Remove assert statement from non-test files

ifpd2/asserts.py

@@ -10,48 +10,58 @@
 
 
 def ert_type(x, stype, label):
-    assert isinstance(x, stype), f"{label} should be {stype}, {type(x)} instead"
+    if not isinstance(x, stype):
+        raise AssertionError(f"{label} should be {stype}, {type(x)} instead")
 
 
 def ert_multiTypes(x, types, label):
     cond = any(isinstance(x, t) for t in types)
-    assert cond, f"{label} should be one of {types}, {type(x)} instead"
+    if not cond:
+        raise AssertionError(f"{label} should be one of {types}, {type(x)} instead")
 
 
 def ert_nonNeg(x, label, include_zero=False):
     if not include_zero:
-        assert x > 0, f"{label} should be greater than 0"
+        if x <= 0:
+            raise AssertionError(f"{label} should be greater than 0")
     else:
-        assert x >= 0, f"{label} should be greater than or equal to 0"
+        if x < 0:
+            raise AssertionError(f"{label} should be greater than or equal to 0")
 
 
 def ert_inInterv(x, vmin, vmax, label, leftClose=False, rightClose=True):
     if leftClose:
         if rightClose:
-            assert x >= vmin and x <= vmax, f"expected {vmin}<={label}<={vmax}"
+            if not (x >= vmin and x <= vmax):
+                raise AssertionError(f"expected {vmin}<={label}<={vmax}")
         else:
-            assert x >= vmin and x < vmax, f"expected {vmin}<={label}<{vmax}"
+            if not (x >= vmin and x < vmax):
+                raise AssertionError(f"expected {vmin}<={label}<{vmax}")
     elif rightClose:
-        assert x > vmin and x <= vmax, f"expected {vmin}<{label}<={vmax}"
+        if not (x > vmin and x <= vmax):
+            raise AssertionError(f"expected {vmin}<{label}<={vmax}")
     else:
-        assert x > vmin and x < vmax, f"expected {vmin}<{label}<{vmax}"
+        if not (x > vmin and x < vmax):
+            raise AssertionError(f"expected {vmin}<{label}<{vmax}")
 
 
 def ert_in_dtype(x, dtype):
     if dtype.startswith("f"):
-        assert x <= np.finfo(dtype).max, " ".join(
-            [
-                "expected to be lower than {dtype} max:",
-                f"{x} < {np.finfo(dtype).max}",
-            ]
-        )
+        if x > np.finfo(dtype).max:
+            raise AssertionError(" ".join(
+                [
+                    "expected to be lower than {dtype} max:",
+                    f"{x} < {np.finfo(dtype).max}",
+                ]
+            ))
     elif dtype.startswith("u") or dtype.startswith("i"):
-        assert x <= np.iinfo(dtype).max, " ".join(
-            [
-                "expected to be lower than {dtype} max:",
-                f"{x} < {np.iinfo(dtype).max}",
-            ]
-        )
+        if x > np.iinfo(dtype).max:
+            raise AssertionError(" ".join(
+                [
+                    "expected to be lower than {dtype} max:",
+                    f"{x} < {np.iinfo(dtype).max}",
+                ]
+            ))
     else:
         logging.warning(f"assert not implemented for dtype '{dtype}'")
 

ifpd2/chromosome.py

@@ -20,7 +20,8 @@ class ChromosomeIndex(object):
 
     def __init__(self, bin_size: int):
         super(ChromosomeIndex, self).__init__()
-        assert bin_size >= 1
+        if bin_size < 1:
+            raise AssertionError
         self._bin_size = bin_size
 
     def __init_index(self, chrom_db: pd.DataFrame) -> None:
@@ -63,7 +64,8 @@ def __populate_bins(
         for i in range(chrom_db.shape[0]):
             track[0].update(track[1], advance=1)
             position_in_nt = chrom_db["start"].values[i]
-            assert position_in_nt > current_position
+            if position_in_nt <= current_position:
+                raise AssertionError
             current_position = position_in_nt
 
             position_in_bytes = record_byte_size * i
@@ -101,16 +103,19 @@ def build(
             track {Tuple[Progress, TaskID]} -- progress bar details
         """
         for colname in ("chromosome", "start", "end"):
-            assert colname in chrom_db.columns, f"missing '{colname}' column"
+            if colname not in chrom_db.columns:
+                raise AssertionError(f"missing '{colname}' column")
         chromosome_set: Set[bytes] = set(chrom_db["chromosome"].values)
-        assert len(chromosome_set) == 1
+        if len(chromosome_set) != 1:
+            raise AssertionError
 
         self.__init_index(chrom_db)
         self.__populate_bins(chrom_db, record_byte_size, track)
         self.__fill_empty_bins()
 
     def __getitem__(self, position_in_nt: int) -> int:
-        assert self._index is not None
+        if self._index is None:
+            raise AssertionError
         binned_to = position_in_nt // self._bin_size
         if binned_to not in self._index:
             return -1
@@ -145,12 +150,15 @@ def __init__(
     ):
         super(ChromosomeData, self).__init__()
 
