Skip to content

Parse MathClass and MathClassEx #1213

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

Merged
merged 18 commits into from
Oct 2, 2025
Merged

Parse MathClass and MathClassEx #1213

Show file tree
Hide file tree
Changes from 13 commits
Commits
Show all changes
18 commits
Select commit Hold shift + click to select a range
717a553
Parse UTR25 data
eggrobin Sep 27, 2025
a62480c
Last Resort as last resort
eggrobin Sep 27, 2025
69d2a6a
This is a mess but it parses the whole math history
eggrobin Sep 29, 2025
a58e964
Realistic expectations
eggrobin Sep 29, 2025
c997fb3
Some cleanup
eggrobin Sep 29, 2025
cc63d43
More testing
eggrobin Sep 29, 2025
86371af
More cleanup
eggrobin Sep 30, 2025
7c690cb
A constant for the version that will correspond to the next version o…
eggrobin Sep 30, 2025
42e9e20
Another 16
eggrobin Sep 30, 2025
94d3edc
comments
eggrobin Sep 30, 2025
f7b7ce3
Revert "Last Resort as last resort"
eggrobin Sep 30, 2025
652c5d2
words
eggrobin Sep 30, 2025
367d6e7
Clarify comment further
eggrobin Sep 30, 2025
4a3f1da
Comment
eggrobin Sep 30, 2025
0839ff3
Make Math_Class multivalued to honestly show its multiple values of o…
eggrobin Oct 2, 2025
43d5446
A null check and a comment
eggrobin Oct 2, 2025
ba839cc
Merge remote-tracking branch 'la-vache/main' into math
eggrobin Oct 2, 2025
fa84c4a
spotless
eggrobin Oct 2, 2025
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
79 changes: 79 additions & 0 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 @@ -666,6 +666,18 @@ static void parseSourceFile(
&& (propInfo = propInfoSet.iterator().next()).special
== SpecialProperty.None
&& propInfo.getFieldNumber(indexUnicodeProperties.ucdVersion) == 1) {
if (fileName.equals("math/*/MathClass")
&& indexUnicodeProperties.ucdVersion.compareTo(
VersionInfo.UNICODE_6_3)
<= 0) {
parser =
parser.withLinePreprocessor(
s ->
s.startsWith("1D455=210E;")
|| s.equals("code point;class")
? "#" + s
: s);
}
parseSimpleFieldFile(
parser.withMissing(true),
propInfo,
Expand All @@ -674,6 +686,20 @@ static void parseSourceFile(
? null
: nextProperties.getProperty(propInfo.property));
} else {
if (fileName.equals("math/*/MathClassEx")
&& indexUnicodeProperties.ucdVersion.compareTo(
VersionInfo.UNICODE_6_3)
<= 0) {
parser =
parser.withLinePreprocessor(
s ->
s.startsWith("FE61-FE68;")
? s.replaceFirst(
"FE61-FE68;", "FE61..FE68;")
: s.startsWith("1D455=210E;")
? "#" + s
: s);
}
parseFieldFile(
parser.withMissing(true),
indexUnicodeProperties,
Expand Down Expand Up @@ -1510,6 +1536,38 @@ private static void parseFields(
value = "No";
}
}
if ((propInfo.property == UcdProperty.Math_Entity_Name
|| propInfo.property == UcdProperty.Math_Entity_Set)
&& indexUnicodeProperties.ucdVersion.compareTo(Utility.UTR25_REVISION_16)
< 0) {
merger = IndexUnicodeProperties.MULTIVALUED_JOINER;
}
if (propInfo.property == UcdProperty.Math_Descriptive_Comments
&& indexUnicodeProperties.ucdVersion.compareTo(Utility.UTR25_REVISION_16)
< 0) {
merger = new PropertyUtilities.NullIgnorer();
}
if (propInfo.property == UcdProperty.Math_Class_Ex
&& indexUnicodeProperties.ucdVersion.compareTo(Utility.UTR25_REVISION_16)
< 0) {
merger = new PropertyUtilities.RedundancyIgnorer();
}
if (propInfo.property == UcdProperty.Math_Class_Ex
&& indexUnicodeProperties.ucdVersion.compareTo(VersionInfo.UNICODE_6_0) < 0
&& (line.getRange().start == 0x2020 || line.getRange().start == 0x2021)
&& line.getRange().end == line.getRange().start
&& value.equals("N")) {
value = "R";
}
if (propInfo.property == UcdProperty.Math_Class_Ex
&& indexUnicodeProperties.ucdVersion.compareTo(VersionInfo.UNICODE_6_1) < 0
&& value.isEmpty()) {
// MathClassEx-12 has
// 27CA;;;;;;VERTICAL BAR WITH HORIZONTAL STROKE
// MathClassEx-11 has
// 21EA..21F3;;⇪..⇳;;;; 21EA-21F3 are keyboard
value = "None";
}
propInfo.put(
data,
line.getMissingSet(),
Expand Down Expand Up @@ -1646,6 +1704,27 @@ private static void parseSimpleFieldFile(
}
}
continue;
} else if (propInfo.property == UcdProperty.Math_Class
&& version.compareTo(VersionInfo.UNICODE_6_0) < 0) {
// MathClass-11 had conflicting assignments for these two characters. Instead
// of making Math_Class multivalued, keep the one that stayed (R), and discard
// the N.
if ((line.getRange().start == 0x2020 || line.getRange().start == 0x2021)
&& line.getRange().start == line.getRange().end
&& line.getParts()[1].equals("N")) {
continue;
}
// MathClass-9 had the same problem for U+0021 ! as well.
if (version.compareTo(VersionInfo.UNICODE_5_1) < 0
&& line.getRange().start == 0x0021
&& line.getRange().start == line.getRange().end
&& line.getParts()[1].equals("P")) {
continue;
}
// MathClass-11 had a line without a value, 21EA..21F3;
if (line.getParts()[1].isEmpty()) {
line.getParts()[1] = "None";
}
} else if (line.getParts().length != 2
&& version.compareTo(VersionInfo.UNICODE_3_0_1) > 0) {
// Unicode 3.0 and earlier had name comments as an extra field.
Expand Down
29 changes: 29 additions & 0 deletions unicodetools/src/main/java/org/unicode/props/PropertyUtilities.java
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,5 +1,6 @@
package org.unicode.props;

