Fix HTML errors

Fixes various HTML errors left over from the conversion to Slim.
joegattnet · Sep 3, 2013 · 5a77602 · 5a77602
1 parent 392b0c7
commit 5a77602
Show file tree

Hide file tree

Showing 20 changed files with 122 additions and 99 deletions.
diff --git a/app/assets/stylesheets/themes/default.css.sass b/app/assets/stylesheets/themes/default.css.sass
@@ -446,35 +446,31 @@ iframe
         size: $body-font-size
         weight: normal
     a
-      &:hover
-        h2
-          color: $link-hover-color
+      &:hover *
+        color: $link-hover-color
         blockquote
           &:before
             color: $link-hover-color
-        figcaption
-          color: $link-hover-color
-          &:before
-            color: $link-hover-color
         &:after
           border-color: $link-hover-color
     &:last-child
       margin-bottom: 0
 
-.tags
-  ul
-    +horizontal-list
-    &:before
-      +icon-tags
-      color: $secondary-color
-      display: inline
-      float: left
-    li
-      a:after
-        content: ', '
-      &:last-child
+article
+  .tags
+    ul
+      +horizontal-list
+      &:before
+        +icon-tags
+        color: $secondary-color
+        display: inline
+        float: left
+      li
         a:after
-          content: ''
+          content: ', '
+        &:last-child
+          a:after
+            content: ''
 
 ///////////////////////////////////////////////////////////////////////////////////////////////////////////////////////
 //
@@ -709,6 +705,7 @@ iframe
     +pull(4, 12)
     +first-column
     a
+      display: block
       padding-right: 34.38889%
 
   .notes

diff --git a/app/helpers/formatting_helper.rb b/app/helpers/formatting_helper.rb
@@ -23,8 +23,7 @@ def blurbify(text, books = [], links = [], books_citation_style = 'citation.book
     text = deheaderize(text)
     text = bookify(text, books, books_citation_style)
     text = linkify(text, links, links_citation_style)
-    text = smartify(text)
-    clean_up(text)
+    clean_up_via_dom(text, true)
   end
 
   def simple_blurbify(text)
@@ -91,7 +90,7 @@ def linkify(text, links, citation_style)
                  path: link_path(link), 
                  accessed_at: (timeago_tag link.updated_at)))
       # We replace links in the body copy (look-arounds prevent us catching urls inside anchor tags).
-      text.gsub!(/(?<=[^"])(#{ link.url })(?=[^"])/,
+      text.gsub!(/(?!<=")(#{ link.url })(?!=")/,
                  t(citation_style,
                  link_text: link.headline,
                  title: link.headline,
@@ -103,7 +102,6 @@ def linkify(text, links, citation_style)
   end
 
   def annotate(text)
-    # text.gsub!(/(\[[^\]]*)\[([^\]]*)\]([^\[]*\])/, '\1(\2)\3') # Remove any nested annotations
     text.gsub!(/(\[[^\]]*)\[([^\]]*)\]([^\[]*\])/, '\1\3') # Remove any nested annotations
     annotations = text.scan(/\[([^\.].*? .*?)\]/)
     if !annotations.empty?
@@ -126,26 +124,32 @@ def clean_up(text, clean_up_dom = true)
                .html_safe
   end
 
