Big progress on refactoring

Author: cmutel

src/flowmapper/__init__.py

@@ -5,15 +5,17 @@
     "Flow",
     "Flowmap",
     "flowmapper",
-    "OutputFormat",
+    "Match",
+    "MatchCondition",
+    "NormalizedFlow",
     "UnitField",
 )
 
 __version__ = "0.4.2"
 
 from flowmapper.cas import CASField
 from flowmapper.context import ContextField
-from flowmapper.flow import Flow
+from flowmapper.domain import Flow, Match, MatchCondition, NormalizedFlow
 from flowmapper.flowmap import Flowmap
-from flowmapper.main import OutputFormat, flowmapper
+from flowmapper.main import flowmapper
 from flowmapper.unit import UnitField

src/flowmapper/cas.py

@@ -1,23 +1,24 @@
+import re
 from collections import UserString
 from functools import cached_property
-import re
-
 
-valid_cas = re.compile(r"^\s*[0-9]{3,7}-[0-9]{2}-[0-9]{1}\s*$")
+valid_cas = re.compile(r"^\s*[0-9]{2,7}-[0-9]{2}-[0-9]{1}\s*$")
 
 
 class CASField(UserString):
     def __init__(self, string: str):
         if not isinstance(string, (str, UserString)):
-            raise TypeError(f"CASField takes only `str`, but got {type(string)} for {string}")
-        if not valid_cas.search(string):
-            raise ValueError(f"Given input is not valid CAS formatting: {string}")
-        super().__init__(string)
+            raise TypeError(
+                f"CASField takes only `str`, but got {type(string)} for {string}"
+            )
+        if not valid_cas.search(str(string)):
+            raise ValueError(f"Given input is not valid CAS formatting: '{string}'")
+        super().__init__(str(string))
 
     @staticmethod
     def from_string(string: str | None) -> "CASField | None":
         """Returns `None` if CAS number is invalid"""
-        if string is None:
+        if string is None or not isinstance(string, (str, UserString)):
             return None
         new_cas = CASField(string.strip().lstrip("0").strip())
         if not new_cas.valid():
@@ -52,5 +53,6 @@ def check_digit_expected(self):
         return result
 
     def valid(self):
-        return self.digits[-1] == self.check_digit_expected
-
+        return (self.digits[-1] == self.check_digit_expected) and bool(
+            valid_cas.search(self.data)
+        )

src/flowmapper/cli.py

@@ -1,12 +1,15 @@
 import importlib.metadata
 from pathlib import Path
-
-import typer
 from typing import Annotated
+
 import structlog
+import typer
 
-from flowmapper.extraction import ecospold2_biosphere_extractor, simapro_csv_biosphere_extractor
-from flowmapper.main import OutputFormat, flowmapper
+from flowmapper.extraction import (
+    ecospold2_biosphere_extractor,
+    simapro_csv_biosphere_extractor,
+)
+from flowmapper.main import flowmapper
 
 try:
     from pyinstrument import Profiler
@@ -44,10 +47,6 @@ def map(
     output_dir: Annotated[
         Path, typer.Option(help="Directory to save mapping and diagnostics files")
     ] = Path("."),
-    format: Annotated[
-        OutputFormat,
-        typer.Option(help="Mapping file output format", case_sensitive=False),
-    ] = "randonneur",
     default_transformations: Annotated[
         bool, typer.Option(help="Include default context and unit transformations?")
     ] = True,
@@ -92,7 +91,7 @@ def map(
             "location": "location",
         },
     }
-    
+
     if profile:
         if Profiler is None:
             raise ImportError("`pyinstrument` not installed")
@@ -106,9 +105,14 @@ def map(
         mapping_target=generic_mapping,
         source_id=source.stem,
         target_id=target.stem,
-        contributors=[{"title": "flowmapper", "roles": ["author"], "path": "https://github.com/cmutel/flowmapper"}],
+        contributors=[
+            {
+                "title": "flowmapper",
+                "roles": ["author"],
+                "path": "https://github.com/cmutel/flowmapper",
+            }
+        ],
         output_dir=output_dir,
-        format=format,
         default_transformations=default_transformations,
         transformations=transformations,
         unmatched_source=unmatched_source,

src/flowmapper/context.py

@@ -1,5 +1,4 @@
-from typing import Self, Any
-
+from typing import Any, Self
 
 MISSING_VALUES = {
     "",
@@ -28,13 +27,18 @@ def normalize(self, obj: Any | None = None, mapping: dict | None = None) -> Self
 
         intermediate = [elem.lower().strip() for elem in intermediate]
 
-        while intermediate[-1] in MISSING_VALUES:
+        while intermediate and intermediate[-1] in MISSING_VALUES:
+            if len(intermediate) == 1:
+                break
             intermediate = intermediate[:-1]
 
-        # TODO: Apply mapping
-
         return type(self)(value=tuple(intermediate))
 
+    def as_tuple(self) -> tuple | str:
+        if isinstance(self.value, str):
+            return self.value
+        return tuple(self.value)
+
     def export_as_string(self, join_character: str = "✂️"):
         if isinstance(self.value, (list, tuple)):
             return join_character.join(self.value)
@@ -53,7 +57,7 @@ def __eq__(self, other: Any) -> bool:
                 return False
 
     def __repr__(self):
-        return f"ContextField: {self.value}"
+        return str(self.value)
 
     def __bool__(self):
         return bool(self.value)