fix(schema-compiler): Allow calling cube functions in yaml python blocks (cube-js#9473)

* fix(schema-compiler): Allow calling cube functions in yaml python blocks

* regenerate antlr

* exclude antlr auto generated code from coverage

* add tests

* Add docs and YAML examples

* some fixes in tests

---------

Co-authored-by: Igor Lukanin <[email protected]>

Author: 2 people

docs/pages/guides/recipes/analytics/event-analytics.mdx

@@ -75,6 +75,8 @@ First, we need to generate a range with all dates of interest, from the earliest
 to the latest. Second, we need to join the dates with the statuses and leave
 only the most recent statuses to date.
 
+<CodeTabs>
+
 ```javascript
 cube(`status_snapshots`, {
   extends: statuses,
@@ -111,6 +113,39 @@ cube(`status_snapshots`, {
 });
 ```
 
+```yaml
+cubes:
+  - name: status_snapshots
+    extends: statuses
+    sql: >
+      -- Create a range from the earlist date to the latest date
+      WITH range AS (
+        SELECT date
+        FROM GENERATE_SERIES(
+          (SELECT MIN(changed_at) FROM {statuses.sql()} AS statuses),
+          (SELECT MAX(changed_at) FROM {statuses.sql()} AS statuses),
+          INTERVAL '1 DAY'
+        ) AS date
+      )
+
+      -- Calculate snapshots for every date in the range
+      SELECT range.date, statuses.*
+      FROM range
+      LEFT JOIN {statuses.sql()} AS statuses
+        ON range.date >= statuses.changed_at
+        AND statuses.changed_at = (
+          SELECT MAX(changed_at)
+          FROM {statuses.sql()} AS sub_statuses
+          WHERE sub_statuses.order_id = statuses.order_id
+        )
+    dimensions:
+      date:
+        sql: date
+        type: time
+```
+
+</CodeTabs>
+
 <InfoBox>
 
 To generate a range of dates, here we use the

docs/pages/guides/recipes/data-modeling/snapshots.mdx

@@ -128,6 +128,8 @@ cube(`online_orders`, {
 
 Given the above cubes, a data blending cube can be introduced as follows:
 
+<CodeTabs>
+
 ```javascript
 cube(`all_sales`, {
   sql: `
@@ -136,14 +138,14 @@ cube(`all_sales`, {
       user_id AS customer_id,
       created_at,
       'online' AS row_type
-    FROM (${online_orders.sql()}) AS online
+    FROM ${online_orders.sql()} AS online
     UNION ALL
     SELECT
       amount,
       customer_id,
       created_at,
       'retail' AS row_type
-    FROM (${retail_orders.sql()}) AS retail
+    FROM ${retail_orders.sql()} AS retail
  `,
 
   measures: {
@@ -193,16 +195,63 @@ cube(`all_sales`, {
 });
 ```
 
-<ReferenceBox>
+```yaml
+cubes:
+  - name: all_sales
+    sql: >
+      SELECT
+        amount,
+        user_id AS customer_id,
+        created_at,
+        'online' AS row_type
+      FROM {online_orders.sql()} AS online
+      UNION ALL
+      SELECT
+        amount,
+        customer_id,
+        created_at,
+        'retail' AS row_type
+      FROM {retail_orders.sql()} AS retail
+
+    measures:
+      - name: customer_count
+        sql: customer_id
+        type: count_distinct
+
+      - name: revenue
+        sql: amount
+        type: sum
+
+      - name: online_revenue
+        sql: amount
+        type: sum
+        filters:
+          - sql: "{CUBE}.row_type = 'online'"
 
-Currently, [`{cube.sql()}` function][ref-cube-sql-func] is not supported in YAML data models.
-Please [track this issue](https://github.com/cube-js/cube/issues/7484).
+      - name: offline_revenue
+        sql: amount
+        type: sum
+        filters:
+          - sql: "{CUBE}.row_type = 'retail'"
 
-As a workaround, you can use JavaScript data models, put a SQL query in a
-[Jinja](/product/data-modeling/dynamic/jinja#jinja) variable, or load it from
-the [template context](/reference/python/cube#templatecontext-class).
+      - name: online_revenue_percentage
+        sql: >
+          {online_revenue} /
+          NULLIF({online_revenue} + {offline_revenue}, 0)
+        type: number
+        format: percent
 
-</ReferenceBox>
+    dimensions:
+      - name: created_at
+        sql: created_at
+        type: time
+
+      - name: revenue_type
+        sql: row_type
+        type: string
+```
+
+</CodeTabs>
 
 Another use case of the Data Blending approach would be when you want to chart
 some measures (business related) together and see how they correlate.

docs/pages/product/data-modeling/concepts/data-blending.mdx

@@ -90,6 +90,8 @@ cube(`users`, {
 
 Then you can derive the `teachers` and `students` cubes from `users`:
 
+<CodeTabs>
+
 ```javascript
 cube(`teachers`, {
   extends: users,
@@ -110,16 +112,24 @@ cube(`students`, {
 });
 ```
 
-<ReferenceBox>
-
-Currently, [`{cube.sql()}` function][ref-cube-sql-func] is not supported in YAML data models.
-Please [track this issue](https://github.com/cube-js/cube/issues/7484).
-
-As a workaround, you can use JavaScript data models, put a SQL query in a
-[Jinja](/product/data-modeling/dynamic/jinja#jinja) variable, or load it from
-the [template context](/reference/python/cube#templatecontext-class).
+```yaml
+cubes:
+  - name: teachers
+    extends: users
+    sql: >
+      SELECT *
+      FROM {users.sql()}
+      WHERE type = 'teacher'
+
+  - name: students
+    extends: users
+    sql: >
+      SELECT *
+      FROM {users.sql()}
+      WHERE type = 'student'
+```
 
-</ReferenceBox>
+</CodeTabs>
 
 Once we have those cubes, we can define correct joins from the `lessons` cube:
 

docs/pages/product/data-modeling/concepts/polymorphic-cubes.mdx

@@ -38,7 +38,7 @@ model
 Cube supports two ways to define data model files: with [YAML][wiki-yaml] or
 JavaScript syntax. YAML data model files should have the `.yml` extension,
 whereas JavaScript data model files should end with `.js`. You can mix YAML and
-JavaScript files within a single data model. 
+JavaScript files within a single data model.
 
 <CodeTabs>
 
@@ -547,6 +547,8 @@ when defining [polymorphic cubes][ref-polymorphism] or using [data blending][ref
 
 Consider the following data model:
 
+<CodeTabs>
+
 ```javascript
 cube(`organisms`, {
   sql_table: `organisms`
@@ -564,7 +566,7 @@ cube(`dogs`, {
   sql: `
     SELECT *
     FROM ${animals.sql()}
-    WHERE species = 'dogs' 
+    WHERE species = 'dogs'
   `,
 
   measures: {
@@ -575,6 +577,30 @@ cube(`dogs`, {
 })
 ```
 
+```yaml
+cubes:
+  - name: organisms
+    sql_table: organisms
+
+  - name: animals
+    sql: >
+      SELECT *
+      FROM {organisms.sql()}
+      WHERE kingdom = 'animals'
+
+  - name: dogs
+    sql: >
+      SELECT *
+      FROM {animals.sql()}
+      WHERE species = 'dogs'
+
+    measures:
+      - name: count
+        type: count
+```
+
+</CodeTabs>
+
 If you query for `dogs.count`, Cube will generate the following SQL:
 
 ```sql
@@ -590,18 +616,6 @@ FROM (
 ) AS "dogs"
 ```
 
-<ReferenceBox>
-
-Currently, `{cube.sql()}` function is only supported in JavaScript data models.
-It is not supported in YAML data models.
-Please [track this issue](https://github.com/cube-js/cube/issues/7484).
-
-As a workaround, you can use JavaScript data models, put a SQL query in a
-[Jinja](/product/data-modeling/dynamic/jinja#jinja) variable, or load it from
-the [template context](/reference/python/cube#templatecontext-class).
-
-</ReferenceBox>
-
 ### Curly braces and escaping
 
 As you can see in the examples above, within [SQL expressions][self-sql-expressions],
@@ -761,4 +775,4 @@ defining dynamic data models.
 [ref-style-guide]: /guides/style-guide
 [ref-polymorphism]: /product/data-modeling/concepts/polymorphic-cubes
 [ref-data-blending]: /product/data-modeling/concepts/data-blending
-[link-js-template-literals]: https://developer.mozilla.org/en-US/docs/Learn_web_development/Core/Scripting/Strings#embedding_javascript
+[link-js-template-literals]: https://developer.mozilla.org/en-US/docs/Learn_web_development/Core/Scripting/Strings#embedding_javascript

docs/pages/product/data-modeling/syntax.mdx

@@ -269,18 +269,34 @@ cubes:
 
 </CodeTabs>
 
-With JavaScript models, you can also reference other cubes' SQL statements for
-code reuse:
+You can also reference other cubes' SQL statements for code reuse using the
+[`{cube.sql()}`][ref-syntax-cube-sql] function:
+
+<CodeTabs>
 
 ```javascript
 cube(`companies`, {
   sql: `
-    SELECT users.company_name, users.company_id
+    SELECT
+      users.company_name,
+      users.company_id
     FROM ${users.sql()} AS users
   `,
 });
 ```
 
+```yaml
+cubes:
+  - name: companies
+    sql:
+      SELECT
+        users.company_name,
+        users.company_id
+      FROM {users.sql()} AS users
+```
+
+</CodeTabs>
+
 It is recommended to prefer the [`sql_table`](#parameters-sql-table) parameter
 over the `sql` parameter for all cubes that are supposed to use queries like
 this: `SELECT * FROM table`.
@@ -626,4 +642,5 @@ The `access_policy` parameter is used to configure [data access policies][ref-re
 [ref-ref-segments]: /reference/data-model/segments
 [ref-ref-joins]: /reference/data-model/joins
 [ref-ref-pre-aggs]: /reference/data-model/pre-aggregations
-[ref-ref-dap]: /reference/data-model/data-access-policies
+[ref-ref-dap]: /reference/data-model/data-access-policies
+[ref-syntax-cube-sql]: /product/data-modeling/syntax#cubesql-function

docs/pages/reference/data-model/cube.mdx

@@ -98,7 +98,9 @@
     "coverageDirectory": "coverage/",
     "collectCoverageFrom": [
       "dist/src/**/*.js",
-      "dist/src/**/*.ts"
+      "dist/src/**/*.ts",
+      "!dist/src/parser/GenericSql*.js",
+      "!dist/src/parser/Python3*.js"
     ],
     "coveragePathIgnorePatterns": [
       ".*\\.d\\.ts"

packages/cubejs-schema-compiler/package.json

@@ -228,7 +228,7 @@ testlist_comp: (test | star_expr) (
 		comp_for
 		| (COMMA (test | star_expr))* (COMMA)?
 	);
-trailer: '(' (arglist)? ')' | '[' subscriptlist ']' | '.' NAME;
+trailer: callArguments | '[' subscriptlist ']' | '.' NAME;
 subscriptlist: subscript (COMMA subscript)* (COMMA)?;
 subscript: test | (test)? ':' (test)? (sliceop)?;
 sliceop: ':' (test)?;
@@ -251,6 +251,8 @@ dictorsetmaker: (
 
 classdef: 'class' NAME ('(' (arglist)? ')')? ':' suite;
 
+callArguments: '(' (arglist)? ')';
+
 arglist: argument (COMMA argument)* (COMMA)?;
 
 // The reason that keywords are test nodes instead of NAME is that using NAME results in an