Skip to content

Parquet binary #12777

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Closed
wants to merge 1 commit into from
Closed

Parquet binary #12777

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
44 changes: 1 addition & 43 deletions benchmarks/queries/clickbench/queries.sql
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,43 +1 @@
SELECT COUNT(*) FROM hits;
SELECT COUNT(*) FROM hits WHERE "AdvEngineID" <> 0;
SELECT SUM("AdvEngineID"), COUNT(*), AVG("ResolutionWidth") FROM hits;
SELECT AVG("UserID") FROM hits;
SELECT COUNT(DISTINCT "UserID") FROM hits;
SELECT COUNT(DISTINCT "SearchPhrase") FROM hits;
SELECT MIN("EventDate"::INT::DATE), MAX("EventDate"::INT::DATE) FROM hits;
SELECT "AdvEngineID", COUNT(*) FROM hits WHERE "AdvEngineID" <> 0 GROUP BY "AdvEngineID" ORDER BY COUNT(*) DESC;
SELECT "RegionID", COUNT(DISTINCT "UserID") AS u FROM hits GROUP BY "RegionID" ORDER BY u DESC LIMIT 10;
SELECT "RegionID", SUM("AdvEngineID"), COUNT(*) AS c, AVG("ResolutionWidth"), COUNT(DISTINCT "UserID") FROM hits GROUP BY "RegionID" ORDER BY c DESC LIMIT 10;
SELECT "MobilePhoneModel", COUNT(DISTINCT "UserID") AS u FROM hits WHERE "MobilePhoneModel" <> '' GROUP BY "MobilePhoneModel" ORDER BY u DESC LIMIT 10;
SELECT "MobilePhone", "MobilePhoneModel", COUNT(DISTINCT "UserID") AS u FROM hits WHERE "MobilePhoneModel" <> '' GROUP BY "MobilePhone", "MobilePhoneModel" ORDER BY u DESC LIMIT 10;
SELECT "SearchPhrase", COUNT(*) AS c FROM hits WHERE "SearchPhrase" <> '' GROUP BY "SearchPhrase" ORDER BY c DESC LIMIT 10;
SELECT "SearchPhrase", COUNT(DISTINCT "UserID") AS u FROM hits WHERE "SearchPhrase" <> '' GROUP BY "SearchPhrase" ORDER BY u DESC LIMIT 10;
SELECT "SearchEngineID", "SearchPhrase", COUNT(*) AS c FROM hits WHERE "SearchPhrase" <> '' GROUP BY "SearchEngineID", "SearchPhrase" ORDER BY c DESC LIMIT 10;
SELECT "UserID", COUNT(*) FROM hits GROUP BY "UserID" ORDER BY COUNT(*) DESC LIMIT 10;
SELECT "UserID", "SearchPhrase", COUNT(*) FROM hits GROUP BY "UserID", "SearchPhrase" ORDER BY COUNT(*) DESC LIMIT 10;
SELECT "UserID", "SearchPhrase", COUNT(*) FROM hits GROUP BY "UserID", "SearchPhrase" LIMIT 10;
SELECT "UserID", extract(minute FROM to_timestamp_seconds("EventTime")) AS m, "SearchPhrase", COUNT(*) FROM hits GROUP BY "UserID", m, "SearchPhrase" ORDER BY COUNT(*) DESC LIMIT 10;
SELECT "UserID" FROM hits WHERE "UserID" = 435090932899640449;
SELECT COUNT(*) FROM hits WHERE "URL" LIKE '%google%';
SELECT "SearchPhrase", MIN("URL"), COUNT(*) AS c FROM hits WHERE "URL" LIKE '%google%' AND "SearchPhrase" <> '' GROUP BY "SearchPhrase" ORDER BY c DESC LIMIT 10;
SELECT "SearchPhrase", MIN("URL"), MIN("Title"), COUNT(*) AS c, COUNT(DISTINCT "UserID") FROM hits WHERE "Title" LIKE '%Google%' AND "URL" NOT LIKE '%.google.%' AND "SearchPhrase" <> '' GROUP BY "SearchPhrase" ORDER BY c DESC LIMIT 10;
SELECT * FROM hits WHERE "URL" LIKE '%google%' ORDER BY to_timestamp_seconds("EventTime") LIMIT 10;
SELECT "SearchPhrase" FROM hits WHERE "SearchPhrase" <> '' ORDER BY to_timestamp_seconds("EventTime") LIMIT 10;
SELECT "SearchPhrase" FROM hits WHERE "SearchPhrase" <> '' ORDER BY "SearchPhrase" LIMIT 10;
SELECT "SearchPhrase" FROM hits WHERE "SearchPhrase" <> '' ORDER BY to_timestamp_seconds("EventTime"), "SearchPhrase" LIMIT 10;
SELECT "CounterID", AVG(length("URL")) AS l, COUNT(*) AS c FROM hits WHERE "URL" <> '' GROUP BY "CounterID" HAVING COUNT(*) > 100000 ORDER BY l DESC LIMIT 25;
