commit e3af15beb2bcea9004bd1eed42301488ec3365d8
author Marc Kupietz <kupietz@ids-mannheim.de> Thu Mar 28 10:16:13 2024 +0100
committer Marc Kupietz <kupietz@ids-mannheim.de> Thu Mar 28 10:16:13 2024 +0100
tree a91877488c5e82190f682163ec7a55e2ea14fb43
parent 323e93e7323f3a62794850656955328c396d90ca

Catch sentence indices out of bounds like in v0

Change-Id: I27ee856890af1bc6604c0f32e3172fa2404a90e4

app/src/main/kotlin/de/ids_mannheim/korapxmltools/KorapXml2Conllu.kt

diff --git a/app/src/main/kotlin/de/ids_mannheim/korapxmltools/KorapXml2Conllu.kt b/app/src/main/kotlin/de/ids_mannheim/korapxmltools/KorapXml2Conllu.kt
index 01ebd58..763ecaf 100644
--- a/app/src/main/kotlin/de/ids_mannheim/korapxmltools/KorapXml2Conllu.kt
+++ b/app/src/main/kotlin/de/ids_mannheim/korapxmltools/KorapXml2Conllu.kt
@@ -504,7 +504,10 @@
                 }
                 if (morpho[docId]?.containsKey("${span.from}-${span.to}") == true) {
                     val mfs = morpho[docId]!!["${span.from}-${span.to}"]
-
+                    if (span.to > texts[docId]!!.length) {
+                        span.to = texts[docId]!!.length
+                        LOGGER.warning("Offset error: could not retrieve token at ${span.from}-${span.to} – ending with: ${texts[docId]!!.substring(span.from, span.to)}")
+                    }
                     output.append(
                         printConlluToken(
                             token_index,