chore: resolve Ruff warnings A003, B023, D103 and PLR0911 (#684)

Co-authored-by: Johannes Nussbaum <39048939+jnussbaum@users.noreply.github.com>

.github/workflows/tests-on-push.yml

@@ -67,7 +67,7 @@ jobs:
         run: >
           poetry run ruff check . 
           --output-format=github 
-          --ignore=A002,A003,B023,D101,D102,D103,PLR0911,PLR0912,PLR0913,PLR0915,PLR2004,PLR5501,PLW0603
+          --ignore=A002,D101,D102,PLR0912,PLR0913,PLR0915,PLR2004,PLR5501,PLW0603
       - name: Formatting with ruff
         run: poetry run ruff format .
       - name: Linting with mypy

.pre-commit-config.yaml

@@ -8,12 +8,8 @@ repos:
       - id: ruff
         args: [
           --ignore=A002,
-          --ignore=A003,
-          --ignore=B023,
           --ignore=D101,
           --ignore=D102,
-          --ignore=D103,
-          --ignore=PLR0911,
           --ignore=PLR0912,
           --ignore=PLR0913,
           --ignore=PLR0915,

pyproject.toml

@@ -104,20 +104,20 @@ pythonpath = [".", "src", "test"]
 
 
 [tool.mypy]
-ignore_missing_imports = true                                       # TODO: deactivate this
+ignore_missing_imports = true                                 # TODO: deactivate this
 show_column_numbers = true
 strict = true
 exclude = [
-    "src/dsp_tools/models/helpers.py",                              # TODO: activate this
-    "src/dsp_tools/models/langstring.py",                           # TODO: activate this
-    "src/dsp_tools/commands/project/models/group.py",               # TODO: activate this
-    "src/dsp_tools/commands/project/models/listnode.py",            # TODO: activate this
-    "src/dsp_tools/commands/project/models/ontology.py",            # TODO: activate this
-    "src/dsp_tools/commands/project/models/project.py",             # TODO: activate this
-    "src/dsp_tools/models/projectContext.py",                       # TODO: activate this
-    "src/dsp_tools/commands/project/models/propertyclass.py",       # TODO: activate this
-    "src/dsp_tools/commands/project/models/resourceclass.py",       # TODO: activate this
-    "src/dsp_tools/commands/project/models/user.py",                # TODO: activate this
+    "src/dsp_tools/models/helpers.py",                        # TODO: activate this
+    "src/dsp_tools/models/langstring.py",                     # TODO: activate this
+    "src/dsp_tools/commands/project/models/group.py",         # TODO: activate this
+    "src/dsp_tools/commands/project/models/listnode.py",      # TODO: activate this
+    "src/dsp_tools/commands/project/models/ontology.py",      # TODO: activate this
+    "src/dsp_tools/commands/project/models/project.py",       # TODO: activate this
+    "src/dsp_tools/models/projectContext.py",                 # TODO: activate this
+    "src/dsp_tools/commands/project/models/propertyclass.py", # TODO: activate this
+    "src/dsp_tools/commands/project/models/resourceclass.py", # TODO: activate this
+    "src/dsp_tools/commands/project/models/user.py",          # TODO: activate this
 ]
 
 
@@ -167,6 +167,11 @@ ignore = [
 "testdata/**" = [
     "INP001",   # implicit-namespace-package    # there are some python files, but no __init__.py
 ]
+"test/*" = [
+    "D103",     # pydocstyle: undocumented-public-function
+    "D102",     # pydocstyle: undocumented-public-method
+    "D101",     # pydocstyle: undocumented-public-class
+]
 
 
 [tool.ruff.lint.pydocstyle]

src/dsp_tools/cli/call_action.py

@@ -24,7 +24,7 @@
 logger = get_logger(__name__)
 
 
-def call_requested_action(args: argparse.Namespace) -> bool:
+def call_requested_action(args: argparse.Namespace) -> bool:  # noqa: PLR0911 (Too many return statements)
     """
     Call the appropriate method of DSP-TOOLS.
 

src/dsp_tools/commands/excel2json/project.py

@@ -57,7 +57,7 @@ def excel2json(
 def _validate_folder_structure_get_filenames(data_model_files: str) -> tuple[list[Path], list[Path]]:
     if not Path(data_model_files).is_dir():
         raise UserError(f"ERROR: {data_model_files} is not a directory.")
-    folder = [x for x in Path(data_model_files).glob("*") if not regex.search(r"^(\.|~\$).+", x.name)]
+    folder = [x for x in Path(data_model_files).glob("*") if _non_hidden(x)]
     processed_files = []
     onto_folders, processed_onto = _get_validate_onto_folder(data_model_files, folder)
     processed_files.extend(processed_onto)
@@ -77,7 +77,7 @@ def _get_validate_list_folder(data_model_files: str, folder: list[Path]) -> tupl
     processed_files: list[str] = []
     listfolder = [x for x in folder if x.is_dir() and x.name == "lists"]
     if listfolder:
-        listfolder_contents = [x for x in Path(listfolder[0]).glob("*") if not regex.search(r"^(\.|~\$).+", x.name)]
+        listfolder_contents = [x for x in Path(listfolder[0]).glob("*") if _non_hidden(x)]
         if not all(regex.search(r"(de|en|fr|it|rm).xlsx", file.name) for file in listfolder_contents):
             raise UserError(
                 f"The only files allowed in '{data_model_files}/lists' are en.xlsx, de.xlsx, fr.xlsx, it.xlsx, rm.xlsx"
@@ -94,7 +94,7 @@ def _get_validate_onto_folder(data_model_files: str, folder: list[Path]) -> tupl
             f"'{data_model_files}' must contain at least one subfolder named after the pattern 'onto_name (onto_label)'"
         )
     for onto_folder in onto_folders:
-        contents = sorted([x.name for x in Path(onto_folder).glob("*") if not regex.search(r"^(\.|~\$).+", x.name)])
+        contents = sorted([x.name for x in Path(onto_folder).glob("*") if _non_hidden(x)])
         if contents != ["properties.xlsx", "resources.xlsx"]:
             raise UserError(
                 f"ERROR: '{data_model_files}/{onto_folder.name}' must contain one file 'properties.xlsx' "
@@ -104,6 +104,10 @@ def _get_validate_onto_folder(data_model_files: str, folder: list[Path]) -> tupl
     return onto_folders, processed_files
 
 
+def _non_hidden(path: Path) -> bool:
+    return not regex.search(r"^(\.|~\$).+", path.name)
+
+
 def _create_project_json(
     data_model_files: str, listfolder: list[Path], onto_folders: list[Path]
 ) -> tuple[bool, dict[str, Any]]:

src/dsp_tools/commands/excel2xml/excel2xml_lib.py

@@ -11,6 +11,7 @@
 import regex
 from lxml import etree
 from lxml.builder import E
+from regex import Match
 
 from dsp_tools.commands.excel2xml.propertyelement import PropertyElement
 from dsp_tools.models.exceptions import BaseError
@@ -136,38 +137,43 @@ def find_date_in_string(string: str) -> Optional[str]:
     # sanitize input, just in case that the method was called on an empty or N/A cell
     if not check_notna(string):
         return None
+    try:
+        return _find_date_in_string_throwing(string)
+    except ValueError:
+        return None
 
-    months_dict = {
-        "January": 1,
-        "Jan": 1,
-        "February": 2,
-        "Feb": 2,
-        "March": 3,
-        "Mar": 3,
-        "April": 4,
-        "Apr": 4,
-        "May": 5,
-        "June": 6,
-        "Jun": 6,
-        "July": 7,
-        "Jul": 7,
-        "August": 8,
-        "Aug": 8,
-        "September": 9,
-        "Sept": 9,
-        "October": 10,
-        "Oct": 10,
-        "November": 11,
-        "Nov": 11,
-        "December": 12,
-        "Dec": 12,
-    }
-
-    startdate: Optional[datetime.date] = None
-    enddate: Optional[datetime.date] = None
-    startyear: Optional[int] = None
-    endyear: Optional[int] = None
 
+_months_dict = {
+    "January": 1,
+    "Jan": 1,
+    "February": 2,
+    "Feb": 2,
+    "March": 3,
+    "Mar": 3,
+    "April": 4,
+    "Apr": 4,
+    "May": 5,
+    "June": 6,
+    "Jun": 6,
+    "July": 7,
+    "Jul": 7,
+    "August": 8,
+    "Aug": 8,
+    "September": 9,
+    "Sept": 9,
+    "October": 10,
+    "Oct": 10,
+    "November": 11,
+    "Nov": 11,
+    "December": 12,
+    "Dec": 12,
+}
+
+
+def _find_date_in_string_throwing(string: str) -> str | None:
+    """
+    This function is the same as find_date_in_string(), but may raise a ValueError instead of returning None.
+    """
     year_regex = r"([0-2]?[0-9][0-9][0-9])"
     month_regex = r"([0-1]?[0-9])"
     day_regex = r"([0-3]?[0-9])"
@@ -194,79 +200,79 @@ def find_date_in_string(string: str) -> Optional[str]:
         string,
     )
     # template: March 9, 1908 | March5,1908 | May 11, 1906
-    all_months = "|".join(months_dict)
+    all_months = "|".join(_months_dict)
     monthname_date_regex = rf"{lookbehind}({all_months}) ?{day_regex}, ?{year_regex}{lookahead}"
     monthname_date = regex.search(monthname_date_regex, string)
     # template: 1849/50 | 1849-50 | 1849/1850
     year_range = regex.search(lookbehind + year_regex + r"[/-](\d{1,4})" + lookahead, string)
     # template: 1907
     year_only = regex.search(rf"{lookbehind}{year_regex}{lookahead}", string)
 
+    res: str | None = None
     if iso_date:
-        year = int(iso_date.group(1))
-        month = int(iso_date.group(2))
-        day = int(iso_date.group(3))
-        try:
-            startdate = datetime.date(year, month, day)
-            enddate = startdate
-        except ValueError:
-            return None
-
+        res = _from_iso_date(iso_date)
     elif eur_date_range:
-        startday = int(eur_date_range.group(1))
-        startmonth = int(eur_date_range.group(2)) if eur_date_range.group(2) else int(eur_date_range.group(5))
-        startyear = int(eur_date_range.group(3)) if eur_date_range.group(3) else int(eur_date_range.group(6))
-        endday = int(eur_date_range.group(4))
-        endmonth = int(eur_date_range.group(5))
-        endyear = int(eur_date_range.group(6))
-        try:
-            startdate = datetime.date(startyear, startmonth, startday)
-            enddate = datetime.date(endyear, endmonth, endday)
-            if enddate < startdate:
-                raise ValueError
-        except ValueError:
-            return None
-
+        res = _from_eur_date_range(eur_date_range)
     elif eur_date:
-        startday = int(eur_date.group(1))
-        startmonth = int(eur_date.group(2))
-        startyear = int(eur_date.group(3))
-        try:
-            startdate = datetime.date(startyear, startmonth, startday)
-            enddate = startdate
-        except ValueError:
-            return None
-
+        res = _from_eur_date(eur_date)
     elif monthname_date:
-        day = int(monthname_date.group(2))
-        month = months_dict[monthname_date.group(1)]
-        year = int(monthname_date.group(3))
-        try:
-            startdate = datetime.date(year, month, day)
-            enddate = startdate
-        except ValueError:
-            return None
-
+        res = _from_monthname_date(monthname_date)
     elif year_range:
-        startyear = int(year_range.group(1))
-        endyear = int(year_range.group(2))
-        if endyear // 10 == 0:
-            # endyear is only 1-digit: add the first 2-3 digits of startyear
-            endyear = startyear // 10 * 10 + endyear
-        elif endyear // 100 == 0:
-            # endyear is only 2-digit: add the first 1-2 digits of startyear
-            endyear = startyear // 100 * 100 + endyear
-
+        res = _from_year_range(year_range)
     elif year_only:
-        startyear = int(year_only.group(0))
-        endyear = startyear
+        year = int(year_only.group(0))
+        res = f"GREGORIAN:CE:{year}:CE:{year}"
+    return res
 
-    if startdate and enddate:
-        return f"GREGORIAN:CE:{startdate.isoformat()}:CE:{enddate.isoformat()}"
-    elif startyear and endyear:
-        return f"GREGORIAN:CE:{startyear}:CE:{endyear}"
-    else:
-        return None
+
+def _from_iso_date(iso_date: Match[str]) -> str:
+    year = int(iso_date.group(1))
+    month = int(iso_date.group(2))
+    day = int(iso_date.group(3))
+    date = datetime.date(year, month, day)
+    return f"GREGORIAN:CE:{date.isoformat()}:CE:{date.isoformat()}"
+
+
+def _from_eur_date_range(eur_date_range: Match[str]) -> str:
+    startday = int(eur_date_range.group(1))
+    startmonth = int(eur_date_range.group(2)) if eur_date_range.group(2) else int(eur_date_range.group(5))
+    startyear = int(eur_date_range.group(3)) if eur_date_range.group(3) else int(eur_date_range.group(6))
+    endday = int(eur_date_range.group(4))
+    endmonth = int(eur_date_range.group(5))
+    endyear = int(eur_date_range.group(6))
+    startdate = datetime.date(startyear, startmonth, startday)
+    enddate = datetime.date(endyear, endmonth, endday)
+    if enddate < startdate:
+        raise ValueError
+    return f"GREGORIAN:CE:{startdate.isoformat()}:CE:{enddate.isoformat()}"
+
+
+def _from_eur_date(eur_date: Match[str]) -> str:
+    startday = int(eur_date.group(1))
+    startmonth = int(eur_date.group(2))
+    startyear = int(eur_date.group(3))
+    date = datetime.date(startyear, startmonth, startday)
+    return f"GREGORIAN:CE:{date.isoformat()}:CE:{date.isoformat()}"
+
+
+def _from_monthname_date(monthname_date: Match[str]) -> str:
+    day = int(monthname_date.group(2))
+    month = _months_dict[monthname_date.group(1)]
+    year = int(monthname_date.group(3))
+    date = datetime.date(year, month, day)
+    return f"GREGORIAN:CE:{date.isoformat()}:CE:{date.isoformat()}"
+
+
+def _from_year_range(year_range: Match[str]) -> str:
+    startyear = int(year_range.group(1))
+    endyear = int(year_range.group(2))
+    if endyear // 10 == 0:
+        # endyear is only 1-digit: add the first 2-3 digits of startyear
+        endyear = startyear // 10 * 10 + endyear
+    elif endyear // 100 == 0:
+        # endyear is only 2-digit: add the first 1-2 digits of startyear
+        endyear = startyear // 100 * 100 + endyear
+    return f"GREGORIAN:CE:{startyear}:CE:{endyear}"
 
 
 def prepare_value(

src/dsp_tools/commands/project/models/listnode.py

@@ -35,27 +35,6 @@
 from dsp_tools.utils.connection import Connection
 
 
-def list_creator(con: Connection, project: Project, parent_node: "ListNode", nodes: list[dict]) -> list["ListNode"]:
-    nodelist: list[ListNode] = []
-
-    for n in nodes:
-        new_node = ListNode(
-            con=con,
-            project=project,
-            label=n["labels"],
-            comments=n.get("comments"),
-            name=n["name"],
-            parent=parent_node,
-        )
-
-        if n.get("nodes"):
-            new_node.children = list_creator(con, project, new_node, n["nodes"])
-
-        nodelist.append(new_node)
-
-    return nodelist
-
-
 class ListNode(Model):
     """
     This class represents a list node

src/dsp_tools/commands/project/models/ontology.py

@@ -199,7 +199,7 @@ def fromJsonObj(cls, con: Connection, json_obj: Any) -> "Ontology":
             property_classes = [
                 PropertyClass.fromJsonObj(con=con, context=context, json_obj=a)
                 for a in properties_obj
-                if WithId(a.get(knora_api + ":objectType")).str() != "knora-api:LinkValue"
+                if WithId(a.get(knora_api + ":objectType")).to_string() != "knora-api:LinkValue"
             ]
         return cls(
             con=con,

src/dsp_tools/commands/project/models/propertyclass.py

@@ -209,13 +209,13 @@ def fromJsonObj(cls, con: Connection, context: Context, json_obj: Any) -> "Prope
             superproperties = [x["@id"] for x in superproperties_obj if x and x.get("@id")]
         else:
             superproperties = None
-        rdf_object = WithId(json_obj.get(knora_api + ":objectType")).str()
-        rdf_subject = WithId(json_obj.get(knora_api + ":subjectType")).str()
+        rdf_object = WithId(json_obj.get(knora_api + ":objectType")).to_string()
+        rdf_subject = WithId(json_obj.get(knora_api + ":subjectType")).to_string()
         label = LangString.fromJsonLdObj(json_obj.get(rdfs + ":label"))
         comment = LangString.fromJsonLdObj(json_obj.get(rdfs + ":comment"))
         gui_element = None
         if json_obj.get(salsah_gui + ":guiElement") is not None:
-            gui_element = WithId(json_obj.get(salsah_gui + ":guiElement")).str()
+            gui_element = WithId(json_obj.get(salsah_gui + ":guiElement")).to_string()
             gui_element = gui_element.replace("Pulldown", "List")
             gui_element = gui_element.replace("Radio", "List")
         gui_attributes_list = json_obj.get(salsah_gui + ":guiAttribute")