18505123992

Committed 14 Oct 2025 05:30PM UTC coverage: 86.888% (-0.01%) from 86.899%

Build # 18505123992

Build Type

push

github

Committed by

web-flow

Commit Message

S3: fix `aws-global` validation in CreateBucket (#13250)

Run Details

10 of 10 new or added lines in 4 files covered. (100.0%)

831 existing lines in 40 files now uncovered.

68028 of 78294 relevant lines covered (86.89%)

0.87 hits per line

Source File
Press 'n' to go to next uncovered line, 'b' for previous

90.55

/localstack-core/localstack/utils/strings.py

import base64
import binascii
import hashlib
import itertools
import random
import re
import string
import uuid
import zlib

from localstack.config import DEFAULT_ENCODING

_unprintables = (
    range(0x00, 0x09),
    range(0x0A, 0x0A),
    range(0x0B, 0x0D),
    range(0x0E, 0x20),
    range(0xD800, 0xE000),
    range(0xFFFE, 0x10000),
)

# regular expression for unprintable characters
# Based on https://docs.aws.amazon.com/AWSSimpleQueueService/latest/APIReference/API_SendMessage.html
#     #x9 | #xA | #xD | #x20 to #xD7FF | #xE000 to #xFFFD | #x10000 to #x10FFFF
REGEX_UNPRINTABLE_CHARS = re.compile(
    f"[{re.escape(''.join(map(chr, itertools.chain(*_unprintables))))}]"
)


def to_str(obj: str | bytes, encoding: str = DEFAULT_ENCODING, errors="strict") -> str:
    """If ``obj`` is an instance of ``binary_type``, return
    ``obj.decode(encoding, errors)``, otherwise return ``obj``"""
    return obj.decode(encoding, errors) if isinstance(obj, bytes) else obj


def to_bytes(obj: str | bytes, encoding: str = DEFAULT_ENCODING, errors="strict") -> bytes:
    """If ``obj`` is an instance of ``text_type``, return
    ``obj.encode(encoding, errors)``, otherwise return ``obj``"""
    return obj.encode(encoding, errors) if isinstance(obj, str) else obj


def truncate(data: str, max_length: int = 100) -> str:
    data = str(data or "")
    return (f"{data[:max_length]}...") if len(data) > max_length else data


def is_string(s, include_unicode=True, exclude_binary=False):
    if isinstance(s, bytes) and exclude_binary:
        return False
    if isinstance(s, str):
        return True
    if include_unicode and isinstance(s, str):
        return True
    return False


def is_string_or_bytes(s):
    return is_string(s) or isinstance(s, str) or isinstance(s, bytes)


def is_base64(s):
    regex = r"^(?:[A-Za-z0-9+/]{4})*(?:[A-Za-z0-9+/]{2}==|[A-Za-z0-9+/]{3}=)?$"
    return is_string(s) and re.match(regex, s)


_re_camel_to_snake_case = re.compile("((?<=[a-z0-9])[A-Z]|(?!^)[A-Z](?=[a-z]))")


def camel_to_snake_case(string: str) -> str:
    return _re_camel_to_snake_case.sub(r"_\1", string).replace("__", "_").lower()


def snake_to_camel_case(string: str, capitalize_first: bool = True) -> str:
    components = string.split("_")
    start_idx = 0 if capitalize_first else 1
    components = [x.title() for x in components[start_idx:]]
    return "".join(components)


def hyphen_to_snake_case(string: str) -> str:
    return string.replace("-", "_")


def canonicalize_bool_to_str(val: bool) -> str:
    return "true" if str(val).lower() == "true" else "false"


def convert_to_printable_chars(value: list | dict | str) -> str:
    """Removes all unprintable characters from the given string."""
    from localstack.utils.objects import recurse_object

    if isinstance(value, (dict, list)):

        def _convert(obj, **kwargs):
            if isinstance(obj, str):
                return convert_to_printable_chars(obj)
            return obj

        return recurse_object(value, _convert)

    result = REGEX_UNPRINTABLE_CHARS.sub("", value)
    return result


def first_char_to_lower(s: str) -> str:
    return s and f"{s[0].lower()}{s[1:]}"


def first_char_to_upper(s: str) -> str:
    return s and f"{s[0].upper()}{s[1:]}"


def str_to_bool(value):
    """Return the boolean value of the given string, or the verbatim value if it is not a string"""
    if isinstance(value, str):
        true_strings = ["true", "True"]
        return value in true_strings
    return value


def str_insert(string, index, content):
    """Insert a substring into an existing string at a certain index."""
    return f"{string[:index]}{content}{string[index:]}"


def str_remove(string, index, end_index=None):
    """Remove a substring from an existing string at a certain from-to index range."""
    end_index = end_index or (index + 1)
    return f"{string[:index]}{string[end_index:]}"


