wortsammler 0.0.3 → 0.0.5

checksums.yaml

@@ -0,0 +1,15 @@
+---
+!binary "U0hBMQ==":
+  metadata.gz: !binary |-
+    YTEzMGQxNGYzNTBmYjBhMTkzYjZkZjQ1YWVmYzE3ZmY5YzY5OGMyYg==
+  data.tar.gz: !binary |-
+    ZWViYmE0Njc3OGQ4NjEzZTgzNWNhMGUyYmYwN2EyNmNiYmVmNmNiMQ==
+!binary "U0hBNTEy":
+  metadata.gz: !binary |-
+    ZTBmOTE5OGU3NGRkNTJmNDE1ZDQ2MzU5ZWVlNzcxZTMxNWE2MTRhMGVkOTVk
+    YzlhMjE3NzczN2VhOWZiNzcwMzI4NTEwMjZiMDMyMzE1NWU1ZjljMTE0NzJk
+    ZTZiZjEyNjRjOGQ4ZWQxYzk5OWZiNzE5ODg0NzcyNGNjOGZiNGU=
+  data.tar.gz: !binary |-
+    YTAxYjZkNzdkMjdjMTMxMTRkODEyYjVjMjhjNjQwYmExYTQyOGU1MDllNzRh
+    NDhmNGRmMjFiYWQ3MWExZTFlNDQ1NmI4ZmJmZWEzOTdhOTdkYzU0YjhkZDVk
+    N2ZjOTcyMDZmNTU2YjNlMjlhNThlNmU1YjkxNzhmZGRiYzUzMjk=

data/.gitignore

@@ -16,3 +16,9 @@ test/version_tmp
 tmp
 testproject
 wortsammler-gem.sublime-workspace
+resources/pandocdefault.docx
+resources/pandocdefault.epub
+resources/pandocdefault.html
+resources/pandocdefault.latex
+pandoc.css
+testoutput

data/README.md

@@ -105,12 +105,14 @@ The rakefile is in `<folder>/30_Sources/ZSUPP_Tools`
 -   Specific syntax in strikethrough is still processed as one line
     which is not very robust
 -   as of now the "framework" is hard to use in other applications
+-   pdf_utilities only run on OSX
 
 ## future plans
 
 -   provide a sublime text package
 -   improve documentation (it is flying around in German and needs to be
-    consolidated, please refer to <https://github.com/bwl21/wortsammler/wiki>)
+    consolidated, please refer to
+    <https://github.com/bwl21/wortsammler/wiki>)
 -   support epub
 
 ## contributing
@@ -147,17 +149,17 @@ Please use Ruby 1.9.3
 ### pandoc
 
 -   Download [ttp://code.google.com/p/pandoc/downloads/list][]
--   Installation [http://rubyinstaller.org/downloads/][1]
--   Homepage [http://johnmacfarlane.net/pandoc/][pandoc]
+-   Installation <http://rubyinstaller.org/downloads/>
+-   Homepage <http://johnmacfarlane.net/pandoc/>
 
 ### TeX
 
--   mac: download [http://tug.org/mactex/][]
+-   mac: download <http://tug.org/mactex/>
 
 -   windows:
 
-    -   [http://www.exomatik.net/U-Latex/USBTeXEnglish\#toc1][]
-    -   [http://www.miktex.org/2.9/setup][]
+    -   <http://www.exomatik.net/U-Latex/USBTeXEnglish#toc1>
+    -   <http://www.miktex.org/2.9/setup>
 
     Alternatively you can use
 
@@ -167,8 +169,4 @@ Please use Ruby 1.9.3
   [http://rubyinstaller.org/downloads/]: http://rubyforge.org/frs/%20download.php/76277/rubyinstaller-1.8.7-p370.exe
   [DevKit-tdm-32-4.5.2-20111229-1559-sfx.exe]: https://github.com/downloads/oneclick/rubyinstaller/DevKit-tdm-32-4.5.2-20111229-1559-sfx.exe
   [ttp://code.google.com/p/pandoc/downloads/list]: http://code.google.com/p/pandoc/downloads/list
-  [1]: http://rubyinstaller.org/downloads/
-  [http://tug.org/mactex/]: http://tug.org/mactex/
-  [http://www.exomatik.net/U-Latex/USBTeXEnglish\#toc1]: http://www.exomatik.net/U-Latex/USBTeXEnglish#toc1
-  [http://www.miktex.org/2.9/setup]: http://www.miktex.org/2.9/setup
   [usbtex]: http://www.exomatik.net/U-Latex/USBTeXEnglish

