cjm-text-plugin-nltk 0.0.12

A local, NLTK-based text processing worker for the cjm-plugin-system that provides sentence splitting and tokenization with character-level span tracking.

cjm-text-plugin-nltk

Install

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

graph LR
    meta["meta<br/>Metadata"]
    plugin["plugin<br/>NLTK Plugin"]

    plugin --> meta

1 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

from cjm_text_plugin_nltk.meta import (
    get_plugin_metadata
)

Functions

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

from cjm_text_plugin_nltk.plugin import (
    NLTKPluginConfig,
    NLTKPlugin
)

Classes

@dataclass
class NLTKPluginConfig:
    "Configuration for NLTK text processing plugin."
    
    tokenizer: str = field(...)
    language: str = field(...)

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."""
            from cjm_text_plugin_nltk import __version__
            return __version__
    
        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
        "First-time setup. CR-4: kept fast (no slow work) so the substrate's load /
initialize timeout isn't exceeded — the NLTK data download is deferred to the
first _get_tokenizer() call (a cold-cache punkt/punkt_tab download takes several
seconds, which previously timed out the load when run here). The manual language
diff-and-reload is replaced by the declarative RELOAD_TRIGGER on `language`; the
substrate's reconfigure path fires _release_tokenizer then re-applies config."
    
    def execute(
            self,
            action: str = "split_sentences",  # Operation: 'split_sentences'
            **kwargs
        ) -> Dict[str, Any]:  # JSON-serializable result
        "Dispatch to the `@plugin_action`-tagged handler for `action` (SG-44)."
    
    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
        "Release resources on unload."