feat: 433 Creates a Dict from a given json List (#437)

* Creates a Dict from a given json List

* Changed wrong Type Str to str

* style: apply automatic fixes of linters

* fix: pytest failed on expected exception

* fix: file location is required

* style: apply automatic fixes of linters

* fix: assumed wrong working dir

* removed changes in .idea and added it to gitignore of package-parser

* revert changes in .idea folder

* improve code style

Co-authored-by: jofaul <jofaul@users.noreply.github.com>
Co-authored-by: Aclrian <32142988+Aclrian@users.noreply.github.com>
Co-authored-by: Aclrian <Aclrian@users.noreply.github.com>
Co-authored-by: GideonKoenig <44088734+GideonKoenig@users.noreply.github.com>

package-parser/.gitignore

@@ -30,3 +30,6 @@ out/
 
 # VSCode Settings
 .vscode/
+
+# IntelliJ/Pycharm settings
+.idea/

package-parser/package_parser/commands/generate_annotations/_generate_unused_annotations.py

@@ -0,0 +1,44 @@
+import json
+import re
+from typing import Dict, List, Tuple
+
+
+def generate_unused_annotations(in_file_path: str):
+    """
+    Returns a Dict of unused functions or classes
+
+    :param in_file_path: JSON file that contains a list of unused functions or classes
+    """
+
+    with open(in_file_path, "r", encoding="UTF-8") as in_file:
+        data = json.load(in_file)
+
+    unuseds: Dict[str, Dict[str, str]] = {}
+    for name in data:
+        formatted_name = format_name(name)
+        unuseds[formatted_name] = {"target": formatted_name}
+
+    return unuseds
+
+
+def format_name(name: str):
+    if name is None:
+        return None
+
+    parts = re.split("\\.", name)
+    newname = "sklearn/" + parts[0]
+
+    if len(parts) == 1:
+        return newname
+
+    slash = False
+    for part in parts[1:-1]:
+        if not slash and re.match("^_{0,2}[A-Z]", part):
+            slash = True
+        if slash:
+            newname += "/" + part
+        else:
+            newname += "." + part
+
+    newname += "/" + parts[-1]
+    return newname

package-parser/tests/commands/generate_annotations/test_generate_unused_annotations.py

@@ -0,0 +1,67 @@
+import pytest
+from package_parser.commands.generate_annotations._generate_unused_annotations import (
+    format_name,
+    generate_unused_annotations,
+)
+
+EXPECTED_VALUE = {
+    "sklearn/sklearn.base/_BaseEstimator/__setstate__": {
+        "target": "sklearn/sklearn.base/_BaseEstimator/__setstate__"
+    },
+    "sklearn/sklearn.base/is_regressor": {
+        "target": "sklearn/sklearn.base/is_regressor"
+    },
+    "sklearn/sklearn.cluster._agglomerative/linkage_tree": {
+        "target": "sklearn/sklearn.cluster._agglomerative/linkage_tree"
+    },
+    "sklearn/sklearn.cluster._kmeans/MiniBatchKMeans/init_size_": {
+        "target": "sklearn/sklearn.cluster._kmeans/MiniBatchKMeans/init_size_"
+    },
+}
+
+
+def test_format_underscores():
+    assert (
+        format_name("sklearn.cluster._kmeans._MiniBatchKMeans.random_state_")
+        == "sklearn/sklearn.cluster._kmeans/_MiniBatchKMeans/random_state_"
+    )
+
+
+def test_format_uppercase():
+    assert (
+        format_name("sklearn.cluster._kmeans.MiniBatchKMeans.random_state_")
+        == "sklearn/sklearn.cluster._kmeans/MiniBatchKMeans/random_state_"
+    )
+
+
+def test_format_normal():
+    assert (
+        format_name("sklearn.cluster._mean_shift.get_bin_seeds")
+        == "sklearn/sklearn.cluster._mean_shift/get_bin_seeds"
+    )
+
+
+def test_format_one_part():
+    assert format_name("test") == "sklearn/test"
+
+
+def test_format_none():
+    assert format_name(None) is None
+
+
+def test_format_empty():
+    assert format_name("") == "sklearn/"
+
+
+def test_generate():
+    assert (
+        generate_unused_annotations(
+            "tests/commands/generate_annotations/unused_functions_list.json"
+        )
+        == EXPECTED_VALUE
+    )
+
+
+def test_generate_bad_path():
+    with pytest.raises(FileNotFoundError):
+        generate_unused_annotations("aaaaaaaaaaaAAAAAAAAAAAA")

package-parser/tests/commands/generate_annotations/unused_functions_list.json

@@ -0,0 +1,6 @@
+[
+    "sklearn.base._BaseEstimator.__setstate__",
+    "sklearn.base.is_regressor",
+    "sklearn.cluster._agglomerative.linkage_tree",
+    "sklearn.cluster._kmeans.MiniBatchKMeans.init_size_"
+]