From 1960b2e050d015d85afaf836b25218a5e4d6492e Mon Sep 17 00:00:00 2001 From: mirnawong1 Date: Fri, 11 Oct 2024 11:57:53 +0100 Subject: [PATCH 01/11] remove styles --- contributing/adding-page-components.md | 53 +++++++- website/src/pages/styles.js | 176 ------------------------- website/vercel.json | 5 + 3 files changed, 54 insertions(+), 180 deletions(-) delete mode 100644 website/src/pages/styles.js diff --git a/contributing/adding-page-components.md b/contributing/adding-page-components.md index 68294e7d149..7a92d627995 100644 --- a/contributing/adding-page-components.md +++ b/contributing/adding-page-components.md @@ -4,7 +4,7 @@ You can use the following components to provide code snippets for each supported Identify code by labeling with the warehouse names: -```code +```sql
@@ -32,7 +32,7 @@ You can use the following components to provide code snippets in a tabbed view. Identify code and code files by labeling with the component they are describing: -```code +```sql ` tag. This allows you to share a link to a page with a pre-selected tab so that clicking on a tab creates a unique hyperlink for that tab. However, this feature doesn't provide an anchor link, which means the browser won't scroll to the tab. Additionally, you can define the search parameter name to use. If the tabs content is under a header, you can alternatively link to the header itself, instaed of the `queryString` prop. +You can use the [queryString](https://docusaurus.io/docs/next/markdown-features/tabs?current-os=ios#query-string) prop in the `` tag. This allows you to share a link to a page with a pre-selected tab so that clicking on a tab creates a unique hyperlink for that tab. However, this feature doesn't provide an anchor link, which means the browser won't scroll to the tab. Additionally, you can define the search parameter name to use. If the tabs content is under a header, you can alternatively link to the header itself, instead of the `queryString` prop. In the following example, clicking a tab adds a search parameter to the end of the URL: `?current-os=android or ?current-os=ios`. -``` +```sql Android @@ -105,3 +105,48 @@ In the following example, clicking a tab adds a search parameter to the end of t ``` + +## Markdown Links + +Refer to the Links section of the Content Style Guide to read about how you can use links in the dbt product documentation. + +## Collapsible header + + +
+

Shows and hides children elements

+
+ + +```markdown + +
+

Shows and hides children elements

+
+ +
+``` + +## File component + +```yml + + +```yaml +password: hunter2 +``` + +``` + +## LoomVideo component + +
{``}
+ + + +## YoutubeVideo component + +
{``}
+ + + diff --git a/website/src/pages/styles.js b/website/src/pages/styles.js deleted file mode 100644 index 23d13d10813..00000000000 --- a/website/src/pages/styles.js +++ /dev/null @@ -1,176 +0,0 @@ - -import React from 'react'; -import Layout from '@theme/Layout'; -import CodeBlock from '@theme/CodeBlock'; -import Changelog from '@site/src/components/changelog'; -import CloudCore from '@site/src/components/cloudcore'; -import Collapsible from '@site/src/components/collapsible'; -import FAQ from '@site/src/components/faqs'; -import File from '@site/src/components/file'; -import Lightbox from '@site/src/components/lightbox'; -import LoomVideo from '@site/src/components/loom'; -import Tabs from '@theme/Tabs'; -import TabItem from '@theme/TabItem'; -import YoutubeVideo from '@site/src/components/youtube'; - -function Styles() { - return ( - -
-
-

- The following components are baked into the Markdown compilation context, - so there is no need to import them from Markdown files. Simply add the components - inline to use them. -

-
-
-

Changelog

-
{`
-    
This functionality has changed in dbt v0.16.0

-
-`}
- This functionality has changed in dbt v0.16.0 -
-
-

CloudCore

-
{`
-    

-        
The first div contains Cloud info

-    

-    

-        
The second div contains Core info

-    

-
-`}
- -
-

The first div contains Cloud info

-
-
-

The second div contains Core info

-
- -
-
-

Collapsible

-
{`
-    

-        
Shows and hides children elements

-    

-
-`}
- -
-

Shows and hides children elements

-
- -
-
-

FAQList

-
{``}
-

(Not shown)

-
- -
-

FAQ

-
{``}
- - -
- -
-

File

-
{`
-
-\`\`\`yml
-password: hunter2
-\`\`\`
-
-
-
-`}
- - 
-                        password: hunter2
-
- -
- -
-

