feat: Added support for read_json for duckdb and clickhouse

grammars/CotEditor/PRQL.yaml

@@ -43,6 +43,7 @@ commands:
   - beginString: stddev
   - beginString: sum
   - beginString: read_csv
+  - beginString: read_json
   - beginString: read_parquet
   - beginString: all
   - beginString: map

grammars/GtkSourceView/prql.lang

@@ -112,6 +112,7 @@
 
     <context id="file-reading-functions" style-ref="function">
       <keyword>read_csv</keyword>
+      <keyword>read_json</keyword>
       <keyword>read_parquet</keyword>
     </context>
 

prqlc/bindings/prqlc-python/src/lib.rs

@@ -232,15 +232,15 @@ mod test {
     fn debug_prql_lineage() {
         assert_snapshot!(
             debug::prql_lineage(r#"from a | select { beta, gamma }"#).unwrap(),
-            @r#"{"frames":[["1:9-31",{"columns":[{"Single":{"name":["a","beta"],"target_id":117,"target_name":null}},{"Single":{"name":["a","gamma"],"target_id":118,"target_name":null}}],"inputs":[{"id":115,"name":"a","table":["default_db","a"]}]}]],"nodes":[{"id":115,"kind":"Ident","span":"1:0-6","ident":{"Ident":["default_db","a"]},"parent":120},{"id":117,"kind":"Ident","span":"1:18-22","ident":{"Ident":["this","a","beta"]},"targets":[115],"parent":119},{"id":118,"kind":"Ident","span":"1:24-29","ident":{"Ident":["this","a","gamma"]},"targets":[115],"parent":119},{"id":119,"kind":"Tuple","span":"1:16-31","children":[117,118],"parent":120},{"id":120,"kind":"TransformCall: Select","span":"1:9-31","children":[115,119]}],"ast":{"name":"Project","stmts":[{"VarDef":{"kind":"Main","name":"main","value":{"Pipeline":{"exprs":[{"FuncCall":{"name":{"Ident":["from"],"span":"1:0-4"},"args":[{"Ident":["a"],"span":"1:5-6"}]},"span":"1:0-6"},{"FuncCall":{"name":{"Ident":["select"],"span":"1:9-15"},"args":[{"Tuple":[{"Ident":["beta"],"span":"1:18-22"},{"Ident":["gamma"],"span":"1:24-29"}],"span":"1:16-31"}]},"span":"1:9-31"}]},"span":"1:0-31"}},"span":"1:0-31"}]}}"#
+            @r#"{"frames":[["1:9-31",{"columns":[{"Single":{"name":["a","beta"],"target_id":118,"target_name":null}},{"Single":{"name":["a","gamma"],"target_id":119,"target_name":null}}],"inputs":[{"id":116,"name":"a","table":["default_db","a"]}]}]],"nodes":[{"id":116,"kind":"Ident","span":"1:0-6","ident":{"Ident":["default_db","a"]},"parent":121},{"id":118,"kind":"Ident","span":"1:18-22","ident":{"Ident":["this","a","beta"]},"targets":[116],"parent":120},{"id":119,"kind":"Ident","span":"1:24-29","ident":{"Ident":["this","a","gamma"]},"targets":[116],"parent":120},{"id":120,"kind":"Tuple","span":"1:16-31","children":[118,119],"parent":121},{"id":121,"kind":"TransformCall: Select","span":"1:9-31","children":[116,120]}],"ast":{"name":"Project","stmts":[{"VarDef":{"kind":"Main","name":"main","value":{"Pipeline":{"exprs":[{"FuncCall":{"name":{"Ident":["from"],"span":"1:0-4"},"args":[{"Ident":["a"],"span":"1:5-6"}]},"span":"1:0-6"},{"FuncCall":{"name":{"Ident":["select"],"span":"1:9-15"},"args":[{"Tuple":[{"Ident":["beta"],"span":"1:18-22"},{"Ident":["gamma"],"span":"1:24-29"}],"span":"1:16-31"}]},"span":"1:9-31"}]},"span":"1:0-31"}},"span":"1:0-31"}]}}"#
         );
     }
 
     #[test]
     fn debug_pl_to_lineage() {
         assert_snapshot!(
             prql_to_pl(r#"from a | select { beta, gamma }"#).and_then(|x| debug::pl_to_lineage(&x)).unwrap(),
-            @r#"{"frames":[["1:9-31",{"columns":[{"Single":{"name":["a","beta"],"target_id":117,"target_name":null}},{"Single":{"name":["a","gamma"],"target_id":118,"target_name":null}}],"inputs":[{"id":115,"name":"a","table":["default_db","a"]}]}]],"nodes":[{"id":115,"kind":"Ident","span":"1:0-6","ident":{"Ident":["default_db","a"]},"parent":120},{"id":117,"kind":"Ident","span":"1:18-22","ident":{"Ident":["this","a","beta"]},"targets":[115],"parent":119},{"id":118,"kind":"Ident","span":"1:24-29","ident":{"Ident":["this","a","gamma"]},"targets":[115],"parent":119},{"id":119,"kind":"Tuple","span":"1:16-31","children":[117,118],"parent":120},{"id":120,"kind":"TransformCall: Select","span":"1:9-31","children":[115,119]}],"ast":{"name":"Project","stmts":[{"VarDef":{"kind":"Main","name":"main","value":{"Pipeline":{"exprs":[{"FuncCall":{"name":{"Ident":["from"],"span":"1:0-4"},"args":[{"Ident":["a"],"span":"1:5-6"}]},"span":"1:0-6"},{"FuncCall":{"name":{"Ident":["select"],"span":"1:9-15"},"args":[{"Tuple":[{"Ident":["beta"],"span":"1:18-22"},{"Ident":["gamma"],"span":"1:24-29"}],"span":"1:16-31"}]},"span":"1:9-31"}]},"span":"1:0-31"}},"span":"1:0-31"}]}}"#
+            @r#"{"frames":[["1:9-31",{"columns":[{"Single":{"name":["a","beta"],"target_id":118,"target_name":null}},{"Single":{"name":["a","gamma"],"target_id":119,"target_name":null}}],"inputs":[{"id":116,"name":"a","table":["default_db","a"]}]}]],"nodes":[{"id":116,"kind":"Ident","span":"1:0-6","ident":{"Ident":["default_db","a"]},"parent":121},{"id":118,"kind":"Ident","span":"1:18-22","ident":{"Ident":["this","a","beta"]},"targets":[116],"parent":120},{"id":119,"kind":"Ident","span":"1:24-29","ident":{"Ident":["this","a","gamma"]},"targets":[116],"parent":120},{"id":120,"kind":"Tuple","span":"1:16-31","children":[118,119],"parent":121},{"id":121,"kind":"TransformCall: Select","span":"1:9-31","children":[116,120]}],"ast":{"name":"Project","stmts":[{"VarDef":{"kind":"Main","name":"main","value":{"Pipeline":{"exprs":[{"FuncCall":{"name":{"Ident":["from"],"span":"1:0-4"},"args":[{"Ident":["a"],"span":"1:5-6"}]},"span":"1:0-6"},{"FuncCall":{"name":{"Ident":["select"],"span":"1:9-15"},"args":[{"Tuple":[{"Ident":["beta"],"span":"1:18-22"},{"Ident":["gamma"],"span":"1:24-29"}],"span":"1:16-31"}]},"span":"1:9-31"}]},"span":"1:0-31"}},"span":"1:0-31"}]}}"#
         );
     }
 }