data/Rakefile

@@ -2,16 +2,22 @@ require "bundler/gem_tasks"
 require 'rake/clean'
 require 'rspec/core/rake_task'
 #require 'ruby-debug'
- 
+
 CLEAN << "testproject"
 
 desc "Run specs"
-RSpec::Core::RakeTask.new do |t|
+RSpec::Core::RakeTask.new(:spec, :focus) do |t, args|
   t.pattern = "./spec/**/*_spec.rb" # don't need this, it's default.
-  t.rspec_opts = ['-fd -fd --out ./testresults/wortsammler_testresults.log -fh --out ./testresults/wortsammler_testresults.html']
+  if args[:focus] then
+    usetags="--tag #{args[:focus]}"
+  else
+    usetags="--tag ~exp"
+  end
+  t.rspec_opts = [usetags,
+                  " -fd -fd --out ./testresults/wortsammler_testresults.log -fh --out ./testresults/wortsammler_testresults.html"]
   # Put spec opts in a file named .rspec in root
 end
- 
+
 desc "Generate code coverage"
 RSpec::Core::RakeTask.new(:coverage) do |t|
   t.pattern = "./spec/**/*_spec.rb" # don't need this, it's default.
@@ -21,14 +27,19 @@ end
 
 desc "create documentation"
 task :doc do
-	sh "bin/wortsammler -bi README.md"
-	sh "bin/wortsammler -pi README.md -o ."
-	sh "yard doc"
+  sh "bin/wortsammler -bi README.md"
+  sh "bin/wortsammler -bi changelog.md"
+  sh "yard --markup markdown doc ."
 end
 
+desc "get the default stylefiles from pandoc" 
+task :getpandocstyles do
+  [:latex, :docx, :html, :epub].each{|format |sh "pandoc -D #{format} > resources/pandocdefault.#{format}"}
+  end
+
 desc "run tests"
-task :test => [:clean, :spec]
+task :test  => [:clean, :spec]
 
 task :default do
-	rake -T
-end	
+  sh "rake -T"
+end

data/changelog.md

@@ -0,0 +1,35 @@
+# 0.0.5
+
+-   Fixed the usual encoding but which occurred on windows
+
+# 0.0.4 (yanked)
+
+-   Improve handling of lists
+    (https://github.com/bwl21/wortsammler/issues/14)
+-   adapt to pandoc 1.11.1
+    (https://github.com/bwl21/wortsammler/issues/13)
+-   provide utilites to convert office documents to pdf with crops
+    enhancement (works only on mac)
+    (https://github.com/bwl21/wortsammler/issues/12)
+-   wortsammler uses pandoc -S when combining documents
+    (https://github.com/bwl21/wortsammler/issues/11)
+-   improved Error message: config file could not be loaded
+    (https://github.com/bwl21/wortsammler/issues/10)
+-   improve handling of the stylefile
+    (https://github.com/bwl21/wortsammler/issues/8)
+-   shall support text flowing around graphics
+    (https://github.com/bwl21/wortsammler/issues/7)
+
+# 0.0.3 (16.4.2013)
+
+-   support front matter (https://github.com/bwl21/wortsammler/issues/6)
+-   refactor low level api Step 1
+    (https://github.com/bwl21/wortsammler/issues/4)
+
+# 0.0.2 (11.4.2013)
+
+-   the first working gem
+
+# 0.0.1
+
+-   initial version

data/lib/wortsammler.rb

@@ -1,5 +1,5 @@
 require "wortsammler/version"
-require 'pry' if false
+require "wortsammler/class.proolib"
 
 
 ##
@@ -22,14 +22,18 @@ module Wortsammler
   # 
   # @return [Nil] No Return
   def self.execute(options)
+
+
+    PandocBeautifier.new($log).check_pandoc_version
+
     ##
     #
     # print version info
     #
     if options[:version] then
-      puts "Wortsammler #{Wortsammler::VERSION}"
+      puts "#{Wortsammler::PROGNAME} #{Wortsammler::VERSION}"
 
