officeparser 3.2.2 → 3.3.0

package/README.md

@@ -12,6 +12,7 @@ A Node.js library to parse text out of any office file.
 
 
 #### Update
+* 2023/04/26 - Added support for file buffers as argument for filepath for parseOffice and parseOfficeAsync
 * 2023/04/07 - Added typings to methods to help with Typescript projects.
 * 2022/12/28 - Added command line method to use officeParser with or without installing it and instantly get parsed content on the console.
 * 2022/12/10 - Fixed memory leak issues, bugs related to parsing open document files and improved error handling.
@@ -62,12 +63,8 @@ officeParser.parseOffice("/path/to/officeFile", function(data, err){
 // promise
 officeParser.parseOfficeAsync("/path/to/officeFile");
 // "data" string in the promise here is the text parsed from the office file passed in the argument above
-.then((data) => {
-    console.log(data)
-})
-.catch(err) => {
-    console.log(err)
-}
+.then((data) => console.log(data))
+.catch((err) => console.error(err))
 
 // async/await
 try {
@@ -78,6 +75,18 @@ try {
     // resolve error
     console.log(err);
 }
+
+// USING FILE BUFFERS
+// instead of file path, you can also pass file buffers of one of the supported files
+// on parseOffice or parseOfficeAsync functions.
+
+// get file buffers
+const fileBuffers = fs.readFileAsync("/path/to/officeFile");
+// get parsed text from officeParser
+// NOTE: Only works with parseOffice. Old functions are not supported.
+officeParser.parseOfficeAsync(fileBuffers);
+.then((data) => console.log(data))
+.catch((err) => console.error(err))
 ```
 
 **Please take note: I have breached convention in placing err as second argument in my callback but please understand that I had to do it to not break other people's existing modules.**
@@ -113,12 +122,8 @@ officeParser.parseOffice("/path/to/officeFile", function(data, err){
 
 // promise
 officeParser.parseOfficeAsync("/path/to/officeFile", false);
-.then((data) => {
-    console.log(data)
-})
-.catch(err) => {
-    console.log(err)
-}
+.then((data) => console.log(data))
+.catch((err) => console.error(err))
 
 // async/await
 try {
@@ -148,9 +153,7 @@ officeParser.parseOfficeAsync("/Users/harsh/Desktop/files/mySlides.pptx");
     var newText = data + "look, I can parse a powerpoint file"
     callSomeOtherFunction(newText);
 })
-.catch(err) => {
-    console.log(err)
-}
+.catch((err) => console.error(err))
 
 // Using relative path for file is also fine
 officeParser.parseOffice("files/myWorkSheet.ods", function(data, err){
@@ -275,36 +278,28 @@ officeParser.parseWordAsync("C:\\files\\myText.docx");
     let newText1 = data1 + "look, I can parse a word file";
     callSomeOtherFunction(newText1);
 })
-.catch(err) => {
-    console.log(err)
-}
+.catch((err) => console.error(err))
 
 officeParser.parsePowerPointAsync("/Users/harsh/Desktop/files/mySlides.pptx");
 .then((data) => {
     let newText2 = data2 + "look, I can parse a powerpoint file";
     callSomeOtherFunction(newText2);
 })
-.catch(err) => {
-    console.log(err)
-}
+.catch((err) => console.error(err))
 
 officeParser.parseExcelAsync("files/myWorkSheet.xlsx");
 .then((data) => {
     let newText3 = data3 + "look, I can parse an excel file";
     callSomeOtherFunction(newText3);
 })
-.catch(err) => {
-    console.log(err)
-}
+.catch((err) => console.error(err))
 
 officeParser.parseOpenOfficeAsync("files/myDocument.odt");
 .then((data) => {
     let newText4 = data4 + "look, I can parse an OpenOffice file";
     callSomeOtherFunction(newText4);
 })
-.catch(err) => {
-    console.log(err)
-}
+.catch((err) => console.error(err))
 
 
 // async/await

package/officeParser.js

@@ -1,9 +1,10 @@
 #!/usr/bin/env node
 
-const decompress = require('decompress');
-const xml2js = require('xml2js')
-const fs = require('fs')
-const rimraf = require('rimraf');
+const decompress            = require('decompress');
+const xml2js                = require('xml2js')
+const fs                    = require('fs')
+const rimraf                = require('rimraf');
+const fileType              = require('file-type');
 
 /** Header for error messages */
 const ERRORHEADER = "[OfficeParser]: ";
@@ -13,7 +14,8 @@ const ERRORMSG = {
     fileCorrupted:        (filename) => `${ERRORHEADER}Your file ${filename} seems to be corrupted. If you are sure it is fine, please create a ticket in Issues on github with the file to reproduce error.`,
