alamb commented on code in PR #119:
URL: https://github.com/apache/parquet-testing/pull/119#discussion_r3711719530
##########
data/alp_extended.zstd.parquet:
##########
Review Comment:
The layout:
```shell
andrewlamb@Andrews-MacBook-Pro-3:~/Software/parquet-testing$
~/Software/arrow-rs/target/release/parquet-layout data/alp_extended.zstd.parquet
```
<details>
```json
{
"row_groups": [
{
"columns": [
{
"path": "float_plain",
"has_offset_index": true,
"has_column_index": true,
"has_bloom_filter": false,
"offset_index": {
"offset": 211391,
"length": 12
},
"column_index": {
"offset": 210367,
"length": 28
},
"bloom_filter": null,
"compression": "ZSTD",
"encodings": [
"PLAIN",
"RLE"
]
},
{
"path": "double_plain",
"has_offset_index": true,
"has_column_index": true,
"has_bloom_filter": false,
"offset_index": {
"offset": 211403,
"length": 14
},
"column_index": {
"offset": 210395,
"length": 36
},
"bloom_filter": null,
"compression": "ZSTD",
"encodings": [
"PLAIN",
"RLE"
]
},
{
"path": "float_alp_1024",
"has_offset_index": true,
"has_column_index": true,
"has_bloom_filter": false,
"offset_index": {
"offset": 211417,
"length": 14
},
"column_index": {
"offset": 210431,
"length": 28
},
"bloom_filter": null,
"compression": "UNCOMPRESSED",
"encodings": [
"RLE",
"ALP"
]
},
{
"path": "double_alp_1024",
"has_offset_index": true,
"has_column_index": true,
"has_bloom_filter": false,
"offset_index": {
"offset": 211431,
"length": 14
},
"column_index": {
"offset": 210459,
"length": 36
},
"bloom_filter": null,
"compression": "UNCOMPRESSED",
"encodings": [
"RLE",
"ALP"
]
},
{
"path": "float_alp_4096",
"has_offset_index": true,
"has_column_index": true,
"has_bloom_filter": false,
"offset_index": {
"offset": 211445,
"length": 14
},
"column_index": {
"offset": 210495,
"length": 28
},
"bloom_filter": null,
"compression": "UNCOMPRESSED",
"encodings": [
"RLE",
"ALP"
]
},
{
"path": "double_alp_4096",
"has_offset_index": true,
"has_column_index": true,
"has_bloom_filter": false,
"offset_index": {
"offset": 211459,
"length": 14
},
"column_index": {
"offset": 210523,
"length": 36
},
"bloom_filter": null,
"compression": "UNCOMPRESSED",
"encodings": [
"RLE",
"ALP"
]
},
{
"path": "float_alp_32",
"has_offset_index": true,
"has_column_index": true,
"has_bloom_filter": false,
"offset_index": {
"offset": 211473,
"length": 14
},
"column_index": {
"offset": 210559,
"length": 28
},
"bloom_filter": null,
"compression": "UNCOMPRESSED",
"encodings": [
"RLE",
"ALP"
]
},
{
"path": "double_alp_32",
"has_offset_index": true,
"has_column_index": true,
"has_bloom_filter": false,
"offset_index": {
"offset": 211487,
"length": 14
},
"column_index": {
"offset": 210587,
"length": 36
},
"bloom_filter": null,
"compression": "UNCOMPRESSED",
"encodings": [
"RLE",
"ALP"
]
}
],
"row_count": 6144
},
{
"columns": [
{
"path": "float_plain",
"has_offset_index": true,
"has_column_index": true,
"has_bloom_filter": false,
"offset_index": {
"offset": 211501,
"length": 13
},
"column_index": {
"offset": 210623,
"length": 28
},
"bloom_filter": null,
"compression": "ZSTD",
"encodings": [
"PLAIN",
"RLE"
]
},
{
"path": "double_plain",
"has_offset_index": true,
"has_column_index": true,
"has_bloom_filter": false,
"offset_index": {
"offset": 211514,
"length": 13
},
"column_index": {
"offset": 210651,
"length": 36
},
"bloom_filter": null,
"compression": "ZSTD",
"encodings": [
"PLAIN",
"RLE"
]
},
{
"path": "float_alp_1024",
"has_offset_index": true,
"has_column_index": true,
"has_bloom_filter": false,
"offset_index": {
"offset": 211527,
"length": 13
},
"column_index": {
"offset": 210687,
"length": 28
},
"bloom_filter": null,
"compression": "UNCOMPRESSED",
"encodings": [
"RLE",
"ALP"
]
},
{
"path": "double_alp_1024",
"has_offset_index": true,
"has_column_index": true,
"has_bloom_filter": false,
"offset_index": {
"offset": 211540,
"length": 13
},
"column_index": {
"offset": 210715,
"length": 36
},
"bloom_filter": null,
"compression": "UNCOMPRESSED",
"encodings": [
"RLE",
"ALP"
]
},
{
"path": "float_alp_4096",
"has_offset_index": true,
"has_column_index": true,
"has_bloom_filter": false,
"offset_index": {
"offset": 211553,
"length": 13
},
"column_index": {
"offset": 210751,
"length": 28
},
"bloom_filter": null,
"compression": "UNCOMPRESSED",
"encodings": [
"RLE",
"ALP"
]
},
{
"path": "double_alp_4096",
"has_offset_index": true,
"has_column_index": true,
"has_bloom_filter": false,
"offset_index": {
"offset": 211566,
"length": 13
},
"column_index": {
"offset": 210779,
"length": 36
},
"bloom_filter": null,
"compression": "UNCOMPRESSED",
"encodings": [
"RLE",
"ALP"
]
},
{
"path": "float_alp_32",
"has_offset_index": true,
"has_column_index": true,
"has_bloom_filter": false,
"offset_index": {
"offset": 211579,
"length": 13
},
"column_index": {
"offset": 210815,
"length": 28
},
"bloom_filter": null,
"compression": "UNCOMPRESSED",
"encodings": [
"RLE",
"ALP"
]
},
{
"path": "double_alp_32",
"has_offset_index": true,
"has_column_index": true,
"has_bloom_filter": false,
"offset_index": {
"offset": 211592,
"length": 13
},
"column_index": {
"offset": 210843,
"length": 36
},
"bloom_filter": null,
"compression": "UNCOMPRESSED",
"encodings": [
"RLE",
"ALP"
]
}
],
"row_count": 1024
},
{
"columns": [
{
"path": "float_plain",
"has_offset_index": true,
"has_column_index": true,
"has_bloom_filter": false,
"offset_index": {
"offset": 211605,
"length": 12
},
"column_index": {
"offset": 210879,
"length": 28
},
"bloom_filter": null,
"compression": "ZSTD",
"encodings": [
"PLAIN",
"RLE"
]
},
{
"path": "double_plain",
"has_offset_index": true,
"has_column_index": true,
"has_bloom_filter": false,
"offset_index": {
"offset": 211617,
"length": 12
},
"column_index": {
"offset": 210907,
"length": 36
},
"bloom_filter": null,
"compression": "ZSTD",
"encodings": [
"PLAIN",
"RLE"
]
},
{
"path": "float_alp_1024",
"has_offset_index": true,
"has_column_index": true,
"has_bloom_filter": false,
"offset_index": {
"offset": 211629,
"length": 12
},
"column_index": {
"offset": 210943,
"length": 28
},
"bloom_filter": null,
"compression": "UNCOMPRESSED",
"encodings": [
"RLE",
"ALP"
]
},
{
"path": "double_alp_1024",
"has_offset_index": true,
"has_column_index": true,
"has_bloom_filter": false,
"offset_index": {
"offset": 211641,
"length": 12
},
"column_index": {
"offset": 210971,
"length": 36
},
"bloom_filter": null,
"compression": "UNCOMPRESSED",
"encodings": [
"RLE",
"ALP"
]
},
{
"path": "float_alp_4096",
"has_offset_index": true,
"has_column_index": true,
"has_bloom_filter": false,
"offset_index": {
"offset": 211653,
"length": 12
},
"column_index": {
"offset": 211007,
"length": 28
},
"bloom_filter": null,
"compression": "UNCOMPRESSED",
"encodings": [
"RLE",
"ALP"
]
},
{
"path": "double_alp_4096",
"has_offset_index": true,
