diff --git a/data/README.md b/data/README.md index 34d60ec..aa02ce9 100644 --- a/data/README.md +++ b/data/README.md @@ -32,6 +32,9 @@ | alltypes_tiny_pages.parquet | small page sizes with dictionary encoding with page index from [impala](https://github.com/apache/impala/tree/master/testdata/data/alltypes_tiny_pages.parquet). | | alltypes_tiny_pages_plain.parquet | small page sizes with plain encoding with page index [impala](https://github.com/apache/impala/tree/master/testdata/data/alltypes_tiny_pages.parquet). | | rle_boolean_encoding.parquet | option boolean columns with RLE encoding | +| single_column_[total_rows]kw_[row_group_size].parquet | single column parquet file with different total_rows and different row_group_size. Unit of [row_group_size] is KB | +| sc_1kw_multibit_[bit_width].parquet | parquet file with different different RLE encoded bit width. | + TODO: Document what each file is in the table above. diff --git a/data/sc_1kw_multibit_1.parquet b/data/sc_1kw_multibit_1.parquet new file mode 100644 index 0000000..02c778b Binary files /dev/null and b/data/sc_1kw_multibit_1.parquet differ diff --git a/data/sc_1kw_multibit_10.parquet b/data/sc_1kw_multibit_10.parquet new file mode 100644 index 0000000..e8399c0 Binary files /dev/null and b/data/sc_1kw_multibit_10.parquet differ diff --git a/data/sc_1kw_multibit_11.parquet b/data/sc_1kw_multibit_11.parquet new file mode 100644 index 0000000..903458a Binary files /dev/null and b/data/sc_1kw_multibit_11.parquet differ diff --git a/data/sc_1kw_multibit_12.parquet b/data/sc_1kw_multibit_12.parquet new file mode 100644 index 0000000..baac417 Binary files /dev/null and b/data/sc_1kw_multibit_12.parquet differ diff --git a/data/sc_1kw_multibit_13.parquet b/data/sc_1kw_multibit_13.parquet new file mode 100644 index 0000000..f214e34 Binary files /dev/null and b/data/sc_1kw_multibit_13.parquet differ diff --git a/data/sc_1kw_multibit_14.parquet b/data/sc_1kw_multibit_14.parquet new file mode 100644 index 0000000..ee6c505 Binary files /dev/null and b/data/sc_1kw_multibit_14.parquet differ diff --git a/data/sc_1kw_multibit_15.parquet b/data/sc_1kw_multibit_15.parquet new file mode 100644 index 0000000..3039085 Binary files /dev/null and b/data/sc_1kw_multibit_15.parquet differ diff --git a/data/sc_1kw_multibit_16.parquet b/data/sc_1kw_multibit_16.parquet new file mode 100644 index 0000000..7baf1f8 Binary files /dev/null and b/data/sc_1kw_multibit_16.parquet differ diff --git a/data/sc_1kw_multibit_17_18.parquet b/data/sc_1kw_multibit_17_18.parquet new file mode 100644 index 0000000..10f7651 Binary files /dev/null and b/data/sc_1kw_multibit_17_18.parquet differ diff --git a/data/sc_1kw_multibit_18.parquet b/data/sc_1kw_multibit_18.parquet new file mode 100644 index 0000000..10f7651 Binary files /dev/null and b/data/sc_1kw_multibit_18.parquet differ diff --git a/data/sc_1kw_multibit_3.parquet b/data/sc_1kw_multibit_3.parquet new file mode 100644 index 0000000..b1a62cd Binary files /dev/null and b/data/sc_1kw_multibit_3.parquet differ diff --git a/data/sc_1kw_multibit_5.parquet b/data/sc_1kw_multibit_5.parquet new file mode 100644 index 0000000..58c2f8f Binary files /dev/null and b/data/sc_1kw_multibit_5.parquet differ diff --git a/data/sc_1kw_multibit_6.parquet b/data/sc_1kw_multibit_6.parquet new file mode 100644 index 0000000..bd2daaf Binary files /dev/null and b/data/sc_1kw_multibit_6.parquet differ diff --git a/data/sc_1kw_multibit_8.parquet b/data/sc_1kw_multibit_8.parquet new file mode 100644 index 0000000..76cd5c4 Binary files /dev/null and b/data/sc_1kw_multibit_8.parquet differ diff --git a/data/sc_1kw_multibit_9.parquet b/data/sc_1kw_multibit_9.parquet new file mode 100644 index 0000000..a6064c6 Binary files /dev/null and b/data/sc_1kw_multibit_9.parquet differ diff --git a/data/single_column_1kw_1024.parquet b/data/single_column_1kw_1024.parquet new file mode 100644 index 0000000..715669f Binary files /dev/null and b/data/single_column_1kw_1024.parquet differ diff --git a/data/single_column_1kw_16.parquet b/data/single_column_1kw_16.parquet new file mode 100644 index 0000000..97b36ed Binary files /dev/null and b/data/single_column_1kw_16.parquet differ diff --git a/data/single_column_1kw_512.parquet b/data/single_column_1kw_512.parquet new file mode 100644 index 0000000..b1175f1 Binary files /dev/null and b/data/single_column_1kw_512.parquet differ diff --git a/data/single_column_1kw_64.parquet b/data/single_column_1kw_64.parquet new file mode 100644 index 0000000..1151cb9 Binary files /dev/null and b/data/single_column_1kw_64.parquet differ diff --git a/data/single_column_2kw_16.parquet b/data/single_column_2kw_16.parquet new file mode 100644 index 0000000..d13e15d Binary files /dev/null and b/data/single_column_2kw_16.parquet differ diff --git a/data/single_column_2kw_512.parquet b/data/single_column_2kw_512.parquet new file mode 100644 index 0000000..c236ca4 Binary files /dev/null and b/data/single_column_2kw_512.parquet differ diff --git a/data/single_column_2kw_64.parquet b/data/single_column_2kw_64.parquet new file mode 100644 index 0000000..a750dd5 Binary files /dev/null and b/data/single_column_2kw_64.parquet differ diff --git a/data/single_column_3kw_1024.parquet b/data/single_column_3kw_1024.parquet new file mode 100644 index 0000000..7f0121e Binary files /dev/null and b/data/single_column_3kw_1024.parquet differ diff --git a/data/single_column_3kw_16.parquet b/data/single_column_3kw_16.parquet new file mode 100644 index 0000000..e88d518 Binary files /dev/null and b/data/single_column_3kw_16.parquet differ diff --git a/data/single_column_3kw_512.parquet b/data/single_column_3kw_512.parquet new file mode 100644 index 0000000..4f08c5a Binary files /dev/null and b/data/single_column_3kw_512.parquet differ diff --git a/data/single_column_3kw_64.parquet b/data/single_column_3kw_64.parquet new file mode 100644 index 0000000..f3d00fc Binary files /dev/null and b/data/single_column_3kw_64.parquet differ