[dasher: 112/217] Move "Latin ISO-8859" alphabet out of "Latin" alphabet file



commit 6a51f8b3735d77d5042a5f1d59dc904763ffd602
Author: David Barnett <dbarnett google com>
Date:   Thu Nov 5 09:12:09 2015 -0800

    Move "Latin ISO-8859" alphabet out of "Latin" alphabet file

 Data/alphabets/Makefile.am          |    1 +
 Data/alphabets/alphabet.iso8859.xml |  176 +++++++++++++++++++++++++++++++++++
 Data/alphabets/alphabet.latin.xml   |  173 +----------------------------------
 3 files changed, 178 insertions(+), 172 deletions(-)
---
diff --git a/Data/alphabets/Makefile.am b/Data/alphabets/Makefile.am
index 9498817..794be2a 100644
--- a/Data/alphabets/Makefile.am
+++ b/Data/alphabets/Makefile.am
@@ -87,6 +87,7 @@ dist_pkgdata_DATA = alphabet.dtd alphabet.xsl \
        alphabet.hiragana2.xml          \
        alphabet.hungarian.xml          \
        alphabet.ipa.xml                \
+       alphabet.iso8859.xml            \
        alphabet.italian.xml            \
        alphabet.japanese.canna.xml     \
        alphabet.kazakh.xml             \
diff --git a/Data/alphabets/alphabet.iso8859.xml b/Data/alphabets/alphabet.iso8859.xml
new file mode 100644
index 0000000..e696f7d
--- /dev/null
+++ b/Data/alphabets/alphabet.iso8859.xml
@@ -0,0 +1,176 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<!DOCTYPE alphabets SYSTEM "alphabet.dtd">
+<?xml-stylesheet type="text/xsl" href="alphabet.xsl"?>
+<alphabets>
+<alphabet name="Latin ISO-8859 (combining accents) with numerals and punctuation">
+<!--
+Any word that can be written using one of the Latin ISO-8859 character sets 
(ISO-8859-1,2,3,4,9,10,13,14,15,16) can be written, in decomposed form, using the ASCII characters, the 23 
additional letters, and 14 modifiers
+-->
+<orientation type="LR"/>
+<encoding type="Western"/>
+<palette>European/Asian</palette>
+<train>training_frenchC_FR.txt</train>
+<langcode>fr</langcode>
+<space d="&#x25a1;" t=" " b="9" note="box" />
+<control d="Control" t="" b="8"/>
+<paragraph d="&#182;" b="9"/>
+<group name="Combining accents" b="191"  visible="on">
+<s d="&#x25cc;&#x0300;"  t="&#x0300;" b="72" note="&#x0060; COMBINING GRAVE ACCENT  "/>
+<s d="&#x25cc;&#x0301;"  t="&#x0301;" b="82" note="&#x00B4; COMBINING ACUTE ACCENT  "/>
+<s d="&#x25cc;&#x0302;"  t="&#x0302;" b="72" note="&#x005E; COMBINING CIRCUMFLEX ACCENT  "/>
+<s d="&#x25cc;&#x0303;"  t="&#x0303;" b="82" note="&#x007E; COMBINING TILDE  "/>
+<s d="&#x25cc;&#x0304;"  t="&#x0304;" b="72" note="&#x00AF; COMBINING MACRON  "/>
+<s d="&#x25cc;&#x0306;"  t="&#x0306;" b="82" note="&#x02D8; COMBINING BREVE"/>
+<s d="&#x25cc;&#x0307;"  t="&#x0307;" b="72" note="&#x02D9; COMBINING DOT ABOVE"/>
