This is an automated email from the ASF dual-hosted git repository. tallison pushed a commit to branch branch_1x in repository https://gitbox.apache.org/repos/asf/tika.git
commit 66d09ebb1d030b8135d0f4b22caaf6e87728fa32 Author: tallison <[email protected]> AuthorDate: Mon Nov 25 13:18:33 2019 -0500 TIKA-3000 Users should be able to configure POI's byte array max override --- .../apache/tika/parser/microsoft/AbstractOfficeParser.java | 13 +++++++++++++ 1 file changed, 13 insertions(+) diff --git a/tika-parsers/src/main/java/org/apache/tika/parser/microsoft/AbstractOfficeParser.java b/tika-parsers/src/main/java/org/apache/tika/parser/microsoft/AbstractOfficeParser.java index 53f7dd1..83d8a64 100644 --- a/tika-parsers/src/main/java/org/apache/tika/parser/microsoft/AbstractOfficeParser.java +++ b/tika-parsers/src/main/java/org/apache/tika/parser/microsoft/AbstractOfficeParser.java @@ -16,6 +16,7 @@ */ package org.apache.tika.parser.microsoft; +import org.apache.poi.util.IOUtils; import org.apache.tika.config.Field; import org.apache.tika.parser.AbstractParser; import org.apache.tika.parser.ParseContext; @@ -132,4 +133,16 @@ public abstract class AbstractOfficeParser extends AbstractParser { return defaultOfficeParserConfig.getExtractAllAlternativesFromMSG(); } + /** + * <b>WARNING:</b> this sets a static variable in POI. + * This allows users to override POI's protection of the allocation + * of overly large byte arrays. Use carefully; and please open up issues on + * POI's bugzilla to bump values for specific records. + * + * @param maxOverride + */ + @Field + public void setByteArrayMaxOverride(int maxOverride) { + IOUtils.setByteArrayMaxOverride(maxOverride); + } }
