From 129bc4edf24a2cd0e9f96c8e1311e28f2bf34d9d Mon Sep 17 00:00:00 2001 From: Simon Briggs Date: Mon, 9 Jul 2018 13:17:39 +0100 Subject: [PATCH] Add support for DOI url detection --- .../icm/cermine/metadata/extraction/enhancers/DoiEnhancer.java | 1 + 1 file changed, 1 insertion(+) diff --git a/cermine-impl/src/main/java/pl/edu/icm/cermine/metadata/extraction/enhancers/DoiEnhancer.java b/cermine-impl/src/main/java/pl/edu/icm/cermine/metadata/extraction/enhancers/DoiEnhancer.java index 1b7bb5ef..4f8aa6ad 100644 --- a/cermine-impl/src/main/java/pl/edu/icm/cermine/metadata/extraction/enhancers/DoiEnhancer.java +++ b/cermine-impl/src/main/java/pl/edu/icm/cermine/metadata/extraction/enhancers/DoiEnhancer.java @@ -36,6 +36,7 @@ public class DoiEnhancer extends AbstractMultiPatternEnhancer { private static final List PATTERNS = Lists.newArrayList( Pattern.compile("\\bdoi:?\\s*(" + PatternUtils.DOI_PATTERN + ")", Pattern.CASE_INSENSITIVE), + Pattern.compile("\\bhttps://doi.org/(" + PatternUtils.DOI_PATTERN + ")", Pattern.CASE_INSENSITIVE), Pattern.compile("\\bdx\\.doi\\.org/(" + PatternUtils.DOI_PATTERN + ")", Pattern.CASE_INSENSITIVE) ); private static final Set SEARCHED_ZONE_LABELS = EnumSet.of(BxZoneLabel.MET_BIB_INFO);