Merge pull request #193 from MontrealCorpusTools/update-packaging

Update packaging and neo4j version

environment.yml

@@ -2,16 +2,16 @@ name: polyglotdb-dev
 channels:
     - conda-forge
 dependencies:
+    - openjdk=21
+    - pip
     - librosa
-    - scipy
-    - praatio ~= 5.0
+    - scipy<=1.12.0
+    - praatio<=5.0
     - textgrid
     - influxdb
     - tqdm
     - future
     - requests
-    - openjdk=11
-    - pip
+    - neo4j-python-driver
     - pip:
-        - conch_sounds
-        - neo4j-driver ~= 4.3
+        - conch-sounds

polyglotdb/__init__.py

@@ -1,8 +1,3 @@
-__ver_major__ = 1
-__ver_minor__ = 2
-__ver_patch__ = 1
-__version__ = f"{__ver_major__}.{__ver_minor__}.{__ver_patch__}"
-
 __all__ = ['query', 'io', 'corpus', 'config', 'exceptions', 'CorpusContext', 'CorpusConfig']
 
 import polyglotdb.query.annotations as graph

polyglotdb/acoustics/io.py

@@ -145,10 +145,11 @@ def point_measures_from_csv(corpus_context, header_info, annotation_type="phone"
             import_path = 'file:///{}'.format(make_path_safe(path))
 
         import_statement = '''
-                USING PERIODIC COMMIT 2000
-                LOAD CSV WITH HEADERS FROM "{path}" AS csvLine
-                MATCH (n:{annotation_type}:{corpus_name}) where n.id = csvLine.id
-                SET {new_properties}'''
+                CALL {{
+                    LOAD CSV WITH HEADERS FROM "{path}" AS csvLine
+                    MATCH (n:{annotation_type}:{corpus_name}) WHERE n.id = csvLine.id
+                    SET {new_properties}
+                }} IN TRANSACTIONS OF 2000 ROWS'''
 
         statement = import_statement.format(path=import_path,
                                             corpus_name=corpus_context.cypher_safe_name,
@@ -159,7 +160,7 @@ def point_measures_from_csv(corpus_context, header_info, annotation_type="phone"
         if h == 'id':
             continue
         try:
-            corpus_context.execute_cypher('CREATE INDEX ON :%s(%s)' % (annotation_type, h))
+            corpus_context.execute_cypher('CREATE INDEX FOR (n:%s) ON (n.%s)' % (annotation_type, h))
         except neo4j.exceptions.ClientError as e:
             if e.code != 'Neo.ClientError.Schema.EquivalentSchemaRuleAlreadyExists':
                 raise

polyglotdb/config.py

@@ -2,7 +2,7 @@
 import logging
 import configparser
 
-CONFIG_DIR = os.path.expanduser('~/.pgdb')
+CONFIG_DIR = os.environ.get('PGDB_HOME', os.path.expanduser('~/.pgdb'))
 
 BASE_DIR = os.path.join(CONFIG_DIR, 'data')
 

polyglotdb/corpus/importable.py

@@ -52,13 +52,13 @@ def initialize_import(self, speakers, token_headers, subannotations=None):
                             w.writeheader()
 
         def _corpus_index(tx):
-            tx.run('CREATE CONSTRAINT ON (node:Corpus) ASSERT node.name IS UNIQUE')
+            tx.run('CREATE CONSTRAINT FOR (node:Corpus) REQUIRE node.name IS UNIQUE')
 
         def _discourse_index(tx):
-            tx.run('CREATE INDEX ON :Discourse(name)')
+            tx.run('CREATE INDEX FOR (d:Discourse) ON (d.name)')
 
         def _speaker_index(tx):
-            tx.run('CREATE INDEX ON :Speaker(name)')
+            tx.run('CREATE INDEX FOR (s:Speaker) ON (s.name)')
 
         def _corpus_create(tx, corpus_name):
             tx.run('MERGE (n:Corpus {name: $corpus_name}) return n', corpus_name=corpus_name)

polyglotdb/databases/neo4j.conf

@@ -32,8 +32,8 @@ dbms.security.auth_enabled=false
 # calculated based on available system resources.
 # Uncomment these lines to set specific initial and maximum
 # heap size.
-dbms.memory.heap.initial_size=512m
-dbms.memory.heap.max_size=512m
+server.memory.heap.initial_size=512m
+server.memory.heap.max_size=512m
 
 # The amount of memory to use for mapping the store files, in bytes (or
 # kilobytes with the 'k' suffix, megabytes with 'm' and gigabytes with 'g').
@@ -66,17 +66,17 @@ dbms.memory.heap.max_size=512m
 # individual advertised_address.
 
 # Bolt connector
-dbms.connector.bolt.enabled=true
+server.bolt.enabled=true
 #dbms.connector.bolt.tls_level=OPTIONAL
-dbms.connector.bolt.listen_address=:{bolt_port}
+server.bolt.listen_address=:{bolt_port}
 
 # HTTP Connector. There can be zero or one HTTP connectors.
-dbms.connector.http.enabled=true
-dbms.connector.http.listen_address=:{http_port}
+server.http.enabled=true
+server.http.listen_address=:{http_port}
 
 # HTTPS Connector. There can be zero or one HTTPS connectors.
-dbms.connector.https.enabled=false
-dbms.connector.https.listen_address=:{https_port}
+server.https.enabled=false
+server.https.listen_address=:{https_port}
 
 # Number of Neo4j worker threads.
 #dbms.threads.worker_count=
@@ -255,7 +255,7 @@ dbms.security.allow_csv_import_from_file_urls=true
 #dbms.security.http_strict_transport_security=
 
 # Retention policy for transaction logs needed to perform recovery and backups.
-dbms.tx_log.rotation.retention_policy=false
+db.tx_log.rotation.retention_policy=false
 
 # Only allow read operations from this Neo4j instance. This mode still requires
 # write access to the directory for lock purposes.
@@ -283,31 +283,20 @@ dbms.tx_log.rotation.retention_policy=false
 
 # G1GC generally strikes a good balance between throughput and tail
 # latency, without too much tuning.
-dbms.jvm.additional=-XX:+UseG1GC
-
 # Have common exceptions keep producing stack traces, so they can be
 # debugged regardless of how often logs are rotated.
-dbms.jvm.additional=-XX:-OmitStackTraceInFastThrow
-
 # Make sure that `initmemory` is not only allocated, but committed to
 # the process, before starting the database. This reduces memory
 # fragmentation, increasing the effectiveness of transparent huge
 # pages. It also reduces the possibility of seeing performance drop
 # due to heap-growing GC events, where a decrease in available page
 # cache leads to an increase in mean IO response time.
 # Try reducing the heap memory, if this flag degrades performance.
-dbms.jvm.additional=-XX:+AlwaysPreTouch
-
 # Trust that non-static final fields are really final.
 # This allows more optimizations and improves overall performance.
 # NOTE: Disable this if you use embedded mode, or have extensions or dependencies that may use reflection or
 # serialization to change the value of final fields!
-dbms.jvm.additional=-XX:+UnlockExperimentalVMOptions
-dbms.jvm.additional=-XX:+TrustFinalNonStaticFields
-
 # Disable explicit garbage collection, which is occasionally invoked by the JDK itself.
-dbms.jvm.additional=-XX:+DisableExplicitGC
-
 # Remote JMX monitoring, uncomment and adjust the following lines as needed. Absolute paths to jmx.access and
 # jmx.password files are required.
 # Also make sure to update the jmx.access and jmx.password files with appropriate permission roles and passwords,
@@ -328,10 +317,23 @@ dbms.jvm.additional=-XX:+DisableExplicitGC
 
 # Expand Diffie Hellman (DH) key size from default 1024 to 2048 for DH-RSA cipher suites used in server TLS handshakes.
 # This is to protect the server from any potential passive eavesdropping.
-dbms.jvm.additional=-Djdk.tls.ephemeralDHKeySize=2048
-
 # This mitigates a DDoS vector.
-dbms.jvm.additional=-Djdk.tls.rejectClientInitiatedRenegotiation=true
+#********************************************************************
+# Other Neo4j system properties
+#********************************************************************
+server.jvm.additional=-XX:+UseG1GC
+server.jvm.additional=-XX:-OmitStackTraceInFastThrow
+server.jvm.additional=-XX:+AlwaysPreTouch
+server.jvm.additional=-XX:+UnlockExperimentalVMOptions
+server.jvm.additional=-XX:+TrustFinalNonStaticFields
+server.jvm.additional=-XX:+DisableExplicitGC
+server.jvm.additional=-Djdk.tls.ephemeralDHKeySize=2048
+server.jvm.additional=-Djdk.tls.rejectClientInitiatedRenegotiation=true
+server.jvm.additional=-Dunsupported.dbms.udc.source=tarball
+server.jvm.additional=--add-opens=java.base/java.nio=ALL-UNNAMED
+server.jvm.additional=--add-opens=java.base/java.io=ALL-UNNAMED
+server.jvm.additional=--add-opens=java.base/sun.nio.ch=ALL-UNNAMED
+server.jvm.additional=-Dlog4j2.disable.jmx=true
 
 #********************************************************************
 # Wrapper Windows NT/2000/XP Service Properties
@@ -342,9 +344,4 @@ dbms.jvm.additional=-Djdk.tls.rejectClientInitiatedRenegotiation=true
 #  service can then be reinstalled.
 
 # Name of the service
-dbms.windows_service_name=neo4j
-
-#********************************************************************
-# Other Neo4j system properties
-#********************************************************************
-dbms.jvm.additional=-Dunsupported.dbms.udc.source=tarball
+server.windows_service_name=neo4j