normalise isbn searching

ISBNs are always numeric except for when the check digit in ISBN-10s is a ten, indicated with a capital X.
These changes ensure that ISBNs are always upper-case so that a lower-case 'x' is not used when searching.

Additionally some ancient ISBNs have been printed without a leading zero (i.e. they only have 9 characters on the physical book). This change prepends a zero if something looks like an ISBN but only has 9 chars.

bookwyrm/book_search.py

@@ -30,7 +30,9 @@ def isbn_search(query):
     """search your local database"""
     if not query:
         return []
-
+    # Up-case the ISBN string to ensure any 'X' check-digit is correct
+    # If the ISBN has only 9 characters, prepend missing zero
+    query = query.upper().rjust(10, '0')
     filters = [{f: query} for f in ["isbn_10", "isbn_13"]]
     results = models.Edition.objects.filter(
         reduce(operator.or_, (Q(**f) for f in filters))

bookwyrm/connectors/abstract_connector.py

@@ -42,6 +42,9 @@ class AbstractMinimalConnector(ABC):
         """format the query url"""
         # Check if the query resembles an ISBN
         if maybe_isbn(query) and self.isbn_search_url and self.isbn_search_url != "":
+            # Up-case the ISBN string to ensure any 'X' check-digit is correct
+            # If the ISBN has only 9 characters, prepend missing zero
+            query = query.upper().rjust(10, '0')
             return f"{self.isbn_search_url}{query}"
 
         # NOTE: previously, we tried searching isbn and if that produces no results,
@@ -325,4 +328,7 @@ def unique_physical_format(format_text):
 def maybe_isbn(query):
     """check if a query looks like an isbn"""
     isbn = re.sub(r"[\W_]", "", query)  # removes filler characters
-    return len(isbn) in [10, 13]  # ISBN10 or ISBN13
+    # ISBNs must be numeric except an ISBN10 checkdigit can be 'X'
+    if not isbn.rstrip('X').isnumeric():
+        return False
+    return len(isbn) in [9, 10, 13]  # ISBN10 or ISBN13, or maybe   ISBN10 missing a prepended zero