Implementing Sequence input formats

tests/data/doc_1.txt

-Lorem ipsum dolor sit amet, consectetur adipiscing elit. Pellentesque ullamcorper id ante eu maximus. Nullam efficitur vehicula ante, in luctus ante sollicitudin iaculis. Donec efficitur porta ante, ut venenatis enim faucibus quis. Sed vitae egestas neque, a tempor tortor. Suspendisse nec maximus mi. Nam iaculis convallis ultricies. Nunc vel tempor magna, in ultrices enim. Duis id tristique nisl. In hac habitasse platea dictumst. Suspendisse at arcu placerat lectus interdum sollicitudin.
+Lorem ipsum dolor sit amet
\ No newline at end of file
+Nam lectus turpis
\ No newline at end of file

tests/test_sequence.py

 import pytest
 import pytest
 from textflow.Sequence import Sequence
 from textflow.Sequence import Sequence
 
 
-class CustomSequence(Sequence):
-    def __init__(self, text: str):
-        self.id = "root"
-        self.sequences = text.split(" ")
 
 
-@pytest.fixture
-def sequence():
-    return CustomSequence("Esto es una prueba")
+def test_sequence_wrong_format():
+    with pytest.raises(Exception):
+        sequence = Sequence("csv", "Lorem ipsum dolor sit amet")
 
 
-def test_str(sequence):
-    assert str(sequence) == "id: root, sequences: ['Esto', 'es', 'una', 'prueba']"
 
 
-def test_repr(sequence):
-    assert repr(sequence) == "Sequence('Esto', 'es', 'una', 'prueba')"
+@pytest.mark.parametrize(
+    "sequence, expected", 
+    [
+        pytest.param(
+            Sequence("string", "Lorem ipsum dolor sit amet"),
+            "Lorem ipsum dolor sit amet"
+        ), 
+        pytest.param(
+            Sequence("text", "tests/data/doc_1.txt"),
+            "Lorem ipsum dolor sit amet\nNam lectus turpis"
+        )
+    ]
+)
+def test_str(sequence, expected):
+    assert str(sequence) == expected
 
 
-def test_len(sequence):
-    assert len(sequence) == 4
 
 
-def test_iter(sequence):
-    assert list(sequence) == ["Esto", "es", "una", "prueba"]
+@pytest.mark.parametrize(
+    "sequence, expected", 
+    [
+        pytest.param(
+            Sequence("string", "Lorem ipsum dolor sit amet"),
+            (
+                "Sequence(\n"
+                "  id: string\n"
+                "  sequences: 'Lorem', 'ipsum', 'dolor', 'sit', 'amet'\n"
+                ")"
+            )
+        ), 
+        pytest.param(
+            Sequence("text", "tests/data/doc_1.txt"),
+            (
+                "Sequence(\n"
+                "  id: doc_1\n"
+                "  sequences: 'Lorem ipsum dolor sit amet', 'Nam lectus turpis'\n"
+                ")"
+            )
+        )
+    ]
+)
+def test_repr(sequence, expected):
+    assert repr(sequence) == expected
+
+
+@pytest.mark.parametrize(
+    "sequence, expected", 
+    [
+        pytest.param(
+            Sequence("string", "Lorem ipsum dolor sit amet"),
+            5
+        ), 
+        pytest.param(
+            Sequence("text", "tests/data/doc_1.txt"),
+            2
+        )
+    ]
+)
+def test_len(sequence, expected):
+    assert len(sequence) == expected
+
+
+@pytest.mark.parametrize(
+    "sequence, expected", 
+    [
+        pytest.param(
+            Sequence("string", "Lorem ipsum dolor sit amet"),
+            ["Lorem", "ipsum", "dolor", "sit", "amet"]
+        ), 
+        pytest.param(
+            Sequence("text", "tests/data/doc_1.txt"),
+            ["Lorem ipsum dolor sit amet", "Nam lectus turpis"]
+        )
+    ]
+)
+def test_iter(sequence, expected):
+    assert list(sequence) == expected
+
+
+@pytest.mark.parametrize(
+    "sequence, expected", 
+    [
+        pytest.param(
+            Sequence("string", "Lorem ipsum dolor sit amet"),
+            "Lorem"
+        ), 
+        pytest.param(
+            Sequence("text", "tests/data/doc_1.txt"),
+            "Lorem ipsum dolor sit amet"
+        )
+    ]
+)
+def test_getitem(sequence, expected):
+    assert sequence[0] == expected
 
 
-def test_getitem(sequence):
-    assert sequence[0] == "Esto"
 
 
 def test_get_depth():
 def test_get_depth():
     pass
     pass
 
 
+
 def test_filter():
 def test_filter():
     pass
     pass
\ No newline at end of file

textflow/Sequence.py

+import os
+from typing import Optional
+
+
 class SequenceIterator:
 class SequenceIterator:
     def __init__(self, sequences):
     def __init__(self, sequences):
         self.idx = 0
         self.idx = 0
@@ -16,21 +20,58 @@ class SequenceIterator:
 
 
 
 
 class Sequence:
 class Sequence:
-    def __init__(self, object):
-        # TODO: Extraer id y sequences a partir del object de cualquier forma que se nos ocurra
-        # ver: https://huggingface.co/docs/datasets/v2.0.0/en/package_reference/loading_methods#datasets.load_dataset
-        if isinstance(object, str):
-            self.id = object
-        else:
-            self.id = "collection"
-        self.sequences = ["subcollection_1", "subcollection_2", "subcollection_3"]
+    """Summary of class here.
+
+    Longer class information...
+    Longer class information...
+
+    Attributes:
+        id: ...
+        text: ...
+        sequences: ...
+    """
+    def __init__(self, format: str, item: object, id: Optional[str] = None):
+        """Creates a sequence from an input object.
+
+        Args:
+            format: A string containing the input data's type.
+            item: An object representing the input data. It can be a string for a
+            string format or a file path for a text format.
+            id: A string to overwrite the default's sequence id.
+        """
+        VALID_FORMATS = ("string", "text")
+        
+        if format not in VALID_FORMATS:
+            raise ValueError(
+                f"{format} is not a valid format. Valid formats: {VALID_FORMATS}"
+            )
+
+        # Splits string text by whitespace
+        if format == "string":
+            if not isinstance(item, str):
+                raise ValueError(f"{item} is not an instance of string")
+            self.id = id if id else "string"
+            self.text = item
+            self.sequences = item.split(" ")
+
+        # Splits file text by \n
+        if format == "text":
+            self.id = id if id else os.path.basename(item).split(".")[0]
+            with open(item, "r") as f:
+                self.text = f.read()
+            self.sequences = self.text.split("\n")
 
 
     def __str__(self):
     def __str__(self):
-        return f"id: {self.id}, sequences: {self.sequences}"
+        return self.text
 
 
     def __repr__(self):
     def __repr__(self):
         values = ", ".join([sequence.__repr__() for sequence in self.sequences])
         values = ", ".join([sequence.__repr__() for sequence in self.sequences])
-        return f"Sequence({values})"
+        return (
+            "Sequence(\n"
+            f"  id: {self.id}\n"
+            f"  sequences: {values}\n"
+            ")"
+        )
 
 
     def __len__(self):
     def __len__(self):
         return len(self.sequences)
         return len(self.sequences)