-        assert "chromosome" in chromosome_db.columns
+        if "chromosome" not in chromosome_db.columns:
+            raise AssertionError
         selected_chrom = chromosome_db["chromosome"][0]
-        assert len(set(chromosome_db["chromosome"].values)) == 1
+        if len(set(chromosome_db["chromosome"].values)) != 1:
+            raise AssertionError
 
         self._record_byte_size = get_dtype_length(dtype)
-        assert self._record_byte_size > 0
+        if self._record_byte_size <= 0:
+            raise AssertionError
 
         self._name = selected_chrom
         self._recordno = chromosome_db.shape[0]
@@ -195,7 +203,8 @@ def _build_index(
             index_bin_size {int} -- index bin size
             progress {Progress} -- progress instance for progress bar with rich
         """
-        assert index_bin_size > 0
+        if index_bin_size <= 0:
+            raise AssertionError
         indexing_track = progress.add_task(
             f"indexing {self._name.decode()}.bin",
             total=chromosome_db.shape[0],
@@ -226,7 +235,8 @@ class ChromosomeDict(object):
     def __init__(self, index_bin_size: int = const.DEFAULT_DATABASE_INDEX_BIN_SIZE):
         super(ChromosomeDict, self).__init__()
         self._data = {}
-        assert index_bin_size > 0
+        if index_bin_size <= 0:
+            raise AssertionError
         self._index_bin_size = index_bin_size
 
     def __len__(self) -> int:

ifpd2/database.py

@@ -38,7 +38,8 @@ def __parse_bytes(self, record: bytes, column_dtypes: Dict[str, str]) -> None:
             record {bytes} -- record bytes
             column_dtypes {Dict[str, str]} -- column dtypes
         """
-        assert len(record) == get_dtype_length(column_dtypes)
+        if len(record) != get_dtype_length(column_dtypes):
+            raise AssertionError
         self._data = {}
         current_location = 0
         for label in const.database_columns:
@@ -137,9 +138,11 @@ def __init__(self, path: str):
             path {str} -- absolute path to database folder
         """
         super(DataBase, self).__init__()
-        assert os.path.isdir(path), f"cannot find database folder '{path}'"
+        if not os.path.isdir(path):
+            raise AssertionError(f"cannot find database folder '{path}'")
         db_pickle_path = os.path.join(path, "db.pickle")
-        assert os.path.isfile(db_pickle_path), f"'db.pickle is missing in '{path}'"
+        if not os.path.isfile(db_pickle_path):
+            raise AssertionError(f"'db.pickle is missing in '{path}'")
 
         with open(db_pickle_path, "rb") as IH:
             details = pickle.load(IH)
@@ -150,15 +153,18 @@ def __init__(self, path: str):
             else:
                 self._args = dict(details["args"])
 
-        assert isinstance(self._chromosomes, ChromosomeDict)
+        if not isinstance(self._chromosomes, ChromosomeDict):
+            raise AssertionError
         for chromosome in self.chromosome_list:
             chromosome_path = os.path.join(path, f"{chromosome.decode()}.bin")
-            assert os.path.isfile(
+            if not os.path.isfile(
                 chromosome_path
-            ), f"missing expected chromosome file: '{chromosome_path}'"
+            ):
+                raise AssertionError(f"missing expected chromosome file: '{chromosome_path}'")
 
         self._record_byte_size = get_dtype_length(self._dtype)
-        assert self._record_byte_size > 0
+        if self._record_byte_size <= 0:
+            raise AssertionError
 
         self._root = path
 

ifpd2/dataclasses.py

@@ -19,9 +19,11 @@ class Folder:
 
     def __post_init__(self):
         if self.exists:
-            assert isdir(self.path)
+            if not isdir(self.path):
+                raise AssertionError
         else:
-            assert not path_exists(self.path)
+            if path_exists(self.path):
+                raise AssertionError
 
 
 @dataclass(frozen=True)
@@ -31,33 +33,38 @@ class File:
 
     def __post_init__(self):
         if self.exists:
-            assert isfile(self.path)
+            if not isfile(self.path):
+                raise AssertionError
         else:
-            assert not path_exists(self.path)
+            if path_exists(self.path):
+                raise AssertionError
 
 
 @dataclass(frozen=True)
 class PositiveInteger:
     n: int
 
     def __post_init__(self):
-        assert self.n >= 1
+        if self.n < 1:
+            raise AssertionError
 
 
 @dataclass(frozen=True)
 class NonNegativeFloat:
     n: float
 
     def __post_init__(self):
-        assert self.n >= 0
+        if self.n < 0:
+            raise AssertionError
 
 
 @dataclass(frozen=True)
 class NonNegativeInteger:
     n: int
 
     def __post_init__(self):
-        assert self.n > 0
+        if self.n <= 0:
+            raise AssertionError
 
