Exemplo n.º 1
0
        public byte[] ToBytes()
        {
            if (Serialization.Selected == Serialization.Mode.Spacy)
            {
                using (Py.GIL())
                {
                    return(Interop.GetBytes(PyDoc.to_bytes()));
                }
            }
            else
            {
                using var stream = new MemoryStream();

                var settings = new XmlWriterSettings();
                settings.Indent  = true;
                using var writer = XmlWriter.Create(stream, settings);

                WriteXml(writer);
                writer.Flush();
                return(stream.ToArray());
            }
        }
Exemplo n.º 2
0
        public void WriteXml(XmlWriter writer)
        {
            writer.WriteStartElement(Serialization.Prefix, "Doc", Serialization.Namespace);

            var serializationMode = Serialization.Selected;

            if (serializationMode == Serialization.Mode.SpacyAndDotNet)
            {
                using (Py.GIL())
                {
                    var pyObj    = Interop.GetBytes(PyDoc.to_bytes());
                    var pyObjB64 = Convert.ToBase64String(pyObj);
                    writer.WriteElementString("PyObj", Serialization.Namespace, pyObjB64);
                }
            }

            Debug.Assert(serializationMode != Serialization.Mode.Spacy);

            // Using the property is important form the members to be loaded
            writer.WriteElementString("Text", Serialization.Namespace, Text);
            writer.WriteStartElement("Vocab", Serialization.Namespace);
            Vocab.WriteXml(writer);
            writer.WriteEndElement();

            writer.WriteStartElement("Tokens", Serialization.Namespace);
            foreach (var token in Tokens)
            {
                writer.WriteStartElement("Token", Serialization.Namespace);
                token.WriteXml(writer);
                writer.WriteEndElement();
            }

            writer.WriteEndElement();

            writer.WriteStartElement("Sentences", Serialization.Namespace);
            foreach (var sent in Sents)
            {
                writer.WriteStartElement("Sent", Serialization.Namespace);
                sent.WriteXml(writer);
                writer.WriteEndElement();
            }

            writer.WriteEndElement();

            writer.WriteStartElement("NounChunks", Serialization.Namespace);
            foreach (var nounChunk in NounChunks)
            {
                writer.WriteStartElement("NounChunk", Serialization.Namespace);
                nounChunk.WriteXml(writer);
                writer.WriteEndElement();
            }

            writer.WriteEndElement();

            writer.WriteStartElement("Ents", Serialization.Namespace);
            foreach (var ent in Ents)
            {
                writer.WriteStartElement("Ent", Serialization.Namespace);
                ent.WriteXml(writer);
                writer.WriteEndElement();
            }

            writer.WriteEndElement();

            writer.WriteEndElement();
        }