From d6d2eeb0041006b751fe6ba72b9d3a6300d9b1ac Mon Sep 17 00:00:00 2001 From: amontano Date: Tue, 1 May 2007 02:38:45 +0000 Subject: [PATCH] Updated installers to include unicode to wylie and acip to wylie. --- source/org/thdl/tib/input/ConvertDialog.java | 17 ++- .../tib/input/FontConverterConstants.java | 15 +- .../org/thdl/tib/input/TibetanConverter.java | 13 +- .../BasicTibetanTranscriptionConverter.java | 130 ++++++++++-------- 4 files changed, 103 insertions(+), 72 deletions(-) diff --git a/source/org/thdl/tib/input/ConvertDialog.java b/source/org/thdl/tib/input/ConvertDialog.java index 7b13237..66e131e 100644 --- a/source/org/thdl/tib/input/ConvertDialog.java +++ b/source/org/thdl/tib/input/ConvertDialog.java @@ -238,12 +238,15 @@ class ConvertDialog extends JDialog || cmd.equals(BROWSENEW)) { JButton src = (JButton)ae.getSource(); + String choice = (String)choices.getSelectedItem(); if (src == browseOld) { - jfc.setFileFilter((ACIP_TO_UNI_TEXT.equals((String)choices.getSelectedItem()) - || WYLIE_TO_UNI_TEXT.equals((String)choices.getSelectedItem()) - || UNI_TO_WYLIE_TEXT.equals((String)choices.getSelectedItem()) - || ACIP_TO_TMW.equals((String)choices.getSelectedItem()) - || WYLIE_TO_TMW.equals((String)choices.getSelectedItem())) + jfc.setFileFilter((ACIP_TO_UNI_TEXT.equals(choice) + || WYLIE_TO_UNI_TEXT.equals(choice) + || UNI_TO_WYLIE_TEXT.equals(choice) + || ACIP_TO_TMW.equals(choice) + || WYLIE_TO_TMW.equals(choice) + || ACIP_TO_WYLIE_TEXT.equals(choice) + || WYLIE_TO_ACIP_TEXT.equals(choice)) ? textFileFilter : rtfFileFilter); } else { jfc.setFileFilter((ACIP_TO_UNI_TEXT.equals((String)choices.getSelectedItem()) @@ -500,12 +503,12 @@ class ConvertDialog extends JDialog newFileNamePrefix = suggested_WYLIE_prefix; if (UNI_TO_WYLIE_TEXT == ct) newFileNameExtension = ".TXT"; - } else if (TMW_TO_WYLIE_TEXT == ct) { + } else if (TMW_TO_WYLIE_TEXT == ct || ACIP_TO_WYLIE_TEXT == ct) { newFileNamePrefix = suggested_WYLIE_prefix; newFileNameExtension = ".TXT"; } else if (TMW_TO_ACIP == ct) { newFileNamePrefix = suggested_ACIP_prefix; - } else if (TMW_TO_ACIP_TEXT == ct) { + } else if (TMW_TO_ACIP_TEXT == ct || WYLIE_TO_ACIP_TEXT == ct) { newFileNamePrefix = suggested_ACIP_prefix; newFileNameExtension = ".TXT"; } else if (TMW_TO_UNI == ct || ACIP_TO_UNI_TEXT == ct diff --git a/source/org/thdl/tib/input/FontConverterConstants.java b/source/org/thdl/tib/input/FontConverterConstants.java index a3b5b35..bec4ea5 100644 --- a/source/org/thdl/tib/input/FontConverterConstants.java +++ b/source/org/thdl/tib/input/FontConverterConstants.java @@ -22,13 +22,15 @@ package org.thdl.tib.input; /** Constants used by ConvertDialog. @author Nathaniel Garson, Tibetan and Himalayan Digital Library */ -interface FontConverterConstants +public interface FontConverterConstants { - final String UNI_TO_WYLIE_TEXT = "Unicode to Wylie (UTF-8 Text->Text)"; + final