diff options
| author | Patrick Simianer <pks@pks.rocks> | 2020-08-12 07:32:06 +0200 |
|---|---|---|
| committer | Patrick Simianer <pks@pks.rocks> | 2020-08-12 07:32:06 +0200 |
| commit | 64e8bdba930479249b8dfbc4b5d4b659a95433f0 (patch) | |
| tree | e26969b03d8380ee8d2cbc1328f851772006133c /de-sgm | |
| parent | 74e20e00dfbffdcf117778049e47acd79e320110 (diff) | |
| parent | 4732fb3be94ba3f88b18295cf1c00e8c616eec73 (diff) | |
Merge branch 'master' of ssh://github.com/pks/nlp_scripts
Diffstat (limited to 'de-sgm')
| -rwxr-xr-x | de-sgm | 14 |
1 files changed, 10 insertions, 4 deletions
@@ -1,7 +1,13 @@ #!/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>$||" +egrep -v -i "^[[:space:]]*(<\?xml.*\?>|</?(mteval|doc|srcset|refset|translator|reviewer)[^>]*>)[[:space:]]*$" \ + | egrep -v -i "^[[:space:]]*<(url|description|keywords|talkid|title|translator|reviewer)[^>]*>.*</(url|description|keywords|talkid|title|translator|reviewer)>[[:space:]]*$" \ + | sed "s|<seg[^>]*>\s*||" \ + | sed "s|\s*</seg>\s*$||" \ + | egrep -v -i "^[[:space:]]*<p>[[:space:]]*$|^[[:space:]]*</p>[[:space:]]*$" \ + | sed "s|<speaker>\s*||" \ + | sed "s|\s*</speaker>\s*$||" \ + | sed "s|\s*<hl>\s*$||" \ + | sed "s|\s*</hl>\s*$||" \ + | grep -v -P "^\s*$" |