cjm-text-plugin-nltk 0.0.1__tar.gz

cjm_text_plugin_nltk-0.0.1/LICENSE

@@ -0,0 +1,201 @@
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright 2022, fastai
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.

cjm_text_plugin_nltk-0.0.1/MANIFEST.in

@@ -0,0 +1,5 @@
+include settings.ini
+include LICENSE
+include CONTRIBUTING.md
+include README.md
+recursive-exclude * __pycache__

cjm_text_plugin_nltk-0.0.1/PKG-INFO

@@ -0,0 +1,199 @@
+Metadata-Version: 2.4
+Name: cjm-text-plugin-nltk
+Version: 0.0.1
+Summary: A local, NLTK-based text processing worker for the cjm-plugin-system that provides sentence splitting and tokenization with character-level span tracking.
+Home-page: https://github.com/cj-mills/cjm-text-plugin-nltk
+Author: Christian J. Mills
+Author-email: 9126128+cj-mills@users.noreply.github.com
+License: Apache-2.0
+Keywords: nbdev jupyter notebook python
+Classifier: Development Status :: 4 - Beta
+Classifier: Intended Audience :: Developers
+Classifier: Natural Language :: English
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
+Requires-Python: >=3.11
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: cjm_text_plugin_system
+Requires-Dist: nltk
+Provides-Extra: dev
+Dynamic: author
+Dynamic: author-email
+Dynamic: classifier
+Dynamic: description
+Dynamic: description-content-type
+Dynamic: home-page
+Dynamic: keywords
+Dynamic: license
+Dynamic: license-file
+Dynamic: provides-extra
+Dynamic: requires-dist
+Dynamic: requires-python
+Dynamic: summary
+
+# cjm-text-plugin-nltk
+
+
+<!-- WARNING: THIS FILE WAS AUTOGENERATED! DO NOT EDIT! -->
+
+## Install
+
+``` bash
+pip install cjm_text_plugin_nltk
+```
+
+## Project Structure
+
+    nbs/
+    ├── meta.ipynb   # Metadata introspection for the NLTK text plugin used by cjm-ctl to generate the registration manifest.
+    └── plugin.ipynb # Plugin implementation for NLTK-based text processing with character-level span tracking
+
+Total: 2 notebooks
+
+## Module Dependencies
+
+``` mermaid
+graph LR
+    meta[meta<br/>Metadata]
+    plugin[plugin<br/>NLTK Plugin]
+```
+
+No cross-module dependencies detected.
+
+## CLI Reference
+
+No CLI commands found in this project.
+
+## Module Overview
+
+Detailed documentation for each module in the project:
+
+### Metadata (`meta.ipynb`)
+
+> Metadata introspection for the NLTK text plugin used by cjm-ctl to
+> generate the registration manifest.
+
+#### Import
+
+``` python
+from cjm_text_plugin_nltk.meta import (
+    get_plugin_metadata
+)
+```
+
+#### Functions
+
+``` python
+def get_plugin_metadata() -> Dict[str, Any]:  # Plugin metadata for manifest generation
+    """Return metadata required to register this plugin with the PluginManager."""
+    # Fallback base path (current behavior for backward compatibility)
+    base_path = os.path.dirname(os.path.dirname(sys.executable))
+    
+    # Use CJM config if available, else fallback to env-relative paths
+    cjm_data_dir = os.environ.get("CJM_DATA_DIR")
+    
+    # Plugin data directory
+    plugin_name = "cjm-text-plugin-nltk"
+    if cjm_data_dir
+    "Return metadata required to register this plugin with the PluginManager."
+```
+
+### NLTK Plugin (`plugin.ipynb`)
+
+> Plugin implementation for NLTK-based text processing with
+> character-level span tracking
+
+#### Import
+
+``` python
+from cjm_text_plugin_nltk.plugin import (
+    NLTKPluginConfig,
+    NLTKPlugin
+)
+```
+
+#### Classes
+
+``` python
+@dataclass
+class NLTKPluginConfig:
+    "Configuration for NLTK text processing plugin."
+    
+    tokenizer: str = field(...)
+    language: str = field(...)
+```
+
+``` python
+class NLTKPlugin:
+    def __init__(self):
+        """Initialize the NLTK plugin."""
+        self.logger = logging.getLogger(f"{__name__}.{type(self).__name__}")
+        self.config: NLTKPluginConfig = None
+    "NLTK-based text processing plugin with character-level span tracking."
+    
+    def __init__(self):
+            """Initialize the NLTK plugin."""
+            self.logger = logging.getLogger(f"{__name__}.{type(self).__name__}")
+            self.config: NLTKPluginConfig = None
+        "Initialize the NLTK plugin."
+    
+    def name(self) -> str:  # Plugin name identifier
+            """Get the plugin name identifier."""
+            return "nltk_text"
+        
+        @property
+        def version(self) -> str:  # Plugin version string
+        "Get the plugin name identifier."
+    
+    def version(self) -> str:  # Plugin version string
+            """Get the plugin version string."""
+            return "1.0.0"
+    
+        def get_current_config(self) -> Dict[str, Any]:  # Current configuration as dictionary
+        "Get the plugin version string."
+    
+    def get_current_config(self) -> Dict[str, Any]:  # Current configuration as dictionary
+            """Return current configuration state."""
+            if not self.config
+        "Return current configuration state."
+    
+    def get_config_schema(self) -> Dict[str, Any]:  # JSON Schema for configuration
+            """Return JSON Schema for UI generation."""
+            return dataclass_to_jsonschema(NLTKPluginConfig)
+    
+        @staticmethod
+        def get_config_dataclass() -> NLTKPluginConfig:  # Configuration dataclass
+        "Return JSON Schema for UI generation."
+    
+    def get_config_dataclass() -> NLTKPluginConfig:  # Configuration dataclass
+            """Return dataclass describing the plugin's configuration options."""
+            return NLTKPluginConfig
+        
+        def _ensure_nltk_data(self) -> None
+        "Return dataclass describing the plugin's configuration options."
+    
+    def initialize(
+            self,
+            config: Optional[Any] = None  # Configuration dataclass, dict, or None
+        ) -> None
+        "Initialize or re-configure the plugin (idempotent)."
+    
+    def execute(
+            self,
+            action: str = "split_sentences",  # Operation: 'split_sentences'
+            **kwargs
+        ) -> Dict[str, Any]:  # JSON-serializable result
+        "Execute a text processing operation."
+    
+    def split_sentences(
+            self,
+            text: str,  # Input text to split into sentences
+            **kwargs
+        ) -> TextProcessResult:  # Result with TextSpan objects containing character indices
+        "Split text into sentence spans with accurate character positions."
+    
+    def cleanup(self) -> None
+        "Clean up resources."
+```

