From 00a38c8cbe72695b394509fbd29f4d649a00fcc4 Mon Sep 17 00:00:00 2001
From: Samuel Larkin <Samuel.Larkin@cnrc-nrc.gc.ca>
Date: Wed, 3 Jul 2024 10:07:22 -0400
Subject: [PATCH] doc: remove repeating characters using Perl

---
 docs/perl.md | 6 ++++++
 mkdocs.yml   | 1 +
 2 files changed, 7 insertions(+)
 create mode 100644 docs/perl.md

diff --git a/docs/perl.md b/docs/perl.md
new file mode 100644
index 0000000..d0b4912
--- /dev/null
+++ b/docs/perl.md
@@ -0,0 +1,6 @@
+# Perl
+
+## Remove Repeating Chinese Characters
+```sh
+perl -ple 'BEGIN{use utf8;use open qw(:std :utf8);} s/(\p{Han})\1{1,}/\1/gm' < translation.zho.word
+```
diff --git a/mkdocs.yml b/mkdocs.yml
index 9253f42..6cbde4d 100644
--- a/mkdocs.yml
+++ b/mkdocs.yml
@@ -65,6 +65,7 @@ nav:
   - Miller: milller.md
   - Miscellaneous: doc.md
   - nvim: nvim.md
+  - Perl: perl.md
   - rsync: rsync.md
   - SLURM: slurm.md
   - tmux: tmux.md