batch-analytics 0.2.5__tar.gz → 0.2.7__tar.gz

{batch_analytics-0.2.5 → batch_analytics-0.2.7}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: batch-analytics
-Version: 0.2.5
+Version: 0.2.7
 Summary: PySpark batch analytics: Extract, Transform, Stage, and analytical modules (linear regression, correlation, PCA, t-test).
 Author: Litewave Analytics Team
 License: MIT

{batch_analytics-0.2.5 → batch_analytics-0.2.7}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "batch-analytics"
-version = "0.2.5"
+version = "0.2.7"
 description = "PySpark batch analytics: Extract, Transform, Stage, and analytical modules (linear regression, correlation, PCA, t-test)."
 readme = "README.md"
 requires-python = ">=3.8"

{batch_analytics-0.2.5 → batch_analytics-0.2.7}/src/batch_analytics/config.py

@@ -29,7 +29,14 @@ class ClickHouseConfig:
 
     @property
     def jdbc_properties(self) -> dict:
-        props = {"user": self.user, "driver": "com.clickhouse.jdbc.ClickHouseDriver"}
+        props = {
+            "user": self.user,
+            "driver": "com.clickhouse.jdbc.ClickHouseDriver",
+            # Match Spark read codec default: avoids JDBC LZ4/gzip mismatches with server HTTP compression
+            "compress_algorithm": os.environ.get(
+                "CLICKHOUSE_JDBC_COMPRESS_ALGORITHM", "none"
+            ),
+        }
         if self.password:
             props["password"] = self.password
         return props

{batch_analytics-0.2.5 → batch_analytics-0.2.7}/src/batch_analytics/job_runner.py

@@ -92,6 +92,16 @@ def create_spark_session(
             builder = builder.config(f"spark.sql.catalog.{ch_cat}.password", ch.password)
         if ch.protocol.lower() == "https":
             builder = builder.config(f"spark.sql.catalog.{ch_cat}.option.ssl", "true")
+        # Avoid Lz4InputStream "Magic is not correct" when server HTTP compression != client expectation
+        # (see clickhouse-java#1449 / server enable_http_compression user defaults).
+        read_codec = os.environ.get(
+            "SPARK_CLICKHOUSE_READ_COMPRESSION_CODEC", "none"
+        ).strip()
+        if read_codec:
+            builder = builder.config(
+                "spark.clickhouse.read.compression.codec",
+                read_codec,
+            )
 
     if cfg.master.startswith("k8s://"):
         driver_host = socket.gethostbyname(socket.gethostname())
@@ -166,10 +176,12 @@ def run_pipeline(
         # Override: BATCH_SPARK_CLICKHOUSE_PACKAGES=maven coords / https jar URLs (comma-sep) or "" for SPARK_JARS only.
         _raw_ch = os.environ.get("BATCH_SPARK_CLICKHOUSE_PACKAGES")
         if _raw_ch is None:
+            # Shaded *-all.jar; pin matches Docker image / SPARK_JARS (0.9.x; no 0.10.x on Central for this artifact).
+            _ch_jdbc = os.environ.get("BATCH_CLICKHOUSE_JDBC_VERSION", "0.9.8").strip()
             ch_pkgs = (
                 "com.clickhouse.spark:clickhouse-spark-runtime-3.5_2.12:0.8.0,"
-                "https://repo1.maven.org/maven2/com/clickhouse/clickhouse-jdbc/0.6.2/"
-                "clickhouse-jdbc-0.6.2-all.jar"
+                f"https://repo1.maven.org/maven2/com/clickhouse/clickhouse-jdbc/{_ch_jdbc}/"
+                f"clickhouse-jdbc-{_ch_jdbc}-all.jar"
             )
         elif not _raw_ch.strip():
             ch_pkgs = None

{batch_analytics-0.2.5 → batch_analytics-0.2.7}/src/batch_analytics.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: batch-analytics
-Version: 0.2.5
+Version: 0.2.7
 Summary: PySpark batch analytics: Extract, Transform, Stage, and analytical modules (linear regression, correlation, PCA, t-test).
 Author: Litewave Analytics Team
 License: MIT