Skip to content
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

Fix misparsing of old binary defaults #1029

Merged
merged 1 commit into from
Jan 31, 2025
Merged

Fix misparsing of old binary defaults #1029

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
53 changes: 44 additions & 9 deletions unicodetools/src/main/java/org/unicode/props/PropertyParsingInfo.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -26,6 +26,7 @@
import org.unicode.props.IndexUnicodeProperties.DefaultValueType;
import org.unicode.props.PropertyUtilities.Merge;
import org.unicode.props.UcdLineParser.IntRange;
import org.unicode.props.UcdLineParser.UcdLine.Contents;
import org.unicode.text.utility.Settings;
import org.unicode.text.utility.Utility;

Expand Down Expand Up @@ -771,19 +772,53 @@ private static void parsePropertyValueFile(
// file: " + propInfo);
// }
String value;
if (line.getParts().length == 2) {
assert propInfo.property.getType() == PropertyType.Binary;
// The file emoji-sequences.txt has a comment-like field after the binary property.
if (line.getParts().length == 2
|| filename.equals("emoji/*/emoji-sequences")
|| filename.equals("emoji/*/emoji-zwj-sequences")) {
if (propInfo.property.getType() != PropertyType.Binary) {
throw new IllegalArgumentException(
"Expected a value for "
+ propInfo.property.getType()
+ " property "
+ propName);
}
value = "Yes";
} else {
value =
propInfo.property.getType() == PropertyType.Binary
? "Yes"
: line.getParts()[2];
value = line.getParts()[2];
if (propInfo.property.getType() == PropertyType.Binary) {
if (line.getType() == Contents.DATA
&& UcdPropertyValues.Binary.forName(value)
!= UcdPropertyValues.Binary.Yes) {
// Most binary properties have no value field, but at least kEH_NoRotate has
// Y.
throw new IllegalArgumentException(
"Unexpected value "
+ value
+ " for binary property "
+ propName
+ " in "
+ filename);
} else if (line.getType() == Contents.MISSING
&& UcdPropertyValues.Binary.forName(value)
!= UcdPropertyValues.Binary.No) {
throw new IllegalArgumentException(
"Unexpected default "
+ value
+ " for binary property "
+ propName
+ " in "
+ filename);
}
}
// The value should not be an empty string.
// Exception: NFKC_Casefold does remove some characters by mapping them to nothing.
assert !value.isEmpty()
|| propInfo.property == UcdProperty.NFKC_Casefold
|| propInfo.property == UcdProperty.NFKC_Simple_Casefold;
if (value.isEmpty()
&& !(propInfo.property == UcdProperty.NFKC_Casefold
|| propInfo.property == UcdProperty.NFKC_Simple_Casefold)) {
throw new IllegalArgumentException(
"Unexpected empty value for property " + propName);
}
if (propInfo.property == UcdProperty.kMandarin) {
if (indexUnicodeProperties.oldVersion) {
value =
Expand Down
Loading