kernpy 1.0.1__tar.gz → 1.0.2__tar.gz

{kernpy-1.0.1 → kernpy-1.0.2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: kernpy
-Version: 1.0.1
+Version: 1.0.2
 Summary: Python Humdrum **kern and **mens utilities
 Project-URL: Homepage, https://github.com/OMR-PRAIG-UA-ES/kernpy
 Project-URL: Documentation, https://github.com/OMR-PRAIG-UA-ES/kernpy#readme
@@ -174,32 +174,32 @@ kp.dump(document, "newfile_custom.krn",
 print(kp.BEKERN_CATEGORIES)
 ```
 
-- Use `tokenizer` to select how the categories are split. By default, the `normalizedKern` tokenizer is used.
+- Use `encoding` to select how the categories are split. By default, the `normalizedKern` encoding is used.
 
 ```python
 import kernpy as kp
 
 kp.dump(document, "newfile_normalized.krn",
-        tokenizer=kp.Encoding.normalizedKern)  # Default tokenizer
+        encoding=kp.Encoding.normalizedKern)  # Default encoding
 ```
-Select the proper Humdrum **kern tokenizer:
+Select the proper Humdrum **kern encoding:
 
-`kernpy` provides different tokenizers to export the content each symbol in different formats.
+`kernpy` provides different encodings to export the content each symbol in different formats.
 
-| Encoding | Tokenized    | Description                            |
+| Encoding | Output       | Description                            |
 |----------|--------------|----------------------------------------|
 | kern     | 2.bb-_L      | Traditional Humdrum **kern encoding    |
 | ekern    | 2@.@bb@-·_·L | Extended Humdrum **kern encoding       |
 
-Use the `Encoding` enum class to select the tokenizer:
+Use the `Encoding` enum class to select the encoding:
 
 ```python
 import kernpy as kp
 
 doc, _ = kp.load('resource_dir/legacy/chor048.krn')
 
-kern_content = kp.dumps(doc, tokenizer=kp.Encoding.normalizedKern)
-ekern_content = kp.dumps(doc, tokenizer=kp.Encoding.eKern)
+kern_content = kp.dumps(doc, encoding=kp.Encoding.normalizedKern)
+ekern_content = kp.dumps(doc, encoding=kp.Encoding.eKern)
 ```
 
 - Use `from_measure` and `to_measure` to select the measures to export. By default, all the measures are exported.
@@ -236,7 +236,7 @@ kp.dump(document, "newfile.krn",
         spine_types=['**kern'],  # Export only the **kern spines
         include=kp.BEKERN_CATEGORIES,  # Token categories to include
         exclude={kp.TokenCategory.PITCH},  # Token categories to exclude
-        tokenizer=kp.Encoding.eKern,  # Kern encoding
+        encoding=kp.Encoding.eKern,  # Kern encoding
         from_measure=1,  # First from measure 1
         to_measure=10,  # Last measure exported
         spine_ids=[0, 1],  # Export only the first and the second spine
@@ -339,7 +339,7 @@ for page_label, bounding_box_measure in doc.page_bounding_boxes.items():
    kp.dump(doc, f"foo_{page_label}.ekrn",
            spine_types=['**kern'],
            token_categories=kp.BEKERN_CATEGORIES,
-           tokenizer=kp.Encoding.eKern,
+           encoding=kp.Encoding.eKern,
            from_measure=bounding_box_measure.from_measure,
            to_measure=bounding_box_measure.to_measure - 1  # TODO: Check bounds            
            )

{kernpy-1.0.1 → kernpy-1.0.2}/README.md

@@ -155,32 +155,32 @@ kp.dump(document, "newfile_custom.krn",
 print(kp.BEKERN_CATEGORIES)
 ```
 
-- Use `tokenizer` to select how the categories are split. By default, the `normalizedKern` tokenizer is used.
+- Use `encoding` to select how the categories are split. By default, the `normalizedKern` encoding is used.
 
 ```python
 import kernpy as kp
 
 kp.dump(document, "newfile_normalized.krn",
-        tokenizer=kp.Encoding.normalizedKern)  # Default tokenizer
+        encoding=kp.Encoding.normalizedKern)  # Default encoding
 ```
-Select the proper Humdrum **kern tokenizer:
+Select the proper Humdrum **kern encoding:
 
-`kernpy` provides different tokenizers to export the content each symbol in different formats.
+`kernpy` provides different encodings to export the content each symbol in different formats.
 
