Python highlight.SentenceFragmenter方法代码示例

# 需要导入模块: from whoosh import highlight [as 别名]
# 或者: from whoosh.highlight import SentenceFragmenter [as 别名]
def test_highlight_ngrams():
    schema = fields.Schema(text=fields.NGRAMWORDS(stored=True))
    ix = RamStorage().create_index(schema)
    with ix.writer() as w:
        w.add_document(text=u("Multiplication and subtraction are good"))

    with ix.searcher() as s:
        qp = qparser.QueryParser("text", ix.schema)
        q = qp.parse(u("multiplication"))
        r = s.search(q)
        assert r.scored_length() == 1

        r.fragmenter = highlight.SentenceFragmenter()
        r.formatter = highlight.UppercaseFormatter()
        snippet = r[0].highlights("text")
        assert snippet == "MULTIPLICATIon and subtracTION are good" 

# 需要导入模块: from whoosh import highlight [as 别名]
# 或者: from whoosh.highlight import SentenceFragmenter [as 别名]
def test_snippets():
    ana = analysis.StemmingAnalyzer()
    schema = fields.Schema(text=fields.TEXT(stored=True, analyzer=ana))
    ix = RamStorage().create_index(schema)
    w = ix.writer()
    w.add_document(text=u("Lay out the rough animation by creating the important poses where they occur on the timeline."))
    w.add_document(text=u("Set key frames on everything that's key-able. This is for control and predictability: you don't want to accidentally leave something un-keyed. This is also much faster than selecting the parameters to key."))
    w.add_document(text=u("Use constant (straight) or sometimes linear transitions between keyframes in the channel editor. This makes the character jump between poses."))
    w.add_document(text=u("Keying everything gives quick, immediate results. But it can become difficult to tweak the animation later, especially for complex characters."))
    w.add_document(text=u("Copy the current pose to create the next one: pose the character, key everything, then copy the keyframe in the playbar to another frame, and key everything at that frame."))
    w.commit()

    target = ["Set KEY frames on everything that's KEY-able",
              "Copy the current pose to create the next one: pose the character, KEY everything, then copy the keyframe in the playbar to another frame, and KEY everything at that frame",
              "KEYING everything gives quick, immediate results"]

    with ix.searcher() as s:
        qp = qparser.QueryParser("text", ix.schema)
        q = qp.parse(u("key"))
        r = s.search(q, terms=True)
        r.fragmenter = highlight.SentenceFragmenter()
        r.formatter = highlight.UppercaseFormatter()

        assert sorted([hit.highlights("text", top=1) for hit in r]) == sorted(target) 

# 需要导入模块: from whoosh import highlight [as 别名]
# 或者: from whoosh.highlight import SentenceFragmenter [as 别名]
def search(ix, text):
	with ix.searcher() as searcher:
		qp = QueryParser("body", schema=ix.schema)
		q = qp.parse(text)

		search_hits = searcher.search(q, limit=None, terms=True)
		search_hits.fragmenter = highlight.SentenceFragmenter(maxchars=450)

		res = []
		for hit in search_hits:
			tmp = dict(hit)
			tmp['matching_terms'] = [x[1] for x in hit.matched_terms()]
			tmp['highlights'] = hit.highlights("body")
			res.append(tmp)

	return {"hits": res, "matched_terms": [x[1] for x in search_hits.matched_terms()]} 

# 需要导入模块: from whoosh import highlight [as 别名]
# 或者: from whoosh.highlight import SentenceFragmenter [as 别名]
def highlights(self, fieldname, text=None, top=3, minscore=1):
        """Returns highlighted snippets from the given field::

            r = searcher.search(myquery)
            for hit in r:
                print(hit["title"])
                print(hit.highlights("content"))

        See :doc:`/highlight`.

        To change the fragmeter, formatter, order, or scorer used in
        highlighting, you can set attributes on the results object::

            from whoosh import highlight

            results = searcher.search(myquery, terms=True)
            results.fragmenter = highlight.SentenceFragmenter()

        ...or use a custom :class:`whoosh.highlight.Highlighter` object::

            hl = highlight.Highlighter(fragmenter=sf)
            results.highlighter = hl

        :param fieldname: the name of the field you want to highlight.
        :param text: by default, the method will attempt to load the contents
            of the field from the stored fields for the document. If the field
            you want to highlight isn't stored in the index, but you have
            access to the text another way (for example, loading from a file or
            a database), you can supply it using the ``text`` parameter.
        :param top: the maximum number of fragments to return.
        :param minscore: the minimum score for fragments to appear in the
            highlights.
        """

        hliter = self.results.highlighter
        return hliter.highlight_hit(self, fieldname, text=text, top=top,
                                    minscore=minscore) 

# 需要导入模块: from whoosh import highlight [as 别名]
# 或者: from whoosh.highlight import SentenceFragmenter [as 别名]
def test_sentence_fragment():
    text = u("This is the first sentence. This one doesn't have the word. " +
             "This sentence is the second. Third sentence here.")
    terms = ("sentence",)
    sa = analysis.StandardAnalyzer(stoplist=None)
    sf = highlight.SentenceFragmenter()
    uc = highlight.UppercaseFormatter()
    htext = highlight.highlight(text, terms, sa, sf, uc)
    assert htext == "This is the first SENTENCE...This SENTENCE is the second...Third SENTENCE here"