cjm_text_plugin_nltk-0.0.1/README.md

@@ -0,0 +1,164 @@
+# cjm-text-plugin-nltk
+
+
+<!-- WARNING: THIS FILE WAS AUTOGENERATED! DO NOT EDIT! -->
+
+## Install
+
+``` bash
+pip install cjm_text_plugin_nltk
+```
+
+## Project Structure
+
+    nbs/
+    ├── meta.ipynb   # Metadata introspection for the NLTK text plugin used by cjm-ctl to generate the registration manifest.
+    └── plugin.ipynb # Plugin implementation for NLTK-based text processing with character-level span tracking
+
+Total: 2 notebooks
+
+## Module Dependencies
+
+``` mermaid
+graph LR
+    meta[meta<br/>Metadata]
+    plugin[plugin<br/>NLTK Plugin]
+```
+
+No cross-module dependencies detected.
+
+## CLI Reference
+
+No CLI commands found in this project.
+
+## Module Overview
+
+Detailed documentation for each module in the project:
+
+### Metadata (`meta.ipynb`)
+
+> Metadata introspection for the NLTK text plugin used by cjm-ctl to
+> generate the registration manifest.
+
+#### Import
+
+``` python
+from cjm_text_plugin_nltk.meta import (
+    get_plugin_metadata
+)
+```
+
+#### Functions
+
+``` python
+def get_plugin_metadata() -> Dict[str, Any]:  # Plugin metadata for manifest generation
+    """Return metadata required to register this plugin with the PluginManager."""
+    # Fallback base path (current behavior for backward compatibility)
+    base_path = os.path.dirname(os.path.dirname(sys.executable))
+    
+    # Use CJM config if available, else fallback to env-relative paths
+    cjm_data_dir = os.environ.get("CJM_DATA_DIR")
+    
+    # Plugin data directory
+    plugin_name = "cjm-text-plugin-nltk"
+    if cjm_data_dir
+    "Return metadata required to register this plugin with the PluginManager."
+```
+
+### NLTK Plugin (`plugin.ipynb`)
+
+> Plugin implementation for NLTK-based text processing with
+> character-level span tracking
+
+#### Import
+
+``` python
+from cjm_text_plugin_nltk.plugin import (
+    NLTKPluginConfig,
+    NLTKPlugin
+)
+```
+
+#### Classes
+
+``` python
+@dataclass
+class NLTKPluginConfig:
+    "Configuration for NLTK text processing plugin."
+    
+    tokenizer: str = field(...)
+    language: str = field(...)
+```
+
+``` python
+class NLTKPlugin:
+    def __init__(self):
+        """Initialize the NLTK plugin."""
+        self.logger = logging.getLogger(f"{__name__}.{type(self).__name__}")
+        self.config: NLTKPluginConfig = None
+    "NLTK-based text processing plugin with character-level span tracking."
+    
+    def __init__(self):
+            """Initialize the NLTK plugin."""
+            self.logger = logging.getLogger(f"{__name__}.{type(self).__name__}")
+            self.config: NLTKPluginConfig = None
+        "Initialize the NLTK plugin."
+    
+    def name(self) -> str:  # Plugin name identifier
+            """Get the plugin name identifier."""
+            return "nltk_text"
+        
+        @property
+        def version(self) -> str:  # Plugin version string
+        "Get the plugin name identifier."
+    
+    def version(self) -> str:  # Plugin version string
+            """Get the plugin version string."""
+            return "1.0.0"
+    
+        def get_current_config(self) -> Dict[str, Any]:  # Current configuration as dictionary
+        "Get the plugin version string."
+    
+    def get_current_config(self) -> Dict[str, Any]:  # Current configuration as dictionary
+            """Return current configuration state."""
+            if not self.config
+        "Return current configuration state."
+    
+    def get_config_schema(self) -> Dict[str, Any]:  # JSON Schema for configuration
+            """Return JSON Schema for UI generation."""
+            return dataclass_to_jsonschema(NLTKPluginConfig)
+    
+        @staticmethod
+        def get_config_dataclass() -> NLTKPluginConfig:  # Configuration dataclass
+        "Return JSON Schema for UI generation."
+    
+    def get_config_dataclass() -> NLTKPluginConfig:  # Configuration dataclass
+            """Return dataclass describing the plugin's configuration options."""
+            return NLTKPluginConfig
+        
+        def _ensure_nltk_data(self) -> None
+        "Return dataclass describing the plugin's configuration options."
+    
+    def initialize(
+            self,
+            config: Optional[Any] = None  # Configuration dataclass, dict, or None
+        ) -> None
+        "Initialize or re-configure the plugin (idempotent)."
+    
+    def execute(
+            self,
+            action: str = "split_sentences",  # Operation: 'split_sentences'
+            **kwargs
+        ) -> Dict[str, Any]:  # JSON-serializable result
+        "Execute a text processing operation."
+    
+    def split_sentences(
+            self,
+            text: str,  # Input text to split into sentences
+            **kwargs
+        ) -> TextProcessResult:  # Result with TextSpan objects containing character indices
+        "Split text into sentence spans with accurate character positions."
+    
+    def cleanup(self) -> None
+        "Clean up resources."
+```

cjm_text_plugin_nltk-0.0.1/cjm_text_plugin_nltk/__init__.py

@@ -0,0 +1 @@
+__version__ = "0.0.1"

cjm_text_plugin_nltk-0.0.1/cjm_text_plugin_nltk/_modidx.py

@@ -0,0 +1,37 @@
+# Autogenerated by nbdev
+
+d = { 'settings': { 'branch': 'main',
+                'doc_baseurl': '/cjm-text-plugin-nltk',
+                'doc_host': 'https://cj-mills.github.io',
+                'git_url': 'https://github.com/cj-mills/cjm-text-plugin-nltk',
+                'lib_path': 'cjm_text_plugin_nltk'},
+  'syms': { 'cjm_text_plugin_nltk.meta': { 'cjm_text_plugin_nltk.meta.get_plugin_metadata': ( 'meta.html#get_plugin_metadata',
+                                                                                              'cjm_text_plugin_nltk/meta.py')},
+            'cjm_text_plugin_nltk.plugin': { 'cjm_text_plugin_nltk.plugin.NLTKPlugin': ( 'plugin.html#nltkplugin',
+                                                                                         'cjm_text_plugin_nltk/plugin.py'),
+                                             'cjm_text_plugin_nltk.plugin.NLTKPlugin.__init__': ( 'plugin.html#nltkplugin.__init__',
+                                                                                                  'cjm_text_plugin_nltk/plugin.py'),
+                                             'cjm_text_plugin_nltk.plugin.NLTKPlugin._ensure_nltk_data': ( 'plugin.html#nltkplugin._ensure_nltk_data',
+                                                                                                           'cjm_text_plugin_nltk/plugin.py'),
+                                             'cjm_text_plugin_nltk.plugin.NLTKPlugin._get_tokenizer': ( 'plugin.html#nltkplugin._get_tokenizer',
+                                                                                                        'cjm_text_plugin_nltk/plugin.py'),
+                                             'cjm_text_plugin_nltk.plugin.NLTKPlugin.cleanup': ( 'plugin.html#nltkplugin.cleanup',
+                                                                                                 'cjm_text_plugin_nltk/plugin.py'),
+                                             'cjm_text_plugin_nltk.plugin.NLTKPlugin.execute': ( 'plugin.html#nltkplugin.execute',
+                                                                                                 'cjm_text_plugin_nltk/plugin.py'),
+                                             'cjm_text_plugin_nltk.plugin.NLTKPlugin.get_config_dataclass': ( 'plugin.html#nltkplugin.get_config_dataclass',
+                                                                                                              'cjm_text_plugin_nltk/plugin.py'),
+                                             'cjm_text_plugin_nltk.plugin.NLTKPlugin.get_config_schema': ( 'plugin.html#nltkplugin.get_config_schema',
+                                                                                                           'cjm_text_plugin_nltk/plugin.py'),
+                                             'cjm_text_plugin_nltk.plugin.NLTKPlugin.get_current_config': ( 'plugin.html#nltkplugin.get_current_config',
+                                                                                                            'cjm_text_plugin_nltk/plugin.py'),
+                                             'cjm_text_plugin_nltk.plugin.NLTKPlugin.initialize': ( 'plugin.html#nltkplugin.initialize',
+                                                                                                    'cjm_text_plugin_nltk/plugin.py'),
+                                             'cjm_text_plugin_nltk.plugin.NLTKPlugin.name': ( 'plugin.html#nltkplugin.name',
+                                                                                              'cjm_text_plugin_nltk/plugin.py'),
+                                             'cjm_text_plugin_nltk.plugin.NLTKPlugin.split_sentences': ( 'plugin.html#nltkplugin.split_sentences',
+                                                                                                         'cjm_text_plugin_nltk/plugin.py'),
+                                             'cjm_text_plugin_nltk.plugin.NLTKPlugin.version': ( 'plugin.html#nltkplugin.version',
+                                                                                                 'cjm_text_plugin_nltk/plugin.py'),
+                                             'cjm_text_plugin_nltk.plugin.NLTKPluginConfig': ( 'plugin.html#nltkpluginconfig',
+                                                                                               'cjm_text_plugin_nltk/plugin.py')}}}

cjm_text_plugin_nltk-0.0.1/cjm_text_plugin_nltk/meta.py

@@ -0,0 +1,60 @@
+"""Metadata introspection for the NLTK text plugin used by cjm-ctl to generate the registration manifest."""
+
+# AUTOGENERATED! DO NOT EDIT! File to edit: ../nbs/meta.ipynb.
+
+# %% auto #0
+__all__ = ['get_plugin_metadata']
+
+# %% ../nbs/meta.ipynb #3508402d
+import os
+import sys
+from typing import Any, Dict
+
+from . import __version__
+
+# %% ../nbs/meta.ipynb #791d750b
+def get_plugin_metadata() -> Dict[str, Any]:  # Plugin metadata for manifest generation
+    """Return metadata required to register this plugin with the PluginManager."""
+    # Fallback base path (current behavior for backward compatibility)
+    base_path = os.path.dirname(os.path.dirname(sys.executable))
+    
+    # Use CJM config if available, else fallback to env-relative paths
+    cjm_data_dir = os.environ.get("CJM_DATA_DIR")
+    
+    # Plugin data directory
+    plugin_name = "cjm-text-plugin-nltk"
+    if cjm_data_dir:
+        data_dir = os.path.join(cjm_data_dir, plugin_name)
+    else:
+        data_dir = os.path.join(base_path, "data")
+    
+    # Ensure data directory exists
+    os.makedirs(data_dir, exist_ok=True)
+    
+    # NLTK data directory
+    nltk_data_path = os.path.join(data_dir, "nltk_data")
+    os.makedirs(nltk_data_path, exist_ok=True)
+
+    return {
+        "name": plugin_name,
+        "version": __version__,
+        "type": "text-processing",
+        "category": "text-processing",
+        "interface": "cjm_text_plugin_system.plugin_interface.TextProcessingPlugin",
+        
+        "module": "cjm_text_plugin_nltk.plugin",
+        "class": "NLTKPlugin",
+        
+        # Critical: The absolute path to THIS environment's python
+        "python_path": sys.executable,
+        
+        # NLTK is lightweight - no GPU required
+        "resources": {
+            "requires_gpu": False,
+            "min_system_ram_mb": 512
+        },
+        
+        "env_vars": {
+            "NLTK_DATA": nltk_data_path
+        }
+    }

cjm_text_plugin_nltk-0.0.1/cjm_text_plugin_nltk/plugin.py

@@ -0,0 +1,204 @@
+"""Plugin implementation for NLTK-based text processing with character-level span tracking"""
+
+# AUTOGENERATED! DO NOT EDIT! File to edit: ../nbs/plugin.ipynb.
+
+# %% auto #0
+__all__ = ['NLTKPluginConfig', 'NLTKPlugin']
+
+# %% ../nbs/plugin.ipynb #1899201c
+import logging
+import os
+from dataclasses import dataclass, field
+from typing import Dict, Any, Optional, List
+
+import nltk
+from nltk.tokenize import PunktSentenceTokenizer
+
+from cjm_text_plugin_system.plugin_interface import TextProcessingPlugin
+from cjm_text_plugin_system.core import TextProcessResult, TextSpan
+from cjm_plugin_system.utils.validation import (
+    dict_to_config, config_to_dict, dataclass_to_jsonschema,
+    SCHEMA_TITLE, SCHEMA_DESC, SCHEMA_ENUM
+)
+
+# %% ../nbs/plugin.ipynb #687955b4
+@dataclass
+class NLTKPluginConfig:
+    """Configuration for NLTK text processing plugin."""
+    tokenizer: str = field(
+        default="punkt",
+        metadata={
+            SCHEMA_TITLE: "Tokenizer",
+            SCHEMA_DESC: "NLTK tokenizer to use for sentence splitting",
+            SCHEMA_ENUM: ["punkt"]
+        }
+    )
+    language: str = field(
+        default="english",
+        metadata={
+            SCHEMA_TITLE: "Language",
+            SCHEMA_DESC: "Language for tokenization (affects sentence boundary detection)",
+            SCHEMA_ENUM: ["english", "german", "french", "spanish", "italian", "portuguese", "dutch"]
+        }
+    )
+
+# %% ../nbs/plugin.ipynb #330602bc
+class NLTKPlugin(TextProcessingPlugin):
+    """NLTK-based text processing plugin with character-level span tracking."""
+    
+    config_class = NLTKPluginConfig
+    
+    def __init__(self):
+        """Initialize the NLTK plugin."""
+        self.logger = logging.getLogger(f"{__name__}.{type(self).__name__}")
+        self.config: NLTKPluginConfig = None
+        self._tokenizer: PunktSentenceTokenizer = None
+        self._nltk_data_dir: Optional[str] = None
+    
+    @property
+    def name(self) -> str:  # Plugin name identifier
+        """Get the plugin name identifier."""
+        return "nltk_text"
+    
+    @property
+    def version(self) -> str:  # Plugin version string
+        """Get the plugin version string."""
+        return "1.0.0"
+
+    def get_current_config(self) -> Dict[str, Any]:  # Current configuration as dictionary
+        """Return current configuration state."""
+        if not self.config:
+            return {}
+        return config_to_dict(self.config)
+
+    def get_config_schema(self) -> Dict[str, Any]:  # JSON Schema for configuration
+        """Return JSON Schema for UI generation."""
+        return dataclass_to_jsonschema(NLTKPluginConfig)
+
+    @staticmethod
+    def get_config_dataclass() -> NLTKPluginConfig:  # Configuration dataclass
+        """Return dataclass describing the plugin's configuration options."""
+        return NLTKPluginConfig
+    
+    def _ensure_nltk_data(self) -> None:
+        """Ensure required NLTK data packages are downloaded to the configured directory."""
+        # Get NLTK data directory from environment (set by manifest env_vars)
+        nltk_data_dir = os.environ.get("NLTK_DATA")
+        
+        if nltk_data_dir:
+            # Ensure the directory exists
+            os.makedirs(nltk_data_dir, exist_ok=True)
+            
+            # Replace NLTK's search path to ONLY use our directory
+            # This prevents NLTK from finding/using data in ~/nltk_data
+            nltk.data.path = [nltk_data_dir]
+            
+            self._nltk_data_dir = nltk_data_dir
+            self.logger.info(f"Using NLTK data directory: {nltk_data_dir}")
+            
+            # Check if data exists in OUR directory specifically
+            punkt_path = os.path.join(nltk_data_dir, "tokenizers", "punkt")
+            punkt_tab_path = os.path.join(nltk_data_dir, "tokenizers", "punkt_tab")
+            
+            if not os.path.exists(punkt_path):
+                self.logger.info(f"Downloading NLTK 'punkt' tokenizer to {nltk_data_dir}...")
+                nltk.download('punkt', quiet=True, download_dir=nltk_data_dir)
+            
+            if not os.path.exists(punkt_tab_path):
+                self.logger.info(f"Downloading NLTK 'punkt_tab' tokenizer to {nltk_data_dir}...")
+                nltk.download('punkt_tab', quiet=True, download_dir=nltk_data_dir)
+        else:
+            # No custom directory - use NLTK defaults
+            try:
+                nltk.data.find('tokenizers/punkt')
+            except LookupError:
+                self.logger.info("Downloading NLTK 'punkt' tokenizer...")
+                nltk.download('punkt', quiet=True)
+            
+            try:
+                nltk.data.find('tokenizers/punkt_tab')
+            except LookupError:
+                self.logger.info("Downloading NLTK 'punkt_tab' tokenizer...")
+                nltk.download('punkt_tab', quiet=True)
+    
+    def initialize(
+        self,
+        config: Optional[Any] = None  # Configuration dataclass, dict, or None
+    ) -> None:
+        """Initialize or re-configure the plugin (idempotent)."""
+        # Parse new config
+        new_config = dict_to_config(NLTKPluginConfig, config or {})
+        
+        # Check for changes if already running
+        if self.config:
+            if self.config.language != new_config.language:
+                self.logger.info(f"Config change: Language {self.config.language} -> {new_config.language}")
+                self._tokenizer = None  # Reset tokenizer for new language
+        
+        # Apply new config
+        self.config = new_config
+        
+        # Ensure NLTK data is available
+        self._ensure_nltk_data()
+        
+        self.logger.info(f"Initialized NLTK plugin with language '{self.config.language}'")
+    
+    def _get_tokenizer(self) -> PunktSentenceTokenizer:
+        """Get or create the sentence tokenizer (lazy loading)."""
+        if self._tokenizer is None:
+            self._tokenizer = PunktSentenceTokenizer()
+        return self._tokenizer
+    
+    def execute(
+        self,
+        action: str = "split_sentences",  # Operation: 'split_sentences'
+        **kwargs
+    ) -> Dict[str, Any]:  # JSON-serializable result
+        """Execute a text processing operation."""
+        if action == "split_sentences":
+            text = kwargs.pop("text", "")
+            result = self.split_sentences(text, **kwargs)
+            
+            # Serialize for IPC
+            return {
+                "spans": [s.to_dict() for s in result.spans],
+                "metadata": result.metadata
+            }
+        else:
+            raise ValueError(f"Unknown action: {action}")
+
+    def split_sentences(
+        self,
+        text: str,  # Input text to split into sentences
+        **kwargs
+    ) -> TextProcessResult:  # Result with TextSpan objects containing character indices
+        """Split text into sentence spans with accurate character positions."""
+        tokenizer = self._get_tokenizer()
+        
+        # Get (start, end) tuples using span_tokenize
+        span_indices = list(tokenizer.span_tokenize(text))
+        
+        text_spans: List[TextSpan] = []
+        for start, end in span_indices:
+            span_text = text[start:end]
+            text_spans.append(TextSpan(
+                text=span_text,
+                start_char=start,
+                end_char=end,
+                label="sentence"
+            ))
+        
+        return TextProcessResult(
+            spans=text_spans,
+            metadata={
+                "processor": self.name,
+                "tokenizer": self.config.tokenizer if self.config else "punkt",
+                "language": self.config.language if self.config else "english",
+                "nltk_data_dir": self._nltk_data_dir
+            }
+        )
+    
+    def cleanup(self) -> None:
+        """Clean up resources."""
+        self._tokenizer = None
+        self.logger.info("NLTK plugin cleanup completed")

cjm_text_plugin_nltk-0.0.1/cjm_text_plugin_nltk.egg-info/PKG-INFO

@@ -0,0 +1,199 @@
+Metadata-Version: 2.4
+Name: cjm-text-plugin-nltk
+Version: 0.0.1
+Summary: A local, NLTK-based text processing worker for the cjm-plugin-system that provides sentence splitting and tokenization with character-level span tracking.
+Home-page: https://github.com/cj-mills/cjm-text-plugin-nltk
+Author: Christian J. Mills
+Author-email: 9126128+cj-mills@users.noreply.github.com
+License: Apache-2.0
+Keywords: nbdev jupyter notebook python
+Classifier: Development Status :: 4 - Beta
+Classifier: Intended Audience :: Developers
+Classifier: Natural Language :: English
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
+Requires-Python: >=3.11
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: cjm_text_plugin_system
+Requires-Dist: nltk
+Provides-Extra: dev
+Dynamic: author
+Dynamic: author-email
+Dynamic: classifier
+Dynamic: description
+Dynamic: description-content-type
+Dynamic: home-page
+Dynamic: keywords
+Dynamic: license
+Dynamic: license-file
+Dynamic: provides-extra
+Dynamic: requires-dist
+Dynamic: requires-python
+Dynamic: summary
+
+# cjm-text-plugin-nltk
+
+
+<!-- WARNING: THIS FILE WAS AUTOGENERATED! DO NOT EDIT! -->
+
+## Install
+
+``` bash
+pip install cjm_text_plugin_nltk
+```
+
+## Project Structure
+
+    nbs/
+    ├── meta.ipynb   # Metadata introspection for the NLTK text plugin used by cjm-ctl to generate the registration manifest.
+    └── plugin.ipynb # Plugin implementation for NLTK-based text processing with character-level span tracking
+
+Total: 2 notebooks
+
+## Module Dependencies
+
+``` mermaid
+graph LR
+    meta[meta<br/>Metadata]
+    plugin[plugin<br/>NLTK Plugin]
+```
+
+No cross-module dependencies detected.
+
+## CLI Reference
+
+No CLI commands found in this project.
+
+## Module Overview
+
+Detailed documentation for each module in the project:
+
+### Metadata (`meta.ipynb`)
+
+> Metadata introspection for the NLTK text plugin used by cjm-ctl to
+> generate the registration manifest.
+
+#### Import
+
+``` python
+from cjm_text_plugin_nltk.meta import (
+    get_plugin_metadata
+)
+```
+
+#### Functions
+
+``` python
+def get_plugin_metadata() -> Dict[str, Any]:  # Plugin metadata for manifest generation
+    """Return metadata required to register this plugin with the PluginManager."""
+    # Fallback base path (current behavior for backward compatibility)
+    base_path = os.path.dirname(os.path.dirname(sys.executable))
+    
+    # Use CJM config if available, else fallback to env-relative paths
+    cjm_data_dir = os.environ.get("CJM_DATA_DIR")
+    
+    # Plugin data directory
+    plugin_name = "cjm-text-plugin-nltk"
+    if cjm_data_dir
+    "Return metadata required to register this plugin with the PluginManager."
+```
+
+### NLTK Plugin (`plugin.ipynb`)
+
+> Plugin implementation for NLTK-based text processing with
+> character-level span tracking
+
+#### Import
+
+``` python
+from cjm_text_plugin_nltk.plugin import (
+    NLTKPluginConfig,
+    NLTKPlugin
+)
+```
+
+#### Classes
+
+``` python
+@dataclass
+class NLTKPluginConfig:
+    "Configuration for NLTK text processing plugin."
+    
+    tokenizer: str = field(...)
+    language: str = field(...)
+```
+
+``` python
+class NLTKPlugin:
+    def __init__(self):
+        """Initialize the NLTK plugin."""
+        self.logger = logging.getLogger(f"{__name__}.{type(self).__name__}")
+        self.config: NLTKPluginConfig = None
+    "NLTK-based text processing plugin with character-level span tracking."
+    
+    def __init__(self):
+            """Initialize the NLTK plugin."""
+            self.logger = logging.getLogger(f"{__name__}.{type(self).__name__}")
+            self.config: NLTKPluginConfig = None
+        "Initialize the NLTK plugin."
+    
+    def name(self) -> str:  # Plugin name identifier
+            """Get the plugin name identifier."""
+            return "nltk_text"
+        
+        @property
+        def version(self) -> str:  # Plugin version string
+        "Get the plugin name identifier."
+    
+    def version(self) -> str:  # Plugin version string
+            """Get the plugin version string."""
+            return "1.0.0"
+    
+        def get_current_config(self) -> Dict[str, Any]:  # Current configuration as dictionary
+        "Get the plugin version string."
+    
+    def get_current_config(self) -> Dict[str, Any]:  # Current configuration as dictionary
+            """Return current configuration state."""
+            if not self.config
+        "Return current configuration state."
+    
+    def get_config_schema(self) -> Dict[str, Any]:  # JSON Schema for configuration
+            """Return JSON Schema for UI generation."""
+            return dataclass_to_jsonschema(NLTKPluginConfig)
+    
+        @staticmethod
+        def get_config_dataclass() -> NLTKPluginConfig:  # Configuration dataclass
+        "Return JSON Schema for UI generation."
+    
+    def get_config_dataclass() -> NLTKPluginConfig:  # Configuration dataclass
+            """Return dataclass describing the plugin's configuration options."""
+            return NLTKPluginConfig
+        
+        def _ensure_nltk_data(self) -> None
+        "Return dataclass describing the plugin's configuration options."
+    
+    def initialize(
+            self,
+            config: Optional[Any] = None  # Configuration dataclass, dict, or None
+        ) -> None
+        "Initialize or re-configure the plugin (idempotent)."
+    
+    def execute(
+            self,
+            action: str = "split_sentences",  # Operation: 'split_sentences'
+            **kwargs
+        ) -> Dict[str, Any]:  # JSON-serializable result
+        "Execute a text processing operation."
+    
+    def split_sentences(
+            self,
+            text: str,  # Input text to split into sentences
+            **kwargs
+        ) -> TextProcessResult:  # Result with TextSpan objects containing character indices
+        "Split text into sentence spans with accurate character positions."
+    
+    def cleanup(self) -> None
+        "Clean up resources."
+```

