move helpers to utils

4 files changed, 30 insertions, 27 deletions

diff --git a/fuzzycat/utils.py b/fuzzycat/utils.py
index 7a8f067..4d1325d 100644
--- a/fuzzycat/utils.py
+++ b/fuzzycat/utils.py
@@ -1,9 +1,13 @@
 import io
 import itertools
+import re
 import string
 
 printable_no_punct = string.digits + string.ascii_letters + string.whitespace
 
+# More correct: https://www.johndcook.com/blog/2016/02/04/regular-expression-to-match-a-chemical-element/
+CHEM_FORMULA = re.compile(r"([A-Z]{1,2}[0-9]{1,2})+")
+
 
 def slugify_string(s: str) -> str:
     """
@@ -67,3 +71,22 @@ def nwise(iterable, n=2):
     while piece:
         yield piece
         piece = tuple(itertools.islice(i, n))
+
+
+def num_project(s):
+    """
+    Cf. https://fatcat.wiki/release/6b5yupd7bfcw7gp73hjoavbgfq,
+    https://fatcat.wiki/release/7hgzqz3hrngq7omtwdxz4qx34u
+
+    Unify every occurence of a digit (or group of digits).
+    """
+    return re.sub(r'\d+', '<NUM>', s)
+
+
+def contains_chemical_formula(s):
+    """
+    Returns true, if we find C3H8O or the like in title.
+    """
+    for token in s.split():
+        if CHEM_FORMULA.search(token):
+            return True
diff --git a/fuzzycat/verify.py b/fuzzycat/verify.py
index 0fb9358..ab26603 100644
--- a/fuzzycat/verify.py
+++ b/fuzzycat/verify.py
@@ -66,15 +66,13 @@ import re
 import sys
 
 from fuzzycat.common import OK, Miss, Status
-from fuzzycat.utils import author_similarity_score, slugify_string
+from fuzzycat.utils import (author_similarity_score, contains_chemical_formula, num_project,
+                            slugify_string)
 
 # The result of clustering are documents that have a key k and a list of values
 # (of the cluster) v.
 get_key_values = operator.itemgetter("k", "v")
 
-# More correct: https://www.johndcook.com/blog/2016/02/04/regular-expression-to-match-a-chemical-element/
-CHEM_FORMULA = re.compile(r"([A-Z]{1,2}[0-9]{1,2})+")
-
 
 class GroupVerifier:
     """
@@ -319,25 +317,6 @@ def compare(a, b):
     return (Status.AMBIGUOUS, OK.DUMMY)
 
 
-def num_project(s):
-    """
-    Cf. https://fatcat.wiki/release/6b5yupd7bfcw7gp73hjoavbgfq,
-    https://fatcat.wiki/release/7hgzqz3hrngq7omtwdxz4qx34u
-
-    Unify every occurence of a digit (or group of digits).
-    """
-    return re.sub(r'\d+', '<NUM>', s)
-
-
-def contains_chemical_formula(s):
-    """
-    Returns true, if we find C3H8O or the like in title.
-    """
-    for token in s.split():
-        if CHEM_FORMULA.search(token):
-            return True
-
-
 TITLE_FRAGMENT_BLACKLIST = set([
     "air quality data from the life+respira project in pamplona",
     "animaux vivants exclus ceux de la division",
diff --git a/tests/test_utils.py b/tests/test_utils.py
index bc0d918..9357fe8 100644
--- a/tests/test_utils.py
+++ b/tests/test_utils.py
@@ -1,6 +1,7 @@
 import pytest
 
-from fuzzycat.utils import author_similarity_score, cut, slugify_string, jaccard, token_n_grams, tokenize_string, nwise
+from fuzzycat.utils import (author_similarity_score, cut, jaccard, nwise, slugify_string,
+                            token_n_grams, tokenize_string)
 
 
 def test_slugify_string():
@@ -62,4 +63,3 @@ def test_nwise():
     assert list(nwise("1234")) == [("1", "2"), ("3", "4")]
     assert list(nwise("1234", n=1)) == [("1", ), ("2", ), ("3", ), ("4", )]
     assert list(nwise([1, 2, 3, 4, 5], n=3)) == [(1, 2, 3), (4, 5)]
-
diff --git a/tests/test_verify.py b/tests/test_verify.py
index 75e0277..90a22b5 100644
--- a/tests/test_verify.py
+++ b/tests/test_verify.py
@@ -1,8 +1,9 @@
-import pytest
 import csv
 import json
-import os
 import logging
+import os
+
+import pytest
 
 from fuzzycat.verify import Status, compare