X-Git-Url: https://wannabe.guru.org/gitweb/?a=blobdiff_plain;f=string_utils.py;h=6f3cc90ed46f5c238b0887848c1cf7504ec3bcc0;hb=90dc74b2ff8f36dd2495632a8150ce37dab61f1c;hp=1ed9b4ad10790685290838cd30a2322d59b1b373;hpb=e596cc5a8f9cd58d88ad11d177a21eb25895f083;p=python_utils.git

diff --git a/string_utils.py b/string_utils.py
index 1ed9b4a..6f3cc90 100644
--- a/string_utils.py
+++ b/string_utils.py
@@ -72,9 +72,7 @@ URLS_RE = re.compile(r"({})".format(URLS_RAW_STRING), re.IGNORECASE)
 
 ESCAPED_AT_SIGN = re.compile(r'(?!"[^"]*)@+(?=[^"]*")|\\@')
 
-EMAILS_RAW_STRING = (
-    r"[a-zA-Z\d._\+\-'`!%#$&*/=\?\^\{\}\|~\\]+@[a-z\d-]+\.?[a-z\d-]+\.[a-z]{2,4}"
-)
+EMAILS_RAW_STRING = r"[a-zA-Z\d._\+\-'`!%#$&*/=\?\^\{\}\|~\\]+@[a-z\d-]+\.?[a-z\d-]+\.[a-z]{2,4}"
 
 EMAIL_RE = re.compile(r"^{}$".format(EMAILS_RAW_STRING))
 
@@ -84,13 +82,9 @@ CAMEL_CASE_TEST_RE = re.compile(r"^[a-zA-Z]*([a-z]+[A-Z]+|[A-Z]+[a-z]+)[a-zA-Z\d
 
 CAMEL_CASE_REPLACE_RE = re.compile(r"([a-z]|[A-Z]+)(?=[A-Z])")
 
-SNAKE_CASE_TEST_RE = re.compile(
-    r"^([a-z]+\d*_[a-z\d_]*|_+[a-z\d]+[a-z\d_]*)$", re.IGNORECASE
-)
+SNAKE_CASE_TEST_RE = re.compile(r"^([a-z]+\d*_[a-z\d_]*|_+[a-z\d]+[a-z\d_]*)$", re.IGNORECASE)
 
-SNAKE_CASE_TEST_DASH_RE = re.compile(
-    r"([a-z]+\d*-[a-z\d-]*|-+[a-z\d]+[a-z\d-]*)$", re.IGNORECASE
-)
+SNAKE_CASE_TEST_DASH_RE = re.compile(r"([a-z]+\d*-[a-z\d-]*|-+[a-z\d]+[a-z\d-]*)$", re.IGNORECASE)
 
 SNAKE_CASE_REPLACE_RE = re.compile(r"(_)([a-z\d])")
 
@@ -107,9 +101,7 @@ CREDIT_CARDS = {
 
 JSON_WRAPPER_RE = re.compile(r"^\s*[\[{]\s*(.*)\s*[\}\]]\s*$", re.MULTILINE | re.DOTALL)
 
-UUID_RE = re.compile(
-    r"^[a-f\d]{8}-[a-f\d]{4}-[a-f\d]{4}-[a-f\d]{4}-[a-f\d]{12}$", re.IGNORECASE
-)
+UUID_RE = re.compile(r"^[a-f\d]{8}-[a-f\d]{4}-[a-f\d]{4}-[a-f\d]{4}-[a-f\d]{12}$", re.IGNORECASE)
 
 UUID_HEX_OK_RE = re.compile(
     r"^[a-f\d]{8}-?[a-f\d]{4}-?[a-f\d]{4}-?[a-f\d]{4}-?[a-f\d]{12}$",
@@ -126,9 +118,7 @@ ANYWHERE_IP_V6_RE = re.compile(r"([a-z\d]{0,4}:){7}[a-z\d]{0,4}", re.IGNORECASE)
 
 MAC_ADDRESS_RE = re.compile(r"^([0-9A-F]{2}[:-]){5}([0-9A-F]{2})$", re.IGNORECASE)
 
-ANYWHERE_MAC_ADDRESS_RE = re.compile(
-    r"([0-9A-F]{2}[:-]){5}([0-9A-F]{2})", re.IGNORECASE
-)
+ANYWHERE_MAC_ADDRESS_RE = re.compile(r"([0-9A-F]{2}[:-]){5}([0-9A-F]{2})", re.IGNORECASE)
 
 WORDS_COUNT_RE = re.compile(r"\W*[^\W_]+\W*", re.IGNORECASE | re.MULTILINE | re.UNICODE)
 
@@ -418,9 +408,7 @@ def add_thousands_separator(in_str: str, *, separator_char=',', places=3) -> str
     if isinstance(in_str, numbers.Number):
         in_str = f'{in_str}'
     if is_number(in_str):
-        return _add_thousands_separator(
-            in_str, separator_char=separator_char, places=places
-        )
+        return _add_thousands_separator(in_str, separator_char=separator_char, places=places)
     raise ValueError(in_str)
 
 
@@ -1366,20 +1354,23 @@ def make_contractions(txt: str) -> str:
         ),
     ]
 
-    # Special cases
+    # Special cases: can't, shan't and won't.
     txt = re.sub(r'\b(can)\s*no(t)\b', r"\1'\2", txt, count=0, flags=re.IGNORECASE)
+    txt = re.sub(r'\b(sha)ll\s*(n)o(t)\b', r"\1\2'\3", txt, count=0, flags=re.IGNORECASE)
     txt = re.sub(
-        r'\b(sha)ll\s*(n)o(t)\b', r"\1\2'\3", txt, count=0, flags=re.IGNORECASE
-    )
-    txt = re.sub(
-        r'\b(w)ill\s*(n)(o)(t)\b', r"\1\3\2'\4", txt, count=0, flags=re.IGNORECASE
+        r'\b(w)ill\s*(n)(o)(t)\b',
+        r"\1\3\2'\4",
+        txt,
+        count=0,
+        flags=re.IGNORECASE,
     )
 
     for first_list, second_list in first_second:
         for first in first_list:
             for second in second_list:
-                # Disallow there're.  It's valid English but sounds weird.
-                if first == 'there' and second == 'a(re)':
+                # Disallow there're/where're.  They're valid English
+                # but sound weird.
+                if (first == 'there' or first == 'where') and second == 'a(re)':
                     continue
 
                 pattern = fr'\b({first})\s+{second}\b'
@@ -1589,9 +1580,7 @@ def chunk(txt: str, chunk_size):
         yield txt[x : x + chunk_size]
 
 
-def to_bitstring(
-    txt: str, *, delimiter='', encoding='utf-8', errors='surrogatepass'
-) -> str:
+def to_bitstring(txt: str, *, delimiter='', encoding='utf-8', errors='surrogatepass') -> str:
     """Encode txt and then chop it into bytes.  Note: only bitstrings
     with delimiter='' are interpretable by from_bitstring.