Python highlight.HtmlFormatter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 HtmlFormatter [as 别名]
def test_html_format():
    terms = frozenset(("bravo", "india"))
    sa = analysis.StandardAnalyzer()
    cf = highlight.ContextFragmenter(surround=6)
    hf = highlight.HtmlFormatter()
    htext = highlight.highlight(_doc, terms, sa, cf, hf)
    assert htext == 'alfa <strong class="match term0">bravo</strong> charlie...hotel <strong class="match term1">india</strong> juliet' 

# 需要导入模块: from whoosh import highlight [as 别名]
# 或者: from whoosh.highlight import HtmlFormatter [as 别名]
def test_html_escape():
    terms = frozenset(["bravo"])
    sa = analysis.StandardAnalyzer()
    wf = highlight.WholeFragmenter()
    hf = highlight.HtmlFormatter()
    htext = highlight.highlight(u('alfa <bravo "charlie"> delta'), terms, sa,
                                wf, hf)
    assert htext == 'alfa &lt;<strong class="match term0">bravo</strong> "charlie"&gt; delta' 

# 需要导入模块: from whoosh import highlight [as 别名]
# 或者: from whoosh.highlight import HtmlFormatter [as 别名]
def test_maxclasses():
    terms = frozenset(("alfa", "bravo", "charlie", "delta", "echo"))
    sa = analysis.StandardAnalyzer()
    cf = highlight.ContextFragmenter(surround=6)
    hf = highlight.HtmlFormatter(tagname="b", termclass="t", maxclasses=2)
    htext = highlight.highlight(_doc, terms, sa, cf, hf)
    assert htext == '<b class="match t0">alfa</b> <b class="match t1">bravo</b> <b class="match t0">charlie</b>...<b class="match t1">delta</b> <b class="match t0">echo</b> foxtrot' 

# 需要导入模块: from whoosh import highlight [as 别名]
# 或者: from whoosh.highlight import HtmlFormatter [as 别名]
def test_query_highlight():
    qp = QueryParser("a", None)
    hf = highlight.HtmlFormatter()

    def do(text, terms):
        q = qp.parse(text)
        tks = [tk for tk in q.all_tokens() if tk.text in terms]
        for tk in tks:
            if tk.startchar is None or tk.endchar is None:
                assert False, tk
        fragment = highlight.Fragment(text, tks)
        return hf.format_fragment(fragment)

    assert do("a b c d", ["b"]) == 'a <strong class="match term0">b</strong> c d'
    assert do('a (x:b OR y:"c d") e', ("b", "c")) == 'a (x:<strong class="match term0">b</strong> OR y:"<strong class="match term1">c</strong> d") e' 

# 需要导入模块: from whoosh import highlight [as 别名]
# 或者: from whoosh.highlight import HtmlFormatter [as 别名]
def test_correct_query():
    schema = fields.Schema(a=fields.TEXT(spelling=True), b=fields.TEXT)
    ix = RamStorage().create_index(schema)
    w = ix.writer()
    w.add_document(a=u("alfa bravo charlie delta"))
    w.add_document(a=u("delta echo foxtrot golf"))
    w.add_document(a=u("golf hotel india juliet"))
    w.add_document(a=u("juliet kilo lima mike"))
    w.commit()

    s = ix.searcher()
    qp = QueryParser("a", ix.schema)
    qtext = u('alpha ("brovo november" OR b:dolta) detail')
    q = qp.parse(qtext, ix.schema)

    c = s.correct_query(q, qtext)
    assert c.query.__unicode__() == '(a:alfa AND (a:"bravo november" OR b:dolta) AND a:detail)'
    assert c.string == 'alfa ("bravo november" OR b:dolta) detail'

    qtext = u('alpha b:("brovo november" a:delta) detail')
    q = qp.parse(qtext, ix.schema)
    c = s.correct_query(q, qtext)
    assert c.query.__unicode__() == '(a:alfa AND b:"brovo november" AND a:delta AND a:detail)'
    assert c.string == 'alfa b:("brovo november" a:delta) detail'

    hf = highlight.HtmlFormatter(classname="c")
    assert c.format_string(hf) == '<strong class="c term0">alfa</strong> b:("brovo november" a:delta) detail' 

# 需要导入模块: from whoosh import highlight [as 别名]
# 或者: from whoosh.highlight import HtmlFormatter [as 别名]
def highlight(self, text, words):
        fragmenter = ContextFragmenter()
        formatter = HtmlFormatter()
        analyzer = self.project_schema['text'].analyzer
        return highlight(text, words, analyzer, fragmenter, formatter, top=1)