This is an automated email from the ASF dual-hosted git repository.
andy pushed a commit to branch main
in repository https://gitbox.apache.org/repos/asf/jena.git
commit e1ddb7fbc8e1de7d776ca1861d1bca701d7cb90a
Author: Andy Seaborne <a...@apache.org>
AuthorDate: Thu Jun 26 19:07:06 2025 +0100
GH-3281: Update SPARQL/ARQ to check RDF Strings
---
jena-arq/Grammar/arq.jj | 4 ++--
jena-arq/Grammar/main.jj | 4 ++--
jena-arq/Grammar/sparql_12.jj | 4 ++--
.../java/org/apache/jena/sparql/lang/QueryParserBase.java | 14 +++++++++++---
.../org/apache/jena/sparql/lang/arq/javacc/ARQParser.java | 6 +++---
.../jena/sparql/lang/sparql_12/javacc/SPARQLParser12.java | 6 +++---
.../org/apache/jena/sparql/syntax/TestQueryParser.java | 2 +-
7 files changed, 24 insertions(+), 16 deletions(-)
diff --git a/jena-arq/Grammar/arq.jj b/jena-arq/Grammar/arq.jj
index 50d0d3c5cb..434bdb3a66 100644
--- a/jena-arq/Grammar/arq.jj
+++ b/jena-arq/Grammar/arq.jj
@@ -93,8 +93,8 @@ String VersionSpecifier() : { Token t ; String version ; }
| t = <STRING_LITERAL2> { version = stripQuotes(t.image) ; }
)
{
- checkString(version, t.beginLine, t.beginColumn) ;
version = unescapeStr(version, t.beginLine, t.beginColumn) ;
+ checkRDFString(version, t.beginLine, t.beginColumn) ;
return version;
}
}
@@ -1933,7 +1933,7 @@ String String() : { Token t ; String lex ; }
| t = <STRING_LITERAL_LONG2> { lex = stripQuotes3(t.image) ; }
)
{ lex = unescapeStr(lex, t.beginLine, t.beginColumn) ;
- checkString(lex, t.beginLine, t.beginColumn) ;
+ checkRDFString(lex, t.beginLine, t.beginColumn) ;
return lex ;
}
}
diff --git a/jena-arq/Grammar/main.jj b/jena-arq/Grammar/main.jj
index 52448abe4a..8512dedaee 100644
--- a/jena-arq/Grammar/main.jj
+++ b/jena-arq/Grammar/main.jj
@@ -188,8 +188,8 @@ String VersionSpecifier() : { Token t ; String version ; }
| t = <STRING_LITERAL2> { version = stripQuotes(t.image) ; }
)
{
- checkString(version, t.beginLine, t.beginColumn) ;
version = unescapeStr(version, t.beginLine, t.beginColumn) ;
+ checkRDFString(version, t.beginLine, t.beginColumn) ;
return version;
}
}
@@ -2631,7 +2631,7 @@ String String() : { Token t ; String lex ; }
| t = <STRING_LITERAL_LONG2> { lex = stripQuotes3(t.image) ; }
)
{ lex = unescapeStr(lex, t.beginLine, t.beginColumn) ;
- checkString(lex, t.beginLine, t.beginColumn) ;
+ checkRDFString(lex, t.beginLine, t.beginColumn) ;
return lex ;
}
}
diff --git a/jena-arq/Grammar/sparql_12.jj b/jena-arq/Grammar/sparql_12.jj
index 8404acc9c9..50c67ab5ec 100644
--- a/jena-arq/Grammar/sparql_12.jj
+++ b/jena-arq/Grammar/sparql_12.jj
@@ -83,8 +83,8 @@ String VersionSpecifier() : { Token t ; String version ; }
| t = <STRING_LITERAL2> { version = stripQuotes(t.image) ; }
)
{
- checkString(version, t.beginLine, t.beginColumn) ;
version = unescapeStr(version, t.beginLine, t.beginColumn) ;
+ checkRDFString(version, t.beginLine, t.beginColumn) ;
return version;
}
}
@@ -1646,7 +1646,7 @@ String String() : { Token t ; String lex ; }
| t = <STRING_LITERAL_LONG2> { lex = stripQuotes3(t.image) ; }
)
{ lex = unescapeStr(lex, t.beginLine, t.beginColumn) ;
- checkString(lex, t.beginLine, t.beginColumn) ;
+ checkRDFString(lex, t.beginLine, t.beginColumn) ;
return lex ;
}
}
diff --git
a/jena-arq/src/main/java/org/apache/jena/sparql/lang/QueryParserBase.java
b/jena-arq/src/main/java/org/apache/jena/sparql/lang/QueryParserBase.java
index 0c3d81d05a..e2b4449262 100644
--- a/jena-arq/src/main/java/org/apache/jena/sparql/lang/QueryParserBase.java
+++ b/jena-arq/src/main/java/org/apache/jena/sparql/lang/QueryParserBase.java
@@ -212,13 +212,21 @@ public class QueryParserBase {
return NodeFactory.createLiteral(lex, lang, dt);
}
- // Because of Java (Java strings have surrogate pairs) we only detect
singleton surrogates.
- protected void checkString(String string, int line, int column) {
+ /**
+ * Apply any checks for "RDF String" to a string that has already had
escape processing applied.
