Merge branch 'master' into _shard_num

docs/ru/sql-reference/statements/create/user.md

@@ -43,7 +43,7 @@ CREATE USER [IF NOT EXISTS | OR REPLACE] name1 [ON CLUSTER cluster_name1]
 -   `HOST ANY` — Пользователь может подключиться с любого хоста. Используется по умолчанию.
 -   `HOST LOCAL` — Пользователь может подключиться только локально.
 -   `HOST NAME 'fqdn'` — Хост задается через FQDN. Например, `HOST NAME 'mysite.com'`.
--   `HOST NAME REGEXP 'regexp'` — Позволяет использовать регулярные выражения [pcre](http://www.pcre.org/), чтобы задать хосты. Например, `HOST NAME REGEXP '.*\.mysite\.com'`.
+-   `HOST REGEXP 'regexp'` — Позволяет использовать регулярные выражения [pcre](http://www.pcre.org/), чтобы задать хосты. Например, `HOST REGEXP '.*\.mysite\.com'`.
 -   `HOST LIKE 'template'` — Позволяет использовать оператор [LIKE](../../functions/string-search-functions.md#function-like) для фильтрации хостов. Например, `HOST LIKE '%'` эквивалентен `HOST ANY`; `HOST LIKE '%.mysite.com'` разрешает подключение со всех хостов в домене `mysite.com`.
 
 Также, чтобы задать хост, вы можете использовать `@` вместе с именем пользователя. Примеры:

docs/zh/faq/index.md

@@ -19,6 +19,7 @@ toc_priority: 76
     -   [什么是 OLAP?](../faq/general/olap.md)
     -   [什么是列存储数据库?](../faq/general/columnar-database.md)
     -   [为何不使用 MapReduce等技术?](../faq/general/mapreduce.md)
+    -   [我如何为 ClickHouse贡献代码?](../faq/general/how-do-i-contribute-code-to-clickhouse.md)
 -   **[应用案例](../faq/use-cases/index.md)**
     -   [我能把 ClickHouse 作为时序数据库来使用吗?](../faq/use-cases/time-series.md)
     -   [我能把 ClickHouse 作为 key-value 键值存储吗？](../faq/use-cases/key-value.md)

programs/install/Install.cpp

@@ -364,7 +364,9 @@ int mainEntryClickHouseInstall(int argc, char ** argv)
             "clickhouse-git-import",
             "clickhouse-compressor",
             "clickhouse-format",
-            "clickhouse-extract-from-config"
+            "clickhouse-extract-from-config",
+            "clickhouse-keeper",
+            "clickhouse-keeper-converter",
         };
 
         for (const auto & tool : tools)

src/Storages/MergeTree/ReplicatedMergeTreeQueue.cpp

@@ -1123,7 +1123,7 @@ bool ReplicatedMergeTreeQueue::addFuturePartIfNotCoveredByThem(const String & pa
 
     if (isNotCoveredByFuturePartsImpl(entry, part_name, reject_reason, lock))
     {
-        CurrentlyExecuting::setActualPartName(entry, part_name, *this);
+        CurrentlyExecuting::setActualPartName(entry, part_name, *this, lock);
         return true;
     }
 
@@ -1375,7 +1375,8 @@ Int64 ReplicatedMergeTreeQueue::getCurrentMutationVersion(const String & partiti
 }
 
 
-ReplicatedMergeTreeQueue::CurrentlyExecuting::CurrentlyExecuting(const ReplicatedMergeTreeQueue::LogEntryPtr & entry_, ReplicatedMergeTreeQueue & queue_)
+ReplicatedMergeTreeQueue::CurrentlyExecuting::CurrentlyExecuting(
+    const ReplicatedMergeTreeQueue::LogEntryPtr & entry_, ReplicatedMergeTreeQueue & queue_, std::lock_guard<std::mutex> & /* state_lock */)
     : entry(entry_), queue(queue_)
 {
     if (entry->type == ReplicatedMergeTreeLogEntry::DROP_RANGE || entry->type == ReplicatedMergeTreeLogEntry::REPLACE_RANGE)
@@ -1397,8 +1398,11 @@ ReplicatedMergeTreeQueue::CurrentlyExecuting::CurrentlyExecuting(const Replicate
 }
 
