Merge pull request #2 from fchorney/cstr-implementation

Add string_t type

README.md

@@ -98,6 +98,40 @@ s.decode([10, 5, 6])
 # MyStruct(myInt=10, myInts=[5, 6])
 ```
 
+# String / char[] Type
+
+Defining c-string types is a little different. Instead of using
+`size` in the `TypeMeta`, we need to instead use `chunk_size`.
+
+This is because the way the struct format is defined for c-strings needs
+to know how big the string data is expected to be so that it can put the
+whole string in a single variable. 
+
+The `chunk_size` is also introduced to allow for `char[][]` for converting
+a list of strings.
+
+```c
+struct MyStruct {
+    char myStr[3];
+    char myStrList[2][3];
+};
+```
+```python
+@struct_dataclass
+class MyStruct(StructDataclass):
+    myStr: Annotated[string_t, TypeMeta[str](chunk_size=3)]
+    myStrList: Annotated[list[string_t], TypeMeta[str](size=2, chunk_size=3)]
+
+
+s = MyStruct()
+s.decode([65, 66, 67, 68, 69, 70, 71, 72, 73])
+# MyStruct(myStr=b"ABC", myStrList=[b"DEF", b"GHI"])
+```
+
+If you instead try to define this as a list of `char_t` types,
+you would only be able to end up with 
+`MyStruct(myStr=[b"A", b"B", b"C"], myStrList=[b"D", b"E", b"F", b"G", b"H", b"I"])`
+
 # The Bits Abstraction
 
 This library includes a `bits` abstraction to map bits to variables for easier access.
@@ -205,7 +239,6 @@ s.decode([15, 15, 15, 15, 0])
 #   [False, False, False, False],
 #   [True, True, True, True],
 #   [False, False, False, False],
-#   [False, False, False, False]
 # ]
 
 # With the get/set functioned defined, we can access the data
@@ -249,7 +282,6 @@ l.decode([1, 2, 3, 4, 5, 6, 7, 8, 9])
 # Future Updates
 
 - Bitfield: Similar to the `Bits` abstraction. An easy way to define bitfields
-- C-Strings: Make a base class to handle C strings (arrays of chars)
 - Potentially more ways to define bits (dicts/lists/etc).
 - Potentially allowing list defaults to be entire pre-defined lists.
 - ???

pyproject.toml

@@ -17,9 +17,7 @@ classifiers = [
 ]
 keywords = ["struct", "cstruct", "type"]
 requires-python = ">=3.13"
-dependencies = [
-    "loguru>=0.7.3",
-]
+dependencies = []
 
 [project.urls]
 Homepage = "https://github.com/fchorney/pystructtype"

src/pystructtype/__init__.py

@@ -10,6 +10,7 @@
     int16_t,
     int32_t,
     int64_t,
+    string_t,
     uint8_t,
     uint16_t,
     uint32_t,
@@ -29,6 +30,7 @@
     "int16_t",
     "int32_t",
     "int64_t",
+    "string_t",
     "struct_dataclass",
     "uint8_t",
     "uint16_t",

src/pystructtype/structdataclass.py

@@ -19,6 +19,7 @@ class StructState:
     name: str
     struct_fmt: str
     size: int
+    chunk_size: int
 
 
 class StructDataclass:
@@ -39,18 +40,18 @@ def __post_init__(self) -> None:
                         type_iterator.key,
                         type_iterator.type_info.format,
                         type_iterator.size,
+                        type_iterator.chunk_size,
                     )
                 )
-                self.struct_fmt += (
-                    f"{type_iterator.size if type_iterator.size > 1 else ''}{type_iterator.type_info.format}"
-                )
+                _fmt_prefix = type_iterator.chunk_size if type_iterator.chunk_size > 1 else ""
+                self.struct_fmt += f"{_fmt_prefix}{type_iterator.type_info.format}" * type_iterator.size
             elif inspect.isclass(type_iterator.base_type) and issubclass(type_iterator.base_type, StructDataclass):
                 attr = getattr(self, type_iterator.key)
                 if type_iterator.is_list:
                     fmt = attr[0].struct_fmt
                 else:
                     fmt = attr.struct_fmt
-                self._state.append(StructState(type_iterator.key, fmt, type_iterator.size))
+                self._state.append(StructState(type_iterator.key, fmt, type_iterator.size, type_iterator.chunk_size))
                 self.struct_fmt += fmt * type_iterator.size
             else:
                 # We have no TypeInfo object, and we're not a StructDataclass
@@ -76,14 +77,26 @@ def _simplify_format(self) -> None:
         while idx < items_len:
             if "0" <= (item := items[idx]) <= "9":
                 idx += 1
-                expanded_format += items[idx] * int(item)
+
+                if items[idx] == "s":
+                    # Shouldn't expand actual char[]/string types as they need to be grouped
+                    # so we know how big the strings should be
+                    expanded_format += item + items[idx]
+                else:
+                    expanded_format += items[idx] * int(item)
             else:
                 expanded_format += item
             idx += 1
 
         # Simplify the format by turning multiple consecutive letters into a number + letter combo
         simplified_format = ""
-        for group in (x[0] for x in re.findall(r"(([a-zA-Z])\2*)", expanded_format)):
+        for group in (x[0] for x in re.findall(r"(\d*([a-zA-Z])\2*)", expanded_format)):
+            if re.match(r"\d+", group[0]):
+                # Just pass through any format that we've explicitly kept
+                # a number in front of
+                simplified_format += group
+                continue
+
             simplified_format += f"{group_len if (group_len := len(group)) > 1 else ''}{group[0]}"
 
         self.struct_fmt = simplified_format

src/pystructtype/structtypes.py

@@ -5,7 +5,7 @@
 
 from pystructtype import structdataclass
 
-T = TypeVar("T", int, float, default=int)
+T = TypeVar("T", int, float, str, default=int)
 """Generic Data Type for StructDataclass Contents"""
 
 
@@ -17,6 +17,7 @@ class TypeMeta[T]:
     """
 
     size: int = 1
+    chunk_size: int = 1
     default: T | None = None
 
 
@@ -31,8 +32,6 @@ class TypeInfo:
     byte_size: int
 
 
-# TODO: Support proper "c-string" types
-
 # Fixed Size Types
 char_t = Annotated[int, TypeInfo("c", 1)]
 """1 Byte char Type"""
@@ -60,6 +59,8 @@ class TypeInfo:
 """4 Byte float Type"""
 double_t = Annotated[float, TypeInfo("d", 8)]
 """8 Byte double Type"""
+string_t = Annotated[str, TypeInfo("s", 1)]
+"""1 Byte char[] Type"""
 
 
 @dataclass
@@ -89,6 +90,20 @@ def size(self) -> int:
         """
         return getattr(self.type_meta, "size", 1)
 
+    @property
+    def chunk_size(self) -> int:
+        """
+        Return the chunk size of the type. Typically, this is used for char[]/string
+        types as these are defined in chunks rather than in a size of individual
+        values.
+
+        This defaults to 1, else this will return the size defined in the `type_meta` object
+        if it exists.
+
+        :return: integer containing the chunk size of the type
+        """
+        return getattr(self.type_meta, "chunk_size", 1)
+
 
 def iterate_types(cls: type) -> Generator[TypeIterator]:
     """

test/test_ctypes.py

@@ -1,10 +1,36 @@
 from typing import Annotated
 
-from pystructtype import BitsType, StructDataclass, TypeMeta, bits, struct_dataclass, uint8_t
+from pystructtype import BitsType, StructDataclass, TypeMeta, bits, string_t, struct_dataclass, uint8_t
 
 from .examples import TEST_CONFIG_DATA, SMXConfigType  # type: ignore
 
 
+def test_strings():
+    @struct_dataclass
+    class TestString(StructDataclass):
+        boo: uint8_t
+        foo: Annotated[string_t, TypeMeta[str](chunk_size=3)]
+        far: Annotated[list[uint8_t], TypeMeta(size=2)]
+        bar: Annotated[string_t, TypeMeta[str](chunk_size=5)]
+        rob: uint8_t
+        rar: Annotated[list[string_t], TypeMeta[str](size=2, chunk_size=2)]
+
+    data = [0, 65, 66, 67, 1, 2, 65, 66, 67, 68, 69, 2, 65, 66, 67, 68]
+
+    s = TestString()
+    s.decode(data)
+
+    assert s.foo == b"ABC"
+    assert s.bar == b"ABCDE"
+    assert s.boo == 0
+    assert s.far == [1, 2]
+    assert s.rob == 2
+    assert s.rar == [b"AB", b"CD"]
+
+    e = s.encode()
+    assert s._to_list(e) == data
+
+
 def test_smx_config():
     c = SMXConfigType()