Add missing solr 9 configuration directory

dbmdz · May 18, 2022 · d5c22ad · d5c22ad
1 parent 17e29e2
commit d5c22ad
Show file tree

Hide file tree

Showing 4 changed files with 67 additions and 9 deletions.
diff --git a/.github/workflows/ci.yml b/.github/workflows/ci.yml
@@ -7,15 +7,12 @@ on:
 jobs:
   build:
     runs-on: ubuntu-latest
-    strategy:
-      matrix:
-        java: [11, 14]
     steps:
       - uses: actions/checkout@v2
       - name: Set up JDK
         uses: actions/setup-java@v1
         with:
-          java-version: ${{ matrix.java }}
+          java-version: 11
       - uses: actions/cache@v2
         env:
           cache-name: cache-maven-artifacts

diff --git a/integration-tests/run.sh b/integration-tests/run.sh
@@ -4,13 +4,21 @@ SOLR_HOST="${SOLR_HOST:-localhost}"
 SCRIPT_DIR="$( cd "$( dirname "${BASH_SOURCE[0]}" )" >/dev/null 2>&1 && pwd )"
 SOLR7_VERSIONS="7.7 7.6 7.5"
 SOLR8_VERSIONS="8.11 8.10 8.9 8.8 8.7 8.6 8.5 8.4 8.3 8.2 8.1 8.0"
-SOLR9_VERSIONS="9.0.0"
+SOLR9_VERSIONS="9.0"
 SOLR78_PLUGIN_PATH=/tmp/solrocr-solr78
 
 wait_for_solr() {
-    while [[ "$(curl -s -o /dev/null http://$SOLR_HOST:31337/solr/ocr/select -w '%{http_code}')" != "200" ]]; do
+    status="404"
+    while [[ "$status" != "200" ]]; do
+        set +e
+        status="$(curl -s -o /dev/null http://$SOLR_HOST:31337/solr/ocr/select -w '%{http_code}')"
+        if [[ "$status" == "500" ]]; then
+            docker logs $1
+            exit 1
+        fi
         sleep 3;
     done
+    set -e
 }
 
 create_solr78_jar() {
@@ -43,7 +51,7 @@ for version in $SOLR9_VERSIONS; do
         -p "31337:8983" \
         solr:$version \
         solr-precreate ocr /opt/core-config > /dev/null 2>&1 & \
-    wait_for_solr
+    wait_for_solr "$container_name"
     if ! python3 test.py; then
         printf " !!!FAIL!!!\n"
         docker logs
@@ -68,7 +76,7 @@ for version in $SOLR8_VERSIONS; do
         -p "31337:8983" \
         solr:$version \
         solr-precreate ocr /opt/core-config > /dev/null 2>&1 & \
-    wait_for_solr
+    wait_for_solr "$container_name"
     if ! python3 test.py; then
         printf " !!!FAIL!!!\n"
         docker logs
@@ -92,7 +100,7 @@ for version in $SOLR7_VERSIONS; do
         -p "31337:8983" \
         solr:$version \
         solr-precreate ocr /opt/core-config > /dev/null 2>&1 & \
-    wait_for_solr
+    wait_for_solr "$container_name"
     if ! python3 test.py; then
         printf " !!!FAIL!!!\n"
         docker logs

diff --git a/integration-tests/solr/core/v9/schema.xml b/integration-tests/solr/core/v9/schema.xml
@@ -0,0 +1,35 @@
+<schema name="coordinateHighlight" version="1.0">
+  <types>
+    <fieldType name="string" class="solr.StrField" sortMissingLast="true" omitNorms="true"/>
+    <fieldtype name="text_ocr" class="solr.TextField" storeOffsetsWithPositions="true" termVectors="true">
+      <analyzer type="index">
+        <charFilter class="de.digitalcollections.solrocr.lucene.filters.ExternalUtf8ContentFilterFactory" />
+        <charFilter class="de.digitalcollections.solrocr.lucene.filters.OcrCharFilterFactory" />
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.StopFilterFactory"/>
+        <filter class="solr.PorterStemFilterFactory"/>
+      </analyzer>
+      <analyzer type="query">
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.StopFilterFactory"/>
+        <filter class="solr.PorterStemFilterFactory"/>
+      </analyzer>
+    </fieldtype>
+    <fieldType name="text" class="solr.TextField">
+      <analyzer>
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.StopFilterFactory"/>
+        <filter class="solr.PorterStemFilterFactory"/>
+      </analyzer>
+  </fieldType>
+  </types>
+
+  <fields>
+    <field name="id"              type="string"   multiValued="false" indexed="true" stored="true" required="true" />
+    <field name="ocr_text"        type="text_ocr" multiValued="false" indexed="true" stored="true" />
+  </fields>
+  <uniqueKey>id</uniqueKey>
+</schema>
diff --git a/integration-tests/solr/core/v9/solrconfig.xml b/integration-tests/solr/core/v9/solrconfig.xml
@@ -0,0 +1,18 @@
+<config>
+  <luceneMatchVersion>9.0</luceneMatchVersion>
+  <directoryFactory name="DirectoryFactory" class="${solr.directoryFactory:solr.StandardDirectoryFactory}"/>
+  <schemaFactory class="ClassicIndexSchemaFactory"/>
+
+  <lib dir="/var/solr/data/plugins" regex=".*\.jar" />
+
+  <searchComponent class="de.digitalcollections.solrocr.solr.OcrHighlightComponent"
+                   name="ocrHighlight" />
+
+  <requestHandler name="/select" class="solr.SearchHandler">
+    <arr name="components">
+      <str>query</str>
+      <str>ocrHighlight</str>
+      <str>highlight</str>
+    </arr>
+  </requestHandler>
+</config>