+olit
+olitte
+olivat
+olla
+olleet
+olli
+ollut
+oma
+omaa
+omaan
+omaksi
+omalle
+omalta
+oman
+omassa
+omat
+omia
+omien
+omiin
+omiksi
+omille
+omilta
+omissa
+omista
+on
+onkin
+onko
+ovat
+päälle
+paikoittain
+paitsi
+pakosti
+paljon
+paremmin
+parempi
+parhaillaan
+parhaiten
+peräti
+perusteella
+pian
+pieneen
+pieneksi
+pienellä
+pienelle
+pieneltä
+pienempi
+pienestä
+pieni
+pienin
+puolesta
+puolestaan
+runsaasti
+saakka
+sadam
+sama
+samaa
+samaan
+samalla
+samallalta
+samallassa
+samallasta
+saman
+samat
+samoin
+sata
+sataa
+satojen
+se
+seitsemän
+sekä
+sen
+seuraavat
+siellä
+sieltä
+siihen
+siinä
+siis
+siitä
+sijaan
+siksi
+sillä
+silloin
+silti
+sinä
+sinne
+sinua
+sinulle
+sinulta
+sinun
+sinussa
+sinusta
+sinut
+sisäkkäin
+sisällä
+sitä
+siten
+sitten
+suoraan
+suuntaan
+suuren
+suuret
+suuri
+suuria
+suurin
+suurten
+taa
+täällä
+täältä
+taas
+taemmas
+tähän
+tahansa
+tai
+takaa
+takaisin
+takana
+takia
+tällä
+tällöin
+tämä
+tämän
+tänä
+tänään
+tänne
+tapauksessa
+tässä
+tästä
+tätä
+täten
+tavalla
+tavoitteena
+täysin
+täytyvät
+täytyy
+te
+tietysti
+todella
+toinen
+toisaalla
+toisaalle
+toisaalta
+toiseen
+toiseksi
+toisella
+toiselle
+toiselta
+toisemme
+toisen
+toisensa
+toisessa
+toisesta
+toista
+toistaiseksi
+toki
+tosin
+tuhannen
+tuhat
+tule
+tulee
+tulemme
+tulen
+tulet
+tulette
+tulevat
+tulimme
+tulin
+tulisi
+tulisimme
+tulisin
+tulisit
+tulisitte
+tulisivat
+tulit
+tulitte
+tulivat
+tulla
+tulleet
+tullut
+tuntuu
+tuo
+tuolla
+tuolloin
+tuolta
+tuonne
+tuskin
+tykö
+usea
+useasti
+useimmiten
+usein
+useita
+uudeksi
+uudelleen
+uuden
+uudet
+uusi
+uusia
+uusien
+uusinta
+uuteen
+uutta
+vaan
+vähän
+vähemmän
+vähintään
+vähiten
+vai
+vaiheessa
+vaikea
+vaikean
+vaikeat
+vaikeilla
+vaikeille
+vaikeilta
+vaikeissa
+vaikeista
+vaikka
+vain
+välillä
+varmasti
+varsin
+varsinkin
+varten
+vasta
+vastaan
+vastakkain
+verran
+vielä
+vierekkäin
+vieri
+viiden
+viime
+viimeinen
+viimeisen
+viimeksi
+viisi
+voi
+voidaan
+voimme
+voin
+voisi
+voit
+voitte
+voivat
+vuoden
+vuoksi
+vuosi
+vuosien
+vuosina
+vuotta
+yhä
+yhdeksän
+yhden
+yhdessä
+yhtä
+yhtäällä
+yhtäälle
+yhtäältä
+yhtään
+yhteen
+yhteensä
+yhteydessä
+yhteyteen
+yksi
+yksin
+yksittäin
+yleensä
+ylemmäs
+yli
+ylös
+ympäri
diff --git a/src/tfidf/stop-words/stop-words-french.txt b/src/tfidf/stop-words/stop-words-french.txt
new file mode 100644
index 0000000..b44c17d
--- /dev/null
+++ b/src/tfidf/stop-words/stop-words-french.txt
@@ -0,0 +1,126 @@
+alors
+au
+aucuns
+aussi
+autre
+avant
+avec
+avoir
+bon
+car
+ce
+cela
+ces
+ceux
+chaque
+ci
+comme
+comment
+dans
+des
+du
+dedans
+dehors
+depuis
+deux
+devrait
+doit
+donc
+dos
+droite
+début
+elle
+elles
+en
+encore
+essai
+est
+et
+eu
+fait
+faites
+fois
+font
+force
+haut
+hors
+ici
+il
+ils
+je
+juste
+la
+le
+les
+leur
+là
+ma
+maintenant
+mais
+mes
+mine
+moins
+mon
+mot
+même
+ni
+nommés
+notre
+nous
+nouveaux
+ou
+où
+par
+parce
+parole
+pas
+personnes
+peut
