Add known terms with special characters
diff --git a/src/tokenizer.xfst b/src/tokenizer.xfst
index 780884a..56917ea 100644
--- a/src/tokenizer.xfst
+++ b/src/tokenizer.xfst
@@ -107,6 +107,8 @@
define Abbr @txt"txt/abbrv.txt";
+define Plusampersand @txt"txt/plusampersand.txt";
+
! A solution to the "(author): problem" may be to add ) at the end of any
! string as a possible ending
@@ -189,7 +191,7 @@
-define RealToken [XML|Email|URL|SNS|[Abbr %.]|Streetname|Omission|Domain|AcronymDep|File|Emdash|Punct|Ord|Num|Years|Emoji|Word];
+define RealToken [XML|Email|URL|SNS|[Abbr %.]|Plusampersand|Streetname|Omission|Domain|AcronymDep|File|Emdash|Punct|Ord|Num|Years|Emoji|Word];
echo - Introduce Token splitter
define Token [RealToken @-> ... NLout]
diff --git a/src/txt/plusampersand.txt b/src/txt/plusampersand.txt
new file mode 100644
index 0000000..7921ca1
--- /dev/null
+++ b/src/txt/plusampersand.txt
@@ -0,0 +1,644 @@
+&
+'
+>
+&K
+<
+&M
+"
+&RQ
++Ale
++ALe
++Anima
++APD
++co
++Co
++GF+
++Leif
++Strang
++Teamgeist
+A&A
+A&E
+A&F
+A&M
+A&O
+A&P
+A&R
+A&V
+A&W
+A++
+A+++
+A+E
+A+f
+AAC+
+ABC&D
+AC+
+AD&D
+AE&E
+AES+F
+AEW&C
+AFM+E
+AGTL+
+Altenpflege+ProPflege
+Analyse+kritik
+anlagen+verfahren
+ANT+
+Anynet+
+Applus+
+Arch+
+ARCH+
+ART+COM
+AS&P
+ASC+T
+ASEAN+
+Asis&t
+AT&L
+AT&S
+AT&SF
+AT&T
+ATV+
+Auer+Weber
+Auer+Weber+Assoziierte
+Axis&Allies
+B&B
+B&C
+B&F
+B&G
+B&H
+B&I
+B&K
+B&M
+B&MTJR
+B&NES
+B&O
+B&Q
+B&R
+B&T
+B&V
+B&W
+B+B
+B+R
+B+T
+Baby&Co
+Bayern+
+BB&T
+BD+
+Beast+
+BEAST+
+Beck+Schubert
+Belle&Sebastian
+BFE+
+BG+BRG
+BIBEL+ORIENT
+Bild+Funk
+Binder+Co
+Blohm+Voss
+Blood+
+Blut+Eisen
+BM&F
+BM&FBovespa
+Bolles+Wilson
+Bottega+Ehrhardt
+Brangs+Heinrich
+BRF+
+Briner+Kern
+BUCH&media
+Burghardt+Schmidt
+bus+bahn
+C&A
+C&C
+C&D
+C&L
+C&M
+C&O
+C&P
+C&R
+C&S
+C&T
+C&W
+C++
+C++Builder
+C+c
+C+C
+C+M+B
+Ca++
+Cafe+co
+Cafe+Co
+Canal+
+Cantata++
+CB&I
+CC&G
+CCC&StL
+CD&E
+CD&V
+CD+DVD
+CD+G
+CDIA+
+Celtic+
+Cendres+M
+Chage&Aska
+Chage&Asuka
+Channel+smile
+Charm++
+Chip&Chap
+CI&CEQ
+CI+
+Click&Buy
+Cocl&Seff
+Com&Com
+COM+
+Comicplus+
