Add code spell task, fix issues and run the task in CI (#1661)

dmathieu · mwear · web-flow · commit f9c86da5daf3 · 2024-08-14T10:57:40.000-07:00
* setup codespell

* fix all codespell issues

* add codespell github action

---------

Co-authored-by: Matthew Wear &lt;matthew.wear@gmail.com&gt;
diff --git a/.codespellignore b/.codespellignore
@@ -0,0 +1,2 @@
+ot
+te
diff --git a/.codespellrc b/.codespellrc
@@ -0,0 +1,10 @@
+# https://github.com/codespell-project/codespell
+[codespell]
+builtin = clear,rare,informal
+check-filenames =
+check-hidden =
+ignore-words = .codespellignore
+interactive = 1
+skip = .git,venv,coverage,doc,docs
+uri-ignore-words-list = *
+write =
diff --git a/.github/workflows/ci.yml b/.github/workflows/ci.yml
@@ -208,3 +208,9 @@ jobs:
         with:
           gem: "${{ matrix.gem }}"
           ruby: "truffleruby"
+
+  codespell:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+      - run: make codespell
diff --git a/.gitignore b/.gitignore
@@ -22,4 +22,7 @@
 # rbenv configuration
 .ruby-version
 
+# Python virtual env for codespell
+venv
+
 tags
diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -46,6 +46,6 @@ All notable changes to this project were documented in this file. This is of his
 
 * [#286](https://github.com/open-telemetry/opentelemetry-ruby/pull/286) Update Schedule. ([@fbogsany](https://github.com/fbogsany))
 
-* [#288](https://github.com/open-telemetry/opentelemetry-ruby/pull/288) Fix api/sdk gem install instuctions. ([@mwlang](https://github.com/mwlang))
+* [#288](https://github.com/open-telemetry/opentelemetry-ruby/pull/288) Fix api/sdk gem install instructions. ([@mwlang](https://github.com/mwlang))
 
 * [#294](https://github.com/open-telemetry/opentelemetry-ruby/pull/294) Add CHANGELOG. ([@ericmustin](https://github.com/ericmustin))
diff --git a/CONTRIBUTING.md b/CONTRIBUTING.md
@@ -154,7 +154,7 @@ to ensure that your code complies before opening a pull request.
 We also use Yard to generate class documentation automatically. Among other
 things, this means:
 
- *  Methods and arguments should include the appropraite type annotations
+ *  Methods and arguments should include the appropriate type annotations
  *  You can use markdown formatting in your documentation comments
 
 You can generate the docs locally to see the results, by running:
diff --git a/Makefile b/Makefile
@@ -0,0 +1,35 @@
+# Virtualized python tools via docker
+
+# The directory where the virtual environment is created.
+VENVDIR := venv
+
+PYTOOLS := $(VENVDIR)/bin
+
+# The pip executable in the virtual environment.
+PIP := $(PYTOOLS)/pip
+
+# The directory in the docker image where the current directory is mounted.
+WORKDIR := /workdir
+
+# The python image to use for the virtual environment.
+PYTHONIMAGE := python:3.11.3-slim-bullseye
+
+# Run the python image with the current directory mounted.
+DOCKERPY := docker run --rm -v "$(CURDIR):$(WORKDIR)" -w $(WORKDIR) $(PYTHONIMAGE)
+
+# Create a virtual environment for Python tools.
+$(PYTOOLS):
+# The `--upgrade` flag is needed to ensure that the virtual environment is
+# created with the latest pip version.
+	@$(DOCKERPY) bash -c "python3 -m venv $(VENVDIR) && $(PIP) install --upgrade pip"
+
+# Install python packages into the virtual environment.
+$(PYTOOLS)/%: $(PYTOOLS)
+	@$(DOCKERPY) $(PIP) install -r requirements.txt
+
+CODESPELL = $(PYTOOLS)/codespell
+$(CODESPELL): PACKAGE=codespell
+
+.PHONY: codespell
+codespell: $(CODESPELL)
+	@$(DOCKERPY) $(CODESPELL)
diff --git a/api/CHANGELOG.md b/api/CHANGELOG.md
@@ -71,7 +71,7 @@
 
 * BREAKING CHANGE: Remove optional parent_context from in_span [729](https://github.com/open-telemetry/opentelemetry-ruby/pull/729)
 * BREAKING CHANGE: Refactor Baggage to remove Noop* [800](https://github.com/open-telemetry/opentelemetry-ruby/pull/800)
-  - The noop baggage manger has been removed.
+  - The noop baggage manager has been removed.
   - The baggage management methods are now available through OpenTelemetry::Baggage#method, previously OpenTelemetry.baggage#method
 * BREAKING CHANGE: Total order constraint on span.status= [805](https://github.com/open-telemetry/opentelemetry-ruby/pull/805)
   - The OpenTelemetry::Trace::Util::HttpToStatus module has been removed as it was incorrectly setting the span status to OK for codes codes in the range 100..399
diff --git a/api/README.md b/api/README.md
@@ -12,7 +12,10 @@ OpenTelemetry provides a single set of APIs, libraries, agents, and collector se
 
 The `opentelemetry-api` gem defines the core OpenTelemetry interfaces in the form of abstract classes and no-op implementations. That is, it defines interfaces and data types sufficient for a library or application to code against to produce telemetry data, but does not actually collect, analyze, or export the data.
 
-To collect and analyze telemetry data, *applications* should also install a concrete implementation of the API, such as the `opentelemetry-sdk` gem. However, *libraries* that produce telemetry data should depend only on `opentelemetry-api`, deferring the choise of concrete implementation to the application developer.
+To collect and analyze telemetry data, *applications* should also
+install a concrete implementation of the API, such as the
+`opentelemetry-sdk` gem. However, *libraries* that produce telemetry
+data should depend only on `opentelemetry-api`, deferring the choice of concrete implementation to the application developer.
 
 ## How do I get started?
 
diff --git a/api/lib/opentelemetry/baggage.rb b/api/lib/opentelemetry/baggage.rb
@@ -73,7 +73,7 @@ def raw_entries(context: Context.current)
     # @param [String] key The key to store this value under
     # @param [String] value String value to be stored under key
     # @param [optional String] metadata This is here to store properties
-    #   received from other W3C Baggage impelmentations but is not exposed in
+    #   received from other W3C Baggage implementations but is not exposed in
     #   OpenTelemetry. This is condsidered private API and not for use by
     #   end-users.
     # @param [optional Context] context The context to update with new
diff --git a/api/lib/opentelemetry/baggage/builder.rb b/api/lib/opentelemetry/baggage/builder.rb
@@ -21,7 +21,7 @@ def initialize(entries)
       # @param [String] key The key to store this value under
       # @param [String] value String value to be stored under key
       # @param [optional String] metadata This is here to store properties
-      #   received from other W3C Baggage impelmentations but is not exposed in
+      #   received from other W3C Baggage implementations but is not exposed in
       #   OpenTelemetry. This is condsidered private API and not for use by
       #   end-users.
       def set_value(key, value, metadata: nil)
diff --git a/api/lib/opentelemetry/baggage/propagation/text_map_propagator.rb b/api/lib/opentelemetry/baggage/propagation/text_map_propagator.rb
@@ -100,7 +100,7 @@ def encode(baggage)
 
         def encode_value(key, entry)
           result = +"#{CGI.escape(key.to_s)}=#{CGI.escape(entry.value.to_s)}"
-          # We preserve metadata recieved on extract and assume it's already formatted
+          # We preserve metadata received on extract and assume it's already formatted
           # for transport. It's sent as-is without further processing.
           result << ";#{entry.metadata}" if entry.metadata
           result
diff --git a/api/lib/opentelemetry/trace/propagation/trace_context.rb b/api/lib/opentelemetry/trace/propagation/trace_context.rb
@@ -10,7 +10,7 @@
 module OpenTelemetry
   module Trace
     module Propagation
-      # The TraceContext module contains injectors, extractors, and utilties
+      # The TraceContext module contains injectors, extractors, and utilities
       # for context propagation in the W3C Trace Context format.
       module TraceContext
         extend self
diff --git a/api/lib/opentelemetry/trace/span_kind.rb b/api/lib/opentelemetry/trace/span_kind.rb
@@ -26,7 +26,7 @@ module SpanKind
       # spans.
       PRODUCER = :producer
 
-      # Indicates that the span describes consumer recieving a message from a broker. Unlike client
+      # Indicates that the span describes consumer receiving a message from a broker. Unlike client
       # and server, there is no direct critical path latency relationship between producer and
       # consumer spans.
       CONSUMER = :consumer
diff --git a/api/test/opentelemetry/context/propagation/text_map_getter_test.rb b/api/test/opentelemetry/context/propagation/text_map_getter_test.rb
@@ -20,7 +20,7 @@
       _(getter.get(carrier, 'x-source-id')).must_equal('123')
     end
 
-    it 'returns nil for non-existant key' do
+    it 'returns nil for non-existent key' do
       _(getter.get(carrier, 'not-here')).must_be_nil
     end
   end
diff --git a/api/test/opentelemetry/trace/propagation/trace_context/trace_parent_test.rb b/api/test/opentelemetry/trace/propagation/trace_context/trace_parent_test.rb
@@ -76,7 +76,7 @@
       _(tp.to_s).must_equal(expected)
     end
 
-    it 'must ignore flags it doesnt know (use the mask)' do
+    it 'must ignore flags it doesn\'t know (use the mask)' do
       value = '00-0000000000000000000000000000000a-000000000000000a-ff'
       assert TraceParent.from_string(value).sampled?
       value = '00-0000000000000000000000000000000a-000000000000000a-04'
diff --git a/exporter/jaeger/thrift/gen-rb/zipkincore_types.rb b/exporter/jaeger/thrift/gen-rb/zipkincore_types.rb
diff --git a/exporter/jaeger/thrift/zipkincore.thrift b/exporter/jaeger/thrift/zipkincore.thrift
@@ -292,7 +292,7 @@ struct Span {
   3: string name,
   4: i64 id,                       # unique span id, only used for this span
   5: optional i64 parent_id,       # parent span id
-  6: list<Annotation> annotations, # all annotations/events that occured, sorted by timestamp
+  6: list<Annotation> annotations, # all annotations/events that occurred, sorted by timestamp
   8: list<BinaryAnnotation> binary_annotations # any binary annotations
   9: optional bool debug = 0       # if true, we DEMAND that this span passes all samplers
   /**
@@ -302,7 +302,7 @@ struct Span {
    * precise value possible. For example, gettimeofday or syncing nanoTime
    * against a tick of currentTimeMillis.
    *
-   * For compatibilty with instrumentation that precede this field, collectors
+   * For compatibility with instrumentation that precede this field, collectors
    * or span stores can derive this via Annotation.timestamp.
    * For example, SERVER_RECV.timestamp or CLIENT_SEND.timestamp.
    *
@@ -317,7 +317,7 @@ struct Span {
    * precise measurement decoupled from problems of clocks, such as skew or NTP
    * updates causing time to move backwards.
    *
-   * For compatibilty with instrumentation that precede this field, collectors
+   * For compatibility with instrumentation that precede this field, collectors
    * or span stores can derive this by subtracting Annotation.timestamp.
    * For example, SERVER_SEND.timestamp - SERVER_RECV.timestamp.
    *
diff --git a/exporter/otlp-metrics/README.md b/exporter/otlp-metrics/README.md
@@ -122,7 +122,7 @@ The `opentelemetry-exporter-otlp-metrics` gem is distributed under the Apache 2.
 
 ## Working with Proto Definitions
 
-The OTel community maintains a [repository with protobuf definitions][otel-proto-github] that language and collector implementors use to generate code.
+The OTel community maintains a [repository with protobuf definitions][otel-proto-github] that language and collector implementers use to generate code.
 
 Maintainers are expected to keep up to date with the latest version of protos. This guide will provide you with step-by-step instructions on updating the OTLP Exporter gem with the latest definitions.
 
diff --git a/exporter/otlp/README.md b/exporter/otlp/README.md
@@ -99,7 +99,7 @@ The `opentelemetry-exporter-otlp` gem is distributed under the Apache 2.0 licens
 
 ## Working with Proto Definitions
 
-The OTel community maintains a [repository with protobuf definitions][otel-proto-github] that language and collector implementors use to generate code.
+The OTel community maintains a [repository with protobuf definitions][otel-proto-github] that language and collector implementers use to generate code.
 
 Maintainers are expected to keep up to date with the latest version of protos. This guide will provide you with step-by-step instructions on updating the OTLP Exporter gem with the latest definitions.
 
@@ -138,7 +138,7 @@ $> bundle exec rake test
 
 ```
 
-**Commit the chnages and open a PR!**
+**Commit the changes and open a PR!**
 
 [opentelemetry-collector-home]: https://opentelemetry.io/docs/collector/about/
 [opentelemetry-home]: https://opentelemetry.io
diff --git a/exporter/zipkin/lib/opentelemetry/exporter/zipkin/exporter.rb b/exporter/zipkin/lib/opentelemetry/exporter/zipkin/exporter.rb
@@ -135,7 +135,7 @@ def send_spans(zipkin_spans, timeout: nil) # rubocop:disable Metrics/MethodLengt
 
             response = measure_request_duration { @http.request(request) }
             response.body # Read and discard body
-            # in opentelemetry-js 200-399 is succcess, in opentelemetry-collector zipkin exporter,200-299 is a success
+            # in opentelemetry-js 200-399 is success, in opentelemetry-collector zipkin exporter,200-299 is a success
             # zipkin api docs list 202 as default success code
             # https://zipkin.io/zipkin-api/#/default/post_spans
             # TODO: redirect
diff --git a/exporter/zipkin/lib/opentelemetry/exporter/zipkin/transformer.rb b/exporter/zipkin/lib/opentelemetry/exporter/zipkin/transformer.rb
@@ -50,7 +50,7 @@ def to_zipkin_span(span_d, resource)
           add_status_tags(span_d, tags)
           tags = aggregate_span_tags(span_d, tags)
 
-          # TOOO: set debug flag? (is that represented in tracestate?)
+          # TODO: set debug flag? (is that represented in tracestate?)
           # https://github.com/openzipkin/b3-propagation#why-is-debug-encoded-as-x-b3-flags-1
           # https://github.com/openzipkin/zipkin-api/blob/7692ca7be4dc3be9225db550d60c4d30e6e9ec59/zipkin2-api.yaml#L475
           # TODO: shared key mapping
diff --git a/logs_sdk/lib/opentelemetry/sdk/logs/log_record.rb b/logs_sdk/lib/opentelemetry/sdk/logs/log_record.rb
@@ -45,7 +45,7 @@ class LogRecord < OpenTelemetry::Logs::LogRecord
         #   current context.
         # @param [optional OpenTelemetry::Trace::TraceFlags] trace_flags The
         #   trace flags associated with the current context.
-        # @param [optional OpenTelemetry::SDK::Resources::Resource] recource The
+        # @param [optional OpenTelemetry::SDK::Resources::Resource] resource The
         #   source of the log, desrived from the LoggerProvider.
         # @param [optional OpenTelemetry::SDK::InstrumentationScope] instrumentation_scope
         #   The instrumentation scope, derived from the emitting Logger
diff --git a/metrics_api/README.md b/metrics_api/README.md
@@ -12,7 +12,11 @@ OpenTelemetry provides a single set of APIs, libraries, agents, and collector se
 
 The `opentelemetry-metrics-api` gem defines the core OpenTelemetry interfaces in the form of abstract classes and no-op implementations. That is, it defines interfaces and data types sufficient for a library or application to code against to produce telemetry data, but does not actually collect, analyze, or export the data.
 
-To collect and analyze telemetry data, _applications_ should also install a concrete implementation of the API, such as the `opentelemetry-metrics-sdk` gem. However, _libraries_ that produce telemetry data should depend only on `opentelemetry-metrics-api`, deferring the choise of concrete implementation to the application developer.
+To collect and analyze telemetry data, _applications_ should also
+install a concrete implementation of the API, such as the
+`opentelemetry-metrics-sdk` gem. However, _libraries_ that produce
+telemetry data should depend only on `opentelemetry-metrics-api`,
+deferring the choice of concrete implementation to the application developer.
 
 This code is still under development and is not a complete implementation of the Metrics API. Until the code becomes stable, Metrics API functionality will live outside the `opentelemetry-api` library.
 
diff --git a/metrics_api/test/opentelemetry/opentelemetry_test.rb b/metrics_api/test/opentelemetry/opentelemetry_test.rb
@@ -8,7 +8,7 @@
 
 describe OpenTelemetry do
   after do
-    # TODO: After Metrics SDK is incoporated into OpenTelemetry SDK, move this
+    # TODO: After Metrics SDK is incorporated into OpenTelemetry SDK, move this
     # to OpenTelemetry::TestHelpers.reset_opentelemetry
     OpenTelemetry.instance_variable_set(
       :@meter_provider,
diff --git a/propagator/b3/CHANGELOG.md b/propagator/b3/CHANGELOG.md
@@ -24,7 +24,7 @@
 
 ### v0.18.0 / 2021-05-21
 
-* ADDED: Updated API depedency for 1.0.0.rc1
+* ADDED: Updated API dependency for 1.0.0.rc1
 
 ### v0.17.0 / 2021-04-22
 
diff --git a/propagator/jaeger/CHANGELOG.md b/propagator/jaeger/CHANGELOG.md
@@ -39,7 +39,7 @@
 
 ### v0.18.0 / 2021-05-21
 
-* ADDED: Updated API depedency for 1.0.0.rc1
+* ADDED: Updated API dependency for 1.0.0.rc1
 
 ### v0.17.0 / 2021-04-22
 
diff --git a/registry/CHANGELOG.md b/registry/CHANGELOG.md
@@ -12,7 +12,7 @@
 
 ### v0.2.0 / 2022-09-14
 
-* Bump minimum API version depedency to 1.1
+* Bump minimum API version dependency to 1.1
 
 ### v0.1.0 / 2022-04-11
 
diff --git a/registry/lib/opentelemetry/instrumentation/registry.rb b/registry/lib/opentelemetry/instrumentation/registry.rb
@@ -9,7 +9,7 @@ module Instrumentation
     # The instrumentation Registry contains information about instrumentation
     # available and facilitates discovery, installation and
     # configuration. This functionality is primarily useful for SDK
-    # implementors.
+    # implementers.
     class Registry
       def initialize
         @lock = Mutex.new
diff --git a/requirements.txt b/requirements.txt
@@ -0,0 +1 @@
+codespell==2.3.0
diff --git a/sdk/README.md b/sdk/README.md
@@ -12,7 +12,13 @@ OpenTelemetry provides a single set of APIs, libraries, agents, and collector se
 
 The `opentelemetry-sdk` gem provides the reference implementation of the OpenTelemetry Ruby interfaces defined in the `opentelemetry-api` gem. That is, it includes the *functionality* needed to collect, analyze, and export telemetry data produced using the API.
 
-Generally, Ruby *applications* should install `opentelemetry-sdk` (or other concrete implementation of the OpenTelemetry API). Using the SDK, an application can configure how it wants telemetry data to be handled, including which data should be persisted, how it should be formatted, and where it should be recorded or exported. However, *libraries* that produce telemetry data should generally depend only on `opentelemetry-api`, deferring the choise of concrete implementation to the application developer.
