verbose

collect.sh

@@ -6,6 +6,20 @@ unset CDPATH
 PATH=/net/corpora/nlnieuws/bin:/net/aps/bin:$PATH
 export TZ=Europe/Amsterdam
 
+verbose=0
+if [ "$1" = "-v" ]
+then
+    shift
+    verbose=1
+fi
+
+say () {
+    if [ "$verbose" = "1" ]
+    then
+        echo "$*"
+    fi
+}
+
 if [ "$1" = "" ]
 then
     ds=`ISOWeek -7`
@@ -57,6 +71,7 @@ do
         # tellingen te voorkomen.
         # Dit speelt alleen(?) bij atom-feeds, zoals van de VRT.
 
+        say $part-nieuwe-namen-$ds-$i
         alto \
             'fp://node[((@cat="mwu" and node[@pt="spec"]) or (@pt and @*="eigen" and not(@rel="mwp"))) and not(@his="normal") and not(@his_1="decap" or @his_1="0")]' \
             'tt:%w\t%d\t%I' $files \
@@ -65,6 +80,7 @@ do
             | items2count > $part-nieuwe-namen-$ds-$i
         top20 $part-nieuwe-namen-$ds-$i
 
+        say $part-nieuwe-woorden-$ds-$i
         alto \
             'fp://node[@his and not(@rel="mwp" or @cat="mwu") and not(@his="normal" or @his="name" or @his="prefix_name" or @his_1="decap" or @his_1="0" or @his="skip" or @his="robust_skip" or @his="w_dia" or @his="wo_dia" or @his="within_word_conjunct")]' \
             'tt:%w\t%d\t%I' $files \
@@ -73,6 +89,7 @@ do
             | items2count > $part-nieuwe-woorden-$ds-$i
         top20 $part-nieuwe-woorden-$ds-$i
 
+        say $part-locaties-$ds-$i
         alto \
             'fp://node[(@neclass="LOC" and not(@rel="mwp")) or (@cat="mwu" and node[@pt="spec" and @neclass="LOC"])]' \
             'tt:%l\t%d\t%I' $files \
@@ -80,6 +97,7 @@ do
             | sed -e 's/\.[0-9][0-9]*$//' | sort | uniq \
             | items2count > $part-locaties-$ds-$i
 
+        say $part-personen-$ds-$i
         alto \
             'fp://node[(@neclass="PER" and not(@rel="mwp")) or (@cat="mwu" and node[@pt="spec" and @neclass="PER"])]' \
             'tt:%l\t%d\t%I' $files \
@@ -87,6 +105,7 @@ do
             | sed -e 's/\.[0-9][0-9]*$//' | sort | uniq \
             | items2count > $part-personen-$ds-$i
 
+        say $part-organisaties-$ds-$i
         alto \
             'fp://node[(@neclass="ORG" and not(@rel="mwp")) or (@cat="mwu" and node[@pt="spec" and @neclass="ORG"])]' \
             'tt:%l\t%d\t%I' $files \
@@ -94,6 +113,7 @@ do
             | sed -e 's/\.[0-9][0-9]*$//' | sort | uniq \
             | items2count > $part-organisaties-$ds-$i
 
+        say $part-overige-namen-$ds-$i
         alto \
             'fp://node[(@neclass="MISC" and not(@rel="mwp")) or (@cat="mwu" and node[@pt="spec" and @neclass="MISC"])]' \
             'tt:%l\t%d\t%I' $files \
@@ -103,6 +123,7 @@ do
 
         # tellingen met postags
 
+        say $part-nieuwe-woorden-extra-$ds-$i
         alto \
             'fp://node[@his and not(@rel="mwp" or @cat="mwu") and not(@his="normal" or @his="name" or @his="prefix_name" or @his_1="decap" or @
         his_1="0" or @his="skip" or @his="robust_skip" or @his="w_dia" or @his="wo_dia" or @his="within_word_conjunct")]' \
@@ -113,6 +134,7 @@ do
             | sed -e 's/\([0-9]\)  */\1\t/' | sort -f -k 2 | sort -n -r -k 1,1 -s \
             > $part-nieuwe-woorden-extra-$ds-$i
 
+        say $part-nieuwe-adjww-extra-$ds-$i
         alto \
             'fp://node[@pt and @his and not(../@his="normal" or @rel="mwp" or ../@his="name" or ../@his_1="decap") and not(@his="normal" or @his="name" or @his="skip" or @his="robust_skip" or @his="w_dia" or @his="wo_dia" or @his="decap" or @his="within_word_conjunct") and not(@pt="n") ]' \
             'tt:%w\t%P\t%I' $files \

www/mkAll.py

@@ -1,7 +1,6 @@
 #!/usr/bin/env python3
 
 import sys
-import os
 import re
 import subprocess
 
@@ -37,6 +36,11 @@ namen = {
         'Tzum': 'Literatuur'
 }
 
+verbose=False
+if sys.argv[1] == '-v':
+    verbose=True
+    sys.argv = sys.argv[:1] + sys.argv[2:]
+
 ep=sys.argv[1]
 if not re.match('^2[0-9][0-9][0-9]-[0-5][0-9]$', ep):
     print("Ongeldig patroon '", ep, "', moet yyyy-ww zijn")
@@ -47,23 +51,20 @@ week=ep[5:].lstrip('0')
 
 for base in ('algemeen', 'VRT', 'groningen', 'AT5', 'Tzum'):
     name = namen[base]
-    fp = open(name + '.html', 'wt', encoding='utf-8')
-    fp.write(head.format(name, jaar, week, name, jaar, week))
-    fp.flush()
-    for part in ('nieuwe-namen', 'nieuwe-woorden', 'personen', 'overige-namen', 'locaties', 'organisaties'):
-        if part == 'locaties':
-            fp.write('</div>\n<div class="main next">\n')
-            fp.flush()
-        top = ''
-        if part.startswith('nieuwe'):
-            top = '.t20'
-        subprocess.run(
-                ['./top2html.py', '../data/{}-{}-{}-4{}'.format(base, part, ep, top)],
-                stdout = fp,
-                check = False)
-    fp.write(tail)
-    fp.close()
-
-
-
-
+    with open(name + '.html', 'wt', encoding='utf-8') as fp:
+        fp.write(head.format(name, jaar, week, name, jaar, week))
+        fp.flush()
+        for part in ('nieuwe-namen', 'nieuwe-woorden', 'personen', 'overige-namen', 'locaties', 'organisaties'):
+            if verbose:
+                print(base, part)
+            if part == 'locaties':
+                fp.write('</div>\n<div class="main next">\n')
+                fp.flush()
+            top = ''
+            if part.startswith('nieuwe'):
+                top = '.t20'
+            subprocess.run(
+                    ['./top2html.py', '../data/{}-{}-{}-4{}'.format(base, part, ep, top)],
+                    stdout = fp,
+                    check = False)
+        fp.write(tail)