janus-llm 3.2.0__tar.gz → 3.2.1__tar.gz

{janus_llm-3.2.0 → janus_llm-3.2.1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: janus-llm
-Version: 3.2.0
+Version: 3.2.1
 Summary: A transcoding library using LLMs.
 Home-page: https://github.com/janus-llm/janus-llm
 License: Apache 2.0

{janus_llm-3.2.0 → janus_llm-3.2.1}/janus/__init__.py

@@ -2,10 +2,10 @@ import warnings
 
 from langchain_core._api.deprecation import LangChainDeprecationWarning
 
-from .converter.translate import Translator
-from .metrics import *  # noqa: F403
+from janus.converter.translate import Translator
+from janus.metrics import *  # noqa: F403
 
-__version__ = "3.2.0"
+__version__ = "3.2.1"
 
 # Ignoring a deprecation warning from langchain_core that I can't seem to hunt down
 warnings.filterwarnings("ignore", category=LangChainDeprecationWarning)

{janus_llm-3.2.0 → janus_llm-3.2.1}/janus/_tests/test_cli.py

@@ -4,9 +4,9 @@ from unittest.mock import ANY, patch
 
 from typer.testing import CliRunner
 
-from ..cli import app, translate
-from ..embedding.embedding_models_info import EMBEDDING_MODEL_CONFIG_DIR
-from ..llm.models_info import MODEL_CONFIG_DIR
+from janus.cli import app, translate
+from janus.embedding.embedding_models_info import EMBEDDING_MODEL_CONFIG_DIR
+from janus.llm.models_info import MODEL_CONFIG_DIR
 
 
 class TestCli(unittest.TestCase):

{janus_llm-3.2.0 → janus_llm-3.2.1}/janus/cli.py

@@ -108,7 +108,7 @@ embedding = typer.Typer(
 
 def version_callback(value: bool) -> None:
     if value:
-        from . import __version__ as version
+        from janus import __version__ as version
 
         print(f"Janus CLI [blue]v{version}[/blue]")
         raise typer.Exit()

janus_llm-3.2.1/janus/converter/__init__.py

@@ -0,0 +1,6 @@
+from janus.converter.converter import Converter
+from janus.converter.diagram import DiagramGenerator
+from janus.converter.document import Documenter, MadLibsDocumenter, MultiDocumenter
+from janus.converter.evaluate import Evaluator
+from janus.converter.requirements import RequirementsDocumenter
+from janus.converter.translate import Translator

janus_llm-3.2.1/janus/converter/_tests/test_translate.py

@@ -0,0 +1,155 @@
+import unittest
+from pathlib import Path
+from typing import Any, Iterable, List, Optional, Type
+
+import pytest
+from langchain.schema import Document
+from langchain.schema.embeddings import Embeddings
+from langchain.schema.vectorstore import VST, VectorStore
+
+from janus.converter.diagram import DiagramGenerator
+from janus.converter.requirements import RequirementsDocumenter
+from janus.converter.translate import Translator
+from janus.language.block import CodeBlock, TranslatedCodeBlock
+
+
+class MockCollection(VectorStore):
+    """Vector store for testing"""
+
+    def __init__(self):
+        self._add_texts_calls = 0
+
+    def add_texts(
+        self, texts: Iterable[str], metadatas: Optional[List[dict]] = None, **kwargs: Any
+    ) -> List[str]:
+        self._add_texts_calls += 1
+        return ["id"]
+
+    def similarity_search(self, query: str, k: int = 4, **kwargs: Any) -> List[Document]:
+        raise NotImplementedError("similarity_search() not implemented!")
+
+    @classmethod
+    def from_texts(
+        cls: Type[VST],
+        texts: List[str],
+        embedding: Embeddings,
+        metadatas: Optional[List[dict]] = None,
+        **kwargs: Any,
+    ) -> VST:
+        raise NotImplementedError("from_texts() not implemented!")
+
+
+class TestTranslator(unittest.TestCase):
+    """Tests for the Translator class."""
+
+    def setUp(self):
+        """Set up the tests."""
+        self.translator = Translator(
+            model="gpt-4o",
+            source_language="fortran",
+            target_language="python",
+            target_version="3.10",
+        )
+        self.test_file = Path("janus/language/treesitter/_tests/languages/fortran.f90")
+        self.TEST_FILE_EMBEDDING_COUNT = 14
+
+        self.req_translator = RequirementsDocumenter(
+            model="gpt-4o",
+            source_language="fortran",
+            prompt_template="requirements",
+        )
+
+    @pytest.mark.translate
+    def test_translate(self):
+        """Test translate method."""
+        # Delete a file if it's already there
+        python_file = self.test_file.parent / "python" / f"{self.test_file.stem}.py"
+        python_file.unlink(missing_ok=True)
+        python_file.parent.rmdir() if python_file.parent.is_dir() else None
+        self.translator.translate(self.test_file.parent, self.test_file.parent / "python")
+        # Only check the top-most level functionality, since it should be handled by other
+        # unit tests anyway
+        self.assertTrue(python_file.exists())
+
+    def test_invalid_selections(self) -> None:
+        """Tests that settings values for the translator will raise exceptions"""
+        self.assertRaises(
+            ValueError, self.translator.set_target_language, "gobbledy", "goobledy"
+        )
+        self.assertRaises(
+            ValueError, self.translator.set_source_language, "scribbledy-doop"
+        )
+        self.translator.set_prompt("pish posh")
+        self.assertRaises(ValueError, self.translator._load_parameters)
+
+
+class TestDiagramGenerator(unittest.TestCase):
+    """Tests for the DiagramGenerator class."""
+
+    def setUp(self):
+        """Set up the tests."""
+        self.diagram_generator = DiagramGenerator(
+            model="gpt-4o",
+            source_language="fortran",
+            diagram_type="Activity",
+        )
+
+    def test_init(self):
+        """Test __init__ method."""
+        self.assertEqual(self.diagram_generator._model_name, "gpt-4o")
+        self.assertEqual(self.diagram_generator._source_language, "fortran")
+        self.assertEqual(self.diagram_generator._diagram_type, "Activity")
+
+    def test_add_translation(self):
+        """Test _add_translation method."""
+        block = TranslatedCodeBlock(
+            original=CodeBlock(
+                id="test",
+                name="Test Block",
+                node_type="function",
+                language="python",
+                text="print('Hello, World!')",
+                start_point=(0, 0),
+                end_point=(1, 0),
+                start_byte=0,
+                end_byte=1,
+                tokens=5,
+                children=[],
+            ),
+            language="python",
+        )
+        self.diagram_generator._add_translation(block)
+        self.assertTrue(block.translated)
+        self.assertIsNotNone(block.text)
+        self.assertIsNotNone(block.tokens)
+
+
+@pytest.mark.parametrize(
+    "source_language,prompt_template,expected_target_language,expected_target_version,",
+    [
+        ("python", "document_inline", "python", "3.10"),
+        ("fortran", "document", "text", None),
+        ("mumps", "requirements", "text", None),
+        ("python", "simple", "javascript", "es6"),
+    ],
+)
+def test_language_combinations(
+    source_language: str,
+    prompt_template: str,
+    expected_target_language: str,
+    expected_target_version: str,
+):
+    """Tests that translator target language settings are consistent
+    with prompt template expectations.
+    """
+    translator = Translator(model="gpt-4o")
+    translator.set_model("gpt-4o")
+    translator.set_source_language(source_language)
+    translator.set_target_language(expected_target_language, expected_target_version)
+    translator.set_prompt(prompt_template)
+    translator._load_parameters()
+    assert translator._target_language == expected_target_language  # nosec
+    assert translator._target_version == expected_target_version  # nosec
+    assert translator._splitter.language == source_language  # nosec
+    assert translator._splitter.model.model_name == "gpt-4o"  # nosec
+    assert translator._prompt_template_name == prompt_template  # nosec

{janus_llm-3.2.0 → janus_llm-3.2.1}/janus/embedding/_tests/test_collections.py

@@ -4,8 +4,8 @@ from unittest.mock import MagicMock
 
 import pytest
 
-from ...utils.enums import EmbeddingType
-from ..collections import Collections
+from janus.embedding.collections import Collections
+from janus.utils.enums import EmbeddingType
 
 
 class TestCollections(unittest.TestCase):

{janus_llm-3.2.0 → janus_llm-3.2.1}/janus/embedding/_tests/test_database.py

@@ -2,7 +2,7 @@ import unittest
 from pathlib import Path
 from unittest.mock import patch
 
-from ..database import ChromaEmbeddingDatabase, uri_to_path
+from janus.embedding.database import ChromaEmbeddingDatabase, uri_to_path
 
 
 class TestDatabase(unittest.TestCase):

{janus_llm-3.2.0 → janus_llm-3.2.1}/janus/embedding/_tests/test_vectorize.py

@@ -5,9 +5,9 @@ from unittest.mock import MagicMock
 
 from chromadb.api.client import Client
 
-from ...language.treesitter import TreeSitterSplitter
-from ...utils.enums import EmbeddingType
-from ..vectorize import Vectorizer, VectorizerFactory
+from janus.embedding.vectorize import Vectorizer, VectorizerFactory
+from janus.language.treesitter import TreeSitterSplitter
+from janus.utils.enums import EmbeddingType
 
 
 class MockDBVectorizer(VectorizerFactory):

{janus_llm-3.2.0 → janus_llm-3.2.1}/janus/embedding/collections.py

@@ -5,8 +5,8 @@ from typing import Dict, Optional, Sequence
 from chromadb import Client, Collection
 from langchain_community.vectorstores import Chroma
 
-from ..utils.enums import EmbeddingType
-from .embedding_models_info import load_embedding_model
+from janus.embedding.embedding_models_info import load_embedding_model
+from janus.utils.enums import EmbeddingType
 
 # See https://docs.trychroma.com/telemetry#in-chromas-backend-using-environment-variables
 os.environ["ANONYMIZED_TELEMETRY"] = "False"

{janus_llm-3.2.0 → janus_llm-3.2.1}/janus/embedding/database.py

@@ -5,7 +5,7 @@ from urllib.request import url2pathname
 
 import chromadb
 
-from ..utils.logger import create_logger
+from janus.utils.logger import create_logger
 
 log = create_logger(__name__)
 

{janus_llm-3.2.0 → janus_llm-3.2.1}/janus/embedding/embedding_models_info.py

@@ -8,7 +8,7 @@ from langchain_community.embeddings.huggingface import HuggingFaceInferenceAPIEm
 from langchain_core.embeddings import Embeddings
 from langchain_openai import OpenAIEmbeddings
 
-from ..utils.logger import create_logger
+from janus.utils.logger import create_logger
 
 load_dotenv()
 

{janus_llm-3.2.0 → janus_llm-3.2.1}/janus/embedding/vectorize.py

@@ -6,10 +6,10 @@ from typing import Any, Dict, Optional, Sequence
 from chromadb import Client, Collection
 from langchain_community.vectorstores import Chroma
 
-from ..language.block import CodeBlock, TranslatedCodeBlock
-from ..utils.enums import EmbeddingType
-from .collections import Collections
-from .database import ChromaEmbeddingDatabase
+from janus.embedding.collections import Collections
+from janus.embedding.database import ChromaEmbeddingDatabase
+from janus.language.block import CodeBlock, TranslatedCodeBlock
+from janus.utils.enums import EmbeddingType
 
 
 class Vectorizer(object):
@@ -59,7 +59,7 @@ class Vectorizer(object):
         self,
         code_block: CodeBlock,
         collection_name: EmbeddingType | str,
-        filename: str  # perhaps this should be a relative path from the source, but for
+        filename: str,  # perhaps this should be a relative path from the source, but for
         # now we're all in 1 directory
     ) -> None:
         """Calculate `code_block` embedding, returning success & storing in `embedding_id`

{janus_llm-3.2.0 → janus_llm-3.2.1}/janus/language/_tests/test_combine.py

@@ -1,6 +1,6 @@
 import unittest
 
-from ..combine import CodeBlock, Combiner, TranslatedCodeBlock
+from janus.language.combine import CodeBlock, Combiner, TranslatedCodeBlock
 
 
 class TestCombiner(unittest.TestCase):

{janus_llm-3.2.0 → janus_llm-3.2.1}/janus/language/_tests/test_splitter.py

@@ -1,6 +1,6 @@
 import unittest
 
-from ..splitter import Splitter
+from janus.language.splitter import Splitter
 
 
 class TestSplitter(unittest.TestCase):

{janus_llm-3.2.0 → janus_llm-3.2.1}/janus/language/alc/_tests/test_alc.py

@@ -1,9 +1,9 @@
 import unittest
 from pathlib import Path
 
-from ....llm import load_model
-from ...combine import Combiner
-from ..alc import AlcSplitter
+from janus.language.alc import AlcSplitter
+from janus.language.combine import Combiner
+from janus.llm import load_model
 
 
 class TestAlcSplitter(unittest.TestCase):

{janus_llm-3.2.0 → janus_llm-3.2.1}/janus/language/alc/alc.py

@@ -1,10 +1,10 @@
 from langchain.schema.language_model import BaseLanguageModel
 
-from ...utils.logger import create_logger
-from ..block import CodeBlock
-from ..combine import Combiner
-from ..node import NodeType
-from ..treesitter import TreeSitterSplitter
+from janus.language.block import CodeBlock
+from janus.language.combine import Combiner
+from janus.language.node import NodeType
+from janus.language.treesitter import TreeSitterSplitter
+from janus.utils.logger import create_logger
 
 log = create_logger(__name__)
 

{janus_llm-3.2.0 → janus_llm-3.2.1}/janus/language/binary/_tests/test_binary.py

@@ -5,8 +5,8 @@ from unittest.mock import patch
 
 import pytest
 
-from ....llm import load_model
-from ..binary import BinarySplitter
+from janus.language.binary import BinarySplitter
+from janus.llm import load_model
 
 
 class TestBinarySplitter(unittest.TestCase):

{janus_llm-3.2.0 → janus_llm-3.2.1}/janus/language/binary/binary.py

@@ -7,11 +7,11 @@ from pathlib import Path
 import tree_sitter
 from langchain.schema.language_model import BaseLanguageModel
 
-from ...utils.enums import LANGUAGES
-from ...utils.logger import create_logger
-from ..block import CodeBlock
-from ..combine import Combiner
-from ..treesitter import TreeSitterSplitter
+from janus.language.block import CodeBlock
+from janus.language.combine import Combiner
+from janus.language.treesitter import TreeSitterSplitter
+from janus.utils.enums import LANGUAGES
+from janus.utils.logger import create_logger
 
 log = create_logger(__name__)
 

{janus_llm-3.2.0 → janus_llm-3.2.1}/janus/language/block.py

@@ -1,8 +1,8 @@
 from functools import total_ordering
 from typing import ForwardRef, Hashable, Optional, Tuple
 
-from ..utils.logger import create_logger
-from .node import NodeType
+from janus.language.node import NodeType
+from janus.utils.logger import create_logger
 
 log = create_logger(__name__)
 

{janus_llm-3.2.0 → janus_llm-3.2.1}/janus/language/combine.py

@@ -1,6 +1,6 @@
-from ..utils.logger import create_logger
-from .block import CodeBlock, TranslatedCodeBlock
-from .file import FileManager
+from janus.language.block import CodeBlock, TranslatedCodeBlock
+from janus.language.file import FileManager
+from janus.utils.logger import create_logger
 
 log = create_logger(__name__)
 

{janus_llm-3.2.0 → janus_llm-3.2.1}/janus/language/file.py

@@ -1,5 +1,5 @@
-from ..utils.enums import LANGUAGES
-from ..utils.logger import create_logger
+from janus.utils.enums import LANGUAGES
+from janus.utils.logger import create_logger
 
 log = create_logger(__name__)
 

{janus_llm-3.2.0 → janus_llm-3.2.1}/janus/language/mumps/_tests/test_mumps.py

@@ -1,9 +1,9 @@
 import unittest
 from pathlib import Path
 
-from ....llm import load_model
-from ...combine import Combiner
-from ..mumps import MumpsSplitter
+from janus.language.combine import Combiner
+from janus.language.mumps import MumpsSplitter
+from janus.llm import load_model
 
 
 class TestMumpsSplitter(unittest.TestCase):

{janus_llm-3.2.0 → janus_llm-3.2.1}/janus/language/mumps/mumps.py

@@ -2,11 +2,11 @@ import re
 
 from langchain.schema.language_model import BaseLanguageModel
 
-from ...utils.logger import create_logger
-from ..block import CodeBlock
-from ..combine import Combiner
-from ..node import NodeType
-from ..splitter import Splitter
+from janus.language.block import CodeBlock
+from janus.language.combine import Combiner
+from janus.language.node import NodeType
+from janus.language.splitter import Splitter
+from janus.utils.logger import create_logger
 
 log = create_logger(__name__)
 

{janus_llm-3.2.0 → janus_llm-3.2.1}/janus/language/mumps/patterns.py

@@ -1,7 +1,7 @@
 import re
 from dataclasses import dataclass
 
-from ...utils.logger import create_logger
+from janus.utils.logger import create_logger
 
 log = create_logger(__name__)
 

janus_llm-3.2.1/janus/language/naive/__init__.py

@@ -0,0 +1,4 @@
+from janus.language.naive.basic_splitter import FileSplitter
+from janus.language.naive.chunk_splitter import ChunkSplitter
+from janus.language.naive.simple_ast import get_flexible_ast, get_strict_ast
+from janus.language.naive.tag_splitter import TagSplitter

{janus_llm-3.2.0 → janus_llm-3.2.1}/janus/language/naive/basic_splitter.py

@@ -1,7 +1,7 @@
-from ..block import CodeBlock
-from ..naive.chunk_splitter import ChunkSplitter
-from ..naive.registry import register_splitter
-from ..splitter import FileSizeError
+from janus.language.block import CodeBlock
+from janus.language.naive.chunk_splitter import ChunkSplitter
+from janus.language.naive.registry import register_splitter
+from janus.language.splitter import FileSizeError
 
 
 @register_splitter("file")

{janus_llm-3.2.0 → janus_llm-3.2.1}/janus/language/naive/chunk_splitter.py

@@ -1,7 +1,7 @@
-from ..block import CodeBlock
-from ..node import NodeType
-from ..splitter import Splitter
-from .registry import register_splitter
+from janus.language.block import CodeBlock
+from janus.language.naive.registry import register_splitter
+from janus.language.node import NodeType
+from janus.language.splitter import Splitter
 
 
 @register_splitter("chunk")

{janus_llm-3.2.0 → janus_llm-3.2.1}/janus/language/naive/registry.py

@@ -1,6 +1,6 @@
 from typing import Callable, Dict
 
-from ..splitter import Splitter
+from janus.language.splitter import Splitter
 
 CUSTOM_SPLITTERS: Dict[str, Callable[..., Splitter]] = dict()
 

{janus_llm-3.2.0 → janus_llm-3.2.1}/janus/language/naive/simple_ast.py

@@ -1,8 +1,8 @@
-from ...utils.enums import LANGUAGES
-from ..alc.alc import AlcSplitter
-from ..mumps.mumps import MumpsSplitter
-from ..treesitter import TreeSitterSplitter
-from .registry import register_splitter
+from janus.language.alc.alc import AlcSplitter
+from janus.language.mumps.mumps import MumpsSplitter
+from janus.language.naive.registry import register_splitter
+from janus.language.treesitter import TreeSitterSplitter
+from janus.utils.enums import LANGUAGES
 
 
 @register_splitter("ast-flex")

{janus_llm-3.2.0 → janus_llm-3.2.1}/janus/language/naive/tag_splitter.py

@@ -1,7 +1,7 @@
-from ..block import CodeBlock
-from ..node import NodeType
-from ..splitter import Splitter
-from .registry import register_splitter
+from janus.language.block import CodeBlock
+from janus.language.naive.registry import register_splitter
+from janus.language.node import NodeType
+from janus.language.splitter import Splitter
 
 
 @register_splitter("tag")

{janus_llm-3.2.0 → janus_llm-3.2.1}/janus/language/node.py

@@ -1,6 +1,6 @@
 from typing import NewType, Tuple
 
-from ..utils.logger import create_logger
+from janus.utils.logger import create_logger
 
 log = create_logger(__name__)
 

{janus_llm-3.2.0 → janus_llm-3.2.1}/janus/language/splitter.py

@@ -6,10 +6,10 @@ from typing import List
 import tiktoken
 from langchain.schema.language_model import BaseLanguageModel
 
-from ..utils.logger import create_logger
-from .block import CodeBlock
-from .file import FileManager
-from .node import NodeType
+from janus.language.block import CodeBlock
+from janus.language.file import FileManager
+from janus.language.node import NodeType
+from janus.utils.logger import create_logger
 
 log = create_logger(__name__)
 

{janus_llm-3.2.0 → janus_llm-3.2.1}/janus/language/treesitter/_tests/test_treesitter.py

@@ -1,9 +1,9 @@
 import unittest
 from pathlib import Path
 
-from ....llm import load_model
-from ...combine import Combiner
-from ..treesitter import TreeSitterSplitter
+from janus.language.combine import Combiner
+from janus.language.treesitter import TreeSitterSplitter
+from janus.llm import load_model
 
 
 class TestTreeSitterSplitter(unittest.TestCase):

{janus_llm-3.2.0 → janus_llm-3.2.1}/janus/language/treesitter/treesitter.py

@@ -9,10 +9,10 @@ import tree_sitter
 from git import Repo
 from langchain.schema.language_model import BaseLanguageModel
 
-from ...utils.enums import LANGUAGES
-from ...utils.logger import create_logger
-from ..block import CodeBlock, NodeType
-from ..splitter import Splitter
+from janus.language.block import CodeBlock, NodeType
+from janus.language.splitter import Splitter
+from janus.utils.enums import LANGUAGES
+from janus.utils.logger import create_logger
 
 log = create_logger(__name__)
 

janus_llm-3.2.1/janus/llm/__init__.py

@@ -0,0 +1 @@
+from janus.llm.models_info import load_model

{janus_llm-3.2.0 → janus_llm-3.2.1}/janus/llm/model_callbacks.py

@@ -8,7 +8,7 @@ from langchain_core.messages import AIMessage
 from langchain_core.outputs import ChatGeneration, LLMResult
 from langchain_core.tracers.context import register_configure_hook
 
-from ..utils.logger import create_logger
+from janus.utils.logger import create_logger
 
 log = create_logger(__name__)
 

{janus_llm-3.2.0 → janus_llm-3.2.1}/janus/llm/models_info.py

@@ -8,7 +8,8 @@ from langchain_community.llms import HuggingFaceTextGenInference
 from langchain_core.language_models import BaseLanguageModel
 from langchain_openai import ChatOpenAI
 
-from ..prompts.prompt import (
+from janus.llm.model_callbacks import COST_PER_1K_TOKENS
+from janus.prompts.prompt import (
     ChatGptPromptEngine,
     ClaudePromptEngine,
     CoherePromptEngine,
@@ -18,8 +19,7 @@ from ..prompts.prompt import (
     PromptEngine,
     TitanPromptEngine,
 )
-from ..utils.logger import create_logger
-from .model_callbacks import COST_PER_1K_TOKENS
+from janus.utils.logger import create_logger
 
 log = create_logger(__name__)
 

{janus_llm-3.2.0 → janus_llm-3.2.1}/janus/metrics/_tests/test_bleu.py

@@ -2,7 +2,7 @@ import unittest
 
 from sacrebleu import sentence_bleu
 
-from ..bleu import bleu
+from janus.metrics.bleu import bleu
 
 
 class TestBLEU(unittest.TestCase):

{janus_llm-3.2.0 → janus_llm-3.2.1}/janus/metrics/_tests/test_chrf.py

@@ -2,7 +2,7 @@ import unittest
 
 from sacrebleu import sentence_chrf
 
-from ..chrf import chrf
+from janus.metrics.chrf import chrf
 
 
 class TestChrF(unittest.TestCase):

{janus_llm-3.2.0 → janus_llm-3.2.1}/janus/metrics/_tests/test_file_pairing.py

@@ -3,7 +3,7 @@
 import unittest
 from pathlib import Path
 
-from ..file_pairing import (
+from janus.metrics.file_pairing import (
     FILE_PAIRING_METHODS,
     pair_by_file,
     pair_by_line,