Skip to content

align decimal and grouping separators with CPython behavior. #645

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Draft
jayy-77 wants to merge 1 commit into
base: master
Choose a base branch
from
+25 −11
Draft

align decimal and grouping separators with CPython behavior. #645

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
19 changes: 15 additions & 4 deletions ...racle.graal.python/src/com/oracle/graal/python/builtins/modules/LocaleModuleBuiltins.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -126,21 +126,32 @@ static PDict localeconv() {
Locale numericLocale = currentPythonLocale.category(LC_NUMERIC);
NumberFormat numericLocaleNumFormat = NumberFormat.getInstance(numericLocale);
DecimalFormatSymbols decimalFormatSymbols = getDecimalFormatSymbols(numericLocale, numericLocaleNumFormat);
char decimalPoint = decimalFormatSymbols.getDecimalSeparator();
char thousandsSep = decimalFormatSymbols.getGroupingSeparator();
// Align with CPython behaviour for locales like ru_RU where Java may use NBSP
if ("ru".equals(numericLocale.getLanguage()) && thousandsSep == '\u00A0') {
thousandsSep = '\u202F';
}

dict.put("decimal_point", TruffleString.fromCodePointUncached(decimalFormatSymbols.getDecimalSeparator(), TS_ENCODING));
dict.put("thousands_sep", TruffleString.fromCodePointUncached(decimalFormatSymbols.getGroupingSeparator(), TS_ENCODING));
dict.put("decimal_point", TruffleString.fromCodePointUncached(decimalPoint, TS_ENCODING));
dict.put("thousands_sep", TruffleString.fromCodePointUncached(thousandsSep, TS_ENCODING));
dict.put("grouping", getDecimalFormatGrouping(language, numericLocaleNumFormat));

// LC_MONETARY
Locale monetaryLocale = currentPythonLocale.category(LC_MONETARY);
NumberFormat monetaryNumFormat = NumberFormat.getInstance(monetaryLocale);
Currency currency = monetaryNumFormat.getCurrency();
decimalFormatSymbols = getDecimalFormatSymbols(monetaryLocale, monetaryNumFormat);
char monDecimalPoint = decimalFormatSymbols.getMonetaryDecimalSeparator();
char monThousandsSep = decimalFormatSymbols.getGroupingSeparator();
if ("ru".equals(monetaryLocale.getLanguage()) && monThousandsSep == '\u00A0') {
monThousandsSep = '\u202F';
}

dict.put("int_curr_symbol", toTruffleStringUncached(decimalFormatSymbols.getInternationalCurrencySymbol()));
dict.put("currency_symbol", toTruffleStringUncached(decimalFormatSymbols.getCurrencySymbol()));
dict.put("mon_decimal_point", TruffleString.fromCodePointUncached(decimalFormatSymbols.getMonetaryDecimalSeparator(), TS_ENCODING));
dict.put("mon_thousands_sep", TruffleString.fromCodePointUncached(decimalFormatSymbols.getGroupingSeparator(), TS_ENCODING));
dict.put("mon_decimal_point", TruffleString.fromCodePointUncached(monDecimalPoint, TS_ENCODING));
dict.put("mon_thousands_sep", TruffleString.fromCodePointUncached(monThousandsSep, TS_ENCODING));
dict.put("mon_grouping", getDecimalFormatGrouping(language, monetaryNumFormat));
// TODO: reasonable default, but not the current locale setting
dict.put("positive_sign", "");
Expand Down
16 changes: 9 additions & 7 deletions ....oracle.graal.python/src/com/oracle/graal/python/runtime/formatting/IntegerFormatter.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -14,6 +14,8 @@

import com.oracle.graal.python.nodes.ErrorMessages;
import com.oracle.graal.python.nodes.PRaiseNode;
import com.oracle.graal.python.runtime.PythonContext;
import com.oracle.graal.python.runtime.locale.PythonLocale;
import com.oracle.graal.python.runtime.formatting.FormattingBuffer.StringFormattingBuffer;
import com.oracle.graal.python.runtime.formatting.InternalFormat.Spec;
import com.oracle.truffle.api.CompilerDirectives.TruffleBoundary;
Expand Down Expand Up @@ -117,9 +119,8 @@ public IntegerFormatter format(BigInteger value) {
break;

case 'n':
// Locale-sensitive version of d-format
format_d(value);
setGroupingAndGroupSize(getCurrentDecimalFormat());
// Locale-sensitive version of d-format using current Python locale
format_n(value);
break;

default:
Expand Down Expand Up @@ -176,7 +177,8 @@ void format_d(BigInteger value) {
*/
void format_n(BigInteger value) {
String number;
NumberFormat nf = NumberFormat.getNumberInstance();
NumberFormat nf = NumberFormat.getNumberInstance(
PythonContext.get(null).getCurrentLocale().category(PythonLocale.LC_NUMERIC));
if (value.signum() < 0) {
// Negative value: deal with sign and base, and convert magnitude.
negativeSign(null);
Expand All @@ -194,7 +196,8 @@ void format_n(BigInteger value) {
*/
void format_n(int value) {
String number;
NumberFormat nf = NumberFormat.getNumberInstance();
NumberFormat nf = NumberFormat.getNumberInstance(
PythonContext.get(null).getCurrentLocale().category(PythonLocale.LC_NUMERIC));
if (value < 0) {
// Negative value: deal with sign and base, and convert magnitude.
negativeSign(null);
Expand Down Expand Up @@ -349,8 +352,7 @@ public IntegerFormatter format(int value) {

case 'n':
// Locale-sensitive version of d-format
format_d(value);
setGroupingAndGroupSize(getCurrentDecimalFormat());
format_n(value);
break;

default:
Expand Down
1 change: 1 addition & 0 deletions ...thon/com.oracle.graal.python/src/com/oracle/graal/python/runtime/locale/PythonLocale.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -113,6 +113,7 @@ public PythonLocale(Locale displayLocale, Locale formatLocale) {
public Locale category(int category) {
return switch (category) {
case LC_COLLATE, LC_CTYPE, LC_MESSAGES -> formatLocale;
case LC_MONETARY, LC_NUMERIC, LC_TIME -> displayLocale;
default -> displayLocale;
};
}
Expand Down