From 2742524159ad2bc861711df084f6bd77588e9e9b Mon Sep 17 00:00:00 2001 From: Nick White Date: Sun, 31 Mar 2013 18:32:08 +0100 Subject: Initial commit --- xmlcleanup2.sed | 13 +++++++++++++ 1 file changed, 13 insertions(+) create mode 100644 xmlcleanup2.sed (limited to 'xmlcleanup2.sed') diff --git a/xmlcleanup2.sed b/xmlcleanup2.sed new file mode 100644 index 0000000..5352a92 --- /dev/null +++ b/xmlcleanup2.sed @@ -0,0 +1,13 @@ +#!/bin/sed -f +# sed rules that must run after the main set + +# tags seem to duplicate tags for some quotes +# NOTE this assumes e tags only come at end of lines +s/.*$//g +# TODO: make this work instead of the above +#s/.*?<\/e>//g + +# any xml tags not processed can just go away +s/<[^>]*>//g +# any xml character entities not processed can just go away +s/&[^;]*;//g -- cgit v1.2.3