AuroraMiddleware/scuffed-code
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

Fixed test failure. ClassCastException because the dictionary

Browse Source 
name wasn't a URL as expected  by BreakIterator

X-SVN-Rev: 934
This commit is contained in:
John Fitzpatrick 2000-03-10 00:20:05 +00:00
parent 94cca6161d
commit b4c2715073
4 changed files with 180 additions and 164 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

62
icu4j/src/com/ibm/icu/dev/test/rbbi/BreakIteratorRules_en_US_TEST.java
View File

@ -13,6 +13,7 @@
package com.ibm.text.resources;
import java.util.ListResourceBundle;
import java.net.URL;
/**
* This resource bundle is included for testing and demonstration purposes only.
@ -22,10 +23,14 @@ import java.util.ListResourceBundle;
*/
public class BreakIteratorRules_en_US_TEST extends ListResourceBundle {
public Object[][] getContents() {
return contents;
}
URL url = getClass().getResource("english.dict");
static final Object[][] contents = {
// if dictionary wasn't found, then this resource bundle doesn't have
// much to contribute...
if (url == null) {
return new Object[0][0];
}
return new Object[][] {
// names of classes to instantiate for the different kinds of break
// iterator. Notice we're now using DictionaryBasedBreakIterator
// for word and line breaking.
@ -40,29 +45,29 @@ public class BreakIteratorRules_en_US_TEST extends ListResourceBundle {
// resource, except that the Latin letters, apostrophe, and hyphen are
// specified as dictionary characters
{ "WordBreakRules",
"<ignore>=[:Mn::Me::Cf:];"
+ "<dictionary>=[a-zA-z\\'\\-];"
+ "<kanji>=[\u3005\u4e00-\u9fa5\uf900-\ufa2d];"
+ "<kata>=[\u30a1-\u30fa];"
+ "<hira>=[\u3041-\u3094];"
+ "<cjk-diacrit>=[\u3099-\u309c];"
+ "<let>=[:L:^[<kanji><kata><hira><cjk-diacrit><dictionary>]];"
+ "<dgt>=[:N:];"
+ "<mid-word>=[:Pd:\u00ad\u2027\\\"\\\'\\.];"
+ "<mid-num>=[\\\"\\\'\\,\u066b\\.];"
+ "<pre-num>=[:Sc:\\#\\.^\u00a2];"
+ "<post-num>=[\\%\\&\u00a2\u066a\u2030\u2031];"
+ "<ls>=[\n\u000c\u2028\u2029];"
+ "<ws>=[:Zs:\t];"
+ "<word>=(<let><let>*(<mid-word><let><let>*)*|[a-zA-Z][a-z\\'\\-]*);"
+ "<number>=(<dgt><dgt>*(<mid-num><dgt><dgt>*)*);"
"$ignore=[[:Mn:][:Me:][:Cf:]];"
+ "dictionary=[a-zA-z\\'\\-];"
+ "kanji=[\u3005\u4e00-\u9fa5\uf900-\ufa2d];"
+ "kata=[\u30a1-\u30fa];"
+ "hira=[\u3041-\u3094];"
+ "cjk-diacrit=[\u3099-\u309c];"
+ "let=[[:L:]^[{kanji}{kata}{hira}{cjk-diacrit}{dictionary}]];"
+ "dgt=[[:N:]];"
+ "mid-word=[[:Pd:]\u00ad\u2027\\\"\\\'\\.];"
+ "mid-num=[\\\"\\\'\\,\u066b\\.];"
+ "pre-num=[[:Sc:]\\#\\.^\u00a2];"
+ "post-num=[\\%\\&\u00a2\u066a\u2030\u2031];"
+ "ls=[\n\u000c\u2028\u2029];"
+ "ws=[[:Zs:]\t];"
+ "word=({let}{let}*({mid-word}{let}{let}*)*|[a-zA-Z][a-z\\'\\-]*);"
+ "number=({dgt}{dgt}*({mid-num}{dgt}{dgt}*)*);"
+ ".;"
+ "{<word>}(<number><word>)*{<number>{<post-num>}};"
+ "<pre-num>(<number><word>)*{<number>{<post-num>}};"
+ "<ws>*{\r}{<ls>};"
+ "[<kata><cjk-diacrit>]*;"
+ "[<hira><cjk-diacrit>]*;"
+ "<kanji>*;" },
+ "{{word}}({number}{word})*{{number}{{post-num}}};"
+ "{pre-num}({number}{word})*{{number}{{post-num}}};"
+ "{ws}*{\r}{{ls}};"
+ "[{kata}{cjk-diacrit}]*;"
+ "[{hira}{cjk-diacrit}]*;"
+ "{kanji}*;" },
// These are the same line-breaking rules as are specified in the default
// resource, except that the Latin letters, apostrophe, and hyphen are
@ -99,7 +104,10 @@ public class BreakIteratorRules_en_US_TEST extends ListResourceBundle {
// words (basically, it contains all the words in the Declaration of
// Independence, and the Revised Standard Version of the book of Genesis,
// plus a few other words thrown in to show more interesting cases).
{ "WordBreakDictionary", "com\\ibm\\text\\resources\\english.dict" },
{ "LineBreakDictionary", "com\\ibm\\text\\resources\\english.dict" }
// { "WordBreakDictionary", "com\\ibm\\text\\resources\\english.dict" },
// { "LineBreakDictionary", "com\\ibm\\text\\resources\\english.dict" }
{ "WordBreakDictionary", url },
{ "LineBreakDictionary", url }
};
}
}

6
icu4j/src/com/ibm/icu/dev/test/rbbi/SimpleBITest.java
View File

@ -107,19 +107,19 @@ public class SimpleBITest extends TestFmwk{
public void testWordBreak() throws Exception {
BreakIterator wordBreak = BreakIterator.getWordInstance(new Locale("en", "US", "TEST"));
int breaks = doTest(wordBreak);
errln(String.valueOf(breaks));
logln(String.valueOf(breaks));
}
public void testLineBreak() throws Exception {
BreakIterator lineBreak = BreakIterator.getLineInstance(new Locale("en", "US", "TEST"));
int breaks = doTest(lineBreak);
errln(String.valueOf(breaks));
logln(String.valueOf(breaks));
}
public void testSentenceBreak() throws Exception {
BreakIterator sentenceBreak = BreakIterator.getSentenceInstance(new Locale("en", "US", "TEST"));
int breaks = doTest(sentenceBreak);
errln(String.valueOf(breaks));
logln(String.valueOf(breaks));
}
private int doTest(BreakIterator bi) {

62
icu4j/src/com/ibm/test/rbbi/BreakIteratorRules_en_US_TEST.java
View File

@ -13,6 +13,7 @@
package com.ibm.text.resources;
import java.util.ListResourceBundle;
import java.net.URL;
/**
* This resource bundle is included for testing and demonstration purposes only.
@ -22,10 +23,14 @@ import java.util.ListResourceBundle;
*/
public class BreakIteratorRules_en_US_TEST extends ListResourceBundle {
public Object[][] getContents() {
return contents;
}
URL url = getClass().getResource("english.dict");
static final Object[][] contents = {
// if dictionary wasn't found, then this resource bundle doesn't have
// much to contribute...
if (url == null) {
return new Object[0][0];
}
return new Object[][] {
// names of classes to instantiate for the different kinds of break
// iterator. Notice we're now using DictionaryBasedBreakIterator
// for word and line breaking.
@ -40,29 +45,29 @@ public class BreakIteratorRules_en_US_TEST extends ListResourceBundle {
// resource, except that the Latin letters, apostrophe, and hyphen are
// specified as dictionary characters
{ "WordBreakRules",
"<ignore>=[:Mn::Me::Cf:];"
+ "<dictionary>=[a-zA-z\\'\\-];"
+ "<kanji>=[\u3005\u4e00-\u9fa5\uf900-\ufa2d];"
+ "<kata>=[\u30a1-\u30fa];"
+ "<hira>=[\u3041-\u3094];"
+ "<cjk-diacrit>=[\u3099-\u309c];"
+ "<let>=[:L:^[<kanji><kata><hira><cjk-diacrit><dictionary>]];"
+ "<dgt>=[:N:];"
+ "<mid-word>=[:Pd:\u00ad\u2027\\\"\\\'\\.];"
+ "<mid-num>=[\\\"\\\'\\,\u066b\\.];"
+ "<pre-num>=[:Sc:\\#\\.^\u00a2];"
+ "<post-num>=[\\%\\&\u00a2\u066a\u2030\u2031];"
+ "<ls>=[\n\u000c\u2028\u2029];"
+ "<ws>=[:Zs:\t];"
+ "<word>=(<let><let>*(<mid-word><let><let>*)*|[a-zA-Z][a-z\\'\\-]*);"
+ "<number>=(<dgt><dgt>*(<mid-num><dgt><dgt>*)*);"
"$ignore=[[:Mn:][:Me:][:Cf:]];"
+ "dictionary=[a-zA-z\\'\\-];"
