swarmauri_tool_searchword 0.11.0.dev1

Case-insensitive Swarmauri file-search tool for counting and highlighting word or phrase matches.

Swarmauri Tool Search Word

swarmauri_tool_searchword is a Swarmauri file-analysis tool for finding case-insensitive word or phrase matches inside UTF-8 text files. It returns the total match count and a line-by-line view with matching lines highlighted, which makes it useful for documentation QA, terminology enforcement, audit workflows, and agent-assisted text review.

Why Use Swarmauri Tool Search Word

• Count repeated terms or phrases inside local text files.
• Surface matching lines for agent answers, reviews, and diagnostics.
• Enforce style-guide or terminology rules in docs and content pipelines.
• Reuse a simple search primitive inside larger Swarmauri toolchains.

FAQ

What inputs does the tool expect?
It expects a string file_path and a string search_word.

Is the search case-sensitive?
No. Matching is case-insensitive.

What does the tool return?
A dictionary with count and lines, where lines contains every line from the file and highlights matching lines with ANSI color codes.

Does it only search single words?
No. It can search multi-word phrases as well.

Features

• Case-insensitive search across UTF-8 text files.
• Returns both total occurrence count and full-file line output.
• Highlights matching lines using ANSI escape codes.
• Simple Swarmauri ToolBase interface for scripting and agents.
• Supports Python 3.10, 3.11, 3.12, 3.13, and 3.14.

Installation

uv add swarmauri_tool_searchword

pip install swarmauri_tool_searchword

Usage

from swarmauri_tool_searchword import SearchWordTool

tool = SearchWordTool()
result = tool(file_path="docs/README.md", search_word="swarmauri")

print(result["count"])

Examples

Scan documentation for banned terminology

from pathlib import Path
from swarmauri_tool_searchword import SearchWordTool

tool = SearchWordTool()

for path in Path("docs").rglob("*.md"):
    result = tool(str(path), "utilize")
    if result["count"]:
        print(path, result["count"])

Highlight policy terms in a compliance file

from swarmauri_tool_searchword import SearchWordTool

tool = SearchWordTool()
result = tool("policies/security.txt", "retention period")

for line in result["lines"]:
    print(line)

Use the tool in a Swarmauri workflow

from swarmauri_standard.tools.ToolCollection import ToolCollection
from swarmauri_tool_searchword import SearchWordTool

tools = ToolCollection(tools=[SearchWordTool()])
print(tools)

Related Packages

• swarmauri_tool_textlength
• swarmauri_tool_lexicaldensity
• swarmauri_tool_sentencecomplexity
• swarmauri_tool_smogindex
• swarmauri_tool_dalechallreadability

Swarmauri Foundations

• swarmauri
• swarmauri_core
• swarmauri_base
• swarmauri_standard

More Documentation

• Swarmauri SDK repository
• Python re module documentation

Best Practices

• Strip ANSI sequences before rendering in interfaces that do not support them.
• Use absolute or well-scoped relative paths in CI jobs.
• Reserve this tool for text files encoded as UTF-8.
• Combine match counts with readability tools when reviewing large content sets.

License

This project is licensed under the Apache-2.0 License.