+peu
+pièce
+plupart
+pour
+pourquoi
+quand
+que
+quel
+quelle
+quelles
+quels
+qui
+sa
+sans
+ses
+seulement
+si
+sien
+son
+sont
+sous
+soyez
+sujet
+sur
+ta
+tandis
+tellement
+tels
+tes
+ton
+tous
+tout
+trop
+très
+tu
+valeur
+voie
+voient
+vont
+votre
+vous
+vu
+ça
+étaient
+état
+étions
+été
+être
diff --git a/src/tfidf/stop-words/stop-words-german.txt b/src/tfidf/stop-words/stop-words-german.txt
new file mode 100644
index 0000000..af52194
--- /dev/null
+++ b/src/tfidf/stop-words/stop-words-german.txt
@@ -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
diff --git a/src/tfidf/stop-words/stop-words-greek.txt b/src/tfidf/stop-words/stop-words-greek.txt
new file mode 100644
index 0000000..9e7eba3
--- /dev/null
+++ b/src/tfidf/stop-words/stop-words-greek.txt
@@ -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
diff --git a/src/tfidf/stop-words/stop-words-hungarian.txt b/src/tfidf/stop-words/stop-words-hungarian.txt
new file mode 100644
index 0000000..e23d97f
--- /dev/null
+++ b/src/tfidf/stop-words/stop-words-hungarian.txt
@@ -0,0 +1,35 @@
+a
+át
+az
+be
+csak
+de
+egy
+el
+én
+és
+fel
+hát
+hogy
+ide
+igen
+ki
+le
+lesz
+meg
+mi
+mint
+nem
+õ
+oda
+õk
+ön
+össze
+rá
+szét
+te
+ti
+vagy
+van
+vissza
+volt
diff --git a/src/tfidf/stop-words/stop-words-italian.txt b/src/tfidf/stop-words/stop-words-italian.txt
new file mode 100644
index 0000000..bdab8ac
--- /dev/null
+++ b/src/tfidf/stop-words/stop-words-italian.txt
@@ -0,0 +1,134 @@
+a
+adesso
+ai
+al
+alla
+allo
+allora
+altre
+altri
+altro
+anche
+ancora
+avere
+aveva
+avevano
+ben
+buono
+che
+chi
+cinque
+comprare
+con
+consecutivi
+consecutivo
+cosa
+cui
+da
+del
+della
+dello
+dentro
+deve
+devo
+di
+doppio
+due
+e
+ecco
+fare
+fine
+fino
+fra
+gente
+giu
+ha
+hai
+hanno
+ho
+il
+indietro
+invece
+io
+la
+lavoro
+le
+lei
+lo
+loro
+lui
+lungo
+ma
+me
+meglio
+molta
+molti
+molto
+nei
+nella
+no
+noi
+nome
+nostro
+nove
+nuovi
+nuovo
+o
+oltre
+ora
+otto
+peggio
+pero
+persone
+piu
+poco
+primo
+promesso
+qua
+quarto
+quasi
+quattro
+quello
+questo
+qui
+quindi
+quinto
+rispetto
+sara
+secondo
+sei
+sembra
+sembrava
+senza
+sette
+sia
+siamo
+siete
+solo
+sono
+sopra
+soprattutto
+sotto
+stati
+stato
+stesso
+su
+subito
+sul
+sulla
+tanto
+te
+tempo
+terzo
+tra
+tre
+triplo
+ultimo
+un
+una
+uno
+va
+vai
+voi
+volte
+vostro
diff --git a/src/tfidf/stop-words/stop-words-norwegian.txt b/src/tfidf/stop-words/stop-words-norwegian.txt
new file mode 100644
index 0000000..4e2a039
--- /dev/null
+++ b/src/tfidf/stop-words/stop-words-norwegian.txt
@@ -0,0 +1,119 @@
+Å
+alle
+andre
+arbeid
+av
+begge
+bort
+bra
+bruke
+da
+denne
+der
+deres
+det
+din
+disse
+du
+eller
+en
+ene
+eneste
+enhver
+enn
+er
+et
+fÅ
+folk
+for
+fordi
+forsÛke
+fra
+fÛr
+fÛrst
+gÅ
+gjorde
+gjÛre
+god
+ha
+hadde
+han
+hans
+hennes
+her
+hva
+hvem
+hver
+hvilken
+hvis
+hvor
+hvordan
+hvorfor
+i
+ikke
+inn
+innen
+kan
+kunne
+lage
+lang
+lik
+like
+mÅ
+makt
+mange
+mÅte
+med
