#62951 - FileMagic not correctly identified

git-svn-id: https://svn.apache.org/repos/asf/poi/trunk@1847429 13f79535-47bb-0310-9956-ffa450edef68
This commit is contained in:
Andreas Beeker 2018-11-25 20:50:13 +00:00
parent d2cf03d353
commit 283ebe0e08
2 changed files with 28 additions and 11 deletions

View File

@ -78,7 +78,7 @@ public enum FileMagic {
/** PDF document */
PDF("%PDF"),
/** Some different HTML documents */
HTML("<!DOCTYP".getBytes(UTF_8), "<html".getBytes(UTF_8)),
HTML("<!DOCTYP".getBytes(UTF_8), "<html".getBytes(UTF_8), "<HTML".getBytes(UTF_8)),
WORD2(new byte[]{ (byte)0xdb, (byte)0xa5, 0x2d, 0x00}),
// keep UNKNOWN always as last enum!
/** UNKNOWN magic */
@ -101,17 +101,8 @@ public enum FileMagic {
public static FileMagic valueOf(byte[] magic) {
for (FileMagic fm : values()) {
int i=0;
boolean found = true;
for (byte[] ma : fm.magic) {
for (byte m : ma) {
byte d = magic[i++];
if (!(d == m || (m == 0x70 && (d == 0x10 || d == 0x20 || d == 0x40)))) {
found = false;
break;
}
}
if (found) {
if (findMagic(ma, magic)) {
return fm;
}
}
@ -119,6 +110,17 @@ public enum FileMagic {
return UNKNOWN;
}
private static boolean findMagic(byte[] cmp, byte[] actual) {
int i=0;
for (byte m : cmp) {
byte d = actual[i++];
if (!(d == m || (m == 0x70 && (d == 0x10 || d == 0x20 || d == 0x40)))) {
return false;
}
}
return true;
}
/**
* Get the file magic of the supplied {@link File}<p>

View File

@ -17,6 +17,7 @@
package org.apache.poi.poifs.filesystem;
import static java.nio.charset.StandardCharsets.UTF_8;
import static org.junit.Assert.assertEquals;
import static org.junit.Assert.assertTrue;
import static org.junit.Assert.fail;
@ -278,4 +279,18 @@ public final class TestPOIFSFileSystem {
private static InputStream openSampleStream(String sampleFileName) {
return HSSFTestDataSamples.openSampleFileStream(sampleFileName);
}
@Test
public void fileMagics() {
for (FileMagic fm : FileMagic.values()) {
if (fm == FileMagic.UNKNOWN) {
continue;
}
for (byte[] b : fm.magic) {
assertEquals(fm, FileMagic.valueOf(b));
}
}
assertEquals(FileMagic.UNKNOWN, FileMagic.valueOf("foobaa".getBytes(UTF_8)));
}
}