Merge branch 'main' of github.com:ClickHouse/clickhouse-docs

Author: Blargian

.github/workflows/build-search.yml

@@ -0,0 +1,44 @@
+name: Update Algolia Search
+
+on:
+  pull_request:
+    types:
+      - closed
+
+  workflow_dispatch:
+  
+  schedule:
+    - cron: '0 4 * * *'
+
+env:
+  PYTHONUNBUFFERED: 1 # Force the stdout and stderr streams to be unbuffered
+
+jobs:
+  update-search:
+    if: github.event.pull_request.merged == true && contains(github.event.pull_request.labels.*.name, 'update search') && github.event.pull_request.base.ref == 'main'
+    #if: contains(github.event.pull_request.labels.*.name, 'update search') # Updated to trigger directly on PRs with the label
+    runs-on: ubuntu-latest
+
+    steps:
+      - name: Checkout Repository
+        uses: actions/checkout@v3
+
+      - name: Set up Node.js
+        uses: actions/setup-node@v3
+        with:
+          node-version: '20' 
+
+      - name: Run Prep from Master
+        run: yarn copy-clickhouse-repo-docs
+
+      - name: Run Auto Generate Settings
+        run: yarn auto-generate-settings
+
+      - name: Run Indexer
+        run: yarn run-indexer
+        env:
+          ALGOLIA_API_KEY: ${{ secrets.ALGOLIA_API_KEY }}
+          ALGOLIA_APP_ID: 5H9UG7CX5W
+
+      - name: Verify Completion
+        run: echo "All steps completed successfully!"

.github/workflows/table_of_contents.yml

@@ -0,0 +1,79 @@
+# This GitHub Action is used for triggering updates of
+# the toc.json files present in any directory that
+# needs an automatically generated table of contents.
+
+name: Generate Table of Contents files
+
+env:
+  # Force the stdout and stderr streams to be unbuffered
+  PYTHONUNBUFFERED: 1
+
+on:
+  schedule:
+    - cron: '0 0 * * *'
+  workflow_dispatch:
+
+permissions:
+  contents: write
+
+jobs:
+  generate_toc_formats:
+    runs-on: ubuntu-latest
+    steps:
+    
+      # Step 1 - Check out the repository
+      - name: Check out repository
+        uses: actions/checkout@v3
+        
+      # Step 2 - Pull changes
+      - name: Pull remote Changes
+        run: git pull
+        
+      # Step 3 - Setup python
+      - name: Set up python
+        uses: actions/setup-python@v3
+        with:
+          python-version: '3.x'
+
+      # Step 4 - Install python dependencies
+      - name: Install dependencies
+        run: |
+          python -m pip install --upgrade pip
+          pip install -r 'scripts/table-of-contents-generator/requirements.txt'
+
+      # Step 5 -  Pull main repo docs, run script to generate TOCs:
+      - name: Generate table of contents files
+        run: |
+          yarn prep-from-master
+          python -u ./scripts/table-of-contents-generator/toc_gen.py --dir="docs/en/interfaces/formats" --single-toc --out="table-of-contents-files" --ignore "_snippets"
+
+      # Step 6 - Fail the workflow if script returns exit code 1
+      - name: Check exit code
+        run: |
+          if [[ "${{ steps.toc_gen.outcome }}" == "failure" ]]; then
+            echo "Ran into trouble generating a table of contents. See the logs for details."
+            exit 1
+          fi
+
+      # Step 7 - Check if anything was actually updated
+      - name: Check for changes
+        id: check_changes
+        run: |
+          git status -u
+          if [[ -n "$(git diff --exit-code)" ]]; then
+            echo "Changes detected."
+            echo "has_changes=true" >> $GITHUB_OUTPUT
+          else
+            echo "No changes detected."
+            echo "has_changes=false" >> $GITHUB_OUTPUT
+          fi
+
+      # Step 8 - Commit and Push generated Table Of Contents files
+      - uses: stefanzweifel/git-auto-commit-action@v5
+        env:
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+        with:
+          commit_message: "Autogenerate table of contents files from GitHub action - $(date '+%Y-%m-%d %H:%M:%S')"
+          file_pattern: 'table-of-contents-files/*'
+          branch: generate_table_of_contents
+          create_branch: true

.gitignore

@@ -49,3 +49,6 @@ docs/en/cloud/manage/api/services-api-reference.md
 .vscode
 .aspell.en.prepl
 *.md.bak
+
+# Don't ignore generated table of contents files
+!toc.json

copyClickhouseRepoDocs.sh

@@ -31,10 +31,13 @@ echo "[$SCRIPT_NAME] Copying completed"
 
 echo "[$SCRIPT_NAME] Generate changelog"
 cp docs/en/_placeholders/changelog/_index.md docs/en/whats-new/changelog/index.md
-if grep -q '^# $(date +%Y) Changelog' ClickHouse/CHANGELOG.md; then
-  sed '/^# $(date +%Y) Changelog/d' ClickHouse/CHANGELOG.md > temp.txt
-  cat >> docs/en/whats-new/changelog/index.md
-  rm temp.txt
+if grep -q "^# $(date +%Y) Changelog" ClickHouse/CHANGELOG.md; then
+  echo "Generating $(date +%Y) Changelog..."
+  sed "/^# $(date +%Y) Changelog/d" ClickHouse/CHANGELOG.md > temp.txt
+  echo "Changelog copied to temp.txt"
+  cat temp.txt >> docs/en/whats-new/changelog/index.md
+  echo "Changelog written to docs/en/whats-new/changelog/index.md"
+  rm -f temp.txt
   echo "$(date +%Y) Changelog was updated."
 else
   current_year="$(date +%Y)"

docs/en/about-us/cloud.md

@@ -8,7 +8,7 @@ description: ClickHouse Cloud
 # ClickHouse Cloud
 
 ClickHouse Cloud is the cloud offering created by the original creators of the popular open-source OLAP database ClickHouse. 
-You can experience ClickHouse Cloud by [starting a free trial](https://clickhouse.cloud/signUp).
+You can experience ClickHouse Cloud by [starting a free trial](https://console.clickhouse.cloud/signUp).
 
 ### ClickHouse Cloud benefits:
 

docs/en/about-us/history.md

@@ -2,16 +2,17 @@
 slug: /en/about-us/history
 sidebar_label: ClickHouse History
 sidebar_position: 40
-description: Where it all began...
+description: History of ClickHouse development
+tags: ['history', 'development', 'Metrica']
 ---
 
 # ClickHouse History {#clickhouse-history}
 
-ClickHouse has been developed initially to power [Yandex.Metrica](https://metrica.yandex.com/), [the second largest web analytics platform in the world](http://w3techs.com/technologies/overview/traffic_analysis/all), and continues to be the core component of this system. With more than 13 trillion records in the database and more than 20 billion events daily, ClickHouse allows generating custom reports on the fly directly from non-aggregated data. This article briefly covers the goals of ClickHouse in the early stages of its development.
+ClickHouse was initially developed to power [Yandex.Metrica](https://metrica.yandex.com/), [the second largest web analytics platform in the world](http://w3techs.com/technologies/overview/traffic_analysis/all), and continues to be its core component. With more than 13 trillion records in the database and more than 20 billion events daily, ClickHouse allows generating custom reports on the fly directly from non-aggregated data. This article briefly covers the goals of ClickHouse in the early stages of its development.
 
-Yandex.Metrica builds customized reports on the fly based on hits and sessions, with arbitrary segments defined by the user. Doing so often requires building complex aggregates, such as the number of unique users. New data for building a report arrives in real-time.
+Yandex.Metrica builds customized reports on the fly based on hits and sessions, with arbitrary segments defined by the user. Doing so often requires building complex aggregates, such as the number of unique users, with new data for building reports arriving in real-time.
 
-As of April 2014, Yandex.Metrica was tracking about 12 billion events (page views and clicks) daily. All these events must be stored to build custom reports. A single query may require scanning millions of rows within a few hundred milliseconds, or hundreds of millions of rows in just a few seconds.
+As of April 2014, Yandex.Metrica was tracking about 12 billion events (page views and clicks) daily. All these events needed to be stored, in order to build custom reports. A single query may have required scanning millions of rows within a few hundred milliseconds, or hundreds of millions of rows in just a few seconds.
 
 ## Usage in Yandex.Metrica and Other Yandex Services {#usage-in-yandex-metrica-and-other-yandex-services}
 
@@ -26,30 +27,30 @@ ClickHouse also plays a key role in the following processes:
 - Running queries for debugging the Yandex.Metrica engine.
 - Analyzing logs from the API and the user interface.
 
-Nowadays, there are multiple dozen ClickHouse installations in other Yandex services and departments: search verticals, e-commerce, advertisement, business analytics, mobile development, personal services, and others.
+Nowadays, there are a multiple dozen ClickHouse installations in other Yandex services and departments: search verticals, e-commerce, advertisement, business analytics, mobile development, personal services, and others.
 
 ## Aggregated and Non-aggregated Data {#aggregated-and-non-aggregated-data}
 
 There is a widespread opinion that to calculate statistics effectively, you must aggregate data since this reduces the volume of data.
 
-But data aggregation comes with a lot of limitations:
+However data aggregation comes with a lot of limitations:
 
 - You must have a pre-defined list of required reports.
 - The user can’t make custom reports.
 - When aggregating over a large number of distinct keys, the data volume is barely reduced, so aggregation is useless.
 - For a large number of reports, there are too many aggregation variations (combinatorial explosion).
 - When aggregating keys with high cardinality (such as URLs), the volume of data is not reduced by much (less than twofold).
 - For this reason, the volume of data with aggregation might grow instead of shrink.
-- Users do not view all the reports we generate for them. A large portion of those calculations is useless.
-- The logical integrity of data may be violated for various aggregations.
+- Users do not view all the reports we generate for them. A large portion of those calculations are useless.
+- The logical integrity of the data may be violated for various aggregations.
 
 If we do not aggregate anything and work with non-aggregated data, this might reduce the volume of calculations.
 
 However, with aggregation, a significant part of the work is taken offline and completed relatively calmly. In contrast, online calculations require calculating as fast as possible, since the user is waiting for the result.
 
 Yandex.Metrica has a specialized system for aggregating data called Metrage, which was used for the majority of reports.
 Starting in 2009, Yandex.Metrica also used a specialized OLAP database for non-aggregated data called OLAPServer, which was previously used for the report builder.
-OLAPServer worked well for non-aggregated data, but it had many restrictions that did not allow it to be used for all reports as desired. These included the lack of support for data types (only numbers), and the inability to incrementally update data in real-time (it could only be done by rewriting data daily). OLAPServer is not a DBMS, but a specialized DB.
+OLAPServer worked well for non-aggregated data, but it had many restrictions that did not allow it to be used for all reports as desired. These included a lack of support for data types (numbers only), and the inability to incrementally update data in real-time (it could only be done by rewriting data daily). OLAPServer is not a DBMS, but a specialized DB.
 
 The initial goal for ClickHouse was to remove the limitations of OLAPServer and solve the problem of working with non-aggregated data for all reports, but over the years, it has grown into a general-purpose database management system suitable for a wide range of analytical tasks.
 

docs/en/about-us/support.md

@@ -7,7 +7,7 @@ sidebar_position: 30
 
 ClickHouse provides Support Services for our ClickHouse Cloud users and customers. Our objective is a Support Services team that represents the ClickHouse product – unparalleled performance, ease of use, and exceptionally fast, high-quality results. For details, [visit our Support Services](https://clickhouse.com/support/program/) page.
 
-[Login to the Cloud console](https://clickhouse.cloud/support) and select **Help -> Support** from the menu options to open a new support case and view the status of your submitted cases. 
+[Login to the Cloud console](https://console.clickhouse.cloud/support) and select **Help -> Support** from the menu options to open a new support case and view the status of your submitted cases. 
 
 **Service level agreements ("SLA")**
 Classification of severity levels for issues reported and response times.

docs/en/chdb/getting-started.md

@@ -49,7 +49,7 @@ pip install pandas pyarrow
 ## Querying a JSON file in S3
 
 Let's now have a look at how to query a JSON file that's stored in an S3 bucket. 
-The [YouTube dislikes dataset](https://clickhouse.com/docs/en/getting-started/example-datasets/youtube-dislikes) contains more than 4 billion rows of dislikes on YouTube videos up to 2021.
+The [YouTube dislikes dataset](/docs/en/getting-started/example-datasets/youtube-dislikes) contains more than 4 billion rows of dislikes on YouTube videos up to 2021.
 We're going to work with one of the JSON files from that dataset.
 
 Import chdb:

docs/en/cloud/bestpractices/usagelimits.md

@@ -12,12 +12,6 @@ Clickhouse is very fast and reliable, but any database has its limits. For examp
 If you've reached one of those limits, it may mean that you are implementing your use case in an unoptimized way. You can contact our support so we can help you refine your use case to avoid going through the limits or to increase the limits in a guided way. 
 :::
 
-# Tables
-Clickhouse Cloud have a limit of **5000** tables per instance
-
-# Databases
-Clickhouse Cloud have a limit of **1000** databases per instance
-
 # Partitions
 Clickhouse Cloud have a limit of **50000** [partitions](https://clickhouse.com/docs/en/engines/table-engines/mergetree-family/custom-partitioning-key) per instance
 

docs/en/cloud/get-started/cloud-quick-start.md

@@ -10,13 +10,13 @@ import SQLConsoleDetail from '@site/docs/en/_snippets/_launch_sql_console.md';
 # ClickHouse Cloud Quick Start
 
 The quickest and easiest way to get up and running with ClickHouse is to create a new
-service in [ClickHouse Cloud](https://clickhouse.cloud).
+service in [ClickHouse Cloud](https://console.clickhouse.cloud).
 
 ## 1. Create a ClickHouse service 
 
-To create a free ClickHouse service in [ClickHouse Cloud](https://clickhouse.cloud), you just need to sign up by completing the following steps:
+To create a free ClickHouse service in [ClickHouse Cloud](https://console.clickhouse.cloud), you just need to sign up by completing the following steps:
 
-  - Create an account on the [sign-up page](https://clickhouse.cloud/signUp)
+  - Create an account on the [sign-up page](https://console.clickhouse.cloud/signUp)
   - You can choose to sign up using your email or via Google SSO, Microsoft SSO, AWS Marketplace, Google Cloud or Microsoft Azure
   - If you sign up using an email and password, remember to verify your email address within the next 24h via the link you receive in your email
   - Login using the username and password you just created