Script for merging files in multiple nested directories by symbolic link

I think the following shellscript will do what you want

• The original folders are in main
• There can be subfolders in several levels
• The merged folder is links
• run the main shellscript script in the directory containing main and links

script

#!/bin/bash

mkdir -p links

find main -type d -exec bash -c \
'for pathname do
  #echo "------------------------------${pathname} ${pathname#*/*/}"
  if [ "${pathname/*\/*\/}" != "${pathname}" ]
  then
   mkdir -p "links/${pathname#*/*/}"
  fi
 done' bash {} +

find main -type f -exec bash -c \
'curdir=$(pwd)
for pathname do
  tpat=${pathname/main\/}
  ln -s "${curdir}/${pathname}" "links/${tpat#*/}" 2> /dev/null;
 done' bash {} +

find links -type l -exec bash -c \
'for pathname do
  LANG=C
  file "$pathname"|grep -o  "$pathname: broken symbolic link" > /dev/null; \
  if [ $? -eq 0 ];then rm "$pathname";fi
 done' \
 bash {} +

Demo

$ \rm -r links

$ find main
main
main/f 4
main/f 4/s 4
main/f 4/s 4/k 4
main/asdf
main/f2
main/f2/s3
main/f2/s3/h
main/f2/s3/g
main/f2/s3/ss
main/f2/s3/ss/i
main/f2/s1
main/f2/s1/c
main/f2/s1/d
main/j
main/f1
main/f1/s2
main/f1/s2/x y
main/f1/s2/f
main/f1/s2/e
main/f1/s1
main/f1/s1/a
main/f1/s1/b

$ ./script  # doing it

$ find links/ -type l -exec file {} \;
links/s2/x y: symbolic link to /media/multimed-2/test/test0/matohak/main/f1/s2/x y
links/s2/f: symbolic link to /media/multimed-2/test/test0/matohak/main/f1/s2/f
links/s2/e: symbolic link to /media/multimed-2/test/test0/matohak/main/f1/s2/e
links/s3/h: symbolic link to /media/multimed-2/test/test0/matohak/main/f2/s3/h
links/s3/g: symbolic link to /media/multimed-2/test/test0/matohak/main/f2/s3/g
links/s3/ss/i: symbolic link to /media/multimed-2/test/test0/matohak/main/f2/s3/ss/i
links/s 4/k 4: symbolic link to /media/multimed-2/test/test0/matohak/main/f 4/s 4/k 4
links/asdf: symbolic link to /media/multimed-2/test/test0/matohak/main/asdf
links/s1/a: symbolic link to /media/multimed-2/test/test0/matohak/main/f1/s1/a
links/s1/c: symbolic link to /media/multimed-2/test/test0/matohak/main/f2/s1/c
links/s1/b: symbolic link to /media/multimed-2/test/test0/matohak/main/f1/s1/b
links/s1/d: symbolic link to /media/multimed-2/test/test0/matohak/main/f2/s1/d
links/j: symbolic link to /media/multimed-2/test/test0/matohak/main/j

$ ln -s main/asdf links/asdf-b  # create a broken link

$ find links/ -type l -name "asdf*" -exec file {} \;
links/asdf-b: broken symbolic link to main/asdf
links/asdf: symbolic link to /media/multimed-2/test/test0/matohak/main/asdf

$ ./script  # this time only to remove the broken link

$ find links/ -type l -name "asdf*" -exec file {} \;
links/asdf: symbolic link to /media/multimed-2/test/test0/matohak/main/asdf
$

