text extractions

extractionConfiguration/download.text.properties

+# Default download server. It lists mirrors which may be faster.
+# base-url=https://dumps.wikimedia.org/
+# base-url=https://ftp.acc.umu.se/mirror/wikimedia.org/dumps/
+base-url=http://dumps.wikimedia.your.org/
+
+# the source file name
+# should be the same as in universal.properties
+# source=pages-articles.xml.bz2
+
+# languages to download
+TODO testing for english
+languages=en
+#,af,als,am,an,ar,arz,ast,azb,az,ba,bar,bat-smg,be,bg,bn,bpy,br,bs,bug,ca,cdo,ceb,ce,ckb,cs,cv,cy,da,de,el,eml,eo,es,et,eu,fa,fi,fo,fr,fy,ga,gd,gl,gu,he,hi,hr,hsb,ht,hu,hy,ia,id,ilo,io,is,it,ja,jv,ka,kk,kn,ko,ku,ky,la,lb,li,lmo,lt,lv,mai,mg,mhr,min,mk,ml,mn,mrj,mr,ms,my,mzn,nap,nds,ne,new,nl,nn,no,oc,or,os,pa,pl,pms,pnb,pt,qu,ro,ru,sah,sa,scn,sco,sd,sh,si,simple,sk,sl,sq,sr,su,sv,sw,ta,te,tg,th,tl,tr,tt,uk,ur,uz,vec,vi,vo,wa,war,wuu,xmf,yi,yo,zh,zh-min-nan,zh-yue
+
+# Unzip files while downloading? Not necessary, extraction will unzip on the fly. Let's save space.
+unzip=false
+
+# Sometimes connecting to the server fails, so we try five times with pauses of 10 seconds.
+retry-max=5
+retry-millis=10000
+
+#for specific dump dates (e.g. 20170101) if empty: the most recent dump-date is used
+dump-date=

functions.sh

@@ -34,6 +34,9 @@ extractDumps() {
     then
        >&2 ../run sparkextraction $CONFIGDIR/extraction.generic.properties;
        >&2 ../run sparkextraction $CONFIGDIR/extraction.generic.en.properties;
+    elif ["$GROUP" = "text" ]
+    then
+      >&2 ../run extraction $CONFIGDIR/extraction.$GROUP.en.properties;
     else
 		# run for all 
 	    >&2 ../run extraction $CONFIGDIR/extraction.$GROUP.properties;
@@ -66,7 +69,7 @@ postProcessing() {
 		for i in $(find $EXTRACTIONBASEDIR -name "*._redirects.ttl.bz2") ; do cp $i $LOGDIR ; rename -f 's/_redirected//' $i ; done
     elif [ "$GROUP" = "text" ]
     then
-        echo "TODO"
+        echo "check whether text has post-processing"
 
     elif [ "$GROUP" = "test" ]
     then