# Find duplicate files

It uses the portable `File::Find` module which means that it should work, virtually, on any platform.

```ruby
# usage: sidef fdf.sf [size] [dir1] [...]

require('File::Find')

func find_duplicate_files(Block code, size_min=0, *dirs) {
    var files = Hash()
    %S<File::Find>.find(
        Hash(
            no_chdir => true,
            wanted   => func(arg) {
                var file = File(arg)
                file.is_file || return()
                file.is_link && return()
                var size = file.size
                size >= size_min || return()
                files{size} := [] << file
            },
        ) => dirs...
    )

    files.values.each { |set|
        set.len > 1 || next
        var dups = Hash()
        for i in (^set.end) {
            for (var j = set.end; j > i; --j) {
                if (set[i].compare(set[j]) == 0) {
                    dups{set[i]} := [] << set.pop_at(j++)
                }
            }
        }
        dups.each{ |k,v| code(k.to_file, v...) }
    }

    return()
}

var duplicates = Hash()
func collect(*files) {
    duplicates{files[0].size} := [] << files
}

find_duplicate_files(collect, Num(ARGV.shift), ARGV...)

for k,v in (duplicates.sort_by { |k| -k.to_i }) {
    say "=> Size: #{k}\n#{'~'*80}"
    for files in v {
        say "#{files.sort.join(%Q[\n])}\n#{'-'*80}"
    }
}
```

Section of sample output:

#### Output:

```
% sidef fdf.sf 0 /tmp /usr/bin
=> Size: 5656
~~~~~~~~~~~~~~~~~~~~~~~~~~
/usr/bin/precat
/usr/bin/preunzip
/usr/bin/prezip
--------------------------
=> Size: 2305
~~~~~~~~~~~~~~~~~~~~~~~~~~
/usr/bin/gunzip
/usr/bin/uncompress
--------------------------
=> Size: 2
~~~~~~~~~~~~~~~~~~~~~~~~~~
/tmp/a.txt
/tmp/b.txt
--------------------------
/tmp/m.txt
/tmp/n.txt
--------------------------
```


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://trizen.gitbook.io/sidef-lang/programming_tasks/f/find_duplicate_files.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.