prqlc/prqlc/src/cli/test.rs

@@ -434,61 +434,61 @@ fn debug() {
           name:
           - tracks
           - artist
-          target_id: 117
+          target_id: 118
           target_name: null
         - !Single
           name:
           - tracks
           - album
-          target_id: 118
+          target_id: 119
           target_name: null
         inputs:
-        - id: 115
+        - id: 116
           name: tracks
           table:
           - default_db
           - tracks
     nodes:
-    - id: 115
+    - id: 116
       kind: Ident
       span: 1:0-11
       ident: !Ident
       - default_db
       - tracks
-      parent: 120
-    - id: 117
+      parent: 121
+    - id: 118
       kind: Ident
       span: 1:22-28
       ident: !Ident
       - this
       - tracks
       - artist
       targets:
-      - 115
-      parent: 119
-    - id: 118
+      - 116
+      parent: 120
+    - id: 119
       kind: Ident
       span: 1:30-35
       ident: !Ident
       - this
       - tracks
       - album
       targets:
-      - 115
-      parent: 119
-    - id: 119
+      - 116
+      parent: 120
+    - id: 120
       kind: Tuple
       span: 1:21-36
       children:
-      - 117
       - 118
-      parent: 120
-    - id: 120
+      - 119
+      parent: 121
+    - id: 121
       kind: 'TransformCall: Select'
       span: 1:14-36
       children:
-      - 115
-      - 119
+      - 116
+      - 120
     ast:
       name: Project
       stmts:

prqlc/prqlc/src/semantic/resolver/snapshots/prqlc__semantic__resolver__test__append_union_different_tables.snap

@@ -1,28 +1,27 @@
 ---
 source: prqlc/prqlc/src/semantic/resolver/mod.rs
-assertion_line: 234
 expression: final_lineage
 ---
 columns:
   - Single:
       name:
         - employees
         - name
-      target_id: 131
+      target_id: 132
       target_name: ~
   - Single:
       name:
         - employees
         - salary
-      target_id: 132
+      target_id: 133
       target_name: ~
 inputs:
-  - id: 129
+  - id: 130
     name: employees
     table:
       - default_db
       - employees
-  - id: 118
+  - id: 119
     name: managers
     table:
       - default_db

prqlc/prqlc/src/semantic/resolver/snapshots/prqlc__semantic__resolver__test__frames_and_names-2.snap

@@ -4,18 +4,18 @@ expression: "resolve_lineage(r#\"\n            from table_1\n            join cu
 ---
 columns:
   - All:
-      input_id: 116
+      input_id: 117
       except: []
   - All:
-      input_id: 113
+      input_id: 114
       except: []
 inputs:
-  - id: 116
+  - id: 117
     name: table_1
     table:
       - default_db
       - table_1
-  - id: 113
+  - id: 114
     name: customers
     table:
       - default_db

prqlc/prqlc/src/semantic/resolver/snapshots/prqlc__semantic__resolver__test__frames_and_names-3.snap

@@ -7,26 +7,26 @@ columns:
       name:
         - e
         - emp_no
-      target_id: 126
+      target_id: 127
       target_name: ~
   - Single:
       name:
         - e
         - gender
-      target_id: 127
+      target_id: 128
       target_name: ~
   - Single:
       name:
         - emp_salary
-      target_id: 145
+      target_id: 146
       target_name: ~
 inputs:
-  - id: 119
+  - id: 120
     name: e
     table:
       - default_db
       - employees
-  - id: 116
+  - id: 117
     name: salaries
     table:
       - default_db

prqlc/prqlc/src/semantic/resolver/snapshots/prqlc__semantic__resolver__test__frames_and_names.snap

@@ -7,26 +7,26 @@ columns:
       name:
         - orders
         - customer_no
-      target_id: 120
+      target_id: 121
       target_name: ~
   - Single:
       name:
         - orders
         - gross
-      target_id: 121
+      target_id: 122
       target_name: ~
   - Single:
       name:
         - orders
         - tax
-      target_id: 122
+      target_id: 123
       target_name: ~
   - Single:
       name: ~
-      target_id: 123
+      target_id: 124
       target_name: ~
 inputs:
-  - id: 118
+  - id: 119
     name: orders
     table:
       - default_db

prqlc/prqlc/src/semantic/resolver/snapshots/prqlc__semantic__resolver__transforms__tests__aggregate_positional_arg-2.snap

@@ -21,10 +21,10 @@ TransformCall:
     lineage:
       columns:
         - All:
-            input_id: 115
+            input_id: 116
             except: []
       inputs:
-        - id: 115
+        - id: 116
           name: c_invoice
           table:
             - default_db
@@ -94,14 +94,14 @@ lineage:
         name:
           - c_invoice
           - issued_at
-        target_id: 117
+        target_id: 118
         target_name: ~
     - Single:
         name: ~
-        target_id: 133
+        target_id: 134
         target_name: ~
   inputs:
-    - id: 115
+    - id: 116
       name: c_invoice
       table:
         - default_db

prqlc/prqlc/src/semantic/std.prql

@@ -237,6 +237,7 @@ let read_parquet = func
   union_by_name <bool>:false
   -> <relation> internal std.read_parquet
 let read_csv = source<text> -> <relation> internal std.read_csv
+let read_json = source<text> -> <relation> internal std.read_json
 
 
 ## PRQL compiler functions

prqlc/prqlc/src/sql/std.sql.prql

@@ -123,6 +123,7 @@ module text {
 # Source-reading functions, primarily for DuckDB
 let read_parquet = binary_as_string file_row_number hive_partitioning union_by_name source -> s"read_parquet({source:0})"
 let read_csv = source -> s"read_csv({source:0})"
+let read_json = source -> s"read_json({source:0})"
 
 @{binding_strength=11}
 let mul = l r -> null
@@ -218,7 +219,7 @@ module clickhouse {
   let regex_search = text pattern -> s"match({text:0}, {pattern:0})"
 
   let read_csv = source -> s"file({source:0}, 'CSV')"
-
+  let read_json = source -> s"file({source:0}, 'Json')"
   let read_parquet = source -> s"file({source:0}, 'Parquet')"
 }
 
@@ -244,7 +245,7 @@ module duckdb {
   let regex_search = text pattern -> s"REGEXP_MATCHES({text:0}, {pattern:0})"
 
   let read_csv = source -> s"read_csv_auto({source:0})"
-
+  let read_json = source -> s"read_json_auto({source:0})"
   let read_parquet = binary_as_string file_row_number hive_partitioning union_by_name source -> s"read_parquet({source:0}, binary_as_string={binary_as_string:0}, file_row_number={file_row_number:0}, hive_partitioning={hive_partitioning:0}, union_by_name={union_by_name:0})"
 }
 

prqlc/prqlc/tests/integration/data/chinook/media_types.json

@@ -0,0 +1,7 @@
+[
+  { "media_type_id": 1, "name": "MPEG audio file" },
+  { "media_type_id": 2, "name": "Protected AAC audio file" },
+  { "media_type_id": 3, "name": "Protected MPEG-4 video file" },
+  { "media_type_id": 4, "name": "Purchased AAC audio file" },
+  { "media_type_id": 5, "name": "AAC audio file" }
+]

prqlc/prqlc/tests/integration/queries/read_csv.prql

@@ -2,4 +2,5 @@
 # postgres:skip
 # mysql:skip
 from (read_csv "data_file_root/media_types.csv")
+append (read_json "data_file_root/media_types.json")
 sort media_type_id

prqlc/prqlc/tests/integration/snapshots/integration__queries__compile__read_csv.snap

@@ -1,17 +1,29 @@
 ---
 source: prqlc/prqlc/tests/integration/queries.rs
-expression: "# sqlite:skip\n# postgres:skip\n# mysql:skip\nfrom (read_csv \"data_file_root/media_types.csv\")\nsort media_type_id\n"
+expression: "# sqlite:skip\n# postgres:skip\n# mysql:skip\nfrom (read_csv \"data_file_root/media_types.csv\")\nappend (read_json \"data_file_root/media_types.json\")\nsort media_type_id\n"
 input_file: prqlc/prqlc/tests/integration/queries/read_csv.prql
 ---
 WITH table_0 AS (
   SELECT
     *
   FROM
     read_csv('data_file_root/media_types.csv')
+),
+table_2 AS (
+  SELECT
+    *
+  FROM
+    table_0
+  UNION
+  ALL
+  SELECT
+    *
+  FROM
+    read_json('data_file_root/media_types.json')
 )
 SELECT
   *
 FROM
-  table_0
+  table_2
 ORDER BY
   media_type_id