html2doc 0.7.0 → 0.7.1

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 0f88d61ea0bbf6baa2a355ec6d5abfd35399c91e
-  data.tar.gz: 1f135f2907b6a7d51196dd6774fc0b81b2e51e34
+  metadata.gz: 326527587765630ec2b376716c48428cfa946d94
+  data.tar.gz: 1690c23c76ce1cea7971d8f399544c5dea36166c
 SHA512:
-  metadata.gz: 69b5db648e40a37723b5591caa28c3f3131b40ce777245b80ff578cb80de7e183dbdfad677e13dccbdcb5aa2327520f386d52b975ea930d676f250113c2163a3
-  data.tar.gz: eca2bc4cb73d72345b362ec2f3eaa6389073aba39c77d20fbe2bd413c73347b10f2c6f4a9b2e216016a3c1f74cf4ed461b6f812ba525d3b44c9083ed3c49684a
+  metadata.gz: 0405adec203661a00d411a0c14458493eb58992a5c052f43c4470f7ad8d9943207b8d917ef91eafc4dfa4b79f2dad4db6ff381568682149d19d001cb1aad775b
+  data.tar.gz: 6cae33b7a484bf5c41ad55c9355aeebd89fef0a95c59aec68771dac95af64b151a303e2876c8eb31aef43ea9ddc143c5e770d86e8c86d509c4e1a06c13ebc59e

data/.rubocop.tb.yml

@@ -352,8 +352,18 @@ Style/TrailingCommaInArguments:
     - no_comma
   Enabled: true
 
-Style/TrailingCommaInLiteral:
-  Description: 'Checks for trailing comma in array and hash literals.'
+Style/TrailingCommaInArrayLiteral:
+  Description: 'Checks for trailing comma in array literals.'
+  StyleGuide: 'https://github.com/bbatsov/ruby-style-guide#no-trailing-array-commas'
+  EnforcedStyleForMultiline: comma
+  SupportedStylesForMultiline:
+    - comma
+    - consistent_comma
+    - no_comma
+  Enabled: true
+
+Style/TrailingCommaInHashLiteral:
+  Description: 'Checks for trailing comma in hash literals.'
   StyleGuide: 'https://github.com/bbatsov/ruby-style-guide#no-trailing-array-commas'
   EnforcedStyleForMultiline: comma
   SupportedStylesForMultiline:
@@ -398,6 +408,13 @@ Layout/AlignParameters:
   StyleGuide: 'https://github.com/bbatsov/ruby-style-guide#no-double-indent'
   Enabled: false
 
+Layout/ConditionPosition:
+  Description: >-
+                 Checks for condition placed in a confusing position relative to
+                 the keyword.
+  StyleGuide: 'https://github.com/bbatsov/ruby-style-guide#same-line-condition'
+  Enabled: false
+
 Layout/DotPosition:
   Description: 'Checks the position of the dot in multi-line method calls.'
   StyleGuide: 'https://github.com/bbatsov/ruby-style-guide#consistent-multi-line-chains'
@@ -450,13 +467,6 @@ Lint/CircularArgumentReference:
   Description: "Don't refer to the keyword argument in the default value."
   Enabled: false
 
-Lint/ConditionPosition:
-  Description: >-
-                 Checks for condition placed in a confusing position relative to
-                 the keyword.
-  StyleGuide: 'https://github.com/bbatsov/ruby-style-guide#same-line-condition'
-  Enabled: false
-
 Lint/DeprecatedClassMethods:
   Description: 'Check for deprecated class method calls.'
   Enabled: false
@@ -523,7 +533,7 @@ Lint/UnderscorePrefixedVariableName:
   Description: 'Do not use prefix `_` for a variable that is used.'
   Enabled: false
 
-Lint/UnneededDisable:
+Lint/UnneededCopDisableDirective:
   Description: >-
                  Checks for rubocop:disable comments that can be removed.
                  Note: this cop is not disabled when disabling all cops.

data/README.adoc

@@ -9,7 +9,7 @@ Gem to convert an HTML document into a Word document (.doc) format. This is inte
 
 This gem originated out of https://github.com/riboseinc/asciidoctor-iso, which creates a Word document from a automatically generated HTML document (created in turn by processing Asciidoc).
 
-This work is driven by the Word document generation procedure documented in http://sebsauvage.net/wiki/doku.php?id=word_document_generation
+This work is driven by the Word document generation procedure documented in http://sebsauvage.net/wiki/doku.php?id=word_document_generation. For more on the approach taken, and on alternative approaches, see https://github.com/riboseinc/html2doc/wiki/Why-not-docx%3F
 
 The gem currently does the following:
 

data/lib/html2doc/base.rb

@@ -9,14 +9,20 @@ module Html2Doc
   def self.process(result, hash)
     hash[:dir1] = create_dir(hash[:filename], hash[:dir])
     result = process_html(result, hash)
-    hash[:header_file].nil? ||
-      system("cp #{hash[:header_file]} #{hash[:dir1]}/header.html")
+    process_header(hash[:header_file], hash)
     generate_filelist(hash[:filename], hash[:dir1])
     File.open("#{hash[:filename]}.htm", "w") { |f| f.write(result) }
     mime_package result, hash[:filename], hash[:dir1]
     rm_temp_files(hash[:filename], hash[:dir], hash[:dir1])
   end
 
