fix: display of math blocks (#421)

* refactor: minor changes

* fix: keep newlines in description

* fix: update scikit-learn data

* style: apply automatic fixes of linters

* fix: tests

* style: apply automatic fixes of linters

Co-authored-by: lars-reimann <[email protected]>

Author: lars-reimann

api-editor/client/src/features/packageData/selectionView/DocumentationText.tsx

@@ -43,8 +43,11 @@ const DocumentationText: React.FC<DocumentationTextProps> = function ({
     inputText = '',
 }) {
     const preprocessedText = inputText
+        // replace single new-lines by spaces
         .replaceAll(/(?<!\n)\n(?!\n)/gu, ' ')
+        // replace inline math elements
         .replaceAll(/:math:`([^`]*)`/gu, '$$1$')
+        // replace block math elements
         .replaceAll(/\.\. math::\s*(\S.*)\n\n/gu, '$$\n$1\n$$\n\n');
 
     const shortenedText = preprocessedText.split('\n\n')[0];

api-editor/data/scikit-learn__sklearn__1.0.1__api.json renamed to api-editor/data/scikit-learn__sklearn__1.0.2__api.json

@@ -1,6 +1,6 @@
-# library-analyzer
+# package-parser
 
-A tool to analyzer client and API code written in Python.
+A tool to analyze client and API code written in Python.
 
 ## Usage
 

package-parser/README.md

@@ -1,14 +1,22 @@
 from ._get_api import get_api
 from ._model import (
     API,
+    Action,
+    APIDependencies,
     Class,
+    Condition,
+    Dependency,
     FromImport,
     Function,
     Import,
     Module,
     Parameter,
     ParameterAndResultDocstring,
     ParameterAssignment,
+    ParameterHasValue,
+    ParameterIsIgnored,
+    ParameterIsIllegal,
+    ParameterIsNone,
     Result,
 )
 from ._package_metadata import (

package-parser/package_parser/commands/get_api/__init__.py

@@ -160,11 +160,11 @@ def __description(numpydoc: NumpyDocString) -> str:
 
         result = ""
         if has_summary:
-            result += " ".join(numpydoc["Summary"])
+            result += "\n".join(numpydoc["Summary"])
         if has_summary and has_extended_summary:
             result += "\n\n"
         if has_extended_summary:
-            result += " ".join(numpydoc["Extended Summary"])
+            result += "\n".join(numpydoc["Extended Summary"])
         return result
 
     @staticmethod

package-parser/package_parser/commands/get_api/_ast_visitor.py

@@ -167,29 +167,29 @@ def to_json(self) -> Any:
         }
 
 
+@dataclass
 class Import:
+    module_name: str
+    alias: Optional[str]
+
     @staticmethod
     def from_json(json: Any) -> Import:
         return Import(json["module"], json["alias"])
 
-    def __init__(self, module_name: str, alias: Optional[str]):
-        self.module: str = module_name
-        self.alias: Optional[str] = alias
-
     def to_json(self) -> Any:
-        return {"module": self.module, "alias": self.alias}
+        return {"module": self.module_name, "alias": self.alias}
 
 
+@dataclass
 class FromImport:
+    module_name: str
+    declaration_name: str
+    alias: Optional[str]
+
     @staticmethod
     def from_json(json: Any) -> FromImport:
         return FromImport(json["module"], json["declaration"], json["alias"])
 
-    def __init__(self, module_name: str, declaration_name: str, alias: Optional[str]):
-        self.module_name: str = module_name
-        self.declaration_name: str = declaration_name
-        self.alias: Optional[str] = alias
-
     def to_json(self) -> Any:
         return {
             "module": self.module_name,
@@ -256,7 +256,17 @@ def to_json(self) -> Any:
         }
 
 
+@dataclass
 class Function:
+    qname: str
+    decorators: list[str]
+    parameters: list[Parameter]
+    results: list[Result]
+    is_public: bool
+    description: str
+    docstring: str
+    source_code: str
+
     @staticmethod
     def from_json(json: Any) -> Function:
         return Function(
@@ -273,26 +283,6 @@ def from_json(json: Any) -> Function:
             json["source_code"],
         )
 
-    def __init__(
-        self,
-        qname: str,
-        decorators: list[str],
-        parameters: list[Parameter],
-        results: list[Result],
-        is_public: bool,
-        description: str,
-        docstring: str,
-        source_code: str,
-    ) -> None:
-        self.qname: str = qname
-        self.decorators: list[str] = decorators
-        self.parameters: list[Parameter] = parameters
-        self.results: list[Result] = results
-        self.is_public: bool = is_public
-        self.description: str = description
-        self.docstring: str = inspect.cleandoc(docstring or "")
-        self.source_code: str = source_code
-
     @property
     def name(self) -> str:
         return self.qname.split(".")[-1]
@@ -370,7 +360,7 @@ def from_docstring(cls, docstring: ParameterAndResultDocstring) -> RefinedType:
 
     def __init__(
         self,
-        ref_type: Optional[Union[UnionType, BoundaryType, EnumType, NamedType]] = None,
+        ref_type: Union[UnionType, BoundaryType, EnumType, NamedType, None] = None,
     ) -> None:
         self.ref_type = ref_type
 
@@ -423,34 +413,30 @@ class ParameterAssignment(Enum):
     NAME_ONLY = (auto(),)
 
 
+@dataclass
 class Result:
+    name: str
+    docstring: ParameterAndResultDocstring
+
     @staticmethod
     def from_json(json: Any) -> Result:
         return Result(
             json["name"], ParameterAndResultDocstring.from_json(json["docstring"])
         )
 
-    def __init__(self, name: str, docstring: ParameterAndResultDocstring) -> None:
-        self.name: str = name
-        self.docstring = docstring
-
     def to_json(self) -> Any:
         return {"name": self.name, "docstring": self.docstring.to_json()}
 
 
+@dataclass
 class ParameterAndResultDocstring:
+    type: str
+    description: str
+
     @classmethod
     def from_json(cls, json: Any):
         return cls(json["type"], json["description"])
 
-    def __init__(
-        self,
-        type_: str,
-        description: str,
-    ) -> None:
-        self.type: str = type_
-        self.description: str = description
-
     def to_json(self) -> Any:
         return {"type": self.type, "description": self.description}
 
@@ -529,10 +515,10 @@ class Dependency:
     @classmethod
     def from_json(cls, json: Any):
         return cls(
-            Parameter.from_json(["hasDependentParameter"]),
-            Parameter.from_json(["isDependingOn"]),
-            Condition.from_json(["hasCondition"]),
-            Action.from_json(["hasAction"]),
+            Parameter.from_json(json["hasDependentParameter"]),
+            Parameter.from_json(json["isDependingOn"]),
+            Condition.from_json(json["hasCondition"]),
+            Action.from_json(json["hasAction"]),
         )
 
     def to_json(self) -> Dict:

package-parser/package_parser/commands/get_api/_model.py

@@ -1,4 +1,4 @@
-# Dependency Extaction
+# Dependency Extraction
 
 ## How do we imagine a Dependency
 
@@ -16,13 +16,13 @@ Parsing a dependency subtree in an InOrder traversal, we can rebuild a sentence
 
 ### Dependency Tree Example
 
-![Alt text](../../../package_parser/commands/get_dependencies/dependency_tree_example.png "Dependency Tree Example")
+![Alt text](dependency_tree_example.png "Dependency Tree Example")
 
 
 ## Where to continue work?
 * Development of more patterns in _dependency_patterns.py, see [Dependency Parser](https://spacy.io/usage/linguistic-features#dependency-parse), [Dependency Matcher](https://spacy.io/usage/rule-based-matching#dependencymatcher)
 * Look into pattern matching over multiple sentences. Have a more theoretical understanding of the meaning of a dependency in the english language.
-* Better classification of the subclasses of Actions, Condtions. These classes are found in __../get_api/_model.py__.
+* Better classification of the subclasses of Actions, Conditions. These classes are found in __../get_api/_model.py__.
 
 ### How to continue work?
 It is currently constructed such that for each pattern, there exists a corresponding function __extract_(pattern_name)__ within the class DependencyExtractor. This is due to the assumption that different types of dependency patterns will have different structured sentences, and thus require slightly different combinations of methods to extract the wanted information.

package-parser/package_parser/commands/get_dependencies/README.md

@@ -6,7 +6,7 @@
 from spacy.tokens.doc import Doc
 from spacy.tokens.span import Span
 
-from ..get_api._model import (
+from ..get_api import (
     API,
     Action,
     APIDependencies,
@@ -61,7 +61,7 @@ def extract_action(action_token: Token, condition_token: Token) -> Action:
         if token != condition_token:
             action_tokens.extend(extract_lefts_and_rights(token))
 
-    # Remove trailing punctiation
+    # Remove trailing punctuation
     if any(p == action_tokens[-1] for p in [",", "."]):
         del action_tokens[-1]
     action_text = " ".join(action_tokens)

package-parser/package_parser/commands/get_dependencies/_get_dependency.py

@@ -5,6 +5,7 @@
     Dependency,
     Parameter,
     ParameterAndResultDocstring,
+    ParameterAssignment,
     ParameterHasValue,
     ParameterIsIgnored,
     ParameterIsIllegal,
@@ -99,18 +100,18 @@ def test_extract_dependencies_from_docstring_pattern_adverbial_clause():
         name="random_state",
         default_value=None,
         is_public=True,
-        assigned_by="NAME_ONLY",
+        assigned_by=ParameterAssignment.NAME_ONLY,
         docstring=ParameterAndResultDocstring(
-            type_="param possible types", description=param_docstring_nlp.text
+            type="param possible types", description=param_docstring_nlp.text
         ),
     )
     dependee_param = Parameter(
         name="probability",
         default_value=None,
         is_public=True,
-        assigned_by="NAME_ONLY",
+        assigned_by=ParameterAssignment.NAME_ONLY,
         docstring=ParameterAndResultDocstring(
-            type_="param possible types", description="param probability docstring"
+            type="param possible types", description="param probability docstring"
         ),
     )
     pattern_parameter_subordinating_conjunction = nlp(