From 9b5d54947de9cfaeb4751c9de04be1b1a36952bd Mon Sep 17 00:00:00 2001
From: agust <acanalis@itba.edu.ar>
Date: Sat, 27 Feb 2021 22:24:23 -0300
Subject: [PATCH] Add duplicates script

---
 duplicates/duplicates.nu | 22 ++++++++++++++++++++++
 duplicates/example.nu    | 13 +++++++++++++
 2 files changed, 35 insertions(+)
 create mode 100644 duplicates/duplicates.nu
 create mode 100644 duplicates/example.nu

diff --git a/duplicates/duplicates.nu b/duplicates/duplicates.nu
new file mode 100644
index 0000000..77b8dae
--- /dev/null
+++ b/duplicates/duplicates.nu
@@ -0,0 +1,22 @@
+# duplicates returns the rows that correspond to duplicates of the given column.
+def duplicates [
+column: string # Column to look duplicates at
+--count(-c) # set it to display the number of times the value is repeated.
+] {
+    group-by $column |
+    pivot |
+    insert count { = $it.Column1 | flatten | count} |
+    where count > 1 |
+    reject Column0 |
+    if  $(= $count | empty?) {reject count} {each {=$it}}  |
+    flatten |
+    flatten
+}
+
+# duplicates files recursively finds duplicate files in the current working folder. 
+# It uses a heuristic based on duplicate files having the same size. 
+def "duplicates files" [] {
+    do -i {ls **/*} | duplicates size
+}
+
+
diff --git a/duplicates/example.nu b/duplicates/example.nu
new file mode 100644
index 0000000..7f38a64
--- /dev/null
+++ b/duplicates/example.nu
@@ -0,0 +1,13 @@
+# duplicates example
+echo $info | from json
+let info = "[{name: "John", lastname: "Doe"}, {name: "John", lastname: "Roe"}, {name: "Jane", lastname: "Soe"}]"
+echo $info | from json | duplicates name
+
+#duplicates files example
+echo A | save A.txt
+echo A | save B.txt 
+# note that if I used "echo B | save B.txt" the function will give a false positive
+echo ABC | save C.txt
+ls
+duplicates files
+rm A.txt B.txt C.txt --permanent
\ No newline at end of file