style: Add typos pre-commit hook (#2041)

Author: mathbunnyru

.cmake-format.yaml

@@ -115,7 +115,7 @@ format:
   _help_require_valid_layout:
     - By default, if cmake-format cannot successfully fit
     - everything into the desired linewidth it will apply the
-    - last, most agressive attempt that it made. If this flag is
+    - last, most aggressive attempt that it made. If this flag is
     - True, however, cmake-format will print error, exit with non-
     - zero status code, and write-out nothing
   require_valid_layout: false
@@ -152,7 +152,7 @@ markup:
   ruler_pattern: ^\s*[^\w\s]{3}.*[^\w\s]{3}$
   _help_explicit_trailing_pattern:
     - If a comment line matches starts with this pattern then it
-    - is explicitly a trailing comment for the preceeding
+    - is explicitly a trailing comment for the preceding
     - argument. Default is '#<'
   explicit_trailing_pattern: "#<"
   _help_hashruler_min_length:

.githooks/check-docs

@@ -2,7 +2,7 @@
 
 # Note: This script is intended to be run from the root of the repository.
 #
-# Not really a hook but should be used to check the completness of documentation for added code, otherwise CI will come for you.
+# Not really a hook but should be used to check the completeness of documentation for added code, otherwise CI will come for you.
 # It's good to have /tmp as the output so that consecutive runs are fast but no clutter in the repository.
 
 echo "+ Checking documentation..."

.github/actions/build_clio/action.yml

@@ -4,7 +4,7 @@ inputs:
   target:
     description: Build target name
     default: all
-  substract_threads:
+  subtract_threads:
     description: An option for the action get_number_of_threads. See get_number_of_threads
     required: true
     default: "0"
@@ -15,7 +15,7 @@ runs:
       uses: ./.github/actions/get_number_of_threads
       id: number_of_threads
       with:
-        substract_threads: ${{ inputs.substract_threads }}
+        subtract_threads: ${{ inputs.subtract_threads }}
 
     - name: Build Clio
       shell: bash

.github/actions/get_number_of_threads/action.yml

@@ -1,8 +1,8 @@
 name: Get number of threads
 description: Determines number of threads to use on macOS and Linux
 inputs:
-  substract_threads:
-    description: How many threads to substract from the calculated number
+  subtract_threads:
+    description: How many threads to subtract from the calculated number
     required: true
     default: "0"
 outputs:
@@ -29,6 +29,6 @@ runs:
       shell: bash
       run: |
         num_of_threads=${{ steps.mac_threads.outputs.num || steps.linux_threads.outputs.num }}
-        shift_by=${{ inputs.substract_threads }}
+        shift_by=${{ inputs.subtract_threads }}
         shifted=$((num_of_threads - shift_by))
         echo "num=$(( shifted > 1 ? shifted : 1 ))" >> $GITHUB_OUTPUT

.pre-commit-config.yaml

@@ -45,3 +45,8 @@ repos:
     hooks:
       - id: markdownlint-fix
         exclude: LICENSE.md
+
+  - repo: https://github.com/crate-ci/typos
+    rev: v1.31.2
+    hooks:
+      - id: typos

_typos.toml

@@ -0,0 +1,22 @@
+[default]
+# This allows to ignore account ids in tests and private keys
+# More info: https://github.com/crate-ci/typos/issues/415
+extend-ignore-re = [
+    "[a-z-A-Z0-9]{33}",
+    "[a-z-A-Z0-9]{34}",
+    "[a-z-A-Z0-9]{64}",
+]
+
+[default.extend-identifiers]
+# (S)tring
+tring = "tring"
+trings = "trings"
+
+ASSERTs = "ASSERTs"
+EXCLUDEs = "EXCLUDEs"
+
+ser = "ser"
+
+[default.extend-words]
+strat = "strat"
+datas = "datas"

docs/examples/infrastructure/grafana/clio_dashboard.json

@@ -1398,7 +1398,7 @@
           "refId": "B"
         }
       ],
-      "title": "DB Opperations Error Rate",
+      "title": "DB Operations Error Rate",
       "type": "timeseries"
     },
     {

docs/trouble_shooting.md

@@ -33,7 +33,7 @@ If you see the error log message `Failed to fetch ETL state from...`, this means
 - Make sure the rippled node is running at the specified address and port.
 - Make sure the rippled node is accessible from the machine where Clio is running.
 
