officeparser 4.1.2 → 4.2.0

package/README.md

@@ -13,6 +13,8 @@ A Node.js library to parse text out of any office file.
 
 
 #### Update
+* 2024/10/15 - Fixed erroring out while deleting temp files when multiple worker threads make parallel executions resulting in same file name for multiple files. Fixed erroring out when multiple executions are made without waiting for the previous execution to finish which resulted in deleting the file from other execution. Upgraded dependencies.
+* 2024/10/13 - Fixed parsing text from xlsx files which contain no shared strings file and files which have inlineStr based strings.
 * 2024/05/06 - Replaced pdf parsing support from pdf-parse library to natively building it using pdf.js library from Mozilla by analyzing its output. Added pdfjs-dist build as a local library.
 * 2023/11/25 - Fixed error catching when an error occurs within the parsing of a file, especially after decompressing it. Also fixed the problem with parallel parsing of files as we were using only timestamp in file names.
 * 2023/10/24 - Revamped content parsing code. Fixed order of content in files, especially in word files where table information would always land up at the end of the text. Added config object as argument for parseOffice which can be used to set new line delimiter and multiple other configurations. Added support for parsing pdf files using the popular npm library pdf-parse. Removed support for individual file parsing functions.

package/officeParser.js

@@ -1,11 +1,11 @@
 #!/usr/bin/env node
 
-const decompress    = require('decompress');
-const fs            = require('fs');
-const rimraf        = require('rimraf');
-const fileType      = require('file-type');
-const pdfjs         = require('./pdfjs-dist-build/pdf.js');
-const { DOMParser } = require('@xmldom/xmldom');
+const decompress     = require('decompress');
+const fs             = require('fs');
+const { rimrafSync } = require('rimraf');
+const fileType       = require('file-type');
+const pdfjs          = require('./pdfjs-dist-build/pdf.js');
+const { DOMParser }  = require('@xmldom/xmldom');
 
 /** Header for error messages */
 const ERRORHEADER = "[OfficeParser]: ";
@@ -543,7 +543,7 @@ function parseOffice(file, callback, config = {}) {
         }
 
         // create temp file subdirectory if it does not exist
-        fs.mkdirSync(`${internalConfig.tempFilesLocation}/tempfiles`, { recursive: true });
+        fs.mkdirSync(getTempFilesDirectory(internalConfig.tempFilesLocation), { recursive: true });
 
         // Check if buffer
         if (Buffer.isBuffer(file)) {
@@ -552,11 +552,11 @@ function parseOffice(file, callback, config = {}) {
                 .then(data =>
                 {
                     // temp file name
-                    const newfilepath = getNewFileName(internalConfig.tempFilesLocation, data.ext.toLowerCase());
+                    const newFileName = getNewFileName(data.ext.toLowerCase());
                     // write new file
-                    fs.writeFileSync(newfilepath, file);
+                    fs.writeFileSync(getFilePath(getTempFilesDirectory(internalConfig.tempFilesLocation), newFileName), file);
                     // resolve promise
-                    res(newfilepath);
+                    res(newFileName);
                 })
                 .catch(() => rej(ERRORMSG.improperBuffers));
             return;
@@ -569,16 +569,18 @@ function parseOffice(file, callback, config = {}) {
             throw ERRORMSG.fileDoesNotExist(file);
 
         // temp file name
-        const newfilepath = getNewFileName(internalConfig.tempFilesLocation, file.split(".").pop().toLowerCase());
+        const newFileName = getNewFileName(file.split(".").pop().toLowerCase());
         // Copy the file into a temp location with the temp name
-        fs.copyFileSync(file, newfilepath)
+        fs.copyFileSync(file, getFilePath(getTempFilesDirectory(internalConfig.tempFilesLocation), newFileName))
         // resolve promise
-        res(newfilepath);
+        res(newFileName);
     });
 
     // Process filePreparedPromise resolution.
     filePreparedPromise
-        .then(filepath => {
+        .then(filename => {
+            // The file path
+            const filepath = getFilePath(getTempFilesDirectory(internalConfig.tempFilesLocation), filename);
             // File extension. Already in lowercase when we prepared the temp file above.
             const extension = filepath.split(".").pop();
 