+meg
+meget
+men
+mens
+mer
+mest
+min
+mye
+nÅ
+nÅr
+navn
+nei
+ny
+og
+ogsÅ
+om
+opp
+oss
+over
+pÅ
+part
+punkt
+rett
+riktig
+sÅ
+samme
+sant
+si
+siden
+sist
+skulle
+slik
+slutt
+som
+start
+stille
+tid
+til
+tilbake
+tilstand
+under
+ut
+uten
+var
+vÅr
+ved
+verdi
+vi
+vil
+ville
+vite
+vÖre
+vÖrt
diff --git a/src/tfidf/stop-words/stop-words-polish1.txt b/src/tfidf/stop-words/stop-words-polish1.txt
new file mode 100644
index 0000000..2f8823a
--- /dev/null
+++ b/src/tfidf/stop-words/stop-words-polish1.txt
@@ -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
diff --git a/src/tfidf/stop-words/stop-words-polish2.txt b/src/tfidf/stop-words/stop-words-polish2.txt
new file mode 100644
index 0000000..cd16c2a
--- /dev/null
+++ b/src/tfidf/stop-words/stop-words-polish2.txt
@@ -0,0 +1,272 @@
+a
+aby
+ach
+acz
+aczkolwiek
+aj
+albo
+ale
+ależ
+aż
+bardziej
+bardzo
+bez
+bo
+bowiem
+by
+byli
+bynajmniej
+być
+był
+była
+było
+były
+będzie
+będą
+cali
+cała
+cały
+ci
+cię
+ciebie
+co
+cokolwiek
+coś
+czasami
+czasem
+czemu
+czy
+czyli
+daleko
+dla
+dlaczego
+dlatego
+do
+dobrze
+dokąd
+dość
+dużo
+dwa
+dwaj
+dwie
+dwoje
+dziś
+dzisiaj
+gdy
+gdyby
+gdyż
+gdzie
+gdziekolwiek
+gdzieś
+go
+i
+ich
+ile
+im
+inna
+inne
+inny
+innych
+iż
+ja
+ją
+jak
+jakaś
+jakby
+jaki
+jakichś
+jakie
+jakiś
+jakiż
+jakkolwiek
+jako
+jakoś
+je
+jeden
+jedna
+jedno
+jednak
+jednakże
+jego
+jej
+jemu
+jest
+jestem
+jeszcze
+jeśli
+jeżeli
+już
+ją
+każdy
+kiedy
+kilka
+kimś
+kto
+ktokolwiek
+ktoś
+która
+które
+którego
+której
+który
+których
+którym
+którzy
+ku
+lat
+lecz
+lub
+ma
+mają
+mam
+mi
+mimo
+między
+mną
+mnie
+mogą
+moi
+moim
+moja
+moje
+może
+możliwe
+można
+mój
+mu
+musi
+my
+na
+nad
+nam
+nami
+nas
+nasi
+nasz
+nasza
+nasze
+naszego
+naszych
+natomiast
+natychmiast
+nawet
+nią
+nic
+nich
+nie
+niego
+niej
+niemu
+nigdy
+nim
+nimi
+niż
+no
+o
+obok
+od
+około
+on
+ona
+one
+oni
+ono
+oraz
+owszem
+pan
+pana
+pani
+po
+pod
+podczas
+pomimo
+ponad
+ponieważ
+powinien
+powinna
+powinni
+powinno
+poza
+prawie
+przecież
+przed
+przede
+przedtem
+przez
+przy
+roku
+również
+sam
+sama
+są
+się
+skąd
+sobie
+sobą
+sposób
+swoje
+są
+ta
+tak
+taka
+taki
+takie
+także
+tam
+te
+tego
+tej
+ten
+teraz
+też
+totobą
+tobie
+toteż
+trzeba
+tu
+tutaj
+twoi
+twoim
+twoja
+twoje
+twym
+twój
+ty
+tych
+tylko
+tym
+u
+w
+wam
+wami
+was
+wasz
+wasza
+wasze
+we
+według
+wiele
+wielu
+więc
+więcej
+wszyscy
+wszystkich
+wszystkie
+wszystkim
+wszystko
+wtedy
+wy
+właśnie
+z
+za
+zapewne
+zawsze
+zeznowu
+znów
+został
+żaden
+żadna
+żadne
+żadnych
+że
+żeby
\ No newline at end of file
diff --git a/src/tfidf/stop-words/stop-words-portugese.txt b/src/tfidf/stop-words/stop-words-portugese.txt
new file mode 100644
index 0000000..cc0b170
--- /dev/null
+++ b/src/tfidf/stop-words/stop-words-portugese.txt
@@ -0,0 +1,147 @@
+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
+é
+ela
+ele
+eles
+em
+enquanto
+então
+está
+estado
+estão
+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
+não
+nome
+nós
+nosso
+novo
+o
+onde
+os
+ou
+outro
+para
+parte
+pegar
+pelo
+pessoas
+pode
+poderá
+podia
+por
+porque
+povo
+promeiro
+qual
+qualquer
+quando
+quê
+quem
+quieto
+saber
+são
+sem
+ser
+seu
+somente
+tal
+também
+tem
+têm
+tempo
+tenho
+tentar
+tentaram
+tente
+tentei
+teu
+teve
+tipo
+tive
+todos
+trabalhar
+trabalho
+tu
+último
+um
+uma
+umas
+uns
+usa
+usar
+valor
+veja
+ver
+verdade
+verdadeiro
+você
diff --git a/src/tfidf/stop-words/stop-words-russian.txt b/src/tfidf/stop-words/stop-words-russian.txt
new file mode 100644
index 0000000..9498480
--- /dev/null
+++ b/src/tfidf/stop-words/stop-words-russian.txt
@@ -0,0 +1,421 @@
+а
+е
+и
+ж
+м
+о
+на
+не
+ни
+об
+но
+он
+мне
+мои
+мож
+она
+они
+оно
+мной
+много
+многочисленное
+многочисленная
+многочисленные
+многочисленный
+мною
+мой
+мог
+могут
+можно
+может
+можхо
+мор
+моя
+моё
+мочь
+над
+нее
+оба
+нам
+нем
+нами
+ними
+мимо
+немного
+одной
+одного
+менее
+однажды
+однако
+меня
+нему
+меньше
+ней
+наверху
+него
+ниже
+мало
+надо
+один
+одиннадцать
+одиннадцатый
+назад
+наиболее
+недавно
+миллионов
+недалеко
+между
+низко
+меля
+нельзя
+нибудь
+непрерывно
+наконец
+никогда
+никуда
+нас
+наш
+нет
+нею
+неё
+них
+мира
+наша
+наше
+наши
+ничего
+начала
+нередко
+несколько
+обычно
+опять
+около
+мы
+ну
+нх
+от
+отовсюду
+особенно
+нужно
+очень
+отсюда
+в
+во
+вон
+вниз
+внизу
+вокруг
+вот
+восемнадцать
+восемнадцатый
+восемь
+восьмой
+вверх
+вам
+вами
+важное
+важная
+важные
+важный
+вдали
+везде
+ведь
+вас
+ваш
+ваша
+ваше
+ваши
+впрочем
+весь
+вдруг
+вы
+все
+второй
+всем
+всеми
+времени
+время
+всему
+всего
+всегда
+всех
+всею
+всю
+вся
+всё
+всюду
+г
+год
+говорил
+говорит
+года
+году
+где
+да
+ее
+за
+из
+ли
+же
+им
+до
+по
+ими
+под
+иногда
+довольно
+именно
+долго
+позже
+более
+должно
+пожалуйста
+значит
+иметь
+больше
+пока
+ему
+имя
+пор
+пора
+потом
+потому
+после
+почему
+почти
+посреди
+ей
+два
+две
+двенадцать
+двенадцатый
+двадцать
+двадцатый
+двух
+его
+дел
+или
+без
+день
+занят
+занята
+занято
+заняты
+действительно
+давно
+девятнадцать
+девятнадцатый
+девять
+девятый
+даже
+алло
+жизнь
+далеко
+близко
+здесь
+дальше
+для
+лет
+зато
+даром
+первый
+перед
+затем
+зачем
+лишь
+десять
+десятый
+ею
+её
+их
+бы
+еще
+при
+был
+про
+процентов
+против
+просто
+бывает
+бывь
+если
+люди
+была
+были
+было
+будем
+будет
+будете
+будешь
+прекрасно
+буду
+будь
+будто
+будут
+ещё
+пятнадцать
+пятнадцатый
+друго
+другое
+другой
+другие
+другая
+других
+есть
+пять
+быть
+лучше
+пятый
+к
+ком
+конечно
+кому
+кого
+когда
+которой
+которого
+которая
+которые
+который
+которых
+кем
+каждое
+каждая
+каждые
+каждый
+кажется
+как
+какой
+какая
+кто
+кроме
+куда
+кругом
+с
+т
+у
+я
+та
+те
+уж
+со
+то
+том
+снова
+тому
+совсем
+того
+тогда
+тоже
+собой
+тобой
+собою
+тобою
+сначала
+только
+уметь
+тот
+тою
+хорошо
+хотеть
+хочешь
+хоть
+хотя
+свое
+свои
+твой
+своей
+своего
+своих
+свою
+твоя
+твоё
+раз
+уже
+сам
+там
+тем
+чем
+сама
+сами
+теми
+само
+рано
+самом
+самому
+самой
+самого
+семнадцать
+семнадцатый
+самим
+самими
+самих
+саму
+семь
+чему
+раньше
+сейчас
+чего
+сегодня
+себе
+тебе
+сеаой
+человек
+разве
+теперь
+себя
+тебя
+седьмой
+спасибо
+слишком
+так
+такое
+такой
+такие
+также
+такая
+сих
+тех
+чаще
+четвертый
+через
+часто
+шестой
+шестнадцать
+шестнадцатый
+шесть
+четыре
+четырнадцать
+четырнадцатый
+сколько
+сказал
+сказала
+сказать
+ту
+ты
+три
+эта
+эти
+что
+это
+чтоб
+этом
+этому
+этой
+этого
+чтобы
+этот
+стал
+туда
+этим
+этими
+рядом
+тринадцать
+тринадцатый
+этих
+третий
+тут
+эту
+суть
+чуть
+тысяч
diff --git a/src/tfidf/stop-words/stop-words-slovak.txt b/src/tfidf/stop-words/stop-words-slovak.txt
new file mode 100644
index 0000000..07da7b3
--- /dev/null
+++ b/src/tfidf/stop-words/stop-words-slovak.txt
@@ -0,0 +1,173 @@
+a
+aby
+aj
+ak
+ako
+ale
+alebo
+and
+ani
+áno
+asi
+až
+bez
+bude
+budem
+budeš
+budeme
+budete
+budú
+by
+bol
+bola
+boli
+bolo
+byť
+cez
+čo
+či
+ďalší
+ďalšia
+ďalšie
+dnes
+do
+ho
+ešte
+for
+i
+ja
+je
+jeho
+jej
+ich
+iba
+iné
+iný
+som
+si
+sme
+sú
+k
+kam
+každý
+každá
+každé
+každí
+kde
+keď
+kto
+ktorá
+ktoré
+ktorou
+ktorý
+ktorí
+ku
+lebo
+len
+ma
+mať
+má
+máte
+medzi
+mi
+mna
+mne
+mnou
+musieť
+môcť
+môj
+môže
+my
+na
+nad
+nám
+náš
+naši
+nie
+nech
+než
+nič
+niektorý
+nové
+nový
+nová
+nové
+noví
+o
+od
+odo
+of
+on
+ona
+ono
+oni
+ony
+po
+pod
+podľa
+pokiaľ
+potom
+práve
+pre
+prečo
+preto
+pretože
+prvý
+prvá
+prvé
+prví
+pred
+predo
+pri
+pýta
+s
+sa
+so
+si
+svoje
+svoj
+svojich
+svojím
+svojími
+ta
+tak
+takže
+táto
+teda
+te
+tě
+ten
+tento
+the
+tieto
+tým
+týmto
+tiež
+to
+toto
+toho
+tohoto
+tom
+tomto
+tomuto
+toto
+tu
+tú
+túto
+tvoj
+ty
+tvojími
+už
+v
+vám
+váš
+vaše
+vo
+viac
+však
+všetok
+vy
+z
+za
+zo
+že
diff --git a/src/tfidf/stop-words/stop-words-slovak2.txt b/src/tfidf/stop-words/stop-words-slovak2.txt
new file mode 100644
index 0000000..d21096a
--- /dev/null
+++ b/src/tfidf/stop-words/stop-words-slovak2.txt
@@ -0,0 +1,106 @@
+a
+aby
+aj
+ako
+ale
+alebo
+ani
+áno
+asi
+až
+bez
+buď
+by
+cez
+či
+čo
+ešte
+ho
+i
+iba
+ich
+ja
+je
+jeho
+jej
+ju
+k
+kam
+kde
+keď
+kto
+ku
+menej
+mi
+moja
+moje
+môj
+my
+nad
+nám
+než
+nič
+nie
+o
+od
+on
+on
+ona
+ona
+oni
+ono
+po
+pod
+podľa
+pokiaľ
+potom
+práve
+prečo
+pred
+preto
+pretože
+pri
+s
+sa
+si
+sme
+so
+som
+späť
+ste
+sú
+sú
+ta
+tá
+tak
+tak
+takže
+tam
+tam
+táto
+teda
+ten
+tento
+tieto
+tiež
+to
+to
+toho
+tom
+tomto
+toto
+tu
+túto
+ty
+tým
+týmto
+už
+v
+vám
+viac
+vo
+však
+vy
+z
+za
+zo
diff --git a/src/tfidf/stop-words/stop-words-spanish.txt b/src/tfidf/stop-words/stop-words-spanish.txt
new file mode 100644
index 0000000..8095338
--- /dev/null
+++ b/src/tfidf/stop-words/stop-words-spanish.txt
@@ -0,0 +1,181 @@
+algún
+alguna
+algunas
+alguno
+algunos
+ambos
+ampleamos
+ante
+antes
+aquel
+aquellas
+aquellos
+aqui
+arriba
+atras
+bajo
+bastante
+bien
+cada
+cierta
+ciertas
+cierto
+ciertos
+como
+con
+conseguimos
+conseguir
+consigo
+consigue
+consiguen
+consigues
+cual
+cuando
+de
+dentro
+desde
+donde
+dos
+el
+ellas
+ellos
+empleais
+emplean
+emplear
+empleas
+empleo
+en
+encima
+entonces
+entre
+era
+eramos
+eran
+eras
+eres
+es
+esta
+estaba
+estado
+estais
+estamos
+estan
+estoy
+fin
+fue
+fueron
+fui
+fuimos
+gueno
+ha
+hace
+haceis
+hacemos
+hacen
+hacer
+haces
+hago
+incluso
+intenta
+intentais
+intentamos
+intentan
+intentar
+intentas
+intento
+ir
+la
+largo
+las
+lo
+los
+mientras
+mio
+modo
+muchos
+muy
+nos
+nosotros
+otro
+para
+pero
+podeis
+podemos
+poder
+podria
+podriais
+podriamos
+podrian
+podrias
+por
+por
+porque
+primero
+puede
+pueden
+puedo
+que
+qué
+quien
+sabe
+sabeis
+sabemos
+saben
+saber
+sabes
+ser
+si
+siendo
+sin
+sobre
+sois
+solamente
+solo
+somos
+soy
+su
+sus
+también
+teneis
+tenemos
+tener
+tengo
+tiempo
+tiene
+tienen
+todo
+trabaja
+trabajais
+trabajamos
+trabajan
+trabajar
+trabajas
+trabajo
+tras
+tuyo
+ultimo
+un
+una
+unas
+uno
+unos
+usa
+usais
+usamos
+usan
+usar
+usas
+uso
+va
+vais
+valor
+vamos
+van
+vaya
+verdad
+verdadera
+verdadero
+vosotras
+vosotros
+voy
+yo
diff --git a/src/tfidf/stop-words/stop-words-swedish.txt b/src/tfidf/stop-words/stop-words-swedish.txt
new file mode 100644
index 0000000..05c3e14
--- /dev/null
+++ b/src/tfidf/stop-words/stop-words-swedish.txt
@@ -0,0 +1,386 @@
+aderton
+adertonde
+adjö
+aldrig
+alla
+allas
+allt
+alltid
+alltså
+än
+andra
+andras
+annan
+annat
+ännu
+artonde
+artonn
+åtminstone
+att
+åtta
+åttio
+åttionde
+åttonde
+av
+även
+båda
+bådas
+bakom
+bara
+bäst
+bättre
+behöva
+behövas
+behövde
+behövt
+beslut
+beslutat
+beslutit
+bland
+blev
+bli
+blir
+blivit
+bort
+borta
+bra
+då
+dag
+dagar
+dagarna
+dagen
+där
+därför
+de
+del
+delen
+dem
+den
+deras
+dess
+det
+detta
+dig
+din
+dina
+dit
+ditt
+dock
+du
+efter
+eftersom
+elfte
+eller
+elva
+en
+enkel
+enkelt
+enkla
+enligt
+er
+era
+ert
+ett
+ettusen
+få 
+fanns
+får
+fått 
+fem
+femte
+femtio
+femtionde
+femton
+femtonde
+fick
+fin
+finnas
+finns
+fjärde
+fjorton
+fjortonde
+fler
+flera
+flesta
+följande
+för
+före
+förlåt
+förra
+första
+fram
+framför
+från
+fyra
+fyrtio
+fyrtionde
+gå
+gälla
+gäller
+gällt
+går
+gärna
+gått
+genast
+genom
+gick
+gjorde
+gjort
+god
+goda
+godare
+godast
+gör
+göra
+gott
+ha
+hade
+haft
+han
+hans
+har
+här
+heller
+hellre
+helst
+helt
+henne
+hennes
+hit
+hög
+höger
+högre
+högst
+hon
+honom
+hundra
+hundraen
+hundraett
+hur
+i
+ibland
+idag
+igår
+igen
+imorgon
+in
+inför
+inga
+ingen
+ingenting
+inget
+innan
+inne
+inom
+inte
+inuti
+ja
+jag
+jämfört
+kan
+kanske
+knappast
+kom
+komma
+kommer
+kommit
+kr
+kunde
+kunna
+kunnat
+kvar
+länge
+längre
+långsam
+långsammare
+långsammast
+långsamt
+längst
+långt
+lätt
+lättare
+lättast
+legat
+ligga
+ligger
+lika
+likställd
+likställda
+lilla
+lite
+liten
+litet
+man
+många
+måste
+med
+mellan
+men
+mer
+mera
+mest
+mig
+min
+mina
+mindre
+minst
+mitt
+mittemot
+möjlig
+möjligen
+möjligt
+möjligtvis
+mot
+mycket
+någon
+någonting
+något
+några
+när
+nästa
+ned
+nederst
+nedersta
+nedre
+nej
+ner
+ni
+nio
+nionde
+nittio
+nittionde
+nitton
+nittonde
+nödvändig
+nödvändiga
+nödvändigt
+nödvändigtvis
+nog
+noll
+nr
+nu
+nummer
+och
+också
+ofta
+oftast
+olika
+olikt
+om
+oss
+över
+övermorgon
+överst
+övre
+på
+rakt
+rätt
+redan
+så
+sade
+säga
+säger
+sagt
+samma
+sämre
+sämst
+sedan
+senare
+senast
+sent
+sex
+sextio
+sextionde
+sexton
+sextonde
+sig
+sin
+sina
+sist
+sista
+siste
+sitt
+sjätte
+sju
+sjunde
+sjuttio
+sjuttionde
+sjutton
+sjuttonde
+ska
+skall
+skulle
+slutligen
+små
+smått
+snart
+som
+stor
+stora
+större
+störst
+stort
+tack
+tidig
+tidigare
+tidigast
+tidigt
+till
+tills
+tillsammans
+tio
+tionde
+tjugo
+tjugoen
+tjugoett
+tjugonde
+tjugotre
+tjugotvå
+tjungo
+tolfte
+tolv
+tre
+tredje
+trettio
+trettionde
+tretton
+trettonde
+två
+tvåhundra
+under
+upp
+ur
+ursäkt
+ut
+utan
+utanför
+ute
+vad
+vänster
+vänstra
+var
+vår
+vara
+våra
+varför
+varifrån
+varit
+varken
+värre
+varsågod
+vart
+vårt
+vem
+vems
+verkligen
+vi
+vid
+vidare
+viktig
+viktigare
+viktigast
+viktigt
+vilka
+vilken
+vilket
+vill
diff --git a/src/tfidf/stop-words/stop-words-turkish.txt b/src/tfidf/stop-words/stop-words-turkish.txt
new file mode 100644
index 0000000..03cdd1d
--- /dev/null
+++ b/src/tfidf/stop-words/stop-words-turkish.txt
@@ -0,0 +1,114 @@
+acaba
+altmýþ
+altý
+ama
+bana
+bazý
+belki
+ben
+benden
+beni
+benim
+beþ
+bin
+bir
+biri
+birkaç
+birkez
+birþey
+birþeyi
+biz
+bizden
+bizi
+bizim
+bu
+buna
+bunda
+bundan
+bunu
+bunun
+da
+daha
+dahi
+de
+defa
+diye
+doksan
+dokuz
+dört
+elli
+en
+gibi
+hem
+hep
+hepsi
+her
+hiç
+iki
+ile
+INSERmi
+ise
+için
+katrilyon
+kez
+ki
+kim
+kimden
+kime
+kimi
+kýrk
+milyar
+milyon
+mu
+mü
+mý
+nasýl
+ne
+neden
+nerde
+nerede
+nereye
+niye
+niçin
+on
+ona
+ondan
+onlar
+onlardan
+onlari
+onlarýn
+onu
+otuz
+sanki
+sekiz
+seksen
+sen
+senden
+seni
+senin
+siz
+sizden
+sizi
+sizin
+trilyon
+tüm
+ve
+veya
+ya
+yani
+yedi
+yetmiþ
+yirmi
+yüz
+çok
+çünkü
+üç
+þey
+þeyden
+þeyi
+þeyler
+þu
+þuna
+þunda
+þundan
+þunu
diff --git a/src/tfidf/tfidf.go b/src/tfidf/tfidf.go
new file mode 100644
index 0000000..4d78b4f
--- /dev/null
+++ b/src/tfidf/tfidf.go
@@ -0,0 +1,182 @@
+package tfidf
+
+import (
+	"fmt"
+	"io/ioutil"
+	"math"
+	"regexp"
+	"sort"
+	"strings"
+)
+
+type TfIdfMatrix struct {
+	Stopwords []string
+	TotalFreq map[string]float64
+	DocFreqs  []map[string]float64
+}
+
+// totalFreq := make(map[string]float64)
+// docFreqs := make([]map[string]float64, 0)
+
+func (matrix *TfIdfMatrix) LoadStopWords(filename string) {
+	contents, err := ioutil.ReadFile(filename)
+	if err != nil {
+		fmt.Println(err)
+		return
+	}
+
+	elements := strings.Fields(string(contents))
+
+	fmt.Printf("Loaded %d stopwords.\n", len(elements))
+	matrix.Stopwords = append(matrix.Stopwords, elements...)
+}
+
+func (matrix *TfIdfMatrix) checkStopWords(word string) bool {
+	result := false
+
+	for _, stopword := range matrix.Stopwords {
+		if word == stopword {
+			result = true
+			break
+		}
+	}
+
+	return result
+}
+
+func ClearHtml(text string) string {
+	htmlCleaner, _ := regexp.Compile("<.*?>")
+	result := string(htmlCleaner.ReplaceAllString(text, ""))
+
+	return result
+}
+
+func (matrix *TfIdfMatrix) TfCalc(text string) map[string]float64 {
+	tfMatrix := make(map[string]float64)
+
+	punctuation := regexp.MustCompile("(,|;|:|!||¡|¿)")
+	noStrangeChars := regexp.MustCompile("^[A-Za-z]*?$")
+
+	temp := strings.Replace(text, ".", " ", -1)
+	temp = strings.Replace(temp, "?", " ", -1)
+
+	temp = string(punctuation.ReplaceAllString(temp, ""))
+
+	temp = strings.ToLower(temp)
+
+	for _, value := range strings.Fields(temp) {
+		if noStrangeChars.MatchString(value) && !matrix.checkStopWords(value) {
+			if amount, ok := tfMatrix[value]; ok {
+				tfMatrix[value] = amount + 1.0
+			} else {
+				tfMatrix[value] = 1.0
+			}
+		}
+	}
+
+	return tfMatrix
+}
+
+func (matrix *TfIdfMatrix) DfUpdate(docFreqs map[string]float64) {
+	if matrix.TotalFreq == nil {
+		matrix.TotalFreq = make(map[string]float64)
+	}
+
+	for word, quantity := range docFreqs {
+		if amount, ok := matrix.TotalFreq[word]; ok {
+			matrix.TotalFreq[word] = amount + quantity
+		} else {
+			matrix.TotalFreq[word] = quantity
+		}
+	}
+}
+
+func (matrix *TfIdfMatrix) CalculateIdf(totalDocNo int) {
+	for word, amount := range matrix.TotalFreq {
+		matrix.TotalFreq[word] = math.Log(float64(totalDocNo) / amount)
+	}
+}
+
+func (matrix *TfIdfMatrix) PrintTfIdf(documentFreqs map[string]float64) {
+	maxTfIdf := 0.0
+
+	res := make(map[string]float64, 0)
+
+	for word, amount := range documentFreqs {
+		if value, ok := matrix.TotalFreq[word]; ok {
+			temp := amount * value
+			res[word] = temp
+			if temp > maxTfIdf {
+				maxTfIdf = temp
+			}
+		} else {
+			temp := amount
+			res[word] = temp
+			if temp > maxTfIdf {
+				maxTfIdf = temp
+			}
+		}
+	}
+
+	for word, amount := range res {
+		normalized := (amount / maxTfIdf) * 50.0 // Normalize and extend to 50 range
+		if !(normalized < 1.0) {
+			fmt.Printf("%s:\n", word)
+			fmt.Println(strings.Repeat("#", int(normalized)))
+		}
+	}
+}
+
+func (matrix *TfIdfMatrix) SearchDocumentsByWord(text string) ([]int, []float64) {
+	match := make([]float64, 0)
+	docs := make([]int, 0)
+	result := make([]int, 0)
+
+	for count, document := range matrix.DocFreqs {
+		if value, ok := document[text]; ok {
+			temp := matrix.TotalFreq[text]
+			fr := temp * value
+			if fr > 0 {
+				match = append(match, temp*value)
+				docs = append(docs, count)
+			}
+		}
+	}
+
+	temp := make([]float64, len(match))
+	_ = copy(temp, match)
+
+	sort.Sort(sort.Reverse(sort.Float64Slice(temp)))
+
+	for cnt, freq := range temp {
+		if cnt > 5 {
+			break
+		}
+		count := 0
+		value := match[count]
+		for value != freq {
+			count++
+			value = match[count]
+		}
+		match[count] = -1.0 // Mark this result as used
+		result = append(result, count)
+	}
+
+	if len(result) > 5 {
+        return result[:5], temp[:5]
+	} else {
+		return result, temp
+	}
+}
+
+func (matrix *TfIdfMatrix) TfIdf(texts []string) {
+	totalDocuments := len(texts)
+
+	for _, text := range texts {
+		tf := matrix.TfCalc(text)
+		matrix.DocFreqs = append(matrix.DocFreqs, tf)
+		matrix.DfUpdate(tf)
+	}
+
+	matrix.CalculateIdf(totalDocuments)
+}
diff --git a/test.go b/test.go
new file mode 100644
index 0000000..33e0720
--- /dev/null
+++ b/test.go
@@ -0,0 +1,15 @@
+
+package main
+
+import (
+   "tfidf"
+)
+
+func main() {
+    text1 := "This is a text for testing the TFIDF, but we expect the algorithm to crash."
+    text2 := "Is that so? We create the world that is put in front of your eyes."
+
+    input := []string{text1, text2}
+
+    tfidf.TfIdf(input)
+}