Update itextcore hyph xml files encoding to utf-8

DEVSIX-6326

Author: Kate Ivanova

itext/itext.hyph/de.xml

@@ -1,4 +1,4 @@
-<?xml version="1.0" encoding="US-ASCII"?>
+<?xml version="1.0" encoding="utf-8"?>
 <!-- 
 %
 %  Created by Jeff Kingston, 16 November 1996, from a TeX

itext/itext.hyph/de_DR.xml

@@ -1,4 +1,4 @@
-<?xml version="1.0" encoding="US-ASCII"?>
+<?xml version="1.0" encoding="utf-8"?>
 <!-- 
 %
 %  Created by Jeff Kingston, 16 November 1996, from a TeX

itext/itext.hyph/el.xml

@@ -1,4 +1,4 @@
-<?xml version="1.0" encoding="US-ASCII"?>
+<?xml version="1.0" encoding="utf-8"?>
 <!-- 
 %
 %  Created by Jeff Kingston, 16 November 1996, from a TeX

itext/itext.hyph/en.xml

@@ -1,4 +1,4 @@
-<?xml version="1.0" encoding="iso-8859-1"?>
+<?xml version="1.0" encoding="utf-8"?>
 
 <!-- Adapted by Carlos Villegas from Lout's spanish.lh.
      Spanish is probably the easiest language to hyphenate!
@@ -53,13 +53,13 @@ wW
 xX
 yY
 zZ
-áÁ
-éÉ
-íÍ
-óÓ
-úÚ
-üÜ
-ñÑ
+áÁ
+éÉ
+íÍ
+óÓ
+úÚ
+üÜ
+ñÑ
 </classes>
 