String UNI_TO_WYLIE_TEXT = "Unicode to Wylie (UTF-16 Text->Text)"; final String WYLIE_TO_UNI_TEXT = "Wylie to Unicode (Text->Text)"; final String WYLIE_TO_TMW = "Wylie to TMW (Text->RTF)"; + final String WYLIE_TO_ACIP_TEXT = "Wylie to ACIP (Text->Text)"; final String TMW_TO_SAME_TMW = "TMW to the same TMW (for testing only) (RTF->RTF)"; final String ACIP_TO_UNI_TEXT = "ACIP to Unicode (Text->Text)"; + final String ACIP_TO_WYLIE_TEXT = "ACIP to Wylie (Text->Text)"; final String ACIP_TO_TMW = "ACIP to TMW (Text->RTF)"; final String TMW_TO_ACIP = "TMW to ACIP (RTF->RTF)"; final String TMW_TO_ACIP_TEXT = "TMW to ACIP (RTF->Text)"; @@ -45,7 +47,9 @@ interface FontConverterConstants final String[] CHOICES = new String[] { WYLIE_TO_UNI_TEXT, WYLIE_TO_TMW, + //WYLIE_TO_ACIP_TEXT, ACIP_TO_UNI_TEXT, + ACIP_TO_WYLIE_TEXT, ACIP_TO_TMW, TMW_TO_ACIP, TMW_TO_ACIP_TEXT, @@ -54,6 +58,7 @@ interface FontConverterConstants TMW_TO_UNI, TMW_TO_WYLIE, TMW_TO_WYLIE_TEXT, + UNI_TO_WYLIE_TEXT, FIND_SOME_NON_TMW, // TODO(dchandler): should this be in DEBUG_CHOICES only? FIND_SOME_NON_TM, // TODO(dchandler): should this be in DEBUG_CHOICES only? FIND_ALL_NON_TMW, // TODO(dchandler): should this be in DEBUG_CHOICES only? @@ -61,11 +66,11 @@ interface FontConverterConstants }; final String[] DEBUG_CHOICES = new String[] { - UNI_TO_WYLIE_TEXT, TMW_TO_SAME_TMW, WYLIE_TO_UNI_TEXT, WYLIE_TO_TMW, ACIP_TO_UNI_TEXT, + ACIP_TO_WYLIE_TEXT, ACIP_TO_TMW, TMW_TO_ACIP, TMW_TO_ACIP_TEXT, @@ -74,6 +79,7 @@ interface FontConverterConstants TMW_TO_UNI, TMW_TO_WYLIE, TMW_TO_WYLIE_TEXT, + UNI_TO_WYLIE_TEXT, FIND_SOME_NON_TMW, FIND_SOME_NON_TM, FIND_ALL_NON_TMW, @@ -88,5 +94,4 @@ interface FontConverterConstants // String Constants public final String PROGRAM_TITLE = "THDL Tibetan Converters -- featuring Jskad Technology"; - -} +} \ No newline at end of file diff --git a/source/org/thdl/tib/input/TibetanConverter.java b/source/org/thdl/tib/input/TibetanConverter.java index 2af64ca..4562dc7 100644 --- a/source/org/thdl/tib/input/TibetanConverter.java +++ b/source/org/thdl/tib/input/TibetanConverter.java @@ -26,6 +26,7 @@ import java.io.InputStream; import java.io.InputStreamReader; import java.io.OutputStreamWriter; import java.io.PrintStream; +import java.io.PrintWriter; import java.util.ArrayList; import javax.swing.text.SimpleAttributeSet; @@ -43,6 +44,7 @@ import org.thdl.util.ThdlDebug; import org.thdl.util.ThdlLazyException; import org.thdl.util.ThdlOptions; import org.thdl.util.ThdlVersion; +import org.thdl.tib.scanner.