Merge pull request 'release_1.1.8' (#12) from release_1.1.8 into master

Reviewed-on: https://gitea.intranda.com/intranda/goobi-vocabulary-server/pulls/12
intranda · Oct 29, 2024 · f1fea75 · f1fea75
2 parents b244332 + bc7aa23
commit f1fea75
Show file tree

Hide file tree

Showing 7 changed files with 56 additions and 34 deletions.
diff --git a/Jenkinsfile b/Jenkinsfile
@@ -172,15 +172,25 @@ pipeline {
     }
     stage('build and publish production image to GitHub container registry') {
       agent any
+      when {
+        anyOf {
+          branch 'master'
+          branch 'develop'
+          branch 'hotfix_release_*'
+        }
+      }
       steps {
         unstash 'target'
         script {
           docker.withRegistry('https://ghcr.io','jenkins-github-container-registry') {
             dockerimage_public = docker.build("intranda/goobi-vocabulary-server:${env.BUILD_ID}_${env.GIT_COMMIT}")
+            if (env.GIT_BRANCH == 'origin/master' || env.GIT_BRANCH == 'master') {
+              dockerimage_public.push("latest")
+            }
             if (env.GIT_BRANCH == 'origin/develop' || env.GIT_BRANCH == 'develop') {
               dockerimage_public.push("develop")
             }
-            if (!latestTag == '' ) {
+            if (latestTag != '') {
               dockerimage_public.push(latestTag)
             }
           }

diff --git a/docs/de/setup.md b/docs/de/setup.md
@@ -86,7 +86,7 @@ sudo systemctl daemon-reload
 sudo systemctl enable vocabulary.service
 
 # create and configure the database
-sudo mysql -e "CREATE DATABASE ${VOC_SQL_DB};
+sudo mysql -e "CREATE DATABASE ${VOC_SQL_DB} CHARACTER SET = 'utf8mb4' COLLATE = 'utf8mb4_unicode_ci';
                CREATE USER '${VOC_SQL_USER}'@'localhost' IDENTIFIED BY '${PW_SQL_VOC}';
                GRANT ALL PRIVILEGES ON ${VOC_SQL_DB}.* TO '${VOC_SQL_USER}'@'localhost' WITH GRANT OPTION;
                FLUSH PRIVILEGES;"

diff --git a/migration/lib/api.py b/migration/lib/api.py
@@ -31,6 +31,9 @@
 
 class API:
     def __init__(self, host, port, token):
+        self.host = host
+        self.port = port
+        self.token = token
         self.urls = {}
         self.urls[SCHEMA_INSERTION] = SCHEMA_INSERTION_URL
         self.urls[VOCABULARY_INSERTION] = VOCABULARY_INSERTION_URL

diff --git a/migration/lib/mets_manipulator.py b/migration/lib/mets_manipulator.py
@@ -2,19 +2,21 @@
 import datetime
 import shutil
 from lxml import etree as ET
+import sys
 import re
 
-VOCABULARY_ENDPOINT = 'http://localhost:8081/api/v1/vocabularies/{{ID}}'
-RECORD_ENDPOINT = 'http://localhost:8081/api/v1/records/{{ID}}'
-
-VOCABULARY_URI_REGEX = re.compile(VOCABULARY_ENDPOINT.replace('{{ID}}', '\\d+'))
-RECORD_URI_REGEX = re.compile(RECORD_ENDPOINT.replace('{{ID}}', '\\d+'))
+VOCABULARY_ENDPOINT = 'http://{{HOST}}:{{PORT}}/api/v1/vocabularies/{{ID}}'
+RECORD_ENDPOINT = 'http://{{HOST}}:{{PORT}}/api/v1/records/{{ID}}'
 
 class MetsManipulator:
     def __init__(self, ctx, file_path):
         self.ctx = ctx
         self.file_path = file_path
         self.changed = False
+        self.vocabulary_endpoint = VOCABULARY_ENDPOINT.replace('{{HOST}}', ctx.api.host).replace('{{PORT}}', ctx.api.port)
+        self.record_endpoint = RECORD_ENDPOINT.replace('{{HOST}}', ctx.api.host).replace('{{PORT}}', ctx.api.port)
+        self.vocabulary_uri_regex = re.compile(self.vocabulary_endpoint.replace('{{ID}}', '\\d+'))
+        self.record_uri_regex = re.compile(self.record_endpoint.replace('{{ID}}', '\\d+'))
 
     def process(self):
         logging.debug(f'Processing mets file {self.file_path}')
@@ -56,7 +58,13 @@ def is_manual_id_reference(self, node):
         return self.ctx.manual_id_fix != None and node.tag.endswith('metadata') and 'name' in node.attrib and node.attrib['name'] == self.ctx.manual_id_fix
 
     def is_already_migrated(self, node):
-        return re.match(VOCABULARY_URI_REGEX, node.attrib['authorityURI']) != None and re.match(RECORD_URI_REGEX, node.attrib['valueURI']) != None
+        return re.match(self.vocabulary_uri_regex, node.attrib['authorityURI']) != None and re.match(self.record_uri_regex, node.attrib['valueURI']) != None
+
+    def generate_vocabulary_uri(self, vocabulary_id):
+        return self.vocabulary_endpoint.replace('{{ID}}', str(vocabulary_id))
+
+    def generate_record_uri(self, record_id):
+        return self.record_endpoint.replace('{{ID}}', str(record_id))
 
     def process_vocabulary_reference(self, node):
         try:
@@ -98,24 +106,26 @@ def process_vocabulary_reference(self, node):
             if vocabulary_id_new == None or record_id_new == None:
                 raise Exception(f'Unable to read old IDs from mets')
 
