httpspell 1.5.0 → 1.5.1

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: d66cfcc88c0bc7e0e237033b8c76f1aaccc40f9aba3f68766d45204a2b133401
-  data.tar.gz: 6c488170f95d0f33fdcbc5c55f2416d654f2b4558214943f21d19e1220f2ad96
+  metadata.gz: 509242695286e955675a85e15957752f1ac19eba7a5ffda317f6e45fd41c6c01
+  data.tar.gz: 4537ecafb9c882a23024c00246b0c1a07359d5180b2ee052d68a25ea23a64f6f
 SHA512:
-  metadata.gz: f493b3411cd162e4a714203b05277f26810d71a0c23e52d69c36297c19e03db7b97692c1e4928c8f8fb0b9bc9a59f04b9ae4113c5cdd309c1edcf2a493d68687
-  data.tar.gz: ed44c8adf0dcd63330e8e7f837d9f515fd6131e58ae02808a01ed430ef42e5ee258a8c8d5a6fb9552c6b2c0dc460966453d3f1cda6e359739a18b6a01a25cdeb
+  metadata.gz: ddf6cb8856cf025e21956c49efe2d94c35204c273a086f60b6ae5e61c7bd56ec9fddda5ec8890f78c0ff106b03baba6ced6bfcf733f1e93622721ebf0b966a08
+  data.tar.gz: c217f2635966096b1ab86df7c52d6dd76145359d761b3cccc6829fde018760407e7207b7d6b89e3f709b8a966f82de93964656e64ad32474e4e8e3ad7cea43f8

data/Gemfile.lock

@@ -1,7 +1,7 @@
 PATH
   remote: .
   specs:
-    httpspell (1.5.0)
+    httpspell (1.5.1)
       nokogiri
 
 GEM

data/README.markdown

@@ -39,7 +39,7 @@ Words that are not in the dictionary for the given language (inferred from the `
 
 # Misc
 
-If you produce content with kramdown (e.g. using Jekyll), setting `spellcheck='false'` for an element is a simple as adding this line *after* the element (e.g. heading):
+If you produce content with kramdown (e.g. using Jekyll), an [Inline Attribute List](https://kramdown.gettalong.org/syntax.html#inline-attribute-lists) can be used to set `spellcheck='false'` for an element by adding this line *after* the element (e.g. heading):
 
 ```
 {: spellcheck="false"}

data/exe/httpspell

@@ -7,6 +7,7 @@ require 'http_spell/spellchecker'
 require 'http_spell/version'
 
 personal_dictionary_path = nil
+ignore_file_path = nil
 force_language = nil
 tracing = nil
 verbose = nil
@@ -14,6 +15,7 @@ included = nil
 excluded = []
 
 begin
+  # rubocop:disable Metrics/BlockLength
   OptionParser.new do |parser|
     parser.banner.prepend <<~BANNER
       Spellchecks a website via HTTP.
@@ -25,6 +27,10 @@ begin
       personal_dictionary_path = p
     end
 
+    parser.on('-I', '--ignore=FILE', 'path to a file containing spelling errors to ignore') do |i|
+      ignore_file_path = i
+    end
+
     parser.on('-l', '--language=LANGUAGE', 'override LANGUAGE of content') do |l|
       force_language = l
     end
@@ -49,6 +55,7 @@ begin
     # TODO: --recursive, defaults to false
     # TODO wget has some additional options for recursive behavior that should be reviewed
   end.parse!
+  # rubocop:enable Metrics/BlockLength
 rescue StandardError
   warn "Error: #{$ERROR_INFO}"
   exit 1
@@ -59,18 +66,38 @@ if ARGV.size != 1
   exit 1
 end
 
-def check(url, doc, lang, personal_dictionary_path, verbose)
-  unknown_words = HttpSpell::SpellChecker.new(personal_dictionary_path, verbose:).check(doc, lang)
+# rubocop:disable Metrics/ParameterLists
+def check(url, doc, lang, personal_dictionary_path, ignore_file_path, verbose)
+  has_unknown_words = false
+
+  # Handle elements with a different lang attribute separately
+  doc.css(%([lang]:not([lang="#{lang}"]))).each do |element|
+    has_unknown_words |= check("#{url} => #{element.name} with", element, element['lang'], personal_dictionary_path, ignore_file_path, verbose)
+    element.unlink
+  end
+
+  unknown_words = HttpSpell::SpellChecker.new(personal_dictionary_path, verbose:).check(doc.to_s, lang)
+
+  if ignore_file_path && unknown_words.any?
+    ignore_words = File.read(ignore_file_path).lines.map(&:chomp)
+    ignored_words = unknown_words.intersection(ignore_words)
+
+    if ignored_words.any?
+      warn "#{url} (lang=#{lang}): Ignoring the following spelling errors because they are in the ignore list: #{ignored_words}" if verbose
+      unknown_words -= ignore_words
+    end
+  end
 
   if unknown_words.empty?
     warn "#{url} (lang=#{lang}): No unknown words" if verbose
-    false
+    has_unknown_words # no unknown words in doc, but maybe in elements with a different language
   else
     warn "#{url} (lang=#{lang}): #{unknown_words.size} unknown words:" if verbose
     puts unknown_words
-    true
+    true # regardless of what elements with a different language had, at least doc has unknown words
   end
 end
+# rubocop:enable Metrics/ParameterLists
 
 has_unknown_words = false
 
@@ -83,14 +110,7 @@ spider_success = HttpSpell::Spider.new(ARGV.first, included:, excluded:, verbose
   doc.css('iframe').each(&:unlink)
   doc.css('[spellcheck=false]').each(&:unlink)
 
-  # Handle elements with a different lang attribute separately
-  doc.css(%([lang]:not([lang="#{lang}"]))).each do |element|
-    has_unknown_words |= check("#{url} => #{element.name} with", element.to_s, element['lang'], personal_dictionary_path, verbose)
-    element.unlink
-  end
-
-  # Everything else
-  has_unknown_words |= check("#{url} => document with", doc.to_s, lang, personal_dictionary_path, verbose)
+  has_unknown_words |= check("#{url} => document with", doc, lang, personal_dictionary_path, ignore_file_path, verbose)
 end
 
 exit 2 unless spider_success

data/lib/http_spell/version.rb

@@ -1,5 +1,5 @@
 # frozen_string_literal: true
 
 module HttpSpell
-  VERSION = '1.5.0'
+  VERSION = '1.5.1'
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: httpspell
 version: !ruby/object:Gem::Version
-  version: 1.5.0
+  version: 1.5.1
 platform: ruby
 authors:
 - Steffen Uhlig
 autorequire:
 bindir: exe
 cert_chain: []
-date: 2024-05-31 00:00:00.000000000 Z
+date: 2024-06-01 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: nokogiri