mirror: 初始快照

2026-10-02 22:51:03 +08:00
commit bf87c99809
@@ -0,0 +1,7 @@
+2010-11-03 Piotr Bański
+  * converted to TEI P5
+
+2004-10-04 Michael Bunk
+
+	* initial release
+
@@ -0,0 +1 @@
+../shared/INSTALL
@@ -0,0 +1,7 @@
+# The line below is really just a fallback and only works if you have got a copy of the tools directory at this location. It's better to set the environment variable in your shell.
+FREEDICT_TOOLS ?= ../../tools
+DISTFILES = ChangeLog eng-tur.tei eng-tur.tei.header README ChangeLog ingtur-ing.utf8 \
+	    ingtur-tur.utf8 eng-tur2tei.pl general.footer Makefile  \
+      INSTALL freedict-P5.dtd freedict-P5.rng freedict-P5.xml freedict-dictionary.css
+supported_phonetics=
+include $(FREEDICT_TOOLS)/mk/dicts.mk
@@ -0,0 +1,47 @@
+This database is not related to the existing (and presently
+small) (FreeDict) tur-eng FreeDict database.
+
+The data was taken from the GPL program gtksozluk2:
+ 
+http://www.linuxprogramlama.com/index.php?sayfa=gtksozluk2.htm
+ftp://ftp.deu.edu.tr/pub/infosystem/gtksozluk/gtksozluk-2.2.tgz
+
+Original Turkish files were encoded in ISO 8859-9.
+
+Original Author: Mehmet Ali Vardar <ali@linuxprogramlama.com>
+
+The converter splits Turkish entries at ";" characters to separate
+senses. It also separates translation equivalents at ","
+characters. But this should not be done, since it may split too
+aggressively (at wrong places).
+
+After the eng-tur.tei file was made, `make validation` complains:
+
+> nsgmls:eng-tur.tei:136233:13:E: non SGML character number 149
+
+The offending character was subsituted by a "'".
+
+
+================================================
+
+The TEI P4 version of this database was created by 
+FreeDict tools on the basis of the accompanying 
+non-XML source file(s). Next, that TEI P4 version 
+was converted to TEI P5 using revision 978 of the 
+tools/xsl/freedict_P4toP5.xsl script.
+
+In some cases I checked whether a newer version 
+of the database existed but I wasn't lucky. 
+Still, any maintenance of this dictionary should 
+begin by checking on the existence of an updated version.
+
+Piotr Bański, 3 November 2010
+
+PS. Something is wrong with the splitting indeed, so 
+I leave the P4 version for comparison and commit the 
+freedict_P4toP5.xsl script [revision 1005] so that it 
+is easy to dig out of the SVN in case another P4-to-P5 
+transformation is necessary (possibly, it may be 
+easier to fix at the Perl level). In case that happens,
+please bear in mind that the P5 header has been modified 
+and needs to be copied over to the new P5 version.
@@ -0,0 +1,71 @@
+<?xml version="1.0" encoding="utf-8"?>
+<!DOCTYPE TEI.2
+  PUBLIC "-//TEI P4//DTD Main Document Type//EN"
+  "http://www.tei-c.org/Guidelines/DTD/tei2.dtd" [
+<!ENTITY % TEI.XML          "INCLUDE" >
+<!ENTITY % TEI.dictionaries "INCLUDE" >
+<!ENTITY % TEI.linking	    "INCLUDE" >
+<!ATTLIST xptr url CDATA #IMPLIED >
+<!ATTLIST xref url CDATA #IMPLIED >
+]>
+
+<TEI.2>
+
+  <teiHeader>
+    <fileDesc>
+      <titleStmt>
+	<title>English-Turkish FreeDict Dictionary</title>
+	<respStmt>
+	  <resp>converted by</resp> <name>Michael Bunk &lt;michael.bunk@gmail.com></name>
+	</respStmt>
+      </titleStmt>
+
+      <editionStmt>
+	<edition>0.2</edition>
+      </editionStmt>
+
+      <extent>about 36500 headwords</extent>
+
+      <publicationStmt>
+	<publisher>FreeDict</publisher>
+	<availability>
+	  <p>Available under the terms of the GNU General Public
+	    License.</p>
+	</availability>
+	<date>2004</date>
+	<pubPlace>http://freedict.org/</pubPlace>
+      </publicationStmt>
+
+      <notesStmt>
+	<note type="status">unknown</note><!-- descriptive adjective, eg. "stable" -->
+      </notesStmt>
+
+      <sourceDesc>
+	<p>Home: <xptr url="http://www.linuxprogramlama.com/index.php?sayfa=gtksozluk2.htm"/></p>
+	<p>This file was converted from another electronic document.</p>
+      </sourceDesc>
+    </fileDesc>
+
+    <encodingDesc>
+      <projectDesc>
+	<p>This dictionary comes to you through nice people making it
+	  available for free and for good. It is part of the FreeDict project,
+	  http://www.freedict.org / http://freedict.de. This
+	  project aims to make available many translating dictionaries
+	  for free. Your contributions are welcome!</p>
+      </projectDesc>
+    </encodingDesc>
+    <revisionDesc>
+      <change>
+	<date>2007-02-13</date>
+	<respStmt>
+	  <name>Michael Bunk</name>
+	</respStmt>
+	<item>Enabled phonetics import</item>
+      </change>
+    </revisionDesc>
+  </teiHeader>
+
+<text>
+  <body>
+    <div0 type='dictionary'>
@@ -0,0 +1,54 @@
+#!/usr/bin/perl
+
+open(E, "<:utf8", "ingtur-ing.utf8") || die("can't open ingtur-ing: $!");
+open(T, "<:utf8", "ingtur-tur.utf8") || die("can't open ingtur-tur: $!");
+binmode(STDOUT, ":utf8");
+
+sub escape
+{
+  my $s = shift;
+  $s =~ s/&/&amp;/;
+  return $s;
+}
+
+while(<E>)
+{
+  $e = $_;
+  $e =~ tr/\x{FEFF}//d;# remove Byte Order Mark
+  $e =~ s/\s*\r\n//;# remove trailing space & newline
+
+  $t = <T>;
+  # `ingtur-tur.utf' contains an invalid unicode character, which
+  # leads to `make validation` complaining, if it stays unreplaced:
+  # > nsgmls:eng-tur.tei:136233:13:E: non SGML character number 149
+  $t =~ tr/\x{95}\x{FEFF}/'/d;# remove Byte Order Mark
+  $t =~ s/\s*\r\n//;
+  $t =~ s/^\s*//;# remove leading space
+
+  @senses = split /;/, $t;
+  
+  print "<entry>\n";
+  print "     <form>\n";
+  print '       <orth>' . escape($e) . "</orth>\n";
+  print "     </form>\n";
+  $s = 0;
+  foreach(@senses)
+  {
+    $s++;
+    s/\s*$//;# remove trailing space
+    s/^\s*//;# remove leading space
+    print "     <sense n=\"$s\">\n";
+    print "       <trans>\n";
+    @equiv = split /,/;
+    foreach(@equiv)
+    {
+      s/\s*$//;# remove trailing space
+      s/^\s*//;# remove leading space
+      print '         <tr>' . escape($_) . "</tr>\n";
+    }
+    print "       </trans>\n";
+    print "     </sense>\n";
+  }
+  print "   </entry>\n";
+}
+
@@ -0,0 +1 @@
+../shared/freedict-P5.dtd
@@ -0,0 +1 @@
+../shared/freedict-P5.rng
@@ -0,0 +1 @@
+../shared/freedict-P5.xml
@@ -0,0 +1 @@
+../shared/freedict-dictionary.css
@@ -0,0 +1,2 @@
+</div0></body></text></TEI.2>
+