I did this stuff back in August. It's all in support of EWTS->Tibetan

conversion.  The tag 'TODO(DLC)[EWTS->Tibetan]' exists all over the
place.  EWTS->Tibetan isn't here yet; lexing isn't here yet; this is
mainly a refactoring so that the ACIP->Tibetan code can be reused to
do EWTS->Tibetan.

I'm committing this because tests pass (it shouldn't be breaking
anything), because I want a checkpoint, and because the laptop this
sandbox was on isn't my preferred development environment.
This commit is contained in:
dchandler 2005-02-21 01:16:10 +00:00
parent 83f499b7a8
commit 37bf9a736d
26 changed files with 43219 additions and 98 deletions

View file

@ -32,7 +32,9 @@ import org.apache.commons.jrcs.diff.Revision;
/**
* @author David Chandler
*
* Tests {@link org.thdl.tib.input.TibetanConverter} at the unit level.
* Tests {@link org.thdl.tib.input.TibetanConverter} at the unit
* level. The name is a misnomer; we test more than just
* TMW.rtf->EWTS conversions.
*/
public class TMW_RTF_TO_THDL_WYLIETest extends TestCase {
/**
@ -52,6 +54,11 @@ public class TMW_RTF_TO_THDL_WYLIETest extends TestCase {
// We don't want to use options.txt:
ThdlOptions.forTestingOnlyInitializeWithoutDefaultOptionsFile();
ThdlOptions.setUserPreference("thdl.acip.to.tibetan.warning.and.error.severities.are.built.in.defaults", "true");
ThdlOptions.setUserPreference("thdl.acip.to.tibetan.warning.severity.507", "Most");
org.thdl.tib.text.ttt.ErrorsAndWarnings.setupSeverityMap();
// We do want debugging assertions:
ThdlOptions.setUserPreference("thdl.debug", true);
}
@ -77,9 +84,11 @@ public class TMW_RTF_TO_THDL_WYLIETest extends TestCase {
+ "tib" + File.separator
+ "input" + File.separator
+ "TMW_RTF_TO_THDL_WYLIE" + testName + ".expected";
assertTrue("The file the converter should've produced doesn't exist",
assertTrue("The file the converter should've produced doesn't exist: "
+ actualFile,
new File(actualFile).exists());
assertTrue("The baseline file, the file containing the expected results, doesn't exist",
assertTrue("The baseline file, the file containing the expected results, doesn't exist: "
+ expectedFile,
new File(expectedFile).exists());
Revision rev = JDiff.getDiff(expectedFile, actualFile);
assertTrue("JDiff.getDiff returned null", null != rev);
@ -100,16 +109,17 @@ public class TMW_RTF_TO_THDL_WYLIETest extends TestCase {
}
private void helper(String testName, String mode, String extension, int erc) {
private void helper(String testName, String inputExtension, String mode,
String extension, int erc, String errorMessageLength) {
String[] args = new String[] {
"--colors",
"no",
"--warning-level",
"All",
"--acip-to-tibetan-warning-and-error-messages",
"long",
errorMessageLength,
mode,
getTestFileName(testName)
getTestFileName(testName, inputExtension)
};
boolean fileNotFound = false;
try {
@ -126,45 +136,53 @@ public class TMW_RTF_TO_THDL_WYLIETest extends TestCase {
testActualAndExpected(testName + "Result" + extension);
}
private static String getTestFileName(String testName) {
private static String getTestFileName(String testName,
String inputExtension) {
return "source" + File.separator
+ "org" + File.separator
+ "thdl" + File.separator
+ "tib" + File.separator
+ "input" + File.separator
// FIXME: one of the files named '.rtf' is really a text
// file:
+ "TMW_RTF_TO_THDL_WYLIE" + testName + ".rtf";
+ "TMW_RTF_TO_THDL_WYLIE" + testName + inputExtension;
}
/** Tests the --find-some-non-tmw mode of {@link
* org.thdl.tib.input.TibetanConverter}. */
public void testFindSomeNonTMWMode() {
helper("Test1", "--find-some-non-tmw", "FindSome", 1);
helper("Test1", ".rtf", "--find-some-non-tmw", "FindSome", 1, "long");
}
/** Tests the --find-all-non-tmw mode of {@link
* org.thdl.tib.input.TibetanConverter}. */
public void testFindAllNonTMWMode() {
helper("Test1", "--find-all-non-tmw", "FindAll", 1);
helper("Test1", ".rtf", "--find-all-non-tmw", "FindAll", 1, "long");
}
/** Tests the --to-wylie converter mode of {@link
* org.thdl.tib.input.TibetanConverter}. */
public void testConverterMode() {
helper("Test1", "--to-wylie", "Conversion", 0);
helper("Test2", "--to-wylie", "Conversion", 44);
public void testToWylieConverterMode() {
helper("Test1", ".rtf", "--to-wylie", "Conversion", 0, "long");
helper("Test2", ".rtf", "--to-wylie", "Conversion", 44, "long");
}
/** Tests the --to-tibetan-machine, --to-tibetan-machine-web,
* --to-acip, and --acip-to-tmw converter modes of {@link
* org.thdl.tib.input.TibetanConverter}. */
public void testTMConverterMode() {
helper("Test1", "--to-tibetan-machine", "TM", 0);
helper("Test2", "--to-tibetan-machine", "TM", 0);
helper("Test2", "--to-tibetan-machine-web", "TMW", 0);
helper("Test2", "--to-acip", "ACIP", 49);
helper("Test3", "--acip-to-tmw", "TMW", 0);
public void testSomeConverters() {
/* TODO(DLC)[EWTS->Tibetan]: NOW runs out of memory
helper("Test4_aka_TD4222I1.INC", "", "--acip-to-tmw", "TMW", 46,
"short"); */
helper("Test4_aka_TD4222I1.INC", "", "--acip-to-unicode", "UNI", 46,
"short");
helper("Test1", ".rtf", "--to-tibetan-machine", "TM", 0, "long");
helper("Test2", ".rtf", "--to-tibetan-machine", "TM", 0, "long");
helper("Test2", ".rtf", "--to-tibetan-machine-web", "TMW", 0, "long");
helper("Test2", ".rtf", "--to-acip", "ACIP", 49, "long");
helper("Test3", ".acip", "--acip-to-tmw", "TMW", 0, "long");
}
}
// TODO(dchandler): put the line 'THIS IS ENGLISH' in
// TMW_RTF_TO_THDL_WYLIETest3.rtf; what would that mean? I did this once but
// didn't check it in...

View file

@ -0,0 +1,386 @@
[# \u0F40\u0F00: ]\u0F40\u0F00
[# \u0F40\u0F01: ]\u0F40\u0F01
[# \u0F40\u0F02: ]\u0F40\u0F02
[# \u0F40\u0F03: ]\u0F40\u0F03
[# \u0F40\u0F04: ]\u0F40\u0F04
[# \u0F40\u0F05: ]\u0F40\u0F05
[# \u0F40\u0F06: ]\u0F40\u0F06
[# \u0F40\u0F07: ]\u0F40\u0F07
[# \u0F40\u0F08: ]\u0F40\u0F08
[# \u0F40\u0F09: ]\u0F40\u0F09
[# \u0F40\u0F0A: ]\u0F40\u0F0A
[# \u0F40\u0F0B: ]\u0F40\u0F0B
[# \u0F40\u0F0C: ]\u0F40\u0F0C
[# \u0F40\u0F0D: ]\u0F40\u0F0D
[# \u0F40\u0F0E: ]\u0F40\u0F0E
[# \u0F40\u0F0F: ]\u0F40\u0F0F
[# \u0F40\u0F10: ]\u0F40\u0F10
[# \u0F40\u0F11: ]\u0F40\u0F11
[# \u0F40\u0F12: ]\u0F40\u0F12
[# \u0F40\u0F13: ]\u0F40\u0F13
[# \u0F40\u0F14: ]\u0F40\u0F14
[# \u0F40\u0F15: ]\u0F40\u0F15
[# \u0F40\u0F16: ]\u0F40\u0F16
[# \u0F40\u0F17: ]\u0F40\u0F17
[# \u0F40\u0F18: ]\u0F40\u0F18
[# \u0F40\u0F19: ]\u0F40\u0F19
[# \u0F40\u0F1A: ]\u0F40\u0F1A
[# \u0F40\u0F1B: ]\u0F40\u0F1B
[# \u0F40\u0F1C: ]\u0F40\u0F1C
[# \u0F40\u0F1D: ]\u0F40\u0F1D
[# \u0F40\u0F1E: ]\u0F40\u0F1E
[# \u0F40\u0F1F: ]\u0F40\u0F1F
[# \u0F40\u0F20: ]\u0F40\u0F20
[# \u0F40\u0F21: ]\u0F40\u0F21
[# \u0F40\u0F22: ]\u0F40\u0F22
[# \u0F40\u0F23: ]\u0F40\u0F23
[# \u0F40\u0F24: ]\u0F40\u0F24
[# \u0F40\u0F25: ]\u0F40\u0F25
[# \u0F40\u0F26: ]\u0F40\u0F26
[# \u0F40\u0F27: ]\u0F40\u0F27
[# \u0F40\u0F28: ]\u0F40\u0F28
[# \u0F40\u0F29: ]\u0F40\u0F29
[# \u0F40\u0F2A: ]\u0F40\u0F2A
[# \u0F40\u0F2B: ]\u0F40\u0F2B
[# \u0F40\u0F2C: ]\u0F40\u0F2C
[# \u0F40\u0F2D: ]\u0F40\u0F2D
[# \u0F40\u0F2E: ]\u0F40\u0F2E
[# \u0F40\u0F2F: ]\u0F40\u0F2F
[# \u0F40\u0F30: ]\u0F40\u0F30
[# \u0F40\u0F31: ]\u0F40\u0F31
[# \u0F40\u0F32: ]\u0F40\u0F32
[# \u0F40\u0F33: ]\u0F40\u0F33
[# \u0F40\u0F34: ]\u0F40\u0F34
[# \u0F40\u0F35: ]\u0F40\u0F35
[# \u0F40\u0F36: ]\u0F40\u0F36
[# \u0F40\u0F37: ]\u0F40\u0F37
[# \u0F40\u0F38: ]\u0F40\u0F38
[# \u0F40\u0F39: ]\u0F40\u0F39
[# \u0F40\u0F3A: ]\u0F40\u0F3A
[# \u0F40\u0F3B: ]\u0F40\u0F3B
[# \u0F40\u0F3C: ]\u0F40\u0F3C
[# \u0F40\u0F3D: ]\u0F40\u0F3D
[# \u0F40\u0F3E: ]\u0F40\u0F3E
[# \u0F40\u0F3F: ]\u0F40\u0F3F
[# \u0F40\u0F40: ]\u0F40\u0F40
[# \u0F40\u0F41: ]\u0F40\u0F41
[# \u0F40\u0F42: ]\u0F40\u0F42
[# \u0F40\u0F43: ]\u0F40\u0F43
[# \u0F40\u0F44: ]\u0F40\u0F44
[# \u0F40\u0F45: ]\u0F40\u0F45
[# \u0F40\u0F46: ]\u0F40\u0F46
[# \u0F40\u0F47: ]\u0F40\u0F47
[# \u0F40\u0F49: ]\u0F40\u0F49
[# \u0F40\u0F4A: ]\u0F40\u0F4A
[# \u0F40\u0F4B: ]\u0F40\u0F4B
[# \u0F40\u0F4C: ]\u0F40\u0F4C
[# \u0F40\u0F4D: ]\u0F40\u0F4D
[# \u0F40\u0F4E: ]\u0F40\u0F4E
[# \u0F40\u0F4F: ]\u0F40\u0F4F
[# \u0F40\u0F50: ]\u0F40\u0F50
[# \u0F40\u0F51: ]\u0F40\u0F51
[# \u0F40\u0F52: ]\u0F40\u0F52
[# \u0F40\u0F53: ]\u0F40\u0F53
[# \u0F40\u0F54: ]\u0F40\u0F54
[# \u0F40\u0F55: ]\u0F40\u0F55
[# \u0F40\u0F56: ]\u0F40\u0F56
[# \u0F40\u0F57: ]\u0F40\u0F57
[# \u0F40\u0F58: ]\u0F40\u0F58
[# \u0F40\u0F59: ]\u0F40\u0F59
[# \u0F40\u0F5A: ]\u0F40\u0F5A
[# \u0F40\u0F5B: ]\u0F40\u0F5B
[# \u0F40\u0F5C: ]\u0F40\u0F5C
[# \u0F40\u0F5D: ]\u0F40\u0F5D
[# \u0F40\u0F5E: ]\u0F40\u0F5E
[# \u0F40\u0F5F: ]\u0F40\u0F5F
[# \u0F40\u0F60: ]\u0F40\u0F60
[# \u0F40\u0F61: ]\u0F40\u0F61
[# \u0F40\u0F62: ]\u0F40\u0F62
[# \u0F40\u0F63: ]\u0F40\u0F63
[# \u0F40\u0F64: ]\u0F40\u0F64
[# \u0F40\u0F65: ]\u0F40\u0F65
[# \u0F40\u0F66: ]\u0F40\u0F66
[# \u0F40\u0F67: ]\u0F40\u0F67
[# \u0F40\u0F68: ]\u0F40\u0F68
[# \u0F40\u0F69: ]\u0F40\u0F69
[# \u0F40\u0F6A: ]\u0F40\u0F6A
[# \u0F40\u0F71: ]\u0F40\u0F71
[# \u0F40\u0F72: ]\u0F40\u0F72
[# \u0F40\u0F73: ]\u0F40\u0F73
[# \u0F40\u0F74: ]\u0F40\u0F74
[# \u0F40\u0F75: ]\u0F40\u0F75
[# \u0F40\u0F76: ]\u0F40\u0F76
[# \u0F40\u0F77: ]\u0F40\u0F77
[# \u0F40\u0F78: ]\u0F40\u0F78
[# \u0F40\u0F79: ]\u0F40\u0F79
[# \u0F40\u0F7A: ]\u0F40\u0F7A
[# \u0F40\u0F7B: ]\u0F40\u0F7B
[# \u0F40\u0F7C: ]\u0F40\u0F7C
[# \u0F40\u0F7D: ]\u0F40\u0F7D
[# \u0F40\u0F7E: ]\u0F40\u0F7E
[# \u0F40\u0F7F: ]\u0F40\u0F7F
[# \u0F40\u0F80: ]\u0F40\u0F80
[# \u0F40\u0F81: ]\u0F40\u0F81
[# \u0F40\u0F82: ]\u0F40\u0F82
[# \u0F40\u0F83: ]\u0F40\u0F83
[# \u0F40\u0F84: ]\u0F40\u0F84
[# \u0F40\u0F85: ]\u0F40\u0F85
[# \u0F40\u0F86: ]\u0F40\u0F86
[# \u0F40\u0F87: ]\u0F40\u0F87
[# \u0F40\u0F88: ]\u0F40\u0F88
[# \u0F40\u0F89: ]\u0F40\u0F89
[# \u0F40\u0F8A: ]\u0F40\u0F8A
[# \u0F40\u0F8B: ]\u0F40\u0F8B
[# \u0F40\u0F90: ]\u0F40\u0F90
[# \u0F40\u0F91: ]\u0F40\u0F91
[# \u0F40\u0F92: ]\u0F40\u0F92
[# \u0F40\u0F93: ]\u0F40\u0F93
[# \u0F40\u0F94: ]\u0F40\u0F94
[# \u0F40\u0F95: ]\u0F40\u0F95
[# \u0F40\u0F96: ]\u0F40\u0F96
[# \u0F40\u0F97: ]\u0F40\u0F97
[# \u0F40\u0F99: ]\u0F40\u0F99
[# \u0F40\u0F9A: ]\u0F40\u0F9A
[# \u0F40\u0F9B: ]\u0F40\u0F9B
[# \u0F40\u0F9C: ]\u0F40\u0F9C
[# \u0F40\u0F9D: ]\u0F40\u0F9D
[# \u0F40\u0F9E: ]\u0F40\u0F9E
[# \u0F40\u0F9F: ]\u0F40\u0F9F
[# \u0F40\u0FA0: ]\u0F40\u0FA0
[# \u0F40\u0FA1: ]\u0F40\u0FA1
[# \u0F40\u0FA2: ]\u0F40\u0FA2
[# \u0F40\u0FA3: ]\u0F40\u0FA3
[# \u0F40\u0FA4: ]\u0F40\u0FA4
[# \u0F40\u0FA5: ]\u0F40\u0FA5
[# \u0F40\u0FA6: ]\u0F40\u0FA6
[# \u0F40\u0FA7: ]\u0F40\u0FA7
[# \u0F40\u0FA8: ]\u0F40\u0FA8
[# \u0F40\u0FA9: ]\u0F40\u0FA9
[# \u0F40\u0FAA: ]\u0F40\u0FAA
[# \u0F40\u0FAB: ]\u0F40\u0FAB
[# \u0F40\u0FAC: ]\u0F40\u0FAC
[# \u0F40\u0FAD: ]\u0F40\u0FAD
[# \u0F40\u0FAE: ]\u0F40\u0FAE
[# \u0F40\u0FAF: ]\u0F40\u0FAF
[# \u0F40\u0FB0: ]\u0F40\u0FB0
[# \u0F40\u0FB1: ]\u0F40\u0FB1
[# \u0F40\u0FB2: ]\u0F40\u0FB2
[# \u0F40\u0FB3: ]\u0F40\u0FB3
[# \u0F40\u0FB4: ]\u0F40\u0FB4
[# \u0F40\u0FB5: ]\u0F40\u0FB5
[# \u0F40\u0FB6: ]\u0F40\u0FB6
[# \u0F40\u0FB7: ]\u0F40\u0FB7
[# \u0F40\u0FB8: ]\u0F40\u0FB8
[# \u0F40\u0FB9: ]\u0F40\u0FB9
[# \u0F40\u0FBA: ]\u0F40\u0FBA
[# \u0F40\u0FBB: ]\u0F40\u0FBB
[# \u0F40\u0FBC: ]\u0F40\u0FBC
[# \u0F40\u0FBE: ]\u0F40\u0FBE
[# \u0F40\u0FBF: ]\u0F40\u0FBF
[# \u0F40\u0FC0: ]\u0F40\u0FC0
[# \u0F40\u0FC1: ]\u0F40\u0FC1
[# \u0F40\u0FC2: ]\u0F40\u0FC2
[# \u0F40\u0FC3: ]\u0F40\u0FC3
[# \u0F40\u0FC4: ]\u0F40\u0FC4
[# \u0F40\u0FC5: ]\u0F40\u0FC5
[# \u0F40\u0FC6: ]\u0F40\u0FC6
[# \u0F40\u0FC7: ]\u0F40\u0FC7
[# \u0F40\u0FC8: ]\u0F40\u0FC8
[# \u0F40\u0FC9: ]\u0F40\u0FC9
[# \u0F40\u0FCA: ]\u0F40\u0FCA
[# \u0F40\u0FCB: ]\u0F40\u0FCB
[# \u0F40\u0FCC: ]\u0F40\u0FCC
[# \u0F40\u0FCF: ]\u0F40\u0FCF

File diff suppressed because it is too large Load diff