Merge branch 'main' into feat/infra

Cargo.toml

@@ -194,11 +194,14 @@ chrono-tz = "0.8.4"
 comfy-table = "7.1.1"
 common-daft-config = {path = "src/common/daft-config"}
 common-error = {path = "src/common/error", default-features = false}
+daft-core = {path = "src/daft-core"}
+daft-dsl = {path = "src/daft-dsl"}
 daft-hash = {path = "src/daft-hash"}
 daft-local-execution = {path = "src/daft-local-execution"}
 daft-local-plan = {path = "src/daft-local-plan"}
 daft-logical-plan = {path = "src/daft-logical-plan"}
 daft-scan = {path = "src/daft-scan"}
+daft-schema = {path = "src/daft-schema"}
 daft-table = {path = "src/daft-table"}
 derivative = "2.2.0"
 derive_builder = "0.20.2"

benchmarking/tpch/queries/01.sql

@@ -0,0 +1,21 @@
+SELECT
+    l_returnflag,
+    l_linestatus,
+    sum(l_quantity) AS sum_qty,
+    sum(l_extendedprice) AS sum_base_price,
+    sum(l_extendedprice * (1 - l_discount)) AS sum_disc_price,
+    sum(l_extendedprice * (1 - l_discount) * (1 + l_tax)) AS sum_charge,
+    avg(l_quantity) AS avg_qty,
+    avg(l_extendedprice) AS avg_price,
+    avg(l_discount) AS avg_disc,
+    count(*) AS count_order
+FROM
+    lineitem
+WHERE
+    l_shipdate <= CAST('1998-09-02' AS date)
+GROUP BY
+    l_returnflag,
+    l_linestatus
+ORDER BY
+    l_returnflag,
+    l_linestatus;

benchmarking/tpch/queries/02.sql

@@ -0,0 +1,43 @@
+SELECT
+    s_acctbal,
+    s_name,
+    n_name,
+    p_partkey,
+    p_mfgr,
+    s_address,
+    s_phone,
+    s_comment
+FROM
+    part,
+    supplier,
+    partsupp,
+    nation,
+    region
+WHERE
+    p_partkey = ps_partkey
+    AND s_suppkey = ps_suppkey
+    AND p_size = 15
+    AND p_type LIKE '%BRASS'
+    AND s_nationkey = n_nationkey
+    AND n_regionkey = r_regionkey
+    AND r_name = 'EUROPE'
+    AND ps_supplycost = (
+        SELECT
+            min(ps_supplycost)
+        FROM
+            partsupp,
+            supplier,
+            nation,
+            region
+        WHERE
+            p_partkey = ps_partkey
+            AND s_suppkey = ps_suppkey
+            AND s_nationkey = n_nationkey
+            AND n_regionkey = r_regionkey
+            AND r_name = 'EUROPE')
+ORDER BY
+    s_acctbal DESC,
+    n_name,
+    s_name,
+    p_partkey
+LIMIT 100;

benchmarking/tpch/queries/03.sql

@@ -0,0 +1,23 @@
+SELECT
+    l_orderkey,
+    sum(l_extendedprice * (1 - l_discount)) AS revenue,
+    o_orderdate,
+    o_shippriority
+FROM
+    customer,
+    orders,
+    lineitem
+WHERE
+    c_mktsegment = 'BUILDING'
+    AND c_custkey = o_custkey
+    AND l_orderkey = o_orderkey
+    AND o_orderdate < CAST('1995-03-15' AS date)
+    AND l_shipdate > CAST('1995-03-15' AS date)
+GROUP BY
+    l_orderkey,
+    o_orderdate,
+    o_shippriority
+ORDER BY
+    revenue DESC,
+    o_orderdate
+LIMIT 10;

benchmarking/tpch/queries/04.sql

@@ -0,0 +1,20 @@
+SELECT
+    o_orderpriority,
+    count(*) AS order_count
+FROM
+    orders
+WHERE
+    o_orderdate >= CAST('1993-07-01' AS date)
+    AND o_orderdate < CAST('1993-10-01' AS date)
+    AND EXISTS (
+        SELECT
+            *
+        FROM
+            lineitem
+        WHERE
+            l_orderkey = o_orderkey
+            AND l_commitdate < l_receiptdate)
+GROUP BY
+    o_orderpriority
+ORDER BY
+    o_orderpriority;

benchmarking/tpch/queries/05.sql

@@ -0,0 +1,24 @@
+SELECT
+    n_name,
+    sum(l_extendedprice * (1 - l_discount)) AS revenue
+FROM
+    customer,
+    orders,
+    lineitem,
+    supplier,
+    nation,
+    region
+WHERE
+    c_custkey = o_custkey
+    AND l_orderkey = o_orderkey
+    AND l_suppkey = s_suppkey
+    AND c_nationkey = s_nationkey
+    AND s_nationkey = n_nationkey
+    AND n_regionkey = r_regionkey
+    AND r_name = 'ASIA'
+    AND o_orderdate >= CAST('1994-01-01' AS date)
+    AND o_orderdate < CAST('1995-01-01' AS date)
+GROUP BY
+    n_name
+ORDER BY
+    revenue DESC;

benchmarking/tpch/queries/06.sql

@@ -0,0 +1,10 @@
+SELECT
+    sum(l_extendedprice * l_discount) AS revenue
+FROM
+    lineitem
+WHERE
+    l_shipdate >= CAST('1994-01-01' AS date)
+    AND l_shipdate < CAST('1995-01-01' AS date)
+    AND l_discount BETWEEN 0.05
+    AND 0.07
+    AND l_quantity < 24;

benchmarking/tpch/queries/07.sql

@@ -0,0 +1,38 @@
+SELECT
+    supp_nation,
+    cust_nation,
+    l_year,
+    sum(volume) AS revenue
+FROM (
+    SELECT
+        n1.n_name AS supp_nation,
+        n2.n_name AS cust_nation,
+        extract(year FROM l_shipdate) AS l_year,
+        l_extendedprice * (1 - l_discount) AS volume
+    FROM
+        supplier,
+        lineitem,
+        orders,
+        customer,
+        nation n1,
+        nation n2
+    WHERE
+        s_suppkey = l_suppkey
+        AND o_orderkey = l_orderkey
+        AND c_custkey = o_custkey
+        AND s_nationkey = n1.n_nationkey
+        AND c_nationkey = n2.n_nationkey
+        AND ((n1.n_name = 'FRANCE'
+                AND n2.n_name = 'GERMANY')
+            OR (n1.n_name = 'GERMANY'
+                AND n2.n_name = 'FRANCE'))
+        AND l_shipdate BETWEEN CAST('1995-01-01' AS date)
+        AND CAST('1996-12-31' AS date)) AS shipping
+GROUP BY
+    supp_nation,
+    cust_nation,
+    l_year
+ORDER BY
+    supp_nation,
+    cust_nation,
+    l_year;

benchmarking/tpch/queries/08.sql

@@ -0,0 +1,38 @@
+SELECT
+    o_year,
+    sum(
+        CASE WHEN nation = 'BRAZIL' THEN
+            volume
+        ELSE
+            0
+        END) / sum(volume) AS mkt_share
+FROM (
+    SELECT
+        extract(year FROM o_orderdate) AS o_year,
+        l_extendedprice * (1 - l_discount) AS volume,
+        n2.n_name AS nation
+    FROM
+        part,
+        supplier,
+        lineitem,
+        orders,
+        customer,
+        nation n1,
+        nation n2,
+        region
+    WHERE
+        p_partkey = l_partkey
+        AND s_suppkey = l_suppkey
+        AND l_orderkey = o_orderkey
+        AND o_custkey = c_custkey
+        AND c_nationkey = n1.n_nationkey
+        AND n1.n_regionkey = r_regionkey
+        AND r_name = 'AMERICA'
+        AND s_nationkey = n2.n_nationkey
+        AND o_orderdate BETWEEN CAST('1995-01-01' AS date)
+        AND CAST('1996-12-31' AS date)
+        AND p_type = 'ECONOMY ANODIZED STEEL') AS all_nations
+GROUP BY
+    o_year
+ORDER BY
+    o_year;

benchmarking/tpch/queries/09.sql

@@ -0,0 +1,30 @@
+SELECT
+    nation,
+    o_year,
+    sum(amount) AS sum_profit
+FROM (
+    SELECT
+        n_name AS nation,
+        extract(year FROM o_orderdate) AS o_year,
+        l_extendedprice * (1 - l_discount) - ps_supplycost * l_quantity AS amount
+    FROM
+        part,
+        supplier,
+        lineitem,
+        partsupp,
+        orders,
+        nation
+    WHERE
+        s_suppkey = l_suppkey
+        AND ps_suppkey = l_suppkey
+        AND ps_partkey = l_partkey
+        AND p_partkey = l_partkey
+        AND o_orderkey = l_orderkey
+        AND s_nationkey = n_nationkey
+        AND p_name LIKE '%green%') AS profit
+GROUP BY
+    nation,
+    o_year
+ORDER BY
+    nation,
+    o_year DESC;

benchmarking/tpch/queries/10.sql

@@ -0,0 +1,32 @@
+SELECT
+    c_custkey,
+    c_name,
+    sum(l_extendedprice * (1 - l_discount)) AS revenue,
+    c_acctbal,
+    n_name,
+    c_address,
+    c_phone,
+    c_comment
+FROM
+    customer,
+    orders,
+    lineitem,
+    nation
+WHERE
+    c_custkey = o_custkey
+    AND l_orderkey = o_orderkey
+    AND o_orderdate >= CAST('1993-10-01' AS date)
+    AND o_orderdate < CAST('1994-01-01' AS date)
+    AND l_returnflag = 'R'
+    AND c_nationkey = n_nationkey
+GROUP BY
+    c_custkey,
+    c_name,
+    c_acctbal,
+    c_phone,
+    n_name,
+    c_address,
+    c_comment
+ORDER BY
+    revenue DESC
+LIMIT 20;

benchmarking/tpch/queries/11.sql

@@ -0,0 +1,27 @@
+SELECT
+    ps_partkey,
+    sum(ps_supplycost * ps_availqty) AS value
+FROM
+    partsupp,
+    supplier,
+    nation
+WHERE
+    ps_suppkey = s_suppkey
+    AND s_nationkey = n_nationkey
+    AND n_name = 'GERMANY'
+GROUP BY
+    ps_partkey
+HAVING
+    sum(ps_supplycost * ps_availqty) > (
+        SELECT
+            sum(ps_supplycost * ps_availqty) * 0.0001000000
+        FROM
+            partsupp,
+            supplier,
+            nation
+        WHERE
+            ps_suppkey = s_suppkey
+            AND s_nationkey = n_nationkey
+            AND n_name = 'GERMANY')
+ORDER BY
+    value DESC;

benchmarking/tpch/queries/12.sql

@@ -0,0 +1,30 @@
+SELECT
+    l_shipmode,
+    sum(
+        CASE WHEN o_orderpriority = '1-URGENT'
+            OR o_orderpriority = '2-HIGH' THEN
+            1
+        ELSE
+            0
+        END) AS high_line_count,
+    sum(
+        CASE WHEN o_orderpriority <> '1-URGENT'
+            AND o_orderpriority <> '2-HIGH' THEN
+            1
+        ELSE
+            0
+        END) AS low_line_count
+FROM
+    orders,
+    lineitem
+WHERE
+    o_orderkey = l_orderkey
+    AND l_shipmode IN ('MAIL', 'SHIP')
+    AND l_commitdate < l_receiptdate
+    AND l_shipdate < l_commitdate
+    AND l_receiptdate >= CAST('1994-01-01' AS date)
+    AND l_receiptdate < CAST('1995-01-01' AS date)
+GROUP BY
+    l_shipmode
+ORDER BY
+    l_shipmode;