 
-void ReplicatedMergeTreeQueue::CurrentlyExecuting::setActualPartName(ReplicatedMergeTreeQueue::LogEntry & entry,
-                                                                     const String & actual_part_name, ReplicatedMergeTreeQueue & queue)
+void ReplicatedMergeTreeQueue::CurrentlyExecuting::setActualPartName(
+    ReplicatedMergeTreeQueue::LogEntry & entry,
+    const String & actual_part_name,
+    ReplicatedMergeTreeQueue & queue,
+    std::lock_guard<std::mutex> & /* state_lock */)
 {
     if (!entry.actual_new_part_name.empty())
         throw Exception("Entry actual part isn't empty yet. This is a bug.", ErrorCodes::LOGICAL_ERROR);
@@ -1477,7 +1481,7 @@ ReplicatedMergeTreeQueue::SelectedEntryPtr ReplicatedMergeTreeQueue::selectEntry
     }
 
     if (entry)
-        return std::make_shared<SelectedEntry>(entry, std::unique_ptr<CurrentlyExecuting>{ new CurrentlyExecuting(entry, *this) });
+        return std::make_shared<SelectedEntry>(entry, std::unique_ptr<CurrentlyExecuting>{new CurrentlyExecuting(entry, *this, lock)});
     else
         return {};
 }

src/Storages/MergeTree/ReplicatedMergeTreeQueue.h

@@ -251,11 +251,18 @@ private:
         friend class ReplicatedMergeTreeQueue;
 
         /// Created only in the selectEntryToProcess function. It is called under mutex.
-        CurrentlyExecuting(const ReplicatedMergeTreeQueue::LogEntryPtr & entry_, ReplicatedMergeTreeQueue & queue_);
+        CurrentlyExecuting(
+            const ReplicatedMergeTreeQueue::LogEntryPtr & entry_,
+            ReplicatedMergeTreeQueue & queue_,
+            std::lock_guard<std::mutex> & state_lock);
 
         /// In case of fetch, we determine actual part during the execution, so we need to update entry. It is called under state_mutex.
-        static void setActualPartName(ReplicatedMergeTreeQueue::LogEntry & entry, const String & actual_part_name,
-            ReplicatedMergeTreeQueue & queue);
+        static void setActualPartName(
+            ReplicatedMergeTreeQueue::LogEntry & entry,
+            const String & actual_part_name,
+            ReplicatedMergeTreeQueue & queue,
+            std::lock_guard<std::mutex> & state_lock);
+
     public:
         ~CurrentlyExecuting();
     };

tests/ci/build_download_helper.py

@@ -5,36 +5,66 @@ import json
 import logging
 import sys
 import time
+from typing import Optional
 
-import requests
+import requests  # type: ignore
 
 from ci_config import CI_CONFIG
 
 DOWNLOAD_RETRIES_COUNT = 5
 
+
+def get_with_retries(
+    url: str,
+    retries: int = DOWNLOAD_RETRIES_COUNT,
+    sleep: int = 3,
+    **kwargs,
+) -> requests.Response:
+    logging.info("Getting URL with %i and sleep %i in between: %s", retries, sleep, url)
+    exc = None  # type: Optional[Exception]
+    for i in range(DOWNLOAD_RETRIES_COUNT):
+        try:
+            response = requests.get(url, **kwargs)
+            response.raise_for_status()
+            break
+        except Exception as e:
+            if i + 1 < DOWNLOAD_RETRIES_COUNT:
+                logging.info("Exception '%s' while getting, retry %i", e, i + 1)
+                time.sleep(sleep)
+
+            exc = e
+    else:
+        raise Exception(exc)
+
+    return response
+
+
 def get_build_name_for_check(check_name):
-    return CI_CONFIG['tests_config'][check_name]['required_build']
+    return CI_CONFIG["tests_config"][check_name]["required_build"]
+
 
 def get_build_urls(build_name, reports_path):
     for root, _, files in os.walk(reports_path):
         for f in files:
-            if build_name in f :
+            if build_name in f:
                 logging.info("Found build report json %s", f)
-                with open(os.path.join(root, f), 'r', encoding='utf-8') as file_handler:
+                with open(os.path.join(root, f), "r", encoding="utf-8") as file_handler:
                     build_report = json.load(file_handler)
-                    return build_report['build_urls']
+                    return build_report["build_urls"]
     return []
 