-      pandoc=`pandocx -v`.split("\n")[0] rescue pandoc="error running pandoc"
+      pandoc=`pandoc -v`.split("\n")[0] rescue pandoc="error running pandoc"
       xetex=`xelatex -v`.split("\n")[0] rescue pandoc="error running xelatex"
 
       puts "found #{pandoc}"
@@ -236,7 +240,8 @@ module Wortsammler
              "ZSUPP_Tools",
              "ZSUPP_Styles",
              "ZGEN_RequirementsTracing",
-             "001_Main"
+             "001_Main",
+             "900_snippets"
              ]
 
     folders.each{|folder|
@@ -249,8 +254,9 @@ module Wortsammler
     }
     FileUtils.cp("#{resourcedir}/main.md", "#{root}/001_Main")
     FileUtils.cp("#{resourcedir}/rakefile.rb", "#{root}/ZSUPP_Tools")
-    FileUtils.cp("#{resourcedir}/default.latex", "#{root}/ZSUPP_Styles")
+    FileUtils.cp("#{resourcedir}/default.wortsammler.latex", "#{root}/ZSUPP_Styles")
     FileUtils.cp("#{resourcedir}/logo.jpg", "#{root}/ZSUPP_Styles")
+    FileUtils.cp("#{resourcedir}/snippets.xlsx", "#{root}/900_snippets")
 
     nil
   end

data/lib/wortsammler/class.proolib.rb

@@ -16,8 +16,10 @@ require 'yaml'
 require 'tmpdir'
 require 'nokogiri'
 require "rubyXL"
+require 'logger'
 
-
+Encoding.default_external = Encoding::UTF_8
+Encoding.default_internal = Encoding::UTF_8
 
 # TODO: make these patterns part of the configuration
 
@@ -39,6 +41,7 @@ INCLUDE_MD_PATTERN    = /^\s+~~MD\s+"(.+)" \s+ "(.+)" \s* (\d*) \s* (\d+-\d+)? \
 
 SNIPPET_PATTERN       = /(\s*)~~SN \s+ (\w+)~~/x
 
+EMBEDDED_IMAGE_PATTERN   = /~~EMBED\s+ "(.+)" \s+ (r|l|i|o) \s+ (.+) \s+ (.+)~~/x
 
 #
 # This mixin convertes a file path to the os Path representation
@@ -129,7 +132,7 @@ class ReferenceTweaker
 
   # this does the postprocessing
   # of the file
-  # in particluar handloe wortsammler's specific syntax.
+  # in particluar handle wortsammler's specific syntax.
   def prepareFile(infile, outfile)
 
     infileIo=File.new(infile)
@@ -167,6 +170,19 @@ class ReferenceTweaker
       }
     end
 
+
+    # embed images
+    #
+    if @target == "pdf"
+      text.gsub!(EMBEDDED_IMAGE_PATTERN){|m|
+        "\\wsembedimage{#{$1}}{#{$2}}{#{$3}}{#{$4}}"
+      }
+    else #if not pdf then it gets a regular image
+      text.gsub!(EMBEDDED_IMAGE_PATTERN){|m|
+        "![#{$1}](#{$1})"
+      }
+    end
+
     #inject the anchors for references to traces ->[traceid]
     if @target == "pdf" then
       text.gsub!(TRACE_ANCHOR_PATTERN){|m| "[#{$1}]#{$2}\\hypertarget{#{mkInternalTraceId($1)}}{}"}
@@ -236,6 +252,10 @@ class ProoConfig
         $log.error "config file not found '#{configFileName}'"
       else
         $log.error "config file could not be loaded '#{configFileName}'"
+        if File.directory?(configFileName)then
+          # note that windows does not disinguish this.
+          $log.error "#{configFileName} is a directory"
+        end
         $log.error "reason '#{e.message}'"
       end
       exit(false)
@@ -329,6 +349,33 @@ class PandocBeautifier
     end
   end
 
+
+
+  #
+
+  # This checks if an appropriate pandoc version can be
+  # started on the machine
+
+  #
+
+  # @return [boolean] true if an appropriate version is available
+  def check_pandoc_version
+    required_version_string="1.11"
+    begin
+      pandoc_version=`pandoc -v`.split("\n").first.split(" ")[1]
+      if pandoc_version < required_version_string then
+        @log.error "found pandoc #{pandoc_version} need #{required_version_string}"
+        result = false
+      else
+        result = true
+      end
+    rescue Exception => e
+      @log.error("could not run pandoc: #{e.message}")
+      result=false
+    end
+    result
+  end
+
   # perform the beautify
   # * process the file with pandoc
   # * revoke some quotes introduced by pandoc
@@ -392,16 +439,16 @@ class PandocBeautifier
   def replace_snippets_in_text(text, snippets)
     changed=false
     text.gsub!(SNIPPET_PATTERN){|m|
-      unless $1.nil? then
-        replacetext_raw=snippets[$2.to_sym]
-        leading_whitespace=$1.split("\n",100)
-        leading_lines=leading_whitespace[0..-1].join("\n")
-        leading_spaces=leading_whitespace.last || ""
-        replacetext=leading_lines+replacetext_raw.gsub("\n", "\n#{leading_spaces}")
-      end
+      replacetext_raw=snippets[$2.to_sym]
 
