Skip to content
GenAIScript
Blog

Search And Transform

This script is an evolution of the “search and replace” feature from text editor, where the “replace” step has been replaced by a LLM transformation.

It can be useful to batch apply text transformations that are not easily done with regular expressions.

For example, when GenAIScript added the ability to use a string command string in the exec command, we needed to convert all script using

host.exec("cmd", ["arg0", "arg1", "arg2"])

to

host.exec(`cmd arg0 arg1 arg2`)`

While it’s possible to match this function call with a regular expression

host\.exec\s*\([^,]+,\s*\[[^\]]+\]\s*\)

it’s not easy to formulate the replacement string… unless you can describe it in natural language:

Convert the call to a single string command shell in TypeScript

Here are some example of the transformations where the LLM correctly handled variables.

  • concatenate the arguments of a function call into a single string
const { stdout } = await host.exec("git", ["diff"])
const { stdout } = await host.exec(`git diff`)
  • concatenate the arguments and use the ${} syntax to interpolate variables
const { stdout: commits } = await host.exec("git", [
    "log",
    "--author",
    author,
    "--until",
    until,
    "--format=oneline",
])
const { stdout: commits } = await host.exec(`git log --author ${author} --until ${until} --format=oneline`)

The search step is done with the workspace.grep that allows to efficiently search for a pattern in files (this is the same search engine that powers the Visual Studio Code search).

const { pattern, glob } = env.vars
const patternRx = new RegExp(pattern, "g")
const { files } = await workspace.grep(patternRx, glob)

Compute Transforms

The second step is to apply the regular expression to the file content and pre-compute the LLM transformation of each match using an inline prompt.

const { transform } = env.vars
...
const patches = {} // map of match -> transformed
for (const file of files) {
    const { content } = await workspace.readText(file.filename)
    for (const match of content.matchAll(patternRx)) {
        const res = await runPrompt(
            (ctx) => {
                ctx.$`
            ## Task


            Your task is to transform the MATCH with the following TRANSFORM.
            Return the transformed text.
            - do NOT add enclosing quotes.


            ## Context
            `
                ctx.def("MATCHED", match[0])
                ctx.def("TRANSFORM", transform)
            },
            { label: match[0], system: [], cache: "search-and-transform" }
        )
        ...

Since the LLM sometimes decides to wrap the answer in quotes, we need to remove them.

    ...
    const transformed = res.fences?.[0].content ?? res.text
    patches[match[0]] = transformed

Transform

Finally, with the transforms pre-computed, we apply a final regex replace to patch the old file content with the transformed strings.

    const newContent = content.replace(
        patternRx,
        (match) => patches[match] ?? match
    )
    await workspace.writeText(file.filename, newContent)
}

Parameters

The script takes three parameters: a file glob, a pattern to search for, and a LLM transformation to apply. We declare these parameters in the script metadata and extract them from the env.vars object.

script({ ...,
    parameters: {
        glob: {
            type: "string",
            description: "The glob pattern to filter files",
            default: "*",
        },
        pattern: {
            type: "string",
            description: "The text pattern (regular expression) to search for",
        },
        transform: {
            type: "string",
            description: "The LLM transformation to apply to the match",
        },
    },
})
const { pattern, glob, transform } = env.vars

Full source

st.genai.mts
script({
    title: "Search and transform",
    description:
        "Search for a pattern in files and apply a LLM transformation the match",
    parameters: {
        glob: {
            type: "string",
            description: "The glob pattern to filter files",
            default: "*",
        },
        pattern: {
            type: "string",
            description: "The text pattern (regular expression) to search for",
        },
        transform: {
            type: "string",
            description: "The LLM transformation to apply to the match",
        },
    },
})
const { pattern, glob, transform } = env.vars
if (!pattern) cancel("pattern is missing")
const patternRx = new RegExp(pattern, "g")


if (!transform) cancel("transform is missing")


const { files } = await workspace.grep(patternRx, glob)
// cached computed transformations
const patches = {}
for (const file of files) {
    console.log(file.filename)
    const { content } = await workspace.readText(file.filename)


    // skip binary files
    if (!content) continue


    // compute transforms
    for (const match of content.matchAll(patternRx)) {
        console.log(`  ${match[0]}`)
        if (patches[match[0]]) continue


        const res = await runPrompt(
            (_) => {
                _.$`
            ## Task


            Your task is to transform the MATCH with the following TRANSFORM.
            Return the transformed text.
            - do NOT add enclosing quotes.


            ## Context
            `
                _.def("MATCHED", match[0])
                _.def("TRANSFORM", transform)
            },
            { label: match[0], system: [], cache: "search-and-transform" }
        )


        const transformed = res.fences?.[0].content ?? res.text
        if (transformed) patches[match[0]] = transformed
        console.log(`  ${match[0]} -> ${transformed ?? "?"}`)
    }


    // apply transforms
    const newContent = content.replace(
        patternRx,
        (match) => patches[match] ?? match
    )


    // save results if file content is modified
    if (content !== newContent)
        await workspace.writeText(file.filename, newContent)
}

To run this script, you can use the --vars option to pass the pattern and the transform.

Terminal window
genaiscript st --vars 'pattern=host\.exec\s*\([^,]+,\s*\[[^\]]+\]\s*\)' 'transform=Convert the call to a single string command shell in TypeScript'