Rename parsers to DATE_REGEX

In moving the `parsers` variable into the package-level, it lost the
context, so a more descriptive name was needed.

src/documents/parsers.py

@@ -13,11 +13,12 @@ from django.conf import settings
 # - XX. MONTH ZZZZ with XX being 1 or 2 and ZZZZ being 2 or 4 digits
 # - MONTH ZZZZ, with ZZZZ being 4 digits
 # - MONTH XX, ZZZZ with XX being 1 or 2 and ZZZZ being 4 digits
-pattern = re.compile(
+DATE_REGEX = re.compile(
     r'\b([0-9]{1,2})[\.\/-]([0-9]{1,2})[\.\/-]([0-9]{4}|[0-9]{2})\b|' +
     r'\b([0-9]{1,2}[\. ]+[^ ]{3,9} ([0-9]{4}|[0-9]{2}))\b|' +
     r'\b([^\W\d_]{3,9} [0-9]{1,2}, ([0-9]{4}))\b|' +
-    r'\b([^\W\d_]{3,9} [0-9]{4})\b')
+    r'\b([^\W\d_]{3,9} [0-9]{4})\b'
+)
 
 
 class ParseError(Exception):

src/paperless_tesseract/parsers.py

@@ -14,7 +14,7 @@ from pyocr.libtesseract.tesseract_raw import \
 from pyocr.tesseract import TesseractError
 
 import pdftotext
-from documents.parsers import DocumentParser, ParseError, pattern
+from documents.parsers import DocumentParser, ParseError, DATE_REGEX
 
 from .languages import ISO639
 
@@ -211,7 +211,7 @@ class RasterisedDocumentParser(DocumentParser):
             return None
 
         # Iterate through all regex matches and try to parse the date
-        for m in re.finditer(pattern, text):
+        for m in re.finditer(DATE_REGEX, text):
             datestring = m.group(0)
 
             try:

src/paperless_text/parsers.py

@@ -5,7 +5,7 @@ import subprocess
 import dateparser
 from django.conf import settings
 
-from documents.parsers import DocumentParser, ParseError, pattern
+from documents.parsers import DocumentParser, ParseError, DATE_REGEX
 
 
 class TextDocumentParser(DocumentParser):
@@ -94,7 +94,7 @@ class TextDocumentParser(DocumentParser):
             return None
 
         # Iterate through all regex matches and try to parse the date
-        for m in re.finditer(pattern, text):
+        for m in re.finditer(DATE_REGEX, text):
             datestring = m.group(0)
 
             try: