add cluster tests

2 files changed, 6 insertions, 4 deletions

diff --git a/fuzzycat/cluster.py b/fuzzycat/cluster.py
index a40db06..b2f739f 100644
--- a/fuzzycat/cluster.py
+++ b/fuzzycat/cluster.py
@@ -6,13 +6,13 @@ Clustering stage.
 import fileinput
 import itertools
 import json
+import logging
 import operator
 import os
 import re
 import subprocess
 import sys
 import tempfile
-import logging
 
 import fuzzy
 
@@ -29,6 +29,7 @@ get_ident_title = operator.itemgetter("ident", "title")
 ws_replacer = str.maketrans({"\t": " ", "\n": " "})
 non_word_re = re.compile(r'[\W_]+', re.UNICODE)
 
+
 def release_key_title(release_entity):
     id, title = get_ident_title(release_entity)
     if not title:
@@ -48,6 +49,7 @@ def release_key_title_nysiis(release_entity):
     id, title = release_key_title(release_entity)
     return (id, fuzzy.nysiis(title))
 
+
 def release_key_title_authors_ngram(release_entity):
     """
     Derive a key from title and authors.
@@ -55,7 +57,6 @@ def release_key_title_authors_ngram(release_entity):
     # SS: compare ngram sets?
 
 
-
 def sort_by_column(filename, opts="-k 2", fast=True, mode="w", prefix="fuzzycat-", tmpdir=None):
     """
     Sort tabular file with sort(1), returns the filename of the sorted file.
@@ -81,8 +82,9 @@ def group_by(seq, key=None, value=None, comment=""):
         doc = {
             "k": k.strip(),
             "v": [value(v) for v in g],
-            "c": comment,
         }
+        if comment:
+            doc["c"] = comment
         yield doc
 
 
diff --git a/fuzzycat/main.py b/fuzzycat/main.py
index 44e0857..5f9efc3 100644
--- a/fuzzycat/main.py
+++ b/fuzzycat/main.py
@@ -11,9 +11,9 @@ Run, e.g. fuzzycat cluster --help for more options. Example:
 """
 
 import argparse
+import logging
 import sys
 import tempfile
-import logging
 
 from fuzzycat.cluster import (Cluster, release_key_title, release_key_title_normalized,
                               release_key_title_nysiis)