merge V0.1.3 onto main

CHANGES.md

@@ -1,3 +1,8 @@
+Version 0.1.3 (2024-09-03)
+---------------------------
+* Separate rapidfuzz dependency into optional [search] extra
+
+
 Version 0.1.2 (2024-09-02)
 ---------------------------
 * Added JSON-LD serialization support

docker/ubuntu2204-install/Dockerfile

@@ -1,5 +1,8 @@
 FROM ubuntu:22.04
 
+# define package version
+ARG SOLI_VERSION=0.1.3
+
 # Avoid prompts from apt
 ENV DEBIAN_FRONTEND=noninteractive
 
@@ -20,11 +23,11 @@ RUN python3 -m venv /app/.venv
 # install pytest into it
 RUN /app/.venv/bin/pip install pytest pytest-benchmark
 
-# copy the target/wheels/*.whl files
-COPY dist/*.whl /app
+# copy the SOLI_VERSION wheel:
+COPY dist/soli_python-${SOLI_VERSION}-py3-none-any.whl /app/
 
-# install the wheels
-RUN /app/.venv/bin/pip install /app/*.whl
+# install the wheels with extra 'search'
+RUN /app/.venv/bin/pip install /app/soli_python-${SOLI_VERSION}-py3-none-any.whl[search]
 
 # copy the tests directory
 COPY tests /app/tests

docker/ubuntu2404-install/Dockerfile

@@ -1,5 +1,8 @@
 FROM ubuntu:24.04
 
+# define package version
+ARG SOLI_VERSION=0.1.3
+
 # Avoid prompts from apt
 ENV DEBIAN_FRONTEND=noninteractive
 
@@ -20,11 +23,11 @@ RUN python3 -m venv /app/.venv
 # install pytest into it
 RUN /app/.venv/bin/pip install pytest pytest-benchmark
 
-# copy the target/wheels/*.whl files
-COPY dist/*.whl /app
+# copy the SOLI_VERSION wheel:
+COPY dist/soli_python-${SOLI_VERSION}-py3-none-any.whl /app/
 
-# install the wheels
-RUN /app/.venv/bin/pip install /app/*.whl
+# install the wheels with extra 'search'
+RUN /app/.venv/bin/pip install /app/soli_python-${SOLI_VERSION}-py3-none-any.whl[search]
 
 # copy the tests directory
 COPY tests /app/tests

docs/conf.py

@@ -25,8 +25,8 @@
 project = "soli-python"
 copyright = "2024, ALEA Institute"
 author = "ALEA Institute (https://aleainstitute.ai)"
-release = "0.1.2"
-version = "0.1.2"
+release = "0.1.3"
+version = "0.1.3"
 master_doc = "index"
 language = "en"
 
@@ -67,7 +67,7 @@
     "use_sidenotes": True,
     "collapse_navbar": True,
     "show_navbar_depth": 2,
-    "repository_url": "https://github.com/alea-institute/soli-api",
+    "repository_url": "https://github.com/alea-institute/soli-python",
     "repository_branch": "main",
     "path_to_docs": "sphinx",
     "use_issues_button": True,

docs/examples.md

@@ -62,6 +62,9 @@ print(f"First class: {first_class.label}")
 
 ### Search by Label
 
+**Make sure that you have installed with the `[search]` extra to use the search functionality. See the [installation instructions](index.md#search-extras).**
+
+
 ```python
 # Search for classes with "SDNY" in the label
 results = soli.search_by_label("SDNY", limit=3)

docs/index.md

@@ -34,6 +34,16 @@ pip install --upgrade https://github.com/alea-institute/soli-python/archive/refs
 pip install soli-python
 ```
 
+#### Search Extras
+
+**If you want to use the basic search functionality to run fuzzy searches on labels or definitions,
+you should install the library with the `[search]` extra:**
+
+```bash
+pip install soli-python[search]
+```
+
+
 
 
 ## Getting Started
@@ -179,7 +189,7 @@ For detailed information about the SOLI Python library API, please refer to the
 
 ## Contributing
 
-Contributions to the SOLI Python library are welcome! Please see our [contribution guidelines](contributing.md) for more information. You can also contribute to the SOLI standard itself through the [SOLI GitHub repository](https://github.com/alea-institute/soli-api).
+Contributions to the SOLI Python library are welcome! Please see our [contribution guidelines](contributing.md) for more information. You can also contribute to the SOLI standard itself through the [SOLI GitHub repository](https://github.com/alea-institute/soli-python).
 
 ## License
 

pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "soli-python"
-version = "0.1.2"
+version = "0.1.3"
 description = "Python library for SOLI, the Standard for Open Legal Information"
 authors = ["ALEA Institute <[email protected]>"]
 license = "MIT"
@@ -39,7 +39,7 @@ python = ">=3.10,<4.0.0"
 pydantic = "^2.8.2"
 lxml = "^5.2.2"
 httpx = "^0.27.2"
-rapidfuzz = "^3.9.6"
+rapidfuzz = {version = "^3.9.7", optional = true}
 
 [tool.poetry.group.dev.dependencies]
 types-lxml = "^2024.8.7"
@@ -57,6 +57,14 @@ sphinx-copybutton = "^0.5.2"
 sphinxext-opengraph = "^0.9.1"
 sphinx-plausible = "^0.1.2"
 
+[tool.poetry.group.search.dependencies]
+rapidfuzz = "^3.9.7"
+
+# extras
+[tool.poetry.extras]
+search = ["rapidfuzz"]
+
+
 [build-system]
 requires = ["poetry-core"]
 build-backend = "poetry.core.masonry.api"

soli/__init__.py

@@ -5,7 +5,7 @@
 # SPDX-License-Identifier: MIT
 # (c) 2024 ALEA Institute.
 
-__version__ = "0.1.2"
+__version__ = "0.1.3"
 __author__ = "ALEA Institute"
 __license__ = "MIT"
 __description__ = "Python library for SOLI, the Standard for Open Legal Information"

soli/graph.py

@@ -14,6 +14,7 @@
 # imports
 import base64
 import hashlib
+import importlib.util
 import time
 import uuid
 from enum import Enum
@@ -24,7 +25,6 @@
 # packages
 import httpx
 import lxml.etree
-import rapidfuzz
 
 # project imports
 from soli.config import (
@@ -114,6 +114,18 @@ class SOLITypes(Enum):
 LOGGER = get_logger(__name__)
 
 
+# try to import rapidfuzz with importlib; log if not able to.
+try:
+    if importlib.util.find_spec("rapidfuzz") is not None:
+        import rapidfuzz
+    else:
+        LOGGER.warning("Disabling search functionality: rapidfuzz not found.")
+        rapidfuzz = None
+except ImportError as e:
+    LOGGER.warning("Failed to check for search functionality: %s", e)
+    rapidfuzz = None
+
+
 # pylint: disable=too-many-instance-attributes
 class SOLI:
     """
@@ -1028,6 +1040,12 @@ def search_by_label(
             List[Tuple[OWLClass, int | float]]: The list of search results with
                 the OWL class and the search score.
         """
+        # check if we can search
+        if rapidfuzz is None:
+            raise RuntimeError(
+                "search extra must be installed to use search functions: pip install soli-python[search]"
+            )
+
         # get search labels
         if not include_alt_labels:
             search_labels = tuple(self.label_to_index.keys())
@@ -1069,6 +1087,12 @@ def search_by_definition(
             List[Tuple[OWLClass, int | float]]: The list of search results with
                 the OWL class and the search score.
         """
+        # check if we can search
+        if rapidfuzz is None:
+            raise RuntimeError(
+                "search extra must be installed to use search functions: pip install soli-python[search]"
+            )
+
         # get definitions to search with zip pattern
         class_index, class_definitions = zip(
             *[