1 files changed, 7 insertions, 2 deletions
diff --git a/urlgrep b/urlgrep
index ba81765..665f19a 100755
--- a/urlgrep
+++ b/urlgrep
@@ -2,7 +2,12 @@
 # Find all url in stdin, print them newline-separated to stdout
-reg='(((http|https|ftp)|mailto)[.:][^ >"\t]*|www\.[-a-z0-9.]+)[^ .,;\t>">\):]'
+# Old regex (PCRE), kept it for later review:
+# reg='(((http|https|ftp)|mailto)[.:][^ >"\t]*|www\.[-a-z0-9.]+)[^ .,;\t>">\):]'
+# grep -Po "$reg"
-grep -Po "$reg"
+protocols='http|https|ftp|gemini|mailto'
+valid_chars="][a-zA-Z0-9_~/?#@!$&'()*+=.,;:-"
+regex="(($protocols):|www\.)[$valid_chars]+"
+egrep -o "$regex"

diff --git a/urlgrep b/urlgrep index ba81765..665f19a 100755 --- a/urlgrep +++ b/urlgrep
@@ -2,7 +2,12 @@
2		2
3	# Find all url in stdin, print them newline-separated to stdout	3	# Find all url in stdin, print them newline-separated to stdout
4		4
5	reg='(((http\|https\|ftp)\|mailto)[.:][^ >"\t]*\|www\.[-a-z0-9.]+)[^ .,;\t>">\):]'	5	# Old regex (PCRE), kept it for later review:
		6	# reg='(((http\|https\|ftp)\|mailto)[.:][^ >"\t]*\|www\.[-a-z0-9.]+)[^ .,;\t>">\):]'
		7	# grep -Po "$reg"
6		8
7	grep -Po "$reg"	9	protocols='http\|https\|ftp\|gemini\|mailto'
		10	valid_chars="][a-zA-Z0-9_~/?#@!$&'()*+=.,;:-"
		11	regex="(($protocols):\|www\.)[$valid_chars]+"
8		12
		13	egrep -o "$regex"