Author: lehmi
Date: Wed Sep 23 05:41:04 2026
New Revision: 1938450
Log:
PDFBOX-5660: remove no longer used code
Modified:
pdfbox/branches/3.0/pdfbox/src/main/java/org/apache/pdfbox/pdfparser/BaseParser.java
Modified:
pdfbox/branches/3.0/pdfbox/src/main/java/org/apache/pdfbox/pdfparser/BaseParser.java
==============================================================================
---
pdfbox/branches/3.0/pdfbox/src/main/java/org/apache/pdfbox/pdfparser/BaseParser.java
Wed Sep 23 04:26:07 2026 (r1938449)
+++
pdfbox/branches/3.0/pdfbox/src/main/java/org/apache/pdfbox/pdfparser/BaseParser.java
Wed Sep 23 05:41:04 2026 (r1938450)
@@ -18,13 +18,7 @@ package org.apache.pdfbox.pdfparser;
import java.io.ByteArrayOutputStream;
import java.io.IOException;
-import java.io.UnsupportedEncodingException;
-import java.nio.ByteBuffer;
-import java.nio.charset.CharacterCodingException;
-import java.nio.charset.Charset;
-import java.nio.charset.CharsetDecoder;
-import java.nio.charset.CodingErrorAction;
import java.nio.charset.StandardCharsets;
import org.apache.commons.logging.Log;
@@ -62,35 +56,12 @@ public abstract class BaseParser
static final int MAX_LENGTH_LONG = Long.toString(Long.MAX_VALUE).length();
- private static final Charset ALTERNATIVE_CHARSET;
-
private static final int MAX_RECURSION_DEPTH = 500;
private static final String MAX_RECUSRION_MSG = //
"Reached maximum recursion depth " +
Integer.toString(MAX_RECURSION_DEPTH);
private int recursionDepth = 0;
- static
- {
- Charset cs;
- String charsetName = "Windows-1252";
- try
- {
- cs = Charset.forName(charsetName);
- }
- catch (IllegalArgumentException | UnsupportedOperationException e)
- {
- cs = StandardCharsets.ISO_8859_1;
- LOG.warn("Charset is not supported: " + charsetName + ", falling
back to " + cs.name(), e);
- }
- ALTERNATIVE_CHARSET = cs;
- }
-
- // CharSetDecoders are not threadsafe so not static
- private final CharsetDecoder utf8Decoder =
StandardCharsets.UTF_8.newDecoder()
- .onMalformedInput(CodingErrorAction.REPORT)
- .onUnmappableCharacter(CodingErrorAction.REPORT);
-
protected static final int E = 'e';
protected static final int N = 'n';
protected static final int D = 'd';
@@ -920,27 +891,6 @@ public abstract class BaseParser
}
/**
- * Tries to decode the buffer cotent to an UTF-8 String.
- * If that fails, tries the alternative Encoding.
- * @param buffer the {@link ByteArrayOutputStream} containing the bytes to
decode
- * @return the decoded String
- */
- private String decodeBuffer(ByteArrayOutputStream buffer) throws
UnsupportedEncodingException
- {
- try
- {
- return
utf8Decoder.decode(ByteBuffer.wrap(buffer.toByteArray())).toString();
- }
- catch (CharacterCodingException e)
- {
- // some malformed PDFs don't use UTF-8 see PDFBOX-3347
- LOG.debug("Buffer could not be decoded using
StandardCharsets.UTF_8 - "
- + "trying " + ALTERNATIVE_CHARSET.name(), e);
- return buffer.toString(ALTERNATIVE_CHARSET.name());
- }
- }
-
- /**
* This will parse a directory object from the stream.
*
* @return The parsed object.
