louisdevie/mustangproject
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

merged BOM functionality in XMLtools

Browse Source
This commit is contained in:
jstaerk
2020-11-12 06:49:46 +01:00
parent 599320462d
commit 46c7e25ef9
2 changed files with 3 additions and 30 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
library/src/main/java/org/mustangproject/XMLTools.java
View File

@@ -98,7 +98,7 @@ public class XMLTools extends XMLWriter {
* @param is the ByteArrayInputStream used
* @throws IOException if can not be read from is
* @see <a href="https://www.w3.org/TR/xml/#sec-guessing">Autodetection of Character Encodings</a>
*/
*
public static int guessBOMSize(ByteArrayInputStream is) throws IOException {
byte[] pad = new byte[4];
is.read(pad);
@@ -118,7 +118,7 @@ public class XMLTools extends XMLWriter {
return 2;
}
return 0;
}
}*/
/***
* removes utf8 byte order marks from byte arrays, in case one is there

29
library/src/main/java/org/mustangproject/ZUGFeRD/ZUGFeRDImporter.java
View File

@@ -171,7 +171,7 @@ public class ZUGFeRDImporter {
xmlFact.setNamespaceAware(false);
DocumentBuilder builder = xmlFact.newDocumentBuilder();
ByteArrayInputStream is = new ByteArrayInputStream(rawXML);
is.skip(guessBOMSize(is));
/// is.skip(guessBOMSize(is));
document = builder.parse(is);
}
@@ -187,33 +187,6 @@ public class ZUGFeRDImporter {
}
/**
* Skips over a BOM at the beginning of the given ByteArrayInputStream, if one exists.
*
* @param is the ByteArrayInputStream used
* @throws IOException if can not be read from is
* @see <a href="https://www.w3.org/TR/xml/#sec-guessing">Autodetection of Character Encodings</a>
*/
private int guessBOMSize(ByteArrayInputStream is) throws IOException {
byte[] pad = new byte[4];
is.read(pad);
is.reset();
int test2 = ((pad[0] & 0xFF) << 8) | (pad[1] & 0xFF);
int test3 = ((test2 & 0xFFFF) << 8) | (pad[2] & 0xFF);
int test4 = ((test3 & 0xFFFFFF) << 8) | (pad[3] & 0xFF);
//
if (test4 == 0x0000FEFF || test4 == 0xFFFE0000 || test4 == 0x0000FFFE || test4 == 0xFEFF0000) {
// UCS-4: BOM takes 4 bytes
return 4;
} else if (test3 == 0xEFBBFF) {
// UTF-8: BOM takes 3 bytes
return 3;
} else if (test2 == 0xFEFF || test2 == 0xFFFE) {
// UTF-16: BOM takes 2 bytes
return 2;
}
return 0;
}
protected String extractString(String xpathStr) {