import com.google.common.base.Objects;
import com.ibm.icu.impl.UnicodeMap;
import com.ibm.icu.text.UnicodeSet;
import java.util.Collection;
Expand Down Expand Up @@ -37,6 +38,34 @@ public String merge(String first, String second) {
}
}

public static final class NullIgnorer implements Merge<String> {
public NullIgnorer() {}

@Override
public String merge(String first, String second) {
if (second == null) {
return first;
} else {
throw new UnicodePropertyException(
"Key already present in UnicodeMap:\told: " + first + ",\tnew: " + second);
}
}
}

public static final class RedundancyIgnorer implements Merge<String> {
public RedundancyIgnorer() {}

@Override
public String merge(String first, String second) {
if (Objects.equal(first, second)) {
return first;
} else {
throw new UnicodePropertyException(
"Key already present in UnicodeMap:\told: " + first + ",\tnew: " + second);
}
}
}

static final <K, V, M extends Map<K, V>> M putNew(M map, K key, V value) {
final V oldValue = map.get(key);
if (oldValue != null) {
Expand Down
27 changes: 25 additions & 2 deletions unicodetools/src/main/java/org/unicode/props/UcdLineParser.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -4,6 +4,7 @@
import java.util.ArrayList;
import java.util.Iterator;
import java.util.NoSuchElementException;
import java.util.function.Function;
import java.util.regex.Matcher;
import java.util.regex.Pattern;
import org.unicode.cldr.util.RegexUtilities;
Expand Down Expand Up @@ -85,18 +86,21 @@ public enum Contents {
private final ArrayList<String> partsList = new ArrayList<>();
private String[] parts = null;
private final IntRange intRange = new IntRange();
private final Function<String, String> linePreprocessor;

UcdLine(
Pattern splitPattern,
boolean withRange,
boolean withMissing,
Iterator<String> rawLines,
UcdFileStats stats) {
UcdFileStats stats,
Function<String, String> linePreprocessor) {
splitter = splitPattern.matcher("");
this.withRange = withRange;
this.withMissing = withMissing;
this.rawLines = rawLines;
this.stats = stats;
this.linePreprocessor = linePreprocessor;
}

@Override
Expand All @@ -117,6 +121,9 @@ public boolean hasNext() {
|| line.startsWith(">>>>>>>")) {
line2 = "";
}
if (linePreprocessor != null) {
line2 = linePreprocessor.apply(line2);
}
++stats.lineCount;
final int hashPos = line2.indexOf('#');
if (hashPos >= 0) {
Expand Down Expand Up @@ -223,6 +230,7 @@ public UnicodeSet getMissingSet() {
private boolean withTabs = false;
private boolean withRange = true;
private boolean withMissing = false;
private Function<String, String> linePreprocessor;
private final Iterable<String> rawLines;
private final UcdFileStats stats = new UcdFileStats();

Expand All @@ -245,10 +253,25 @@ public UcdLineParser withMissing(boolean m) {
return this;
}

// Sets a line preprocessor to which the line is fed before removing comments,
// splitting fields, and decoding ranges.
// This makes it possible to correct lines with ill-formed ranges.
// For corrections affecting only subsequent fields rather than the range,
// prefer handling in the parse* functions in PropertyParsingInfo.
public UcdLineParser withLinePreprocessor(Function<String, String> f) {
linePreprocessor = f;
return this;
}

@Override
public Iterator<UcdLine> iterator() {
return new UcdLine(
withTabs ? TAB : SEMICOLON, withRange, withMissing, rawLines.iterator(), stats);
withTabs ? TAB : SEMICOLON,
withRange,
withMissing,
rawLines.iterator(),
stats,
linePreprocessor);
}

public int getLineCount() {
Expand Down
30 changes: 30 additions & 0 deletions unicodetools/src/main/java/org/unicode/props/UcdProperty.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -26,6 +26,8 @@
import org.unicode.props.UcdPropertyValues.Joining_Group_Values;
import org.unicode.props.UcdPropertyValues.Joining_Type_Values;
import org.unicode.props.UcdPropertyValues.Line_Break_Values;
import org.unicode.props.UcdPropertyValues.Math_Class_Ex_Values;
import org.unicode.props.UcdPropertyValues.Math_Class_Values;
import org.unicode.props.UcdPropertyValues.NFC_Quick_Check_Values;
import org.unicode.props.UcdPropertyValues.NFD_Quick_Check_Values;
import org.unicode.props.UcdPropertyValues.NFKC_Quick_Check_Values;
Expand Down Expand Up @@ -124,6 +126,22 @@ public enum UcdProperty {
Emoji_SB(PropertyType.Miscellaneous, DerivedPropertyStatus.UCDNonProperty, "ESB"),
ISO_Comment(PropertyType.Miscellaneous, DerivedPropertyStatus.Approved, "isc"),
Jamo_Short_Name(PropertyType.Miscellaneous, DerivedPropertyStatus.Approved, "JSN"),
Math_Descriptive_Comments(
PropertyType.Miscellaneous,
DerivedPropertyStatus.NonUCDNonProperty,
"Math_Descriptive_Comments"),
Math_Entity_Name(
PropertyType.Miscellaneous,
DerivedPropertyStatus.NonUCDNonProperty,
null,
ValueCardinality.Unordered,
"Math_Entity_Name"),
Math_Entity_Set(
PropertyType.Miscellaneous,
DerivedPropertyStatus.NonUCDNonProperty,
null,
ValueCardinality.Unordered,
"Math_Entity_Set"),
Name(PropertyType.Miscellaneous, DerivedPropertyStatus.Approved, "na"),
Name_Alias(
PropertyType.Miscellaneous,
Expand Down Expand Up @@ -713,6 +731,18 @@ public enum UcdProperty {
Line_Break_Values.class,
null,
"lb"),
Math_Class(
PropertyType.Enumerated,
DerivedPropertyStatus.NonUCDProperty,
Math_Class_Values.class,
null,
"Math_Class"),
Math_Class_Ex(
PropertyType.Enumerated,
DerivedPropertyStatus.NonUCDNonProperty,
Math_Class_Ex_Values.class,
null,
"Math_Class_Ex"),
NFC_Quick_Check(
PropertyType.Enumerated,
DerivedPropertyStatus.Approved,
Expand Down
90 changes: 90 additions & 0 deletions unicodetools/src/main/java/org/unicode/props/UcdPropertyValues.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1817,6 +1817,96 @@ public static Line_Break_Values forName(String name) {
}

// Lowercase_Mapping
public enum Math_Class_Values implements Named {
None("None"),
Normal("N"),
Alphabetic("A"),
Binary("B"),
Closing("C"),
Diacritic("D"),
Fence("F"),
Glyph_Part("G"),
Invisible("I"),
Large("L"),
Opening("O"),
Punctuation("P"),
Relation("R", "R?"),
Space("S"),
Unary("U"),
Vary("V"),
Special("X");
private final PropertyNames<Math_Class_Values> names;

private Math_Class_Values(String shortName, String... otherNames) {
names =
new PropertyNames<Math_Class_Values>(
Math_Class_Values.class, this, shortName, otherNames);
}

@Override
public PropertyNames<Math_Class_Values> getNames() {
return names;
}

@Override
public String getShortName() {
return names.getShortName();
}

private static final NameMatcher<Math_Class_Values> NAME_MATCHER =
PropertyNames.getNameToEnums(Math_Class_Values.class);

public static Math_Class_Values forName(String name) {
return NAME_MATCHER.get(name);
}
}

public enum Math_Class_Ex_Values implements Named {
None("None"),
Normal("N"),
Alphabetic("A"),
Binary("B"),
Closing("C"),
Diacritic("D"),
Fence("F"),
Glyph_Part("G"),
Large("L"),
Opening("O"),
Punctuation("P"),
Relation("R", "R?"),
Space("S"),
Unary("U"),
Vary("V"),
Special("X");
private final PropertyNames<Math_Class_Ex_Values> names;

private Math_Class_Ex_Values(String shortName, String... otherNames) {
names =
new PropertyNames<Math_Class_Ex_Values>(
Math_Class_Ex_Values.class, this, shortName, otherNames);
}

@Override
public PropertyNames<Math_Class_Ex_Values> getNames() {
return names;
}

@Override
public String getShortName() {
return names.getShortName();
}

private static final NameMatcher<Math_Class_Ex_Values> NAME_MATCHER =
PropertyNames.getNameToEnums(Math_Class_Ex_Values.class);

public static Math_Class_Ex_Values forName(String name) {
return NAME_MATCHER.get(name);
}
}

// Math_Descriptive_Comments
// Math_Entity_Name
// Math_Entity_Set
// Name
// Name_Alias
// Named_Sequences
Expand Down
Loading