dycw-utilities 0.110.0__py3-none-any.whl → 0.110.2__py3-none-any.whl

{dycw_utilities-0.110.0.dist-info → dycw_utilities-0.110.2.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: dycw-utilities
-Version: 0.110.0
+Version: 0.110.2
 Author-email: Derek Wan <d.wan@icloud.com>
 License-File: LICENSE
 Requires-Python: >=3.12

{dycw_utilities-0.110.0.dist-info → dycw_utilities-0.110.2.dist-info}/RECORD

@@ -1,4 +1,4 @@
-utilities/__init__.py,sha256=H5Ma2FOh3z_dBcZTVaSY2VI14JUFHWspBQs7dYAHnjc,60
+utilities/__init__.py,sha256=N5L_-mBy__dabTcP63GXeZ0UmhNEqKjJ0SR5XKVgg5Y,60
 utilities/altair.py,sha256=Gpja-flOo-Db0PIPJLJsgzAlXWoKUjPU1qY-DQ829ek,9156
 utilities/astor.py,sha256=xuDUkjq0-b6fhtwjhbnebzbqQZAjMSHR1IIS5uOodVg,777
 utilities/asyncio.py,sha256=41oQUurWMvadFK5gFnaG21hMM0Vmfn2WS6OpC0R9mas,14757
@@ -11,7 +11,7 @@ utilities/contextlib.py,sha256=OOIIEa5lXKGzFAnauaul40nlQnQko6Na4ryiMJcHkIg,478
 utilities/contextvars.py,sha256=RsSGGrbQqqZ67rOydnM7WWIsM2lIE31UHJLejnHJPWY,505
 utilities/cryptography.py,sha256=HyOewI20cl3uRXsKivhIaeLVDInQdzgXZGaly7hS5dE,771
 utilities/cvxpy.py,sha256=Rv1-fD-XYerosCavRF8Pohop2DBkU3AlFaGTfD8AEAA,13776
-utilities/dataclasses.py,sha256=vkrcV-qnMS4qGHJ2z3kmcugNH_Fk20SPXfttXb3H5Bs,25950
+utilities/dataclasses.py,sha256=e2YuCj1DF4eecFFxsu20MknghXJ4SNkWCmbIAOXXr18,25942
 utilities/datetime.py,sha256=GOs-MIEW_A49kzqa1yhIoeNeSqqPVgGO-h2AThtgTDk,37326
 utilities/enum.py,sha256=HoRwVCWzsnH0vpO9ZEcAAIZLMv0Sn2vJxxA4sYMQgDs,5793
 utilities/errors.py,sha256=BtSNP0JC3ik536ddPyTerLomCRJV9f6kdMe6POz0QHM,361
@@ -73,7 +73,7 @@ utilities/streamlit.py,sha256=U9PJBaKP1IdSykKhPZhIzSPTZsmLsnwbEPZWzNhJPKk,2955
 utilities/sys.py,sha256=h0Xr7Vj86wNalvwJVP1wj5Y0kD_VWm1vzuXZ_jw94mE,2743
 utilities/tempfile.py,sha256=VqmZJAhTJ1OaVywFzk5eqROV8iJbW9XQ_QYAV0bpdRo,1384
 utilities/tenacity.py,sha256=1PUvODiBVgeqIh7G5TRt5WWMSqjLYkEqP53itT97WQc,4914
-utilities/text.py,sha256=Ax_n-nY80_onWxag9M0PkmbaAqwyut9AEA9tEMd5lBs,6694
+utilities/text.py,sha256=VcNAJtjA2BOGEVY6yXnC9UIAsgECgiWCQ_QnpilZV2o,10089
 utilities/threading.py,sha256=GvBOp4CyhHfN90wGXZuA2VKe9fGzMaEa7oCl4f3nnPU,1009
 utilities/timer.py,sha256=Rkc49KSpHuC8s7vUxGO9DU55U9I6yDKnchsQqrUCVBs,4075
 utilities/traceback.py,sha256=KwHPLdEbdj0fFhXo8MBfxcvem8A-VXYDwFMNJ6f0cTM,27328
@@ -87,7 +87,7 @@ utilities/warnings.py,sha256=yUgjnmkCRf6QhdyAXzl7u0qQFejhQG3PrjoSwxpbHrs,1819
 utilities/whenever.py,sha256=TjoTAJ1R27-rKXiXzdE4GzPidmYqm0W58XydDXp-QZM,17786
 utilities/zipfile.py,sha256=24lQc9ATcJxHXBPc_tBDiJk48pWyRrlxO2fIsFxU0A8,699
 utilities/zoneinfo.py,sha256=-DQz5a0Ikw9jfSZtL0BEQkXOMC9yGn_xiJYNCLMiqEc,1989
-dycw_utilities-0.110.0.dist-info/METADATA,sha256=z9nJyYO-djaRWCX7iT7S0vdy40gXfUedyu_jhw3O-Cs,13004
-dycw_utilities-0.110.0.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
-dycw_utilities-0.110.0.dist-info/licenses/LICENSE,sha256=gppZp16M6nSVpBbUBrNL6JuYfvKwZiKgV7XoKKsHzqo,1066
-dycw_utilities-0.110.0.dist-info/RECORD,,
+dycw_utilities-0.110.2.dist-info/METADATA,sha256=TK9SINDsRCnIKjF2YyzOvlQ5mTpD1hjJJ6SD_aNKFI4,13004
+dycw_utilities-0.110.2.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
+dycw_utilities-0.110.2.dist-info/licenses/LICENSE,sha256=gppZp16M6nSVpBbUBrNL6JuYfvKwZiKgV7XoKKsHzqo,1066
+dycw_utilities-0.110.2.dist-info/RECORD,,

