b933a75bd436e7ecdb62778f591be3c6b52aa175,textacy/corpus.py,Corpus,add_doc,#Corpus#Any#Any#,218

Before Change

                print("**WARNING: Doc already associated with a Corpus; adding anyway...")
        doc.corpus_index = self.n_docs
        doc.corpus = self
        self.docs.append(doc)
        self.n_docs += 1
        self.n_tokens += doc.n_tokens
        // sentence segmentation requires parse; if not available, just skip this
        try:

After Change

            it will be deep-copied and then added as if a new document. A warning
            message will be logged. This is probably not a thing you should do.
        
        if isinstance(doc, Doc):
            if doc.spacy_vocab is not self.spacy_vocab:
                msg = "Doc.spacy_vocab {} != Corpus.spacy_vocab {}".format(
                    doc.spacy_vocab, self.spacy_vocab)
                raise ValueError(msg)
            if hasattr(doc, "corpus_index"):
                doc = copy.deepcopy(doc)
                // TODO: make this into a logging warning
                print("**WARNING: Doc already associated with a Corpus; adding anyway...")
            if metadata is not None:
                doc.metadata = metadata
            self._add_textacy_doc(doc)
        elif isinstance(doc, SpacyDoc):
            if doc.vocab is not self.spacy_vocab:
                msg = "SpacyDoc.vocab {} != Corpus.spacy_vocab {}".format(
                    doc.vocab, self.spacy_vocab)
                raise ValueError(msg)
            self._add_textacy_doc(
                Doc(doc, lang=self.spacy_lang, metadata=metadata))
        else:
            msg = "`doc` must be {}, not "{}"".format(
                {Doc, SpacyDoc}, type(doc))
            raise ValueError(msg)

    //////////////////////////////////
    // GET DOCUMENTS //

    def get_doc(self, index):
        
        Get a single :class:`textacy.Doc <Doc>` by its position ``index`` in
        the corpus.

Instances