❯ head -30 target/rat.txt
*****************************************************
Summary
-------
Generated at: 2025年10月21日T18:46:08-07:00
Notes: 4
Binaries: 5
Archives: 0
Standards: 311
Apache Licensed: 307
Generated Documents: 0
JavaDocs are generated and so license header is optional
Generated files do not required license headers
4 Unknown Licenses
*******************************
Unapproved licenses:
 src/ports/cloudberry/cmake/FindCloudberry.cmake
 src/ports/cloudberry/cmake/FindCloudberry_1.cmake
 src/ports/cloudberry/cmake/FindCloudberry_2.cmake
 src/ports/cloudberry/cmake/FindCloudberry_3.cmake
*******************************

cmake \
 -DCLOUDBERRY_3_PG_CONFIG=/usr/local/cloudberry/bin/pg_config \
 -DCMAKE_C_COMPILER=gcc \
 -DCMAKE_CXX_COMPILER=g++ \
 -DCMAKE_BUILD_TYPE=Release \
 -DCMAKE_INSTALL_PREFIX=/usr/local/madlib \
 -DCLOUDBERRY_3_EXECUTABLE=/usr/local/cloudberry/bin/postgres \
 ..

Error:
CMake Error at src/CMakeLists.txt:202 (add_library):
 Cannot find source file:
 /home/cbadmin/bom-parts/madlib/src/ports/cloudberry/dbconnector/Compatibility.hpp

## Download this PR change
git clone https://github.com/apache/madlib.git
cd madlib
git fetch origin pull/627/head:zhangwenchao-123/support_cloudberry
git switch zhangwenchao-123/support_cloudberry
## Set Python env
sudo alternatives --install /usr/bin/python python /usr/bin/python3 1
## Install required depencies to the Cloudberry Dev container
sudo dnf install boost-devel -y
sudo dnf install -y graphviz # for docs
sudo dnf install --enablerepo=crb doxygen -y # for docs
pip install mock pandas numpy xgboost scikit-learn pyyaml pyxb-x pypmml
## 
cd ~/madlib
mkdir build ; cd build
## for Cloudberry 3.0
cmake \
 -DCLOUDBERRY_3_PG_CONFIG=$GPHOME/bin/pg_config \
 -DCMAKE_C_COMPILER=gcc \
 -DCMAKE_CXX_COMPILER=g++ \
 -DCMAKE_BUILD_TYPE=Release \
 -DCMAKE_INSTALL_PREFIX=/usr/local/madlib \
 -DCLOUDBERRY_3_EXECUTABLE=$GPHOME/bin/postgres \
 ..
## for Cloudberry 2.0
cmake \
 -DCLOUDBERRY_2_PG_CONFIG=$GPHOME/bin/pg_config \
 -DCMAKE_C_COMPILER=gcc \
 -DCMAKE_CXX_COMPILER=g++ \
 -DCMAKE_BUILD_TYPE=Release \
 -DCMAKE_INSTALL_PREFIX=/usr/local/madlib \
 -DCLOUDBERRY_2_EXECUTABLE=$GPHOME/bin/postgres \
 ..
## Make, deploy, and run test
make -j$(nproc)
./src/bin/madpack -p cloudberry -c gpadmin@localhost:7000/postgres install
./src/bin/madpack -p cloudberry -c gpadmin@localhost:7000/postgres install-check

[gpadmin@cdw build]$ ./src/bin/madpack -p cloudberry -c gpadmin@localhost:7000/postgres install-check
madpack.py: INFO : Detected Apache Cloudberry version 2.0.0.
