Merge pull request #13513 from ClickHouse/codespell-2

Enable codespell

benchmark/monetdb/usability.md

@@ -2,7 +2,7 @@ Go to https://www.monetdb.org/
 
 The graphical design of the website is a bit old-fashioned but I do not afraid.
 
-Dowload now.
+Download now.
 Latest binary releases.
 Ubuntu & Debian.
 
@@ -1103,7 +1103,7 @@ Ok, it's doing something at least for twenty minues...
 clk: 28:02 min
 ```
 
-Finally it has loaded data successfuly in 28 minutes. It's not fast - just below 60 000 rows per second.
+Finally it has loaded data successfully in 28 minutes. It's not fast - just below 60 000 rows per second.
 
 But the second query from the test does not work:
 

docker/test/style/Dockerfile

@@ -1,7 +1,7 @@
-# docker build -t yandex/clickhouse-style-test . 
+# docker build -t yandex/clickhouse-style-test .
 FROM ubuntu:20.04
 
-RUN apt-get update && env DEBIAN_FRONTEND=noninteractive apt-get install --yes shellcheck libxml2-utils git
+RUN apt-get update && env DEBIAN_FRONTEND=noninteractive apt-get install --yes shellcheck libxml2-utils git python3-pip && pip3 install codespell
 
 
 CMD cd /ClickHouse/utils/check-style && ./check-style -n | tee /test_output/style_output.txt && \

programs/server/Server.cpp

@@ -356,7 +356,7 @@ int Server::main(const std::vector<std::string> & /*args*/)
     std::string path = getCanonicalPath(config().getString("path", DBMS_DEFAULT_PATH));
     std::string default_database = config().getString("default_database", "default");
 
-    /// Check that the process' user id matches the owner of the data.
+    /// Check that the process user id matches the owner of the data.
     const auto effective_user_id = geteuid();
     struct stat statbuf;
     if (stat(path.c_str(), &statbuf) == 0 && effective_user_id != statbuf.st_uid)

src/Common/tests/gtest_thread_pool_schedule_exception.cpp

@@ -20,7 +20,7 @@ static bool check()
             /// as soon as the throwing thread executed.
 
             /// This innocent thread may or may not be executed, the following possibilities exist:
-            /// 1. The throwing thread has already throwed exception and the attempt to schedule the innocent thread will rethrow it.
+            /// 1. The throwing thread has already thrown exception and the attempt to schedule the innocent thread will rethrow it.
             /// 2. The throwing thread has not executed, the innocent thread will be scheduled and executed.
             /// 3. The throwing thread has not executed, the innocent thread will be scheduled but before it will be executed,
             ///    the throwing thread will be executed and throw exception and it will prevent starting of execution of the innocent thread

src/Processors/Pipe.cpp

@@ -74,7 +74,7 @@ static OutputPort * uniteTotals(const OutputPortRawPtrs & ports, const Block & h
     if (ports.size() == 1)
         return ports.front();
 
-    /// Calculate totals fro several streams.
+    /// Calculate totals from several streams.
     /// Take totals from first sources which has any, skip others.
 
     /// ->> Concat -> Limit

utils/check-style/check-style

@@ -69,6 +69,10 @@ find $ROOT_PATH -name '.gitmodules' | while read i; do grep -F 'url = ' $i | gre
 # There shouldn't be any code snippets under GPL or LGPL
 find $ROOT_PATH/{src,base,programs} -name '*.h' -or -name '*.cpp' 2>/dev/null | xargs grep -i -F 'General Public License' && echo "There shouldn't be any code snippets under GPL or LGPL"
 
+# Check for typos in code
+CURDIR=$(dirname "${BASH_SOURCE[0]}")
+"${CURDIR}"/check-typos
+
 # Check sh tests with Shellcheck
 (cd $ROOT_PATH/tests/queries/0_stateless/ && shellcheck --check-sourced --external-sources --severity info --exclude SC1071,SC2086 *.sh ../1_stateful/*.sh)
 

utils/check-style/check-typos

@@ -0,0 +1,15 @@
+#!/usr/bin/env bash
+
+# Check for typos in code.
+
+ROOT_PATH=$(git rev-parse --show-toplevel)
+CURDIR=$(dirname "${BASH_SOURCE[0]}")
+
+codespell \
+    --skip '*generated*,*gperf*,*.bin,*.mrk*,*.idx,checksums.txt,*.dat,*.pyc,*.kate-swp' \
+    --ignore-words "${CURDIR}/codespell-ignore-words.list" \
+    --exclude-file "${CURDIR}/codespell-ignore-lines.list" \
+    --quiet-level 2 \
+    "$ROOT_PATH"/{src,base,programs,utils} \
+    $@ | grep -P '.' \
+    && echo -e "\nFound some typos in code.\nSee the files utils/check-style/codespell* if you want to add an exception."

utils/check-style/codespell-ignore-lines.list

@@ -0,0 +1,6 @@
+/// https://groups.google.com/forum/#!searchin/kona-dev/variadic$20macro%7Csort:date/kona-dev/XMA-lDOqtlI/GCzdfZsD41sJ
+Jo-Philipp Wich
+The TRE regular expression implementation (src/regex/reg* and
+src/regex/tre*) is Copyright © 2001-2008 Ville Laurikari and licensed
+                pullRequests(first: {min_page_size} baseRefName: "{base}" headRefName: "{head}") {{
+    uint64_t time_to_wait = nanoseconds * timebase_info.denom / timebase_info.numer;

utils/check-style/codespell-ignore-words.list

@@ -0,0 +1,7 @@
+thenn
+fpr
+creat
+parsering
+nd
+ect
+pullrequest