@juspay/neurolink/dist/utils/htmlText.d.ts

The pipe layer of an AI nervous system: one interface connecting provider neurons to your application, across three inference types — generate, stream and decide. `decide` returns typed, calibrated judgements from a non-generative model (~400ms, ~$0.00002

/**
 * Single-pass markup removal for turning HTML into indexable text.
 *
 * This is text conversion, not output sanitization. The result is plain text
 * for retrieval and chunking; it is not meant to be written back into a page,
 * and the caller's entity decoding can legitimately turn `<b>` into
 * `<b>`.
 *
 * Why one pass: the previous implementation chained several global regex
 * replacements (script, style, comment, block end, generic tag). Each removal
 * could join the text on either side of it into a new tag for the next
 * replacement (`<scr<!---->ipt>`), and the lazy `[\s\S]*?` bodies rescanned
 * the rest of the input once per unclosed `<script`, which is quadratic.
 * Here the input is read left to right exactly once. Every character of the
 * output is copied from an unremoved stretch of the input, a removed stretch
 * is never re-read, and every search either consumes what it scans or is
 * answered in constant time from an index computed up front, so the work is
 * linear in the input length.
 *
 * Invariant: the output never matches `<[^>]+>`. A `<` survives only when no
 * `>` follows it in the input, or when the next character is the `>` itself
 * (`<>`, which is not a tag). A removed span therefore cannot leave behind,
 * or assemble, a tag.
 */
/**
 * Remove HTML markup from `html` in one linear pass.
 *
 * - `<script>` / `<style>` elements are removed with their bodies. The end
 *   tag may carry whitespace or attributes (`</script >`). An element with
 *   no usable end tag loses only its start tag, as before.
 * - `<!-- ... -->` is replaced with `commentReplacement`. An unterminated
 *   comment is treated like any other tag and ends at the next `>`.
 * - A closing tag named in `lineBreakEndTags` and a void tag named in
 *   `lineBreakVoidTags` (`<br>`, `<hr />`) become a newline.
 * - Any other `<...>` becomes `tagReplacement`. A `<` with no `>` after it,
 *   and the empty `<>`, are literal text and are kept.
 *
 * Tag-name lists are lower case.
 */
export declare function removeHtmlMarkup(html: string, options: {
    readonly tagReplacement: string;
    readonly commentReplacement: string;
    readonly lineBreakEndTags: readonly string[];
    readonly lineBreakVoidTags: readonly string[];
}): string;