add implementation

Author: picnixz

Lib/uuid.py

@@ -1,8 +1,9 @@
 r"""UUID objects (universally unique identifiers) according to RFC 4122.
 
 This module provides immutable UUID objects (class UUID) and the functions
-uuid1(), uuid3(), uuid4(), uuid5() for generating version 1, 3, 4, and 5
-UUIDs as specified in RFC 4122.
+uuid1(), uuid3(), uuid4(), uuid5() for generating version 1 to 8 UUIDs as
+specified in RFC 4122 (superseeded by RFC 9562 but will still be referred
+to as RFC 4122 in the future for compatibility purposes).
 
 If all you want is a unique ID, you should probably call uuid1() or uuid4().
 Note that uuid1() may compromise privacy since it creates a UUID containing
@@ -129,7 +130,7 @@ class UUID:
         variant     the UUID variant (one of the constants RESERVED_NCS,
                     RFC_4122, RESERVED_MICROSOFT, or RESERVED_FUTURE)
 
-        version     the UUID version number (1 through 5, meaningful only
+        version     the UUID version number (1 through 8, meaningful only
                     when the variant is RFC_4122)
 
         is_safe     An enum indicating whether the UUID has been generated in
@@ -214,9 +215,9 @@ def __init__(self, hex=None, bytes=None, bytes_le=None, fields=None,
             if not 0 <= int < 1<<128:
                 raise ValueError('int is out of range (need a 128-bit value)')
         if version is not None:
-            if not 1 <= version <= 5:
+            if not 1 <= version <= 8:
                 raise ValueError('illegal version number')
-            # Set the variant to RFC 4122.
+            # Set the variant to RFC 9562.
             int &= ~(0xc000 << 48)
             int |= 0x8000 << 48
             # Set the version number.
@@ -297,17 +298,29 @@ def bytes_le(self):
 
     @property
     def fields(self):
+        if self.version == 6:
+            # the first field should be a 32-bit integer
+            return (self.time_hi, self.time_mid, self.time_hi_version,
+                    self.clock_seq_hi_variant, self.clock_seq_low, self.node)
         return (self.time_low, self.time_mid, self.time_hi_version,
                 self.clock_seq_hi_variant, self.clock_seq_low, self.node)
 
     @property
     def time_low(self):
+        if self.version == 6:
+            return (self.int >> 64) & 0x0fff
         return self.int >> 96
 
     @property
     def time_mid(self):
         return (self.int >> 80) & 0xffff
 
+    @property
+    def time_hi(self):
+        if self.version == 6:
+            return self.int >> 96
+        return (self.int >> 64) & 0x0fff
+
     @property
     def time_hi_version(self):
         return (self.int >> 64) & 0xffff
@@ -322,8 +335,9 @@ def clock_seq_low(self):
 
     @property
     def time(self):
-        return (((self.time_hi_version & 0x0fff) << 48) |
-                (self.time_mid << 32) | self.time_low)
+        if self.version == 6:
+            return (self.time_hi << 28) | (self.time_mid << 12) | self.time_low
+        return (self.time_hi << 48) | (self.time_mid << 32) | self.time_low
 
     @property
     def clock_seq(self):
@@ -656,7 +670,7 @@ def getnode():
     assert False, '_random_getnode() returned invalid value: {}'.format(_node)
 
 
-_last_timestamp = None
+_last_timestamp_v1 = None
 
 def uuid1(node=None, clock_seq=None):
     """Generate a UUID from a host ID, sequence number, and the current time.
@@ -674,15 +688,15 @@ def uuid1(node=None, clock_seq=None):
             is_safe = SafeUUID.unknown
         return UUID(bytes=uuid_time, is_safe=is_safe)
 
-    global _last_timestamp
+    global _last_timestamp_v1
     import time
     nanoseconds = time.time_ns()
     # 0x01b21dd213814000 is the number of 100-ns intervals between the
     # UUID epoch 1582-10-15 00:00:00 and the Unix epoch 1970-01-01 00:00:00.
     timestamp = nanoseconds // 100 + 0x01b21dd213814000
-    if _last_timestamp is not None and timestamp <= _last_timestamp:
-        timestamp = _last_timestamp + 1
-    _last_timestamp = timestamp
+    if _last_timestamp_v1 is not None and timestamp <= _last_timestamp_v1:
+        timestamp = _last_timestamp_v1 + 1
+    _last_timestamp_v1 = timestamp
     if clock_seq is None:
         import random
         clock_seq = random.getrandbits(14) # instead of stable storage
@@ -719,14 +733,97 @@ def uuid5(namespace, name):
     hash = sha1(namespace.bytes + name).digest()
     return UUID(bytes=hash[:16], version=5)
 