-| Encoding | Tokenized    | Description                            |
+| Encoding | Output       | Description                            |
 |----------|--------------|----------------------------------------|
 | kern     | 2.bb-_L      | Traditional Humdrum **kern encoding    |
 | ekern    | 2@.@bb@-·_·L | Extended Humdrum **kern encoding       |
 
-Use the `Encoding` enum class to select the tokenizer:
+Use the `Encoding` enum class to select the encoding:
 
 ```python
 import kernpy as kp
 
 doc, _ = kp.load('resource_dir/legacy/chor048.krn')
 
-kern_content = kp.dumps(doc, tokenizer=kp.Encoding.normalizedKern)
-ekern_content = kp.dumps(doc, tokenizer=kp.Encoding.eKern)
+kern_content = kp.dumps(doc, encoding=kp.Encoding.normalizedKern)
+ekern_content = kp.dumps(doc, encoding=kp.Encoding.eKern)
 ```
 
 - Use `from_measure` and `to_measure` to select the measures to export. By default, all the measures are exported.
@@ -217,7 +217,7 @@ kp.dump(document, "newfile.krn",
         spine_types=['**kern'],  # Export only the **kern spines
         include=kp.BEKERN_CATEGORIES,  # Token categories to include
         exclude={kp.TokenCategory.PITCH},  # Token categories to exclude
-        tokenizer=kp.Encoding.eKern,  # Kern encoding
+        encoding=kp.Encoding.eKern,  # Kern encoding
         from_measure=1,  # First from measure 1
         to_measure=10,  # Last measure exported
         spine_ids=[0, 1],  # Export only the first and the second spine
@@ -320,7 +320,7 @@ for page_label, bounding_box_measure in doc.page_bounding_boxes.items():
    kp.dump(doc, f"foo_{page_label}.ekrn",
            spine_types=['**kern'],
            token_categories=kp.BEKERN_CATEGORIES,
-           tokenizer=kp.Encoding.eKern,
+           encoding=kp.Encoding.eKern,
            from_measure=bounding_box_measure.from_measure,
            to_measure=bounding_box_measure.to_measure - 1  # TODO: Check bounds            
            )

{kernpy-1.0.1 → kernpy-1.0.2}/docs/get-started/tutorial.md

@@ -117,15 +117,15 @@ kp.dump(document, "newfile_custom.krn",
         exclude={kp.TokenCategory.PITCH})
 ```
 
-- Use `tokenizer` to select how the categories are split. By default, the `normalizedKern` tokenizer is used.
+- Use `encoding` to select how the categories are split. By default, the `normalizedKern` encoding is used.
 
 ```python
 import kernpy as kp
 
 kp.dump(document, "newfile_normalized.krn",
-        tokenizer=kp.Encoding.normalizedKern)  # Default tokenizer
+        encoding=kp.Encoding.normalizedKern)  # Default encoding
 ```
-Select the proper Humdrum **kern tokenizer:
+Select the proper Humdrum **kern encoding:
 
 `kernpy` provides different tokenizers to export the content each symbol in different formats.
 
@@ -134,15 +134,15 @@ Select the proper Humdrum **kern tokenizer:
 | kern     | 2.bb-_L      | Traditional Humdrum **kern encoding    |
 | ekern    | 2@.@bb@-·_·L | Extended Humdrum **kern encoding       |
 
-Use the `Encoding` enum class to select the tokenizer:
+Use the `Encoding` enum class to select the encoding:
 
 ```python
 import kernpy as kp
 
 doc, _ = kp.load('resource_dir/legacy/chor048.krn')
 
