commit ecc793da0777eafd3c183f7b160cd0647c93d61b
Author: Lukas Winkler <git@lw1.at>
Date:   Tue Apr 27 19:04:08 2021 +0200

    initial version

diff --git a/input.csv b/input.csv
new file mode 100644
index 0000000..9b18c00
--- /dev/null
+++ b/input.csv
@@ -0,0 +1,4 @@
+label	nb_visits
+somelabel|anotherlabel	1423
+somelabel|anotherlabel|test	1187
+test|word	1131
diff --git a/out.csv b/out.csv
new file mode 100644
index 0000000..25de6e0
--- /dev/null
+++ b/out.csv
@@ -0,0 +1,4 @@
+somelabel;2610
+anotherlabel;2610
+test;2318
+word;1131
diff --git a/script.py b/script.py
new file mode 100644
index 0000000..a732c10
--- /dev/null
+++ b/script.py
@@ -0,0 +1,27 @@
+from pathlib import Path
+from sys import argv
+
+inputfile = Path(argv[1])
+outputfile = Path(argv[2])
+
+counter = {}
+
+with inputfile.open() as ip:
+    next(ip)  # skip the first line
+    for line in ip:  # go through all lines
+        columns = line.split("\t")
+        value = int(columns[1])
+        names = columns[0].split("|")
+        for name in names:
+            if name not in counter:
+                # if this is the first time the name showed up,
+                # set the counter to the value
+                counter[name] = value
+            else:
+                # otherwise increase it by the value
+                counter[name] += value
+print(counter)
+
+with outputfile.open("w") as wf:
+    for name, count in counter.items():
+        wf.write(f"{name};{count}\n")  # Cinema;4