nora_mark 0.2beta5 → 0.2beta6

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 70b55ff7edfd0ea3832a9d7f239471c408dc640c
-  data.tar.gz: e3f7e05cdfb71d9681a4ce4dc3a609cde17206e8
+  metadata.gz: ade2dd5b4cdd69d794a353b7753554cee5d147d8
+  data.tar.gz: e98bc05bb7a68cb64de1d10ecd213d6a4891fd1c
 SHA512:
-  metadata.gz: de1829be0f4054b59effdfa4f46e418865e916ba2d96125682e165b37f4eb7afc18f62b8729bbbf90f565ff58d6bf3e12ca611bf8bda89fa1ccc4f6a9ffc11d8
-  data.tar.gz: cb44418db3abd96505643d739501785595aa94b9eef5b596b6e185ee9ff475677fc323f768c859ae4cd3a532ace6ee243a47c61ccbe118c1064166adc97f25ae
+  metadata.gz: 9a04a47daf848c44003e0acaa6c69da73e64c8c1aaa4f445ff36f5bd550f7e37297533c04c572bb1f6110deeb0a3492793cfc80d38f35946a65ff6a5079dc5f7
+  data.tar.gz: 3e009acb8be92588512b73554abd8f54b126e7ba5c57392d503ad0c609c9f1dbd151e0a07b5fad7d45d231cc9214837cbe6662d1c0133f294a8c11fb2517f363

data/README.md

@@ -32,6 +32,17 @@ Or install it yourself as:
     document = NoraMark::Document.parse(string_or_io)
     put document.html[0] # outputs 1st page of converted XHTML file
 
+From commandline:
+
+    $ nora2html < text.nora > result.xhtml
+    
+Note: nora2html replace ``newpage:`` command to ``<hr class="page-break" />`` and output all pages in one xhtml.
+Main purpose of ``nora2html`` is to validate your markup.
+
+I am planning to release nora2epub and other external tools.
+
+## Markup
+
 An example of markup text (text is in english, but the paragraph style is japanese)
 
     # line begins with # is a comment.

data/example/noramark-reference-ja.nora

@@ -43,6 +43,20 @@ gem install nora_mark
 
 ==: 使い方
 
+===: コマンドラインから
+
+code {
+$ nora2html < source.nora > output.xhtml
+}
+
+入力はutf-8のみ受け付けます。日本語のテキストであれば、kconvオプションでうまくうごくかもしれません。
+
+code {
+$ nora2html --kconv < source.nora > output.xhtml
+}
+
+[s.strong{nora2htmlは、newpageコマンドを<hr />タグに置き換え、すべてのページをひとつのxhtmlとして出力します}]
+===: コードから
 code {//ruby
 require 'nora_mark'
 

data/example/noramark-reference-ja_00001.xhtml

@@ -34,10 +34,20 @@
 <pre><code>gem install nora_mark</code></pre>
 </section>
 <section><h2>使い方</h2>
+<section><h3>コマンドラインから</h3>
+<pre><code>$ nora2html &lt; source.nora &gt; output.xhtml</code></pre>
+<div class='pgroup'><p>入力はutf-8のみ受け付けます。日本語のテキストであれば、kconvオプションでうまくうごくかもしれません。</p>
+</div>
+<pre><code>$ nora2html --kconv &lt; source.nora &gt; output.xhtml</code></pre>
+<div class='pgroup'><p><span class='strong'>nora2htmlは、newpageコマンドを&lt;hr /&gt;タグに置き換え、すべてのページをひとつのxhtmlとして出力します</span></p>
+</div>
+</section>
+<section><h3>コードから</h3>
 <pre class='code-ruby' data-code-language='ruby'><code>require 'nora_mark'
 document = NoraMark::Document.parse(string_or_io, lang: 'ja')
 document.html.write_as_files</code></pre>
 </section>
+</section>
 <section><h2>マークアップ</h2>
 <section><h3>通常のテキスト</h3>
 <div class='pgroup'><p>単なるテキストもHTMLに変換されます。</p>

data/lib/nora_mark.rb

@@ -11,7 +11,7 @@ module NoraMark
 
     def self.parse(string_or_io, param = {})
       instance = new param
-      src = string_or_io.respond_to?(:read) ? string_or_io.read : string_or_io
+      src = (string_or_io.respond_to?(:read) ? string_or_io.read : string_or_io).encode 'utf-8'
       yield instance if block_given?
       instance.instance_eval do 
         @preprocessors.each do

data/lib/nora_mark/parser.kpeg

@@ -21,6 +21,7 @@
 %% page = ast Page(content)
 
 # literals
+BOM = /\uFEFF/
 Eof = !. 
 Space = ' ' | '\t' 
 EofComment = Space* "#" (!Eof .)* 
@@ -178,7 +179,7 @@ Pages = Page:page Newpage:newpage Pages:pages { [ page, newpage ] + pages }
       | Page:page { [ page ] }  
 
 #root
-root = Pages:pages - EofComment? Eof { pages }
+root = BOM? Pages:pages - EofComment? Eof { pages }
 
 
 

data/lib/nora_mark/parser.kpeg.rb

@@ -262,6 +262,13 @@ class NoraMark::Parser < KPeg::CompiledParser
   end
   include ::NoraMarkConstruction
 
+  # BOM = /\uFEFF/
+  def _BOM
+    _tmp = scan(/\A(?-mix:\uFEFF)/)
+    set_failed_rule :_BOM unless _tmp
+    return _tmp
+  end
+
   # Eof = !.
   def _Eof
     _save = self.pos
@@ -3622,11 +3629,21 @@ class NoraMark::Parser < KPeg::CompiledParser
     return _tmp
   end
 
-  # root = Pages:pages - EofComment? Eof { pages }
+  # root = BOM? Pages:pages - EofComment? Eof { pages }
   def _root
 
     _save = self.pos
     while true # sequence
+      _save1 = self.pos
+      _tmp = apply(:_BOM)
+      unless _tmp
+        _tmp = true
+        self.pos = _save1
+      end
+      unless _tmp
+        self.pos = _save
+        break
+      end
       _tmp = apply(:_Pages)
       pages = @result
       unless _tmp
@@ -3638,11 +3655,11 @@ class NoraMark::Parser < KPeg::CompiledParser
         self.pos = _save
         break
       end
-      _save1 = self.pos
+      _save2 = self.pos
       _tmp = apply(:_EofComment)
       unless _tmp
         _tmp = true
-        self.pos = _save1
+        self.pos = _save2
       end
       unless _tmp
         self.pos = _save
@@ -3666,6 +3683,7 @@ class NoraMark::Parser < KPeg::CompiledParser
   end
 
   Rules = {}
+  Rules[:_BOM] = rule_info("BOM", "/\\uFEFF/")
   Rules[:_Eof] = rule_info("Eof", "!.")
   Rules[:_Space] = rule_info("Space", "(\" \" | \"\\\\t\")")
   Rules[:_EofComment] = rule_info("EofComment", "Space* \"\#\" (!Eof .)*")
@@ -3744,6 +3762,6 @@ class NoraMark::Parser < KPeg::CompiledParser
   Rules[:_DocumentLine] = rule_info("DocumentLine", "DocumentContent:content Le { content }")
   Rules[:_Page] = rule_info("Page", "Frontmatter?:frontmatter - (!Newpage Block)*:blocks {page(([frontmatter] +  blocks).select{ |x| !x.nil?})}")
   Rules[:_Pages] = rule_info("Pages", "(Page:page Newpage:newpage Pages:pages { [ page, newpage ] + pages } | Page:page { [ page ] })")
-  Rules[:_root] = rule_info("root", "Pages:pages - EofComment? Eof { pages }")
+  Rules[:_root] = rule_info("root", "BOM? Pages:pages - EofComment? Eof { pages }")
   # :startdoc:
 end

data/lib/nora_mark/version.rb

@@ -1,3 +1,3 @@
 module NoraMark
-  VERSION = "0.2beta5"
+  VERSION = "0.2beta6"
 end

data/spec/nora_mark_spec.rb

@@ -36,6 +36,26 @@ describe NoraMark do
           ['p', 'ここから、次のパラグラフです。']]
       )
     end
+    it 'should convert simple paragraph with BOM' do
+      text = "\uFEFFここから、パラグラフがはじまります。\n「二行目です。」\n三行目です。\n\n\n ここから、次のパラグラフです。"
+      noramark = NoraMark::Document.parse(text, lang: 'ja', title: 'the title')
+      converted = noramark.html
+      body = Nokogiri::XML::Document.parse(converted[0]).root.at_xpath('xmlns:body')
+      expect(body.element_children.size).to eq 2
+      expect(body.element_children[0].selector_and_children).to eq(
+        ['div.pgroup', 
+         ['p', 'ここから、パラグラフがはじまります。'],
+         ['p.noindent', '「二行目です。」'],
+         ['p', '三行目です。']
+        ]
+      )
+
+      expect(body.element_children[1].selector_and_children).to eq(
+        ['div.pgroup',
+          ['p', 'ここから、次のパラグラフです。']]
+      )
+    end
+
     it 'should convert simple paragraph in english mode' do
       text = "paragraph begins.\n2nd line.\n 3rd line.\n\n\n next paragraph."
       noramark = NoraMark::Document.parse(text, lang: 'en', title: 'the title')

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: nora_mark
 version: !ruby/object:Gem::Version
-  version: 0.2beta5
+  version: 0.2beta6
 platform: ruby
 authors:
 - KOJIMA Satoshi