+<s d="&#x25cc;&#x0308;"  t="&#x0308;" b="82" note="&#x00A8; COMBINING DIAERESIS or UMLAUT "/>
+<s d="&#x25cc;&#x030A;"  t="&#x030A;" b="72" note="&#x02DA; COMBINING RING ABOVE"/>
+<s d="&#x25cc;&#x030B;"  t="&#x030B;" b="82" note="&#x02DD; COMBINING DOUBLE ACUTE ACCENT"/>
+<s d="&#x25cc;&#x030C;"  t="&#x030C;" b="72" note="&#x02C7; COMBINING CARON"/>
+<s d="&#x25cc;&#x0326;"  t="&#x0326;" b="82" note="       COMBINING COMMA BELOW"/>
+<s d="&#x25cc;&#x0327;"  t="&#x0327;" b="72" note="&#x00B8; COMBINING CEDILLA  "/>
+<s d="&#x25cc;&#x0328;"  t="&#x0328;" b="82" note="&#x02DB; COMBINING OGONEK"/>
+</group>
+<group name="Lower case Latin letters" b="0">
+<s d="a" t="a" b="10"/>
+<s d="b" t="b" b="11"/>
+<s d="c" t="c" b="12"/>
+<s d="d" t="d" b="13"/>
+<s d="e" t="e" b="14"/>
+<s d="f" t="f" b="15"/>
+<s d="g" t="g" b="16"/>
+<s d="h" t="h" b="17"/>
+<s d="i" t="i" b="18"/>
+<s d="j" t="j" b="19"/>
+<s d="k" t="k" b="20"/>
+<s d="l" t="l" b="21"/>
+<s d="m" t="m" b="22"/>
+<s d="n" t="n" b="23"/>
+<s d="o" t="o" b="24"/>
+<s d="p" t="p" b="25"/>
+<s d="q" t="q" b="26"/>
+<s d="r" t="r" b="27"/>
+<s d="s" t="s" b="28"/>
+<s d="t" t="t" b="29"/>
+<s d="u" t="u" b="30"/>
+<s d="v" t="v" b="31"/>
+<s d="w" t="w" b="32"/>
+<s d="x" t="x" b="33"/>
+<s d="y" t="y" b="34"/>
+<s d="z" t="z" b="35"/>
+</group>
+<group name="Upper case Latin letters"  b="111">
+<s d="A" t="A" b="10"/>
+<s d="B" t="B" b="11"/>
+<s d="C" t="C" b="12"/>
+<s d="D" t="D" b="13"/>
+<s d="E" t="E" b="14"/>
+<s d="F" t="F" b="15"/>
+<s d="G" t="G" b="16"/>
+<s d="H" t="H" b="17"/>
+<s d="I" t="I" b="18"/>
+<s d="J" t="J" b="19"/>
+<s d="K" t="K" b="20"/>
+<s d="L" t="L" b="21"/>
+<s d="M" t="M" b="22"/>
+<s d="N" t="N" b="23"/>
+<s d="O" t="O" b="24"/>
+<s d="P" t="P" b="25"/>
+<s d="Q" t="Q" b="26"/>
+<s d="R" t="R" b="27"/>
+<s d="S" t="S" b="28"/>
+<s d="T" t="T" b="29"/>
+<s d="U" t="U" b="30"/>
+<s d="V" t="V" b="31"/>
+<s d="W" t="W" b="32"/>
+<s d="X" t="X" b="33"/>
+<s d="Y" t="Y" b="34"/>
+<s d="Z" t="Z" b="35"/>
+</group>
+<group name="LC non-ascii Characters" b="70">
+<s d="&#x00E6;" t="&#x00E6;" note="SMALL LETTER AE"/>
+<s d="&#x00F0;" t="&#x00F0;" note="SMALL LETTER ETH"/>
+<s d="&#x0111;" t="&#x0111;" note="SMALL LETTER D WITH STROKE"/>
+<s d="&#x0127;" t="&#x0127;" note="SMALL LETTER H WITH STROKE"/>
+<s d="&#x0131;" t="&#x0131;" note="SMALL LETTER DOTLESS I"/>
+<s d="&#x0138;" t="&#x0138;" note="SMALL LETTER KRA"/>
+<s d="&#x0142;" t="&#x0142;" note="SMALL LETTER L WITH STROKE"/>
+<s d="&#x014B;" t="&#x014B;" note="SMALL LETTER ENG"/>
+<s d="&#x00F8;" t="&#x00F8;" note="SMALL LETTER O WITH STROKE"/>
+<s d="&#x0153;" t="&#x0153;" note="SMALL LIGATURE OE"/>
+<s d="&#x00DF;" t="&#x00DF;" note="SMALL LETTER SHARP S (double s)"/>