def str_startswith_ignore_case(value: str, prefix: str) -> bool:
    return value[: len(prefix)].lower() == prefix.lower()


def short_uid() -> str:
    return str(uuid.uuid4())[0:8]


def short_uid_from_seed(seed: str) -> str:
    hash = hashlib.sha1(seed.encode("utf-8")).hexdigest()
    truncated_hash = hash[:32]
    return str(uuid.UUID(truncated_hash))[0:8]


def long_uid() -> str:
    return str(uuid.uuid4())


def md5(string: str | bytes) -> str:
    m = hashlib.md5()
    m.update(to_bytes(string))
    return m.hexdigest()


def checksum_crc32(string: str | bytes) -> str:
    bytes = to_bytes(string)
    checksum = zlib.crc32(bytes)
    return base64.b64encode(checksum.to_bytes(4, "big")).decode()


def checksum_crc32c(string: str | bytes):
    # import botocore locally here to avoid a dependency of the CLI to botocore
    from botocore.httpchecksum import CrtCrc32cChecksum

    checksum = CrtCrc32cChecksum()
    checksum.update(to_bytes(string))
    return base64.b64encode(checksum.digest()).decode()


def checksum_crc64nvme(string: str | bytes):
    # import botocore locally here to avoid a dependency of the CLI to botocore
    from botocore.httpchecksum import CrtCrc64NvmeChecksum

    checksum = CrtCrc64NvmeChecksum()
    checksum.update(to_bytes(string))
    return base64.b64encode(checksum.digest()).decode()


def hash_sha1(string: str | bytes) -> str:
    digest = hashlib.sha1(to_bytes(string)).digest()
    return base64.b64encode(digest).decode()


def hash_sha256(string: str | bytes) -> str:
    digest = hashlib.sha256(to_bytes(string)).digest()
    return base64.b64encode(digest).decode()


def base64_to_hex(b64_string: str) -> bytes:
    return binascii.hexlify(base64.b64decode(b64_string))


def base64_decode(data: str | bytes) -> bytes:
    """Decode base64 data - with optional padding, and able to handle urlsafe encoding (containing -/_)."""
    data = to_str(data)
    missing_padding = len(data) % 4
    if missing_padding != 0:
        data = to_str(data) + "=" * (4 - missing_padding)
    if "-" in data or "_" in data:
        return base64.urlsafe_b64decode(data)
    return base64.b64decode(data)


def get_random_hex(length: int) -> str:
    return "".join(random.choices(string.hexdigits[:16], k=length)).lower()


def remove_leading_extra_slashes(input: str) -> str:
    """
    Remove leading extra slashes from the given input string.
    Example: '///foo/bar' -> '/foo/bar'
    """
    return re.sub(r"^/+", "/", input)


def prepend_with_slash(input: str) -> str:
    """
    Prepend a slash `/` to a given string if it does not have one already.
    """
    if not input.startswith("/"):
        return f"/{input}"
    return input


def key_value_pairs_to_dict(pairs: str, delimiter: str = ",", separator: str = "=") -> dict:
    """
    Converts a string of key-value pairs to a dictionary.

    Args:
        pairs (str): A string containing key-value pairs separated by a delimiter.
        delimiter (str): The delimiter used to separate key-value pairs (default is comma ',').
        separator (str): The separator between keys and values (default is '=').

    Returns:
        dict: A dictionary containing the parsed key-value pairs.
    """
    splits = [split_pair.partition(separator) for split_pair in pairs.split(delimiter)]
    return {key.strip(): value.strip() for key, _, value in splits}


def token_generator(item: str) -> str:
    base64_bytes = base64.b64encode(item.encode("utf-8"))
    token = base64_bytes.decode("utf-8")
    return token