+ "kanji=[\u3005\u4e00-\u9fa5\uf900-\ufa2d];"
+ "kata=[\u30a1-\u30fa];"
+ "hira=[\u3041-\u3094];"
+ "cjk-diacrit=[\u3099-\u309c];"
+ "let=[[:L:]^[{kanji}{kata}{hira}{cjk-diacrit}{dictionary}]];"
+ "dgt=[[:N:]];"
+ "mid-word=[[:Pd:]\u00ad\u2027\\\"\\\'\\.];"
+ "mid-num=[\\\"\\\'\\,\u066b\\.];"
+ "pre-num=[[:Sc:]\\#\\.^\u00a2];"
+ "post-num=[\\%\\&\u00a2\u066a\u2030\u2031];"
+ "ls=[\n\u000c\u2028\u2029];"
+ "ws=[[:Zs:]\t];"
+ "word=({let}{let}*({mid-word}{let}{let}*)*|[a-zA-Z][a-z\\'\\-]*);"
+ "number=({dgt}{dgt}*({mid-num}{dgt}{dgt}*)*);"
+ ".;"
+ "{<word>}(<number><word>)*{<number>{<post-num>}};"
+ "<pre-num>(<number><word>)*{<number>{<post-num>}};"
+ "<ws>*{\r}{<ls>};"
+ "[<kata><cjk-diacrit>]*;"
+ "[<hira><cjk-diacrit>]*;"
+ "<kanji>*;" },
+ "{{word}}({number}{word})*{{number}{{post-num}}};"
+ "{pre-num}({number}{word})*{{number}{{post-num}}};"
+ "{ws}*{\r}{{ls}};"
+ "[{kata}{cjk-diacrit}]*;"
+ "[{hira}{cjk-diacrit}]*;"
+ "{kanji}*;" },
// These are the same line-breaking rules as are specified in the default
// resource, except that the Latin letters, apostrophe, and hyphen are
@ -99,7 +104,10 @@ public class BreakIteratorRules_en_US_TEST extends ListResourceBundle {
// words (basically, it contains all the words in the Declaration of
// Independence, and the Revised Standard Version of the book of Genesis,
// plus a few other words thrown in to show more interesting cases).
{ "WordBreakDictionary", "com\\ibm\\text\\resources\\english.dict" },
{ "LineBreakDictionary", "com\\ibm\\text\\resources\\english.dict" }
// { "WordBreakDictionary", "com\\ibm\\text\\resources\\english.dict" },
// { "LineBreakDictionary", "com\\ibm\\text\\resources\\english.dict" }
{ "WordBreakDictionary", url },
{ "LineBreakDictionary", url }
};
}
}

6
icu4j/src/com/ibm/test/rbbi/SimpleBITest.java
View File

@ -107,19 +107,19 @@ public class SimpleBITest extends TestFmwk{
public void testWordBreak() throws Exception {
BreakIterator wordBreak = BreakIterator.getWordInstance(new Locale("en", "US", "TEST"));
int breaks = doTest(wordBreak);
errln(String.valueOf(breaks));
logln(String.valueOf(breaks));
}
public void testLineBreak() throws Exception {
BreakIterator lineBreak = BreakIterator.getLineInstance(new Locale("en", "US", "TEST"));
int breaks = doTest(lineBreak);
errln(String.valueOf(breaks));
logln(String.valueOf(breaks));
}
public void testSentenceBreak() throws Exception {
BreakIterator sentenceBreak = BreakIterator.getSentenceInstance(new Locale("en", "US", "TEST"));
int breaks = doTest(sentenceBreak);
errln(String.valueOf(breaks));
logln(String.valueOf(breaks));
}
private int doTest(BreakIterator bi) {