+
 def dowload_build_with_progress(url, path):
     logging.info("Downloading from %s to temp path %s", url, path)
     for i in range(DOWNLOAD_RETRIES_COUNT):
         try:
-            with open(path, 'wb') as f:
-                response = requests.get(url, stream=True)
-                response.raise_for_status()
-                total_length = response.headers.get('content-length')
+            with open(path, "wb") as f:
+                response = get_with_retries(url, retries=1, stream=True)
+                total_length = response.headers.get("content-length")
                 if total_length is None or int(total_length) == 0:
-                    logging.info("No content-length, will download file without progress")
+                    logging.info(
+                        "No content-length, will download file without progress"
+                    )
                     f.write(response.content)
                 else:
                     dl = 0
@@ -46,32 +76,38 @@ def dowload_build_with_progress(url, path):
                         if sys.stdout.isatty():
                             done = int(50 * dl / total_length)
                             percent = int(100 * float(dl) / total_length)
-                            eq_str = '=' * done
-                            space_str = ' ' * (50 - done)
+                            eq_str = "=" * done
+                            space_str = " " * (50 - done)
                             sys.stdout.write(f"\r[{eq_str}{space_str}] {percent}%")
                             sys.stdout.flush()
             break
-        except Exception as ex:
-            sys.stdout.write("\n")
-            time.sleep(3)
-            logging.info("Exception while downloading %s, retry %s", ex, i + 1)
+        except Exception:
+            if sys.stdout.isatty():
+                sys.stdout.write("\n")
+            if i + 1 < DOWNLOAD_RETRIES_COUNT:
+                time.sleep(3)
+
             if os.path.exists(path):
                 os.remove(path)
     else:
         raise Exception(f"Cannot download dataset from {url}, all retries exceeded")
 
-    sys.stdout.write("\n")
+    if sys.stdout.isatty():
+        sys.stdout.write("\n")
     logging.info("Downloading finished")
 
 
 def download_builds(result_path, build_urls, filter_fn):
     for url in build_urls:
         if filter_fn(url):
-            fname = os.path.basename(url.replace('%2B', '+').replace('%20', ' '))
+            fname = os.path.basename(url.replace("%2B", "+").replace("%20", " "))
             logging.info("Will download %s to %s", fname, result_path)
             dowload_build_with_progress(url, os.path.join(result_path, fname))
 
-def download_builds_filter(check_name, reports_path, result_path, filter_fn=lambda _: True):
+
+def download_builds_filter(
+    check_name, reports_path, result_path, filter_fn=lambda _: True
+):
     build_name = get_build_name_for_check(check_name)
     urls = get_build_urls(build_name, reports_path)
     print(urls)
@@ -81,17 +117,32 @@ def download_builds_filter(check_name, reports_path, result_path, filter_fn=lamb
 
     download_builds(result_path, urls, filter_fn)
 
+
 def download_all_deb_packages(check_name, reports_path, result_path):
-    download_builds_filter(check_name, reports_path, result_path, lambda x: x.endswith('deb'))
+    download_builds_filter(
+        check_name, reports_path, result_path, lambda x: x.endswith("deb")
+    )
+
 
 def download_shared_build(check_name, reports_path, result_path):
-    download_builds_filter(check_name, reports_path, result_path, lambda x: x.endswith('shared_build.tgz'))
+    download_builds_filter(
+        check_name, reports_path, result_path, lambda x: x.endswith("shared_build.tgz")
+    )
+
 
 def download_unit_tests(check_name, reports_path, result_path):
-    download_builds_filter(check_name, reports_path, result_path, lambda x: x.endswith('unit_tests_dbms'))
+    download_builds_filter(
+        check_name, reports_path, result_path, lambda x: x.endswith("unit_tests_dbms")
+    )
+
 
 def download_clickhouse_binary(check_name, reports_path, result_path):
-    download_builds_filter(check_name, reports_path, result_path, lambda x: x.endswith('clickhouse'))
+    download_builds_filter(
+        check_name, reports_path, result_path, lambda x: x.endswith("clickhouse")
+    )
+
 
 def download_performance_build(check_name, reports_path, result_path):
-    download_builds_filter(check_name, reports_path, result_path, lambda x: x.endswith('performance.tgz'))
+    download_builds_filter(
+        check_name, reports_path, result_path, lambda x: x.endswith("performance.tgz")
+    )

tests/ci/pr_info.py

@@ -2,28 +2,51 @@
 import json
 import os
 
-import requests  # type: ignore
 from unidiff import PatchSet  # type: ignore
 
-from env_helper import GITHUB_REPOSITORY, GITHUB_SERVER_URL, GITHUB_RUN_ID, GITHUB_EVENT_PATH
+from build_download_helper import get_with_retries
+from env_helper import (
+    GITHUB_REPOSITORY,
+    GITHUB_SERVER_URL,
+    GITHUB_RUN_ID,
+    GITHUB_EVENT_PATH,
+)
+
+DIFF_IN_DOCUMENTATION_EXT = [
+    ".html",
+    ".md",
+    ".yml",
+    ".txt",
+    ".css",
+    ".js",
+    ".xml",
+    ".ico",
+    ".conf",
+    ".svg",
+    ".png",
+    ".jpg",
+    ".py",
+    ".sh",
+    ".json",
+]
+RETRY_SLEEP = 0
 
-DIFF_IN_DOCUMENTATION_EXT = [".html", ".md", ".yml", ".txt", ".css", ".js", ".xml", ".ico", ".conf", ".svg", ".png",
-                             ".jpg", ".py", ".sh", ".json"]
 
 def get_pr_for_commit(sha, ref):
     if not ref:
         return None
-    try_get_pr_url = f"https://api.github.com/repos/{GITHUB_REPOSITORY}/commits/{sha}/pulls"
+    try_get_pr_url = (
+        f"https://api.github.com/repos/{GITHUB_REPOSITORY}/commits/{sha}/pulls"
+    )
     try:
-        response = requests.get(try_get_pr_url)
-        response.raise_for_status()
+        response = get_with_retries(try_get_pr_url, sleep=RETRY_SLEEP)
         data = response.json()
         if len(data) > 1:
             print("Got more than one pr for commit", sha)
         for pr in data:
             # refs for pushes looks like refs/head/XX
             # refs for RPs looks like XX
-            if pr['head']['ref'] in ref:
+            if pr["head"]["ref"] in ref:
                 return pr
         print("Cannot find PR with required ref", ref, "returning first one")
         first_pr = data[0]
@@ -35,15 +58,22 @@ def get_pr_for_commit(sha, ref):
 
 class PRInfo:
     default_event = {
-                    'commits': 1,
-                    'before': 'HEAD~',
-                    'after': 'HEAD',
-                    'ref': None,
-                }
-    def __init__(self, github_event=None, need_orgs=False, need_changed_files=False, labels_from_api=False):
+        "commits": 1,
+        "before": "HEAD~",
+        "after": "HEAD",
+        "ref": None,
+    }
+
+    def __init__(
+        self,
+        github_event=None,
+        need_orgs=False,
+        need_changed_files=False,
+        pr_event_from_api=False,
+    ):
         if not github_event:
             if GITHUB_EVENT_PATH:
-                with open(GITHUB_EVENT_PATH, 'r', encoding='utf-8') as event_file:
+                with open(GITHUB_EVENT_PATH, "r", encoding="utf-8") as event_file:
                     github_event = json.load(event_file)
             else:
                 github_event = PRInfo.default_event.copy()
@@ -51,22 +81,34 @@ class PRInfo:
         self.changed_files = set([])
         self.body = ""
         ref = github_event.get("ref", "refs/head/master")
-        if ref and ref.startswith('refs/heads/'):
+        if ref and ref.startswith("refs/heads/"):
             ref = ref[11:]
 
         # workflow completed event, used for PRs only
-        if 'action' in github_event and github_event['action'] == 'completed':
-            self.sha = github_event['workflow_run']['head_sha']
-            prs_for_sha = requests.get(f"https://api.github.com/repos/{GITHUB_REPOSITORY}/commits/{self.sha}/pulls").json()
+        if "action" in github_event and github_event["action"] == "completed":
+            self.sha = github_event["workflow_run"]["head_sha"]
+            prs_for_sha = get_with_retries(
+                f"https://api.github.com/repos/{GITHUB_REPOSITORY}/commits/{self.sha}"
+                "/pulls",
+                sleep=RETRY_SLEEP,
+            ).json()
             if len(prs_for_sha) != 0:
-                github_event['pull_request'] = prs_for_sha[0]
+                github_event["pull_request"] = prs_for_sha[0]
 
-        if 'pull_request' in github_event:  # pull request and other similar events
-            self.number = github_event['pull_request']['number']
-            if 'after' in github_event:
-                self.sha = github_event['after']
+        if "pull_request" in github_event:  # pull request and other similar events
+            self.number = github_event["pull_request"]["number"]
+            if pr_event_from_api:
+                response = get_with_retries(
+                    f"https://api.github.com/repos/{GITHUB_REPOSITORY}"
+                    f"/pulls/{self.number}",
+                    sleep=RETRY_SLEEP,
+                )
+                github_event["pull_request"] = response.json()
+
+            if "after" in github_event:
+                self.sha = github_event["after"]
             else:
-                self.sha = github_event['pull_request']['head']['sha']
+                self.sha = github_event["pull_request"]["head"]["sha"]
 
             repo_prefix = f"{GITHUB_SERVER_URL}/{GITHUB_REPOSITORY}"
             self.task_url = f"{repo_prefix}/actions/runs/{GITHUB_RUN_ID or '0'}"
@@ -75,35 +117,35 @@ class PRInfo:
             self.commit_html_url = f"{repo_prefix}/commits/{self.sha}"
             self.pr_html_url = f"{repo_prefix}/pull/{self.number}"
 
-            self.base_ref = github_event['pull_request']['base']['ref']
-            self.base_name = github_event['pull_request']['base']['repo']['full_name']
-            self.head_ref = github_event['pull_request']['head']['ref']
-            self.head_name = github_event['pull_request']['head']['repo']['full_name']
-            self.body = github_event['pull_request']['body']
+            self.base_ref = github_event["pull_request"]["base"]["ref"]
+            self.base_name = github_event["pull_request"]["base"]["repo"]["full_name"]
+            self.head_ref = github_event["pull_request"]["head"]["ref"]
+            self.head_name = github_event["pull_request"]["head"]["repo"]["full_name"]
+            self.body = github_event["pull_request"]["body"]
+            self.labels = {
+                label["name"] for label in github_event["pull_request"]["labels"]
+            }
 
-            if labels_from_api:
-                response = requests.get(f"https://api.github.com/repos/{GITHUB_REPOSITORY}/issues/{self.number}/labels")
-                self.labels = {l['name'] for l in response.json()}
-            else:
-                self.labels = {l['name'] for l in github_event['pull_request']['labels']}
-
-            self.user_login = github_event['pull_request']['user']['login']
+            self.user_login = github_event["pull_request"]["user"]["login"]
             self.user_orgs = set([])
             if need_orgs:
-                user_orgs_response = requests.get(github_event['pull_request']['user']['organizations_url'])
+                user_orgs_response = get_with_retries(
+                    github_event["pull_request"]["user"]["organizations_url"],
+                    sleep=RETRY_SLEEP,
+                )
                 if user_orgs_response.ok:
                     response_json = user_orgs_response.json()
-                    self.user_orgs = set(org['id'] for org in response_json)
+                    self.user_orgs = set(org["id"] for org in response_json)
 
-            self.diff_url = github_event['pull_request']['diff_url']
-        elif 'commits' in github_event:
-            self.sha = github_event['after']
-            pull_request = get_pr_for_commit(self.sha, github_event['ref'])
+            self.diff_url = github_event["pull_request"]["diff_url"]
+        elif "commits" in github_event:
+            self.sha = github_event["after"]
+            pull_request = get_pr_for_commit(self.sha, github_event["ref"])
             repo_prefix = f"{GITHUB_SERVER_URL}/{GITHUB_REPOSITORY}"
             self.task_url = f"{repo_prefix}/actions/runs/{GITHUB_RUN_ID or '0'}"
             self.commit_html_url = f"{repo_prefix}/commits/{self.sha}"
             self.repo_full_name = GITHUB_REPOSITORY
-            if pull_request is None or pull_request['state'] == 'closed':
+            if pull_request is None or pull_request["state"] == "closed":
                 # it's merged PR to master
                 self.number = 0
                 self.labels = {}
@@ -112,25 +154,25 @@ class PRInfo:
                 self.base_name = self.repo_full_name
                 self.head_ref = ref
                 self.head_name = self.repo_full_name
-                self.diff_url = \
-                    f"https://api.github.com/repos/{GITHUB_REPOSITORY}/compare/{github_event['before']}...{self.sha}"
+                self.diff_url = (
+                    f"https://api.github.com/repos/{GITHUB_REPOSITORY}/"
+                    f"compare/{github_event['before']}...{self.sha}"
+                )
             else:
-                self.number = pull_request['number']
-                if labels_from_api:
-                    response = requests.get(f"https://api.github.com/repos/{GITHUB_REPOSITORY}/issues/{self.number}/labels")
-                    self.labels = {l['name'] for l in response.json()}
-                else:
-                    self.labels = {l['name'] for l in pull_request['labels']}
+                self.labels = {label["name"] for label in pull_request["labels"]}
 
-                self.base_ref = pull_request['base']['ref']
-                self.base_name = pull_request['base']['repo']['full_name']
-                self.head_ref = pull_request['head']['ref']
-                self.head_name = pull_request['head']['repo']['full_name']
-                self.pr_html_url = pull_request['html_url']
-                if 'pr-backport' in self.labels:
-                    self.diff_url = f"https://github.com/{GITHUB_REPOSITORY}/compare/master...{self.head_ref}.diff"
+                self.base_ref = pull_request["base"]["ref"]
+                self.base_name = pull_request["base"]["repo"]["full_name"]
+                self.head_ref = pull_request["head"]["ref"]
+                self.head_name = pull_request["head"]["repo"]["full_name"]
+                self.pr_html_url = pull_request["html_url"]
+                if "pr-backport" in self.labels:
+                    self.diff_url = (
+                        f"https://github.com/{GITHUB_REPOSITORY}/"
+                        f"compare/master...{self.head_ref}.diff"
+                    )
                 else:
-                    self.diff_url = pull_request['diff_url']
+                    self.diff_url = pull_request["diff_url"]
         else:
             print(json.dumps(github_event, sort_keys=True, indent=4))
             self.sha = os.getenv("GITHUB_SHA")
@@ -153,24 +195,27 @@ class PRInfo:
         if not self.diff_url:
             raise Exception("Diff URL cannot be find for event")
 
-        response = requests.get(self.diff_url)
+        response = get_with_retries(
+            self.diff_url,
+            sleep=RETRY_SLEEP,
+        )
         response.raise_for_status()
-        if 'commits' in self.event and self.number == 0:
+        if "commits" in self.event and self.number == 0:
             diff = response.json()
 
