|
| 1 | +# Test MySQL LoadDataLocal NULL handling |
| 2 | +# Validates that NULL values are correctly transmitted via LOAD DATA LOCAL INFILE |
| 3 | +# Uses PostgreSQL as source with generate_data and manual NULL insertions |
| 4 | +source: postgres |
| 5 | +target: mysql |
| 6 | + |
| 7 | +defaults: |
| 8 | + mode: full-refresh |
| 9 | + |
| 10 | +hooks: |
| 11 | + start: |
| 12 | + # Generate test data in PostgreSQL |
| 13 | + - type: query |
| 14 | + connection: '{source.name}' |
| 15 | + operation: generate_data |
| 16 | + params: |
| 17 | + table: public.mysql_null_test |
| 18 | + rows: 50 |
| 19 | + columns: |
| 20 | + col_bigint: bigint |
| 21 | + col_bool: bool |
| 22 | + col_date: date |
| 23 | + col_datetime: datetime |
| 24 | + col_decimal: decimal |
| 25 | + col_integer: integer |
| 26 | + col_smallint: smallint |
| 27 | + col_string: string |
| 28 | + col_text: text |
| 29 | + col_float: float |
| 30 | + |
| 31 | + # Insert 3 rows with NULL values and special characters |
| 32 | + - type: query |
| 33 | + connection: '{source.name}' |
| 34 | + query: | |
| 35 | + INSERT INTO public.mysql_null_test |
| 36 | + (col_bigint, col_bool, col_date, col_datetime, col_decimal, col_integer, col_smallint, col_string, col_text, col_float) |
| 37 | + VALUES |
| 38 | + (NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL), |
| 39 | + (999999, NULL, NULL, '2024-01-15 10:30:00', NULL, 12345, NULL, NULL, 'text with value', NULL), |
| 40 | + (888888, true, '2024-06-20', '2024-06-20 15:45:30', 123.456, 54321, 100, 'string with "double quotes" and ''single quotes''', 'text with tabs and |
| 41 | + newlines and "quotes" here', 999.99); |
| 42 | +
|
| 43 | + end: |
| 44 | + # Check execution succeeded |
| 45 | + - type: check |
| 46 | + check: execution.status.error == 0 |
| 47 | + on_failure: break |
| 48 | + |
| 49 | + # Verify row count matches (50 generated + 3 manual = 53) |
| 50 | + - type: query |
| 51 | + connection: '{source.name}' |
| 52 | + query: SELECT COUNT(*) as cnt FROM public.mysql_null_test |
| 53 | + into: source_count |
| 54 | + |
| 55 | + - type: query |
| 56 | + connection: '{target.name}' |
| 57 | + query: SELECT COUNT(*) as cnt FROM mysql.mysql_null_test |
| 58 | + into: target_count |
| 59 | + |
| 60 | + - type: log |
| 61 | + message: "Source rows: {store.source_count[0].cnt}, Target rows: {store.target_count[0].cnt}" |
| 62 | + |
| 63 | + - type: check |
| 64 | + check: store.source_count[0].cnt == store.target_count[0].cnt |
| 65 | + failure_message: "Row count mismatch: source={store.source_count[0].cnt}, target={store.target_count[0].cnt}" |
| 66 | + |
| 67 | + # Count NULL values in source |
| 68 | + - type: query |
| 69 | + connection: '{source.name}' |
| 70 | + query: | |
| 71 | + SELECT |
| 72 | + SUM(CASE WHEN col_string IS NULL THEN 1 ELSE 0 END) as null_string_cnt, |
| 73 | + SUM(CASE WHEN col_integer IS NULL THEN 1 ELSE 0 END) as null_integer_cnt, |
| 74 | + SUM(CASE WHEN col_decimal IS NULL THEN 1 ELSE 0 END) as null_decimal_cnt, |
| 75 | + SUM(CASE WHEN col_bool IS NULL THEN 1 ELSE 0 END) as null_bool_cnt, |
| 76 | + SUM(CASE WHEN col_text IS NULL THEN 1 ELSE 0 END) as null_text_cnt |
| 77 | + FROM public.mysql_null_test |
| 78 | + into: source_nulls |
| 79 | + |
| 80 | + # Count NULL values in target |
| 81 | + - type: query |
| 82 | + connection: '{target.name}' |
| 83 | + query: | |
| 84 | + SELECT |
| 85 | + SUM(CASE WHEN col_string IS NULL THEN 1 ELSE 0 END) as null_string_cnt, |
| 86 | + SUM(CASE WHEN col_integer IS NULL THEN 1 ELSE 0 END) as null_integer_cnt, |
| 87 | + SUM(CASE WHEN col_decimal IS NULL THEN 1 ELSE 0 END) as null_decimal_cnt, |
| 88 | + SUM(CASE WHEN col_bool IS NULL THEN 1 ELSE 0 END) as null_bool_cnt, |
| 89 | + SUM(CASE WHEN col_text IS NULL THEN 1 ELSE 0 END) as null_text_cnt |
| 90 | + FROM mysql.mysql_null_test |
| 91 | + into: target_nulls |
| 92 | + |
| 93 | + - type: log |
| 94 | + message: | |
| 95 | + Source NULLs: string={store.source_nulls[0].null_string_cnt}, integer={store.source_nulls[0].null_integer_cnt}, decimal={store.source_nulls[0].null_decimal_cnt} |
| 96 | + Target NULLs: string={store.target_nulls[0].null_string_cnt}, integer={store.target_nulls[0].null_integer_cnt}, decimal={store.target_nulls[0].null_decimal_cnt} |
| 97 | +
|
| 98 | + # Verify NULL counts match for each column type |
| 99 | + - type: check |
| 100 | + check: int_parse(store.source_nulls[0].null_string_cnt) == int_parse(store.target_nulls[0].null_string_cnt) |
| 101 | + failure_message: "NULL string count mismatch: source={store.source_nulls[0].null_string_cnt}, target={store.target_nulls[0].null_string_cnt}" |
| 102 | + |
| 103 | + - type: check |
| 104 | + check: int_parse(store.source_nulls[0].null_integer_cnt) == int_parse(store.target_nulls[0].null_integer_cnt) |
| 105 | + failure_message: "NULL integer count mismatch: source={store.source_nulls[0].null_integer_cnt}, target={store.target_nulls[0].null_integer_cnt}" |
| 106 | + |
| 107 | + - type: check |
| 108 | + check: int_parse(store.source_nulls[0].null_decimal_cnt) == int_parse(store.target_nulls[0].null_decimal_cnt) |
| 109 | + failure_message: "NULL decimal count mismatch: source={store.source_nulls[0].null_decimal_cnt}, target={store.target_nulls[0].null_decimal_cnt}" |
| 110 | + |
| 111 | + - type: check |
| 112 | + check: int_parse(store.source_nulls[0].null_text_cnt) == int_parse(store.target_nulls[0].null_text_cnt) |
| 113 | + failure_message: "NULL text count mismatch: source={store.source_nulls[0].null_text_cnt}, target={store.target_nulls[0].null_text_cnt}" |
| 114 | + |
| 115 | + # Calculate checksums on source (PostgreSQL) |
| 116 | + - type: query |
| 117 | + connection: '{source.name}' |
| 118 | + query: | |
| 119 | + SELECT |
| 120 | + SUM(COALESCE(col_bigint, 0)) as sum_bigint, |
| 121 | + SUM(COALESCE(col_integer, 0)) as sum_integer, |
| 122 | + SUM(COALESCE(col_smallint, 0)) as sum_smallint, |
| 123 | + SUM(COALESCE(CAST(col_decimal AS NUMERIC), 0)) as sum_decimal, |
| 124 | + SUM(COALESCE(LENGTH(col_string), 0)) as sum_string_len, |
| 125 | + SUM(COALESCE(LENGTH(col_text), 0)) as sum_text_len |
| 126 | + FROM public.mysql_null_test |
| 127 | + into: source_checksum |
| 128 | + |
| 129 | + # Calculate checksums on target (MySQL) |
| 130 | + - type: query |
| 131 | + connection: '{target.name}' |
| 132 | + query: | |
| 133 | + SELECT |
| 134 | + SUM(COALESCE(col_bigint, 0)) as sum_bigint, |
| 135 | + SUM(COALESCE(col_integer, 0)) as sum_integer, |
| 136 | + SUM(COALESCE(col_smallint, 0)) as sum_smallint, |
| 137 | + SUM(COALESCE(CAST(col_decimal AS DECIMAL(30,10)), 0)) as sum_decimal, |
| 138 | + SUM(COALESCE(LENGTH(col_string), 0)) as sum_string_len, |
| 139 | + SUM(COALESCE(LENGTH(col_text), 0)) as sum_text_len |
| 140 | + FROM mysql.mysql_null_test |
| 141 | + into: target_checksum |
| 142 | + |
| 143 | + - type: log |
| 144 | + message: | |
| 145 | + Checksums: |
| 146 | + Source: bigint={store.source_checksum[0].sum_bigint}, integer={store.source_checksum[0].sum_integer}, string_len={store.source_checksum[0].sum_string_len} |
| 147 | + Target: bigint={store.target_checksum[0].sum_bigint}, integer={store.target_checksum[0].sum_integer}, string_len={store.target_checksum[0].sum_string_len} |
| 148 | +
|
| 149 | + # Verify checksums match |
| 150 | + - type: check |
| 151 | + check: int_parse(store.source_checksum[0].sum_bigint) == int_parse(store.target_checksum[0].sum_bigint) |
| 152 | + failure_message: "Bigint checksum mismatch" |
| 153 | + |
| 154 | + - type: check |
| 155 | + check: int_parse(store.source_checksum[0].sum_integer) == int_parse(store.target_checksum[0].sum_integer) |
| 156 | + failure_message: "Integer checksum mismatch" |
| 157 | + |
| 158 | + - type: check |
| 159 | + check: int_parse(store.source_checksum[0].sum_string_len) == int_parse(store.target_checksum[0].sum_string_len) |
| 160 | + failure_message: "String length checksum mismatch" |
| 161 | + |
| 162 | + - type: check |
| 163 | + check: int_parse(store.source_checksum[0].sum_text_len) == int_parse(store.target_checksum[0].sum_text_len) |
| 164 | + failure_message: "Text length checksum mismatch" |
| 165 | + |
| 166 | + # Verify special characters row (col_bigint = 888888) transferred correctly |
| 167 | + - type: query |
| 168 | + connection: '{target.name}' |
| 169 | + query: | |
| 170 | + SELECT col_string, col_text |
| 171 | + FROM mysql.mysql_null_test |
| 172 | + WHERE col_bigint = 888888 |
| 173 | + into: special_row |
| 174 | + |
| 175 | + - type: log |
| 176 | + message: | |
| 177 | + Special characters row: |
| 178 | + col_string: {store.special_row[0].col_string} |
| 179 | + col_text: {store.special_row[0].col_text} |
| 180 | +
|
| 181 | + - type: check |
| 182 | + check: contains(store.special_row[0].col_string, "\"double quotes\"") && contains(store.special_row[0].col_string, "'single quotes'") |
| 183 | + failure_message: "col_string should contain both double and single quotes" |
| 184 | + |
| 185 | + - type: check |
| 186 | + check: contains(store.special_row[0].col_text, "tabs and") |
| 187 | + failure_message: "col_text should contain 'tabs and'" |
| 188 | + |
| 189 | + - type: check |
| 190 | + check: contains(store.special_row[0].col_text, "newlines and") |
| 191 | + failure_message: "col_text should contain 'newlines and'" |
| 192 | + |
| 193 | + - type: check |
| 194 | + check: contains(store.special_row[0].col_text, "quotes") |
| 195 | + failure_message: "col_text should contain quotes" |
| 196 | + |
| 197 | + - type: log |
| 198 | + message: "SUCCESS: MySQL LoadDataLocal NULL handling test passed" |
| 199 | + |
| 200 | + # Cleanup |
| 201 | + - type: query |
| 202 | + connection: '{source.name}' |
| 203 | + query: DROP TABLE IF EXISTS public.mysql_null_test |
| 204 | + |
| 205 | + - type: query |
| 206 | + connection: '{target.name}' |
| 207 | + query: DROP TABLE IF EXISTS mysql.mysql_null_test |
| 208 | + |
| 209 | +streams: |
| 210 | + public.mysql_null_test: |
| 211 | + object: mysql.mysql_null_test |
0 commit comments