@@ -609,9 +611,33 @@ function parseOffice(file, callback, config = {}) {
             /** Internal callback function that calls the user's callback function passed in argument and removes the temp files if required */
             function internalCallback(data, err) {
                 // Check if we need to preserve unzipped content files or delete them.
-                if (!internalConfig.preserveTempFiles)
-                    // Delete decompress sublocation.
-                    rimraf(internalConfig.tempFilesLocation, rimrafErr => consoleError(rimrafErr, internalConfig.outputErrorToConsole));
+                if (!internalConfig.preserveTempFiles) {
+                    /** Safely delete location */
+                    function safelyDeleteLocation(location, deleteDirIfEmpty) {
+                        if (!fs.existsSync(location))
+                            return;
+
+                        if (!fs.lstatSync(location).isDirectory()       // If not directory
+                            || !deleteDirIfEmpty                        // or if the deleteDirIfEmpty is false or undefined
+                            || fs.readdirSync(location).length == 0) {  // or if it is true, we check if the contents are empty.
+                            try {
+                                rimrafSync(location);
+                            }
+                            catch(rimrafErr) {
+                                consoleError(rimrafErr, internalConfig.outputErrorToConsole);
+                            }
+                        }
+                    }
+
+                    // We delete our file as well as the extracted files inside the office files.
+                    // There is no extraction for pdf files because we don't support any unpacking of it.
+                    // After removing files, we check if the folders containing them are empty.
+                    // If yes, we remove those folders too.
+                    safelyDeleteLocation(filepath);
+                    safelyDeleteLocation(getFilePath(internalConfig.tempFilesLocation, filename));
+                    safelyDeleteLocation(getTempFilesDirectory(internalConfig.tempFilesLocation), true);
+                    safelyDeleteLocation(internalConfig.tempFilesLocation, true);
+                }
 
                 // Check if there is an error. Throw if there is an error.
                 if (err)
@@ -644,21 +670,30 @@ function parseOfficeAsync(file, config = {}) {
 let globalFileNameIterator = 0;
 /**
  * File Name generator that takes the extension as an input and returns a file name that comprises a timestamp and an incrementing number
- * to allow the files to be sorted in chronological order
- * @param {string} tempFilesLocation Directory whether this new file needs to be stored
- * @param {string} ext               File extension for this new generated file name
+ * to allow the files to be sorted in chronological order. We also prefix them with ppid and pid of the process to support
+ * common destination from worker threads as well as multiple processes running them together.
+ * @param {string} ext File extension for this new generated file name
  * @returns {string}
  */
-function getNewFileName(tempFilesLocation, ext) {
+function getNewFileName(ext) {
     // Get the iterator part of the file name
     let iteratorPart = (globalFileNameIterator++).toString().padStart(5, '0');
     // We want the iterator part of the file name to be of 5 digits.
     // Therefore, when the iterator crosses into 6 digits, we reset it to 0.
     if (globalFileNameIterator > 99999)
         globalFileNameIterator = 0;
+    // Return the file name with ppid and pid to allow unique names even with worker threads.
+    return `${process.ppid}_${process.pid}_${new Date().getTime().toString() + iteratorPart}.${ext}`;
+}
+
+/** Gets directory for storing files. */
+function getTempFilesDirectory(root) {
+    return `${root}/tempfiles`;
+}
 
-    // Return the file name
-    return `${tempFilesLocation}/tempfiles/${new Date().getTime().toString() + iteratorPart}.${ext}`;
+/** Gets file path for the supplied directory and the file name. */
+function getFilePath(directory, fileName) {
+    return `${directory}/${fileName}`;
 }
 
 /**

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "officeparser",
-  "version": "4.1.2",
+  "version": "4.2.0",
   "description": "A Node.js library to parse text out of any office file. Currently supports docx, pptx, xlsx, odt, odp, ods, pdf files.",
   "main": "officeParser.js",
   "files": [
@@ -44,10 +44,10 @@
   "homepage": "https://github.com/harshankur/officeParser#readme",
   "dependencies": {
     "@xmldom/xmldom": "^0.8.10",
-    "decompress": "^4.2.0",
+    "decompress": "^4.2.1",
     "file-type": "^16.5.4",
     "node-ensure": "^0.0.0",
-    "rimraf": "^2.6.3"
+    "rimraf": "^5.0.10"
   },
   "devDependencies": {
     "@types/decompress": "^4.2.6",