/* auto-generated by NAPI-RS */
/* eslint-disable */
/**
 * Lightweight PDF classification — returns type, page count, and OCR pages.
 * Faster than detectPdf as it skips building the full PdfResult.
 * Pages in pagesNeedingOcr are 0-indexed.
 */
export declare function classifyPdf(buffer: Buffer): PdfClassification

/** Fast detection only — no text extraction or markdown. */
export declare function detectPdf(buffer: Buffer): PdfResult

/**
 * Extract formatted markdown for specific pages of a PDF, with layout
 * classification metadata.
 *
 * Returns per-page markdown and classification data (tables, columns,
 * OCR needs) from a single parse. Font statistics are computed from the
 * full document so header detection is consistent across pages.
 */
export declare function extractPagesMarkdown(buffer: Buffer, pages: Array<number>): PagesExtractionResult

/**
 * Extract markdown tables within bounding-box regions from a PDF.
 *
 * Like `extractTextInRegions` but runs table detection on items within each
 * region and returns markdown pipe-tables instead of flat text.
 *
 * When table structure is detected, `text` contains a markdown pipe-table and
 * `needsOcr` is `false`. When no table is found, `text` is empty and
 * `needsOcr` is `true` so the caller can fall back to GPU OCR.
 *
 * Coordinates are PDF points with top-left origin.
 */
export declare function extractTablesInRegions(buffer: Buffer, pageRegions: Array<PageRegions>): Array<PageRegionTexts>

/** Extract plain text from a PDF Buffer. */
export declare function extractText(buffer: Buffer): string

/**
 * Extract text within bounding-box regions from a PDF.
 *
 * For hybrid OCR: layout model detects regions in rendered images,
 * this extracts PDF text within those regions — skipping GPU OCR
 * for text-based pages.
 *
 * Each region result includes `needsOcr` — set when the extracted text
 * is unreliable (empty, GID-encoded fonts, garbage, encoding issues).
 *
 * Coordinates are PDF points with top-left origin.
 */
export declare function extractTextInRegions(buffer: Buffer, pageRegions: Array<PageRegions>): Array<PageRegionTexts>

/** Extract text with position information from a PDF Buffer. */
export declare function extractTextWithPositions(buffer: Buffer, pages?: Array<number> | undefined | null): Array<TextItem>

/** Type of a positioned text item. */
export declare const enum ItemType {
  Text = 'Text',
  Image = 'Image',
  Link = 'Link',
  FormField = 'FormField'
}

/** Per-page markdown extraction result. */
export interface PageMarkdownResult {
  /** 0-indexed page number. */
  page: number
  /** Formatted markdown for this page. */
  markdown: string
  /** `true` when text on this page is unreliable. */
  needsOcr: boolean
}

/** A page's regions for text extraction: (page_index_0based, bboxes). */
export interface PageRegions {
  page: number
  /** Each bbox is [x1, y1, x2, y2] in PDF points, top-left origin. */
  regions: Array<Array<number>>
}

/** Extracted text for one page's regions. */
export interface PageRegionTexts {
  page: number
  regions: Array<RegionText>
}

/** Combined per-page markdown extraction and layout classification result. */
export interface PagesExtractionResult {
  /** Per-page markdown results. */
  pages: Array<PageMarkdownResult>
  /** 1-indexed pages where tables were detected. */
  pagesWithTables: Array<number>
  /** 1-indexed pages where multi-column layout was detected. */
  pagesWithColumns: Array<number>
  /** 1-indexed pages that need OCR (scanned/image-based). */
  pagesNeedingOcr: Array<number>
  /** True if any page has tables or columns. */
  isComplex: boolean
}

/** Lightweight PDF classification result. */
export interface PdfClassification {
  pdfType: PdfType
  pageCount: number
  /** 0-indexed page numbers that need OCR. */
  pagesNeedingOcr: Array<number>
  confidence: number
}

/** Full PDF processing result with markdown and metadata. */
export interface PdfResult {
  pdfType: PdfType
  markdown?: string
  pageCount: number
  processingTimeMs: number
  /** 1-indexed page numbers that need OCR. */
  pagesNeedingOcr: Array<number>
  title?: string
  confidence: number
  isComplexLayout: boolean
  pagesWithTables: Array<number>
  pagesWithColumns: Array<number>
  hasEncodingIssues: boolean
}

/** PDF document type classification. */
export declare const enum PdfType {
  TextBased = 'TextBased',
  Scanned = 'Scanned',
  ImageBased = 'ImageBased',
  Mixed = 'Mixed'
}

/** Process a PDF from a Buffer: detect type, extract text, and convert to Markdown. */
export declare function processPdf(buffer: Buffer, pages?: Array<number> | undefined | null): PdfResult

/** Extracted text for a single region. */
export interface RegionText {
  text: string
  /** `true` when the text should not be trusted (empty, GID fonts, garbage, encoding issues). */
  needsOcr: boolean
}

/** A positioned text item extracted from a PDF. */
export interface TextItem {
  text: string
  x: number
  y: number
  width: number
  height: number
  font: string
  fontSize: number
  page: number
  isBold: boolean
  isItalic: boolean
  itemType: ItemType
  /** URL for link items, `None` for other types. */
  linkUrl?: string
}