-If you would like to run Clio without an avaliable rippled node, you can add below setting to Clio's configuration file:
+If you would like to run Clio without an available rippled node, you can add below setting to Clio's configuration file:
 
 ```text
 "allow_no_etl": true
@@ -53,7 +53,7 @@ curl -v -d '{"method":"server_info", "params":[{}]}' 127.0.0.1:51233|python3 -m
 curl -v -d '{"method":"server_info", "params":[{}]}' 127.0.0.1:51233|python3 -m json.tool|grep is_enabled
 ```
 
-If `is_full` is false, it means the cache is still loading. Normally, the Clio can respond quicker if cache finishs loading. If `is_enabled` is false, it means the cache is disabled in the configuration file or there is data corruption in the database.
+If `is_full` is false, it means the cache is still loading. Normally, the Clio can respond quicker if cache finishes loading. If `is_enabled` is false, it means the cache is disabled in the configuration file or there is data corruption in the database.
 
 ## Receive error message `Too many requests`
 

src/cluster/ClusterCommunicationService.hpp

@@ -50,7 +50,7 @@ class ClusterCommunicationService : public ClusterCommunicationServiceInterface
     util::prometheus::Bool isHealthy_ = PrometheusService::boolMetric(
         "cluster_communication_is_healthy",
         {},
-        "Whether cluster communicaton service is operating healthy (1 - healthy, 0 - we have a problem)"
+        "Whether cluster communication service is operating healthy (1 - healthy, 0 - we have a problem)"
     );
 
     // TODO: Use util::async::CoroExecutionContext after https://github.com/XRPLF/clio/issues/1973 is implemented

src/data/BackendInterface.cpp

@@ -61,7 +61,7 @@ BackendInterface::finishWrites(std::uint32_t const ledgerSequence)
     LOG(gLog.debug()) << "Want finish writes for " << ledgerSequence;
     auto commitRes = doFinishWrites();
     if (commitRes) {
-        LOG(gLog.debug()) << "Successfully commited. Updating range now to " << ledgerSequence;
+        LOG(gLog.debug()) << "Successfully committed. Updating range now to " << ledgerSequence;
         updateRange(ledgerSequence);
     }
     return commitRes;
@@ -246,7 +246,7 @@ BackendInterface::fetchBookOffers(
     auto end = std::chrono::system_clock::now();
     LOG(gLog.debug()) << "Fetching " << std::to_string(keys.size()) << " offers took "
                       << std::to_string(getMillis(mid - begin)) << " milliseconds. Fetching next dir took "
-                      << std::to_string(succMillis) << " milliseonds. Fetched next dir " << std::to_string(numSucc)
+                      << std::to_string(succMillis) << " milliseconds. Fetched next dir " << std::to_string(numSucc)
                       << " times"
                       << " Fetching next page of dir took " << std::to_string(pageMillis) << " milliseconds"
                       << ". num pages = " << std::to_string(numPages) << ". Fetching all objects took "

src/data/BackendInterface.hpp

@@ -69,7 +69,7 @@ class DatabaseTimeout : public std::exception {
 
 static constexpr std::size_t kDEFAULT_WAIT_BETWEEN_RETRY = 500;
 /**
- * @brief A helper function that catches DatabaseTimout exceptions and retries indefinitely.
+ * @brief A helper function that catches DatabaseTimeout exceptions and retries indefinitely.
  *
  * @tparam FnType The type of function object to execute
  * @param func The function object to execute
@@ -398,7 +398,7 @@ class BackendInterface {
      * @brief Fetches a specific ledger object.
      *
      * Currently the real fetch happens in doFetchLedgerObject and fetchLedgerObject attempts to fetch from Cache first
-     * and only calls out to the real DB if a cache miss ocurred.
+     * and only calls out to the real DB if a cache miss occurred.
      *
      * @param key The key of the object
      * @param sequence The ledger sequence to fetch for
@@ -512,7 +512,7 @@ class BackendInterface {
      * @param key The key to fetch for
      * @param ledgerSequence The ledger sequence to fetch for
      * @param yield The coroutine context
-     * @return The sucessor on success; nullopt otherwise
+     * @return The successor on success; nullopt otherwise
      */
     std::optional<LedgerObject>
     fetchSuccessorObject(ripple::uint256 key, std::uint32_t ledgerSequence, boost::asio::yield_context yield) const;
@@ -526,7 +526,7 @@ class BackendInterface {
      * @param key The key to fetch for
      * @param ledgerSequence The ledger sequence to fetch for
      * @param yield The coroutine context
-     * @return The sucessor key on success; nullopt otherwise
+     * @return The successor key on success; nullopt otherwise
      */
     std::optional<ripple::uint256>
     fetchSuccessorKey(ripple::uint256 key, std::uint32_t ledgerSequence, boost::asio::yield_context yield) const;
@@ -537,7 +537,7 @@ class BackendInterface {
      * @param key The key to fetch for
      * @param ledgerSequence The ledger sequence to fetch for
      * @param yield The coroutine context
-     * @return The sucessor on success; nullopt otherwise
+     * @return The successor on success; nullopt otherwise
      */
     virtual std::optional<ripple::uint256>
     doFetchSuccessorKey(ripple::uint256 key, std::uint32_t ledgerSequence, boost::asio::yield_context yield) const = 0;

src/data/CassandraBackend.hpp

@@ -780,7 +780,7 @@ class BasicCassandraBackend : public BackendInterface {
 
         while (liveAccounts.size() < number) {
             Statement const statement = lastItem ? schema_->selectAccountFromToken.bind(*lastItem, Limit{pageSize})
-                                                 : schema_->selectAccountFromBegining.bind(Limit{pageSize});
+                                                 : schema_->selectAccountFromBeginning.bind(Limit{pageSize});
 
             auto const res = executor_.read(yield, statement);
             if (res) {

src/data/LedgerCache.cpp

@@ -63,7 +63,7 @@ LedgerCache::update(std::vector<LedgerObject> const& objs, uint32_t seq, bool is
         if (seq > latestSeq_) {
             ASSERT(
                 seq == latestSeq_ + 1 || latestSeq_ == 0,
-                "New sequense must be either next or first. seq = {}, latestSeq_ = {}",
+                "New sequence must be either next or first. seq = {}, latestSeq_ = {}",
                 seq,
                 latestSeq_
             );

src/data/README.md

@@ -162,7 +162,7 @@ This table stores the list of transactions affecting a given account. This inclu
 ```sql
 CREATE TABLE clio.successor (
  key blob,    # Object index
- seq bigint,  # The sequnce that this ledger object's predecessor and successor was updated
+ seq bigint,  # The sequence that this ledger object's predecessor and successor was updated
  next blob,   # Index of the next object that existed in this sequence
  PRIMARY KEY (key, seq)
 ) WITH CLUSTERING ORDER BY (seq ASC) ...

src/data/cassandra/Handle.hpp

@@ -89,7 +89,7 @@ class Handle {
     asyncConnect() const;
 
     /**
-     * @brief Synchonous version of the above.
+     * @brief Synchronous version of the above.
      *
      * See @ref asyncConnect() const for how this works.
      *
@@ -108,7 +108,7 @@ class Handle {
     asyncConnect(std::string_view keyspace) const;
 
     /**
-     * @brief Synchonous version of the above.
+     * @brief Synchronous version of the above.
      *
      * See @ref asyncConnect(std::string_view) const for how this works.
      *
@@ -127,7 +127,7 @@ class Handle {
     asyncDisconnect() const;
 
     /**
-     * @brief Synchonous version of the above.
+     * @brief Synchronous version of the above.
      *
      * See @ref asyncDisconnect() const for how this works.
      *
@@ -146,7 +146,7 @@ class Handle {
     asyncReconnect(std::string_view keyspace) const;
 
     /**
-     * @brief Synchonous version of the above.
+     * @brief Synchronous version of the above.
      *
      * See @ref asyncReconnect(std::string_view) const for how this works.
      *
@@ -172,7 +172,7 @@ class Handle {
     }
 
     /**
-     * @brief Synchonous version of the above.
+     * @brief Synchronous version of the above.
      *
      * See asyncExecute(std::string_view, Args&&...) const for how this works.
      *
@@ -201,7 +201,7 @@ class Handle {
     asyncExecuteEach(std::vector<StatementType> const& statements) const;
 
     /**
-     * @brief Synchonous version of the above.
+     * @brief Synchronous version of the above.
      *
      * See @ref asyncExecuteEach(std::vector<StatementType> const&) const for how this works.
      *
@@ -227,7 +227,7 @@ class Handle {
     }
 
     /**
-     * @brief Synchonous version of the above.
+     * @brief Synchronous version of the above.
      *
      * See asyncExecute(std::vector<StatementType> const&, Args&&...) const for how this works.
      *
@@ -262,7 +262,7 @@ class Handle {
     asyncExecute(StatementType const& statement, std::function<void(ResultOrErrorType)>&& cb) const;
 
     /**
-     * @brief Synchonous version of the above.
+     * @brief Synchronous version of the above.
      *
      * See @ref asyncExecute(StatementType const&) const for how this works.
      *
@@ -282,7 +282,7 @@ class Handle {
     asyncExecute(std::vector<StatementType> const& statements) const;
 
     /**
-     * @brief Synchonous version of the above.
+     * @brief Synchronous version of the above.
      *