1	import base64	1✔
2	import binascii	1✔
3	import hashlib	1✔
4	import itertools	1✔
5	import random	1✔
6	import re	1✔
7	import string	1✔
8	import uuid	1✔
9	import zlib	1✔
10
11	from localstack.config import DEFAULT_ENCODING	1✔
12
13	_unprintables = (	1✔
14	range(0x00, 0x09),
15	range(0x0A, 0x0A),
16	range(0x0B, 0x0D),
17	range(0x0E, 0x20),
18	range(0xD800, 0xE000),
19	range(0xFFFE, 0x10000),
20	)
21
22	# regular expression for unprintable characters
23	# Based on https://docs.aws.amazon.com/AWSSimpleQueueService/latest/APIReference/API_SendMessage.html
24	# #x9 \| #xA \| #xD \| #x20 to #xD7FF \| #xE000 to #xFFFD \| #x10000 to #x10FFFF
25	REGEX_UNPRINTABLE_CHARS = re.compile(	1✔
26	f"[{re.escape(''.join(map(chr, itertools.chain(*_unprintables))))}]"
27	)
28
29
30	def to_str(obj: str \| bytes, encoding: str = DEFAULT_ENCODING, errors="strict") -> str:	1✔
31	"""If ``obj`` is an instance of ``binary_type``, return
32	``obj.decode(encoding, errors)``, otherwise return ``obj``"""
33	return obj.decode(encoding, errors) if isinstance(obj, bytes) else obj	1✔
34
35
36	def to_bytes(obj: str \| bytes, encoding: str = DEFAULT_ENCODING, errors="strict") -> bytes:	1✔
37	"""If ``obj`` is an instance of ``text_type``, return
38	``obj.encode(encoding, errors)``, otherwise return ``obj``"""
39	return obj.encode(encoding, errors) if isinstance(obj, str) else obj	1✔
40
41
42	def truncate(data: str, max_length: int = 100) -> str:	1✔
43	data = str(data or "")	1✔
44	return (f"{data[:max_length]}...") if len(data) > max_length else data	1✔
45
46
47	def is_string(s, include_unicode=True, exclude_binary=False):	1✔
48	if isinstance(s, bytes) and exclude_binary:	1✔
UNCOV 49	return False	×
50	if isinstance(s, str):	1✔
51	return True	1✔
UNCOV 52	if include_unicode and isinstance(s, str):	×
53	return True	×
54	return False	×
55
56
57	def is_string_or_bytes(s):	1✔
UNCOV 58	return is_string(s) or isinstance(s, str) or isinstance(s, bytes)	×
59
60
61	def is_base64(s):	1✔
62	regex = r"^(?:[A-Za-z0-9+/]{4})*(?:[A-Za-z0-9+/]{2}==\|[A-Za-z0-9+/]{3}=)?$"	1✔
63	return is_string(s) and re.match(regex, s)	1✔
64
65
66	_re_camel_to_snake_case = re.compile("((?<=[a-z0-9])[A-Z]\|(?!^)[A-Z](?=[a-z]))")	1✔
67
68
69	def camel_to_snake_case(string: str) -> str:	1✔
70	return _re_camel_to_snake_case.sub(r"_\1", string).replace("__", "_").lower()	1✔
71
72
73	def snake_to_camel_case(string: str, capitalize_first: bool = True) -> str:	1✔
74	components = string.split("_")	1✔
75	start_idx = 0 if capitalize_first else 1	1✔
76	components = [x.title() for x in components[start_idx:]]	1✔
77	return "".join(components)	1✔
78
79
80	def hyphen_to_snake_case(string: str) -> str:	1✔
UNCOV 81	return string.replace("-", "_")	×
82
83
84	def canonicalize_bool_to_str(val: bool) -> str:	1✔
85	return "true" if str(val).lower() == "true" else "false"	1✔
86
87
88	def convert_to_printable_chars(value: list \| dict \| str) -> str:	1✔
89	"""Removes all unprintable characters from the given string."""
90	from localstack.utils.objects import recurse_object	1✔
91
92	if isinstance(value, (dict, list)):	1✔
93
94	def _convert(obj, **kwargs):	1✔
95	if isinstance(obj, str):	1✔
96	return convert_to_printable_chars(obj)	1✔
97	return obj	1✔
98
99	return recurse_object(value, _convert)	1✔
100
101	result = REGEX_UNPRINTABLE_CHARS.sub("", value)	1✔
102	return result	1✔
103
104
105	def first_char_to_lower(s: str) -> str:	1✔
106	return s and f"{s[0].lower()}{s[1:]}"	1✔
107
108
109	def first_char_to_upper(s: str) -> str:	1✔
110	return s and f"{s[0].upper()}{s[1:]}"	1✔
111
112
113	def str_to_bool(value):	1✔
114	"""Return the boolean value of the given string, or the verbatim value if it is not a string"""
115	if isinstance(value, str):	1✔
116	true_strings = ["true", "True"]	1✔
117	return value in true_strings	1✔
118	return value	1✔
119
120
121	def str_insert(string, index, content):	1✔
122	"""Insert a substring into an existing string at a certain index."""
UNCOV 123	return f"{string[:index]}{content}{string[index:]}"	×
124
125
126	def str_remove(string, index, end_index=None):	1✔
127	"""Remove a substring from an existing string at a certain from-to index range."""
UNCOV 128	end_index = end_index or (index + 1)	×
129	return f"{string[:index]}{string[end_index:]}"	×
130
131
132	def str_startswith_ignore_case(value: str, prefix: str) -> bool:	1✔
UNCOV 133	return value[: len(prefix)].lower() == prefix.lower()	×
134
135
136	def short_uid() -> str:	1✔
137	return str(uuid.uuid4())[0:8]	1✔
138
139
140	def short_uid_from_seed(seed: str) -> str:	1✔
141	hash = hashlib.sha1(seed.encode("utf-8")).hexdigest()	1✔
142	truncated_hash = hash[:32]	1✔
143	return str(uuid.UUID(truncated_hash))[0:8]	1✔
144
145
146	def long_uid() -> str:	1✔
147	return str(uuid.uuid4())	1✔
148
149
150	def md5(string: str \| bytes) -> str:	1✔
151	m = hashlib.md5()	1✔
152	m.update(to_bytes(string))	1✔
153	return m.hexdigest()	1✔
154
155
156	def checksum_crc32(string: str \| bytes) -> str:	1✔
157	bytes = to_bytes(string)	1✔
158	checksum = zlib.crc32(bytes)	1✔
159	return base64.b64encode(checksum.to_bytes(4, "big")).decode()	1✔
160
161
162	def checksum_crc32c(string: str \| bytes):	1✔
163	# import botocore locally here to avoid a dependency of the CLI to botocore
164	from botocore.httpchecksum import CrtCrc32cChecksum	1✔
165
166	checksum = CrtCrc32cChecksum()	1✔
167	checksum.update(to_bytes(string))	1✔
168	return base64.b64encode(checksum.digest()).decode()	1✔
169
170
171	def checksum_crc64nvme(string: str \| bytes):	1✔
172	# import botocore locally here to avoid a dependency of the CLI to botocore
173	from botocore.httpchecksum import CrtCrc64NvmeChecksum	1✔
174
175	checksum = CrtCrc64NvmeChecksum()	1✔
176	checksum.update(to_bytes(string))	1✔
177	return base64.b64encode(checksum.digest()).decode()	1✔
178
179
180	def hash_sha1(string: str \| bytes) -> str:	1✔
181	digest = hashlib.sha1(to_bytes(string)).digest()	1✔
182	return base64.b64encode(digest).decode()	1✔
183
184
185	def hash_sha256(string: str \| bytes) -> str:	1✔
186	digest = hashlib.sha256(to_bytes(string)).digest()	1✔
187	return base64.b64encode(digest).decode()	1✔
188
189
190	def base64_to_hex(b64_string: str) -> bytes:	1✔
191	return binascii.hexlify(base64.b64decode(b64_string))	1✔
192
193
194	def base64_decode(data: str \| bytes) -> bytes:	1✔
195	"""Decode base64 data - with optional padding, and able to handle urlsafe encoding (containing -/_)."""
196	data = to_str(data)	1✔
197	missing_padding = len(data) % 4	1✔
198	if missing_padding != 0:	1✔
UNCOV 199	data = to_str(data) + "=" * (4 - missing_padding)	×
200	if "-" in data or "_" in data:	1✔
201	return base64.urlsafe_b64decode(data)	1✔
202	return base64.b64decode(data)	1✔
203
204
205	def get_random_hex(length: int) -> str:	1✔
206	return "".join(random.choices(string.hexdigits[:16], k=length)).lower()	1✔
207
208
209	def remove_leading_extra_slashes(input: str) -> str:	1✔
210	"""
211	Remove leading extra slashes from the given input string.
212	Example: '///foo/bar' -> '/foo/bar'
213	"""
UNCOV 214	return re.sub(r"^/+", "/", input)	×
215
216
217	def prepend_with_slash(input: str) -> str:	1✔
218	"""
219	Prepend a slash `/` to a given string if it does not have one already.
220	"""
221	if not input.startswith("/"):	1✔
222	return f"/{input}"	1✔
223	return input	1✔
224
225
226	def key_value_pairs_to_dict(pairs: str, delimiter: str = ",", separator: str = "=") -> dict:	1✔
227	"""
228	Converts a string of key-value pairs to a dictionary.
229
230	Args:
231	pairs (str): A string containing key-value pairs separated by a delimiter.
232	delimiter (str): The delimiter used to separate key-value pairs (default is comma ',').
233	separator (str): The separator between keys and values (default is '=').
234
235	Returns:
236	dict: A dictionary containing the parsed key-value pairs.
237	"""
238	splits = [split_pair.partition(separator) for split_pair in pairs.split(delimiter)]	1✔
239	return {key.strip(): value.strip() for key, _, value in splits}	1✔
240
241
242	def token_generator(item: str) -> str:	1✔
243	base64_bytes = base64.b64encode(item.encode("utf-8"))	1✔
244	token = base64_bytes.decode("utf-8")	1✔
245	return token	1✔

localstack / localstack / 18505123992

Source File Press 'n' to go to next uncovered line, 'b' for previous

Source File
Press 'n' to go to next uncovered line, 'b' for previous