1 #!/bin/bash

     2 

     3 findFiles() {

     4 	find /bin/ -print0;

     5 }

     6 

     7 fetchAttributes() {

     8 	relpipe-in-filesystem \

     9 		--parallel 4 \

    10 		--file path \

    11 		--file type \

    12 		--file size \

    13 		--streamlet hash;

    14 }

    15 

    16 aggregate() {

    17 	relpipe-tr-sql \

    18 		--relation "file_hashes" \

    19 		"SELECT

    20 			path,

    21 			type,

    22 			size,

    23 			sha256,

    24 			count(*) OVER (PARTITION BY sha256) AS same_hash_count

    25 		FROM filesystem

    26 		ORDER BY same_hash_count, sha256, path, type";

    27 }

    28 

    29 findFiles | fetchAttributes | aggregate | relpipe-out-tabular