+COR&FJA
+CS&S
+CT&T
+ctc++
+Ctrl+Alt+Del
+CTRL+ALT+DEL
+Cube+
+Cyfra+
+CYFRA+
+D&A
+D&AD
+D&b
+D&B
+D&D
+D&G
+D&O
+D&RGW
+D&S
+D&W
+D+Q
+DAB+
+DACH+HOLZ
+DAML+OIL
+DBM&T
+Dc++
+DC++
+DDDBM&T
+Despe&Siga
+DF&S
+Digital+
+DirectConnect++
+Dissing+Weitling
+DL+NT
+DLSW+
+Do&Co
+Dok&Deb
+Dorma+kaba
+DP&L
+Drm+
+DRM+
+DTS++
+DU&ICH
+DVD+R
+Dvd+rw
+DVD+RW
+E&a
+E&N
+E&Y
+E+
+E+e
+E+h
+E+H
+EAAC+
+Ebert+Jacobi
+ECO+
+EG&G
+Eigen+Art
+Eins+Alles
+Electromobility+
+En+
+Endress+Hauser
+Erasmus+
+ES&T
+ETV+
+EV+
+Eve&rave
+Every+
+F&A
+F&B
+F&E
+F&F
+F&K
+F+F
+F+U
+Familie&Co
+FAT+
+Film+
+FILM+SCHULE
+Fischer+Kr
+Fix+Foxi
+FLUXUS+
+FMHL+
+Form+zweck
+fuhrpark+management
+G&B
+G&D
+G&IF
+G&L
+G&V
+G++
+G+H
+G+J
+G+tt
+GC&CS
+GDI+
+ge+her
+GG&L
+Go+
+GO+
+Google+
+Goran+Vujic
+GRAF+ZYX
+Gruner+Jahr
+Gtk+
+GTK+
+GTL+
+GTX+
+Guide+
+H&BC
+H&H
+H&K
+H&M
+h&m
+H&N
+H&R
+H&S
+H+BEDV
+H+H
+H+N
+H+S
+Haase&band
+Hahn+Kolb
+HAHN+KOLB
+Hasta+Coda
+Haubitz&Zoche
+Haubitz+Zoche
+HBCI+
+HD+
+Health&Care
+Heim+Handwerk
+Heute+
+HFS+
+hne+Nagel
+HSPA+
+HT&L
+HTML+TIME
+Huber+Suhner
+Hunger&Seide
+I&A
+I&K
+I&Q
+I&u
+I&U
+I+D
+I+R
+Ich+Ich
+ID&T
+Idee+spiel
+Ihp+
+II+
+IIc+
+III+
+IK+
+In&phone
+In&Phone
+info+
+Interkama+
+IT&Production
+J&B
+J&D
+J&J
+J&M
+J&P
+J&S
+J&T
+J++
+J+S
+Jazz+Az
+Jenna+Ron
+Johnson&Johnson
+JU+TE
+Jugend+Sport
+Jugend+Technik
+Jump&Run
+K&k
+K&K
+K&L
+K&M
+K&N
+K&R
+K&S
+K&U
+K++
+K+A
+K+H
+K+K
+k+Metal
+K+R
+K+S
+K+W
+Kai+Sven
+Kaiser+Kraft
+KAISER+KRAFT
+Kino&Co
+KINO&CO
+Kino+
+Kirche+Leben
+Klassik&JazzMagazin
+Kurz&F
+L&B
+L&C
+L&M
+L&N
+L&P
+L&S
+L+R
+L+T
+Lancia+Voyager
+Landis+Gyr
+LB&SCR
+Leader+
+LEADER+
+Lederer+Ragnarsd
+Leicht&Cross
+Lenord+Bauer
+Leslie+Lohman
+Libsigc++
+Life&Style
+LIFE+
+Light+Building
+Lippmann+Rau
+LISA+
+Lords&Knights
+LT&SR
+Lussi+Halter
+M&A
+M&B
+M&D
+M&G
+M&i
+M&I
+M&M
+M&Ms
+M&N
+M&S
+M&T
+M+a
+M+C
+M+M
+M+O
+M+s
+M+S
+M+W
+Maildir++
+Mann+Hummel
+Markt+Technik
+Means++
+Melodie&Rhythmus
+Metadata+
+Miles&more
+Milk+
+Mining+geo
+Mix&Genest
+mmerly+Frey
+Monet+
+Motion+picture
+MPP+
+MS&D
+MS&L
+MStP&SSM