+<s d="&#x0167;" t="&#x0167;" note="SMALL LETTER T WITH STROKE"/>
+<s d="&#x00DE;" t="&#x00DE;" note="SMALL LETTER THORN"/>
+</group>
+<group name="UC non-ascii Characters" b="69">
+<s d="&#x00C6;" t="&#x00C6;" note="CAPITAL LETTER AE"/>
+<s d="&#x00D0;" t="&#x00D0;" note="CAPITAL LETTER ETH"/>
+<s d="&#x0110;" t="&#x0110;" note="CAPITAL LETTER D WITH STROKE"/>
+<s d="&#x0126;" t="&#x0126;" note="CAPITAL LETTER H WITH STROKE"/>
+<s d="&#x0141;" t="&#x0141;" note="CAPITAL LETTER L WITH STROKE"/>
+<s d="&#x014A;" t="&#x014A;" note="CAPITAL LETTER ENG"/>
+<s d="&#x00D8;" t="&#x00D8;" note="CAPITAL LETTER O WITH STROKE"/>
+<s d="&#x0152;" t="&#x0152;" note="CAPITAL LIGATURE OE"/>
+<s d="&#x0166;" t="&#x0166;" note="CAPITAL LETTER T WITH STROKE"/>
+<!--ACL: same as small letter <s d="&#x00DE;" t="&#x00DE;" note="CAPITAL LETTER THORN"/>-->
+</group>
+<!-- http://www.fileformat.info/info/unicode/char/ -->
+<group name="Numbers" b="113">
+<s d="1" t="1" b="90"/>
+<s d="2" t="2" b="91"/>
+<s d="3" t="3" b="92"/>
+<s d="4" t="4" b="93"/>
+<s d="5" t="5" b="94"/>
+<s d="6" t="6" b="90"/>
+<s d="7" t="7" b="91"/>
+<s d="8" t="8" b="92"/>
+<s d="9" t="9" b="93"/>
+<s d="0" t="0" b="94"/>
+</group>
+<group name="Punctuation" b="112">
+<s b="90" d="%" t="%"/>
+<s b="91" d="*" t="*"/>
+<s b="92" d="+" t="+"/>
+<s b="93" d="=" t="="/>
+<s b="94" d="/" t="/"/>
+<s b="95" d="#" t="#"/>
+<s d="&#8364;" t="&#8364;" b="96" note="euro" />
+<s b="97"  d="&#163;" t="&#163;" note="Pound" />
+<s b="98" d="$" t="$"/>
+<s b="99" d="|" t="|"/>
+<s b="95" d="\" t="\"/>
+<s b="96" d="~" t="~"/>
+<s b="97" d="^" t="^"/>
+<s b="98" d="_" t="_"/>
+<s b="99" d="&amp;" t="&amp;"/>
+<s b="95" d="@" t="@"/>
+<s b="105" d="[" t="["/>
+<s b="106" d="]" t="]"/>
+<s b="107" d="{" t="{"/>
+<s b="108" d="}" t="}"/>
+<s b="109" d="&lt;" t="&lt;"/>
+<s b="105" d="&gt;" t="&gt;"/>
+<s b="106" d="(" t="("/>
+<s b="107" d=")" t=")"/>
+<s b="108" d="&#x2039;" t="&#x2039;" note="French left single quotation mark" />
+<s b="109" d="&#x203A;" t="&#x203A;" note="French right single quotation mark" />
+<s b="105" d="&#x00AB;" t="&#x00AB;" note="French left double quotation mark" />
+<s b="106" d="&#x00BB;" t="&#x00BB;" note="French right double quotation mark" />
+<s b="107" d="&#x201C;" t="&#x201C;" note="left double quotation mark" />
+<s b="108" d="&#x0022;" t="&#x0022;" note="deprecated vertical double quotation mark" />
+<s b="109" d="&#x201D;" t="&#x201D;" note="right double quotation mark" />
+<s b="107" d="&#x2018;" t="&#x2018;" note="left single quotation mark" />
+<s b="108" d="&#x2019;" t="&#x2019;" note="right single quotation mark and apostrophe" />
+<s b="109" d="`" t="`" note="left quote from keyboard" />
