fork download
copy 
  1. #!/bin/bash
  2. # your code goes here
  3.  
  4. #!/bin/bash
  5.  
  6. if [[ ! $1 ]] ; then
  7.     echo -e "Nothing to do, exiting now..."
  8.     exit
  9. fi
  10.  
  11. start_dir="$1"
  12. new_dir="$start_dir"_deduped
  13. new_dir_files="$new_dir"/files
  14.  
  15. mkdir -v "$new_dir"
  16. mkdir -v -p "$new_dir_files"
  17.  
  18. cd "$start_dir"
  19.  
  20. for webpage in * ; do
  21.     # Skip directories
  22.     if [[ $webpage == *"_files"* ]]; then
  23.         continue
  24.     fi
  25.  
  26.     echo $webpage
  27.  
  28.     # copy .html
  29.     new_webpage="../$new_dir/$webpage"
  30.     cp "$webpage" "$new_webpage"
  31.  
  32.     #  select matching directory
  33.     html_dir=$(echo $webpage | sed -e "s/.html/_files/" -e "s/.htm/_files/" )
  34.  
  35.     # check if matching directory exists
  36.     if [ ! -d "$html_dir" ]; then
  37.         echo "$html_dir is not found..."
  38.         continue # move to the next page
  39.     fi
  40.  
  41.     # check if matching directory is not empty
  42.     if [ -z "$(ls -A $html_dir)" ]; then
  43.         echo "$html_dir is empty..."
  44.         continue # move to the next page
  45.     fi
  46.  
  47.     # process files for webpage
  48.     for file in $html_dir/* ; do
  49.             # make hash of current file to compare
  50.             new_file_hash=$(cat "$file" | sha1sum)
  51.  
  52.             # try to find matching file from files already copied
  53.             deduped_file_found=""
  54.  
  55.                 # search for file with matching hash
  56.                 for deduped_file in ../$new_dir_files/* ; do
  57.                     deduped_file_hash=$(cat "$deduped_file" | sha1sum)
  58.  
  59.                     if [[ "$new_file_hash" == "$deduped_file_hash" ]]; then
  60.                         # found matching pair of files
  61.                         deduped_file_found="$deduped_file"
  62.                         break
  63.                     fi
  64.                 done
  65.  
  66.             # extract current filename
  67.             webpage_name=$(echo "$webpage" | sed -e "s/.htm$//" -e "s/.html$//")
  68.             old_filename=$(echo "$file" | sed "s/.*\///")
  69.  
  70.             if [ -z "$deduped_file_found" ]; then 
  71.                 # duplicate file is not found, copy new one
  72.                 new_filename="$webpage_name$old_filename"
  73.                 old_path="$html_dir/$old_filename"
  74.                 new_path="files/$new_filename"
  75.                 cp $file ../$new_dir_files/$new_filename
  76.                 # Append file hash to optimize skipping unique files
  77.             else
  78.                 #reuse existing file
  79.                 new_filename=$(echo "$deduped_file_found" | sed "s/.*\///")
  80.                 old_path="$html_dir/$old_filename"
  81.                 new_path="files/$new_filename"          
  82.             fi
  83.  
  84.             # replace all paths for file
  85.             sed -i 's,'"$old_path,$new_path," $new_webpage
  86.     done
  87. done
Success #stdin #stdout 0s 4512KB
comments (?)
stdin
copy 
Standard input is empty
stdout
copy 
Nothing to do, exiting now...
https://ideone.com/PiycCb
language:
Bash (bash 5.0.3)
created:
4 years ago
visibility:
public

Share or Embed source code

Discover > Sphere Engine API

The brand new service which powers Ideone!

Discover > IDE Widget

Widget for compiling and running the source code in a web browser!