[infra] Move en words into separate word list, set up lists for es and pt (#5011)

Author: chalin

.cspell.yml

@@ -12,9 +12,6 @@ ignorePaths:
   - vendors.yaml
   - content/ja
   - content/zh
-# words here are only listed for their spelling, if there is a certain way
-# to write a word (e.g. OpenTelemetry vs Opentelemetry or cloud native vs
-# cloud-native), edit the text-lint rules in .textlintrc.yml
 patterns:
   - name: CodeBlock
     pattern: |
@@ -28,140 +25,26 @@ languageSettings:
   - languageId: markdown
     ignoreRegExpList:
       - CodeBlock
+dictionaryDefinitions:
+  - name: en-words
+    path: .cspell/en-words.txt
+  - name: es-palabras
+    path: .cspell/es-palabras.txt
+  - name: pt-palavras
+    path: .cspell/pt-palavras.txt
 dictionaries:
-  [pt-br, es-es, companies, cpp, dotnet, golang, node, softwareTerms]
-words:
-  - accountingservice
-  - actix
-  - adservice
-  - alibaba
-  - Alolita
-  - APAC
-  - appdynamics
-  - appender
-  - appenders
-  - aspecto
-  - autoconfiguration
-  - autoinstrumentation
-  - autoloaded
-  - autoloader
-  - autoloading
-  - backoff
-  - caml
-  - cartservice
-  - cassandra
-  - checkoutservice
-  - Chronosphere
-  - classpath
-  - cncf
-  - currencyservice
-  - daemonset
-  - datadog
-  - discoverability
+  # Natural languages
+  - es-es
+  - pt-br
+  # Local word lists
+  - en-words
+  - es-palabras
+  - pt-palavras
+  # Programming languages and software terms
+  - cpp
   - dotnet
-  - Dyla
-  - dynatrace
-  - emailservice
-  - EMEA
-  - erlang
-  - errorf
-  - featureflagservice
-  - frauddetectionservice
-  - frontendproxy
-  - github
-  - gitpod
-  - grafana
-  - Hausenblas
-  - hugo
-  - initializers
-  - instana
-  - istio
-  - jaeger
-  - jaegertracing
-  - javaagent
-  - javadoc
-  - jboss
-  - jdbc
-  - julia
-  - Juraci
-  - knative
-  - kotlin
-  - Kröhling
-  - kubecon
-  - kubernetes
-  - laravel
-  - lifecycles
-  - lightstep
-  - Loffay
-  - Mancuso
-  - microservices
-  - mongodb
-  - ndjson
-  - Neumann
-  - nginx
-  - ocaml
-  - opamp
-  - opencensus
-  - opensearch
-  - opentelemetry
-  - opentracing
-  - openzipkin
-  - OSTIF
-  - otel
-  - otel-comms
-  - otel-endusers
-  - otelcol
-  - otep
-  - otlp
-  - packagist
-  - pageinfo
-  - Paixão
-  - parentbased
-  - Pavol
-  - paymentservice
-  - postgresql
-  - Pranay
-  - Prateek
-  - prepper
-  - productcatalogservice
-  - prometheus
-  - proto
-  - protobuf
-  - quantile
-  - quantiles
-  - quarkus
-  - quoteservice
-  - recommendationservice
-  - redis
-  - relref
-  - Rexed
-  - Rynn
-  - semconv
-  - servlet
-  - Severin
-  - Sharma
-  - shippingservice
-  - Socha
-  - Stalnaker
-  - stdoutmetric
-  - Strimzi
-  - symfony
-  - tabpane
-  - textlint
-  - thanos
-  - tocstop
-  - tracecontext
-  - traceidratio
-  - traceloop
-  - traceparent
-  - traefik
-  - Trask
-  - uids
-  - unsampled
-  - unshallow
-  - upstreamed
-  - Villela
-  - wordpress
-  - WSGI
-  - zend
-  - zipkin
+  - golang
+  - node
+  - softwareTerms
+  # Other
+  - companies

.cspell/en-words.txt

@@ -0,0 +1,138 @@
+# Words listed here are only for their spelling. If there is a certain way to
+# capitalize the word, add capitalization rules to text-lint rules in
+# .textlintrc.yml
+
+accountingservice
+actix
+adservice
+alibaba
+Alolita
+APAC
+appdynamics
+appender
+appenders
+aspecto
+autoconfiguration
+autoinstrumentation
+autoloaded
+autoloader
+autoloading
+backoff
+caml
+cartservice
+cassandra
+checkoutservice
+Chronosphere
+classpath
+cncf
+currencyservice
+daemonset
+datadog
+discoverability
+dotnet
+Dyla
+dynatrace
+emailservice
+EMEA
+erlang
+errorf
+featureflagservice
+frauddetectionservice
+frontendproxy
+github
+gitpod
+grafana
+Hausenblas
+hugo
+initializers
+instana
+istio
+jaeger
+jaegertracing
+javaagent
+javadoc
+jboss
+jdbc
+julia
+Juraci
+knative
+kotlin
+Kröhling
+kubecon
+kubernetes
+laravel
+lifecycles
+lightstep
+Loffay
+Mancuso
+microservices
+mongodb
+ndjson
+Neumann
+nginx
+ocaml
+opamp
+opencensus
+opensearch
+opentelemetry
+opentracing
+openzipkin
+OSTIF
+otel
+otel-comms
+otel-endusers
+otelcol
+otep
+otlp
+packagist
+pageinfo
+Paixão
+parentbased
+Pavol
+paymentservice
+postgresql
+Pranay
+Prateek
+prepper
+productcatalogservice
+prometheus
+proto
+protobuf
+quantile
+quantiles
+quarkus
+quoteservice
+recommendationservice
+redis
+relref
+Rexed
+Rynn
+semconv
+servlet
+Severin
+Sharma
+shippingservice
+Socha
+Stalnaker
+stdoutmetric
+Strimzi
+symfony
+tabpane
+textlint
+thanos
+tocstop
+tracecontext
+traceidratio
+traceloop
+traceparent
+traefik
+Trask
+uids
+unsampled
+unshallow
+upstreamed
+Villela
+wordpress
+WSGI
+zend
+zipkin

.cspell/es-palabras.txt

@@ -0,0 +1,2 @@
+observabilidad
+telemetría

.cspell/pt-palavras.txt

@@ -9,7 +9,6 @@ developer_note:
   de imagen que contenga la palabra "background" en su nombre.
 show_banner: true
 default_lang_commit: 7ac35d6b429165bbe6c28bdd91feeae83fd35142
-cSpell:ignore: observabilidad telemetría
 ---
 
 <div class="d-none"><a rel="me" href="https://fosstodon.org/@opentelemetry"></a></div>

content/es/_index.md

@@ -61,7 +61,7 @@
     "diff:check": "npm run _diff:check || (echo; echo 'WARNING: the files above have not been committed'; echo)",
     "diff:fail": "npm run _diff:check || (echo; echo 'ERROR: the files above have changed. Locally rerun `npm run test-and-fix` and commit changes'; echo; exit 1)",
     "fix:all": "npm run seq -- $(npm -s run _list:fix:*)",
-    "fix:dict": "find content layouts -name \"*.md\" -print0 | xargs -0 scripts/normalize-cspell-front-matter.pl",
+    "fix:dict": "find content/en layouts -name \"*.md\" -print0 | xargs -0 scripts/normalize-cspell-front-matter.pl",
     "fix:filenames": "npm run _rename-to-kebab-case",
     "fix:format": "npm run format",
     "fix:i18n:all": "scripts/check-i18n.sh -a -c HEAD",

package.json

@@ -8,7 +8,7 @@
 my $lineLenLimit = 79;
 my $last_file = '';
 my $last_line = '';
-my %dictionary = getSiteWideDictWords('.cspell.yml', '.textlintrc.yml');
+my %dictionary = getSiteWideDictWords('.cspell/en-words.txt', '.textlintrc.yml');
 
 while (<>) {
   if (/^\s*(spelling: |-\s*)?cSpell:ignore:?\s*(.*)$/
@@ -43,15 +43,16 @@ sub getSiteWideDictWords {
   my $dictionary_file = shift;
   my $textlintrc_file = shift;
 
-  my %dictionary = readYmlListOfWords('words', $dictionary_file);
-  my %textlintDictionary = readYmlListOfWords('terms', $textlintrc_file);
+  my %dictionary = readYmOrPlainlListOfWords('', $dictionary_file);
+  my %textlintDictionary = readYmOrPlainlListOfWords('terms', $textlintrc_file);
   # Merge dictionaries
   @dictionary{keys %textlintDictionary} = values %textlintDictionary;
 
   return %dictionary;
 }
 
-sub readYmlListOfWords {
+sub readYmOrPlainlListOfWords {
+  # Read plain list of words if $wordsFieldName is empty
   my $wordsFieldName = shift;
   my $file_path = shift;
   my $fh = FileHandle->new($file_path, "r") or die "Could not open file '$file_path': $!";
@@ -60,18 +61,24 @@ sub readYmlListOfWords {
 
   my %dictionary;
   my $indentation = '';
-  my $in_terms = 0;
+  my $in_terms = $wordsFieldName eq '' ? 1 : 0;
   foreach my $line (@lines) {
     chomp $line;
-    if ($line =~ /^(\s*)$wordsFieldName:/) {
-      $indentation = $1 || '';
+    next if $line =~ /^\s*#|^\s*$/;
+    # print "> $line\n" if $wordsFieldName;
+
+    if ($wordsFieldName && $line =~ /^(\s*)$wordsFieldName:/) {
+      $indentation = "$1  - " || '';
       $in_terms = 1;
-      # print STDOUT "Found terms!";
-    } elsif ($line =~ /^$indentation  - (\w[^\s]*)$/ && $in_terms) {
+      # print "> FOUND $wordsFieldName keyword\n"
+    } elsif ($line =~ /^$indentation(\w[^\s]*)$/ && $in_terms) {
       my $term = $1;
       $dictionary{$term} = 1 if $term;
-    } elsif ($line !~ /^ / && $in_terms) {
+    } elsif ($wordsFieldName && $line !~ /^ / && $in_terms) {
       $in_terms = 0;
+      # print "FINISHE word list\n" if $in_terms;
+    } else {
+      # print "OOPS LINE DID NOT MATCH\n" if $in_terms;
     }
   }