+<s b="105" d="&#x25cc;&#x0313;" t="&apos;" note=" apostrophe"/>
+<s b="9"  d="&#x25CA;" t="&#x9;" note="TAB (represented by a diamond)"/>
+<s b="104" d="&#x2026;" t="&#x2026;" note="ellipsis"/>
+<s b="100" d="-" t="-"/>
+<s b="101" d=":" t=":"/>
+<s b="102" d=";" t=";"/>
+<s b="103" d="?" t="?"/>
+<s b="104" d="!" t="!"/>
+<s b="100" d="," t=","/>
+<s b="104" d="&#183;" t="."/>
+</group>
+</alphabet>
+</alphabets>
diff --git a/Data/alphabets/alphabet.latin.xml b/Data/alphabets/alphabet.latin.xml
index 11dc9b6..2349790 100644
--- a/Data/alphabets/alphabet.latin.xml
+++ b/Data/alphabets/alphabet.latin.xml
@@ -94,7 +94,7 @@
 <s b="96" d="~" t="~"/>
 <s b="97" d="^" t="^"/>
 <s b="98" d="_" t="_"/>
-<s b="99" d="&amp;" t="&amp;"/> 
+<s b="99" d="&amp;" t="&amp;"/>
 <s b="95" d="@" t="@"/>
 <s b="105" d="[" t="["/>
 <s b="106" d="]" t="]"/>
@@ -121,175 +121,4 @@
 <s b="104" d="&#183;" t="."/>
 </group>
 </alphabet>
-<alphabet name="Latin ISO-8859 (combining accents) with numerals and punctuation">
-<!--
-Any word that can be written using one of the Latin ISO-8859 character sets 
(ISO-8859-1,2,3,4,9,10,13,14,15,16) can be written, in decomposed form, using the ASCII characters, the 23 
additional letters, and 14 modifiers
--->
-<orientation type="LR"/>
-<encoding type="Western"/>
-<palette>European/Asian</palette>
-<train>training_frenchC_FR.txt</train>
-<langcode>fr</langcode>
-<space d="&#x25a1;" t=" " b="9" note="box" />
-<control d="Control" t="" b="8"/>
-<paragraph d="&#182;" b="9"/>
-<group name="Combining accents" b="191"  visible="on">
-<s d="&#x25cc;&#x0300;"  t="&#x0300;" b="72" note="&#x0060; COMBINING GRAVE ACCENT  "/>
-<s d="&#x25cc;&#x0301;"  t="&#x0301;" b="82" note="&#x00B4; COMBINING ACUTE ACCENT  "/>
-<s d="&#x25cc;&#x0302;"  t="&#x0302;" b="72" note="&#x005E; COMBINING CIRCUMFLEX ACCENT  "/>
-<s d="&#x25cc;&#x0303;"  t="&#x0303;" b="82" note="&#x007E; COMBINING TILDE  "/>
-<s d="&#x25cc;&#x0304;"  t="&#x0304;" b="72" note="&#x00AF; COMBINING MACRON  "/>
-<s d="&#x25cc;&#x0306;"  t="&#x0306;" b="82" note="&#x02D8; COMBINING BREVE"/>
-<s d="&#x25cc;&#x0307;"  t="&#x0307;" b="72" note="&#x02D9; COMBINING DOT ABOVE"/>
-<s d="&#x25cc;&#x0308;"  t="&#x0308;" b="82" note="&#x00A8; COMBINING DIAERESIS or UMLAUT "/>
-<s d="&#x25cc;&#x030A;"  t="&#x030A;" b="72" note="&#x02DA; COMBINING RING ABOVE"/>
-<s d="&#x25cc;&#x030B;"  t="&#x030B;" b="82" note="&#x02DD; COMBINING DOUBLE ACUTE ACCENT"/>
-<s d="&#x25cc;&#x030C;"  t="&#x030C;" b="72" note="&#x02C7; COMBINING CARON"/>
-<s d="&#x25cc;&#x0326;"  t="&#x0326;" b="82" note="       COMBINING COMMA BELOW"/>
-<s d="&#x25cc;&#x0327;"  t="&#x0327;" b="72" note="&#x00B8; COMBINING CEDILLA  "/>
-<s d="&#x25cc;&#x0328;"  t="&#x0328;" b="82" note="&#x02DB; COMBINING OGONEK"/>
-</group>
-<group name="Lower case Latin letters" b="0">
-<s d="a" t="a" b="10"/>
-<s d="b" t="b" b="11"/>
-<s d="c" t="c" b="12"/>
-<s d="d" t="d" b="13"/>
-<s d="e" t="e" b="14"/>
-<s d="f" t="f" b="15"/>
-<s d="g" t="g" b="16"/>
-<s d="h" t="h" b="17"/>
-<s d="i" t="i" b="18"/>
-<s d="j" t="j" b="19"/>
-<s d="k" t="k" b="20"/>
-<s d="l" t="l" b="21"/>
-<s d="m" t="m" b="22"/>
-<s d="n" t="n" b="23"/>
-<s d="o" t="o" b="24"/>
-<s d="p" t="p" b="25"/>
-<s d="q" t="q" b="26"/>
-<s d="r" t="r" b="27"/>
-<s d="s" t="s" b="28"/>
-<s d="t" t="t" b="29"/>
-<s d="u" t="u" b="30"/>
-<s d="v" t="v" b="31"/>
-<s d="w" t="w" b="32"/>
-<s d="x" t="x" b="33"/>
-<s d="y" t="y" b="34"/>
-<s d="z" t="z" b="35"/>
-</group>
-<group name="Upper case Latin letters"  b="111">
-<s d="A" t="A" b="10"/>
-<s d="B" t="B" b="11"/>
-<s d="C" t="C" b="12"/>
-<s d="D" t="D" b="13"/>
-<s d="E" t="E" b="14"/>
-<s d="F" t="F" b="15"/>
-<s d="G" t="G" b="16"/>
-<s d="H" t="H" b="17"/>
-<s d="I" t="I" b="18"/>
-<s d="J" t="J" b="19"/>
-<s d="K" t="K" b="20"/>
-<s d="L" t="L" b="21"/>
-<s d="M" t="M" b="22"/>
-<s d="N" t="N" b="23"/>
-<s d="O" t="O" b="24"/>
-<s d="P" t="P" b="25"/>
-<s d="Q" t="Q" b="26"/>
-<s d="R" t="R" b="27"/>
-<s d="S" t="S" b="28"/>
-<s d="T" t="T" b="29"/>
-<s d="U" t="U" b="30"/>
-<s d="V" t="V" b="31"/>
-<s d="W" t="W" b="32"/>
-<s d="X" t="X" b="33"/>
-<s d="Y" t="Y" b="34"/>
-<s d="Z" t="Z" b="35"/>
-</group>
-<group name="LC non-ascii Characters" b="70">
-<s d="&#x00E6;" t="&#x00E6;" note="SMALL LETTER AE"/>
-<s d="&#x00F0;" t="&#x00F0;" note="SMALL LETTER ETH"/>
-<s d="&#x0111;" t="&#x0111;" note="SMALL LETTER D WITH STROKE"/>
-<s d="&#x0127;" t="&#x0127;" note="SMALL LETTER H WITH STROKE"/>
-<s d="&#x0131;" t="&#x0131;" note="SMALL LETTER DOTLESS I"/>
-<s d="&#x0138;" t="&#x0138;" note="SMALL LETTER KRA"/>
-<s d="&#x0142;" t="&#x0142;" note="SMALL LETTER L WITH STROKE"/>
-<s d="&#x014B;" t="&#x014B;" note="SMALL LETTER ENG"/>
-<s d="&#x00F8;" t="&#x00F8;" note="SMALL LETTER O WITH STROKE"/>
-<s d="&#x0153;" t="&#x0153;" note="SMALL LIGATURE OE"/>
-<s d="&#x00DF;" t="&#x00DF;" note="SMALL LETTER SHARP S (double s)"/>
-<s d="&#x0167;" t="&#x0167;" note="SMALL LETTER T WITH STROKE"/>
-<s d="&#x00DE;" t="&#x00DE;" note="SMALL LETTER THORN"/>
-</group>
-<group name="UC non-ascii Characters" b="69">
-<s d="&#x00C6;" t="&#x00C6;" note="CAPITAL LETTER AE"/>
-<s d="&#x00D0;" t="&#x00D0;" note="CAPITAL LETTER ETH"/>
-<s d="&#x0110;" t="&#x0110;" note="CAPITAL LETTER D WITH STROKE"/>
-<s d="&#x0126;" t="&#x0126;" note="CAPITAL LETTER H WITH STROKE"/>
-<s d="&#x0141;" t="&#x0141;" note="CAPITAL LETTER L WITH STROKE"/>