 <patterns>
@@ -68,7 +68,7 @@ zZ
 % Compiled by Julio Sanchez ([email protected]) on September 1991.
 %
 % These patterns have been derived from "On Word Division in Spanish",
-% José A. Mañas, Communications of the ACM, and implemented in his
+% José A. Mañas, Communications of the ACM, and implemented in his
 % package ftc. You can get ftc and a draft of the abovementioned
 % paper from goya.dit.upm.es in src/text.proc/ftc.Z. FTP access may
 % be available. Otherwise, send help to [email protected] for
@@ -140,50 +140,50 @@ zZ
 % Rule SR2
 % Attach vowel groups to left consonant
 -->
-1ba 1be 1bo 1bá 1bé 1bí 1bó 1bú 1bi 1bu 1bü 
-1ca 1ce 1co 1cá 1cé 1cí 1có 1cú 1ci 1cu 1cü 
-1da 1de 1do 1dá 1dé 1dí 1dó 1dú 1di 1du 1dü 
-1fa 1fe 1fo 1fá 1fé 1fí 1fó 1fú 1fi 1fu 1fü 
-1ga 1ge 1go 1gá 1gé 1gí 1gó 1gú 1gi 1gu 1gü 
-1ja 1je 1jo 1já 1jé 1jí 1jó 1jú 1ji 1ju 1jü 
-1ka 1ke 1ko 1ká 1ké 1kí 1kó 1kú 1ki 1ku 1kü 
-1la 1le 1lo 1lá 1lé 1lí 1ló 1lú 1li 1lu 1lü 
-1ma 1me 1mo 1má 1mé 1mí 1mó 1mú 1mi 1mu 1mü 
-1na 1ne 1no 1ná 1né 1ní 1nó 1nú 1ni 1nu 1nü 
-1pa 1pe 1po 1pá 1pé 1pí 1pó 1pú 1pi 1pu 1pü 
-1qa 1qe 1qo 1qá 1qé 1qí 1qó 1qú 1qi 1qu 1qü 
-1ra 1re 1ro 1rá 1ré 1rí 1ró 1rú 1ri 1ru 1rü 
-1sa 1se 1so 1sá 1sé 1sí 1só 1sú 1si 1su 1sü 
-1ta 1te 1to 1tá 1té 1tí 1tó 1tú 1ti 1tu 1tü 
-1va 1ve 1vo 1vá 1vé 1ví 1vó 1vú 1vi 1vu 1vü 
-1wa 1we 1wo 1wá 1wé 1wí 1wó 1wú 1wi 1wu 1wü 
-1xa 1xe 1xo 1xá 1xé 1xí 1xó 1xú 1xi 1xu 1xü 
-1ya 1ye 1yo 1yá 1yé 1yí 1yó 1yú 1yi 1yu 1yü 
-1za 1ze 1zo 1zá 1zé 1zí 1zó 1zú 1zi 1zu 1zü 
-1ña 1ñe 1ño 1ñá 1ñé 1ñí 1ñó 1ñú 1ñi 1ñu 1ñü 
+1ba 1be 1bo 1bá 1bé 1bí 1bó 1bú 1bi 1bu 1bü 
+1ca 1ce 1co 1cá 1cé 1cí 1có 1cú 1ci 1cu 1cü 
+1da 1de 1do 1dá 1dé 1dí 1dó 1dú 1di 1du 1dü 
+1fa 1fe 1fo 1fá 1fé 1fí 1fó 1fú 1fi 1fu 1fü 
+1ga 1ge 1go 1gá 1gé 1gí 1gó 1gú 1gi 1gu 1gü 
+1ja 1je 1jo 1já 1jé 1jí 1jó 1jú 1ji 1ju 1jü 
+1ka 1ke 1ko 1ká 1ké 1kí 1kó 1kú 1ki 1ku 1kü 
+1la 1le 1lo 1lá 1lé 1lí 1ló 1lú 1li 1lu 1lü 
+1ma 1me 1mo 1má 1mé 1mí 1mó 1mú 1mi 1mu 1mü 
+1na 1ne 1no 1ná 1né 1ní 1nó 1nú 1ni 1nu 1nü 
+1pa 1pe 1po 1pá 1pé 1pí 1pó 1pú 1pi 1pu 1pü 
+1qa 1qe 1qo 1qá 1qé 1qí 1qó 1qú 1qi 1qu 1qü 
+1ra 1re 1ro 1rá 1ré 1rí 1ró 1rú 1ri 1ru 1rü 
+1sa 1se 1so 1sá 1sé 1sí 1só 1sú 1si 1su 1sü 
+1ta 1te 1to 1tá 1té 1tí 1tó 1tú 1ti 1tu 1tü 
+1va 1ve 1vo 1vá 1vé 1ví 1vó 1vú 1vi 1vu 1vü 
+1wa 1we 1wo 1wá 1wé 1wí 1wó 1wú 1wi 1wu 1wü 
+1xa 1xe 1xo 1xá 1xé 1xí 1xó 1xú 1xi 1xu 1xü 
+1ya 1ye 1yo 1yá 1yé 1yí 1yó 1yú 1yi 1yu 1yü 
+1za 1ze 1zo 1zá 1zé 1zí 1zó 1zú 1zi 1zu 1zü 
+1ña 1ñe 1ño 1ñá 1ñé 1ñí 1ñó 1ñú 1ñi 1ñu 1ñü 
 <!--
 % Rule SR3
 % Build legal consonant groups, leave other consonants bound to 
 % the previous group. This overrides part of the SR2 pattern
 % group.
 -->
-1c2ha 1c2he 1c2ho 1c2há 1c2hé 1c2hí 1c2hó 1c2hú 1c2hi 1c2hu 1c2hü 
