blob: 0b9177dfac38e993f08924077ceb0a5561589ba4 (
plain)
1
2
3
4
5
6
7
|
#!/bin/sh
egrep -v "^[[:space:]]*(<\?xml.*\?>|</?(mteval|doc|srcset|refset|translator|reviewer)[^>]*>)[[:space:]]*$" \
| egrep -v "^[[:space:]]*<(url|description|keywords|talkid|title|translator|reviewer)[^>]*>.*</(url|description|keywords|talkid|title|translator|reviewer)>[[:space:]]*$" \
| sed "s|<seg[^>]*>\s*||" | sed "s|\s*</seg>$||" | egrep -v "^[[:space:]]*<p>[[:space:]]*$|^[[:space:]]*</p>[[:space:]]*$"
|