      * See @ref asyncExecute(std::vector<StatementType> const&) const for how this works.
      *

src/data/cassandra/Schema.hpp

@@ -633,7 +633,7 @@ class Schema {
             ));
         }();
 
-        PreparedStatement selectAccountFromBegining = [this]() {
+        PreparedStatement selectAccountFromBeginning = [this]() {
             return handle_.get().prepare(fmt::format(
                 R"(
                 SELECT account

src/data/cassandra/impl/AsyncExecutor.hpp

@@ -38,7 +38,7 @@
 namespace data::cassandra::impl {
 
 /**
- * @brief A query executor with a changable retry policy
+ * @brief A query executor with a changeable retry policy
  *
  * Note: this is a bit of an anti-pattern and should be done differently
  * eventually.

src/data/cassandra/impl/ExecutionStrategy.hpp

@@ -267,7 +267,7 @@ class DefaultExecutionStrategy {
     }
 
     /**
-     * @brief Non-blocking  query execution used for writing data. Constrast with write, this method does not execute
+     * @brief Non-blocking  query execution used for writing data. Contrast with write, this method does not execute
      * the statements in a batch.
      *
      * Retries forever with retry policy specified by @ref AsyncExecutor.

src/etl/ETLHelpers.hpp

@@ -143,7 +143,7 @@ class ThreadSafeQueue {
 };
 
 /**
- * @brief Parititions the uint256 keyspace into numMarkers partitions, each of equal size.
+ * @brief Partitions the uint256 keyspace into numMarkers partitions, each of equal size.
  *
  * @param numMarkers Total markers to partition for
  * @return The markers

src/etl/ETLService.cpp

@@ -100,7 +100,7 @@ ETLService::runETLPipeline(uint32_t startSequence, uint32_t numExtractors)
 }
 
 // Main loop of ETL.
-// The software begins monitoring the ledgers that are validated by the nework.
+// The software begins monitoring the ledgers that are validated by the network.
 // The member networkValidatedLedgers_ keeps track of the sequences of ledgers validated by the network.
 // Whenever a ledger is validated by the network, the software looks for that ledger in the database. Once the ledger is
 // found in the database, the software publishes that ledger to the ledgers stream. If a network validated ledger is not

src/etl/ETLService.hpp

@@ -340,7 +340,7 @@ class ETLService : public etlng::ETLServiceInterface, ETLServiceTag {
     /**
      * @brief Get the number of markers to use during the initial ledger download.
      *
-     * This is equivelent to the degree of parallelism during the initial ledger download.
+     * This is equivalent to the degree of parallelism during the initial ledger download.
      *
      * @return The number of markers
      */

src/etl/LedgerFetcherInterface.hpp

@@ -40,7 +40,7 @@ struct LedgerFetcherInterface {
     /**
      * @brief Extract data for a particular ledger from an ETL source
      *
-     * This function continously tries to extract the specified ledger (using all available ETL sources) until the
+     * This function continuously tries to extract the specified ledger (using all available ETL sources) until the
      * extraction succeeds, or the server shuts down.
      *
      * @param seq sequence of the ledger to extract
@@ -52,7 +52,7 @@ struct LedgerFetcherInterface {
     /**
      * @brief Extract diff data for a particular ledger from an ETL source.
      *
-     * This function continously tries to extract the specified ledger (using all available ETL sources) until the
+     * This function continuously tries to extract the specified ledger (using all available ETL sources) until the
      * extraction succeeds, or the server shuts down.
      *
      * @param seq sequence of the ledger to extract

src/etl/impl/ExtractionDataPipe.hpp

@@ -66,7 +66,7 @@ class ExtractionDataPipe {
     /**
      * @brief Push new data package for the specified sequence.
      *
-     * Note: Potentially blocks until the underlying queue can accomodate another entry.
+     * Note: Potentially blocks until the underlying queue can accommodate another entry.
      *
      * @param sequence The sequence for which to enqueue the data package
      * @param data The data to store