SELECT REGEXP_REPLACE("Referer", '^https?://(?:www\.)?([^/]+)/.*$', '\1') AS k, AVG(length("Referer")) AS l, COUNT(*) AS c, MIN("Referer") FROM hits WHERE "Referer" <> '' GROUP BY k HAVING COUNT(*) > 100000 ORDER BY l DESC LIMIT 25;
SELECT SUM("ResolutionWidth"), SUM("ResolutionWidth" + 1), SUM("ResolutionWidth" + 2), SUM("ResolutionWidth" + 3), SUM("ResolutionWidth" + 4), SUM("ResolutionWidth" + 5), SUM("ResolutionWidth" + 6), SUM("ResolutionWidth" + 7), SUM("ResolutionWidth" + 8), SUM("ResolutionWidth" + 9), SUM("ResolutionWidth" + 10), SUM("ResolutionWidth" + 11), SUM("ResolutionWidth" + 12), SUM("ResolutionWidth" + 13), SUM("ResolutionWidth" + 14), SUM("ResolutionWidth" + 15), SUM("ResolutionWidth" + 16), SUM("ResolutionWidth" + 17), SUM("ResolutionWidth" + 18), SUM("ResolutionWidth" + 19), SUM("ResolutionWidth" + 20), SUM("ResolutionWidth" + 21), SUM("ResolutionWidth" + 22), SUM("ResolutionWidth" + 23), SUM("ResolutionWidth" + 24), SUM("ResolutionWidth" + 25), SUM("ResolutionWidth" + 26), SUM("ResolutionWidth" + 27), SUM("ResolutionWidth" + 28), SUM("ResolutionWidth" + 29), SUM("ResolutionWidth" + 30), SUM("ResolutionWidth" + 31), SUM("ResolutionWidth" + 32), SUM("ResolutionWidth" + 33), SUM("ResolutionWidth" + 34), SUM("ResolutionWidth" + 35), SUM("ResolutionWidth" + 36), SUM("ResolutionWidth" + 37), SUM("ResolutionWidth" + 38), SUM("ResolutionWidth" + 39), SUM("ResolutionWidth" + 40), SUM("ResolutionWidth" + 41), SUM("ResolutionWidth" + 42), SUM("ResolutionWidth" + 43), SUM("ResolutionWidth" + 44), SUM("ResolutionWidth" + 45), SUM("ResolutionWidth" + 46), SUM("ResolutionWidth" + 47), SUM("ResolutionWidth" + 48), SUM("ResolutionWidth" + 49), SUM("ResolutionWidth" + 50), SUM("ResolutionWidth" + 51), SUM("ResolutionWidth" + 52), SUM("ResolutionWidth" + 53), SUM("ResolutionWidth" + 54), SUM("ResolutionWidth" + 55), SUM("ResolutionWidth" + 56), SUM("ResolutionWidth" + 57), SUM("ResolutionWidth" + 58), SUM("ResolutionWidth" + 59), SUM("ResolutionWidth" + 60), SUM("ResolutionWidth" + 61), SUM("ResolutionWidth" + 62), SUM("ResolutionWidth" + 63), SUM("ResolutionWidth" + 64), SUM("ResolutionWidth" + 65), SUM("ResolutionWidth" + 66), SUM("ResolutionWidth" + 67), SUM("ResolutionWidth" + 68), SUM("ResolutionWidth" + 69), SUM("ResolutionWidth" + 70), SUM("ResolutionWidth" + 71), SUM("ResolutionWidth" + 72), SUM("ResolutionWidth" + 73), SUM("ResolutionWidth" + 74), SUM("ResolutionWidth" + 75), SUM("ResolutionWidth" + 76), SUM("ResolutionWidth" + 77), SUM("ResolutionWidth" + 78), SUM("ResolutionWidth" + 79), SUM("ResolutionWidth" + 80), SUM("ResolutionWidth" + 81), SUM("ResolutionWidth" + 82), SUM("ResolutionWidth" + 83), SUM("ResolutionWidth" + 84), SUM("ResolutionWidth" + 85), SUM("ResolutionWidth" + 86), SUM("ResolutionWidth" + 87), SUM("ResolutionWidth" + 88), SUM("ResolutionWidth" + 89) FROM hits;
SELECT "SearchEngineID", "ClientIP", COUNT(*) AS c, SUM("IsRefresh"), AVG("ResolutionWidth") FROM hits WHERE "SearchPhrase" <> '' GROUP BY "SearchEngineID", "ClientIP" ORDER BY c DESC LIMIT 10;
SELECT "WatchID", "ClientIP", COUNT(*) AS c, SUM("IsRefresh"), AVG("ResolutionWidth") FROM hits WHERE "SearchPhrase" <> '' GROUP BY "WatchID", "ClientIP" ORDER BY c DESC LIMIT 10;
SELECT "WatchID", "ClientIP", COUNT(*) AS c, SUM("IsRefresh"), AVG("ResolutionWidth") FROM hits GROUP BY "WatchID", "ClientIP" ORDER BY c DESC LIMIT 10;
SELECT "URL", COUNT(*) AS c FROM hits GROUP BY "URL" ORDER BY c DESC LIMIT 10;
SELECT 1, "URL", COUNT(*) AS c FROM hits GROUP BY 1, "URL" ORDER BY c DESC LIMIT 10;
SELECT "ClientIP", "ClientIP" - 1, "ClientIP" - 2, "ClientIP" - 3, COUNT(*) AS c FROM hits GROUP BY "ClientIP", "ClientIP" - 1, "ClientIP" - 2, "ClientIP" - 3 ORDER BY c DESC LIMIT 10;
SELECT "URL", COUNT(*) AS PageViews FROM hits WHERE "CounterID" = 62 AND "EventDate"::INT::DATE >= '2013-07-01' AND "EventDate"::INT::DATE <= '2013-07-31' AND "DontCountHits" = 0 AND "IsRefresh" = 0 AND "URL" <> '' GROUP BY "URL" ORDER BY PageViews DESC LIMIT 10;
SELECT "Title", COUNT(*) AS PageViews FROM hits WHERE "CounterID" = 62 AND "EventDate"::INT::DATE >= '2013-07-01' AND "EventDate"::INT::DATE <= '2013-07-31' AND "DontCountHits" = 0 AND "IsRefresh" = 0 AND "Title" <> '' GROUP BY "Title" ORDER BY PageViews DESC LIMIT 10;
SELECT "URL", COUNT(*) AS PageViews FROM hits WHERE "CounterID" = 62 AND "EventDate"::INT::DATE >= '2013-07-01' AND "EventDate"::INT::DATE <= '2013-07-31' AND "IsRefresh" = 0 AND "IsLink" <> 0 AND "IsDownload" = 0 GROUP BY "URL" ORDER BY PageViews DESC LIMIT 10 OFFSET 1000;
SELECT "TraficSourceID", "SearchEngineID", "AdvEngineID", CASE WHEN ("SearchEngineID" = 0 AND "AdvEngineID" = 0) THEN "Referer" ELSE '' END AS Src, "URL" AS Dst, COUNT(*) AS PageViews FROM hits WHERE "CounterID" = 62 AND "EventDate"::INT::DATE >= '2013-07-01' AND "EventDate"::INT::DATE <= '2013-07-31' AND "IsRefresh" = 0 GROUP BY "TraficSourceID", "SearchEngineID", "AdvEngineID", Src, Dst ORDER BY PageViews DESC LIMIT 10 OFFSET 1000;
SELECT "URLHash", "EventDate"::INT::DATE, COUNT(*) AS PageViews FROM hits WHERE "CounterID" = 62 AND "EventDate"::INT::DATE >= '2013-07-01' AND "EventDate"::INT::DATE <= '2013-07-31' AND "IsRefresh" = 0 AND "TraficSourceID" IN (-1, 6) AND "RefererHash" = 3594120000172545465 GROUP BY "URLHash", "EventDate"::INT::DATE ORDER BY PageViews DESC LIMIT 10 OFFSET 100;
SELECT "WindowClientWidth", "WindowClientHeight", COUNT(*) AS PageViews FROM hits WHERE "CounterID" = 62 AND "EventDate"::INT::DATE >= '2013-07-01' AND "EventDate"::INT::DATE <= '2013-07-31' AND "IsRefresh" = 0 AND "DontCountHits" = 0 AND "URLHash" = 2868770270353813622 GROUP BY "WindowClientWidth", "WindowClientHeight" ORDER BY PageViews DESC LIMIT 10 OFFSET 10000;
SELECT DATE_TRUNC('minute', to_timestamp_seconds("EventTime")) AS M, COUNT(*) AS PageViews FROM hits WHERE "CounterID" = 62 AND "EventDate"::INT::DATE >= '2013-07-14' AND "EventDate"::INT::DATE <= '2013-07-15' AND "IsRefresh" = 0 AND "DontCountHits" = 0 GROUP BY DATE_TRUNC('minute', to_timestamp_seconds("EventTime")) ORDER BY DATE_TRUNC('minute', M) LIMIT 10 OFFSET 1000;
SELECT REGEXP_REPLACE("Referer", '^https?://(?:www\.)?([^/]+)/.*$', '\1') AS k, AVG(length("Referer")) AS l, COUNT(*) AS c, MIN("Referer") FROM hits WHERE "Referer" <> '' GROUP BY k HAVING COUNT(*) > 100000 ORDER BY l DESC LIMIT 25;
9 changes: 8 additions & 1 deletion datafusion/core/src/datasource/physical_plan/file_scan_config.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -231,7 +231,14 @@ impl FileScanConfig {
for idx in proj_iter {
if idx < self.file_schema.fields().len() {
let field = self.file_schema.field(idx);
table_fields.push(field.clone());

let f = if field.data_type().equals_datatype(&DataType::Binary) {
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

If this works out I think we should put this feature behind a feature flag. I think this change will have the effect of changing all binary columns to utf8. This is the right thing to do for the hits_partitioned dataset, but I am not sure it is the right thing to do in general.

I tried to write this up more coeherently in #12788

Field::new(field.name(), DataType::Utf8, field.is_nullable())
} else {
field.clone()
};

table_fields.push(f);
table_cols_stats.push(self.statistics.column_statistics[idx].clone())
} else {
let partition_idx = idx - self.file_schema.fields().len();
Expand Down
18 changes: 17 additions & 1 deletion datafusion/core/src/datasource/physical_plan/parquet/mod.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -40,6 +40,7 @@ use crate::{
};

use arrow::datatypes::SchemaRef;
use arrow_schema::DataType;
use datafusion_physical_expr::{EquivalenceProperties, LexOrdering, PhysicalExpr};

use itertools::Itertools;
Expand Down Expand Up @@ -713,6 +714,21 @@ impl ExecutionPlan for ParquetExec {
.clone()
.unwrap_or_else(|| Arc::new(DefaultSchemaAdapterFactory));


let file_schema = self.base_config.file_schema.clone();
let mut fields = vec![];
for field in file_schema.fields() {
let f = if field.data_type().equals_datatype(&DataType::Binary) {
Arc::new(arrow_schema::Field::new(field.name(), DataType::Utf8, field.is_nullable()))
} else {
field.clone()
};
fields.push(f);
}
let table_schema = Arc::new(arrow_schema::Schema::new(fields));
Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Change the table schema to utf8


