Add docs check to documentation

.github/workflows/main.yml

@@ -21,7 +21,6 @@ jobs:
           python3 run_check.py
   DockerHubPush:
     needs: CheckLabels
-    if: ${{ !contains(github.event.pull_request.labels.*.name, 'pr-documentation') && !contains(github.event.pull_request.labels.*.name, 'pr-doc-fix') }}
     runs-on: [self-hosted, style-checker]
     steps:
       - name: Check out repository code
@@ -57,8 +56,33 @@ jobs:
         run: |
           docker kill $(docker ps -q) ||:
           sudo rm -fr $TEMP_PATH
+    DocsCheck:
+      needs: DockerHubPush
+      runs-on: [self-hosted, style-checker]
+      steps:
+        - name: Download changed images
+          uses: actions/download-artifact@v2
+          with:
+            name: changed_images
+            path: ${{ runner.temp }}/docs_check
+        - name: Check out repository code
+          uses: actions/checkout@v2
+        - name: Style Check
+          env:
+            TEMP_PATH: ${{runner.temp}}/docs_check
+            REPO_COPY: ${{runner.temp}}/docs_check/ClickHouse
+          run: |
+            cp -r $GITHUB_WORKSPACE $TEMP_PATH
+            cd $REPO_COPY/tests/ci
+            python3 docs_check.py
+        - name: Cleanup
+          if: always()
+          run: |
+            docker kill $(docker ps -q) ||:
+            sudo rm -fr $TEMP_PATH
   BuilderDebDebug:
     needs: DockerHubPush
+    if: ${{ !contains(github.event.pull_request.labels.*.name, 'pr-documentation') && !contains(github.event.pull_request.labels.*.name, 'pr-doc-fix') }}
     runs-on: [self-hosted, builder]
     steps:
       - name: Download changed images
@@ -179,6 +203,7 @@ jobs:
           sudo rm -fr $TEMP_PATH
   FastTest:
     needs: DockerHubPush
+    if: ${{ !contains(github.event.pull_request.labels.*.name, 'pr-documentation') && !contains(github.event.pull_request.labels.*.name, 'pr-doc-fix') }}
     runs-on: [self-hosted, builder]
     steps:
       - name: Check out repository code

docker/docs/builder/Dockerfile

@@ -1,4 +1,4 @@
-# docker build -t yandex/clickhouse-docs-build .
+# docker build -t clickhouse/docs-build .
 FROM ubuntu:20.04
 
 ENV LANG=C.UTF-8
@@ -44,7 +44,4 @@ certifi==2020.4.5.2 chardet==3.0.4 click==7.1.2 closure==20191111 cssmin==0.2.0
 idna==2.10 Jinja2>=2.11.3 jinja2-highlight==0.6.1 jsmin==3.0.0 livereload==2.6.2 Markdown==3.3.2 MarkupSafe==2.0.1 \
 mkdocs==1.2.3 mkdocs-htmlproofer-plugin==0.0.3 mkdocs-macros-plugin==0.4.20 nltk==3.5 nose==1.3.7 protobuf==3.14.0 \
 numpy==1.21.2 pymdown-extensions==9.0 python-slugify==4.0.1 PyYAML==5.4.1 repackage==0.7.3 requests==2.25.1 \
-singledispatch==3.4.0.3 six==1.15.0 soupsieve==2.0.1 termcolor==1.1.0 tornado==6.1 Unidecode==1.1.1 urllib3>=1.26.5 
+singledispatch==3.4.0.3 six==1.15.0 soupsieve==2.0.1 termcolor==1.1.0 tornado==6.1 Unidecode==1.1.1 urllib3>=1.26.5
-
-
-COPY * /

docker/images.json

@@ -169,6 +169,11 @@
     },
     "docker/docs/builder": {
         "name": "clickhouse/docs-builder",
-	"dependent": []
+	    "dependent": ["docker/docs/check"]
+    },
+    "docker/docs/check": {
+        "name": "clickhouse/docs-check",
+	    "dependent": []
     }
+
 }

tests/ci/docs_check.py

@@ -0,0 +1,148 @@
+#!/usr/bin/env python3
+import logging
+import subprocess
+import os
+import time
+import json
+import sys
+from github import Github
+from report import create_test_html_report
+from s3_helper import S3Helper
+from pr_info import PRInfo
+from get_robot_token import get_best_robot_token
+
+NAME = "Docs Check (actions)"
+
+def process_logs(s3_client, additional_logs, s3_path_prefix):
+    additional_urls = []
+    for log_path in additional_logs:
+        if log_path:
+            additional_urls.append(
+                s3_client.upload_test_report_to_s3(
+                    log_path,
+                    s3_path_prefix + "/" + os.path.basename(log_path)))
+
+    return additional_urls
+
+def upload_results(s3_client, pr_number, commit_sha, test_results, additional_files):
+    s3_path_prefix = f"{pr_number}/{commit_sha}/docs_check"
+    additional_urls = process_logs(s3_client, additional_files, s3_path_prefix)
+
+    branch_url = "https://github.com/ClickHouse/ClickHouse/commits/master"
+    branch_name = "master"
+    if pr_number != 0:
+        branch_name = f"PR #{pr_number}"
+        branch_url = f"https://github.com/ClickHouse/ClickHouse/pull/{pr_number}"
+    commit_url = f"https://github.com/ClickHouse/ClickHouse/commit/{commit_sha}"
+
+    task_url = f"https://github.com/ClickHouse/ClickHouse/actions/runs/{os.getenv('GITHUB_RUN_ID')}"
+
+    raw_log_url = additional_urls[0]
+    additional_urls.pop(0)
+
+    html_report = create_test_html_report(NAME, test_results, raw_log_url, task_url, branch_url, branch_name, commit_url, additional_urls)
+    with open('report.html', 'w', encoding='utf-8') as f:
+        f.write(html_report)
+
+    url = s3_client.upload_test_report_to_s3('report.html', s3_path_prefix + ".html")
+    logging.info("Search result in url %s", url)
+    return url
+
+def get_commit(gh, commit_sha):
+    repo = gh.get_repo(os.getenv("GITHUB_REPOSITORY", "ClickHouse/ClickHouse"))
+    commit = repo.get_commit(commit_sha)
+    return commit
+
+if __name__ == "__main__":
+    logging.basicConfig(level=logging.INFO)
+
+    temp_path = os.path.join(os.getenv("TEMP_PATH"))
+    repo_path = os.path.join(os.getenv("REPO_COPY"))
+
+    with open(os.getenv('GITHUB_EVENT_PATH'), 'r', encoding='utf-8') as event_file:
+        event = json.load(event_file)
+
+    pr_info = PRInfo(event, need_changed_files=True)
+
+    gh = Github(get_best_robot_token())
+    if not pr_info.has_changes_in_documentation():
+        logging.info ("No changes in documentation")
+        commit = get_commit(gh, pr_info.sha)
+        commit.create_status(context=NAME, description="No changes in docs", state="success")
+        sys.exit(0)
+
+    logging.info("Has changes in docs")
+
+    if not os.path.exists(temp_path):
+        os.makedirs(temp_path)
+
+    images_path = os.path.join(temp_path, 'changed_images.json')
+
+    docker_image = 'clickhouse/docs-check'
+    if os.path.exists(images_path):
+        logging.info("Images file exists")
+        with open(images_path, 'r', encoding='utf-8') as images_fd:
+            images = json.load(images_fd)
+            logging.info("Got images %s", images)
+            if 'clickhouse/docs-check' in images:
+                docker_image += ':' + images['clickhouse/docs-check']
+
+    logging.info("Got docker image %s", docker_image)
+    for i in range(10):
+        try:
+            subprocess.check_output(f"docker pull {docker_image}", shell=True)
+            break
+        except Exception as ex:
+            time.sleep(i * 3)
+            logging.info("Got execption pulling docker %s", ex)
+    else:
+        raise Exception(f"Cannot pull dockerhub for image {docker_image}")
+
+    test_output = os.path.join(temp_path, 'docs_check_log')
+    if not os.path.exists(test_output):
+        os.makedirs(test_output)
+
+    cmd = "docker run --cap-add=SYS_PTRACE --volume={repo_path}:/ClickHouse --volume={test_output}:/test_output {docker_image}"
+
+    run_log_path = os.path.join(test_output, 'runlog.log')
+
+    with open(run_log_path, 'w', encoding='utf-8') as log:
+        with subprocess.Popen(cmd, shell=True, stderr=log, stdout=log) as process:
+            retcode = process.wait()
+        if retcode == 0:
+            logging.info("Run successfully")
+            status = "Success"
+            description = "Run Ok"
+        else:
+            description = "Run failed (non zero exit code)"
+            status = "failure"
+            logging.info("Run failed")
+
+    subprocess.check_call(f"sudo chown -R ubuntu:ubuntu {temp_path}", shell=True)
+    files = os.listdir(test_output)
+    lines = []
+    additional_files = []
+    if not files:
+        logging.error("No output files after docs check")
+        description = "No output files after docs check"
+        status = "failure"
+    else:
+        for f in files:
+            path = os.path.join(test_output, f)
+            additional_files.append(path)
+            with open(path, 'r', encoding='utf-8') as check_file:
+                for line in check_file:
+                    if "ERROR" in line:
+                        lines.append((line.split(':')[-1], "FAIL"))
+        if lines:
+            status = "failure"
+            description = "Found errors during docs check"
+        else:
+            lines.append(("No errors found", "OK"))
+
+    s3_helper = S3Helper('https://s3.amazonaws.com')
+
+    report_url = upload_results(s3_helper, pr_info.number, pr_info.sha, lines, additional_files)
+    print("::notice ::Report url: {report_url}")
+    commit = get_commit(gh, pr_info.sha)
+    commit.create_status(context=NAME, description=description, state=status, target_url=report_url)

tests/ci/pr_info.py

@@ -2,8 +2,11 @@
 import urllib
 import requests
 from unidiff import PatchSet
+import os
 
 
+DIFF_IN_DOCUMENTATION_EXT = [".html", ".md", ".yml", ".txt", ".css", ".js", ".xml", ".ico", ".conf", ".svg", ".png", ".jpg", ".py", ".sh"]
+
 class PRInfo:
     def __init__(self, github_event, need_orgs=False, need_changed_files=False):
         self.number = github_event['number']
@@ -37,6 +40,18 @@ class PRInfo:
             'user_orgs': self.user_orgs,
         }
 
+    def has_changes_in_documentation(self):
+        # If the list wasn't built yet the best we can do is to
+        # assume that there were changes.
+        if self.changed_files is None or not self.changed_files:
+            return True
+
+        for f in self.changed_files:
+            _, ext = os.path.splitext(f)
+            if ext in DIFF_IN_DOCUMENTATION_EXT or 'Dockerfile' in f:
+                return True
+        return False
+
 
 class FakePRInfo:
     def __init__(self):