+_last_timestamp_v6 = None
+
+def uuid6(node=None, clock_seq=None):
+    """Similar to :func:`uuid1` but where fields are ordered differently
+    for improved DB locality.
+
+    More precisely, given a 60-bit timestamp value as specified for UUIDv1,
+    for UUIDv6 the first 48 most significant bits are stored first, followed
+    by the 4-bit version (same position), followed by the remaining 12 bits
+    of the original 60-bit timestamp.
+    """
+    global _last_timestamp_v6
+    import time
+    nanoseconds = time.time_ns()
+    # 0x01b21dd213814000 is the number of 100-ns intervals between the
+    # UUID epoch 1582-10-15 00:00:00 and the Unix epoch 1970-01-01 00:00:00.
+    timestamp = nanoseconds // 100 + 0x01b21dd213814000
+    if _last_timestamp_v6 is not None and timestamp <= _last_timestamp_v6:
+        timestamp = _last_timestamp_v6 + 1
+    _last_timestamp_v6 = timestamp
+    if clock_seq is None:
+        import random
+        clock_seq = random.getrandbits(14) # instead of stable storage
+    time_hi_and_mid = (timestamp >> 12) & 0xffffffffffff
+    time_ver_and_lo = timestamp & 0xffff
+    var_and_clock_s = clock_seq & 0x3fff
+    if node is None:
+        node = getnode()
+    int_uuid_6 = time_hi_and_mid << 80
+    int_uuid_6 |= time_ver_and_lo << 64
+    int_uuid_6 |= var_and_clock_s << 48
+    int_uuid_6 |= node & 0xffffffffffff
+    return UUID(int=int_uuid_6, version=6)
+
+_last_timestamp_v7 = None
+
+def uuid7():
+    """Generate a UUID from a Unix timestamp in milliseconds and random bits."""
+    global _last_timestamp_v7
+    import time
+    nanoseconds = time.time_ns()
+    timestamp_ms = nanoseconds // 10 ** 6  # may be improved
+    if _last_timestamp_v7 is not None and timestamp_ms <= _last_timestamp_v7:
+        timestamp_ms = _last_timestamp_v7 + 1
+    _last_timestamp_v7 = timestamp_ms
+    int_uuid_7 = (timestamp_ms & 0xffffffffffff) << 80
+    # Ideally, we would have 'rand_a' = first 12 bits of 'rand'
+    # and 'rand_b' = lowest 62 bits, but it is easier to test
+    # when we pick 'rand_a' from the lowest bits of 'rand' and
+    # 'rand_b' from the next 62 bits, ignoring the first bits
+    # of 'rand'.
+    rand = int.from_bytes(os.urandom(19))  # 76 random bits (ignore 2 first)
+    int_uuid_7 |= (rand & 0x0fff) << 64  # rand_a
+    int_uuid_7 |= (rand >> 12) & 0x3fffffffffffffff  # rand_b
+    return UUID(int=int_uuid_7, version=7)
+
+def uuid8(a=None, b=None, c=None):
+    """Generate a UUID from three custom blocks.
+
+    'a' is the first 48-bit chunk of the UUID (octets 0-5);
+    'b' is the mid 12-bit chunk (octets 6-7);
+    'c' is the last 62-bit chunk (octets 8-15).
+
+    When a value is not specified, a random value is generated.
+    """
+    if a is None:
+        import random
+        a = random.getrandbits(48)
+    if b is None:
+        import random
+        b = random.getrandbits(12)
+    if c is None:
+        import random
+        c = random.getrandbits(62)
+
+    int_uuid_8 = (a & 0xffffffffffff) << 80
+    int_uuid_8 |= (b & 0xfff) << 64
+    int_uuid_8 |= c & 0x3fffffffffffffff
+    return UUID(int=int_uuid_8, version=8)
+
 
 def main():
     """Run the uuid command line interface."""
     uuid_funcs = {
         "uuid1": uuid1,
         "uuid3": uuid3,
         "uuid4": uuid4,
-        "uuid5": uuid5
+        "uuid5": uuid5,
+        "uuid6": uuid6,
+        "uuid7": uuid7,
+        "uuid8": uuid8,
     }
     uuid_namespace_funcs = ("uuid3", "uuid5")
     namespaces = {