@docling/docling-core/dist/index.cjs

TypeScript definitions and functions for using Docling output.

"use strict";
var __defProp = Object.defineProperty;
var __getOwnPropDesc = Object.getOwnPropertyDescriptor;
var __getOwnPropNames = Object.getOwnPropertyNames;
var __hasOwnProp = Object.prototype.hasOwnProperty;
var __export = (target, all) => {
  for (var name in all)
    __defProp(target, name, { get: all[name], enumerable: true });
};
var __copyProps = (to, from, except, desc) => {
  if (from && typeof from === "object" || typeof from === "function") {
    for (let key of __getOwnPropNames(from))
      if (!__hasOwnProp.call(to, key) && key !== except)
        __defProp(to, key, { get: () => from[key], enumerable: !(desc = __getOwnPropDesc(from, key)) || desc.enumerable });
  }
  return to;
};
var __toCommonJS = (mod) => __copyProps(__defProp({}, "__esModule", { value: true }), mod);

// src/index.ts
var index_exports = {};
__export(index_exports, {
  isDocling: () => isDocling,
  isDoclingDocItem: () => isDoclingDocItem,
  iterateDocumentItems: () => iterateDocumentItems,
  resolveDocumentItem: () => resolveDocumentItem
});
module.exports = __toCommonJS(index_exports);

// src/types/typing.ts
function isByLabel(...labels) {
  return function(item) {
    return isDocling.DocItem(item) && labels.includes(item.label);
  };
}
var isDoclingDocItem = {
  CodeItem: isByLabel("code"),
  ListItem: isByLabel("list_item"),
  PictureItem: isByLabel("picture"),
  SectionHeaderItem: isByLabel("section_header"),
  TableItem: isByLabel("document_index", "table"),
  TextItem: isByLabel(
    "caption",
    "checkbox_selected",
    "checkbox_unselected",
    "footnote",
    "page_footer",
    "page_header",
    "paragraph",
    "reference",
    "text"
  )
};
var isDocling = {
  Document(item) {
    return "schema_name" in item && item.schema_name === "DoclingDocument";
  },
  NodeItem(item) {
    return "self_ref" in item;
  },
  GroupItem(item) {
    return isDocling.NodeItem(item) && (item.self_ref.startsWith("#/groups/") || item.self_ref === "#/body");
  },
  DocItem(item) {
    return isDocling.NodeItem(item) && !isDocling.GroupItem(item);
  },
  ...isDoclingDocItem
};

// src/index.ts
function* iterateDocumentItems(doc, options = {}) {
  if (doc) {
    yield* traverse(options.root ?? doc.body);
  }
  function* traverse(item, level = 0) {
    if (!isDocling.GroupItem(item) || options.withGroups) {
      if (isDocling.DocItem(item)) {
        if (options.pageNo === void 0 || item.prov?.some((prov) => prov.page_no === options.pageNo)) {
          yield [item, level];
        }
      } else {
        yield [item, level];
      }
    }
    if (isDocling.PictureItem(item) && !options.traversePictures) {
      return;
    }
    for (const childRef of item.children ?? []) {
      const child = resolveDocumentItem(doc, childRef);
      if (isDocling.NodeItem(child)) {
        yield* traverse(child, level + 1);
      }
    }
  }
}
function resolveDocumentItem(doc, item) {
  const parts = item.$ref.split("/").slice(1);
  return parts.reduce(
    (item2, p) => item2[p],
    doc
  );
}
// Annotate the CommonJS export names for ESM import in node:
0 && (module.exports = {
  isDocling,
  isDoclingDocItem,
  iterateDocumentItems,
  resolveDocumentItem
});