-            record_data = self.ctx.api.lookup_record(record_id_new)
-            main_field_id = self.ctx.find_main_field_id_for_vocabulary(record_data['vocabularyId'])
-            main_field_data = [f for f in record_data['fields'] if f['definitionId'] == main_field_id]
-            if len(main_field_data) != 1:
-                logging.critical(f'Record [{record_id_new}] has no unique main entry field')
-                sys.exit(1)
+            if not self.is_manual_id_reference(node):
+                record_data = self.ctx.api.lookup_record(record_id_new)
 
-            # Replace node text if not matching any translation of main value
-            translated_main_values = self.ctx.extract_language_values(main_field_data[0])
-            if not self.ctx.record_contains_value(record_data, node.text.strip()):
-                node.text = self.ctx.extract_preferred_language(translated_main_values)
+                main_field_id = self.ctx.find_main_field_id_for_vocabulary(record_data['vocabularyId'])
+                main_field_data = [f for f in record_data['fields'] if f['definitionId'] == main_field_id]
+                if len(main_field_data) != 1:
+                    logging.critical(f'Record [{record_id_new}] has no unique main entry field')
+                    sys.exit(1)
+
+                # Replace node text if not matching any translation of main value
+                translated_main_values = self.ctx.extract_language_values(main_field_data[0])
+                if not self.ctx.record_contains_value(record_data, node.text.strip()):
+                    node.text = self.ctx.extract_preferred_language(translated_main_values)
 
             vocabulary_name = self.ctx.lookup_vocabulary_name(vocabulary_id_new)
 
             # Set all attributes accordingly
             node.attrib['authority'] = vocabulary_name
-            node.attrib['authorityURI'] = generate_vocabulary_uri(vocabulary_id_new)
-            node.attrib['valueURI'] = generate_record_uri(record_id_new)
+            node.attrib['authorityURI'] = self.generate_vocabulary_uri(vocabulary_id_new)
+            node.attrib['valueURI'] = self.generate_record_uri(record_id_new)
 
             self.changed = True
         except Exception as e:
@@ -124,16 +134,15 @@ def process_vocabulary_reference(self, node):
             self.ctx.log_issue(self.file_path, error)
 
     def process_manual_id_reference(self, node):
-        record_id_old = int(node.text)
-        record_id_new = self.ctx.lookup_record_id(record_id_old)
-        node.text = str(record_id_new)
-        self.changed = True
-
-def generate_vocabulary_uri(vocabulary_id):
-    return VOCABULARY_ENDPOINT.replace('{{ID}}', str(vocabulary_id))
-
-def generate_record_uri(record_id):
-    return RECORD_ENDPOINT.replace('{{ID}}', str(record_id))
+        try:
+            record_id_old = int(node.text)
+            record_id_new = self.ctx.lookup_record_id(record_id_old)
+            node.text = str(record_id_new)
+            self.changed = True
+        except Exception as e:
+            msg = f'Unable to read ID {node.text}!'
+            logging.critical(msg)
+            raise Exception(msg)
 
 def dump_node(node):
     attributes = ' '.join(f'{k}="{v}"' for k, v in node.attrib.items())

diff --git a/module-core/pom.xml b/module-core/pom.xml
@@ -10,7 +10,7 @@
     </parent>
     <groupId>io.goobi.vocabulary</groupId>
     <artifactId>vocabulary-server-core</artifactId>
-    <version>1.1.7</version>
+    <version>1.1.8</version>
     <name>Vocabulary-Server-Core</name>
     <description>Spring Boot based RESTful web service for vocabulary management</description>
     <packaging>jar</packaging>
@@ -35,7 +35,7 @@
         <dependency>
             <groupId>io.goobi.vocabulary</groupId>
             <artifactId>vocabulary-server-exchange</artifactId>
-            <version>1.1.7</version>
+            <version>1.1.8</version>
             <scope>compile</scope>
         </dependency>
 

diff --git a/module-exchange/pom.xml b/module-exchange/pom.xml
@@ -4,7 +4,7 @@
     <modelVersion>4.0.0</modelVersion>
     <groupId>io.goobi.vocabulary</groupId>
     <artifactId>vocabulary-server-exchange</artifactId>
-    <version>1.1.7</version>
+    <version>1.1.8</version>
     <name>Vocabulary Exchange</name>
     <description>Vocabulary data exchange classes</description>
     <packaging>jar</packaging>

diff --git a/pom.xml b/pom.xml
@@ -4,7 +4,7 @@
     <modelVersion>4.0.0</modelVersion>
     <groupId>io.goobi.vocabulary</groupId>
     <artifactId>vocabulary-server</artifactId>
-    <version>1.1.7</version>
+    <version>1.1.8</version>
     <name>Vocabulary-Server</name>
     <packaging>pom</packaging>
     <description>RESTful webservice for vocabulary management</description>