+ * An RDF String is a sequence of codepoints in the range U+0000 to
U+10FFFF, excluding surrogates.
+ * Because this is java, we test for no non-paired surrogates.
+ * A surrogate pair is high-low.
+ */
+ protected static void checkRDFString(String string, int line, int column) {
// Checks for bare surrogate pairs.
for ( int i = 0; i < string.length(); i++ ) {
// Not "codePointAt" which does surrogate processing.
char ch = string.charAt(i);
+ if ( ! Character.isValidCodePoint(ch) )
+ throw new QueryParseException(String.format("Illegal code
point in \\U sequence value: 0x%08X", ch), line, column);
+
// Check surrogate pairs are in pairs. Pairs are high-low.
if ( Character.isLowSurrogate(ch) )
throw new QueryParseException("Bad surrogate pair (low
surrogate without high surrogate)", line, column);
@@ -369,7 +377,7 @@ public class QueryParserBase {
iriStr = stripQuotes(iriStr);
iriStr = unescapeUnicode(iriStr, line, column);
// Check for Unicode surrogates
- checkString(iriStr, line, column);
+ checkRDFString(iriStr, line, column);
return resolveIRI(iriStr, line, column);
}
diff --git
a/jena-arq/src/main/java/org/apache/jena/sparql/lang/arq/javacc/ARQParser.java
b/jena-arq/src/main/java/org/apache/jena/sparql/lang/arq/javacc/ARQParser.java
index 7b7b044f61..3ebfd4bb56 100644
---
a/jena-arq/src/main/java/org/apache/jena/sparql/lang/arq/javacc/ARQParser.java
+++
b/jena-arq/src/main/java/org/apache/jena/sparql/lang/arq/javacc/ARQParser.java
@@ -149,8 +149,8 @@ version = stripQuotes(t.image) ;
jj_consume_token(-1);
throw new ParseException();
}
-checkString(version, t.beginLine, t.beginColumn) ;
- version = unescapeStr(version, t.beginLine, t.beginColumn) ;
+version = unescapeStr(version, t.beginLine, t.beginColumn) ;
+ checkRDFString(version, t.beginLine, t.beginColumn) ;
{if ("" != null) return version;}
throw new Error("Missing return statement in function");
}
@@ -7520,7 +7520,7 @@ lex = stripQuotes3(t.image) ;
throw new ParseException();
}
lex = unescapeStr(lex, t.beginLine, t.beginColumn) ;
- checkString(lex, t.beginLine, t.beginColumn) ;
+ checkRDFString(lex, t.beginLine, t.beginColumn) ;
{if ("" != null) return lex ;}
throw new Error("Missing return statement in function");
}
diff --git
a/jena-arq/src/main/java/org/apache/jena/sparql/lang/sparql_12/javacc/SPARQLParser12.java
b/jena-arq/src/main/java/org/apache/jena/sparql/lang/sparql_12/javacc/SPARQLParser12.java
index 77876c05e2..8401b009c6 100644
---
a/jena-arq/src/main/java/org/apache/jena/sparql/lang/sparql_12/javacc/SPARQLParser12.java
+++
b/jena-arq/src/main/java/org/apache/jena/sparql/lang/sparql_12/javacc/SPARQLParser12.java
@@ -128,8 +128,8 @@ version = stripQuotes(t.image) ;
jj_consume_token(-1);
throw new ParseException();
}
-checkString(version, t.beginLine, t.beginColumn) ;
- version = unescapeStr(version, t.beginLine, t.beginColumn) ;
+version = unescapeStr(version, t.beginLine, t.beginColumn) ;
+ checkRDFString(version, t.beginLine, t.beginColumn) ;
{if ("" != null) return version;}
throw new Error("Missing return statement in function");
}
@@ -5889,7 +5889,7 @@ lex = stripQuotes3(t.image) ;
throw new ParseException();
}
lex = unescapeStr(lex, t.beginLine, t.beginColumn) ;
- checkString(lex, t.beginLine, t.beginColumn) ;
+ checkRDFString(lex, t.beginLine, t.beginColumn) ;
{if ("" != null) return lex ;}
throw new Error("Missing return statement in function");
}
diff --git
a/jena-arq/src/test/java/org/apache/jena/sparql/syntax/TestQueryParser.java
b/jena-arq/src/test/java/org/apache/jena/sparql/syntax/TestQueryParser.java
index 6f447f9d61..acae80ff6e 100644
--- a/jena-arq/src/test/java/org/apache/jena/sparql/syntax/TestQueryParser.java
+++ b/jena-arq/src/test/java/org/apache/jena/sparql/syntax/TestQueryParser.java
@@ -70,7 +70,7 @@ public class TestQueryParser {
@Test
public void syntax_unicode_surrogate_pair_by_unicode_escape() {
- // Allow - because Java strings may have surrogate pairs so we allow
then in unicode escapes if paired.
+ // Allow - because Java strings may have surrogate pairs so we allow
them in unicode escapes if paired.
testParse("SELECT * { ?s ?p '\\uD801\\uDC37'}");
// QueryParseException ex = assertThrows(QueryParseException.class,
()->testParse("SELECT * { ?s ?p '\\uD801\\uDC37'}"));
