Merge pull request #389 from ublefo/fix/pdf-annotation

fix: preserve links in PDF

.ci-setup/newpax.lua.patch

@@ -0,0 +1,11 @@
+--- /tmp/texlive/texmf-dist/tex/latex/newpax/newpax.lua
++++ /tmp/texlive/texmf-dist/tex/latex/newpax/newpax.lua
+@@ -206,7 +206,7 @@
+ -- XXXXXX encode/escape the file name?
+ local function outputENTRY_file (file, pdfedoc)
+   local bytes       = GETSIZE(pdfedoc)
+-  local date        = GETINFO(pdfedoc).CreationDate
++  local date        = GETINFO(pdfedoc).CreationDate or "D:22222222222222"
+   -- file
+   local a = strENTRY_BEG
+   a = a .. strCMD_BEG .. constCMD_FILE .. strCMD_END

.ci-setup/texlive-install.sh

@@ -22,7 +22,20 @@ if ! command -v "$TEX_COMPILER" > /dev/null; then
 
   echo "----------------------------------------"
   echo "Installing additional texlive packages:"
-  tlmgr install fontawesome luatextra luacode minted fvextra catchfile xstring framed lastpage
+  tlmgr install fontawesome luatextra luacode minted fvextra catchfile xstring framed lastpage pdfmanagement-testphase newpax
+
+  echo "----------------------------------------"
+  echo "Patching the newpax package version 0.52 to fix a bug:"
+  if NEWPAX_VERSION=$(tlmgr info --only-installed --data cat-version newpax) ; then
+    if [ "$NEWPAX_VERSION" == "0.52" ]; then
+      echo "Version 0.52 found, patching."
+      patch -d / -p0 < "${APP_PATH}"/newpax.lua.patch
+    else
+      echo "Version $NEWPAX_VERSION found, skipping the patch."
+    fi
+  else
+      echo >&2 "Package newpax not found!"; exit 1;
+  fi
 
   cd ..
 

app/helpers/file_helper.rb

@@ -221,9 +221,14 @@ def compress_image_to_dest(source, dest, delete_frames = false)
 
   def compress_pdf(path, max_size = 2_500_000)
     # trusting path... as it needs to be replaced
-    logger.debug "Compressing PDF #{path} (#{File.size?(path)} bytes) using GhostScript"
     # only compress things over max_size -- defaults to 2.5mb
-    return if File.size?(path) < max_size
+    current_filesize = File.size?(path)
+    if current_filesize < max_size
+      logger.debug "PDF #{path} (#{current_filesize} bytes) is smaller than #{max_size}, skipping compression."
+      return
+    else
+      logger.debug "Compressing PDF #{path} (#{current_filesize} bytes) using GhostScript"
+    end
 
     begin
       tmp_file = File.join(Dir.tmpdir, 'doubtfire', 'compress', "#{File.dirname(path).split(File::Separator).last}-file.pdf")

app/views/layouts/application.pdf.erbtex

@@ -1,4 +1,5 @@
 <% @latex_config={ :recipe => [ {:command => "lualatex",:runs => 2} ] } %>
+\DocumentMetadata{uncompress}
 \documentclass[11pt,a4paper]{article}
 \usepackage[T1]{fontenc}
 \usepackage{textcomp}
@@ -24,6 +25,11 @@
   urlcolor=blue,
   citecolor=black}
 
+\usepackage{newpax}
+\newpaxsetup{usefileattributes=true, addannots=true}
+\directlua{require("newpax")}
+<%= yield :preamble_newpax %>
+
 \epstopdfDeclareGraphicsRule{.tif}{png}{.png}{convert #1 \OutputFile}
 \AppendGraphicsExtensions{.tif}
 \epstopdfDeclareGraphicsRule{.tiff}{png}{.png}{convert #1 \OutputFile}

app/views/portfolio/portfolio_pdf.pdf.erb

@@ -27,10 +27,15 @@ end
 def task_for_def(td)
   task_for_def_id(td.id)
 end
+
+# array to hold the list of PDF paths we are inserting for annotation extraction with newpax
+document_list = Array.new
 %>
 
 \begin{titlepage}
   <% if @learning_summary_report %>
+    % add learning summary report to the document list for annotation extraction
+    <% document_list.append(@learning_summary_report)%>
     \includepdf[addtotoc={\thepage,section,1,Learning Summary Report,chap:learningsummary},pages={1-}]{<%= @learning_summary_report %>}
   <% end %>
 
@@ -177,6 +182,12 @@ No Tutor
     \phantomsection
     \label{additional_file_<%= f[:idx] %>}
     \addcontentsline{toc}{subsection}{<%= lesc f[:name] %>}
+
+    % add additional PDF files to the document list for annotation extraction
+    <% if f[:kind] == "document" %>
+         <% document_list.append(@project.portfolio_tmp_file_path(f)) %>
+    <% end %>
+
     <%= render partial:"shared/file", locals: {idx: f[:idx] - 1, count: @files.count - 1, name: f[:name], base_path: @base_path, file_name: @project.portfolio_tmp_file_path(f), file_type: f[:kind]} %>
   <% end %>
 <% end %>
@@ -217,6 +228,19 @@ No Tutor
     \end{tabular}
   <% end %>
   <% if File.exists? task.portfolio_evidence_path %>
+    % add task evidence to the document list for annotation extraction
+    <% document_list.append(task.portfolio_evidence_path)%>
     \includepdf[pages={1-}]{<%= task.portfolio_evidence_path %>}
   <% end %>
 <% end %>
+
+% generate lua calls for newpax and insert it in the preamble for annotation extraction
+<% content_for :preamble_newpax do %>
+  \directlua
+  {
+  <% document_list.each do |path| %>
+    % newpax does not allow the .pdf file extension, file paths must be supplied without extension
+    newpax.writenewpax("<%= File.join(File.dirname(path), File.basename(path, File.extname(path))) %>")
+  <% end %>
+  }
+<% end %>

app/views/task/task_pdf.pdf.erb

@@ -93,6 +93,9 @@ No Tutor % Supervisor's Name
 
 \pagestyle{body}
 
+% array to hold the list of PDF paths we are inserting for annotation extraction with newpax
+<% document_list = Array.new %>
+
 <% @files.each_with_index do |file, idx| %>
   <%  if file != @files.first %>
   \clearpage
@@ -111,8 +114,21 @@ No Tutor % Supervisor's Name
   <% end %>
 
   <% if file[:type] == 'document' %>
+    % add document paths to document_list to generate lua calls to newpax later
+    <% document_list.append(file[:path])%>
     \includepdf[pages={1-}]{<%= file[:path] %>}
   <% end %>
 <% end %>
 
+% generate lua calls for newpax and insert it in the preamble for annotation extraction
+<% content_for :preamble_newpax do %>
+  \directlua
+  {
+  <% document_list.each do |path| %>
+    % newpax does not allow the .pdf file extension, file paths must be supplied without extension
+    newpax.writenewpax("<%= File.join(File.dirname(path), File.basename(path, File.extname(path))) %>")
+  <% end %>
+  }
+<% end %>
+
  % section hello_world (end) Hello World