-kern_content = kp.dumps(doc, tokenizer=kp.Encoding.normalizedKern)
-ekern_content = kp.dumps(doc, tokenizer=kp.Encoding.eKern)
+kern_content = kp.dumps(doc, encoding=kp.Encoding.normalizedKern)
+ekern_content = kp.dumps(doc, encoding=kp.Encoding.eKern)
 ```
 
 - Use `from_measure` and `to_measure` to select the measures to export. By default, all the measures are exported.
@@ -179,7 +179,7 @@ kp.dump(document, "newfile.krn",
         spine_types=['**kern'],  # Export only the **kern spines
         include=kp.BEKERN_CATEGORIES,  # Token categories to include
         exclude={kp.TokenCategory.PITCH},  # Token categories to exclude
-        tokenizer=kp.Encoding.eKern,  # Kern encoding
+        encoding=kp.Encoding.eKern,  # Kern encoding
         from_measure=1,  # First from measure 1
         to_measure=10,  # Last measure exported
         spine_ids=[0, 1],  # Export only the first and the second spine
@@ -282,7 +282,7 @@ for page_label, bounding_box_measure in doc.page_bounding_boxes.items():
     kp.dump(doc, f"foo_{page_label}.ekrn",
             spine_types=['**kern'],
             token_categories=kp.BEKERN_CATEGORIES,
-            tokenizer=kp.Encoding.eKern,
+            encoding=kp.Encoding.eKern,
             from_measure=bounding_box_measure.from_measure,
             to_measure=bounding_box_measure.to_measure - 1  # TODO: Check bounds            
             )

{kernpy-1.0.1 → kernpy-1.0.2}/kernpy/core/exporter.py

@@ -153,7 +153,7 @@ class HeaderTokenGenerator:
     """
     HeaderTokenGenerator class.
 
-    This class is used to translate the HeaderTokens to the specific tokenizer format.
+    This class is used to translate the HeaderTokens to the specific encoding format.
     """
     @classmethod
     def new(cls, *, token: HeaderToken, type: Encoding):
@@ -162,7 +162,7 @@ class HeaderTokenGenerator:
 
         Args:
             token (HeaderToken): The HeaderToken to be translated.
-            type (Encoding): The tokenizer to be used.
+            type (Encoding): The encoding to be used.
 
         Examples:
             >>> header = HeaderToken('**kern', 0)

{kernpy-1.0.1 → kernpy-1.0.2}/kernpy/core/tokenizers.py

@@ -18,7 +18,7 @@ class Encoding(Enum):  # TODO: Eventually, polymorphism will be used to export d
         >>> doc, _ = kp.load('path/to/file.krn')
         >>>
         >>> # Save the file using the specified encoding
-        >>> exported_content = kp.dumps(tokenizer=kp.Encoding.normalizedKern)
+        >>> exported_content = kp.dumps(encoding=kp.Encoding.normalizedKern)
     """
     eKern = 'ekern'
     normalizedKern = 'kern'

{kernpy-1.0.1 → kernpy-1.0.2}/kernpy/io/public.py

@@ -12,7 +12,9 @@ from kernpy import Encoding
 from kernpy.core import (
     Document, Importer, Exporter, ExportOptions, GraphvizExporter,
     generic,
-    TokenCategoryHierarchyMapper)
+    TokenCategoryHierarchyMapper,
+    TokenCategory,
+)
 
 
 def load(fp: Union[str, Path], *, raise_on_errors: Optional[bool] = False, **kwargs) -> (Document, List[str]):
@@ -84,13 +86,13 @@ def loads(s, *, raise_on_errors: Optional[bool] = False, **kwargs) -> (Document,
 
 
 def dump(document: Document, fp: Union[str, Path], *,
-         spine_types: [] = None,
-         include: [] = None,
-         exclude: [] = None,
+         spine_types: [str] = None,
+         include: [TokenCategory] = None,
+         exclude: [TokenCategory] = None,
          from_measure: int = None,
          to_measure: int = None,
-         tokenizer: Encoding = None,
-         instruments: [] = None,
+         encoding: Encoding = None,
+         instruments: [str] = None,
          show_measure_numbers: bool = None,
          spine_ids: [int] = None
          ) -> None:
@@ -104,7 +106,7 @@ def dump(document: Document, fp: Union[str, Path], *,
         exclude (Iterable): The token categories to exclude from the exported file. When None, no token categories will be excluded.
         from_measure (int): The measure to start exporting. When None, the exporter will start from the beginning of the file. The first measure is 1
         to_measure (int): The measure to end exporting. When None, the exporter will end at the end of the file.