*; /** TibetanConverter is a command-line utility for converting to and * from Tibetan Machine Web (TMW). It converts TMW to Wylie, ACIP, @@ -329,9 +331,9 @@ public class TibetanConverter implements FontConverterConstants { static int reallyConvert(InputStream in, PrintStream out, String ct, String warningLevel, boolean shortMessages, boolean colors) { - if (UNI_TO_WYLIE_TEXT == ct) { + if (UNI_TO_WYLIE_TEXT == ct || WYLIE_TO_ACIP_TEXT == ct || ACIP_TO_WYLIE_TEXT == ct) { try { - String uniText; + /*String uniText; { // TODO(dchandler): use, here and elsewhere in the // codebase, @@ -355,7 +357,12 @@ public class TibetanConverter implements FontConverterConstants { String ewtsText = Converter.convertToEwtsForComputers(uniText, errors); // TODO(dchandler): is 51 the right choice? - return (errors.length() > 0) ? 51 : 0; + return (errors.length() > 0) ? 51 : 0;*/ + BasicTibetanTranscriptionConverter bc = null; + if (UNI_TO_WYLIE_TEXT == ct) bc = new BasicTibetanTranscriptionConverter(new BufferedReader(new InputStreamReader(in, "UTF16")), new PrintWriter(out)); + else bc = new BasicTibetanTranscriptionConverter(new BufferedReader(new InputStreamReader(in)), new PrintWriter(out)); + bc.run(ct); + return 0; } catch (IOException e) { // TODO(dchandler): print it? where to? return 48; diff --git a/source/org/thdl/tib/scanner/BasicTibetanTranscriptionConverter.java b/source/org/thdl/tib/scanner/BasicTibetanTranscriptionConverter.java index ce6f227..f10ef88 100644 --- a/source/org/thdl/tib/scanner/BasicTibetanTranscriptionConverter.java +++ b/source/org/thdl/tib/scanner/BasicTibetanTranscriptionConverter.java @@ -23,6 +23,7 @@ import org.thdl.tib.text.TibTextUtils; import org.thdl.tib.text.TibetanDocument; import org.thdl.tib.text.reverter.Converter; import org.thdl.tib.text.ttt.EwtsToUnicodeForXslt; +import org.thdl.tib.input.*; import org.thdl.util.*; import java.net.*; import java.io.*; @@ -35,12 +36,12 @@ import java.io.*; * @author Andres Montano * */ -public class BasicTibetanTranscriptionConverter +public class BasicTibetanTranscriptionConverter implements FontConverterConstants { private static BufferedReader in; private static PrintWriter out; - private static int conversionType=0; + //private static int conversionType=0; private static final int ACIP_TO_WYLIE=1; private static final int WYLIE_TO_ACIP=2; private static final int UNICODE_TO_WYLIE=3; @@ -81,39 +82,39 @@ public class BasicTibetanTranscriptionConverter aa -> a, a'a -> A, ai->i, aee ->ai, au->u, aoo->au, ae->e, ao->o, ee->ai, oo->au, 'I->-I I->-i, a'i->I, a'u->U, a'e->E, a'o->O, a'i->I, a'u->U, a'e->E, a'o->O, ,->/, # -> @##, * -> @#, \ -> ?, ` -> !, - /-/ -> (-), ga-y -> g.y, g-y -> g.y, na-y -> n+y + /-/ -> (-), ga-y -> g.y, g-y -> g.y, na-y -> n+y */ - nuevaLinea = replace(nuevaLinea, "ts", "tq"); - nuevaLinea = replace(nuevaLinea, "tz", "ts"); - nuevaLinea = replace(nuevaLinea, "tq", "tsh"); - nuevaLinea = replace(nuevaLinea, "v", "w"); - nuevaLinea = replace(nuevaLinea, "TH", "Th"); - nuevaLinea = replace(nuevaLinea, "kSH", "k+Sh"); - nuevaLinea = replace(nuevaLinea, "kaSH", "k+Sh"); - nuevaLinea = replace(nuevaLinea, "SH", "Sh"); - nuevaLinea = replace(nuevaLinea, ":", "H"); - nuevaLinea = replace(nuevaLinea, "NH", "NaH"); - nuevaLinea = replace(nuevaLinea, "dh", "d+h"); - nuevaLinea = replace(nuevaLinea, "gh", "g+h"); - nuevaLinea = replace(nuevaLinea, "bh", "b+h"); - nuevaLinea = replace(nuevaLinea, "dzh", "dz+h"); - nuevaLinea = replace(nuevaLinea, "aa", "a"); - nuevaLinea = replace(nuevaLinea, "ai", "i"); - nuevaLinea = replace(nuevaLinea, "aee", "ai"); - nuevaLinea = replace(nuevaLinea, "au", "u"); - nuevaLinea = replace(nuevaLinea, "aoo", "au"); - nuevaLinea = replace(nuevaLinea, "ae", "e"); - nuevaLinea = replace(nuevaLinea, "ao", "o"); - nuevaLinea = replace(nuevaLinea, "ee", "ai"); - nuevaLinea = replace(nuevaLinea, "oo", "au"); - nuevaLinea = replace(nuevaLinea, "\'I", "\'q"); - nuevaLinea = replace(nuevaLinea, "I", "-i"); - nuevaLinea = replace(nuevaLinea, "\'q", "-I"); - nuevaLinea = replace(nuevaLinea, "\\", "?"); - nuevaLinea = replace(nuevaLinea, "`", "!"); - nuevaLinea = replace(nuevaLinea, "ga-y", "g.y"); - nuevaLinea = replace(nuevaLinea, "g-y", "g.y"); - nuevaLinea = replace(nuevaLinea, "na-y", "n+y"); + /* nuevaLinea = Manipulate.replace(nuevaLinea, "ts", "tq"); + nuevaLinea = Manipulate.replace(nuevaLinea, "tz", "ts"); + nuevaLinea = Manipulate.replace(nuevaLinea, "tq", "tsh"); + nuevaLinea = Manipulate.replace(nuevaLinea, "v", "w"); + nuevaLinea = Manipulate.replace(nuevaLinea, "TH", "Th"); + nuevaLinea = Manipulate.replace(nuevaLinea, "kSH", "k+Sh"); + nuevaLinea = Manipulate.replace(nuevaLinea, "kaSH", "k+Sh"); + nuevaLinea = Manipulate.replace(nuevaLinea, "SH", "Sh"); + nuevaLinea = Manipulate.replace(nuevaLinea, ":", "H"); + nuevaLinea = Manipulate.replace(nuevaLinea, "NH", "NaH"); + nuevaLinea = Manipulate.replace(nuevaLinea, "dh", "d+h"); + nuevaLinea = Manipulate.replace(nuevaLinea, "gh", "g+h"); + nuevaLinea = Manipulate.replace(nuevaLinea, "bh", "b+h"); + nuevaLinea = Manipulate.replace(nuevaLinea, "dzh", "dz+h"); + nuevaLinea = Manipulate.replace(nuevaLinea, "aa", "a"); + nuevaLinea = Manipulate.replace(nuevaLinea, "ai", "i"); + nuevaLinea = Manipulate.replace(nuevaLinea, "aee", "ai"); + nuevaLinea = Manipulate.replace(nuevaLinea, "au", "u"); + nuevaLinea = Manipulate.replace(nuevaLinea, "aoo", "au"); + nuevaLinea = Manipulate.replace(nuevaLinea, "ae", "e"); + nuevaLinea = Manipulate.replace(nuevaLinea, "ao", "o"); + nuevaLinea = Manipulate.replace(nuevaLinea, "ee", "ai"); + nuevaLinea = Manipulate.replace(nuevaLinea, "oo", "au"); + nuevaLinea = Manipulate.replace(nuevaLinea, "\'I", "\'q"); + nuevaLinea = Manipulate.replace(nuevaLinea, "I", "-i"); + nuevaLinea = Manipulate.replace(nuevaLinea, "\'q", "-I"); + nuevaLinea = Manipulate.replace(nuevaLinea, "\\", "?"); + nuevaLinea = Manipulate.replace(nuevaLinea, "`", "!"); + nuevaLinea = Manipulate.replace(nuevaLinea, "ga-y", "g.y"); + nuevaLinea = Manipulate.replace(nuevaLinea, "g-y", "g.y"); + nuevaLinea = Manipulate.replace(nuevaLinea, "na-y", "n+y"); len = nuevaLinea.length(); for (i=0; i