Lightbox

- 
{``}
- -
- -
-

Markdown Links

- Refer to the Links section of the Content Style Guide to read about how you can use links in the dbt product documentation. -
- -
-

LoomVideo

- 
{``}
- -
- -
-

Tabs

-
{`
-
-
-
-\`\`\`sql
-select id from customers
-\`\`\`
-
-
-
-
-\`\`\`sql
-select "ID" from customers
-\`\`\`
-
-
-
-`}
- - - -
-select id from customers
-
- - - - -
-select "ID" from customers
-
- - - -
-
-

YoutubeVideo

- 
{``}
- -
-
- - ); -} - -export default Styles; diff --git a/website/vercel.json b/website/vercel.json index 0674313f3f5..1291b5c192e 100644 --- a/website/vercel.json +++ b/website/vercel.json @@ -2,6 +2,11 @@ "cleanUrls": true, "trailingSlash": false, "redirects": [ + { + "source": "/src/pages/styles.js", + "destination": "https://github.com/dbt-labs/docs.getdbt.com/blob/current/contributing/adding-page-components.md", + "permanent": true + }, { "source": "/docs/dbt-cloud-apis/sl-manifest", "destination": "/reference/artifacts/sl-manifest", From d5fd666ef3d9a2ede3153ef99c5f4131feea788e Mon Sep 17 00:00:00 2001 From: Louis Date: Mon, 14 Oct 2024 12:18:51 +0800 Subject: [PATCH 02/11] Update incremental-models.md Make it clear that models do not fail on null values in the unique key. --- website/docs/docs/build/incremental-models.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/website/docs/docs/build/incremental-models.md b/website/docs/docs/build/incremental-models.md index c48030cc32d..e980423da96 100644 --- a/website/docs/docs/build/incremental-models.md +++ b/website/docs/docs/build/incremental-models.md @@ -94,7 +94,7 @@ Not specifying a `unique_key` will result in append-only behavior, which means d The optional `unique_key` parameter specifies a field (or combination of fields) that defines the grain of your model. That is, the field(s) identify a single unique row. You can define `unique_key` in a configuration block at the top of your model, and it can be a single column name or a list of column names. -The `unique_key` should be supplied in your model definition as a string representing a single column or a list of single-quoted column names that can be used together, for example, `['col1', 'col2', …])`. Columns used in this way should not contain any nulls, or the incremental model run may fail. Either ensure that each column has no nulls (for example with `coalesce(COLUMN_NAME, 'VALUE_IF_NULL')`), or define a single-column [surrogate key](https://www.getdbt.com/blog/guide-to-surrogate-key) (for example with [`dbt_utils.generate_surrogate_key`](https://github.com/dbt-labs/dbt-utils#generate_surrogate_key-source)). +The `unique_key` should be supplied in your model definition as a string representing a single column or a list of single-quoted column names that can be used together, for example, `['col1', 'col2', …])`. Columns used in this way should not contain any nulls, or the incremental model will fail to match rows and propergate duplicate rows. Either ensure that each column has no nulls (for example with `coalesce(COLUMN_NAME, 'VALUE_IF_NULL')`), or define a single-column [surrogate key](https://www.getdbt.com/blog/guide-to-surrogate-key) (for example with [`dbt_utils.generate_surrogate_key`](https://github.com/dbt-labs/dbt-utils#generate_surrogate_key-source)). :::tip In cases where you need multiple columns in combination to uniquely identify each row, we recommend you pass these columns as a list (`unique_key = ['user_id', 'session_number']`), rather than a string expression (`unique_key = 'concat(user_id, session_number)'`). From 4c65c050270ab6f6d39854c8f6d2e39a44053324 Mon Sep 17 00:00:00 2001 From: "Leona B. Campbell" <3880403+runleonarun@users.noreply.github.com> Date: Tue, 15 Oct 2024 13:40:08 -0700 Subject: [PATCH 03/11] Fixing link for data tests --- .../docs/docs/dbt-versions/core-upgrade/06-upgrading-to-v1.9.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/website/docs/docs/dbt-versions/core-upgrade/06-upgrading-to-v1.9.md b/website/docs/docs/dbt-versions/core-upgrade/06-upgrading-to-v1.9.md index 29f3650e7a6..aaa85e4ecef 100644 --- a/website/docs/docs/dbt-versions/core-upgrade/06-upgrading-to-v1.9.md +++ b/website/docs/docs/dbt-versions/core-upgrade/06-upgrading-to-v1.9.md @@ -107,6 +107,6 @@ You can read more about each of these behavior changes in the following links: We also made some quality-of-life improvements in Core 1.9, enabling you to: - Maintain data quality now that dbt returns an an error (versioned models) or warning (unversioned models) when someone [removes a contracted model by deleting, renaming, or disabling](/docs/collaborate/govern/model-contracts#how-are-breaking-changes-handled) it. -- Document [singular data tests](/docs/build/data-tests#document-singular-tests). +- Document [singular data tests](/docs/build/data-tests#singular-data-tests). - Use `ref` and `source` in [foreign key constraints](/reference/resource-properties/constraints). - Use `dbt test` with the `--resource-type` / `--exclude-resource-type` flag, making it possible to include or exclude data tests (`test`) or unit tests (`unit_test`). From 4f71cf4a3801c9f60edd14e3353c735ca2bbd9b5 Mon Sep 17 00:00:00 2001 From: culley-hippo Date: Tue, 15 Oct 2024 13:58:26 -0700 Subject: [PATCH 04/11] Update bigquery-configs.md updating in-page html anchor tag from clustering-keys to clustering-clause (clustering-keys is no more) --- website/docs/reference/resource-configs/bigquery-configs.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/website/docs/reference/resource-configs/bigquery-configs.md b/website/docs/reference/resource-configs/bigquery-configs.md index 88ae6e9d193..8567bfed886 100644 --- a/website/docs/reference/resource-configs/bigquery-configs.md +++ b/website/docs/reference/resource-configs/bigquery-configs.md @@ -434,7 +434,7 @@ The `incremental_strategy` config can be set to one of two values: ### Performance and cost The operations performed by dbt while building a BigQuery incremental model can -be made cheaper and faster by using [clustering keys](#clustering-keys) in your +be made cheaper and faster by using a [clustering clause](#clustering-clause) in your model configuration. See [this guide](https://discourse.getdbt.com/t/benchmarking-incremental-strategies-on-bigquery/981) for more information on performance tuning for BigQuery incremental models. **Note:** These performance and cost benefits are applicable to incremental models From 7b8fb37bb2a576f6f507ba9d3f653dfa6b75b3c3 Mon Sep 17 00:00:00 2001 From: Quigley Malcolm Date: Tue, 15 Oct 2024 16:31:34 -0500 Subject: [PATCH 05/11] Fix documentation about of `batch_size` supported values and default Our docs stated that we only support `day`, but we support `hour`, `day`, `month`, and `year`. Our docs also stated that `batch_size` will be defaulted to `day`. This is not true, it is a required value and will not be defaulted. --- website/docs/docs/build/incremental-microbatch.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/website/docs/docs/build/incremental-microbatch.md b/website/docs/docs/build/incremental-microbatch.md index 2cc39e9e3b9..18122af4b7b 100644 --- a/website/docs/docs/build/incremental-microbatch.md +++ b/website/docs/docs/build/incremental-microbatch.md @@ -162,7 +162,7 @@ Several configurations are relevant to microbatch models, and some are required: |----------|------|---------------|---------| | `event_time` | Column (required) | The column indicating "at what time did the row occur." Required for your microbatch model and any direct parents that should be filtered. | N/A | | `begin` | Date (required) | The "beginning of time" for the microbatch model. This is the starting point for any initial or full-refresh builds. For example, a daily-grain microbatch model run on `2024-10-01` with `begin = '2023-10-01` will process 366 batches (it's a leap year!) plus the batch for "today." | N/A | -| `batch_size` | String (required) | The granularity of your batches. The default is `day` (and currently this is the only granularity supported). | `day` | +| `batch_size` | String (required) | The granularity of your batches. Supported values are `hour`, `day`, `month`, and `year` | N/A | | `lookback` | Integer (optional) | Process X batches prior to the latest bookmark to capture late-arriving records. | `0` | From 06917ef865f002b33660488262490022dac818a8 Mon Sep 17 00:00:00 2001 From: runleonarun Date: Tue, 15 Oct 2024 15:52:42 -0700 Subject: [PATCH 06/11] addign example --- website/docs/docs/build/data-tests.md | 20 ++++++++++++++++++-- 1 file changed, 18 insertions(+), 2 deletions(-) diff --git a/website/docs/docs/build/data-tests.md b/website/docs/docs/build/data-tests.md index ae3ac9225db..90ab20cb3a3 100644 --- a/website/docs/docs/build/data-tests.md +++ b/website/docs/docs/build/data-tests.md @@ -66,9 +66,25 @@ having total_amount < 0 -The name of this test is the name of the file: `assert_total_payment_amount_is_positive`. Simple enough. +The name of this test is the name of the file: `assert_total_payment_amount_is_positive`. -Singular data tests are easy to write—so easy that you may find yourself writing the same basic structure over and over, only changing the name of a column or model. By that point, the test isn't so singular! In that case, we recommend... +For example, to add a data test to your project, add a `.yml` file to your `tests` directory, for example, `tests/schema.yml` with the following content: + + + +```yaml +version: 2 +data_tests: + - name: assert_total_payment_amount_is_positive + description: > + Refunds have a negative amount, so the total amount should always be >= 0. + Therefore return records where total amount < 0 to make the test fail. + +``` + + + +Singular data tests are easy to write—so easy that you may find yourself writing the same basic structure over and over, only changing the name of a column or model. By that point, the test isn't so singular! In that case, we recommend generic data tests. ## Generic data tests Certain data tests are generic: they can be reused over and over again. A generic data test is defined in a `test` block, which contains a parametrized query and accepts arguments. It might look like: From 3a533431bcc6b4e32387ed8514a771fc3993cfbd Mon Sep 17 00:00:00 2001 From: runleonarun Date: Tue, 15 Oct 2024 16:02:03 -0700 Subject: [PATCH 07/11] too many for examples --- website/docs/docs/build/data-tests.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/website/docs/docs/build/data-tests.md b/website/docs/docs/build/data-tests.md index 90ab20cb3a3..8ee637bc7cd 100644 --- a/website/docs/docs/build/data-tests.md +++ b/website/docs/docs/build/data-tests.md @@ -68,7 +68,7 @@ having total_amount < 0 The name of this test is the name of the file: `assert_total_payment_amount_is_positive`. -For example, to add a data test to your project, add a `.yml` file to your `tests` directory, for example, `tests/schema.yml` with the following content: +To add a data test to your project, add a `.yml` file to your `tests` directory, for example, `tests/schema.yml` with the following content: From d6e6d74dea4d45414f338b86c56f9b384ad4642d Mon Sep 17 00:00:00 2001 From: Mirna Wong <89008547+mirnawong1@users.noreply.github.com> Date: Wed, 16 Oct 2024 09:20:10 +0100 Subject: [PATCH 08/11] Update bigquery-configs.md --- .../reference/resource-configs/bigquery-configs.md | 14 ++++++-------- 1 file changed, 6 insertions(+), 8 deletions(-) diff --git a/website/docs/reference/resource-configs/bigquery-configs.md b/website/docs/reference/resource-configs/bigquery-configs.md index 8567bfed886..b943f114861 100644 --- a/website/docs/reference/resource-configs/bigquery-configs.md +++ b/website/docs/reference/resource-configs/bigquery-configs.md @@ -265,7 +265,7 @@ If your model has `partition_by` configured, you may optionally specify two addi -### Clustering Clause +### Clustering clause BigQuery tables can be [clustered](https://cloud.google.com/bigquery/docs/clustered-tables) to colocate related data. @@ -286,7 +286,7 @@ select * from ... -Clustering on a multiple columns: +Clustering on multiple columns: @@ -303,11 +303,11 @@ select * from ... -## Managing KMS Encryption +## Managing KMS encryption [Customer managed encryption keys](https://cloud.google.com/bigquery/docs/customer-managed-encryption) can be configured for BigQuery tables using the `kms_key_name` model configuration. -### Using KMS Encryption +### Using KMS encryption To specify the KMS key name for a model (or a group of models), use the `kms_key_name` model configuration. The following example sets the `kms_key_name` for all of the models in the `encrypted/` directory of your dbt project. @@ -328,7 +328,7 @@ models: -## Labels and Tags +## Labels and tags ### Specifying labels @@ -373,8 +373,6 @@ models: - - ### Specifying tags @@ -673,7 +671,7 @@ select ... -## Authorized Views +## Authorized views If the `grant_access_to` config is specified for a model materialized as a view, dbt will grant the view model access to select from the list of datasets From 951e4a36b890c2a94dfeec198b4cad1d54280564 Mon Sep 17 00:00:00 2001 From: Mirna Wong <89008547+mirnawong1@users.noreply.github.com> Date: Wed, 16 Oct 2024 09:24:49 +0100 Subject: [PATCH 09/11] Update website/docs/docs/build/data-tests.md --- website/docs/docs/build/data-tests.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/website/docs/docs/build/data-tests.md b/website/docs/docs/build/data-tests.md index 8ee637bc7cd..b4f25a3d111 100644 --- a/website/docs/docs/build/data-tests.md +++ b/website/docs/docs/build/data-tests.md @@ -84,7 +84,7 @@ data_tests: -Singular data tests are easy to write—so easy that you may find yourself writing the same basic structure over and over, only changing the name of a column or model. By that point, the test isn't so singular! In that case, we recommend generic data tests. +Singular data tests are so easy that you may find yourself writing the same basic structure repeatedly, only changing the name of a column or model. By that point, the test isn't so singular! In that case, we recommend generic data tests. ## Generic data tests Certain data tests are generic: they can be reused over and over again. A generic data test is defined in a `test` block, which contains a parametrized query and accepts arguments. It might look like: From 3a6199579c327af28cd612971f5ca62fb96b0371 Mon Sep 17 00:00:00 2001 From: Mirna Wong <89008547+mirnawong1@users.noreply.github.com> Date: Wed, 16 Oct 2024 11:39:43 +0100 Subject: [PATCH 10/11] Update website/docs/docs/build/incremental-models.md --- website/docs/docs/build/incremental-models.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/website/docs/docs/build/incremental-models.md b/website/docs/docs/build/incremental-models.md index e980423da96..2968496290a 100644 --- a/website/docs/docs/build/incremental-models.md +++ b/website/docs/docs/build/incremental-models.md @@ -94,7 +94,7 @@ Not specifying a `unique_key` will result in append-only behavior, which means d The optional `unique_key` parameter specifies a field (or combination of fields) that defines the grain of your model. That is, the field(s) identify a single unique row. You can define `unique_key` in a configuration block at the top of your model, and it can be a single column name or a list of column names. -The `unique_key` should be supplied in your model definition as a string representing a single column or a list of single-quoted column names that can be used together, for example, `['col1', 'col2', …])`. Columns used in this way should not contain any nulls, or the incremental model will fail to match rows and propergate duplicate rows. Either ensure that each column has no nulls (for example with `coalesce(COLUMN_NAME, 'VALUE_IF_NULL')`), or define a single-column [surrogate key](https://www.getdbt.com/blog/guide-to-surrogate-key) (for example with [`dbt_utils.generate_surrogate_key`](https://github.com/dbt-labs/dbt-utils#generate_surrogate_key-source)). +The `unique_key` should be supplied in your model definition as a string representing a single column or a list of single-quoted column names that can be used together, for example, `['col1', 'col2', …])`. Columns used in this way should not contain any nulls, or the incremental model may fail to match rows and generate duplicate rows. Either ensure that each column has no nulls (for example with `coalesce(COLUMN_NAME, 'VALUE_IF_NULL')`) or define a single-column [surrogate key](https://www.getdbt.com/blog/guide-to-surrogate-key) (for example with [`dbt_utils.generate_surrogate_key`](https://github.com/dbt-labs/dbt-utils#generate_surrogate_key-source)). :::tip In cases where you need multiple columns in combination to uniquely identify each row, we recommend you pass these columns as a list (`unique_key = ['user_id', 'session_number']`), rather than a string expression (`unique_key = 'concat(user_id, session_number)'`). From d784ab2fbe0602d5de337d986e2399448967567e Mon Sep 17 00:00:00 2001 From: Mirna Wong <89008547+mirnawong1@users.noreply.github.com> Date: Wed, 16 Oct 2024 15:17:37 +0100 Subject: [PATCH 11/11] Update website/vercel.json --- website/vercel.json | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/website/vercel.json b/website/vercel.json index 1291b5c192e..74f0eeff65b 100644 --- a/website/vercel.json +++ b/website/vercel.json @@ -3,7 +3,7 @@ "trailingSlash": false, "redirects": [ { - "source": "/src/pages/styles.js", + "source": "/styles", "destination": "https://github.com/dbt-labs/docs.getdbt.com/blob/current/contributing/adding-page-components.md", "permanent": true },