-  def clean_up_via_dom(text)
+  def clean_up_via_dom(text, unwrap_p = false)
     text = text.gsub(/ +/m, ' ')
     text = hyper_conform(text)
     dom = Nokogiri::HTML(text)
-    dom.css('cite cite').find_all.each { |e| e.replace e.inner_html }
-    dom.css('a').find_all.each { |e| e.replace e.inner_html if e.attr('href').blank? and e.attr('href').blank? }
-    dom.css('p').find_all.each { |e| e.remove if e.content.blank? }
-    dom.css('h2').find_all.each { |e| e.remove if e.content.blank? }
-    dom.css('header').find_all.each { |e| e.remove if e.content.blank? }
-    dom.css('section').find_all.each { |e| e.remove if e.content.blank? }
+    dom.css('a, h2, header, p, section').find_all.each { |e| e.remove if e.content.blank? }
+    dom.css('h2 p, cite cite').find_all.each { |e| e.replace e.inner_html }
     # dom.css('h2').find_all.each { |h| h.content = h.content.gsub(/(<h2>)\d+\.? */, '\1') }
     dom.xpath('//text()').find_all.each do |t|
       t.content = smartify(t.content)
       # t.content = hyper_conform(t.content)
     end
-    # tidy = Nokogiri::XSLT File.open('vendor/tidy.xsl')
-    # dom = tidy.transform(dom)
+    dom = indent_dom(dom) if Settings.html.pretty
+    unwrap_from_paragraph_tag(dom) if unwrap_p
     dom.css('body').children.to_html.html_safe
   end
 
+  def indent_dom(dom)
+    tidy = Nokogiri::XSLT File.open('vendor/tidy.xsl')
+    dom = tidy.transform(dom)
+  end
+
+  def unwrap_from_paragraph_tag(dom)
+    e = dom.at_css('body p')
+    e ? e.replace(e.inner_html) : dom
+  end
+
   def smartify(text)
     text = smartify_hyphens(text)
     text = smartify_quotation_marks(text)
@@ -172,15 +176,6 @@ def smartify_quotation_marks(text)
         .gsub(/"(\w|<)/, "\u201C\\1")
         .gsub(/([\w\.\,\?\!>])"/, "\\1\u201D")
         .gsub(/(\u2019|\u201C)([\.\,<])/, "\\2\\1")
-
-#        .gsub(/'([^']+)'/, "\u2018\\1\u2019") # If quotes are not closed this would trip up.
-#        .gsub(/"([^"]+)"/, "\u201C\\1\u201D") # Same here.
-
-#        .gsub(/(<[^>]*?)'([^']+?)'([^<]*?\>)/, '\\1ATTRIBUTE_QUOTES\\2ATTRIBUTE_QUOTES\\3') # IS THIS STILL NECESSARY SINCE WE@RE DOING IT THROUGH DOM?
-#        .gsub(/(<[^>]*?)"([^"]+?)"([^<]*?\>)/, '\\1ATTRIBUTE_QUOTES\\2ATTRIBUTE_QUOTES\\3')
-#        .gsub(/'([^']+)'/, "\u2018\\1\u2019") # If quotes are not closed this would trip up.
-#        .gsub(/"([^"]+)"/, "\u201C\\1\u201D") # Same here.
-#        .gsub(/ATTRIBUTE_QUOTES/, '"')
   end
 
