cats en tags

2026-04-01 19:30:10 +02:00
parent 1fb1867550
commit e550b58889
14 changed files with 61 additions and 22 deletions
--- a/Sargasso/cmd/xml2txt/xml2txt.go
+++ b/Sargasso/cmd/xml2txt/xml2txt.go
@@ -57,7 +57,7 @@ func main() {
 		var item Item
 		x(xml.Unmarshal(b, &item))
 		for _, cat := range item.Cats {
-			x(fmt.Fprintf(fp, "##META text cat = %s\n", fixSpace(cat)))
+			x(fmt.Fprintf(fp, "##META text tag = %s\n", fixSpace(cat)))
 		}
 		x(fp.WriteString(addEnd(fixSpace(item.Title))))
 		doc, err := gokogiri.ParseHtml([]byte(`<html><body>` + item.Text + `</body></html>`))
--- a/Sargasso/txt2corpus.sh
+++ b/Sargasso/txt2corpus.sh
@@ -58,6 +58,9 @@ Alpino -flag treebank xml debug=1 end_hook=xml user_max=900000 -parse < $corpus.
 cd xml
 alto -o $corpus.data.dz *.xml 2> /dev/null

+# telling per bericht, niet per zin
+/net/corpora/nlnieuws/namen.sh -x 10 -s $corpus.data.dz > $corpus.tag.txt
+
 cd ../..
 rm -fr out