@truto/truto-jsonata 1.0.15 → 1.0.17

package/dist/module.js

@@ -1,5 +1,5 @@
 import $hgUW1$jsonata from "jsonata";
-import {difference as $hgUW1$difference, groupBy as $hgUW1$groupBy, castArray as $hgUW1$castArray, keyBy as $hgUW1$keyBy, pick as $hgUW1$pick, omit as $hgUW1$omit, compact as $hgUW1$compact, join as $hgUW1$join, orderBy as $hgUW1$orderBy, find as $hgUW1$find, filter as $hgUW1$filter, values as $hgUW1$values, chunk as $hgUW1$chunk, reduce as $hgUW1$reduce, each as $hgUW1$each, get as $hgUW1$get, isEmpty as $hgUW1$isEmpty, concat as $hgUW1$concat, isEqual as $hgUW1$isEqual, flatMap as $hgUW1$flatMap, map as $hgUW1$map, flattenDeep as $hgUW1$flattenDeep, set as $hgUW1$set, isString as $hgUW1$isString, sortBy as $hgUW1$sortBy, repeat as $hgUW1$repeat, flatten as $hgUW1$flatten, reject as $hgUW1$reject, isNil as $hgUW1$isNil, isFunction as $hgUW1$isFunction, toNumber as $hgUW1$toNumber, includes as $hgUW1$includes} from "lodash-es";
+import {difference as $hgUW1$difference, groupBy as $hgUW1$groupBy, castArray as $hgUW1$castArray, keyBy as $hgUW1$keyBy, pick as $hgUW1$pick, omit as $hgUW1$omit, compact as $hgUW1$compact, join as $hgUW1$join, orderBy as $hgUW1$orderBy, find as $hgUW1$find, filter as $hgUW1$filter, values as $hgUW1$values, chunk as $hgUW1$chunk, reduce as $hgUW1$reduce, each as $hgUW1$each, get as $hgUW1$get, isEmpty as $hgUW1$isEmpty, concat as $hgUW1$concat, isEqual as $hgUW1$isEqual, flatMap as $hgUW1$flatMap, map as $hgUW1$map, flattenDeep as $hgUW1$flattenDeep, set as $hgUW1$set, isString as $hgUW1$isString, sortBy as $hgUW1$sortBy, repeat as $hgUW1$repeat, flatten as $hgUW1$flatten, reject as $hgUW1$reject, isNil as $hgUW1$isNil, isFunction as $hgUW1$isFunction, toNumber as $hgUW1$toNumber, includes as $hgUW1$includes, isPlainObject as $hgUW1$isPlainObject, isArray as $hgUW1$isArray, toString as $hgUW1$toString} from "lodash-es";
 import {DateTime as $hgUW1$DateTime} from "luxon";
 import {Lexer as $hgUW1$Lexer, marked as $hgUW1$marked} from "marked";
 import {diceCoefficient as $hgUW1$diceCoefficient} from "dice-coefficient";
@@ -14,6 +14,7 @@ import $hgUW1$pretry from "p-retry";
 import {Buffer as $hgUW1$Buffer} from "buffer";
 import {parseOfficeAsync as $hgUW1$parseOfficeAsync} from "officeparser";
 import {resolvePDFJS as $hgUW1$resolvePDFJS} from "pdfjs-serverless";
+import {read as $hgUW1$read, utils as $hgUW1$utils} from "xlsx";
 import {RecursiveCharacterTextSplitter as $hgUW1$RecursiveCharacterTextSplitter} from "@langchain/textsplitters";
 
 function $parcel$interopDefault(a) {
@@ -1439,6 +1440,7 @@ var $65fc862361d7fe06$export$2e2bcd8739ae039 = $65fc862361d7fe06$var$bufferToStr
 
 
 
+
 var $f29f00a7536a3143$require$Buffer = $hgUW1$Buffer;
 async function $f29f00a7536a3143$var$parsePdf(buffer) {
     const data = buffer.buffer.slice(buffer?.byteOffset, buffer?.byteOffset + buffer?.byteLength);
@@ -1470,13 +1472,30 @@ async function $f29f00a7536a3143$var$parseDocument(file, fileType) {
         for await (const chunk of file)chunks.push($f29f00a7536a3143$require$Buffer.from(chunk));
         buffer = $f29f00a7536a3143$require$Buffer.concat(chunks);
     }
+    if ((0, $hgUW1$includes)([
+        "application/vnd.ms-excel",
+        "application/vnd.openxmlformats-officedocument.spreadsheetml.sheet"
+    ], fileType)) {
+        const workbook = $hgUW1$read(buffer, {
+            type: "buffer"
+        });
+        const allData = workbook.SheetNames.flatMap((sheetName)=>{
+            const sheetData = $hgUW1$utils.sheet_to_json(workbook.Sheets[sheetName]);
+            return sheetData.map((record)=>{
+                const newRecord = {
+                    sheetName: sheetName
+                };
+                return Object.assign(newRecord, record);
+            });
+        });
+        return allData;
+    }
     if ((0, $hgUW1$includes)([
         "application/vnd.openxmlformats-officedocument.wordprocessingml.document",
         "application/vnd.openxmlformats-officedocument.presentationml.presentation",
-        "application/vnd.openxmlformats-officedocument.spreadsheetml.sheet",
         "application/vnd.oasis.opendocument.text",
-        "application/vnd.oasis.opendocument.presentation",
-        "application/vnd.oasis.opendocument.spreadsheet"
+        "application/vnd.oasis.opendocument.spreadsheet",
+        "application/vnd.oasis.opendocument.presentation"
     ], fileType)) return await (0, $hgUW1$parseOfficeAsync)(buffer);
     if (fileType === "application/pdf") return await $f29f00a7536a3143$var$parsePdf(buffer);
     return (0, $65fc862361d7fe06$export$2e2bcd8739ae039)(buffer, "utf-8");
@@ -1485,12 +1504,17 @@ var $f29f00a7536a3143$export$2e2bcd8739ae039 = $f29f00a7536a3143$var$parseDocume
 
 
 
-function $a12871c9a32cbf3b$export$e600492876ee595b(text, options = {
+
+async function $a12871c9a32cbf3b$export$e600492876ee595b(text, options = {
     chunkSize: 200,
     chunkOverlap: 60
 }) {
+    let textToSplit;
+    if ((0, $hgUW1$isString)(text)) textToSplit = text;
+    else if ((0, $hgUW1$isPlainObject)(text) || (0, $hgUW1$isArray)(text)) textToSplit = JSON.stringify(text, null, 2);
+    else textToSplit = (0, $hgUW1$toString)(text);
     const splitter = new (0, $hgUW1$RecursiveCharacterTextSplitter)(options);
-    return splitter.splitText(text);
+    return splitter.splitText(textToSplit);
 }