   def smartify_numbers(text)
@@ -219,18 +214,17 @@ def sectionize(text)
   end
 
   def hyper_conform(text)
-    text.gsub!(/\s+([\)\n\.\,\?\!])/m, '\1') # Ensure no space before certain punctuation
-    text.gsub!(/([\(])\s+/m, '\1') # Ensure no space after certain elements
-    # text.gsub!(/([\.\,\?\!])([a-zA-Z])/m, '\1 \2') # Ensure space after certain punctuation
-    text.gsub!(/([[:upper:]]{3,})/, '<abbr>\1</abbr>') # Wrap all-caps in <abbr>
-    text.gsub!(/\b([A-Z]{1})\./, '\1') # Wrap all-caps in <abbr>
-    # text.gsub!(/(<p>|<li>)([[:lower:]])/) { "#{ $1 }#{ $2.upcase }" } # Always start with a capital
-    # text.gsub!(/(\.|\?|\!) ([[:lower:]])/) { "#{ $1 }#{ $2.upcase }" } # Always start with a capital
-    text.gsub!(/(\w)(<\/p>|<\/li>)/, '\1.\2') # Always end with punctuation -- What about verse? __VERSE ? (& lists?)
-    text.gsub!(/ *(<a href=\"#annotation-.*?<\/a>) *([\.\,\;\?\!])/, '\2\1')
-    text.gsub!(/ +(<a href=\"#annotation-)/, '\1')
-
-    # text.gsub!(/([\.\?\!])(<\/cite>)([\.\?\!])/, '\1\2') # Ensure no double punctuation after titles
-    text.html_safe
+    text.gsub(/\s+([\)\n\.\,\?\!])/m, '\1') # Ensure no space before certain punctuation
+        .gsub(/([\(])\s+/m, '\1') # Ensure no space after certain elements
+        .gsub(/([\.\,\?\!])([a-zA-Z])/m, '\1 \2') # Ensure space after certain punctuation
+        .gsub(/([[:upper:]]{3,})/, '<abbr>\1</abbr>') # Wrap all-caps in <abbr>
+        .gsub(/\b([A-Z]{1})\./, '\1') # Wrap all-caps in <abbr>
+        .gsub(/(<p>|<li>)([[:lower:]])/) { "#{ $1 }#{ $2.upcase }" } # Always start with a capital
+        .gsub(/(\.|\?|\!) ([[:lower:]])/) { "#{ $1 }#{ $2.upcase }" } # Always start with a capital
+        .gsub(/(\w)(<\/p>|<\/li>)/, '\1.\2') # Always end with punctuation -- What about verse? __VERSE ? (& lists?)
+        .gsub(/ *(<a href=\"#annotation-.*?<\/a>) *([\.\,\;\?\!])/, '\2\1')
+        .gsub(/ +(<a href=\"#annotation-)/, '\1')
+        .gsub(/([\.\?\!])(<\/cite>)([\.\?\!])/, '\1\2') # Ensure no double punctuation after titles
+        .html_safe
   end
 end
diff --git a/app/views/books/_books_list.html.slim b/app/views/books/_books_list.html.slim
@@ -1,7 +1,7 @@
 section.books
 
   header
-    h6=t('books.title')
+    h6 = link_to_unless_current t('books.index.title'), books_path
 
   ul
     - books.each do |book|

diff --git a/app/views/books/show.html.slim b/app/views/books/show.html.slim
@@ -13,7 +13,7 @@ section
     p= classification(@book)
     p= links(@book)
 
-  / %iframe{ src: "http://books.google.de/books?id=#{ @book.google_books_id }&lpg=PR1&ots=Hfep-dhu0H&d&pg=PR1&output=embed" }
+  / iframe src="http://books.google.de/books?id=#{ @book.google_books_id }&lpg=PR1&ots=Hfep-dhu0H&d&pg=PR1&output=embed"
 
   = render 'citations/citations_list', citations: sort_by_page_reference(@book.notes.publishable.citations), books: @books unless @book.notes.publishable.citations.empty?
 

diff --git a/app/views/citations/_citations_list.html.slim b/app/views/citations/_citations_list.html.slim
@@ -1,7 +1,7 @@
 section.citations
 
   header
-    h6=t('citations.index.title')
+    h6 = link_to_unless_current t('citations.index.title'), citations_path
 
   ul
     - citations.each do |citation|

diff --git a/app/views/citations/show.html.slim b/app/views/citations/show.html.slim
@@ -1,16 +1,16 @@
 - document_title = "#{ @citation.headline } | #{ t('site.title') }"
 - set_meta_tags title: document_title,
-                | description: @citation.body,
+                description: @citation.body,
                 open_graph: { title: @citation.title }
 
 article
-  section#content  lang: lang_attr(@citation.lang), dir: dir_attr(@citation.lang)  
+  section#content lang=lang_attr(@citation.lang) dir=dir_attr(@citation.lang)  
 
-    = render 'header', title: t('citations.index.title', id: @citation.id), :document_title => document_title
+    = render 'header', title: t('citations.index.title', id: @citation.id), document_title: document_title
 
-    section  lang: lang_attr(@citation.lang), dir: dir_attr(@citation.lang)  
+    section  lang=lang_attr(@citation.lang) dir=dir_attr(@citation.lang)  
 
-      - citation_text, attribution = citation_blurb(@citation.clean_body_with_parentheses, 99999)
+      - citation_text, attribution = citation_blurb(@citation.clean_body_with_parentheses, 999)
 
       figure.citation
         blockquote= blurbify(citation_text, @citation.books, @citation.links)

diff --git a/app/views/citations/styles/default/_blockquote_with_attribution.html.slim b/app/views/citations/styles/default/_blockquote_with_attribution.html.slim
diff --git a/app/views/citations/styles/default/_blurb.html.slim b/app/views/citations/styles/default/_blurb.html.slim
diff --git a/app/views/citations/styles/default/_book_details.html.slim b/app/views/citations/styles/default/_book_details.html.slim
diff --git a/app/views/links/_links_admin_list.html.slim b/app/views/links/_links_admin_list.html.slim
@@ -1,7 +1,7 @@
 section.books
 
   header
-    h6=t('links.title')
+    h6=t('links.index.title')
 
   table
     - links.each do |link|

diff --git a/app/views/links/_links_list.html.slim b/app/views/links/_links_list.html.slim
@@ -1,7 +1,7 @@
 section.links
 
   header
-    h6 = t('links.index.title')
+    h6 = link_to_unless_current t('links.index.title'), links_path
 
   ul
     - links.each do |link|

diff --git a/app/views/links/show_channel.html.slim b/app/views/links/show_channel.html.slim
@@ -11,6 +11,4 @@ section
     p.main= @name.titlecase
     = link_to @channel, @channel, class: 'url'
 
-    / %p= link_to @channel, "#{ @links_channel.first.protocol }://#{ @channel }"
-
   = render 'links_list', links: @links_channel unless @links_channel.empty?
diff --git a/app/views/notes/_annotated_text.html.slim b/app/views/notes/_annotated_text.html.slim
@@ -3,11 +3,13 @@ section.body = text.html_safe
 section.annotations
 
   header
-    h6 = t('notes.sections.annotations')
+    / h6 =t('notes.sections.annotations')
+    = "<h6>#{ t('notes.sections.annotations') }</h6>".html_safe
 
   ol
     - annotations.each_with_index do |annotation, index|
-      li id="annotation-#{ index + 1 }"  
-        = link_to "#annotation-mark-#{ index + 1 }" do
-          = index + 1
-          = annotation.html_safe
+      = "<li id=\"annotation-#{ index + 1 }\"><a href=\"#annotation-mark-#{ index + 1 }\">#{ index + 1 }</a>#{ annotation.html_safe }</li> ".html_safe
+      / Problematic whitespace
+      / li id="annotation-#{ index + 1 }"
+      /   a href="#annotation-mark-#{ index + 1 }" = index + 1  
+      /   = annotation.html_safe
diff --git a/app/views/notes/_diffed_tag_list.slim b/app/views/notes/_diffed_tag_list.slim
@@ -1,7 +1,7 @@
 nav.tags
 
   header
-    h6= link_to t('tags.title'), tags_path
+    h6 = link_to t('tags.index.title'), tags_path
 
   ul
     - diffed_tag_list.each do |key, value|

diff --git a/app/views/notes/_tag_list.html.slim b/app/views/notes/_tag_list.html.slim
@@ -1,8 +1,8 @@
 nav.tags
 
   header
-    h6 = link_to t('tags.title'), tags_path
+    h6 = link_to t('tags.index.title'), tags_path
 
   ul
     - tags.each do |tag|
-      li = link_to tag.name, tag_path(tag)
+      li = link_to tag.name, tag_path(tag), rel: 'tag'
diff --git a/app/views/notes/_versions_list.html.slim b/app/views/notes/_versions_list.html.slim
@@ -1,7 +1,7 @@
 nav.versions
 
