.github/workflows/mypy.yaml

@@ -0,0 +1,30 @@
+name: Mypy
+
+on:
+  push:
+  pull_request:
+  workflow_dispatch:
+
+jobs:
+  mypy:
+    runs-on: ubuntu-latest
+    env:
+      UV_CACHE_DIR: /tmp/.uv-cache
+    steps:
+      - name: Install git-annex
+        run: |
+          sudo apt-get update
+          sudo apt-get install -y git-annex
+      - name: Check out the repository
+        uses: https://github.com/RouxAntoine/checkout@v4.1.8
+        with:
+          show-progress: true
+      - name: Install uv
+        uses: astral-sh/setup-uv@v7
+        with:
+          python-version: ${{ matrix.python-version }}
+          enable-cache: true
+      - name: Install corrlib
+        run: uv sync --locked --all-extras --dev --python "3.12"
+      - name: Run tests
+        run: uv run mypy corrlib

corrlib/__main__.py

@@ -1,8 +1,9 @@
 from corrlib import cli, __app_name__
 
 
-def main():
+def main() -> None:
     cli.app(prog_name=__app_name__)
+    return
 
 
 if __name__ == "__main__":

corrlib/find.py

@@ -5,10 +5,11 @@ import pandas as pd
 import numpy as np
 from .input.implementations import codes
 from .tools import k2m, get_file
+from typing import Any, Union, Optional
 # this will implement the search functionality
 
 
-def _project_lookup_by_alias(db, alias):
+def _project_lookup_by_alias(db: str, alias: str) -> str:
     # this will lookup the project name based on the alias
     conn = sqlite3.connect(db)
     c = conn.cursor()
@@ -19,10 +20,10 @@ def _project_lookup_by_alias(db, alias):
         print("Error: multiple projects found with alias " + alias)
     elif len(results) == 0:
         raise Exception("Error: no project found with alias " + alias)
-    return results[0][0]
+    return str(results[0][0])
 
 
-def _project_lookup_by_id(db, uuid):
+def _project_lookup_by_id(db: str, uuid: str) -> list[tuple[str, str]]:
     conn = sqlite3.connect(db)
     c = conn.cursor()
     c.execute(f"SELECT * FROM 'projects' WHERE id = '{uuid}'")
@@ -31,7 +32,8 @@ def _project_lookup_by_id(db, uuid):
     return results
 
 
-def _db_lookup(db, ensemble, correlator_name,code, project=None,  parameters=None, created_before=None, created_after=None, updated_before=None, updated_after=None, revision=None):
+def _db_lookup(db: str, ensemble: str, correlator_name: str, code: str, project: Optional[str]=None,  parameters: Optional[str]=None,
+               created_before: Optional[str]=None, created_after: Optional[Any]=None, updated_before: Optional[Any]=None, updated_after: Optional[Any]=None) -> pd.DataFrame:
     project_str = project
 
     search_expr = f"SELECT * FROM 'backlogs' WHERE name = '{correlator_name}' AND ensemble = '{ensemble}'"
@@ -55,7 +57,7 @@ def _db_lookup(db, ensemble, correlator_name,code, project=None,  parameters=Non
     return results
 
 
-def sfcf_filter(results, **kwargs):
+def sfcf_filter(results: pd.DataFrame, **kwargs: Any) -> pd.DataFrame:
     drops = []
     for ind in range(len(results)):
         result = results.iloc[ind]
@@ -138,24 +140,25 @@ def sfcf_filter(results, **kwargs):
     return results.drop(drops)
 
 
-def find_record(path, ensemble, correlator_name, code, project=None, parameters=None, created_before=None, created_after=None, updated_before=None, updated_after=None, revision=None, **kwargs):
+def find_record(path: str, ensemble: str, correlator_name: str, code: str, project: Optional[str]=None, parameters: Optional[str]=None,
+                created_before: Optional[str]=None, created_after: Optional[str]=None, updated_before: Optional[str]=None, updated_after: Optional[str]=None, revision: Optional[str]=None, **kwargs: Any) -> pd.DataFrame:
     db = path + '/backlogger.db'
     if code not in codes:
         raise ValueError("Code " + code + "unknown, take one of the following:" + ", ".join(codes))
     get_file(path, "backlogger.db")
-    results = _db_lookup(db, ensemble, correlator_name,code, project, parameters=parameters, created_before=created_before, created_after=created_after, updated_before=updated_before, updated_after=updated_after, revision=revision)
+    results = _db_lookup(db, ensemble, correlator_name,code, project, parameters=parameters, created_before=created_before, created_after=created_after, updated_before=updated_before, updated_after=updated_after)
     if code == "sfcf":
         results = sfcf_filter(results, **kwargs)
     print("Found " + str(len(results)) + " result" + ("s" if len(results)>1 else ""))
     return results.reset_index()
 
 
-def find_project(path, name):
+def find_project(path: str, name: str) -> str:
     get_file(path, "backlogger.db")
     return _project_lookup_by_alias(os.path.join(path, "backlogger.db"), name)
 
 
-def list_projects(path):
+def list_projects(path: str) -> list[tuple[str, str]]:
     db = path + '/backlogger.db'
     get_file(path, "backlogger.db")
     conn = sqlite3.connect(db)

corrlib/git_tools.py

@@ -5,7 +5,7 @@ import git
 GITMODULES_FILE = '.gitmodules'
 
 
-def move_submodule(repo_path, old_path, new_path):
+def move_submodule(repo_path: str, old_path: str, new_path: str) -> None:
     """
     Move a submodule to a new location.
 
@@ -41,3 +41,4 @@ def move_submodule(repo_path, old_path, new_path):
     repo.git.add('.gitmodules')
     # save new state of the dataset
     dl.save(repo_path, message=f"Move module from {old_path} to {new_path}", dataset=repo_path)
+    return

corrlib/initialization.py

@@ -3,7 +3,7 @@ import datalad.api as dl
 import os
 
 
-def _create_db(db):
+def _create_db(db: str) -> None:
     """
     Create the database file and the table.
 
@@ -32,9 +32,10 @@ def _create_db(db):
                   updated_at TEXT)''')
     conn.commit()
     conn.close()
+    return
 
 
-def create(path):
+def create(path: str) -> None:
     """
     Create folder of backlogs.
 
@@ -50,3 +51,4 @@ def create(path):
         fp.write(".cache")
         fp.close()
     dl.save(path, dataset=path, message="Initialize backlogger directory.")
+    return

corrlib/input/openQCD.py

@@ -2,7 +2,7 @@ import pyerrors.input.openQCD as input
 import datalad.api as dl
 import os
 import fnmatch
-from typing import Any
+from typing import Any, Optional
 
 
 def read_ms1_param(path: str, project: str, file_in_project: str) -> dict[str, Any]:
@@ -67,7 +67,7 @@ def read_ms3_param(path: str, project: str, file_in_project: str) -> dict[str, A
     return param
 
 
-def read_rwms(path: str, project: str, dir_in_project: str, param: dict[str, Any], prefix: str, postfix: str="ms1", version: str='2.0', names: list[str]=None, files: list[str]=None) -> dict[str, Any]:
+def read_rwms(path: str, project: str, dir_in_project: str, param: dict[str, Any], prefix: str, postfix: str="ms1", version: str='2.0', names: Optional[list[str]]=None, files: Optional[list[str]]=None) -> dict[str, Any]:
     dataset = os.path.join(path, "projects", project)
     directory = os.path.join(dataset, dir_in_project)
     if files is None:
@@ -94,7 +94,7 @@ def read_rwms(path: str, project: str, dir_in_project: str, param: dict[str, Any
     return rw_dict
 
 
-def extract_t0(path: str, project: str, dir_in_project: str, param: dict[str, Any], prefix: str, dtr_read: int, xmin: int, spatial_extent: int, fit_range: int = 5, postfix: str=None, names: list[str]=None, files: list[str]=None) -> dict[str, Any]:
+def extract_t0(path: str, project: str, dir_in_project: str, param: dict[str, Any], prefix: str, dtr_read: int, xmin: int, spatial_extent: int, fit_range: int = 5, postfix: str="", names: Optional[list[str]]=None, files: Optional[list[str]]=None) -> dict[str, Any]:
     dataset = os.path.join(path, "projects", project)
     directory = os.path.join(dataset, dir_in_project)
     if files is None:
@@ -132,7 +132,7 @@ def extract_t0(path: str, project: str, dir_in_project: str, param: dict[str, An
     return t0_dict
 
 
-def extract_t1(path: str, project: str, dir_in_project: str, param: dict[str, Any], prefix: str, dtr_read: int, xmin: int, spatial_extent: int, fit_range: int = 5, postfix: str = None, names: list[str]=None, files: list[str]=None) -> dict[str, Any]:
+def extract_t1(path: str, project: str, dir_in_project: str, param: dict[str, Any], prefix: str, dtr_read: int, xmin: int, spatial_extent: int, fit_range: int = 5, postfix: str = "", names: Optional[list[str]]=None, files: Optional[list[str]]=None) -> dict[str, Any]:
     directory = os.path.join(path, "projects", project, dir_in_project)
     if files is None:
         files = []

corrlib/input/sfcf.py

@@ -5,7 +5,7 @@ import os
 from typing import Any
 
 
-bi_corrs: list = ["f_P", "fP", "f_p",
+bi_corrs: list[str] = ["f_P", "fP", "f_p",
             "g_P", "gP", "g_p",
             "fA0", "f_A", "f_a",
             "gA0", "g_A", "g_a",
@@ -43,7 +43,7 @@ bi_corrs: list = ["f_P", "fP", "f_p",
             "l3A2", "l3_A2", "g_av23",
             ]
 
-bb_corrs: list = [
+bb_corrs: list[str] = [
             'F1',
             'F_1',
             'f_1',
@@ -64,7 +64,7 @@ bb_corrs: list = [
             'F_sPdP_d',
             ]
 
-bib_corrs: list = [
+bib_corrs: list[str] = [
             'F_V0',
             'K_V0',
             ]
@@ -184,7 +184,7 @@ def read_param(path: str, project: str, file_in_project: str) -> dict[str, Any]:
     return params
 
 
-def _map_params(params: dict, spec_list: list) -> dict[str, Any]:
+def _map_params(params: dict[str, Any], spec_list: list[str]) -> dict[str, Any]:
     """
     Map the extracted parameters to the extracted data.
 
@@ -194,7 +194,7 @@ def _map_params(params: dict, spec_list: list) -> dict[str, Any]:
         The parameters extracted from the parameter (input) file. in the dict form given by read_param.
     spec_list: list
         The list of specifications that belongs to the dorrelator in question.
-    
+
     Return
     ------
     new_specs: dict
@@ -228,7 +228,7 @@ def _map_params(params: dict, spec_list: list) -> dict[str, Any]:
     return new_specs
 
 
-def get_specs(key, parameters, sep='/') -> str:
+def get_specs(key: str, parameters: dict[str, Any], sep: str = '/') -> str:
     key_parts = key.split(sep)
     if corr_types[key_parts[0]] == 'bi':
         param = _map_params(parameters, key_parts[1:-1])
@@ -238,7 +238,7 @@ def get_specs(key, parameters, sep='/') -> str:
     return s
 
 
-def read_data(path, project, dir_in_project, prefix, param, version='1.0c', cfg_seperator='n', sep='/', **kwargs) -> dict:
+def read_data(path: str, project: str, dir_in_project: str, prefix: str, param: dict[str, Any], version: str = '1.0c', cfg_seperator: str = 'n', sep: str = '/', **kwargs: Any) -> dict[str, Any]:
     """
     Extract the data from the sfcf file.
 

corrlib/main.py

@@ -6,10 +6,10 @@ from .git_tools import move_submodule
 import shutil
 from .find import _project_lookup_by_id
 from .tools import list2str, str2list, get_file
-from typing import Union
+from typing import Union, Optional
 
 
-def create_project(path: str, uuid: str, owner: Union[str, None]=None, tags: Union[str, None]=None, aliases: Union[str, None]=None, code: Union[str, None]=None):
+def create_project(path: str, uuid: str, owner: Union[str, None]=None, tags: Union[list[str], None]=None, aliases: Union[list[str], None]=None, code: Union[str, None]=None) -> None:
     """
     Create a new project entry in the database.
 
@@ -33,10 +33,10 @@ def create_project(path: str, uuid: str, owner: Union[str, None]=None, tags: Uni
         raise ValueError("Project already imported, use update_project() instead.")
 
     dl.unlock(db, dataset=path)
-    alias_str = None
+    alias_str = ""
     if aliases is not None:
         alias_str = list2str(aliases)
-    tag_str = None
+    tag_str = ""
     if tags is not None:
         tag_str = list2str(tags)
     c.execute("INSERT INTO projects (id, aliases, customTags, owner, code, created_at, updated_at) VALUES (?, ?, ?, ?, ?, datetime('now'), datetime('now'))", (uuid, alias_str, tag_str, owner, code))
@@ -45,7 +45,7 @@ def create_project(path: str, uuid: str, owner: Union[str, None]=None, tags: Uni
     dl.save(db, message="Added entry for project " + uuid + " to database", dataset=path)
 
 
-def update_project_data(path, uuid, prop, value = None):
+def update_project_data(path: str, uuid: str, prop: str, value: Union[str, None] = None) -> None:
     get_file(path, "backlogger.db")
     conn = sqlite3.connect(os.path.join(path, "backlogger.db"))
     c = conn.cursor()
@@ -55,7 +55,7 @@ def update_project_data(path, uuid, prop, value = None):
     return
 
 
-def update_aliases(path: str, uuid: str, aliases: list[str]):
+def update_aliases(path: str, uuid: str, aliases: list[str]) -> None:
     db = os.path.join(path, "backlogger.db")
     get_file(path, "backlogger.db")
     known_data = _project_lookup_by_id(db, uuid)[0]
@@ -82,7 +82,7 @@ def update_aliases(path: str, uuid: str, aliases: list[str]):
     return
 
 
-def import_project(path: str, url: str, owner: Union[str, None]=None, tags: Union[str, None]=None, aliases: Union[str, None]=None, code: Union[str, None]=None, isDataset: bool=True):
+def import_project(path: str, url: str, owner: Union[str, None]=None, tags: Optional[list[str]]=None, aliases: Optional[list[str]]=None, code: Optional[str]=None, isDataset: bool=True) -> str:
     """
     Parameters
     ----------
@@ -117,7 +117,7 @@ def import_project(path: str, url: str, owner: Union[str, None]=None, tags: Unio
         dl.install(path=tmp_path, source=url, dataset=path)
     tmp_ds = dl.Dataset(tmp_path)
     conf = dlc.ConfigManager(tmp_ds)
-    uuid = conf.get("datalad.dataset.id")
+    uuid = str(conf.get("datalad.dataset.id"))
     if not uuid:
         raise ValueError("The dataset does not have a uuid!")
     if not os.path.exists(path + "/projects/" + uuid):
@@ -142,9 +142,10 @@ def import_project(path: str, url: str, owner: Union[str, None]=None, tags: Unio
     return uuid
 
 
-def drop_project_data(path: str, uuid: str, path_in_project: str = ""):
+def drop_project_data(path: str, uuid: str, path_in_project: str = "") -> None:
     """
     Drop (parts of) a prject to free up diskspace
     """
     dl.drop(path + "/projects/" + uuid + "/" + path_in_project)
+    return
 

corrlib/meas_io.py

@@ -9,9 +9,10 @@ from pyerrors import Obs, Corr, dump_object, load_object
 from hashlib import sha256
 from .tools import cached, get_file
 import shutil
+from typing import Any
 
 
-def write_measurement(path, ensemble, measurement, uuid, code, parameter_file=None):
+def write_measurement(path: str, ensemble: str, measurement: dict[str, dict[str, dict[str, Any]]], uuid: str, code: str, parameter_file: str) -> None:
     """
     Write a measurement to the backlog.
     If the file for the measurement already exists, update the measurement.
@@ -97,7 +98,7 @@ def write_measurement(path, ensemble, measurement, uuid, code, parameter_file=No
     dl.save(files, message="Add measurements to database", dataset=path)
 
 
-def load_record(path: str, meas_path: str):
+def load_record(path: str, meas_path: str) -> Union[Corr, Obs]:
     """
     Load a list of records by their paths.
 
@@ -116,7 +117,7 @@ def load_record(path: str, meas_path: str):
     return load_records(path, [meas_path])[0]
 
 
-def load_records(path: str, meas_paths: list[str], preloaded = {}) -> list[Union[Corr, Obs]]:
+def load_records(path: str, meas_paths: list[str], preloaded: dict[str, Any] = {}) -> list[Union[Corr, Obs]]:
     """
     Load a list of records by their paths.
 
@@ -138,7 +139,7 @@ def load_records(path: str, meas_paths: list[str], preloaded = {}) -> list[Union
             needed_data[file] = []
         key = mpath.split("::")[1]
         needed_data[file].append(key)
-    returned_data: list = []
+    returned_data: list[Any] = []
     for file in needed_data.keys():
         for key in list(needed_data[file]):
             if os.path.exists(cache_path(path, file, key) + ".p"):
@@ -154,7 +155,7 @@ def load_records(path: str, meas_paths: list[str], preloaded = {}) -> list[Union
     return returned_data
 
 
-def cache_dir(path, file):
+def cache_dir(path: str, file: str) -> str:
     cache_path_list = [path]
     cache_path_list.append(".cache")
     cache_path_list.extend(file.split("/")[1:])
@@ -162,19 +163,19 @@ def cache_dir(path, file):
     return cache_path
 
 
-def cache_path(path, file, key):
+def cache_path(path: str, file: str, key: str) -> str:
     cache_path = os.path.join(cache_dir(path, file), key)
     return cache_path
 
 
-def preload(path: str, file: str):
+def preload(path: str, file: str) -> dict[str, Any]:
     get_file(path, file)
-    filedict = pj.load_json_dict(os.path.join(path, file))
+    filedict: dict[str, Any] = pj.load_json_dict(os.path.join(path, file))
     print("> read file")
     return filedict
 
 
-def drop_record(path: str, meas_path: str):
+def drop_record(path: str, meas_path: str) -> None:
     file_in_archive = meas_path.split("::")[0]
     file = os.path.join(path, file_in_archive)
     db = os.path.join(path, 'backlogger.db')
@@ -199,7 +200,9 @@ def drop_record(path: str, meas_path: str):
     else:
         raise ValueError("This measurement does not exist as a file!")
 
-def drop_cache(path: str):
+
+def drop_cache(path: str) -> None:
     cache_dir = os.path.join(path, ".cache")
     for f in os.listdir(cache_dir):
         shutil.rmtree(os.path.join(cache_dir, f))
+    return

corrlib/toml.py

@@ -16,15 +16,16 @@ from .meas_io import write_measurement
 import datalad.api as dl
 import os
 from .input.implementations import codes as known_codes
+from typing import Any
 
-def replace_string(string: str, name: str, val: str):
+def replace_string(string: str, name: str, val: str) -> str:
     if '{' + name + '}' in string:
         n = string.replace('{' + name + '}', val)
         return n
     else:
         return string
 
-def replace_in_meas(measurements: dict, vars: dict[str, str]):
+def replace_in_meas(measurements: dict[str, dict[str, Any]], vars: dict[str, str]) -> dict[str, dict[str, Any]]:
     # replace global variables
     for name, value in vars.items():
         for m in measurements.keys():
@@ -36,7 +37,7 @@ def replace_in_meas(measurements: dict, vars: dict[str, str]):
                         measurements[m][key][i] = replace_string(measurements[m][key][i], name, value)
     return measurements
 
-def fill_cons(measurements, constants):
+def fill_cons(measurements: dict[str, dict[str, Any]], constants: dict[str, str]) -> dict[str, dict[str, Any]]:
     for m in measurements.keys():
         for name, val in constants.items():
             if name not in measurements[m].keys():
@@ -44,7 +45,7 @@ def fill_cons(measurements, constants):
     return measurements
 
 
-def check_project_data(d: dict) -> None:
+def check_project_data(d: dict[str, dict[str, str]]) -> None:
     if 'project' not in d.keys() or 'measurements' not in d.keys() or len(list(d.keys())) > 4:
         raise ValueError('There should only be maximally be four keys on the top level, "project" and "measurements" are mandatory, "contants" is optional!')
     project_data = d['project']
@@ -57,7 +58,7 @@ def check_project_data(d: dict) -> None:
     return
 
 
-def check_measurement_data(measurements: dict, code: str) -> None:
+def check_measurement_data(measurements: dict[str, dict[str, str]], code: str) -> None:
     var_names: list[str] = []
     if code == "sfcf":
         var_names = ["path", "ensemble", "param_file", "version", "prefix", "cfg_seperator", "names"]
@@ -91,14 +92,14 @@ def import_toml(path: str, file: str, copy_file: bool=True) -> None:
     with open(file, 'rb') as fp:
         toml_dict = toml.load(fp)
     check_project_data(toml_dict)
-    project: dict = toml_dict['project']
+    project: dict[str, Any] = toml_dict['project']
     if project['code'] not in known_codes:
         raise ValueError('Code' + project['code'] + 'has no import implementation!')
-    measurements: dict = toml_dict['measurements']
+    measurements: dict[str, dict[str, Any]] = toml_dict['measurements']
     measurements = fill_cons(measurements, toml_dict['constants'] if 'constants' in toml_dict else {})
     measurements = replace_in_meas(measurements, toml_dict['replace'] if 'replace' in toml_dict else {})
     check_measurement_data(measurements, project['code'])
-    aliases = project.get('aliases', None)
+    aliases = project.get('aliases', [])
     uuid = project.get('uuid', None)
     if uuid is not None:
         if not os.path.exists(path + "/projects/" + uuid):
@@ -133,16 +134,16 @@ def import_toml(path: str, file: str, copy_file: bool=True) -> None:
                     for rwp in ["integrator", "eps", "ntot", "dnms"]:
                         param[rwp] = "Unknown"
                 param['type'] = 't0'
-                measurement = openQCD.extract_t0(path, uuid, md['path'], param, md["prefix"], md["dtr_read"], md["xmin"], md["spatial_extent"],
-                                                 fit_range=md.get('fit_range', 5), postfix=md.get('postfix', None), names=md.get('names', None), files=md.get('files', None))
+                measurement = openQCD.extract_t0(path, uuid, md['path'], param, str(md["prefix"]), int(md["dtr_read"]), int(md["xmin"]), int(md["spatial_extent"]),
+                                                 fit_range=int(md.get('fit_range', 5)), postfix=str(md.get('postfix', '')), names=md.get('names', []), files=md.get('files', []))
             elif md['measurement'] == 't1':
                 if 'param_file' in md:
                     param = openQCD.read_ms3_param(path, uuid, md['param_file'])
                 param['type'] = 't1'
-                measurement = openQCD.extract_t1(path, uuid, md['path'], param, md["prefix"], md["dtr_read"], md["xmin"], md["spatial_extent"],
-                                                 fit_range=md.get('fit_range', 5), postfix=md.get('postfix', None), names=md.get('names', None), files=md.get('files', None))
+                measurement = openQCD.extract_t1(path, uuid, md['path'], param, str(md["prefix"]), int(md["dtr_read"]), int(md["xmin"]), int(md["spatial_extent"]),
+                                                 fit_range=int(md.get('fit_range', 5)), postfix=str(md.get('postfix', '')), names=md.get('names', []), files=md.get('files', []))
 
-        write_measurement(path, ensemble, measurement, uuid, project['code'], (md['param_file'] if 'param_file' in md else None))
+        write_measurement(path, ensemble, measurement, uuid, project['code'], (md['param_file'] if 'param_file' in md else ''))
 
     if not os.path.exists(os.path.join(path, "toml_imports", uuid)):
         os.makedirs(os.path.join(path, "toml_imports", uuid))
@@ -155,7 +156,7 @@ def import_toml(path: str, file: str, copy_file: bool=True) -> None:
     return
 
 
-def reimport_project(path, uuid):
+def reimport_project(path: str, uuid: str) -> None:
     """
     Reimport an existing project using the files that are already available for this project.
 
@@ -173,6 +174,7 @@ def reimport_project(path, uuid):
     return
 
 
-def update_project(path, uuid):
+def update_project(path: str, uuid: str) -> None:
     dl.update(how='merge', follow='sibling', dataset=os.path.join(path, "projects", uuid))
     # reimport_project(path, uuid)
+    return

corrlib/tools.py

@@ -2,10 +2,10 @@ import os
 import datalad.api as dl
 
 
-def str2list(string: str):
+def str2list(string: str) -> list[str]:
     return string.split(",")
 
-def list2str(mylist):
+def list2str(mylist: list[str]) -> str:
     s = ",".join(mylist)
     return s
 
@@ -19,10 +19,11 @@ def k2m(k: float) -> float:
     return (1/(2*k))-4
 
 
-def get_file(path: str, file: str):
+def get_file(path: str, file: str) -> None:
     if file == "backlogger.db":
         print("Downloading database...")
     else:
         print("Downloading data...")
     dl.get(os.path.join(path, file), dataset=path)
     print("> downloaded file")
+    return

pyproject.toml

@@ -9,8 +9,8 @@ dynamic = ["version"]
 dependencies = [
     "gitpython>=3.1.45",
     'pyerrors>=2.11.1',
-    'datalad>=1.1.0',
-    'typer>=0.12.5'
+    "datalad>=1.1.0",
+    'typer>=0.12.5',
 ]
 description = "Python correlation library"
 authors = [
@@ -35,9 +35,16 @@ extend-select = [
   "F",
 ]
 
+[tool.mypy]
+strict = true
+implicit_reexport = false
+follow_untyped_imports = false
+ignore_missing_imports = true
+
 [dependency-groups]
 dev = [
     "mypy>=1.19.0",
+    "pandas-stubs>=2.3.3.251201",
     "pytest>=9.0.1",
     "pytest-cov>=7.0.0",
     "pytest-pretty>=1.3.0",

uv.lock

@@ -416,6 +416,7 @@ dependencies = [
 [package.dev-dependencies]
 dev = [
     { name = "mypy" },
+    { name = "pandas-stubs" },
     { name = "pytest" },
     { name = "pytest-cov" },
     { name = "pytest-pretty" },
@@ -433,6 +434,7 @@ requires-dist = [
 [package.metadata.requires-dev]
 dev = [
     { name = "mypy", specifier = ">=1.19.0" },
+    { name = "pandas-stubs", specifier = ">=2.3.3.251201" },
     { name = "pytest", specifier = ">=9.0.1" },
     { name = "pytest-cov", specifier = ">=7.0.0" },
     { name = "pytest-pretty", specifier = ">=1.3.0" },
@@ -1772,6 +1774,20 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/70/44/5191d2e4026f86a2a109053e194d3ba7a31a2d10a9c2348368c63ed4e85a/pandas-2.3.3-cp314-cp314t-musllinux_1_2_x86_64.whl", hash = "sha256:3869faf4bd07b3b66a9f462417d0ca3a9df29a9f6abd5d0d0dbab15dac7abe87", size = 13202175, upload-time = "2025-09-29T23:31:59.173Z" },
 ]
 
+[[package]]
+name = "pandas-stubs"
+version = "2.3.3.251201"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "numpy", version = "2.2.6", source = { registry = "https://pypi.org/simple" }, marker = "python_full_version < '3.11'" },
+    { name = "numpy", version = "2.3.5", source = { registry = "https://pypi.org/simple" }, marker = "python_full_version >= '3.11'" },
+    { name = "types-pytz" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/ee/a6/491b2af2cb3ee232765a73fb273a44cc1ac33b154f7745b2df2ee1dc4d01/pandas_stubs-2.3.3.251201.tar.gz", hash = "sha256:7a980f4f08cff2a6d7e4c6d6d26f4c5fcdb82a6f6531489b2f75c81567fe4536", size = 107787, upload-time = "2025-12-01T18:29:22.403Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/e2/68/78a3c253f146254b8e2c19f4a4768f272e12ef11001d9b45ec7b165db054/pandas_stubs-2.3.3.251201-py3-none-any.whl", hash = "sha256:eb5c9b6138bd8492fd74a47b09c9497341a278fcfbc8633ea4b35b230ebf4be5", size = 164638, upload-time = "2025-12-01T18:29:21.006Z" },
+]
+
 [[package]]
 name = "pathspec"
 version = "0.12.1"
@@ -2456,6 +2472,15 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/78/64/7713ffe4b5983314e9d436a90d5bd4f63b6054e2aca783a3cfc44cb95bbf/typer-0.20.0-py3-none-any.whl", hash = "sha256:5b463df6793ec1dca6213a3cf4c0f03bc6e322ac5e16e13ddd622a889489784a", size = 47028, upload-time = "2025-10-20T17:03:47.617Z" },
 ]
 
+[[package]]
+name = "types-pytz"
+version = "2025.2.0.20251108"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/40/ff/c047ddc68c803b46470a357454ef76f4acd8c1088f5cc4891cdd909bfcf6/types_pytz-2025.2.0.20251108.tar.gz", hash = "sha256:fca87917836ae843f07129567b74c1929f1870610681b4c92cb86a3df5817bdb", size = 10961, upload-time = "2025-11-08T02:55:57.001Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/e7/c1/56ef16bf5dcd255155cc736d276efa6ae0a5c26fd685e28f0412a4013c01/types_pytz-2025.2.0.20251108-py3-none-any.whl", hash = "sha256:0f1c9792cab4eb0e46c52f8845c8f77cf1e313cb3d68bf826aa867fe4717d91c", size = 10116, upload-time = "2025-11-08T02:55:56.194Z" },
+]
+
 [[package]]
 name = "typing-extensions"
 version = "4.15.0"