-        tokenizer (Encoding): The type of the **kern file to export.
+        encoding (Encoding): The type of the **kern file to export.
         instruments (Iterable): The instruments to export. If None, all the instruments will be exported.
         show_measure_numbers (Bool): Show the measure numbers in the exported file.
         spine_ids (Iterable): The ids of the spines to export. When None, all the spines will be exported. \
@@ -130,7 +132,7 @@ def dump(document: Document, fp: Union[str, Path], *,
         exclude=exclude,
         from_measure=from_measure,
         to_measure=to_measure,
-        kern_type=tokenizer,
+        kern_type=encoding,
         instruments=instruments,
         show_measure_numbers=show_measure_numbers,
         spine_ids=spine_ids
@@ -144,13 +146,13 @@ def dump(document: Document, fp: Union[str, Path], *,
 
 
 def dumps(document: Document, *,
-          spine_types: [] = None,
-          include: [] = None,
-          exclude: [] = None,
+          spine_types: [str] = None,
+          include: [TokenCategory] = None,
+          exclude: [TokenCategory] = None,
           from_measure: int = None,
           to_measure: int = None,
-          tokenizer: Encoding = None,
-          instruments: [] = None,
+          encoding: Encoding = None,
+          instruments: [str] = None,
           show_measure_numbers: bool = None,
           spine_ids: [int] = None
           ) -> str:
@@ -164,7 +166,7 @@ def dumps(document: Document, *,
         exclude (Iterable): The token categories to exclude from the exported file. When None, no token categories will be excluded.
         from_measure (int): The measure to start exporting. When None, the exporter will start from the beginning of the file. The first measure is 1
         to_measure (int): The measure to end exporting. When None, the exporter will end at the end of the file.
-        tokenizer (Encoding): The type of the **kern file to export.
+        encoding (Encoding): The type of the **kern file to export.
         instruments (Iterable): The instruments to export. If None, all the instruments will be exported.
         show_measure_numbers (Bool): Show the measure numbers in the exported file.
         spine_ids (Iterable): The ids of the spines to export. When None, all the spines will be exported. \
@@ -189,7 +191,7 @@ def dumps(document: Document, *,
         exclude=exclude,
         from_measure=from_measure,
         to_measure=to_measure,
-        kern_type=tokenizer,
+        kern_type=encoding,
         instruments=instruments,
         show_measure_numbers=show_measure_numbers,
         spine_ids=spine_ids

{kernpy-1.0.1 → kernpy-1.0.2}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "hatchling.build"
 
 [project]
 name = "kernpy"
-version = "1.0.1"
+version = "1.0.2"
 authors = [
     { name = "David Rizo Valero", email = "drizo@ua.es"},
     { name = "Joan Cerveto Serrano", email = "joan.cerveto@ua.es"}

{kernpy-1.0.1 → kernpy-1.0.2}/test/test_exporter.py

@@ -87,7 +87,7 @@ class ExporterTestCase(unittest.TestCase):
             expected_content = f.read()
 
         doc, _ = kp.read(input_path)
-        real_content = kp.dumps(doc, tokenizer=kp.Encoding.eKern, include=kp.BEKERN_CATEGORIES)
+        real_content = kp.dumps(doc, encoding=kp.Encoding.eKern, include=kp.BEKERN_CATEGORIES)
 
         self.assertEqual(expected_content, real_content,
                          f"File content mismatch: \nExpected:\n{expected_content}\n{40 * '='}\nReal\n{real_content}")

{kernpy-1.0.1 → kernpy-1.0.2}/test/test_humdrum_importer.py

@@ -44,7 +44,7 @@ class ImporterTestCase(unittest.TestCase):
                                   from_measure=from_measure,
                                   to_measure=to_measure,
                                   include=kp.BEKERN_CATEGORIES,
-                                  tokenizer=kp.Encoding.eKern)
+                                  encoding=kp.Encoding.eKern)
 
         if exported_ekern != expected_content:
             logging.info('---- Expected content ----')
@@ -346,7 +346,7 @@ class ImporterTestCase(unittest.TestCase):
         kp.store_graph(doc, '/tmp/x.dot')
         exported_real = kp.dumps(doc,
