Add preparation scripts

create_corpus_file.py

@@ -0,0 +1,16 @@
+import argparse
+import xml.etree.ElementTree as ET
+
+parser = argparse.ArgumentParser()
+parser.add_argument('-i', dest='input_file', required=True)
+parser.add_argument('--author', dest='author', required=True)
+parser.add_argument('--publishing_year', dest='publishing_year', required=True)
+parser.add_argument('--title', dest='title', required=True)
+args = parser.parse_args()
+
+element_tree = ET.parse(args.input_file)
+text_node = element_tree.find('text')
+text_node.set('author', args.author)
+text_node.set('publishing_year', args.publishing_year)
+text_node.set('title', args.title)
+element_tree.write(args.input_file)

foo.sh

@@ -0,0 +1,17 @@
+echo $0
+vrt_file="$1"
+exit
+
+docker run \
+    -d \
+    pjentsch/cqpserver:latest
+docker exec "$CONTAINER_NAME" mkdir /corpora/data/example
+docker exec "$CONTAINER_NAME" cwb-encode \
+    -d /corpora/data/example \
+    -f /root/files/example.vrt \
+    -R /usr/local/share/cwb/registry/example \
+    text, lemma, simple_pos, pos, ner
+    -P lemma -P simple_pos -P pos -P ner \
+    -S s -S text:
+docker exec "$CONTAINER_NAME" cwb-make \
+    -V EXAMPLE

merge_corpus_files.py

@@ -0,0 +1,21 @@
+import argparse
+import os
+import xml.etree.ElementTree as ET
+
+parser = argparse.ArgumentParser()
+parser.add_argument('-dir', dest='corpus_dir', required=True)
+args = parser.parse_args()
+
+text_nodes = []
+for corpus_file in os.listdir(args.corpus_dir):
+    if os.path.isdir(os.path.join(args.corpus_dir, corpus_file)):
+        continue
+    if corpus_file == 'corpus.vrt':
+        continue
+    element_tree = ET.parse(os.path.join(args.corpus_dir, corpus_file))
+    text_nodes.append(element_tree.find('text'))
+element_tree = ET.ElementTree(ET.fromstring('<corpus></corpus>'))
+root = element_tree.getroot()
+for text_node in text_nodes:
+    root.insert(1, text_node)
+element_tree.write(os.path.join(args.corpus_dir, 'corpus.vrt'))