-1l2la 1l2le 1l2lo 1l2lá 1l2lé 1l2lí 1l2ló 1l2lú 1l2li 1l2lu 1l2lü 
-1r2ra 1r2re 1r2ro 1r2rá 1r2ré 1r2rí 1r2ró 1r2rú 1r2ri 1r2ru 1r2rü 
-1b2la 1b2le 1b2lo 1b2lá 1b2lé 1b2lí 1b2ló 1b2lú 1b2li 1b2lu 1b2lü 
-1b2ra 1b2re 1b2ro 1b2rá 1b2ré 1b2rí 1b2ró 1b2rú 1b2ri 1b2ru 1b2rü 
-1c2la 1c2le 1c2lo 1c2lá 1c2lé 1c2lí 1c2ló 1c2lú 1c2li 1c2lu 1c2lü 
-1c2ra 1c2re 1c2ro 1c2rá 1c2ré 1c2rí 1c2ró 1c2rú 1c2ri 1c2ru 1c2rü 
-1d2ra 1d2re 1d2ro 1d2rá 1d2ré 1d2rí 1d2ró 1d2rú 1d2ri 1d2ru 1d2rü 
-1f2la 1f2le 1f2lo 1f2lá 1f2lé 1f2lí 1f2ló 1f2lú 1f2li 1f2lu 1f2lü 
-1f2ra 1f2re 1f2ro 1f2rá 1f2ré 1f2rí 1f2ró 1f2rú 1f2ri 1f2ru 1f2rü 
-1g2la 1g2le 1g2lo 1g2lá 1g2lé 1g2lí 1g2ló 1g2lú 1g2li 1g2lu 1g2lü 
-1g2ra 1g2re 1g2ro 1g2rá 1g2ré 1g2rí 1g2ró 1g2rú 1g2ri 1g2ru 1g2rü 
-1k2la 1k2le 1k2lo 1k2lá 1k2lé 1k2lí 1k2ló 1k2lú 1k2li 1k2lu 1k2lü 
-1k2ra 1k2re 1k2ro 1k2rá 1k2ré 1k2rí 1k2ró 1k2rú 1k2ri 1k2ru 1k2rü 
-1p2la 1p2le 1p2lo 1p2lá 1p2lé 1p2lí 1p2ló 1p2lú 1p2li 1p2lu 1p2lü 
-1p2ra 1p2re 1p2ro 1p2rá 1p2ré 1p2rí 1p2ró 1p2rú 1p2ri 1p2ru 1p2rü 
-1t2ra 1t2re 1t2ro 1t2rá 1t2ré 1t2rí 1t2ró 1t2rú 1t2ri 1t2ru 1t2rü 
+1c2ha 1c2he 1c2ho 1c2há 1c2hé 1c2hí 1c2hó 1c2hú 1c2hi 1c2hu 1c2hü 
+1l2la 1l2le 1l2lo 1l2lá 1l2lé 1l2lí 1l2ló 1l2lú 1l2li 1l2lu 1l2lü 
+1r2ra 1r2re 1r2ro 1r2rá 1r2ré 1r2rí 1r2ró 1r2rú 1r2ri 1r2ru 1r2rü 
+1b2la 1b2le 1b2lo 1b2lá 1b2lé 1b2lí 1b2ló 1b2lú 1b2li 1b2lu 1b2lü 
+1b2ra 1b2re 1b2ro 1b2rá 1b2ré 1b2rí 1b2ró 1b2rú 1b2ri 1b2ru 1b2rü 
+1c2la 1c2le 1c2lo 1c2lá 1c2lé 1c2lí 1c2ló 1c2lú 1c2li 1c2lu 1c2lü 
+1c2ra 1c2re 1c2ro 1c2rá 1c2ré 1c2rí 1c2ró 1c2rú 1c2ri 1c2ru 1c2rü 
+1d2ra 1d2re 1d2ro 1d2rá 1d2ré 1d2rí 1d2ró 1d2rú 1d2ri 1d2ru 1d2rü 
+1f2la 1f2le 1f2lo 1f2lá 1f2lé 1f2lí 1f2ló 1f2lú 1f2li 1f2lu 1f2lü 
+1f2ra 1f2re 1f2ro 1f2rá 1f2ré 1f2rí 1f2ró 1f2rú 1f2ri 1f2ru 1f2rü 
+1g2la 1g2le 1g2lo 1g2lá 1g2lé 1g2lí 1g2ló 1g2lú 1g2li 1g2lu 1g2lü 
+1g2ra 1g2re 1g2ro 1g2rá 1g2ré 1g2rí 1g2ró 1g2rú 1g2ri 1g2ru 1g2rü 
+1k2la 1k2le 1k2lo 1k2lá 1k2lé 1k2lí 1k2ló 1k2lú 1k2li 1k2lu 1k2lü 
+1k2ra 1k2re 1k2ro 1k2rá 1k2ré 1k2rí 1k2ró 1k2rú 1k2ri 1k2ru 1k2rü 
+1p2la 1p2le 1p2lo 1p2lá 1p2lé 1p2lí 1p2ló 1p2lú 1p2li 1p2lu 1p2lü 
+1p2ra 1p2re 1p2ro 1p2rá 1p2ré 1p2rí 1p2ró 1p2rú 1p2ri 1p2ru 1p2rü 
+1t2ra 1t2re 1t2ro 1t2rá 1t2ré 1t2rí 1t2ró 1t2rú 1t2ri 1t2ru 1t2rü 
 <!--
 % Rule SR4 is implicitly implemented by the default values
 % Rule HE1 is implemented by TeX parameters \lefthyphenmin and
@@ -193,7 +193,7 @@ zZ
 % Rule HE2
 % Break between a consonant and an h
 -->
-b1h d1h f1h g1h j1h k1h l1h m1h n1h p1h q1h r1h s1h t1h v1h w1h x1h y1h z1h ñ1h 
+b1h d1h f1h g1h j1h k1h l1h m1h n1h p1h q1h r1h s1h t1h v1h w1h x1h y1h z1h ñ1h 
 <!-- % We now avoid some problematic breaks. -->
 su2b2r su2b2l
 <!--