// let table_schema = self.base_config().file_schema.clone();

let opener = ParquetOpener {
partition_index,
projection: Arc::from(projection),
Expand All @@ -721,7 +737,7 @@ impl ExecutionPlan for ParquetExec {
predicate: self.predicate.clone(),
pruning_predicate: self.pruning_predicate.clone(),
page_pruning_predicate: self.page_pruning_predicate.clone(),
table_schema: self.base_config.file_schema.clone(),
table_schema,
metadata_size_hint: self.metadata_size_hint,
metrics: self.metrics.clone(),
parquet_file_reader_factory,
Expand Down
1 change: 1 addition & 0 deletions datafusion/core/src/execution/session_state.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -539,6 +539,7 @@ impl SessionState {
let resolved = &self.resolve_table_ref(reference);
if let Entry::Vacant(v) = provider.tables.entry(resolved.to_string()) {
if let Ok(schema) = self.schema_for_ref(resolved.clone()) {
// println!("schema provider: {:?}", schema);
if let Some(table) = schema.table(&resolved.table).await? {
v.insert(provider_as_source(table));
}
Expand Down
2 changes: 2 additions & 0 deletions datafusion/core/src/physical_planner.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -658,6 +658,8 @@ impl DefaultPhysicalPlanner {
logical_input_schema.as_ref().clone().into();

if physical_input_schema != physical_input_schema_from_logical {
// println!("physical_input_schema: {:?}", physical_input_schema);
// println!("physical_input_schema_from_logical: {:?}", physical_input_schema_from_logical);
return internal_err!("Physical input schema should be the same as the one converted from logical input schema.");
}

Expand Down
27 changes: 26 additions & 1 deletion datafusion/expr/src/logical_plan/plan.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2556,10 +2556,24 @@ impl TableScan {
return plan_err!("table_name cannot be empty");
}
let schema = table_source.schema();
// println!("schema: {:?}", schema);
let func_dependencies = FunctionalDependencies::new_from_constraints(
table_source.constraints(),
schema.fields.len(),
);
// println!("projection: {:?}", projection);
let mut fields = vec![];
for field in schema.fields() {
let f = if field.data_type().equals_datatype(&DataType::Binary) {
Field::new(field.name(), DataType::Utf8, field.is_nullable()).into()
} else {
field.clone()
};

fields.push(f);
}
let schema = Schema::new_with_metadata(fields, schema.metadata().clone());
Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

We also need to change the one in logical plan too


let projected_schema = projection
.as_ref()
.map(|p| {
Expand All @@ -2569,7 +2583,14 @@ impl TableScan {
let df_schema = DFSchema::new_with_metadata(
p.iter()
.map(|i| {
(Some(table_name.clone()), Arc::new(schema.field(*i).clone()))
let s = schema.field(*i).clone();
// let s = if s.data_type().equals_datatype(&DataType::Binary) {
// Field::new(s.name(), DataType::Utf8, s.is_nullable())
// } else {
// s.clone()
// };
// println!("s({}): {:?}", *i, s);
(Some(table_name.clone()), Arc::new(s))
})
.collect(),
schema.metadata.clone(),
Expand All @@ -2581,7 +2602,11 @@ impl TableScan {
DFSchema::try_from_qualified_schema(table_name.clone(), &schema)?;
df_schema.with_functional_dependencies(func_dependencies)
})?;



let projected_schema = Arc::new(projected_schema);
// println!("projected_schema: {:?}", projected_schema);

Ok(Self {
table_name,
Expand Down
Loading