Skip to content
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

Jump to bottom

[TIKA-1800] Decode the escape characters in front of special characters #578

Open
wants to merge 2 commits into
base: main
Choose a base branch
from
Open

[TIKA-1800] Decode the escape characters in front of special characters #578

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
9150753
[TIKA-1800] Decode the escape characters in front of special characters
longphan98 May 25, 2022
4fe09cf
Merge branch 'apache:main' into TIKA-1800
longphan98 May 29, 2022
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
15 changes: 12 additions & 3 deletions tika-core/src/main/java/org/apache/tika/mime/MediaType.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -39,15 +39,15 @@ public final class MediaType implements Comparable<MediaType>, Serializable {
*/
private static final long serialVersionUID = -3831000556189036392L;

private static final Pattern SPECIAL = Pattern.compile("[\\(\\)<>@,;:\\\\\"/\\[\\]\\?=]");
private static final Pattern SPECIAL = Pattern.compile("[()<>@,;:\\\\\"/\\[\\]?=]");

private static final Pattern SPECIAL_OR_WHITESPACE =
Pattern.compile("[\\(\\)<>@,;:\\\\\"/\\[\\]\\?=\\s]");
Pattern.compile("[()<>@,;:\\\\\"/\\[\\]?=\\s]");

/**
* See http://www.ietf.org/rfc/rfc2045.txt for valid mime-type characters.
*/
private static final String VALID_CHARS = "([^\\c\\(\\)<>@,;:\\\\\"/\\[\\]\\?=\\s]+)";
private static final String VALID_CHARS = "([^\\c\\()<>@,;:\\\\\"/\\[\\]?=\\s]+)";

private static final Pattern TYPE_PATTERN =
Pattern.compile("(?s)\\s*" + VALID_CHARS + "\\s*/\\s*" + VALID_CHARS + "\\s*($|;.*)");
Expand Down Expand Up @@ -331,6 +331,7 @@ private static Map<String, String> parseParameters(String string) {
/**
* Fuzzy unquoting mechanism that works also with somewhat malformed
* quotes.
* TIKA-1800: get rid of the escape characters which are in front of special characters for further usage (.e.g to parse on to a new MediaType as parameters)
*
* @param s string to unquote
* @return unquoted string
Expand All @@ -342,6 +343,14 @@ private static String unquote(String s) {
while (s.endsWith("\"") || s.endsWith("'")) {
s = s.substring(0, s.length() - 1);
}
for (int i = 0; i < s.length() - 1; i++) {
if (s.charAt(i) == '\\' && !('0' <= s.charAt(i + 1) && s.charAt(i + 1) <= '9') &&
!('a' <= s.charAt(i + 1) && s.charAt(i + 1) <= 'z') &&
s.charAt(i + 1) != '-' && s.charAt(i + 1) != '+' &&
s.charAt(i + 1) != '.' && s.charAt(i + 1) != '_') {
s = s.substring(0, i) + s.substring(i + 1);
}
}
return s;
}

Expand Down
13 changes: 13 additions & 0 deletions tika-core/src/test/java/org/apache/tika/mime/MediaTypeTest.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -21,13 +21,26 @@
import static org.junit.jupiter.api.Assertions.assertNotNull;
import static org.junit.jupiter.api.Assertions.assertTrue;

import java.io.IOException;
import java.util.HashMap;
import java.util.Map;

import org.apache.tika.exception.TikaException;
import org.junit.jupiter.api.Test;
import org.xml.sax.SAXException;

public class MediaTypeTest {

// TIKA-1800
@Test
public void testEscapedSpecialChar() {
MediaType mType = new MediaType(MediaType.APPLICATION_XML, "x-report", "#report?");
String cType = mType.toString();
mType = MediaType.parse(cType);
String report = mType.getParameters().get("x-report");
assertEquals("#report?", report);
}

@Test
public void testBasics() {
assertEquals("application/octet-stream",
Expand Down