Esempio n. 1
0
        /// <summary>
        /// Provides the means to extract the text to be indexed from the file specified
        /// </summary>
        /// <param name="file"></param>
        /// <returns></returns>
        protected virtual string ExtractTextFromFile(FileInfo file)
        {
            var pdf = new PDFParser();

            Action <Exception> onError = (e) => OnIndexingError(new IndexingErrorEventArgs("Could not read PDF", -1, e));

            var txt = pdf.GetTextFromAllPages(file.FullName, onError);

            return(txt);
        }
Esempio n. 2
0
        /// <summary>
        /// Provides the means to extract the text to be indexed from the file specified
        /// </summary>
        /// <param name="file"></param>
        /// <returns></returns>
        protected virtual string ExtractTextFromFile(FileInfo file)
        {
            if (!SupportedExtensions.Select(x => x.ToUpper()).Contains(file.Extension.ToUpper()))
            {
                throw new NotSupportedException("The file with the extension specified is not supported");
            }

            var pdf = new PDFParser();

            Action <Exception> onError = (e) => OnIndexingError(new IndexingErrorEventArgs("Could not read PDF", -1, e));

            var txt = pdf.GetTextFromAllPages(file.FullName, onError);

            return(txt);
        }
Esempio n. 3
0
        /// <summary>
        /// Provides the means to extract the text to be indexed from the file specified
        /// </summary>
        /// <param name="filePath"></param>
        /// <param name="mediaFileSystem"></param>
        /// <returns></returns>
        protected virtual string ExtractTextFromFile(string filePath, MediaFileSystem mediaFileSystem)
        {
            var fileExtension = mediaFileSystem.GetExtension(filePath);

            if (!SupportedExtensions.Select(x => x.ToUpper()).Contains(fileExtension.ToUpper()))
            {
                throw new NotSupportedException("The file with the extension specified is not supported");
            }

            var pdf = new PDFParser();

            Action <Exception> onError = (e) => OnIndexingError(new IndexingErrorEventArgs("Could not read PDF", -1, e));

            var txt = pdf.GetTextFromAllPages(filePath, mediaFileSystem, onError);

            return(txt);
        }
Esempio n. 4
0
        /// <summary>
        /// Provides the means to extract the text to be indexed from the file specified
        /// </summary>
        /// <param name="file"></param>
        /// <returns></returns>
        protected virtual string ExtractTextFromFile(FileInfo file)
        {
            if (!SupportedExtensions.Select(x => x.ToUpper()).Contains(file.Extension.ToUpper()))
            {
                throw new NotSupportedException("The file with the extension specified is not supported");
            }

            var pdf = new PDFParser();

            Action<Exception> onError = (e) => OnIndexingError(new IndexingErrorEventArgs("Could not read PDF", -1, e));

            var txt = pdf.GetTextFromAllPages(file.FullName, onError);
            return txt;

        }