This is an automated email from the ASF dual-hosted git repository. tallison pushed a commit to branch main in repository https://gitbox.apache.org/repos/asf/tika.git
commit 83b0de4d60161ebd4bc224141a959ac8c18d95f4 Author: tallison <[email protected]> AuthorDate: Mon Apr 18 15:47:44 2022 -0400 general code improvements --- tika-core/src/main/java/org/apache/tika/sax/StandardsText.java | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tika-core/src/main/java/org/apache/tika/sax/StandardsText.java b/tika-core/src/main/java/org/apache/tika/sax/StandardsText.java index 4bb863e3f..686832dcc 100644 --- a/tika-core/src/main/java/org/apache/tika/sax/StandardsText.java +++ b/tika-core/src/main/java/org/apache/tika/sax/StandardsText.java @@ -53,7 +53,7 @@ import org.apache.tika.sax.StandardReference.StandardReferenceBuilder; public class StandardsText { // Regular expression to match uppercase headers private static final String REGEX_HEADER = - "(\\d+\\.(\\d+\\.?)*)\\p{Blank}+([A-Z]+(\\s[A-Z]+)*){5,}"; + "(\\d{1,10}\\.(\\d{1,10}\\.?){0,10})\\p{Blank}+([A-Z]{1,256}(\\s[A-Z]+){0,256}){5,}"; // Regular expression to match the "APPLICABLE DOCUMENTS" and equivalent // sections
