fix: parse non-utf pkgbuilds as well (#140)

it has been reported that duriing reading pkgbuilds with latin-1 charset
the execption will be raised. Well, it is one more point to rewrite
parser to use own impl instead of shlex and parse raw byte array instead

src/ahriman/core/exceptions.py

@@ -95,6 +95,19 @@ class DuplicateRunError(RuntimeError):
             self, "Another application instance is run. This error can be suppressed by using --force flag.")
 
 
+class EncodeError(ValueError):
+    """
+    exception used for bytes encoding errors
+    """
+
+    def __init__(self, encodings: list[str]) -> None:
+        """
+        Args:
+            encodings(list[str]): list of encodings tried
+        """
+        ValueError.__init__(self, f"Could not encode bytes by using {encodings}")
+
+
 class ExitCode(RuntimeError):
     """
     special exception which has to be thrown to return non-zero status without error message

src/ahriman/models/pkgbuild.py

@@ -24,6 +24,7 @@ from pathlib import Path
 from typing import Any, IO, Self
 
 from ahriman.core.alpm.pkgbuild_parser import PkgbuildParser, PkgbuildToken
+from ahriman.core.exceptions import EncodeError
 from ahriman.models.pkgbuild_patch import PkgbuildPatch
 
 
@@ -33,11 +34,14 @@ class Pkgbuild(Mapping[str, Any]):
     model and proxy for PKGBUILD properties
 
     Attributes:
+        DEFAULT_ENCODINGS(list[str]): (class attribute) list of encoding to be applied on the file content
         fields(dict[str, PkgbuildPatch]): PKGBUILD fields
     """
 
     fields: dict[str, PkgbuildPatch]
 
+    DEFAULT_ENCODINGS = ["utf8", "latin-1"]
+
     @property
     def variables(self) -> dict[str, str]:
         """
@@ -54,18 +58,34 @@ class Pkgbuild(Mapping[str, Any]):
         }
 
     @classmethod
-    def from_file(cls, path: Path) -> Self:
+    def from_file(cls, path: Path, encodings: list[str] | None = None) -> Self:
         """
         parse PKGBUILD from the file
 
         Args:
             path(Path): path to the PKGBUILD file
+            encodings(list[str] | None, optional): the encoding of the file (Default value = None)
 
         Returns:
             Self: constructed instance of self
+
+        Raises:
+            EncodeError: if encoding is unknown
         """
-        with path.open(encoding="utf8") as input_file:
-            return cls.from_io(input_file)
+        # read raw bytes from file
+        with path.open("rb") as input_file:
+            content = input_file.read()
+
+        # decode bytes content based on either
+        encodings = encodings or cls.DEFAULT_ENCODINGS
+        for encoding in encodings:
+            try:
+                io = StringIO(content.decode(encoding))
+                return cls.from_io(io)
+            except ValueError:
+                pass
+
+        raise EncodeError(encodings)
 
     @classmethod
     def from_io(cls, stream: IO[str]) -> Self: