middleman-spellcheck 0.8.0 → 0.9.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 8608b5d6fd9049afe93af7ef3f005566bb10e537
-  data.tar.gz: 00b148f8992c92b178992c485bea7a4275b80ea8
+  metadata.gz: fea98d00ab58220965c1e2b8118063d0fbf50b13
+  data.tar.gz: e35c46312d5c3a4afafea88635142e982d920368
 SHA512:
-  metadata.gz: d86956a715506d4924060b035a3c8edd1f595b154d54b7a6e40ac4ebbb39b72f23a40d31939246e2a561d0f90a05e358975ce929ac0eec14a9c6bd1f8ab21701
-  data.tar.gz: 376ba57130d2b77c563a2ee040adc564012e790ba964451d832d9ebe627e762bfcb0af4538da72bd70eff1496dcdb92e770302020e3dc36ee7e3dacf417225d0
+  metadata.gz: ae6225286fc01dbcfd6abe17f91b3b3b99f0250a1ed3ea2bbc8d2eb9b499af404826262b57e14146931318904b21dc65b51a3836cad6c7f3405b12e68c1cbfe6
+  data.tar.gz: 694260deefae946b9b7c8d76aeb3eb17ae7ffd4edbda7fb81c361113daac96dcacd32ac66917dd291b41cd30b4e461a19d682351f143bf60b49bad4d790a3c55

data/README.md

@@ -16,6 +16,13 @@ Add the following to middleman's `config.rb`:
 
     activate :spellcheck
 
+Spellcheck is run automatically after build, but you can also check individual files and subdirectories:
+
+```
+middleman spellcheck source/about.html
+middleman spellcheck source/blog/
+```
+
 ## Usage
 
 You can spellcheck only some resources using a regex with the URL:
@@ -51,12 +58,20 @@ example, to use Polish dictionary, use:
 activate :spellcheck, lang: "pl"
 ```
 
+If you define the ``lang`` metadata in your pages / articles, then spellcheck will use those language.
+
 Middleman-spellcheck can issue many warnings if you run it over a new
 content. If you want to give yourself a chance to fix mistakes gradually and
 not fail each time you build, use :dontfail flag:
 