       if replacetext_raw
         changed=true
+        unless $1.nil? then
+          leading_whitespace=$1.split("\n",100)
+          leading_lines=leading_whitespace[0..-1].join("\n")
+          leading_spaces=leading_whitespace.last || ""
+          replacetext=leading_lines+replacetext_raw.gsub("\n", "\n#{leading_spaces}")
+        end
         @log.debug("replaced snippet #{$2} with #{replacetext}")
       else
         replacetext=m
@@ -481,7 +528,7 @@ class PandocBeautifier
           color="red"
         end
 
-        "\\color{#{color}}\\rule{2cm}{0.5mm}\\marginpar{#{$1.strip}}"
+        "\\color{#{color}}\\rule{2cm}{0.5mm}\\newline\\marginpar{#{$1.strip}}"
 
       }
 
@@ -505,7 +552,7 @@ class PandocBeautifier
 
     #now combine the input files
     @log.debug("combining the input files #{inputname} et al")
-    cmd="pandoc -s -S -o #{output} --ascii #{inputs}" # note that inputs is already quoted
+    cmd="pandoc -s -o #{output} --ascii #{inputs}" # note that inputs is already quoted
     system(cmd)
     if $?.success? then
       PandocBeautifier.new().beautify(output)
@@ -514,7 +561,7 @@ class PandocBeautifier
 
   #
   # This loads snipptes from xlsx file
-  # @param [String] filename of the xlsx file
+  # @param [String] file name of the xlsx file
   # @return [Hash] a hash with the snippetes
   #
   def load_snippets_from_xlsx(file)
@@ -562,7 +609,7 @@ class PandocBeautifier
   # @param [Hash] vars - the variables passed to pandoc
   # @param [Hash] editions - the editions to process; default nil - no edition processing
   # @param [Array of String] snippetfiles the list of files containing snippets
-  # @param [String] file path to frontmatter the file to processed as frontmatter
+  # @param [String] frontmatter file path to frontmatter the file to processed as frontmatter
   # @param [ProoConfig] config - the configuration file to be used
   def generateDocument(input, outdir, outname, format, vars, editions=nil, snippetfiles=nil, frontmatter=nil, config=nil)
 
@@ -651,7 +698,7 @@ class PandocBeautifier
   # @return [nil] no useful return value
   def render_single_document(input, outdir, format)
     outname=File.basename(input, ".*")
-    render_document(input, outdir, outname, format, Hash.new)
+    render_document(input, outdir, outname, format, {:geometry=>"a4paper"})
   end
   #
   # This renders the final document
@@ -698,9 +745,9 @@ class PandocBeautifier
 
     #todo: make config required, so it can be reduced to the else part
     if config.nil? then
-      latexStyleFile = File.dirname(File.expand_path(__FILE__))+"/../../resources/default.latex"
+      latexStyleFile = File.dirname(File.expand_path(__FILE__))+"/../../resources/default.wortsammler.latex"
       latexStyleFile = File.expand_path(latexStyleFile).to_osPath
-      css_style_file = File.dirname(File.expand_path(__FILE__))+"/../../resources/default.css"
+      css_style_file = File.dirname(File.expand_path(__FILE__))+"/../../resources/default.wortsammler.css"
       css_style_file = File.expand_path(css_style_file).to_osPath
     else
       latexStyleFile = config.stylefiles[:latex]
@@ -711,6 +758,12 @@ class PandocBeautifier
     toc = "--toc"
     toc = "" if vars[:usetoc]=="nousetoc"
 