                                  spine_types=['**kern'],
-                                 tokenizer=kp.Encoding.normalizedKern,
+                                 encoding=kp.Encoding.normalizedKern,
                                  from_measure=9,
                                  to_measure=13)
 
@@ -381,7 +381,7 @@ class ImporterTestCase(unittest.TestCase):
         output_kern = kp.dumps(document,
                                spine_types=['**kern'],
                                include=kp.BEKERN_CATEGORIES,
-                               tokenizer=kp.Encoding.eKern, )
+                               encoding=kp.Encoding.eKern, )
         expected_ekern = "**ekern\n4@c\n4@d\n4@e\n4@f\n*-\n"
         self.assertEqual(expected_ekern, output_kern)
 
@@ -710,7 +710,7 @@ class ImporterTestCase(unittest.TestCase):
         doc, err = kp.load('resource_dir/legacy/chor048.krn')
 
         content = kp.dumps(doc, spine_types=['**kern', '**root', '**harm'],
-                           tokenizer=kp.Encoding.eKern)
+                           encoding=kp.Encoding.eKern)
 
         doc_2, _ = kp.loads(content)  # raise error if the content is not valid
 

{kernpy-1.0.1 → kernpy-1.0.2}/test/test_tokenizer.py

@@ -20,40 +20,40 @@ class TestTokenizer(unittest.TestCase):
 
 
     def test_ekern_tokenizer_1(self):
-        tokenizer = kp.EkernTokenizer(token_categories=self.default_categories)
-        token_str = tokenizer.tokenize(self.token_1)
+        encoding = kp.EkernTokenizer(token_categories=self.default_categories)
+        token_str = encoding.tokenize(self.token_1)
         self.assertEqual('2@.@bb@-·_·L', token_str)
         self.token_1.export.assert_called()
 
     def test_kern_tokenizer_1(self):
-        tokenizer = kp.KernTokenizer(token_categories=self.default_categories)
-        token_str = tokenizer.tokenize(self.token_1)
+        encoding = kp.KernTokenizer(token_categories=self.default_categories)
+        token_str = encoding.tokenize(self.token_1)
         self.assertEqual('2.bb-_L', token_str)
         self.token_1.export.assert_called()
 
     def test_bkern_tokenizer_1(self):
-        tokenizer = kp.BkernTokenizer(token_categories=self.default_categories)
-        token_str = tokenizer.tokenize(self.token_1)
+        encoding = kp.BkernTokenizer(token_categories=self.default_categories)
+        token_str = encoding.tokenize(self.token_1)
         self.assertEqual('2.bb-', token_str)
         self.token_1.export.assert_called()
 
     def test_bekern_tokenizer_1(self):
-        tokenizer = kp.BekernTokenizer(token_categories=self.default_categories)
-        token_str = tokenizer.tokenize(self.token_1)
+        encoding = kp.BekernTokenizer(token_categories=self.default_categories)
+        token_str = encoding.tokenize(self.token_1)
         self.assertEqual('2@.@bb@-', token_str)
         self.token_1.export.assert_called()
 
     def test_tokenizer_factory_kern(self):
-        tokenizer = kp.TokenizerFactory.create(kp.Encoding.normalizedKern.value, token_categories=self.default_categories)
-        self.assertIsInstance(tokenizer, kp.KernTokenizer)
+        encoding = kp.TokenizerFactory.create(kp.Encoding.normalizedKern.value, token_categories=self.default_categories)
+        self.assertIsInstance(encoding, kp.KernTokenizer)
 
     def test_tokenizer_factory_ekern(self):
-        tokenizer = kp.TokenizerFactory.create(kp.Encoding.eKern.value, token_categories=self.default_categories)
-        self.assertIsInstance(tokenizer, kp.EkernTokenizer)
+        encoding = kp.TokenizerFactory.create(kp.Encoding.eKern.value, token_categories=self.default_categories)
+        self.assertIsInstance(encoding, kp.EkernTokenizer)
 
     def test_tokenizer_factory_bkern(self):
-        tokenizer = kp.TokenizerFactory.create(kp.Encoding.bKern.value, token_categories=self.default_categories)
-        self.assertIsInstance(tokenizer, kp.BekernTokenizer)
+        encoding = kp.TokenizerFactory.create(kp.Encoding.bKern.value, token_categories=self.default_categories)
+        self.assertIsInstance(encoding, kp.BekernTokenizer)
 
     def test_tokenizer_factory_raise_error_if_none(self):
         with self.assertRaises(ValueError):