utilities/__init__.py

@@ -1,3 +1,3 @@
 from __future__ import annotations
 
-__version__ = "0.110.0"
+__version__ = "0.110.2"

utilities/dataclasses.py

@@ -439,7 +439,7 @@ def serialize_dataclass(
 
 
 def parse_dataclass(
-    text_or_mapping: str | Mapping[str, str],
+    text_or_mapping: str | StrStrMapping,
     cls: type[TDataclass],
     /,
     *,
@@ -505,7 +505,7 @@ def _parse_dataclass_split_key_value_pairs(
     *,
     list_separator: str = LIST_SEPARATOR,
     pair_separator: str = PAIR_SEPARATOR,
-) -> Mapping[str, str]:
+) -> StrStrMapping:
     try:
         return split_key_value_pairs(
             text,

utilities/text.py

@@ -1,12 +1,14 @@
 from __future__ import annotations
 
 import re
+from collections import deque
 from dataclasses import dataclass
-from re import IGNORECASE, Match, search
+from itertools import chain
+from re import IGNORECASE, Match, escape, search
 from textwrap import dedent
 from typing import TYPE_CHECKING, Any, Literal, overload, override
 
-from utilities.iterables import CheckDuplicatesError, check_duplicates
+from utilities.iterables import CheckDuplicatesError, check_duplicates, transpose
 from utilities.reprlib import get_repr
 
 if TYPE_CHECKING:
@@ -167,47 +169,134 @@ class _SplitKeyValuePairsDuplicateKeysError(SplitKeyValuePairsError):
 
 
 @overload
-def split_str(text: str, /, *, separator: str = ",", n: Literal[1]) -> tuple[str]: ...
+def split_str(
+    text: str,
+    /,
+    *,
+    separator: str = ",",
+    brackets: Iterable[tuple[str, str]] | None = None,
+    n: Literal[1],
+) -> tuple[str]: ...
 @overload
 def split_str(
-    text: str, /, *, separator: str = ",", n: Literal[2]
+    text: str,
+    /,
+    *,
+    separator: str = ",",
+    brackets: Iterable[tuple[str, str]] | None = None,
+    n: Literal[2],
 ) -> tuple[str, str]: ...
 @overload
 def split_str(
-    text: str, /, *, separator: str = ",", n: Literal[3]
+    text: str,
+    /,
+    *,
+    separator: str = ",",
+    brackets: Iterable[tuple[str, str]] | None = None,
+    n: Literal[3],
 ) -> tuple[str, str, str]: ...
 @overload
 def split_str(
-    text: str, /, *, separator: str = ",", n: Literal[4]
+    text: str,
+    /,
+    *,
+    separator: str = ",",
+    brackets: Iterable[tuple[str, str]] | None = None,
+    n: Literal[4],
 ) -> tuple[str, str, str, str]: ...
 @overload
 def split_str(
-    text: str, /, *, separator: str = ",", n: Literal[5]
+    text: str,
+    /,
+    *,
+    separator: str = ",",
+    brackets: Iterable[tuple[str, str]] | None = None,
+    n: Literal[5],
 ) -> tuple[str, str, str, str, str]: ...
 @overload
 def split_str(
-    text: str, /, *, separator: str = ",", n: int | None = None
+    text: str,
+    /,
+    *,
+    separator: str = ",",
+    brackets: Iterable[tuple[str, str]] | None = None,
+    n: int | None = None,
 ) -> Sequence[str]: ...
 def split_str(
-    text: str, /, *, separator: str = ",", n: int | None = None
+    text: str,
+    /,
+    *,
+    separator: str = ",",
+    brackets: Iterable[tuple[str, str]] | None = None,
+    n: int | None = None,
 ) -> Sequence[str]:
     """Split a string, with a special provision for the empty string."""
     if text == "":
         texts = []
     elif text == _escape_separator(separator=separator):
         texts = [""]
-    else:
+    elif brackets is None:
         texts = text.split(separator)
+    else:
+        texts = _split_str_brackets(text, brackets, separator=separator)
     if n is None:
         return texts
     if len(texts) != n:
-        raise SplitStrError(text=text, n=n, texts=texts)
+        raise _SplitStrCountError(text=text, n=n, texts=texts)
     return tuple(texts)
 