TEST CASE RESULT|Module: array_ops|array_ops.ic.sql_in|PASS|Time: 74 milliseconds
TEST CASE RESULT|Module: bayes|bayes.ic.sql_in|PASS|Time: 320 milliseconds
TEST CASE RESULT|Module: crf|crf_test_small.ic.sql_in|PASS|Time: 285 milliseconds
TEST CASE RESULT|Module: crf|crf_train_small.ic.sql_in|PASS|Time: 285 milliseconds
TEST CASE RESULT|Module: elastic_net|elastic_net.ic.sql_in|PASS|Time: 190 milliseconds
TEST CASE RESULT|Module: linalg|svd.ic.sql_in|PASS|Time: 572 milliseconds
TEST CASE RESULT|Module: linalg|matrix_ops.ic.sql_in|PASS|Time: 822 milliseconds
TEST CASE RESULT|Module: linalg|linalg.ic.sql_in|PASS|Time: 76 milliseconds
TEST CASE RESULT|Module: pmml|pmml.ic.sql_in|PASS|Time: 452 milliseconds
TEST CASE RESULT|Module: prob|prob.ic.sql_in|PASS|Time: 28 milliseconds
TEST CASE RESULT|Module: svm|svm.ic.sql_in|PASS|Time: 315 milliseconds
TEST CASE RESULT|Module: tsa|arima.ic.sql_in|PASS|Time: 1074 milliseconds
TEST CASE RESULT|Module: stemmer|porter_stemmer.ic.sql_in|PASS|Time: 34 milliseconds
TEST CASE RESULT|Module: conjugate_gradient|conj_grad.ic.sql_in|PASS|Time: 142 milliseconds
TEST CASE RESULT|Module: knn|knn.ic.sql_in|PASS|Time: 175 milliseconds
TEST CASE RESULT|Module: lda|lda.ic.sql_in|PASS|Time: 246 milliseconds
TEST CASE RESULT|Module: stats|correlation.ic.sql_in|PASS|Time: 182 milliseconds
TEST CASE RESULT|Module: stats|mw_test.ic.sql_in|PASS|Time: 42 milliseconds
TEST CASE RESULT|Module: stats|pred_metrics.ic.sql_in|PASS|Time: 255 milliseconds
TEST CASE RESULT|Module: stats|chi2_test.ic.sql_in|PASS|Time: 37 milliseconds
TEST CASE RESULT|Module: stats|anova_test.ic.sql_in|PASS|Time: 47 milliseconds
TEST CASE RESULT|Module: stats|t_test.ic.sql_in|PASS|Time: 42 milliseconds
TEST CASE RESULT|Module: stats|cox_prop_hazards.ic.sql_in|PASS|Time: 211 milliseconds
TEST CASE RESULT|Module: stats|ks_test.ic.sql_in|PASS|Time: 84 milliseconds
TEST CASE RESULT|Module: stats|robust_and_clustered_variance_coxph.ic.sql_in|PASS|Time: 355 milliseconds
TEST CASE RESULT|Module: stats|wsr_test.ic.sql_in|PASS|Time: 46 milliseconds
TEST CASE RESULT|Module: stats|f_test.ic.sql_in|PASS|Time: 38 milliseconds
TEST CASE RESULT|Module: utilities|utilities.ic.sql_in|PASS|Time: 115 milliseconds
TEST CASE RESULT|Module: utilities|pivot.ic.sql_in|PASS|Time: 119 milliseconds
TEST CASE RESULT|Module: utilities|path.ic.sql_in|PASS|Time: 159 milliseconds
TEST CASE RESULT|Module: utilities|transform_vec_cols.ic.sql_in|PASS|Time: 156 milliseconds
TEST CASE RESULT|Module: utilities|text_utilities.ic.sql_in|PASS|Time: 126 milliseconds
TEST CASE RESULT|Module: utilities|sessionize.ic.sql_in|PASS|Time: 105 milliseconds
TEST CASE RESULT|Module: utilities|encode_categorical.ic.sql_in|PASS|Time: 186 milliseconds
TEST CASE RESULT|Module: utilities|minibatch_preprocessing.ic.sql_in|PASS|Time: 186 milliseconds
TEST CASE RESULT|Module: assoc_rules|assoc_rules.ic.sql_in|FAIL|Time: 568 milliseconds
madpack.py: ERROR : Failed executing /tmp/madlib.7qnxdkya/assoc_rules/assoc_rules.ic.sql_in.tmp
madpack.py: ERROR : Check the log at /tmp/madlib.7qnxdkya/assoc_rules/assoc_rules.ic.sql_in.log
TEST CASE RESULT|Module: convex|lmf.ic.sql_in|PASS|Time: 297 milliseconds
