Don't be tricked by speaker groups living on the same IP address

[python_utils.git] / string_utils.py

diff --git a/string_utils.py b/string_utils.py
index 623ae45f03e6eb12c608f966b421ba9c5495b0e9..6eda2783ea7aafa67bcc4f492825c2aa1bab1cc9 100644 (file)
--- a/string_utils.py
+++ b/string_utils.py
@@ -14,6 +14,7 @@ import string
 from typing import Any, Callable, Dict, Iterable, List, Optional, Sequence, Tuple
 import unicodedata
 from uuid import uuid4
+import warnings
 
 import list_utils
 
@@ -791,6 +792,9 @@ def extract_mac_address(in_str: Any, *, separator: str = ":") -> Optional[str]:
     >>> extract_mac_address(' MAC Address: 34:29:8F:12:0D:2F')
     '34:29:8F:12:0D:2F'
 
+    >>> extract_mac_address('? (10.0.0.30) at d8:5d:e2:34:54:86 on em0 expires in 1176 seconds [ethernet]')
+    'd8:5d:e2:34:54:86'
+
     """
     if not is_full_string(in_str):
         return None
@@ -858,16 +862,16 @@ def words_count(in_str: str) -> int:
     return len(WORDS_COUNT_RE.findall(in_str))
 
 
-def generate_uuid(as_hex: bool = False) -> str:
+def generate_uuid(omit_dashes: bool = False) -> str:
     """
     Generated an UUID string (using `uuid.uuid4()`).
 
     generate_uuid() # possible output: '97e3a716-6b33-4ab9-9bb1-8128cb24d76b'
-    generate_uuid(as_hex=True) # possible output: '97e3a7166b334ab99bb18128cb24d76b'
+    generate_uuid(omit_dashes=True) # possible output: '97e3a7166b334ab99bb18128cb24d76b'
 
     """
     uid = uuid4()
-    if as_hex:
+    if omit_dashes:
         return uid.hex
     return str(uid)
 
@@ -1094,7 +1098,8 @@ def to_date(in_str: str) -> Optional[datetime.date]:
         d.parse(in_str)
         return d.get_date()
     except dp.ParseException:
-        logger.warning(f'Unable to parse date {in_str}.')
+        msg = f'Unable to parse date {in_str}.'
+        logger.warning(msg)
     return None
 
 
@@ -1108,7 +1113,8 @@ def valid_date(in_str: str) -> bool:
         _ = d.parse(in_str)
         return True
     except dp.ParseException:
-        logger.warning(f'Unable to parse date {in_str}.')
+        msg = f'Unable to parse date {in_str}.'
+        logger.warning(msg)
     return False
 
 
@@ -1123,7 +1129,8 @@ def to_datetime(in_str: str) -> Optional[datetime.datetime]:
         if type(dt) == datetime.datetime:
             return dt
     except ValueError:
-        logger.warning(f'Unable to parse datetime {in_str}.')
+        msg = f'Unable to parse datetime {in_str}.'
+        logger.warning(msg)
     return None
 
 
@@ -1134,10 +1141,29 @@ def valid_datetime(in_str: str) -> bool:
     _ = to_datetime(in_str)
     if _ is not None:
         return True
-    logger.warning(f'Unable to parse datetime {in_str}.')
+    msg = f'Unable to parse datetime {in_str}.'
+    logger.warning(msg)
     return False
 
 
+def squeeze(in_str: str, character_to_squeeze: str = ' ') -> str:
+    """
+    Squeeze runs of more than one character_to_squeeze into one.
+
+    >>> squeeze(' this        is       a    test    ')
+    ' this is a test '
+
+    >>> squeeze('one|!||!|two|!||!|three', character_to_squeeze='|!|')
+    'one|!|two|!|three'
+
+    """
+    return re.sub(
+        r'(' + re.escape(character_to_squeeze) + r')+',
+        character_to_squeeze,
+        in_str
+    )
+
+
 def dedent(in_str: str) -> str:
     """
     Removes tab indentation from multi line strings (inspired by analogous Scala function).
@@ -1445,8 +1471,9 @@ def chunk(txt: str, chunk_size):
 
     """
     if len(txt) % chunk_size != 0:
-        logger.warning(
-            f'String to chunk\'s length ({len(txt)} is not an even multiple of chunk_size ({chunk_size})')
+        msg = f'String to chunk\'s length ({len(txt)} is not an even multiple of chunk_size ({chunk_size})'
+        logger.warning(msg)
+        warnings.warn(msg, stacklevel=2)
     for x in range(0, len(txt), chunk_size):
         yield txt[x:x+chunk_size]
 
@@ -1461,10 +1488,14 @@ def to_bitstring(txt: str, *, delimiter='', encoding='utf-8', errors='surrogatep
     >>> to_bitstring('test', delimiter=' ')
     '01110100 01100101 01110011 01110100'
 
+    >>> to_bitstring(b'test')
+    '01110100011001010111001101110100'
+
     """
+    etxt = to_ascii(txt)
     bits = bin(
         int.from_bytes(
-            txt.encode(encoding, errors),
+            etxt,
             'big'
         )
     )
@@ -1496,6 +1527,51 @@ def from_bitstring(bits: str, encoding='utf-8', errors='surrogatepass') -> str:
     return n.to_bytes((n.bit_length() + 7) // 8, 'big').decode(encoding, errors) or '\0'
 
 
+def ip_v4_sort_key(txt: str) -> Tuple[int]:
+    """Turn an IPv4 address into a tuple for sorting purposes.
+
+    >>> ip_v4_sort_key('10.0.0.18')
+    (10, 0, 0, 18)
+
+    >>> ips = ['10.0.0.10', '100.0.0.1', '1.2.3.4', '10.0.0.9']
+    >>> sorted(ips, key=lambda x: ip_v4_sort_key(x))
+    ['1.2.3.4', '10.0.0.9', '10.0.0.10', '100.0.0.1']
+
+    """
+    if not is_ip_v4(txt):
+        print(f"not IP: {txt}")
+        return None
+    return tuple([int(x) for x in txt.split('.')])
+
+
+def path_ancestors_before_descendants_sort_key(volume: str) -> Tuple[str]:
+    """Chunk up a file path so that parent/ancestor paths sort before
+    children/descendant paths.
+
+    >>> path_ancestors_before_descendants_sort_key('/usr/local/bin')
+    ('usr', 'local', 'bin')
+
+    >>> paths = ['/usr/local', '/usr/local/bin', '/usr']
+    >>> sorted(paths, key=lambda x: path_ancestors_before_descendants_sort_key(x))
+    ['/usr', '/usr/local', '/usr/local/bin']
+
+    """
+    return tuple([x for x in volume.split('/') if len(x) > 0])
+
+
+def replace_all(in_str: str, replace_set: str, replacement: str) -> str:
+    """Execute several replace operations in a row.
+
+    >>> s = 'this_is a-test!'
+    >>> replace_all(s, ' _-!', '')
+    'thisisatest'
+
+    """
+    for char in replace_set:
+        in_str = in_str.replace(char, replacement)
+    return in_str
+
+
 if __name__ == '__main__':
     import doctest
     doctest.testmod()