+  def self.process_header(headerfile, hash)
+    return if headerfile.nil?
+    doc = File.read(headerfile, encoding: "utf-8")
+    doc = header_image_cleanup(doc, hash[:dir1], hash[:filename])
+    File.open("#{hash[:dir1]}/header.html", "w") { |f| f.write(doc) }
+  end
+
   def self.create_dir(filename, dir)
     return dir if dir
     dir = "#{filename}_files"

data/lib/html2doc/mime.rb

@@ -84,6 +84,27 @@ module Html2Doc
     docxml
   end
 
+  # do not parse the header through Nokogiri, since it will contain 
+  # non-XML like <![if !supportFootnotes]>
+  def self.header_image_cleanup(doc, dir, filename)
+    doc.split(%r{(<img [^>]*>|<v:imagedata [^>]*>)}).each_slice(2).map do |a|
+      header_image_cleanup1(a, dir, filename)
+    end.join
+  end
+
+  def self.header_image_cleanup1(a, dir, filename)
+      if a.size == 2
+        matched = / src=['"](?<src>[^"']+)['"]/.match a[1]
+        matched2 = /\.(?<suffix>\S+)$/.match matched[:src]
+        uuid = UUIDTools::UUID.random_create.to_s
+        new_full_filename = "file:///C:/Doc/#{filename}_files/#{uuid}.#{matched2[:suffix]}"
+        dest_filename = File.join(dir, "#{uuid}.#{matched2[:suffix]}")
+        system "cp #{matched[:src]} #{dest_filename}"
+        a[1].sub!(%r{ src=['"](?<src>[^"']+)['"]}, " src='#{new_full_filename}'")
+      end
+      a.join
+  end
+
   def self.generate_filelist(filename, dir)
     File.open(File.join(dir, "filelist.xml"), "w") do |f|
       f.write %{<xml xmlns:o="urn:schemas-microsoft-com:office:office">

data/lib/html2doc/version.rb

@@ -1,3 +1,3 @@
 module Html2Doc
-  VERSION = "0.7.0".freeze
+  VERSION = "0.7.1".freeze
 end

data/spec/html2doc_spec.rb

@@ -364,6 +364,12 @@ RSpec.describe Html2Doc do
     OUTPUT
   end
 
+      it "processes a header with an image" do
+    Html2Doc.process(html_input(""), filename: "test", header_file: "spec/header_img.html")
+    expect(guid_clean(File.read("test.doc", encoding: "utf-8"))).to match(%r{Content-Type: image/png})
+  end
+
+
   it "processes a populated document" do
     simple_body = "<h1>Hello word!</h1>
     <div>This is a very simple document</div>"
@@ -407,7 +413,7 @@ RSpec.describe Html2Doc do
       to match_fuzzy(<<~OUTPUT)
     #{WORD_HDR} #{DEFAULT_STYLESHEET} #{WORD_HDR_END}
     #{word_body('
-       <div style="text-align:left;"><m:oMathPara><m:oMathParaPr><m:jc m:val="left"></m:jc></m:oMathParaPr><m:oMath>
+       <div style="text-align:left;"><m:oMathPara><m:oMathParaPr><m:jc m:val="left"/></m:oMathParaPr><m:oMath>
        <m:nary><m:naryPr><m:chr m:val="&#x2211;"></m:chr><m:limLoc m:val="undOvr"></m:limLoc><m:grow m:val="on"></m:grow><m:subHide m:val="off"></m:subHide><m:supHide m:val="off"></m:supHide></m:naryPr><m:sub>
        <m:r><m:t>i=1</m:t></m:r>
        </m:sub><m:sup><m:r><m:t>n</m:t></m:r></m:sup><m:e><m:sSup><m:e><m:r><m:t>i</m:t></m:r></m:e><m:sup><m:r><m:t>3</m:t></m:r></m:sup></m:sSup></m:e></m:nary>
@@ -432,7 +438,7 @@ RSpec.describe Html2Doc do
       to match_fuzzy(<<~OUTPUT)
     #{WORD_HDR} #{DEFAULT_STYLESHEET} #{WORD_HDR_END}
     #{word_body('
-       <div style="text-align:right;"><m:oMathPara><m:oMathParaPr><m:jc m:val="right"></m:jc></m:oMathParaPr><m:oMath>
+       <div style="text-align:right;"><m:oMathPara><m:oMathParaPr><m:jc m:val="right"/></m:oMathParaPr><m:oMath>
        <m:nary><m:naryPr><m:chr m:val="&#x2211;"></m:chr><m:limLoc m:val="undOvr"></m:limLoc><m:grow m:val="on"></m:grow><m:subHide m:val="off"></m:subHide><m:supHide m:val="off"></m:supHide></m:naryPr><m:sub>
        <m:r><m:t>i=1</m:t></m:r>
        </m:sub><m:sup><m:r><m:t>n</m:t></m:r></m:sup><m:e><m:sSup><m:e><m:r><m:t>i</m:t></m:r></m:e><m:sup><m:r><m:t>3</m:t></m:r></m:sup></m:sSup></m:e></m:nary>

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: html2doc
 version: !ruby/object:Gem::Version
-  version: 0.7.0
+  version: 0.7.1
 platform: ruby
 authors:
 - Ribose Inc.
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2018-04-17 00:00:00.000000000 Z
+date: 2018-05-26 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: htmlentities