TEST CASE RESULT|Module: convex|mlp.ic.sql_in|PASS|Time: 507 milliseconds
TEST CASE RESULT|Module: deep_learning|keras_model_arch_table.ic.sql_in|PASS|Time: 149 milliseconds
TEST CASE RESULT|Module: glm|glm.ic.sql_in|PASS|Time: 906 milliseconds
TEST CASE RESULT|Module: graph|graph.ic.sql_in|PASS|Time: 1343 milliseconds
TEST CASE RESULT|Module: linear_systems|sparse_linear_sytems.ic.sql_in|PASS|Time: 132 milliseconds
TEST CASE RESULT|Module: linear_systems|dense_linear_sytems.ic.sql_in|PASS|Time: 125 milliseconds
TEST CASE RESULT|Module: recursive_partitioning|decision_tree.ic.sql_in|PASS|Time: 252 milliseconds
TEST CASE RESULT|Module: recursive_partitioning|random_forest.ic.sql_in|PASS|Time: 322 milliseconds
TEST CASE RESULT|Module: regress|robust.ic.sql_in|PASS|Time: 193 milliseconds
TEST CASE RESULT|Module: regress|logistic.ic.sql_in|PASS|Time: 249 milliseconds
TEST CASE RESULT|Module: regress|linear.ic.sql_in|PASS|Time: 31 milliseconds
TEST CASE RESULT|Module: regress|clustered.ic.sql_in|PASS|Time: 189 milliseconds
TEST CASE RESULT|Module: regress|multilogistic.ic.sql_in|PASS|Time: 323 milliseconds
TEST CASE RESULT|Module: regress|marginal.ic.sql_in|PASS|Time: 457 milliseconds
TEST CASE RESULT|Module: sample|balance_sample.ic.sql_in|PASS|Time: 139 milliseconds
TEST CASE RESULT|Module: sample|train_test_split.ic.sql_in|PASS|Time: 166 milliseconds
TEST CASE RESULT|Module: sample|sample.ic.sql_in|PASS|Time: 20 milliseconds
TEST CASE RESULT|Module: sample|stratified_sample.ic.sql_in|PASS|Time: 112 milliseconds
TEST CASE RESULT|Module: summary|summary.ic.sql_in|PASS|Time: 148 milliseconds
TEST CASE RESULT|Module: kmeans|kmeans.ic.sql_in|PASS|Time: 661 milliseconds
TEST CASE RESULT|Module: pca|pca.ic.sql_in|PASS|Time: 1475 milliseconds
TEST CASE RESULT|Module: pca|pca_project.ic.sql_in|PASS|Time: 528 milliseconds
TEST CASE RESULT|Module: validation|cross_validation.ic.sql_in|PASS|Time: 332 milliseconds
INFO: Log files saved in /tmp/madlib.7qnxdkya

[gpadmin@cdw build]$ cat /tmp/madlib.7qnxdkya/assoc_rules/assoc_rules.ic.sql_in.log
-- Switch to test user:
SET ROLE "madlib_210_installcheck_postgres";
SET
-- Set SEARCH_PATH for install-check:
SET search_path=madlib_installcheck_assoc_rules,madlib;
SET
/* ----------------------------------------------------------------------- *//**
 *
 * Licensed to the Apache Software Foundation (ASF) under one
 * or more contributor license agreements. See the NOTICE file
 * distributed with this work for additional information
 * regarding copyright ownership. The ASF licenses this file
 * to you under the Apache License, Version 2.0 (the
 * "License"); you may not use this file except in compliance
 * with the License. You may obtain a copy of the License at
 *
 * http://www.apache.org/licenses/LICENSE-2.0
 *
 * Unless required by applicable law or agreed to in writing,
 * software distributed under the License is distributed on an
 * "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
 * KIND, either express or implied. See the License for the
 * specific language governing permissions and limitations
 * under the License.