     fileDoesNotExist:     (filename) => `${ERRORHEADER}File ${filename} could not be found! Check if the file exists or verify if the relative path to the file is correct from your terminal's location.`,
     locationNotFound:     (location) => `${ERRORHEADER}Entered location ${location} is not valid! Check relative paths and reenter. OfficeParser will use root directory as decompress location.`,
-    improperArguments:                  `${ERRORHEADER}Improper arguments`
+    improperArguments:                  `${ERRORHEADER}Improper arguments`,
+    improperBuffers:                    `${ERRORHEADER}Error occured while reading the file buffers`
 }
 /** Default sublocation for decompressing files under the current directory. */
 const DEFAULTDECOMPRESSSUBLOCATION = "officeDist";
@@ -434,39 +436,82 @@ function parseOpenOffice(filename, callback, deleteOfficeDist = true) {
 
 
 /** Main async function with callback to execute parseOffice for supported files
- * @param {string} filename File path
+ * @param {string | Buffer} file File path or file buffers
  * @param {function} callback Callback function that returns value or error
  * @param {boolean} [deleteOfficeDist=true] Optional: Delete the officeDist directory created while unarchiving the doc file to get its content underneath. By default, we delete those files after we are done reading them.
  * @returns {void}
  */
-function parseOffice(filename, callback, deleteOfficeDist = true) {
-    if (!fs.existsSync(filename)) {
-        consoleError(ERRORMSG.fileDoesNotExist(filename));
-        return callback(undefined, ERRORMSG.fileDoesNotExist(filename));
-    }
-    var extension = filename.split(".").pop().toLowerCase();
-
-    switch(extension)
-    {
-        case "docx":
-            parseWord(filename, (data, err) => callback(data, err), deleteOfficeDist);
-            return;
-        case "pptx":
-            parsePowerPoint(filename, (data, err) => callback(data, err), deleteOfficeDist);
-            return;
-        case "xlsx":
-            parseExcel(filename, (data, err) => callback(data, err), deleteOfficeDist);
-            return;
-        case "odt":
-        case "odp":
-        case "ods":
-            parseOpenOffice(filename, (data, err) => callback(data, err), deleteOfficeDist);
-            return;
-
-        default:
-            consoleError(ERRORMSG.extensionUnsupported(extension));
-            callback(undefined, ERRORMSG.extensionUnsupported(extension));
-    }
+function parseOffice(file, callback, deleteOfficeDist = true) {
+    // filename that is to be filled below depending on file input from argument
+    let filename = "";
+    // Prepare file for processing
+    const filePreparedPromise = new Promise((res, rej) =>
+        {
+            // Check if buffer
+            if (Buffer.isBuffer(file))
+            {
+                // Guess file type from buffer
+                fileType.fromBuffer(file)
+                    .then(data =>
+                    {
+                        // temp file name
+                        filename = `${decompressSubLocation}/tempfiles/${Math.floor(Math.random()*100000000)}.${data.ext}`;
+                        // create directory if it does not exist
+                        fs.mkdirSync(`${decompressSubLocation}/tempfiles`, { recursive: true });
+                        // write new file
+                        fs.writeFileSync(filename, file);
+                        // resolve promise
+                        res();
+                    })
+                    .catch(() => rej());
+                return;
+            }
+
+            // Treat as filepath
+            filename = file;
+            // resolve promise
+            res();
+        })
+
+    // Process filePreparedPromise resolution.
+    filePreparedPromise
+        .then(() =>
+        {
+            // Check if file exists
+            if (!fs.existsSync(filename)) {
+                consoleError(ERRORMSG.fileDoesNotExist(filename));
+                return callback(undefined, ERRORMSG.fileDoesNotExist(filename));
+            }
+            var extension = filename.split(".").pop().toLowerCase();
+
+            // Switch between parsing functions depending on extension.
+            switch(extension)
+            {
+                case "docx":
+                    parseWord(filename, (data, err) => callback(data, err), deleteOfficeDist);
+                    return;
+                case "pptx":
+                    parsePowerPoint(filename, (data, err) => callback(data, err), deleteOfficeDist);
+                    return;
+                case "xlsx":
+                    parseExcel(filename, (data, err) => callback(data, err), deleteOfficeDist);
+                    return;
+                case "odt":
+                case "odp":
+                case "ods":
+                    parseOpenOffice(filename, (data, err) => callback(data, err), deleteOfficeDist);
+                    return;
+        
+                default:
+                    consoleError(ERRORMSG.extensionUnsupported(extension));
+                    callback(undefined, ERRORMSG.extensionUnsupported(extension));
+            }
+        })
+        .catch(() =>
+        {
+            consoleError(ERRORMSG.improperBuffers);
+            callback(undefined, ERRORMSG.improperBuffers);
+        })
 }
 
 /**
@@ -585,14 +630,14 @@ var parseOpenOfficeAsync = function (filename, deleteOfficeDist = true) {
 
 /**
  * Main async function that can be used with await to execute parseOffice. Or it can be used with promises.
- * @param {string} filename File path
+ * @param {string | Buffer} file File path or file buffers
  * @param {boolean} [deleteOfficeDist=true] Optional: Delete the officeDist directory created while unarchiving the doc file to get its content underneath. By default, we delete those files after we are done reading them.
  * @returns {Promise<string>}
  */
-var parseOfficeAsync = function (filename, deleteOfficeDist = true) {
+var parseOfficeAsync = function (file, deleteOfficeDist = true) {
     return new Promise((resolve, reject) => {
         try {
-            parseOffice(filename, function (data, err) {
+            parseOffice(file, function (data, err) {
                 if (err)
                     return reject(err);
                 return resolve(data);

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "officeparser",
-  "version": "3.2.2",
+  "version": "3.3.0",
   "description": "A Node.js library to parse text out of any office file. Currently supports docx, pptx, xlsx, odt, odp and ods files.",
   "main": "officeParser.js",
   "files": [
@@ -42,10 +42,12 @@
   "homepage": "https://github.com/harshankur/officeParser#readme",
   "dependencies": {
     "decompress": "^4.2.0",
+    "file-type": "^16.5.4",
     "rimraf": "^2.6.3",
     "xml2js": "^0.5.0"
   },
   "devDependencies": {
+    "@types/node": "^18.16.1",
     "typescript": "^5.0.3"
   }
-}
+}

package/typings/officeParser.d.ts

@@ -28,12 +28,12 @@ export function parseExcel(filename: string, callback: Function, deleteOfficeDis
  */
 export function parseOpenOffice(filename: string, callback: Function, deleteOfficeDist?: boolean): void;
 /** Main async function with callback to execute parseOffice for supported files
- * @param {string} filename File path
+ * @param {string | Buffer} file File path or file buffers
  * @param {function} callback Callback function that returns value or error
  * @param {boolean} [deleteOfficeDist=true] Optional: Delete the officeDist directory created while unarchiving the doc file to get its content underneath. By default, we delete those files after we are done reading them.
  * @returns {void}
  */
-export function parseOffice(filename: string, callback: Function, deleteOfficeDist?: boolean): void;
+export function parseOffice(file: string | Buffer, callback: Function, deleteOfficeDist?: boolean): void;
 /** Async function that can be used with await to execute parseWord. Or it can be used with promises.
  * @param {string} filename File path
  * @param {boolean} [deleteOfficeDist=true] Optional: Delete the officeDist directory created while unarchiving the doc file to get its content underneath. By default, we delete those files after we are done reading them.
@@ -60,11 +60,11 @@ export function parseExcelAsync(filename: string, deleteOfficeDist?: boolean): P
 export function parseOpenOfficeAsync(filename: string, deleteOfficeDist?: boolean): Promise<string>;
 /**
  * Main async function that can be used with await to execute parseOffice. Or it can be used with promises.
- * @param {string} filename File path
+ * @param {string | Buffer} file File path or file buffers
  * @param {boolean} [deleteOfficeDist=true] Optional: Delete the officeDist directory created while unarchiving the doc file to get its content underneath. By default, we delete those files after we are done reading them.
  * @returns {Promise<string>}
  */
-export function parseOfficeAsync(filename: string, deleteOfficeDist?: boolean): Promise<string>;
+export function parseOfficeAsync(file: string | Buffer, deleteOfficeDist?: boolean): Promise<string>;
 /**
  * Set decompression directory. The final decompressed data will be put inside officeDist folder within your directory
  * @param {string} newLocation Relative path to the directory that will contain officeDist folder with decompressed data