+Generally, Ruby *applications* should install `opentelemetry-sdk` (or
+other concrete implementation of the OpenTelemetry API). Using the SDK,
+an application can configure how it wants telemetry data to be handled,
+including which data should be persisted, how it should be formatted,
+and where it should be recorded or exported. However, *libraries* that
+produce telemetry data should generally depend only on
+`opentelemetry-api`, deferring the choice of concrete implementation to the application developer.
 
 ## How do I get started?
 
diff --git a/sdk/lib/opentelemetry/sdk/configurator.rb b/sdk/lib/opentelemetry/sdk/configurator.rb
@@ -90,7 +90,7 @@ def service_version=(service_version)
         )
       end
 
-      # Install an instrumentation with specificied optional +config+.
+      # Install an instrumentation with specified optional +config+.
       # Use can be called multiple times to install multiple instrumentation.
       # Only +use+ or +use_all+, but not both when installing
       # instrumentation. A call to +use_all+ after +use+ will result in an
diff --git a/sdk/opentelemetry-sdk.gemspec b/sdk/opentelemetry-sdk.gemspec
@@ -31,7 +31,7 @@ Gem::Specification.new do |spec|
 
   # This is an intentionally loose dependency, since we want to be able to
   # release new versions of opentelemetry-semantic_conventions without requiring
-  # a new SDK release. The requirements of the SDK have been satisifed since the
+  # a new SDK release. The requirements of the SDK have been satisfied since the
   # initial release of opentelemetry-semantic_conventions, so we feel it is safe.
   spec.add_dependency 'opentelemetry-semantic_conventions'
 
diff --git a/sdk/test/opentelemetry/sdk/configurator_test.rb b/sdk/test/opentelemetry/sdk/configurator_test.rb
@@ -292,7 +292,7 @@
         )
       end
 
-      it 'accepts comma separated list with preceeding or trailing spaces as an environment variable' do
+      it 'accepts comma separated list with preceding or trailing spaces as an environment variable' do
         OpenTelemetry::TestHelpers.with_env('OTEL_TRACES_EXPORTER' => 'zipkin , console') do
           configurator.configure
         end
diff --git a/sdk/test/opentelemetry/sdk/trace/export/in_memory_span_exporter_test.rb b/sdk/test/opentelemetry/sdk/trace/export/in_memory_span_exporter_test.rb
@@ -23,7 +23,7 @@
   end
 
   it 'accepts an Enumerable of SpanDatas as argument to #export' do
-    # An anonymous Struct serves as a handy implementor of Enumerable
+    # An anonymous Struct serves as a handy implementer of Enumerable
     enumerable = Struct.new(:span_data1, :span_data2).new
     enumerable.span_data1 = span_data1
     enumerable.span_data2 = span_data2
diff --git a/sdk/test/opentelemetry/sdk/trace/span_limits_test.rb b/sdk/test/opentelemetry/sdk/trace/span_limits_test.rb
@@ -20,7 +20,7 @@
       _(span_limits.link_attribute_count_limit).must_equal 128
     end
 
-    it 'prioritizes specific environment varibles for attribute value length limits' do
+    it 'prioritizes specific environment variables for attribute value length limits' do
       OpenTelemetry::TestHelpers.with_env('OTEL_ATTRIBUTE_VALUE_LENGTH_LIMIT' => '35',
                                           'OTEL_SPAN_ATTRIBUTE_VALUE_LENGTH_LIMIT' => '33',
                                           'OTEL_EVENT_ATTRIBUTE_VALUE_LENGTH_LIMIT' => '32') do
diff --git a/semantic_conventions/lib/opentelemetry/semantic_conventions/resource.rb b/semantic_conventions/lib/opentelemetry/semantic_conventions/resource.rb