 *
 *//* ----------------------------------------------------------------------- */
---------------------------------------------------------------------------
-- Rules:
-- ------
-- 1) Any DB objects should be created w/o schema prefix,
-- since this file is executed in a separate schema context.
-- 2) There should be no DROP statements in this script, since
-- all objects created in the default schema will be cleaned-up outside.
---------------------------------------------------------------------------
---------------------------------------------------------------------------
-- Setup:
---------------------------------------------------------------------------
CREATE OR REPLACE FUNCTION assoc_array_eq
 (
 arr1 TEXT[],
 arr2 TEXT[]
 )
RETURNS BOOL AS $$
 SELECT COUNT(*) = array_upper(1,ドル 1) AND array_upper(1,ドル 1) = array_upper(2,ドル 1)
 FROM (SELECT unnest(1ドル) id) t1, (SELECT unnest(2ドル) id) t2
 WHERE t1.id = t2.id;
$$ LANGUAGE sql IMMUTABLE;
CREATE FUNCTION
CREATE OR REPLACE FUNCTION install_test() RETURNS VOID AS $$
declare
 result1 TEXT;
 result2 TEXT;
 result3 TEXT;
 result_maxiter TEXT;
 res madlib.assoc_rules_results;
 output_schema TEXT;
 output_table TEXT;
 total_rules INT;
 total_time INTERVAL;
begin
 DROP TABLE IF EXISTS test_data1;
 CREATE TABLE test_data1 (
 trans_id INT
 , product INT
 );
 DROP TABLE IF EXISTS test_data2;
 CREATE TABLE test_data2 (
 trans_id INT
 , product VARCHAR
 );
 INSERT INTO test_data1 VALUES (1,1);
 INSERT INTO test_data1 VALUES (1,2);
 INSERT INTO test_data1 VALUES (3,3);
 INSERT INTO test_data1 VALUES (8,4);
 INSERT INTO test_data1 VALUES (10,1);
 INSERT INTO test_data1 VALUES (10,2);
 INSERT INTO test_data1 VALUES (10,3);
 INSERT INTO test_data1 VALUES (19,2);
 INSERT INTO test_data2 VALUES (1, 'beer');
 INSERT INTO test_data2 VALUES (1, 'diapers');
 INSERT INTO test_data2 VALUES (1, 'chips');
 INSERT INTO test_data2 VALUES (2, 'beer');
 INSERT INTO test_data2 VALUES (2, 'diapers');
 INSERT INTO test_data2 VALUES (3, 'beer');
 INSERT INTO test_data2 VALUES (3, 'diapers');
 INSERT INTO test_data2 VALUES (4, 'beer');
 INSERT INTO test_data2 VALUES (4, 'chips');
 INSERT INTO test_data2 VALUES (5, 'beer');
 INSERT INTO test_data2 VALUES (6, 'beer');
 INSERT INTO test_data2 VALUES (6, 'diapers');
 INSERT INTO test_data2 VALUES (6, 'chips');
 INSERT INTO test_data2 VALUES (7, 'beer');
 INSERT INTO test_data2 VALUES (7, 'diapers');
 DROP TABLE IF EXISTS test1_exp_result;
 CREATE TABLE test1_exp_result (
 ruleid integer,
 pre text[],
 post text[],
 support double precision,
 confidence double precision,
 lift double precision,
 conviction double precision
 ) ;
 DROP TABLE IF EXISTS test2_exp_result;
 CREATE TABLE test2_exp_result (
 ruleid integer,
 pre text[],
 post text[],