"has_column_index": true,
"has_bloom_filter": false,
"offset_index": {
"offset": 211665,
"length": 12
},
"column_index": {
"offset": 211035,
"length": 36
},
"bloom_filter": null,
"compression": "UNCOMPRESSED",
"encodings": [
"RLE",
"ALP"
]
},
{
"path": "float_alp_32",
"has_offset_index": true,
"has_column_index": true,
"has_bloom_filter": false,
"offset_index": {
"offset": 211677,
"length": 13
},
"column_index": {
"offset": 211071,
"length": 28
},
"bloom_filter": null,
"compression": "UNCOMPRESSED",
"encodings": [
"RLE",
"ALP"
]
},
{
"path": "double_alp_32",
"has_offset_index": true,
"has_column_index": true,
"has_bloom_filter": false,
"offset_index": {
"offset": 211690,
"length": 13
},
"column_index": {
"offset": 211099,
"length": 36
},
"bloom_filter": null,
"compression": "UNCOMPRESSED",
"encodings": [
"RLE",
"ALP"
]
}
],
"row_count": 1024
},
{
"columns": [
{
"path": "float_plain",
"has_offset_index": true,
"has_column_index": true,
"has_bloom_filter": false,
"offset_index": {
"offset": 211703,
"length": 13
},
"column_index": {
"offset": 211135,
"length": 28
},
"bloom_filter": null,
"compression": "ZSTD",
"encodings": [
"PLAIN",
"RLE"
]
},
{
"path": "double_plain",
"has_offset_index": true,
"has_column_index": true,
"has_bloom_filter": false,
"offset_index": {
"offset": 211716,
"length": 13
},
"column_index": {
"offset": 211163,
"length": 36
},
"bloom_filter": null,
"compression": "ZSTD",
"encodings": [
"PLAIN",
"RLE"
]
},
{
"path": "float_alp_1024",
"has_offset_index": true,
"has_column_index": true,
"has_bloom_filter": false,
"offset_index": {
"offset": 211729,
"length": 13
},
"column_index": {
"offset": 211199,
"length": 28
},
"bloom_filter": null,
"compression": "UNCOMPRESSED",
"encodings": [
"RLE",
"ALP"
]
},
{
"path": "double_alp_1024",
"has_offset_index": true,
"has_column_index": true,
"has_bloom_filter": false,
"offset_index": {
"offset": 211742,
"length": 13
},
"column_index": {
"offset": 211227,
"length": 36
},
"bloom_filter": null,
"compression": "UNCOMPRESSED",
"encodings": [
"RLE",
"ALP"
]
},
{
"path": "float_alp_4096",
"has_offset_index": true,
"has_column_index": true,
"has_bloom_filter": false,
"offset_index": {
"offset": 211755,
"length": 13
},
"column_index": {
"offset": 211263,
"length": 28
},
"bloom_filter": null,
"compression": "UNCOMPRESSED",
"encodings": [
"RLE",
"ALP"
]
},
{
"path": "double_alp_4096",
"has_offset_index": true,
"has_column_index": true,
"has_bloom_filter": false,
"offset_index": {
"offset": 211768,
"length": 13
},
"column_index": {
"offset": 211291,
"length": 36
},
"bloom_filter": null,
"compression": "UNCOMPRESSED",
"encodings": [
"RLE",
"ALP"
]
},
{
"path": "float_alp_32",
"has_offset_index": true,
"has_column_index": true,
"has_bloom_filter": false,
"offset_index": {
"offset": 211781,
"length": 13
},
"column_index": {
"offset": 211327,
"length": 28
},
"bloom_filter": null,
"compression": "UNCOMPRESSED",
"encodings": [
"RLE",
"ALP"
]
},
{
"path": "double_alp_32",
"has_offset_index": true,
"has_column_index": true,
"has_bloom_filter": false,
"offset_index": {
"offset": 211794,
"length": 13
},
"column_index": {
"offset": 211355,
"length": 36
},
"bloom_filter": null,
"compression": "UNCOMPRESSED",
"encodings": [
"RLE",
"ALP"
]
}
],
"row_count": 808
}
],
"footer": {
"metadata_size": 3866
}
}
```
</details>
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