itext/itext.hyph/en_GB.xml

@@ -1,4 +1,4 @@
-<?xml version="1.0" encoding="iso-8859-1"?>
+<?xml version="1.0" encoding="utf-8"?>
 <!-- Constructed by Jarno Elovirta from fi8hyph.tex file:
 
 % fi8hyph.tex, based on fihyph.tex
@@ -53,8 +53,8 @@ wW
 xX
 yY
 zZ
-äÄ
-öÖ
+äÄ
+öÖ
 </classes>
 <patterns>
 1be
@@ -68,8 +68,8 @@ zZ
 1do
 1du
 1dy
-1dä
-1dö
+1dä
+1dö
 1fa
 1fe
 1fi
@@ -82,96 +82,96 @@ zZ
 1go
 1gu
 1gy
-1gä
-1gö
+1gä
+1gö
 1ha
 1he
 1hi
 1ho
 1hu
 1hy
-1hä
-1hö
+1hä
+1hö
 1ja
 1je
 1ji
 1jo
 1ju
 1jy
-1jä
-1jö
+1jä
+1jö
 1ka
 1ke
 1ki
 1ko
 1ku
 1ky
-1kä
-1kö
+1kä
+1kö
 1la
 1le
 1li
 1lo
 1lu
 1ly
-1lä
-1lö
+1lä
+1lö
 1ma
 1me
 1mi
 1mo
 1mu
 1my
-1mä
-1mö
+1mä
+1mö
 1na
 1ne
 1ni
 1no
 1nu
 1ny
-1nä
-1nö
+1nä
+1nö
 1pa
 1pe
 1pi
 1po
 1pu
 1py
-1pä
-1pö
+1pä
+1pö
 1ra
 1re
 1ri
 1ro
 1ru
 1ry
-1rä
-1rö
+1rä
+1rö
 1sa
 1se
 1si
 1so
 1su
 1sy
-1sä
-1sö
+1sä
+1sö
 1ta
 1te
 1ti
 1to
 1tu
 1ty
-1tä
-1tö
+1tä
+1tö
 1va
 1ve
 1vi
 1vo
 1vu
 1vy
-1vä
-1vö
+1vä
+1vö
 <!-- % ======= Some common words borrowed from other languages ======= -->
 <!-- % ======= This part could be updated from time to time    ======= -->
 <!-- % -->
@@ -180,29 +180,29 @@ zZ
 <!-- %  ====== Some special cases occuring with compound words only ==== -->
 <!-- %  ====== There still remains well known problem as 'kaivos\-aukko' etc. -->
 <!-- %a1y   (common in borrowed words) -->
-ä2y
+ä2y
 y1a2
 y1o2
 o1y
-ö2y
+ö2y
 u1y2
 y1u2
-ö3a2
-ö3o2
-ä3a2
-ä3o2
-ä1u2
-ö1u2
-a1ä    <!-- % (a1ä2 ei mahdollinen!) -->
-a1ö
-o1ä
-o1ö
-u1ä2
-u1ö2
-ä2ä
-ö2ö
-ä2ö
-ö2ä
+ö3a2
+ö3o2
+ä3a2
+ä3o2
+ä1u2
+ö1u2
+a1ä    <!-- % (a1ä2 ei mahdollinen!) -->
+a1ö
+o1ä
+o1ö
+u1ä2
+u1ö2
+ä2ä
+ö2ö
+ä2ö
+ö2ä
 <!-- %    lyhyt/pitka -vokaalipareja, tavallisesti sanarajalla -->
 aa1i2    <!-- % maa-ikkuna -->
 aa1e2
@@ -228,13 +228,13 @@ a1uu     <!-- % kala-uuni -->
 i1uu     <!-- % ravi-uutiset -->
 e1uu     <!-- % virhe-uutinen -->
 o1uu     <!-- % radio-uutiset -->
-ää1i
-ää1e
-ää3y
-i1ää
-e1ää
-y1ää
-i1öö  <!-- % yhti-öön etc. -->
+ää1i
+ää1e
+ää3y
+i1ää
+e1ää
+y1ää
+i1öö  <!-- % yhti-öön etc. -->
 <!-- %i1eu     % keski-eurooppalainen -->
 <!-- %          vokaalikolmikkoja etc.  yhdyssanojen rajoissa -->
 <!-- % =======- vowel triples by Fred Karlsson -->
@@ -274,9 +274,9 @@ uo1a
 <!-- % uo1i % ambiguous -->
 uo1u
 <!-- %   ================ End of vowel triples ==================== -->
-e1ö2
-ö1e2
-.ä2     <!-- % don't hyphenate  ä-lyllinen etc. -->
+e1ö2
+ö1e2
+.ä2     <!-- % don't hyphenate  ä-lyllinen etc. -->
 <!-- % -->
 <!-- % The following patterns contain no general scientific rule. They -->
 <!-- % are selected more or less intuitively to solve problems -->