 support double precision,
 confidence double precision,
 lift double precision,
 conviction double precision
 ) ;
 INSERT INTO test1_exp_result VALUES (7, '{3}', '{1}', 0.20000000000000001, 0.5, 1.2499999999999998, 1.2);
 INSERT INTO test1_exp_result VALUES (4, '{2}', '{1}', 0.40000000000000002, 0.66666666666666674, 1.6666666666666667, 1.8000000000000003);
 INSERT INTO test1_exp_result VALUES (1, '{1}', '{2,3}', 0.20000000000000001, 0.5, 2.4999999999999996, 1.6000000000000001);
 INSERT INTO test1_exp_result VALUES (9, '{2,3}', '{1}', 0.20000000000000001, 1, 2.4999999999999996, 0);
 INSERT INTO test1_exp_result VALUES (6, '{1,2}', '{3}', 0.20000000000000001, 0.5, 1.2499999999999998, 1.2);
 INSERT INTO test1_exp_result VALUES (8, '{3}', '{2}', 0.20000000000000001, 0.5, 0.83333333333333337, 0.80000000000000004);
 INSERT INTO test1_exp_result VALUES (5, '{1}', '{2}', 0.40000000000000002, 1, 1.6666666666666667, 0);
 INSERT INTO test1_exp_result VALUES (2, '{3}', '{2,1}', 0.20000000000000001, 0.5, 1.2499999999999998, 1.2);
 INSERT INTO test1_exp_result VALUES (10, '{3,1}', '{2}', 0.20000000000000001, 1, 1.6666666666666667, 0);
 INSERT INTO test1_exp_result VALUES (3, '{1}', '{3}', 0.20000000000000001, 0.5, 1.2499999999999998, 1.2);
 INSERT INTO test2_exp_result VALUES (7, '{chips,diapers}', '{beer}', 0.2857142857142857, 1, 1, 0);
 INSERT INTO test2_exp_result VALUES (2, '{chips}', '{diapers}', 0.2857142857142857, 0.66666666666666663, 0.93333333333333324, 0.85714285714285698);
 INSERT INTO test2_exp_result VALUES (1, '{chips}', '{diapers,beer}', 0.2857142857142857, 0.66666666666666663, 0.93333333333333324, 0.85714285714285698);
 INSERT INTO test2_exp_result VALUES (6, '{diapers}', '{beer}', 0.7142857142857143, 1, 1, 0);
 INSERT INTO test2_exp_result VALUES (4, '{beer}', '{diapers}', 0.7142857142857143, 0.7142857142857143, 1, 1);
 INSERT INTO test2_exp_result VALUES (3, '{chips,beer}', '{diapers}', 0.2857142857142857, 0.66666666666666663, 0.93333333333333324, 0.85714285714285698);
 INSERT INTO test2_exp_result VALUES (5, '{chips}', '{beer}', 0.42857142857142855, 1, 1, 0);
 res = madlib.assoc_rules (.1, .5, 'trans_id', 'product', 'test_data1','madlib_installcheck_assoc_rules', false);
 RETURN;
end $$ language plpgsql;
CREATE FUNCTION
---------------------------------------------------------------------------
-- Test
---------------------------------------------------------------------------
SELECT install_test();
psql:/tmp/madlib.7qnxdkya/assoc_rules/assoc_rules.ic.sql_in.tmp:154: NOTICE: table "test_data1" does not exist, skipping
psql:/tmp/madlib.7qnxdkya/assoc_rules/assoc_rules.ic.sql_in.tmp:154: NOTICE: Table doesn't have 'DISTRIBUTED BY' clause -- Using column named 'trans_id' as the Apache Cloudberry data distribution key for this table.