cjm_text_plugin_nltk-0.0.1/cjm_text_plugin_nltk.egg-info/SOURCES.txt

@@ -0,0 +1,17 @@
+LICENSE
+MANIFEST.in
+README.md
+pyproject.toml
+settings.ini
+setup.py
+cjm_text_plugin_nltk/__init__.py
+cjm_text_plugin_nltk/_modidx.py
+cjm_text_plugin_nltk/meta.py
+cjm_text_plugin_nltk/plugin.py
+cjm_text_plugin_nltk.egg-info/PKG-INFO
+cjm_text_plugin_nltk.egg-info/SOURCES.txt
+cjm_text_plugin_nltk.egg-info/dependency_links.txt
+cjm_text_plugin_nltk.egg-info/entry_points.txt
+cjm_text_plugin_nltk.egg-info/not-zip-safe
+cjm_text_plugin_nltk.egg-info/requires.txt
+cjm_text_plugin_nltk.egg-info/top_level.txt

cjm_text_plugin_nltk-0.0.1/cjm_text_plugin_nltk.egg-info/dependency_links.txt

@@ -0,0 +1 @@
+

cjm_text_plugin_nltk-0.0.1/cjm_text_plugin_nltk.egg-info/entry_points.txt

@@ -0,0 +1,2 @@
+[nbdev]
+cjm_text_plugin_nltk = cjm_text_plugin_nltk._modidx:d

cjm_text_plugin_nltk-0.0.1/cjm_text_plugin_nltk.egg-info/not-zip-safe

@@ -0,0 +1 @@
+

cjm_text_plugin_nltk-0.0.1/cjm_text_plugin_nltk.egg-info/requires.txt

@@ -0,0 +1,4 @@
+cjm_text_plugin_system
+nltk
+
+[dev]

cjm_text_plugin_nltk-0.0.1/cjm_text_plugin_nltk.egg-info/top_level.txt

@@ -0,0 +1 @@
+cjm_text_plugin_nltk

cjm_text_plugin_nltk-0.0.1/pyproject.toml

@@ -0,0 +1,11 @@
+[build-system]
+requires = ["setuptools>=64.0"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name="cjm-text-plugin-nltk"
+requires-python=">=3.11"
+dynamic = [ "keywords", "description", "version", "dependencies", "optional-dependencies", "readme", "license", "authors", "classifiers", "entry-points", "scripts", "urls"]
+
+[tool.uv]
+cache-keys = [{ file = "pyproject.toml" }, { file = "settings.ini" }, { file = "setup.py" }]