A case that would allow you to specify which folder under main/* to merge

#!/bin/bash
# First argument is target, following arbitrary number of target folders
# eg. ./script.sh links main/f1 main/f2 main/f3

argc=$#
argv=($@)

mkdir -p ${argv[0]}

for (( j=1; j<argc; j++ )); do

    find ${argv[j]} -type d -exec bash -c \
    'for pathname do
      #echo "------------------------------${pathname} ${pathname#*/*/}"
      if [ "${pathname/*\/*\/}" != "${pathname}" ]
      then
       mkdir -p "'${argv[0]}'/${pathname#*/*/}"
      fi
     done' bash {} +

    find ${argv[j]} -type f -exec bash -c \
    'curdir=$(pwd)
    for pathname do
      tpat=${pathname/${argv[j]}\/}
      ln -s "${curdir}/${pathname}" "'${argv[0]}'/${tpat#*/}" 2> /dev/null;
     done' bash {} +

    find ${argv[0]} -type l -exec bash -c \
    'for pathname do
      LANG=C
      file "$pathname"|grep -o  "$pathname: broken symbolic link" > /dev/null; \
      if [ $? -eq 0 ];then rm "$pathname";fi
     done' \
     bash {} +

    find ${argv[0]} -type d -empty -delete  # Removes empty dir in target

done

Got it... this python code should be able to walk through arbitrary number of nested directories and create symlinks for files all merged into the target directory. Arguments are the target and the source directories respectively. Source directories should be relative to the target dir. eg.

python script.py ./merged_folder ../folder1 ../folder2 ../folder3

import os
import sys
import time
'''
Loops through merge_symlink.
See https://askubuntu.com/questions/1097502/script-for-merging-files-in-multiple-nested-directories-by-symbolic-link/
KH Tam Nov 2018 (matohak)

Use: python merge_symlink.py ./target ../folder1 ../folder2 ../folder3
Note that if overwrite==True and there are duplicated filenames, links will be overwritten by the last argument's
'''

def merge_symlink(sources, overwrite=True, remove_empty_dir=True, verbose=False):
    '''
    See https://askubuntu.com/questions/1097502/script-for-merging-files-in-multiple-nested-directories-by-symbolic-link/
    Function to be run in the target directory.

    :param sources: a list of directories where the files in the subdirectories are to be merged symbolically. Path relative to the target. eg. ["../folder1", "../folder2"]
    :param overwrite: Bool, whether to overwrite existing symbolic links
    :param remove_empty_dir: Bool, whether to remove empty directories in target.
    :param verbose: Prints stuff.
    :return: None
    '''

    # Creating symlinks and folders
    for source in sources:
        for dirName, subdirList, fileList in os.walk(source):
            # print(dirName, fileList)  # print all source dir and files
            if source[-1] == "/": source=source[:-1]

            target_dir = dirName.replace(source, '.', 1)
            depth = dirName.count("/") - source.count("/")

            try:
                os.mkdir(os.path.join(target_dir))
            except FileExistsError:
                pass

            for file in fileList:
                targetlink = os.path.join(target_dir, file)
                try:
                    os.symlink(os.path.join("../"*depth + dirName, file), targetlink)
                except FileExistsError:
                    if overwrite and not (isvalidlink(targetlink)==2):  # Never replace a real file with a symlink!
                        os.remove(targetlink)
                        os.symlink(os.path.join("../" * depth + dirName, file), targetlink)
                        if verbose: print('overwriting {}'.format(targetlink))

    # Pruning broken links and then deleting empty folders.
    for dirName, subdirList, fileList in os.walk("./"):
        for file in fileList:
            link = os.path.join(dirName,file)
            if isvalidlink(link)==0:
                os.remove(link)
                if verbose: print("Removing broken symlink: {}".format(link))

    if remove_empty_dir:
        for dirName, subdirList, fileList in os.walk("./"):
            if fileList==[] and subdirList==[] and dirName!="./":
                os.rmdir(dirName)

# Checks if file is a broken link. 0: broken link; 1: valid link; 2: not a link
def isvalidlink(path):
    if not os.path.islink(path):
        return 2
    try:
        os.stat(path)
    except os.error:
        return 0
    return 1

if __name__ == "__main__":

    target = sys.argv[1]
    sources = sys.argv[2:]      # Inputs should be relative to the target dir.
    overwrite = False
    loop = False
    looptime = 10

    os.chdir(target)
    if not loop:
        merge_symlink(sources, overwrite=overwrite)
    else:
        while loop:
            merge_symlink(sources, overwrite=overwrite)
            time.sleep(looptime)

Thank @JacobVlijm for the link and @sudodus for helping!