 ```ruby
-activate :spellcheck, lang: en, dontfail: 1
+activate :spellcheck, lang: "en", dontfail: 1
+```
+
+You can also disable the automatic spellcheck after build (and only run manual checks from the command line):
+
+```ruby
+activate :spellcheck, run_after_build: false
 ```
 
 Advanced users wishing to invoke Middleman-spellcheck backend (Aspell) with

data/lib/middleman-spellcheck.rb

@@ -1,7 +1,8 @@
 require "middleman-core"
 require "middleman-spellcheck/version"
+require "middleman-spellcheck/cli"
 
 ::Middleman::Extensions.register(:spellcheck) do
-    require "middleman-spellcheck/extension"
-      ::Middleman::Spellcheck::SpellcheckExtension
+  require "middleman-spellcheck/extension"
+  ::Middleman::Spellcheck::SpellcheckExtension
 end

data/lib/middleman-spellcheck/cli.rb

@@ -0,0 +1,31 @@
+module Middleman
+  module Cli
+    # This class provides an "spellchecl" command for the middleman CLI.
+    class Spellcheck < Thor
+      include Thor::Actions
+      namespace :spellcheck
+      desc "spellcheck FILE", "Run spellcheck on given file or path"
+      def spellcheck(*paths)
+        app = ::Middleman::Application.server.inst
+
+        resources = app.sitemap.resources.select{|resource|
+          paths.any? {|path|
+            resource.source_file.sub(Dir.pwd,'').sub(%r{^/},'')[/^#{Regexp.escape(path)}/]
+          }
+        }
+        if resources.empty?
+          $stderr.puts "File / Directory #{path} not exist"
+          exit 1
+        end
+        ext = app.extensions[:spellcheck]
+        resources.each do |resource|
+          say_status :spellcheck, "Running spell checker for #{resource.url}", :blue
+          current_misspelled = ext.spellcheck_resource(resource)
+          current_misspelled.each do |misspell|
+            say_status :misspell, ext.error_message(misspell), :red
+          end
+        end
+      end
+    end
+  end
+end

data/lib/middleman-spellcheck/extension.rb

@@ -1,4 +1,5 @@
 require 'middleman-spellcheck/spellchecker'
+require 'middleman-spellcheck/cli'
 require 'nokogiri'
 
 module Middleman
@@ -13,8 +14,10 @@ module Middleman
       option :cmdargs, "", "Pass alternative command line arguments"
       option :debug, 0, "Enable debugging (for developers only)"
       option :dontfail, 0, "Don't fail when misspelled words are found"
+      option :run_after_build, true, "Run Spellcheck after build"
 
       def after_build(builder)
+        return if !options.run_after_build
         Spellchecker.cmdargs=(options.cmdargs)
         Spellchecker.debug_enabled=(options.debug)
         filtered = filter_resources(app, options.page)
@@ -22,7 +25,7 @@ module Middleman
 
         filtered.each do |resource|
           builder.say_status :spellcheck, "Running spell checker for #{resource.url}", :blue
-          current_misspelled = run_check(select_content(resource), options.lang)
+          current_misspelled = spellcheck_resource(resource)
           current_misspelled.each do |misspell|
             builder.say_status :misspell, error_message(misspell), :red
           end
@@ -30,19 +33,20 @@ module Middleman
         end
 
         unless total_misspelled.empty?
-	  estr = "Build failed. There are spelling errors."
-	  if options.dontfail
-	    print "== :dontfail set! Will issue warning only, but not fail.\n"
-	    print estr, "\n"
-	  else
+          estr = "Build failed. There are spelling errors."
+          if options.dontfail
+            print "== :dontfail set! Will issue warning only, but not fail.\n"
+            print estr, "\n"
+          else
             raise Thor::Error, estr
-	  end
+          end
         end
       end
 
       def select_content(resource)
         rendered_resource = resource.render(layout: false)
-        doc = Nokogiri::HTML(rendered_resource)
+        doc = Nokogiri::HTML.fragment(rendered_resource)
+        doc.search('code,style,script').each(&:remove)
 
         if options.tags.empty?
           doc.text
@@ -69,7 +73,19 @@ module Middleman
 
       def filter_resources(app, pattern)
         app.sitemap.resources.select { |resource| resource.url.match(pattern) }
-                             .reject { |resource| option_ignored_exts.include? resource.ext }
+          .reject { |resource| option_ignored_exts.include? resource.ext }
+      end
+
+      def spellcheck_resource(resource)
+        lang =
+          if options.lang.respond_to?(:call)
+            options.lang.call(resource)
+          elsif resource.respond_to?(:lang) and resource.lang
+            resource.lang.to_s
+          else
+            options.lang
+          end
+        run_check(select_content(resource), lang)
       end
 
       def run_check(text, lang)

data/lib/middleman-spellcheck/spellchecker.rb

@@ -54,10 +54,11 @@ class Spellchecker
         # should be * or &
         word_check_res = f.gets.strip()
         sdbg "<- got result '#{word_check_res}'"
-
-        # skip the empty line
-        val = f.gets()
-	sdbg "Expected empty line, got '#{val}'"
+        if word_check_res != ""
+          # skip the empty line
+          val = f.gets()
+          sdbg "Expected empty line, got '#{val}'"
+        end
 
         result << word_check_res
       end
@@ -75,9 +76,9 @@ class Spellchecker
     text.gsub! '’', '\''
     sdbg "self.check got raw text:\n#{text}\n"
 
-    words = text.split(/[^A-Za-z']+/).select { |s|
-       s != "" and s != "'s" and s != "'"
-    }
+    words = text.split(/[^\p{L}']+/).select { |s|
+      s != "" and s != "'s" and s != "'"
+    }.uniq
     sdbg "self.check word array:\n#{words}\n"
 
     results = query(words, lang).map do |query_result|

data/lib/middleman-spellcheck/version.rb

@@ -1,5 +1,5 @@
 module Middleman
   module Spellcheck
-    VERSION = "0.8.0"
+    VERSION = "0.9.0"
   end
 end

data/lib/middleman_extension.rb

@@ -1 +1,2 @@
 require "middleman-spellcheck"
+require 'middleman-core/cli'

data/spec/lib/middleman-spellcheck/spellcheck_spec.rb

@@ -3,7 +3,7 @@ require_relative '../../../lib/middleman-spellcheck/spellchecker'
 
 describe Spellchecker do
   let(:text)   { "hello, world! of txet" }
-  let(:result) { Spellchecker.check(text) }
+  let(:result) { Spellchecker.check(text, "en") }
 
   context "with one wrong word" do
     it "can spell check words" do
@@ -55,8 +55,27 @@ describe Spellchecker do
 
     it "whitelists the word" do
       result.should == [{ word: "A", correct: true },
-                        { word: "user’s", correct: true },
+                        { word: "user's", correct: true },
                         { word: "page", correct: true }]
     end
   end
+
+  context "Bugs" do
+    let(:text) { "'http user" }
+
+    it "don't crash" do
+      result.should == [{ word: "'http", correct: false },
+                        { word: "user", correct: true }]
+    end
+  end
+
+  context "Unicode" do
+    let(:text) { "café hånk 你好" }
+
+    it "splits correctly on unicode chars, doesnt crash on Chinese chars" do
+      result.should == [{ word: "café", correct: false },
+                        { word: "hånk", correct: false },
+                        { word: "你好", correct: false }]
+    end
+  end
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: middleman-spellcheck
 version: !ruby/object:Gem::Version
-  version: 0.8.0
+  version: 0.9.0
 platform: ruby
 authors:
 - Ivan Zarea
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2015-08-17 00:00:00.000000000 Z
+date: 2015-11-03 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: middleman-core
@@ -100,6 +100,7 @@ files:
 - fixtures/spelling_path_app/source/check/index.html
 - fixtures/spelling_path_app/source/no_check/index.html
 - lib/middleman-spellcheck.rb
+- lib/middleman-spellcheck/cli.rb
 - lib/middleman-spellcheck/extension.rb
 - lib/middleman-spellcheck/spellchecker.rb
 - lib/middleman-spellcheck/version.rb