Typing (#80)

* Python 3.8 is EOL; add mypy

* Add typing

- remove SegmentCollection, FileSourcableMixin, UNAHandlingMixin

* fmt

* mypy in tests

* Add mypy target in makefile

* Use collections directly (new in 3.9)

* rm SegmentCollection from docs

* rm commented returns

* stricter typing

* Stricter syntax_identifier

* remove py3.8 pipeline

* remove py3.8 from packaging_test.yml

* remove py3.8 from unittests.yml

* 3.10 adjustment: Optional and Union

* 3.10 adjustment: f-strings

* rm 3.9 from ci

* add 3.13 for testing

---------

Co-authored-by: Christian González <christian.gonzalez@nerdocs.at>

Author: tammoippen

.github/workflows/packaging_test.yml

@@ -11,7 +11,7 @@ jobs:
     runs-on: ${{ matrix.os }}
     strategy:
       matrix:
-        python-version: ["3.8", "3.9", "3.10", "3.11", "3.12"]
+        python-version: ["3.10", "3.11", "3.12", "3.13"]
         os: [ubuntu-latest]
     steps:
       - uses: actions/checkout@v4

.github/workflows/unittests.yml

@@ -6,7 +6,7 @@ jobs:
     runs-on: ${{ matrix.os }}
     strategy:
       matrix:
-        python-version: ["3.8", "3.9", "3.10", "3.11", "3.12"]
+        python-version: ["3.10", "3.11", "3.12", "3.13"]
         os: [ubuntu-latest]
     steps:
       - uses: actions/checkout@v4

.travis.yml

@@ -1,10 +1,9 @@
 language: python
 python:
-  - 3.8
-  - 3.9
   - 3.10
   - 3.11
   - 3.12
+  - 3.13
 before_install:
   - python --version
   - pip install -U pip

Makefile

@@ -7,13 +7,14 @@ install:
 build: dev
 	python -m build
 
-
 upload: build
 	twine upload dist/*
 
 test:
 	pytest --ignore tests/test_huge_message.py
 
+mypy:
+	mypy --pretty pydifact
+
 test-extended:
 	pytest
-

README.md

@@ -49,7 +49,7 @@ interchange = Interchange.from_str(
 )
 for message in interchange.get_messages():
     for segment in message.segments:
-        print("Segment tag: {}, content: {}".format(segment.tag, segment.elements))
+        print(f"Segment tag: {segment.tag}, content: {segment.elements}")
 ```
 
 You may also want to iterate directly on segments :
@@ -68,7 +68,7 @@ interchange = Interchange.from_str(
 )
 
 for segment in interchange.segments:
-    print("Segment tag: {}, content: {}".format(segment.tag, segment.elements))
+    print(f"Segment tag: {segment.tags}, content: {segment.elements}")
 ```
 
 Or you can create an EDI interchange on the fly:
@@ -100,7 +100,7 @@ from pydifact.segmentcollection import RawSegmentCollection
 collection = RawSegmentCollection.from_str("UNH+1+ORDERS:D:96A:UN:EAN008'")
 
 for segment in collection.segments:
-    print("Segment tag: {}, content: {}".format(segment.tag, segment.elements))
+    print(f"Segment tag: {segment.tags}, content: {segment.elements}")
 ```
 
 
@@ -124,7 +124,7 @@ To develop pydifact, clone the repository and install the dev requirements:
 
 ```bash
 make dev
-# or 
+# or
 # pip install -e .[dev]
 ```
 

TODO.md

@@ -2,7 +2,4 @@
 
 * Translation of following files:
   * Parser, ParserTest
-  * Message, MessageTest 
-* When Python 3.10 is adapted: 
-  * replace Union[x,y] with x|y and Optional[x] with x|None in annotations
-  * use f-strings instead of .format-strings
+  * Message, MessageTest

docs/API.rst

@@ -1,10 +1,6 @@
 API
 ===
 
-SegmentCollection
-------------------
-.. automodule:: pydifact.segmentcollection
-    :members:
 
 Parser
 ------

pydifact/__init__.py

@@ -25,7 +25,6 @@
 __version__ = "0.1.8"
 
 from .control.characters import Characters
-from .segmentcollection import SegmentCollection
 from .parser import Parser
 from .segments import Segment
 from .serializer import Serializer

pydifact/control/characters.py

@@ -82,13 +82,12 @@ def with_control_character(self, cc_type: str, char: str):
         # set the attribute dynamically.
         if not hasattr(self, cc_type):
             raise AttributeError(
-                "{} doesn't have an attribute with the name '{}'".format(self, cc_type)
+                f"{self} doesn't have an attribute with the name '{cc_type}'"
             )
 
         other = copy(self)
         setattr(other, cc_type, char)
 
-        # return clone
         return other
 
     @property
@@ -115,10 +114,10 @@ def __str__(self) -> str:
         )
 
     def __repr__(self):
-        return "'{}'".format(self.__str__())
+        return f"'{self.__str__()}'"
 
     def __eq__(self, other):
-        if type(other) == str:
+        if isinstance(other, str):
             other = Characters.from_str(other)
         return (
             (self.component_separator == other.component_separator)

pydifact/parser.py

@@ -19,11 +19,11 @@
 # LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
 # OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
 # THE SOFTWARE.
-from typing import Optional, Generator, Any
+from collections.abc import Iterator
 
 from pydifact.tokenizer import Tokenizer
 from pydifact.token import Token
-from pydifact.segments import Segment, SegmentFactory
+from pydifact.segments import Element, Elements, Segment, SegmentFactory
 from pydifact.control import Characters
 
 
@@ -32,15 +32,15 @@ class Parser:
 
     def __init__(
         self,
-        factory: Optional[SegmentFactory] = None,
-        characters: Optional[Characters] = None,
-    ):
+        factory: SegmentFactory | None = None,
+        characters: Characters | None = None,
+    ) -> None:
         self.factory = factory or SegmentFactory()
         self.characters = characters or Characters()
 
     def parse(
-        self, message: str, characters: Characters = None
-    ) -> Generator[Segment, Any, None]:
+        self, message: str, characters: Characters | None = None
+    ) -> Iterator[Segment]:
         """Parse the message into a list of segments.
 
         :param characters: the control characters to use, if there is no
@@ -87,8 +87,8 @@ def parse(
 
     @staticmethod
     def get_control_characters(
-        message: str, characters: Characters = None
-    ) -> Optional[Characters]:
+        message: str, characters: Characters | None = None
+    ) -> Characters | None:
         """Read the UNA segment from the passed string and extract/store the control characters from it.
 
         :param message: a valid EDI message string, or UNA segment string,
@@ -112,7 +112,6 @@ def get_control_characters(
 
         # Get the character definitions
         chars = message[3:9]
-        characters.is_extracted_from_message = True
 
         characters.component_separator = chars[0]
         characters.data_separator = chars[1]
@@ -124,8 +123,8 @@ def get_control_characters(
         return characters
 
     def convert_tokens_to_segments(
-        self, tokens: list, characters: Characters, with_una: bool = False
-    ):
+        self, tokens: Iterator[Token], characters: Characters, with_una: bool = False
+    ) -> Iterator[Segment]:
         """Convert the tokenized message into an array of segments.
         :param tokens: The tokens that make up the message
         :param characters: the control characters to use
@@ -134,9 +133,10 @@ def convert_tokens_to_segments(
         :rtype list of Segment
         """
 
-        segments = []
-        current_segment = []
-        data_element = None
+        segments: list[Elements] = []
+        current_segment: Elements = []
+        data_element: list[str] = []
+        data_element_value: Element
         in_segment = False
         empty_component_counter = 0
 
@@ -149,12 +149,14 @@ def convert_tokens_to_segments(
                 if token.type == Token.Type.TERMINATOR:
                     in_segment = False
                     if len(data_element) == 0:  # empty element
-                        data_element = ""
-                    if len(data_element) == 1:
+                        data_element_value = ""
+                    elif len(data_element) == 1:
                         # use a str instead of a list
-                        data_element = data_element[0]
+                        data_element_value = data_element[0]
+                    else:
+                        data_element_value = data_element
 
-                    current_segment.append(data_element)
+                    current_segment.append(data_element_value)
                     data_element = []
                     continue
 
@@ -174,11 +176,13 @@ def convert_tokens_to_segments(
             # data_element to an empty list []
             if token.type == Token.Type.DATA_SEPARATOR:
                 if len(data_element) == 0:  # empty element
-                    data_element = ""
+                    data_element_value = ""
                 elif len(data_element) == 1:
-                    data_element = data_element[0]
+                    data_element_value = data_element[0]
+                else:
+                    data_element_value = data_element
 
-                current_segment.append(data_element)
+                current_segment.append(data_element_value)
 
                 data_element = []
                 empty_component_counter = 0
@@ -210,4 +214,5 @@ def convert_tokens_to_segments(
 
         for segment in segments:
             name = segment.pop(0)
-            yield self.factory.create_segment(name, *segment)
+            # create_segment tests name type
+            yield self.factory.create_segment(name, *segment)  # type: ignore