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

ICU-13084 Updating set of ignorable control characters to [:DI:].

Browse Source 
X-SVN-Rev: 41002
This commit is contained in:
Shane Carr 2018-02-28 03:42:32 +00:00
parent 9759fc597f
commit 9ae7e8eba1
4 changed files with 30 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
icu4c/source/i18n/numparse_unisets.cpp
View File

@ -63,8 +63,9 @@ void U_CALLCONV initNumberParseUniSets(UErrorCode& status) {
gUnicodeSets[EMPTY] = new UnicodeSet();
// BiDi characters are skipped over and ignored at any point in the string, even in strict mode.
gUnicodeSets[BIDI] = new UnicodeSet(u"[[\\u200E\\u200F\\u061C]]", status);
// These characters are skipped over and ignored at any point in the string, even in strict mode.
// See ticket #13084.
gUnicodeSets[BIDI] = new UnicodeSet(u"[[:DI:]]", status);
// This set was decided after discussion with icu-design@. See ticket #13309.
// Zs+TAB is "horizontal whitespace" according to UTS #18 (blank property).

5
icu4j/main/classes/core/src/com/ibm/icu/impl/number/parse/UnicodeSetStaticCache.java
View File

@ -81,8 +81,9 @@ public class UnicodeSetStaticCache {
}
static {
// BiDi characters are skipped over and ignored at any point in the string, even in strict mode.
unicodeSets.put(Key.BIDI, new UnicodeSet("[[\\u200E\\u200F\\u061C]]").freeze());
// These characters are skipped over and ignored at any point in the string, even in strict mode.
// See ticket #13084.
unicodeSets.put(Key.BIDI, new UnicodeSet("[[:DI:]]").freeze());
// This set was decided after discussion with icu-design@. See ticket #13309.
// Zs+TAB is "horizontal whitespace" according to UTS #18 (blank property).

3
icu4j/main/classes/core/src/com/ibm/icu/text/DecimalFormat.java
View File

@ -198,7 +198,7 @@ import com.ibm.icu.util.ULocale.Category;
* example, a formatter instance gotten from NumberFormat.getInstance(ULocale,
* NumberFormat.CURRENCYSTYLE) can parse both "USD1.00" and "3.00 US dollars".
*
* <p>Whitespace characters (lenient mode) and bidi control characters (lenient and strict mode),
* <p>Whitespace characters (lenient mode) and control characters (lenient and strict mode),
* collectively called "ignorables", do not need to match in identity or quantity between the
* pattern string and the input string. For example, the pattern "# %" matches "35 %" (with a single
* space), "35%" (with no space), "35&nbsp;%" (with a non-breaking space), and "35&nbsp; %" (with
@ -206,6 +206,7 @@ import com.ibm.icu.util.ULocale.Category;
* number: prefix, number, exponent separator, and suffix. Ignorable whitespace characters are those
* having the Unicode "blank" property for regular expressions, defined in UTS #18 Annex C, which is
* "horizontal" whitespace, like spaces and tabs, but not "vertical" whitespace, like line breaks.
* Ignorable control characters are those in the Unicode set [:Default_Ignorable_Code_Point:].
*
* <p>If {@link #parse(String, ParsePosition)} fails to parse a string, it returns <code>null</code>
* and leaves the parse position unchanged. The convenience method {@link #parse(String)} indicates

23
icu4j/main/tests/core/src/com/ibm/icu/dev/test/format/NumberFormatTest.java
View File

@ -1722,11 +1722,32 @@ public class NumberFormatTest extends TestFmwk {
// Test all characters in the UTS 18 "blank" set stated in the API docstring.
UnicodeSet blanks = new UnicodeSet("[[:Zs:][\\u0009]]").freeze();
for (String space : blanks) {
String str = "a " + space + " b1234";
String str = "a " + space + " b1234c ";
expect(fmt, str, n);
}
// Arbitrary whitespace is not accepted in strict mode.
fmt.setParseStrict(true);
for (String space : blanks) {
String str = "a " + space + " b1234c ";
expectParseException(fmt, str, n);
}
// Test default ignorable characters. These should work in both lenient and strict.
UnicodeSet defaultIgnorables = new UnicodeSet("[[:Default_Ignorable_Code_Point:]]").freeze();
fmt.setParseStrict(false);
for (String ignorable : defaultIgnorables) {
String str = "a b " + ignorable + "1234c ";
expect(fmt, str, n);
}
fmt.setParseStrict(true);
for (String ignorable : defaultIgnorables) {
String str = "a b " + ignorable + "1234c ";
expect(fmt, str, n);
}
// Test that other whitespace characters do not work
fmt.setParseStrict(false);
UnicodeSet otherWhitespace = new UnicodeSet("[[:whitespace:]]").removeAll(blanks).freeze();
for (String space : otherWhitespace) {
String str = "a " + space + " b1234";