cjm_text_plugin_nltk-0.0.1/settings.ini

@@ -0,0 +1,46 @@
+[DEFAULT]
+# All sections below are required unless otherwise specified.
+# See https://github.com/AnswerDotAI/nbdev/blob/main/settings.ini for examples.
+
+### Python library ###
+repo = cjm-text-plugin-nltk
+lib_name = %(repo)s
+version = 0.0.1
+min_python = 3.11
+license = apache2
+black_formatting = False
+
+### nbdev ###
+doc_path = _docs
+lib_path = cjm_text_plugin_nltk
+nbs_path = nbs
+recursive = True
+tst_flags = notest
+put_version_in_init = True
+update_pyproject = True
+
+### Docs ###
+branch = main
+custom_sidebar = False
+doc_host = https://%(user)s.github.io
+doc_baseurl = /%(repo)s
+git_url = https://github.com/%(user)s/%(repo)s
+title = %(lib_name)s
+
+### PyPI ###
+audience = Developers
+author = Christian J. Mills
+author_email = 9126128+cj-mills@users.noreply.github.com
+copyright = 2026 onwards, %(author)s
+description = A local, NLTK-based text processing worker for the cjm-plugin-system that provides sentence splitting and tokenization with character-level span tracking.
+keywords = nbdev jupyter notebook python
+language = English
+status = 3
+user = cj-mills
+
+### Optional ###
+requirements = cjm_text_plugin_system nltk
+# dev_requirements = 
+# console_scripts =
+# conda_user = 
+# package_data =

cjm_text_plugin_nltk-0.0.1/setup.cfg

@@ -0,0 +1,4 @@
+[egg_info]
+tag_build = 
+tag_date = 0
+

cjm_text_plugin_nltk-0.0.1/setup.py

@@ -0,0 +1,63 @@
+from pkg_resources import parse_version
+from configparser import ConfigParser
+import setuptools, shlex
+assert parse_version(setuptools.__version__)>=parse_version('36.2')
+
+# note: all settings are in settings.ini; edit there, not here
+config = ConfigParser(delimiters=['='])
+config.read('settings.ini', encoding='utf-8')
+cfg = config['DEFAULT']
+
+cfg_keys = 'version description keywords author author_email'.split()
+expected = cfg_keys + "lib_name user branch license status min_python audience language".split()
+for o in expected: assert o in cfg, "missing expected setting: {}".format(o)
+setup_cfg = {o:cfg[o] for o in cfg_keys}
+
+licenses = {
+    'apache2': 'Apache-2.0',
+    'mit': 'MIT',
+    'gpl2': 'GPL-2.0-only',
+    'gpl3': 'GPL-3.0-or-later',
+    'bsd3': 'BSD-3-Clause',
+}
+statuses = [ '1 - Planning', '2 - Pre-Alpha', '3 - Alpha',
+    '4 - Beta', '5 - Production/Stable', '6 - Mature', '7 - Inactive' ]
+py_versions = '3.6 3.7 3.8 3.9 3.10 3.11 3.12 3.13'.split()
+
+requirements = shlex.split(cfg.get('requirements', ''))
+if cfg.get('pip_requirements'): requirements += shlex.split(cfg.get('pip_requirements', ''))
+min_python = cfg['min_python']
+dev_requirements = (cfg.get('dev_requirements') or '').split()
+
+package_data = dict()
+pkg_data = cfg.get('package_data', None)
+if pkg_data:
+    package_data[cfg['lib_name']] =  pkg_data.split() # split as multiple files might be listed
+# Add package data to setup_cfg for setuptools.setup(..., **setup_cfg)
+setup_cfg['package_data'] = package_data
+
+setuptools.setup(
+    name = cfg['lib_name'],
+    license = licenses.get(cfg['license'].lower(), cfg['license']),
+    classifiers = [
+        'Development Status :: ' + statuses[int(cfg['status'])],
+        'Intended Audience :: ' + cfg['audience'].title(),
+        'Natural Language :: ' + cfg['language'].title(),
+    ] + ['Programming Language :: Python :: '+o for o in py_versions[py_versions.index(min_python):]],
+    url = cfg['git_url'],
+    packages = setuptools.find_packages(),
+    include_package_data = True,
+    install_requires = requirements,
+    extras_require={ 'dev': dev_requirements },
+    dependency_links = cfg.get('dep_links','').split(),
+    python_requires  = '>=' + cfg['min_python'],
+    long_description = open('README.md', encoding='utf-8').read(),
+    long_description_content_type = 'text/markdown',
+    zip_safe = False,
+    entry_points = {
+        'console_scripts': cfg.get('console_scripts','').split(),
+        'nbdev': [f'{cfg.get("lib_path")}={cfg.get("lib_path")}._modidx:d']
+    },
+    **setup_cfg)
+
+