D-Net
/
dnet-hadoop
14
5
Fork 11
Code Issues 14 Pull Requests 12 Projects 2 Releases 2 Wiki Activity

When converting json to XML, remove characters that are not allowed in the XML 1.0 specs, as they will cause xpath failures even if escaped

This commit is contained in:
Giambattista Bloisi 2024-02-28 15:14:18 +01:00
parent 56dd05f85c
commit 3cd5590f3b
2 changed files with 24 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

17
dhp-workflows/dhp-aggregation/src/main/java/eu/dnetlib/dhp/collection/plugin/utils/JsonUtils.java
View File

@ -49,6 +49,23 @@ public class JsonUtils {
res.put(i, cleanValue(array.opt(i))); res.put(i, cleanValue(array.opt(i)));
} }
return res; return res;
} else if (object instanceof String) {
String value = (String) object;
// XML 1.0 Allowed characters
// Char ::= #x9 | #xA | #xD | [#x20-#xD7FF] | [#xE000-#xFFFD] | [#x10000-#x10FFFF]
return value
.codePoints()
.filter(
cp -> cp == 0x9 || cp == 0xA || cp == 0xD || (cp >= 0x20 && cp <= 0xD7FF)
|| (cp >= 0xE000 && cp <= 0xFFFD)
|| (cp >= 0x10000 && cp <= 0x10FFFF))
.collect(
StringBuilder::new,
StringBuilder::appendCodePoint,
StringBuilder::append)
.toString();
} }
return object; return object;

7
dhp-workflows/dhp-aggregation/src/test/java/eu/dnetlib/dhp/collection/plugin/utils/JsonUtilsTest.java
View File

@ -38,4 +38,11 @@ class JsonUtilsTest {
wrapped("<parent><id>1</id></parent><parent><id>2</id></parent>"), wrapped("<parent><id>1</id></parent><parent><id>2</id></parent>"),
JsonUtils.convertToXML("{\"parent\": [{\"id\": 1}, {\"id\": 2}]}")); JsonUtils.convertToXML("{\"parent\": [{\"id\": 1}, {\"id\": 2}]}"));
} }
@Test
void removeControlCharacters() {
assertEquals(
wrapped("<m_100><n_200v>Test</n_200v></m_100>"),
JsonUtils.convertToXML("{\"100\" : {\"200v\" : \"\\u0000\\u000cTest\"}}"));
}
} }