1 files changed, 52 insertions, 0 deletions
diff --git a/run.py b/run.py
new file mode 100755
index 0000000..1551717
--- /dev/null
+++ b/run.py
@@ -0,0 +1,52 @@
+#!/usr/bin/env python3
+
+import fileinput
+import json
+import os
+from urllib.parse import quote_plus
+
+DATADIR = '/home/camil/temp/information-retrieval-data'
+ERRORFILE = 'errors'
+
+def get(dbpediaid):
+    outfile = os.path.join(DATADIR, quote_plus(dbpediaid) + '.json')
+    if not os.path.isfile(outfile):
+        return None
+    with open(outfile) as f:
+        return json.load(f)
+
+def match(value, terms):
+    for v in value.split():
+        if v in terms:
+            return True
+    return False
+
+def run(queries, line):
+    try:
+        query, _, dbpediaid, _, relevance, method = line.split('\t')
+    except ValueError: # For qrels.txt
+        query, _, dbpediaid, relevance = line.split('\t')
+    terms = queries[query].split()
+    try:
+        result = get(dbpediaid)
+        if result is None:
+            return
+        for field, values in result.items():
+            matches = 0
+            for value in values:
+                if match(value, terms):
+                    matches += 1
+            print('{}\t{}\t{}\t{}\t{}\t{}'.format(
+                query, dbpediaid, float(relevance), field, len(values), matches))
+    except Exception as e:
+        print(dbpediaid)
+        print(e)
+        with open(ERRORFILE, 'a') as f:
+            f.write(dbpediaid + '\t' + e + '\n')
+
+if __name__ == '__main__':
+    with open('queries_stopped.json') as f:
+        queries = json.load(f)
+
+        for line in fileinput.input():
+            run(queries, line)