Merge pull request #27 from finos-voice/matthew/FixTests

fix tests broken by phone number regex

asrtoolkit/clean_formatting.py

@@ -188,7 +188,7 @@ def fraction_to_string(input_string):
     ("websites", (re.compile(r"[.](net|org|com|gov)\b"), lambda m: " dot " + m.group().lower().replace(".", ""))),
     (
       "phone_numbers", (
-        re.compile(r"\b((1|44)[ -.]?)?([\(]?([0-9]{1,}[\)]?[ -.]?){2,})[0-9]{4}\b"),
+        re.compile(r"\b((1|44)[ -.]?)?([\(]?([0-9]{1,}[\)]?[ -.]?){2,5})[0-9]{4}\b"),
         lambda m: " ".join(digits_to_string(_) for _ in m.group() if _.isdigit())
       )
     ),

requirements.txt

@@ -6,3 +6,4 @@ termcolor>=1.1.0
 tqdm>=4.27.0
 webvtt-py>=0.4.2
 pandas>0.20.0
+xlrd>=1.0

setup.py

@@ -12,7 +12,7 @@
 
 setup(
   name='asrtoolkit',
-  version='0.1.10',
+  version='0.1.11',
   description=
   'The GreenKey ASRToolkit provides tools for automatic speech recognition (ASR) file conversion and corpora organization.',
   long_description=long_description,

tests/test_xlsx_extraction.py

@@ -3,7 +3,7 @@
 Test xlsx extraction
 """
 
-import hashlib, os
+import os
 from asrtoolkit.extract_excel_spreadsheets import proc_input_dir_to_corpus