HINT: The 'DISTRIBUTED BY' clause determines the distribution of data. Make sure column(s) chosen are the optimal data distribution key to minimize skew.
psql:/tmp/madlib.7qnxdkya/assoc_rules/assoc_rules.ic.sql_in.tmp:154: NOTICE: table "test_data2" does not exist, skipping
psql:/tmp/madlib.7qnxdkya/assoc_rules/assoc_rules.ic.sql_in.tmp:154: NOTICE: Table doesn't have 'DISTRIBUTED BY' clause -- Using column named 'trans_id' as the Apache Cloudberry data distribution key for this table.
HINT: The 'DISTRIBUTED BY' clause determines the distribution of data. Make sure column(s) chosen are the optimal data distribution key to minimize skew.
psql:/tmp/madlib.7qnxdkya/assoc_rules/assoc_rules.ic.sql_in.tmp:154: NOTICE: table "test1_exp_result" does not exist, skipping
psql:/tmp/madlib.7qnxdkya/assoc_rules/assoc_rules.ic.sql_in.tmp:154: NOTICE: Table doesn't have 'DISTRIBUTED BY' clause -- Using column named 'ruleid' as the Apache Cloudberry data distribution key for this table.
HINT: The 'DISTRIBUTED BY' clause determines the distribution of data. Make sure column(s) chosen are the optimal data distribution key to minimize skew.
psql:/tmp/madlib.7qnxdkya/assoc_rules/assoc_rules.ic.sql_in.tmp:154: NOTICE: table "test2_exp_result" does not exist, skipping
psql:/tmp/madlib.7qnxdkya/assoc_rules/assoc_rules.ic.sql_in.tmp:154: NOTICE: Table doesn't have 'DISTRIBUTED BY' clause -- Using column named 'ruleid' as the Apache Cloudberry data distribution key for this table.
HINT: The 'DISTRIBUTED BY' clause determines the distribution of data. Make sure column(s) chosen are the optimal data distribution key to minimize skew.
psql:/tmp/madlib.7qnxdkya/assoc_rules/assoc_rules.ic.sql_in.tmp:154: WARNING: terminating connection because of crash of another server process (seg0 slice3 172.17.0.6:7002 pid=45213)
DETAIL: The postmaster has commanded this server process to roll back the current transaction and exit, because another server process exited abnormally and possibly corrupted shared memory.
HINT: In a moment you should be able to reconnect to the database and repeat your command.
psql:/tmp/madlib.7qnxdkya/assoc_rules/assoc_rules.ic.sql_in.tmp:154: WARNING: terminating connection because of crash of another server process (seg0 slice1 172.17.0.6:7002 pid=45202)
DETAIL: The postmaster has commanded this server process to roll back the current transaction and exit, because another server process exited abnormally and possibly corrupted shared memory.
HINT: In a moment you should be able to reconnect to the database and repeat your command.
psql:/tmp/madlib.7qnxdkya/assoc_rules/assoc_rules.ic.sql_in.tmp:154: WARNING: terminating connection because of crash of another server process (seg0 172.17.0.6:7002 pid=45137)
DETAIL: The postmaster has commanded this server process to roll back the current transaction and exit, because another server process exited abnormally and possibly corrupted shared memory.
HINT: In a moment you should be able to reconnect to the database and repeat your command.
psql:/tmp/madlib.7qnxdkya/assoc_rules/assoc_rules.ic.sql_in.tmp:154: WARNING: writer gang of current global transaction is lost
psql:/tmp/madlib.7qnxdkya/assoc_rules/assoc_rules.ic.sql_in.tmp:154: WARNING: Any temporary tables for this session have been dropped because the gang was disconnected (session id = 596)
psql:/tmp/madlib.7qnxdkya/assoc_rules/assoc_rules.ic.sql_in.tmp:154: ERROR: DTX RollbackAndReleaseCurrentSubTransaction dispatch failed
CONTEXT: PL/Python function "assoc_rules"
PL/pgSQL function install_test() line 93 at assignment