 
 @dataclass(frozen=True)
@@ -68,12 +75,15 @@ class PositiveFloat:
 
     def __post_init__(self):
         if self.limit is None:
-            assert 0 < self.n
+            if 0 >= self.n:
+                raise AssertionError
 
         elif self.limit_included:
-            assert 0 < self.n <= self.limit
+            if not 0 < self.n <= self.limit:
+                raise AssertionError
         else:
-            assert 0 < self.n < self.limit
+            if not 0 < self.n < self.limit:
+                raise AssertionError
 
 
 @dataclass(frozen=True)
@@ -82,8 +92,10 @@ class GenomicRegion:
     end: int
 
     def __post_init__(self):
-        assert self.start >= 0
-        assert self.end >= self.start or self.end == -1
+        if self.start < 0:
+            raise AssertionError
+        if not (self.end >= self.start or self.end == -1):
+            raise AssertionError
 
     def astuple(self) -> Tuple[int, int]:
         return (self.start, self.end)
@@ -95,8 +107,10 @@ class NonNegativeIntInterval:
     end: int
 
     def __post_init__(self):
-        assert self._from >= 0
-        assert self.end >= self.first
+        if self._from < 0:
+            raise AssertionError
+        if self.end < self.first:
+            raise AssertionError
 
     def astuple(self) -> Tuple[int, int]:
         return (self.start, self.end)
@@ -109,8 +123,10 @@ class QueryWindow:
 
     def __post_init__(self):
         if self.size is not None:
-            assert self.size >= 1
-        assert 0 < self.shift <= 1
+            if self.size < 1:
+                raise AssertionError
+        if not 0 < self.shift <= 1:
+            raise AssertionError
 
     def astuple(self) -> Tuple[Optional[int], Optional[float]]:
         return (self.size, self.shift)
@@ -122,8 +138,10 @@ class QueryFocus:
     step: float
 
     def __post_init__(self):
-        assert self.size > 0
-        assert self.step > 0
+        if self.size <= 0:
+            raise AssertionError
+        if self.step <= 0:
+            raise AssertionError
 
 
 @dataclass(frozen=True)
@@ -141,6 +159,9 @@ class GCRange:
     high: float
 
     def __post_init__(self):
-        assert 0 <= self.low <= 1
-        assert 0 <= self.high <= 1
-        assert self.low <= self.high
+        if not 0 <= self.low <= 1:
+            raise AssertionError
+        if not 0 <= self.high <= 1:
+            raise AssertionError
+        if self.low > self.high:
+            raise AssertionError

ifpd2/fasta.py

@@ -10,7 +10,8 @@
 
 
 def extract_kmers(input_path: str, kmer_size: int) -> List[Tuple[str, str]]:
-    assert isfile(input_path)
+    if not isfile(input_path):
+        raise AssertionError
     with open(input_path) as FH:
         oligos_list: List[Tuple[str, str]] = []
         for record_header, record_sequence in tqdm(

ifpd2/io.py

@@ -45,7 +45,8 @@ def parse_hush(path: str) -> pd.DataFrame:
     Returns:
         pd.DataFrame -- parsed HUSH data
     """
-    assert os.path.isfile(path), f"cannot find file '{path}'"
+    if not os.path.isfile(path):
+        raise AssertionError(f"cannot find file '{path}'")
     logging.info(f"parsing: '{path}'")
     sequence_lengths: Set[int] = set()
     parsed_lines: List[Tuple[str, str, int]] = []
@@ -81,11 +82,13 @@ def parse_melting(path: str, sep: str = "\t", header: bool = True) -> pd.DataFra
     Returns:
         pd.DataFrame -- parsed oligo-melting data
     """
-    assert os.path.isfile(path), f"cannot find file '{path}'"
+    if not os.path.isfile(path):
+        raise AssertionError(f"cannot find file '{path}'")
     logging.info(f"parsing: '{path}'")
     expected_columns = copy.copy(const.dtype_melting)
     melting_df = pd.read_csv(path, sep=sep, header=None, skiprows=1 if header else 0)
-    assert melting_df.shape[1] == len(expected_columns)
+    if melting_df.shape[1] != len(expected_columns):
+        raise AssertionError
     melting_df.columns = list(expected_columns.keys())
     melting_df.set_index("name", inplace=True)
     expected_columns.pop("name", None)
@@ -104,7 +107,8 @@ def parse_secondary(path: str) -> pd.DataFrame:
     Returns:
         pd.DataFrame -- parsed OligoArrayAux .ct data
     """
-    assert os.path.isfile(path), f"cannot find file '{path}'"
+    if not os.path.isfile(path):
+        raise AssertionError(f"cannot find file '{path}'")
     logging.info(f"parsing: '{path}'")
     parsed_lines: List[Tuple[str, float]] = []
     with open(path, "r") as IH: