Compile some of the regexes at the module level

Author: JoshData

email_validator/rfc_constants.py

@@ -1,26 +1,29 @@
 # These constants are defined by the email specifications.
 
+import re
+
 # Based on RFC 2822 section 3.2.4 / RFC 5322 section 3.2.3, these
 # characters are permitted in email addresses (not taking into
 # account internationalization):
 ATEXT = r'a-zA-Z0-9_!#\$%&\'\*\+\-/=\?\^`\{\|\}~'
 
 # A "dot atom text", per RFC 2822 3.2.4:
-DOT_ATOM_TEXT = '[' + ATEXT + ']+(?:\\.[' + ATEXT + ']+)*'
+DOT_ATOM_TEXT = re.compile('[' + ATEXT + ']+(?:\\.[' + ATEXT + r']+)*\Z')
 
 # RFC 6531 section 3.3 extends the allowed characters in internationalized
 # addresses to also include three specific ranges of UTF8 defined in
 # RFC3629 section 4, which appear to be the Unicode code points from
 # U+0080 to U+10FFFF.
 ATEXT_INTL = ATEXT + u"\u0080-\U0010FFFF"
-DOT_ATOM_TEXT_INTL = '[' + ATEXT_INTL + ']+(?:\\.[' + ATEXT_INTL + ']+)*'
+DOT_ATOM_TEXT_INTL = re.compile('[' + ATEXT_INTL + ']+(?:\\.[' + ATEXT_INTL + r']+)*\Z')
 
 # The domain part of the email address, after IDNA (ASCII) encoding,
 # must also satisfy the requirements of RFC 952/RFC 1123 which restrict
 # the allowed characters of hostnames further. The hyphen cannot be at
 # the beginning or end of a *dot-atom component* of a hostname either.
 ATEXT_HOSTNAME = r'(?:(?:[a-zA-Z0-9][a-zA-Z0-9\-]*)?[a-zA-Z0-9])'
-DOT_ATOM_TEXT_HOSTNAME = ATEXT_HOSTNAME + r'(?:\.' + ATEXT_HOSTNAME + r')*'
+DOT_ATOM_TEXT_HOSTNAME = re.compile(ATEXT_HOSTNAME + r'(?:\.' + ATEXT_HOSTNAME + r')*\Z')
+DOMAIN_NAME_REGEX = re.compile(r"[A-Za-z]\Z")  # all TLDs currently end with a letter
 
 # Length constants
 # RFC 3696 + errata 1003 + errata 1690 (https://www.rfc-editor.org/errata_search.php?rfc=3696&eid=1690)

email_validator/syntax.py

@@ -1,6 +1,6 @@
 from .exceptions_types import EmailSyntaxError
 from .rfc_constants import EMAIL_MAX_LENGTH, LOCAL_PART_MAX_LENGTH, DOMAIN_MAX_LENGTH, \
-    DOT_ATOM_TEXT, DOT_ATOM_TEXT_INTL, ATEXT, ATEXT_INTL, DNS_LABEL_LENGTH_LIMIT, DOT_ATOM_TEXT_HOSTNAME
+    DOT_ATOM_TEXT, DOT_ATOM_TEXT_INTL, ATEXT, ATEXT_INTL, DNS_LABEL_LENGTH_LIMIT, DOT_ATOM_TEXT_HOSTNAME, DOMAIN_NAME_REGEX
 
 import re
 import unicodedata
@@ -42,7 +42,7 @@ def validate_email_local_part(local, allow_smtputf8=True, allow_empty_local=Fals
         raise EmailSyntaxError("The email address is too long before the @-sign {}.".format(reason))
 
     # Check the local part against the regular expression for the older ASCII requirements.
-    m = re.match(DOT_ATOM_TEXT + "\\Z", local)
+    m = DOT_ATOM_TEXT.match(local)
     if m:
         # Return the local part unchanged and flag that SMTPUTF8 is not needed.
         return {
@@ -53,7 +53,7 @@ def validate_email_local_part(local, allow_smtputf8=True, allow_empty_local=Fals
 
     else:
         # The local part failed the ASCII check. Now try the extended internationalized requirements.
-        m = re.match(DOT_ATOM_TEXT_INTL + "\\Z", local)
+        m = DOT_ATOM_TEXT_INTL.match(local)
         if not m:
             # It's not a valid internationalized address either. Report which characters were not valid.
             bad_chars = ', '.join(sorted(set(
@@ -141,7 +141,7 @@ def validate_email_domain_part(domain, test_environment=False, globally_delivera
     if ".." in domain:
         raise EmailSyntaxError("An email address cannot have two periods in a row.")
 
-    if re.match(DOT_ATOM_TEXT_HOSTNAME + "\\Z", domain):
+    if DOT_ATOM_TEXT_HOSTNAME.match(domain):
         ascii_domain = domain
     else:
         # If international characters are present in the domain name, convert
@@ -170,7 +170,7 @@ def validate_email_domain_part(domain, test_environment=False, globally_delivera
 
         # Check the syntax of the string returned by idna.encode.
         # It should never fail.
-        m = re.match(DOT_ATOM_TEXT_HOSTNAME + "\\Z", ascii_domain)
+        m = DOT_ATOM_TEXT_HOSTNAME.match(ascii_domain)
         if not m:
             raise EmailSyntaxError("The email address contains invalid characters after the @-sign after IDNA encoding.")
 
@@ -198,7 +198,7 @@ def validate_email_domain_part(domain, test_environment=False, globally_delivera
             raise EmailSyntaxError("The part after the @-sign is not valid. It should have a period.")
 
         # We also know that all TLDs currently end with a letter.
-        if not re.search(r"[A-Za-z]\Z", ascii_domain):
+        if not DOMAIN_NAME_REGEX.search(ascii_domain):
             raise EmailSyntaxError("The part after the @-sign is not valid. It is not within a valid top-level domain.")
 
     # Check special-use and reserved domain names.