+Music&Voice
+N&CRR
+N&ER
+n&gut
+N&R
+N&W
+N+M
+Na+
+NADHH+
+Nah&gut
+Natur+kosmos
+natur+mensch
+Nc+
+NI&Co
+nig+Neurath
+Nike+iPod
+Nintendogs+Cats
+Notepad++
+NYW&B
+O&K
+O&L
+O&M
+Ola+
+OMNeT++
+ORFsport+
+Ost+Front
+P&A
+P&C
+P&E
+P&G
+P&I
+P&ID
+P&L
+P&M
+P&O
+P&P
+P&R
+P&T
+P&TLuxembourg
+P&W
+P+M
+P+R
+P+S
+PAL+
+Pan&Scan
+Papier&Stift
+Park&Charge
+Park&Rail
+Park&Ride
+Park&Suites
+PB&J
+Peek&Cloppenburg
+Pen&Paper
+Pepperl&Fuchs
+Pepperl+Fuchs
+Peste&Sida
+PG&E
+Pirelli&C
+Pittel+Brausewetter
+Plug&play
+Plus+
+POB&A
+Pol&is
+POL&IS
+POLO+
+Poses++
+PP&P
+Pratt&Whitney
+Princess+
+Prius+
+Procter&Gamble
+Prozac+
+PS&P
+Pur+
+Q&A
+Q&Q
+Q+Q
+Quanta+
+R&A
+R&B
+R&D
+R&ER
+R&F
+R&G
+R&I
+R&M
+R&Q
+R&R
+R&S
+R+C
+R+S
+R+V
+Rail&Fly
+REDD+
+Reise&Touristik
+Relax+ng
+RF&P
+Richter+Frenzel
+Rio+
+Rohde&Schwarz
+RT+
+Run&Dine
+S&B
+S&D
+S&G
+S&H
+S&K
+S&M
+S&P
+S&T
+S&w
+S&W
+S+D
+S+G
+S+T
+S+U
+Sales&Services
+Sam&Max
+Schedule+
+Schiff&Hafen
+Schlund+Partner
+Schmelzle+Partner
+Schmidt+Clemens
+science+business
+Science+Business
+sd&m
+Sd&m
+Sdr+
+Serve&Volley
+Severin+K
+SiMPLE++
+SMS&park
+SMW+
+Soap&Skin
+Solo+
+Spar+Kreditbank
+Spar+Leihkasse
+speed+
+Speed+
+Spoga+gafa
+SPORT+
+Sport+Technik
+SS+
+St&H
+St&Z
+Standard&Poor
+Standard&Poors
+Station&Service
+Steib+Steib
+Stil&Stadt
+Strategy&
+Strg+Alt+Entf
+StrongDC++
+Such&Find
+Sumol+Compal
+SVS&E
+SVWZ+
+SW&S
+Swift+
+SXGA+
+T&D
+T&L
+T&N
+T&T
+T+A
+T+T
+TACACS+
+Tanz&FolkFest
+Taylor&Francis
+text+kritik
+TEXT+KRITIK
+textil+mode
+Timidity++
+TMRM+
+Toni&Guy
+toon+
+Touch&Travel
+Track+
+Trends+More
+TT&C
+TT&R
+ttir+Oei
+TV+Synchron
+U&D
+U++
+U+F
+Ultimate++
+Urban&Fischer
+URW++
+USC&GS
+UTC+
+V&A
+V&R
+V&S
+V&W
+Valentien+Valentien
+VC++
+VF+
+Vieweg+Teubner
+VISEO+
+Vision+Technik
+VisualDSP++
+VIVA+
+VL&D
+Vorschau+R
+Vorster&Gr
+VT&MA
+W&B
+W&F
+W&G
+W&H
+W&p
+W&V
+W&W
+WB+
+Wein+Markt
+Wienstroth&Hammans
+Winkler+D
+Wirtschaft+Markt
+WP&YR
+WS&P
+WSXGA+
+WXGA+
+X++
+X+Y
+Xbase++
+XHTML+SMIL
+Y&R
+Y&T
+Yin&Yang
+Yotsuba&
+Young&Queer
+Z+W
+Zeidler&Wimmel
+Zinc&Germanium