+    if vars[:documentclass]=="book"
+      option_chapters = "--chapters"
+    else
+      option_chapter = ""
+    end
+
     begin
       vars_string=vars.map.map{|key, value| "-V #{key}=#{value.esc}"}.join(" ")
     rescue
@@ -721,14 +774,6 @@ class PandocBeautifier
 
     begin
 
-      if format.include?("pdf") then
-        ReferenceTweaker.new("pdf").prepareFile(tempfile, tempfilePdf)
-        cmd="pandoc -S #{tempfilePdf.esc} #{toc} --standalone --latex-engine xelatex --number-sections #{vars_string}" +
-          " --template #{latexStyleFile.esc} --ascii -o  #{outfilePdf.esc} #{latexTitleInclude}"
-        `#{cmd}`
-      end
-
-
 
       if format.include?("frontmatter") then
 
@@ -738,17 +783,27 @@ class PandocBeautifier
         `#{cmd}`
       end
 
-      if format.include?("latex") then
+      if format.include?("pdf") then
+        @log.debug("creating  #{outfilePdf}")
+        ReferenceTweaker.new("pdf").prepareFile(tempfile, tempfilePdf)
+        cmd="pandoc -S #{tempfilePdf.esc} #{toc} --standalone #{option_chapters} --latex-engine xelatex --number-sections #{vars_string}" +
+          " --template #{latexStyleFile.esc} --ascii -o  #{outfilePdf.esc} #{latexTitleInclude}"
+        `#{cmd}`
+      end
 
+      if format.include?("latex") then
+        @log.debug("creating  #{outfileLatex}")
         ReferenceTweaker.new("pdf").prepareFile(tempfile, tempfilePdf)
 
-        cmd="pandoc -S #{tempfilePdf.esc} #{toc} --standalone  --latex-engine xelatex --number #{vars_string}" +
+        cmd="pandoc -S #{tempfilePdf.esc} #{toc} --standalone #{option_chapters} --latex-engine xelatex --number-sections #{vars_string}" +
           " --template #{latexStyleFile.esc} --ascii -o  #{outfileLatex.esc} #{latexTitleInclude}"
         `#{cmd}`
       end
 
       if format.include?("html") then
         #todo: handle css
+        @log.debug("creating  #{outfileHtml}")
+
         ReferenceTweaker.new("html").prepareFile(tempfile, tempfileHtml)
 
         cmd="pandoc -S #{tempfileHtml.esc} --toc --standalone --self-contained --ascii --number-sections  #{vars_string}" +
@@ -759,9 +814,11 @@ class PandocBeautifier
 
       if format.include?("docx") then
         #todo: handle style file
+        @log.debug("creating  #{outfileDocx}")
+
         ReferenceTweaker.new("html").prepareFile(tempfile, tempfileHtml)
 
-        cmd="pandoc -S #{tempfileHtml.esc} #{toc} --standalone --self-contained --ascii --number  #{vars_string}" +
+        cmd="pandoc -S #{tempfileHtml.esc} #{toc} --standalone --self-contained --ascii --number-sections  #{vars_string}" +
           " -o  #{outfileDocx.esc}"
         cmd="pandoc -S #{tempfileHtml.esc} --toc --standalone --self-contained --ascii --number-sections  #{vars_string}" +
           " -o  #{outfileDocx.esc}"
@@ -769,7 +826,7 @@ class PandocBeautifier
       end
 
       if format.include?("rtf") then
-
+        @log.debug("creating  #{outfileRtf}")
         ReferenceTweaker.new("html").prepareFile(tempfile, tempfileHtml)
 
         cmd="pandoc -S #{tempfileHtml.esc} --toc --standalone --self-contained --ascii --number-sections  #{vars_string}" +
@@ -778,6 +835,7 @@ class PandocBeautifier
       end
 
       if format.include?("txt") then
+        @log.debug("creating  #{outfileText}")
 
         ReferenceTweaker.new("pdf").prepareFile(tempfile, tempfileHtml)
 
@@ -787,10 +845,11 @@ class PandocBeautifier
       end
 
       if format.include?("slide") then
+        @log.debug("creating  #{outfileSlide}")
 
         ReferenceTweaker.new("slide").prepareFile(tempfile, tempfilePdf)
         #todo: hanlde stylefile
-        cmd="pandoc -S #{tempfileHtml.esc} --toc --standalone --number #{vars_string}" +
+        cmd="pandoc -S #{tempfileHtml.esc} --toc --standalone --number-sections #{vars_string}" +
           "  --ascii -t dzslides --slide-level 2 -o  #{outfileSlide.esc}"
         `#{cmd}`
       end