 
+def _split_str_brackets(
+    text: str, brackets: Iterable[tuple[str, str]], /, *, separator: str = ","
+) -> Sequence[str]:
+    brackets = list(brackets)
+    opens, closes = transpose(brackets)
+    close_to_open = {close: open_ for open_, close in brackets}
+
+    escapes = map(escape, chain(chain.from_iterable(brackets), [separator]))
+    pattern = re.compile("|".join(escapes))
+
+    results: Sequence[str] = []
+    stack: deque[tuple[str, int]] = deque()
+    last = 0
+
+    for match in pattern.finditer(text):
+        token, position = match.group(), match.start()
+        if token in opens:
+            stack.append((token, position))
+        elif token in closes:
+            if len(stack) == 0:
+                raise _SplitStrClosingBracketUnmatchedError(
+                    text=text, token=token, position=position
+                )
+            open_token, open_position = stack.pop()
+            if open_token != close_to_open[token]:
+                raise _SplitStrClosingBracketMismatchedError(
+                    text=text,
+                    opening_token=open_token,
+                    opening_position=open_position,
+                    closing_token=token,
+                    closing_position=position,
+                )
+        elif (token == separator) and (len(stack) == 0):
+            results.append(text[last:position].strip())
+            last = position + 1
+    results.append(text[last:].strip())
+    if len(stack) >= 1:
+        token, position = stack.pop()
+        raise _SplitStrOpeningBracketUnmatchedError(
+            text=text, token=token, position=position
+        )
+    return results
+
+
 @dataclass(kw_only=True, slots=True)
 class SplitStrError(Exception):
     text: str
+
+
+@dataclass(kw_only=True, slots=True)
+class _SplitStrCountError(SplitStrError):
     n: int
     texts: Sequence[str]
 
@@ -216,6 +305,38 @@ class SplitStrError(Exception):
         return f"Unable to split {self.text!r} into {self.n} part(s); got {len(self.texts)}"
 
 
+@dataclass(kw_only=True, slots=True)
+class _SplitStrClosingBracketMismatchedError(SplitStrError):
+    opening_token: str
+    opening_position: int
+    closing_token: str
+    closing_position: int
+
+    @override
+    def __str__(self) -> str:
+        return f"Unable to split {self.text!r}; got mismatched {self.opening_token!r} at position {self.opening_position} and {self.closing_token!r} at position {self.closing_position}"
+
+
+@dataclass(kw_only=True, slots=True)
+class _SplitStrClosingBracketUnmatchedError(SplitStrError):
+    token: str
+    position: int
+
+    @override
+    def __str__(self) -> str:
+        return f"Unable to split {self.text!r}; got unmatched {self.token!r} at position {self.position}"
+
+
+@dataclass(kw_only=True, slots=True)
+class _SplitStrOpeningBracketUnmatchedError(SplitStrError):
+    token: str
+    position: int
+
+    @override
+    def __str__(self) -> str:
+        return f"Unable to split {self.text!r}; got unmatched {self.token!r} at position {self.position}"
+
+
 def join_strs(
     texts: Iterable[str], /, *, sort: bool = False, separator: str = ","
 ) -> str: