sampling-mining-workflows-dsl 0.0.1__tar.gz → 0.0.4__tar.gz

{sampling_mining_workflows_dsl-0.0.1 → sampling_mining_workflows_dsl-0.0.4}/PKG-INFO

@@ -1,6 +1,6 @@
-Metadata-Version: 2.4
+Metadata-Version: 2.5
 Name: sampling-mining-workflows-dsl
-Version: 0.0.1
+Version: 0.0.4
 Summary: A python internal DSL to specify, execute and analyse mining software repositories sampling workflows.
 Author: Maïwenn Le Goasteller
 Author-email: Romain Lefeuvre <contact@romainlefeuvre.com>
@@ -87,8 +87,6 @@ PythonWorkflowDSL/
         │   └── writer/                             # Data writer implementations
         ├── exec_visualizer/                        # Execution visualization
         │   └── ...                                  # Local server and visualization tools
-        ├── github_seart/                           # GitHub SEART integration
-        │   └── ...                                  # SEART data loader and metadata
         ├── metadata/                               # Metadata system
         │   └── ...                                  # Boolean, date, string metadata types
         ├── operator/                               # Workflow operators
@@ -113,6 +111,10 @@ Recommended: install and use [`uv`](https://github.com/astral-sh/uv)
 
 1. ```uv init```
 2. ```uv pip install https://github.com/RomainLefeuvre/samplingMiningWorkflowDSL.git```   
+
+you can also use the published version on pypi
+1. ```pip install sampling-mining-workflows-dsl```
+
 ### Template Repository
 
 A complete template with examples is available at:

{sampling_mining_workflows_dsl-0.0.1 → sampling_mining_workflows_dsl-0.0.4}/README.md

@@ -70,8 +70,6 @@ PythonWorkflowDSL/
         │   └── writer/                             # Data writer implementations
         ├── exec_visualizer/                        # Execution visualization
         │   └── ...                                  # Local server and visualization tools
-        ├── github_seart/                           # GitHub SEART integration
-        │   └── ...                                  # SEART data loader and metadata
         ├── metadata/                               # Metadata system
         │   └── ...                                  # Boolean, date, string metadata types
         ├── operator/                               # Workflow operators
@@ -96,6 +94,10 @@ Recommended: install and use [`uv`](https://github.com/astral-sh/uv)
 
 1. ```uv init```
 2. ```uv pip install https://github.com/RomainLefeuvre/samplingMiningWorkflowDSL.git```   
+
+you can also use the published version on pypi
+1. ```pip install sampling-mining-workflows-dsl```
+
 ### Template Repository
 
 A complete template with examples is available at:

{sampling_mining_workflows_dsl-0.0.1 → sampling_mining_workflows_dsl-0.0.4}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "hatchling.build"
 
 [project]
 name = "sampling-mining-workflows-dsl"
-version = "0.0.1"
+version = "0.0.4"
 description = "A python internal DSL to specify, execute and analyse mining software repositories sampling workflows."
 readme = "README.md"
 requires-python = ">=3.13"

sampling_mining_workflows_dsl-0.0.4/src/sampling_mining_workflows_dsl/element/Loader.py

@@ -0,0 +1,42 @@
+from abc import ABC, abstractmethod
+from typing import TYPE_CHECKING, Any
+
+from sampling_mining_workflows_dsl.element.Set import Set
+from sampling_mining_workflows_dsl.metadata.Metadata import Metadata
+from sampling_mining_workflows_dsl.element.Repository import Repository
+
+if TYPE_CHECKING:
+    from sampling_mining_workflows_dsl.metadata.MetadataValue import MetadataValue
+
+class Loader(ABC):
+    def __init__(self, *metadatas: Metadata | None):
+        # Assuming the first metadata is the ID, store its name for further use
+        self.metadata_id_name = metadatas[0].name
+        self.metadatas: dict[str, Metadata] = {}
+        for metadata in metadatas:
+            self.metadatas[metadata.name] = metadata
+
+    @abstractmethod
+    def load_set(self) -> Set:
+        pass
+
+    def create_repository_from_map(self, map_object: dict[str, Any]) -> Repository:
+        id_metadata_value = map_object.get(self.metadata_id_name)
+
+        if id_metadata_value is None or id_metadata_value == "":
+            raise ValueError(f"Invalid ID {self.metadata_id_name}")
+
+        repo = Repository(self.metadatas.get(self.metadata_id_name))
+
+        metadata_values: list[MetadataValue] = []
+        for metadata in self.metadatas.values():
+            try:
+                metadata_value = metadata.create_metadata_value(map_object.get(metadata.name))
+                metadata_values.append(metadata_value)
+            except Exception as e:
+                raise ValueError(
+                    f"Error creating metadata value for '{metadata.name}' with value '{map_object.get(metadata.name)}'",
+                ) from e
+
+        repo.add_metadata_values(metadata_values)
+        return repo

{sampling_mining_workflows_dsl-0.0.1 → sampling_mining_workflows_dsl-0.0.4}/src/sampling_mining_workflows_dsl/element/loader/CsvLoader.py

@@ -45,23 +45,3 @@ class CsvLoader(Loader):
         except OSError as e:
             raise RuntimeError("Error reading the CSV file", e) from e
 
-    def create_repository_from_map(self, csv_row: dict[str, Any]) -> Repository:
-        id_metadata_value = csv_row.get(self.metadata_id_name)
-
-        if id_metadata_value is None or id_metadata_value == "":
-            raise ValueError(f"Invalid ID {self.metadata_id_name}")
-
-        repo = Repository(self.metadatas.get(self.metadata_id_name))
-
-        metadata_values: list[MetadataValue] = []
-        for metadata in self.metadatas.values():
-            try:
-                metadata_value = metadata.create_metadata_value(csv_row.get(metadata.name))
-                metadata_values.append(metadata_value)
-            except Exception as e:
-                raise ValueError(
-                    f"Error creating metadata value for '{metadata.name}' with value '{csv_row.get(metadata.name)}'",
-                ) from e
-
-        repo.add_metadata_values(metadata_values)
-        return repo

{sampling_mining_workflows_dsl-0.0.1 → sampling_mining_workflows_dsl-0.0.4}/src/sampling_mining_workflows_dsl/element/loader/JsonLoader.py

@@ -45,27 +45,6 @@ class JsonLoader(Loader):
         except OSError as e:
             raise RuntimeError("Error reading the JSON file", e) from e
 
-    def create_repository_from_map(self, json_object: dict[str, Any]) -> Repository:
-        id_metadata_value = json_object.get(self.metadata_id_name)
-
-        if id_metadata_value is None or id_metadata_value == "":
-            raise ValueError(f"Invalid ID {self.metadata_id_name}")
-
-        repo = Repository(self.metadatas.get(self.metadata_id_name))
-
-        metadata_values: list[MetadataValue] = []
-        for metadata in self.metadatas.values():
-            try:
-                metadata_value = metadata.create_metadata_value(json_object.get(metadata.name))
-                metadata_values.append(metadata_value)
-            except Exception as e:
-                raise ValueError(
-                    f"Error creating metadata value for '{metadata.name}' with value '{json_object.get(metadata.name)}'",
-                ) from e
-
-        repo.add_metadata_values(metadata_values)
-        return repo
-
     @staticmethod
     def parse_args(args: list[str]) -> dict[str, str]:
         import argparse

{sampling_mining_workflows_dsl-0.0.1 → sampling_mining_workflows_dsl-0.0.4}/src/sampling_mining_workflows_dsl/element/writer/WriterFactory.py

@@ -1,7 +1,7 @@
 from sampling_mining_workflows_dsl.element.writer.JsonWriter import JsonWriter
 
 
-class WritterFactory:
+class WriterFactory:
     @staticmethod
     def json_writer(path: str):
         return JsonWriter(path)

{sampling_mining_workflows_dsl-0.0.1 → sampling_mining_workflows_dsl-0.0.4}/src/sampling_mining_workflows_dsl/exec_visualizer/WorkflowVisualizer.py

@@ -1,4 +1,5 @@
 import os
+import re
 from typing import cast
 
 from graphviz import Digraph
@@ -11,9 +12,10 @@ from sampling_mining_workflows_dsl.operator.selection.filter.FilterOperator impo
 
 
 class WorkflowVisualizer:
-    def __init__(self, workflow,output_dir: str = "output_workflow_graph"):
+    def __init__(self, workflow, output_dir: str = "output_workflow_graph", wrap_constraint_operators: bool = False):
         self.workflow = workflow
         self.global_set_counter = 0  # Global counter shared across all levels
+        self.wrap_constraint_operators = wrap_constraint_operators
         if output_dir:
             self.output_dir = output_dir
             os.makedirs(self.output_dir, exist_ok=True)
@@ -51,8 +53,10 @@ class WorkflowVisualizer:
             dot.edge(node, "OutputSet")
 
         # Render
-        dot.render(svg_path, format="svg", cleanup=True)
+        dot_path = dot.save(f"{svg_path}.dot")
+        dot.render(svg_path, format="svg", cleanup=False)
         print(f"Workflow graph saved to {svg_path}")
+        print(f"Editable Graphviz source saved to {dot_path}")
 
         # HTML wrapper
         self.create_html_page(svg_path)
@@ -86,6 +90,8 @@ class WorkflowVisualizer:
                     constraint = cast(
                         "BoolConstraintString", op.get_constraint()
                     ).get_string_constraint()
+                    if self.wrap_constraint_operators:
+                        constraint = re.sub(r'\s+(and|or)\s+', r'\n\1 ', constraint, flags=re.IGNORECASE)
                     formatted_size = f"{output_set.flatten_set().size():,}".replace(',', ' ')
                     label = f"Filter Operator\n{constraint}\n\nSET#{self.global_set_counter}\n Size : {formatted_size}"
                 elif isinstance(op.get_constraint(), BoolConstraint):

{sampling_mining_workflows_dsl-0.0.1 → sampling_mining_workflows_dsl-0.0.4}/src/sampling_mining_workflows_dsl/operator/Operator.py

@@ -16,7 +16,7 @@ class Operator(ABC):
         self.workflow = worflow
         self._input: Set | None = None
         self._output: Set | None = None
-        self._output_writter: Writer | None = None
+        self._output_writer: Writer | None = None
         self._next_operator: Operator | None = None
         self._previous_operator: Operator | None = None
         # Loader to add metadata on output during the execution
@@ -68,8 +68,8 @@ class Operator(ABC):
         if self._next_operator:
             self._next_operator._input = self._output
             self._next_operator.execute()
-        elif self._output_writter:
-            self._output_writter.write_set(self._output)
+        elif self._output_writer:
+            self._output_writer.write_set(self._output)
         return self
 
     def get_workflow_root_operator(self) -> "Operator":
@@ -99,8 +99,8 @@ class Operator(ABC):
                 result.add_element(element)
         return result
 
-    def output(self, writter: Writer) -> "Operator":
-        self._output_writter = writter
+    def output(self, writer: Writer) -> "Operator":
+        self._output_writer = writer
         return self
 
     def input_set(self, input_set: Set) -> "Operator":

{sampling_mining_workflows_dsl-0.0.1 → sampling_mining_workflows_dsl-0.0.4}/src/sampling_mining_workflows_dsl/test/Workflow_simple.py

@@ -1,5 +1,5 @@
 from sampling_mining_workflows_dsl.element.loader.LoaderFactory import LoaderFactory
-from sampling_mining_workflows_dsl.element.writer.WriterFactory import WritterFactory
+from sampling_mining_workflows_dsl.element.writer.WriterFactory import WriterFactory
 from sampling_mining_workflows_dsl.exec_visualizer.WorkflowVisualizer import WorkflowVisualizer
 from sampling_mining_workflows_dsl.metadata.Metadata import Metadata
 from sampling_mining_workflows_dsl.operator.clustering.SubWorkflowOperatorBuilder import (
@@ -8,7 +8,7 @@ from sampling_mining_workflows_dsl.operator.clustering.SubWorkflowOperatorBuilde
 from sampling_mining_workflows_dsl.WorkflowBuilder import WorkflowBuilder
 
 json_loader = LoaderFactory.json_loader
-json_writer = WritterFactory.json_writer
+json_writer = WriterFactory.json_writer
 filter_operator = SubWorkflowOperatorBuilder.filter_operator
 
 

sampling_mining_workflows_dsl-0.0.1/src/sampling_mining_workflows_dsl/element/Loader.py

@@ -1,17 +0,0 @@
-from abc import ABC, abstractmethod
-
-from sampling_mining_workflows_dsl.element import Set
-from sampling_mining_workflows_dsl.metadata.Metadata import Metadata
-
-
-class Loader(ABC):
-    def __init__(self, *metadatas: Metadata | None):
-        # Assuming the first metadata is the ID, store its name for further use
-        self.metadata_id_name = metadatas[0].name
-        self.metadatas: dict[str, Metadata] = {}
-        for metadata in metadatas:
-            self.metadatas[metadata.name] = metadata
-
-    @abstractmethod
-    def load_set(self) -> Set:
-        pass

sampling_mining_workflows_dsl-0.0.1/src/sampling_mining_workflows_dsl/github_seart/loader.py

@@ -1,17 +0,0 @@
-from pathlib import Path
-from typing import TYPE_CHECKING, Any
-
-from sampling_mining_workflows_dsl.element.loader.CsvLoader import CsvLoader
-from sampling_mining_workflows_dsl.element.Repository import Repository
-from sampling_mining_workflows_dsl.element.Set import Set
-from sampling_mining_workflows_dsl.github_seart.metadata import all_metadatas
-
-if TYPE_CHECKING:
-    from sampling_mining_workflows_dsl.metadata.MetadataValue import MetadataValue
-
-class SEARTGithubLoader(CsvLoader):
-    def __init__(self, set_path: Path):
-        super().__init__(*all_metadatas)
-        self.set_path = set_path
-        self.set = Set()
-

sampling_mining_workflows_dsl-0.0.1/src/sampling_mining_workflows_dsl/github_seart/metadata.py

@@ -1,106 +0,0 @@
-
-import json
-from typing import TypedDict
-
-from sampling_mining_workflows_dsl.metadata.Metadata import Metadata
-from sampling_mining_workflows_dsl.metadata.MetadataValue import MetadataValue
-
-
-class LanguageMetrics(TypedDict):
-    commentLines: int
-    codeLines: int
-    blankLines: int
-
-class MetadataMetrics(Metadata[dict[str, LanguageMetrics]]):
-    def __init__(self, name: str):
-        super().__init__(name, dict[str, LanguageMetrics])
-
-    def create_metadata_value(self, value):
-        # the raw value is list[dict[str, str|int]], convert it to dict[str, LanguageMetrics]
-        typed_value = {}
-        for item in json.loads(value):
-            lang = item["language"]
-            metrics = LanguageMetrics(
-                commentLines=item.get("commentLines", 0),
-                codeLines=item.get("codeLines", 0),
-                blankLines=item.get("blankLines", 0),
-            )
-            typed_value[lang] = metrics
-
-        return MetadataValue(self, typed_value)
-
-
-
-id = Metadata.of_string("id")
-name = Metadata.of_string("name")
-isFork = Metadata.of_boolean("isFork")
-commits = Metadata.of_integer("commits")
-branches = Metadata.of_integer("branches")
-releases = Metadata.of_integer("releases")
-forks = Metadata.of_integer("forks")
-mainLanguage = Metadata.of_string("mainLanguage")
-defaultBranch = Metadata.of_string("defaultBranch")
-license = Metadata.of_string("license")
-homepage = Metadata.of_string("homepage")
-watchers = Metadata.of_integer("watchers")
-stargazers = Metadata.of_integer("stargazers")
-contributors = Metadata.of_integer("contributors")
-size = Metadata.of_integer("size")
-createdAt = Metadata.of_date("createdAt")
-pushedAt = Metadata.of_date("pushedAt")
-updatedAt = Metadata.of_date("updatedAt")
-totalIssues = Metadata.of_integer("totalIssues")
-openIssues = Metadata.of_integer("openIssues")
-totalPullRequests = Metadata.of_integer("totalPullRequests")
-openPullRequests = Metadata.of_integer("openPullRequests")
-blankLines = Metadata.of_integer("blankLines")
-codeLines = Metadata.of_integer("codeLines")
-commentLines = Metadata.of_integer("commentLines")
-metrics = MetadataMetrics("metrics")
-lastCommit = Metadata.of_date("lastCommit")
-lastCommitSHA = Metadata.of_string("lastCommitSHA")
-hasWiki = Metadata.of_boolean("hasWiki")
-isArchived = Metadata.of_boolean("isArchived")
-isDisabled = Metadata.of_boolean("isDisabled")
-isLocked = Metadata.of_boolean("isLocked")
-languages = Metadata.of_dict("languages", str, int, lambda s: json.loads(s) if s else {})
-labels = Metadata.of_list("labels", list[str], lambda s: s.split(";") if s else [])
-topics = Metadata.of_list("topics", list[str], lambda s: s.split(";") if s else [])
-
-all_metadatas = [
-    id,
-    name,
-    isFork,
-    commits,
-    branches,
-    releases,
-    forks,
-    mainLanguage,
-    defaultBranch,
-    license,
-    homepage,
-    watchers,
-    stargazers,
-    contributors,
-    size,
-    createdAt,
-    pushedAt,
-    updatedAt,
-    totalIssues,
-    openIssues,
-    totalPullRequests,
-    openPullRequests,
-    blankLines,
-    codeLines,
-    commentLines,
-    metrics,
-    lastCommit,
-    lastCommitSHA,
-    hasWiki,
-    isArchived,
-    isDisabled,
-    isLocked,
-    languages,
-    labels,
-    topics
-]