Add escape of the path for the tesseract command. Closes #18

dbashford · Mar 29, 2014 · 5141365 · 5141365
1 parent a72f3d4
commit 5141365
Showing 1 changed file with 7 additions and 3 deletions.
diff --git a/lib/extractors/images.js b/lib/extractors/images.js
@@ -27,7 +27,11 @@ var extractText = function( filePath, options, cb ) {
     }
   }
 
-  exec( "tesseract " + filePath + " " + fileTempOutPath + " quiet",
+  // escape the paths for the tesseract command
+  var escapedFilePath = filePath.replace(/\s/g, '\\ ');
+  var escapedFileTempOutPath = fileTempOutPath.replace(/\s/g, '\\ ');
+
+  exec( "tesseract " + escapedFilePath + " " + escapedFileTempOutPath + " quiet",
     execOptions,
     function ( error, stdout, stderr ) {
       if ( error !== null ) {
@@ -40,7 +44,7 @@ var extractText = function( filePath, options, cb ) {
         if ( exists ) {
           fs.readFile(fileTempOutPath + ".txt", function( error, text ) {
             if (error) {
-              error = new Error( "Error reading tesseract output at [[ " + filePath + " ]], error: " + error );
+              error = new Error( "Error reading tesseract output at [[ " + fileTempOutPath + " ]], error: " + error );
               cb( error, null );
             } else {
               fs.unlink(fileTempOutPath + ".txt", function(error) {
@@ -54,7 +58,7 @@ var extractText = function( filePath, options, cb ) {
             }
           });
         } else {
-          error = new Error( "Error reading tesseract output at [[ " + filePath + " ]], file does not exist" );
+          error = new Error( "Error reading tesseract output at [[ " + fileTempOutPath + " ]], file does not exist" );
           cb( error, null );
         }
       });