   header
-    h6 = t('notes.version.description')
+    h6 = t('notes.version.title')
 
   ol
     - if note.versions.length == 0

diff --git a/app/views/shared/_notes_list.html.slim b/app/views/shared/_notes_list.html.slim
@@ -1,7 +1,7 @@
 section.notes
 
   header
-    h6= t('notes.index.title')
+    h6 = link_to_unless_current t('notes.index.title'), notes_path
 
   ul
     - notes.each do |note|

diff --git a/app/views/tags/_tags_list.html.slim b/app/views/tags/_tags_list.html.slim
@@ -1,8 +1,8 @@
-- if Settings.tags.index.style == 'cloud'
-  ul.cloud
-    - tag_cloud(tags, %w(css1 css2 css3 css4)) do |tag, css_class|
-      = link_to tag.name, tag_path(tag), class: css_class, title: tag.count
-- else
-  ul.tags
+section.tags
+
+  header
+    h6 = link_to_unless_current t('tags.index.title'), tags_path
+
+  ul
     - tags.each do |tag|
-      li = link_to "#{ tag.name } <span class=\"count\">#{ tag.count }</span>".html_safe, tag_path(tag), rel: 'tag'
+      li = link_to "#{ tag.name } <span class=\"count\">#{ tag.count }</span>".html_safe, tag_path(tag)
diff --git a/config/environments/staging.rb b/config/environments/staging.rb
@@ -52,9 +52,6 @@
   # Add the fonts path
   config.assets.paths << Rails.root.join('app', 'assets', 'fonts')
 
-  # See https://github.com/ndbroadbent/turbo-sprockets-rails3
-  config.assets.expire_after 2.weeks
-
   # Disable delivery errors, bad email addresses will be ignored
   # config.action_mailer.raise_delivery_errors = false
 

diff --git a/vendor/tidy.xsl b/vendor/tidy.xsl
@@ -0,0 +1,47 @@
+<!-- From: https://gist.github.com/mislav/398334 -->
+<xsl:stylesheet version="1.0" xmlns:xsl="http://www.w3.org/1999/XSL/Transform">
+  <xsl:output method="xml" encoding="UTF-8"/>
+  <xsl:param name="indent-increment" select="'  '"/>
+
+  <xsl:template name="newline">
+    <xsl:text disable-output-escaping="yes">
+</xsl:text>
+  </xsl:template>
+
+  <xsl:template match="comment() | processing-instruction()">
+    <xsl:param name="indent" select="''"/>
+    <xsl:call-template name="newline"/>    
+    <xsl:value-of select="$indent"/>
+    <xsl:copy />
+  </xsl:template>
+
+  <xsl:template match="text()">
+    <xsl:param name="indent" select="''"/>
+    <xsl:call-template name="newline"/>    
+    <xsl:value-of select="$indent"/>
+    <xsl:value-of select="normalize-space(.)"/>
+  </xsl:template>
+
+  <xsl:template match="text()[normalize-space(.)='']"/>
+
+  <xsl:template match="*">
+    <xsl:param name="indent" select="''"/>
+    <xsl:call-template name="newline"/>    
+    <xsl:value-of select="$indent"/>
+      <xsl:choose>
+       <xsl:when test="count(child::*) > 0">
+        <xsl:copy>
+         <xsl:copy-of select="@*"/>
+         <xsl:apply-templates select="*|text()">
+           <xsl:with-param name="indent" select="concat ($indent, $indent-increment)"/>
+         </xsl:apply-templates>
+         <xsl:call-template name="newline"/>
+         <xsl:value-of select="$indent"/>
+        </xsl:copy>
+       </xsl:when>       
+       <xsl:otherwise>
+        <xsl:copy-of select="."/>
+       </xsl:otherwise>
+     </xsl:choose>
+  </xsl:template>    
+</xsl:stylesheet>