-<s d="&#x014A;" t="&#x014A;" note="CAPITAL LETTER ENG"/>
-<s d="&#x00D8;" t="&#x00D8;" note="CAPITAL LETTER O WITH STROKE"/>
-<s d="&#x0152;" t="&#x0152;" note="CAPITAL LIGATURE OE"/>
-<s d="&#x0166;" t="&#x0166;" note="CAPITAL LETTER T WITH STROKE"/>
-<!--ACL: same as small letter <s d="&#x00DE;" t="&#x00DE;" note="CAPITAL LETTER THORN"/>-->
-</group>
-<!-- http://www.fileformat.info/info/unicode/char/ -->
-<group name="Numbers" b="113">
-<s d="1" t="1" b="90"/>
-<s d="2" t="2" b="91"/>
-<s d="3" t="3" b="92"/>
-<s d="4" t="4" b="93"/>
-<s d="5" t="5" b="94"/>
-<s d="6" t="6" b="90"/>
-<s d="7" t="7" b="91"/>
-<s d="8" t="8" b="92"/>
-<s d="9" t="9" b="93"/>
-<s d="0" t="0" b="94"/>
-</group>
-<group name="Punctuation" b="112">
-<s b="90" d="%" t="%"/>
-<s b="91" d="*" t="*"/>
-<s b="92" d="+" t="+"/>
-<s b="93" d="=" t="="/>
-<s b="94" d="/" t="/"/>
-<s b="95" d="#" t="#"/>
-<s d="&#8364;" t="&#8364;" b="96" note="euro" />
-<s b="97"  d="&#163;" t="&#163;" note="Pound" />
-<s b="98" d="$" t="$"/>
-<s b="99" d="|" t="|"/>
-<s b="95" d="\" t="\"/>
-<s b="96" d="~" t="~"/>
-<s b="97" d="^" t="^"/>
-<s b="98" d="_" t="_"/>
-<s b="99" d="&amp;" t="&amp;"/> 
-<s b="95" d="@" t="@"/>
-<s b="105" d="[" t="["/>
-<s b="106" d="]" t="]"/>
-<s b="107" d="{" t="{"/>
-<s b="108" d="}" t="}"/>
-<s b="109" d="&lt;" t="&lt;"/>
-<s b="105" d="&gt;" t="&gt;"/>
-<s b="106" d="(" t="("/>
-<s b="107" d=")" t=")"/>
-<s b="108" d="&#x2039;" t="&#x2039;" note="French left single quotation mark" />
-<s b="109" d="&#x203A;" t="&#x203A;" note="French right single quotation mark" />
-<s b="105" d="&#x00AB;" t="&#x00AB;" note="French left double quotation mark" />
-<s b="106" d="&#x00BB;" t="&#x00BB;" note="French right double quotation mark" />
-<s b="107" d="&#x201C;" t="&#x201C;" note="left double quotation mark" />
-<s b="108" d="&#x0022;" t="&#x0022;" note="deprecated vertical double quotation mark" />
-<s b="109" d="&#x201D;" t="&#x201D;" note="right double quotation mark" />
-<s b="107" d="&#x2018;" t="&#x2018;" note="left single quotation mark" />
-<s b="108" d="&#x2019;" t="&#x2019;" note="right single quotation mark and apostrophe" />
-<s b="109" d="`" t="`" note="left quote from keyboard" />
-<s b="105" d="&#x25cc;&#x0313;" t="&apos;" note=" apostrophe"/>
-<s b="9"  d="&#x25CA;" t="&#x9;" note="TAB (represented by a diamond)"/>
-<s b="104" d="&#x2026;" t="&#x2026;" note="ellipsis"/>
-<s b="100" d="-" t="-"/>
-<s b="101" d=":" t=":"/>
-<s b="102" d=";" t=";"/>
-<s b="103" d="?" t="?"/>
-<s b="104" d="!" t="!"/>
-<s b="100" d="," t=","/>
-<s b="104" d="&#183;" t="."/>
-</group>
-</alphabet>
 </alphabets>


[Date Prev][Date Next]   [Thread Prev][Thread Next]   [Thread Index] [Date Index] [Author Index]