-            if 'files' in diff:
-                self.changed_files = [f['filename'] for f in diff['files']]
+            if "files" in diff:
+                self.changed_files = [f["filename"] for f in diff["files"]]
         else:
             diff_object = PatchSet(response.text)
             self.changed_files = {f.path for f in diff_object}
 
     def get_dict(self):
         return {
-            'sha': self.sha,
-            'number': self.number,
-            'labels': self.labels,
-            'user_login': self.user_login,
-            'user_orgs': self.user_orgs,
+            "sha": self.sha,
+            "number": self.number,
+            "labels": self.labels,
+            "user_login": self.user_login,
+            "user_orgs": self.user_orgs,
         }
 
     def has_changes_in_documentation(self):
@@ -181,49 +226,63 @@ class PRInfo:
 
         for f in self.changed_files:
             _, ext = os.path.splitext(f)
-            path_in_docs = 'docs' in f
-            path_in_website = 'website' in f
-            if (ext in DIFF_IN_DOCUMENTATION_EXT and (path_in_docs or path_in_website)) or 'docker/docs' in f:
+            path_in_docs = "docs" in f
+            path_in_website = "website" in f
+            if (
+                ext in DIFF_IN_DOCUMENTATION_EXT and (path_in_docs or path_in_website)
+            ) or "docker/docs" in f:
                 return True
         return False
 
     def can_skip_builds_and_use_version_from_master(self):
-        if 'force tests' in self.labels:
+        # TODO: See a broken loop
+        if "force tests" in self.labels:
             return False
 
         if self.changed_files is None or not self.changed_files:
             return False
 
         for f in self.changed_files:
-            if (not f.startswith('tests/queries')
-                or not f.startswith('tests/integration')
-                or not f.startswith('tests/performance')):
+            # TODO: this logic is broken, should be fixed before using
+            if (
+                not f.startswith("tests/queries")
+                or not f.startswith("tests/integration")
+                or not f.startswith("tests/performance")
+            ):
                 return False
 
         return True
 
     def can_skip_integration_tests(self):
-        if 'force tests' in self.labels:
+        # TODO: See a broken loop
+        if "force tests" in self.labels:
             return False
 
         if self.changed_files is None or not self.changed_files:
             return False
 
         for f in self.changed_files:
-            if not f.startswith('tests/queries') or not f.startswith('tests/performance'):
+            # TODO: this logic is broken, should be fixed before using
+            if not f.startswith("tests/queries") or not f.startswith(
+                "tests/performance"
+            ):
                 return False
 
         return True
 
     def can_skip_functional_tests(self):
-        if 'force tests' in self.labels:
+        # TODO: See a broken loop
+        if "force tests" in self.labels:
             return False
 
         if self.changed_files is None or not self.changed_files:
             return False
 
         for f in self.changed_files:
-            if not f.startswith('tests/integration') or not f.startswith('tests/performance'):
+            # TODO: this logic is broken, should be fixed before using
+            if not f.startswith("tests/integration") or not f.startswith(
+                "tests/performance"
+            ):
                 return False
 
         return True

tests/ci/run_check.py

@@ -204,7 +204,7 @@ def check_pr_description(pr_info):
 if __name__ == "__main__":
     logging.basicConfig(level=logging.INFO)
 
-    pr_info = PRInfo(need_orgs=True, labels_from_api=True)
+    pr_info = PRInfo(need_orgs=True, pr_event_from_api=True)
     can_run, description = should_run_checks_for_pr(pr_info)
     gh = Github(get_best_robot_token())
     commit = get_commit(gh, pr_info.sha)
@@ -212,6 +212,9 @@ if __name__ == "__main__":
     description_report = check_pr_description(pr_info)[:139]
     if description_report:
         print("::notice ::Cannot run, description does not match the template")
+        logging.info(
+            "PR body doesn't match the template: (start)\n%s\n(end)", pr_info.body
+        )
         url = (
             f"{GITHUB_SERVER_URL}/{GITHUB_REPOSITORY}/"
             "blob/master/.github/PULL_REQUEST_TEMPLATE.md?plain=1"