namen.sh

2026-03-02 21:41:24 +01:00
parent fd750a8d47
commit 4cbe44d43b
1 changed files with 9 additions and 0 deletions
--- a/namen.sh
+++ b/namen.sh
@@ -0,0 +1,9 @@
+#!/bin/bash
+
+cd /net/corpora/nlnieuws
+
+select i in `find . -name '*data.dz' | sort`
+do
+    alto "$i" fp:'//node[@cat="mwu" and node[@pt="spec"] and not(@his="normal") and not(@his_1="decap")]' tt:%w | \
+        sort | uniq -c | sort -nr | head -n 40
+done