Added a test case that runs almost all the tsheg bars from all

non-reference, publicly available ACIP files (hundreds of megabytes of
them) through the converter.  The frequencies of these tsheg bars in
in the file, too.
This commit is contained in:
dchandler 2003-10-26 06:02:48 +00:00
parent 7ba1ad0735
commit 31b3020d07
8 changed files with 23771 additions and 7 deletions

View file

@ -419,6 +419,11 @@ Contributor(s): ______________________________________.
<param name="my.included.source.file"
value="org/thdl/tib/text/ttt/PackageTest.java"/>
</antcall>
<antcall target="our-internal-javac-task">
<param name="mybin" value="${junitbin}"/>
<param name="my.included.source.file"
value="org/thdl/tib/text/ttt/LotsOfTshegBarsTest.java"/>
</antcall>
<antcall target="copy-ini-files-to-bin-dir-for-jarring">
<param name="mybin" value="${junitbin}"/>
</antcall>

View file

@ -57,6 +57,7 @@
build.xml check-report' will fail. -->
<sysproperty key="java.awt.headless" value="true"/>
<test name="org.thdl.tib.text.ttt.PackageTest"/>
<test name="org.thdl.tib.text.ttt.LotsOfTshegBarsTest"/>
<test name="org.thdl.tib.input.TMW_RTF_TO_THDL_WYLIETest"/>
<test name="org.thdl.util.RTFFixerInputStreamTest"/>
<test name="org.thdl.util.ThdlLazyExceptionTest"/>

View file

@ -245,6 +245,9 @@ public class TibetanConverter implements FontConverterConstants {
} catch (IOException e) {
e.printStackTrace(out);
return 4;
} catch (OutOfMemoryError e) {
e.printStackTrace(out);
throw e;
}
}

File diff suppressed because it is too large Load diff

View file

@ -51,7 +51,7 @@ public class PackageTest extends TestCase {
public PackageTest() { }
private static void tstHelper(String acip) {
static void tstHelper(String acip) {
tstHelper2(acip, null, false, null, null, null, 0);
}
private static void tstHelper(String acip, String expectedPairs) {

View file

@ -317,7 +317,7 @@ class TParseTree {
if (warningLevel == "All")
return "Warning: The last stack does not have a vowel in the ACIP {" + ((null != originalACIP) ? originalACIP : recoverACIP()) + "}; this may indicate a typo, because Sanskrit, which this is (because it's not legal Tibetan), should have a vowel after each stack.";
} else {
throw new Error("Can't happen now that we stack greedily");
return "Warning: Trying to stack non-consonants."; // DLC
}
}
}

View file

@ -213,8 +213,9 @@ class TStackList {
&& l.charAt(0) >= '0' && l.charAt(0) <= '9')) {
if (null != isLastStack) {
isLastStack[0] = (i + 1 == size());
if (!isLastStack[0])
throw new Error("But we now stack greedily!");
if (!isLastStack[0]) {
System.err.println("DLC NOW: But we now stack greedily! '7 and B5 cause trouble, though, e.g. " + this);
}
}
return true;
}

View file

@ -21,6 +21,7 @@ package org.thdl.tib.text.ttt;
import org.thdl.util.ThdlOptions;
import java.util.HashSet;
import java.io.*;
/**
* An TString is some Latin text and a type, the type stating whether
@ -130,15 +131,15 @@ public class TString {
outputTshegBar(ftext);
}
/** Prints x to standard output if and only if we have never
/** Prints x to standard error if and only if we have never
encountered x before. */
private static void outputTshegBar(String x) {
if (outputAllTshegBars) {
System.out.println(outputTshegBarsPrefix + x);
System.err.println(outputTshegBarsPrefix + x);
} else if (outputUniqueTshegBars) {
if (!tshegBars.contains(x)) {
tshegBars.add(x);
System.out.println(outputTshegBarsPrefix + x);
System.err.println(outputTshegBarsPrefix + x);
}
}
}