public void ReadTextBySlideIndex()
        {
            string           path    = Path.GetFullPath(TestDataSample.GetPowerpointPath("testPPT.pptx"));
            ParserContext    context = new ParserContext(path);
            ISlideshowParser parser  = ParserFactory.CreateSlideshow(context);
            var result = parser.Parse(1);

            Assert.AreEqual(6, result.Texts.Count);
            Assert.AreEqual("This is a test file data with the same content as every other file being tested for ",
                            result.Texts[0]);
            Assert.AreEqual("tika", result.Texts[1]);
            Assert.AreEqual(" content parsing. This has been developed by Rajiv ", result.Texts[2]);
            Assert.AreEqual("Kumar ", result.Texts[3]);
        }
예제 #2
0
        private static string ExtractPptxText(FileInfo file)
        {
            StringBuilder result = new StringBuilder();

            var parser = ParserFactory.CreateSlideshow(new ParserContext(file.FullName));
            var slides = parser.Parse();

            for (int i = 0; i < slides.Slides.Count; i++)
            {
                result.Append(ConcatListstring(slides.Slides[i].Texts));
            }

            return(result.ToString());
        }
예제 #3
0
        public string ExtractText(string filePath, string extension)
        {
            StringBuilder textResult = new StringBuilder("");

            ParserContext    context   = new ParserContext(filePath);
            ISlideshowParser parser    = ParserFactory.CreateSlideshow(context);
            ToxySlideshow    slideshow = parser.Parse();

            foreach (ToxySlide slide in slideshow.Slides)
            {
                foreach (String text in slide.Texts)
                {
                    textResult.Append('.' + text);
                }
            }

            return(textResult.ToString());
        }
        public void ReadTextBasicTest()
        {
            string           path    = Path.GetFullPath(TestDataSample.GetPowerpointPath("testPPT.pptx"));
            ParserContext    context = new ParserContext(path);
            ISlideshowParser parser  = ParserFactory.CreateSlideshow(context);
            var result = parser.Parse();

            Assert.AreEqual(3, result.Slides.Count);
            Assert.AreEqual(2, result.Slides[0].Texts.Count);
            Assert.AreEqual("Attachment Test", result.Slides[0].Texts[0]);
            Assert.AreEqual("Rajiv", result.Slides[0].Texts[1]);
            Assert.AreEqual(6, result.Slides[1].Texts.Count);
            Assert.AreEqual("This is a test file data with the same content as every other file being tested for ",
                            result.Slides[1].Texts[0]);
            Assert.AreEqual("tika", result.Slides[1].Texts[1]);
            Assert.AreEqual("Kumar ", result.Slides[1].Texts[3]);

            Assert.AreEqual(10, result.Slides[2].Texts.Count);
            Assert.AreEqual("Different words to test against", result.Slides[2].Texts[0]);
        }