def test_location_method_2(self):
        document = build_document_from_string("""
            # na nb nc ha hb
            ha = 1 + 1 + 0 = 2
            middle = 0
            ha hb = 2 + 1 + 0 = 3

            first = 1
            ha hb ha = 3
            last = 1

            # hc hd
            hb hc hd = 3 + 1 + 0 = 4
            ha hb = 2 + 1 + 0 = 3
        """)

        summarizer = EdmundsonSummarizer()
        summarizer.null_words = ("na", "nb", "nc", "nd", "ne",)

        sentences = summarizer.location_method(document, 4, w_p1=0, w_p2=0)
        self.assertEqual(len(sentences), 4)
        self.assertEqual(to_unicode(sentences[0]), "ha hb = 2 + 1 + 0 = 3")
        self.assertEqual(to_unicode(sentences[1]), "ha hb ha = 3")
        self.assertEqual(to_unicode(sentences[2]), "hb hc hd = 3 + 1 + 0 = 4")
        self.assertEqual(to_unicode(sentences[3]), "ha hb = 2 + 1 + 0 = 3")

    def test_cue_3(self):
        document = build_document(
            (
                "ba "*10,
                "bb "*10,
                " sa"*8 + " bb"*10,
                "bb bc ba",
            ),
            (),
            (
                "babbbc "*10,
                "na nb nc nd sa" + " bc"*10,
                " ba n"*10,
            )
        )

        summarizer = EdmundsonSummarizer()
        summarizer.bonus_words = ("ba", "bb", "bc",)
        summarizer.stigma_words = ("sa", "sb", "sc",)

        sentences = summarizer.cue_method(document, 5)
        self.assertEqual(len(sentences), 5)
        self.assertEqual(to_unicode(sentences[0]), ("ba "*10).strip())
        self.assertEqual(to_unicode(sentences[1]), ("bb "*10).strip())
        self.assertEqual(to_unicode(sentences[2]), "bb bc ba")
        self.assertEqual(to_unicode(sentences[3]),
            "na nb nc nd sa bc bc bc bc bc bc bc bc bc bc")
        self.assertEqual(to_unicode(sentences[4]), ("ba n "*10).strip())

def test_two_sentences():
    document = build_document(("I am that 1. sentence", "And I am 2. winning prize"))
    summarizer = TextRankSummarizer()
    summarizer.stop_words = ("I", "am", "and", "that",)

    returned = summarizer(document, 10)
    assert len(returned) == 2
    assert to_unicode(returned[0]) == "I am that 1. sentence"
    assert to_unicode(returned[1]) == "And I am 2. winning prize"

    def test_two_sentences(self):
        document = build_document(("I am that 1. sentence", "And I am 2. winning prize"))
        summarizer = GraphSummarizer()
        summarizer.stop_words = ("I", "am", "and", "that",)

        returned = summarizer(document, 10)
        self.assertEqual(len(returned), 2)
        self.assertEqual(to_unicode(returned[0]), "I am that 1. sentence")
        self.assertEqual(to_unicode(returned[1]), "And I am 2. winning prize")

    def test_two_sentences(self):
        document = build_document(("Já jsem 1. věta", "A já ta 2. vítězná výhra"))
        summarizer = LuhnSummarizer()
        summarizer.stop_words = ("já", "jsem", "a", "ta",)

        returned = summarizer(document, 10)
        self.assertEqual(len(returned), 2)
        self.assertEqual(to_unicode(returned[0]), "Já jsem 1. věta")
        self.assertEqual(to_unicode(returned[1]), "A já ta 2. vítězná výhra")

    def test_document(self):
        document = build_document(
            ("I am the sentence you like", "Do you like me too",),
            ("This sentence is better than that above", "Are you kidding me",)
        )
        summarizer = LsaSummarizer()
        summarizer.stopwords = ("I", "am", "the", "you", "are", "me", "is", "than", "that", "this",)

        sentences = summarizer(document, 2)
        self.assertEqual(len(sentences), 2)
        self.assertEqual(to_unicode(sentences[0]), "I am the sentence you like")
        self.assertEqual(to_unicode(sentences[1]), "This sentence is better than that above")

    def test_key_2(self):
        document = build_document(
            ("Om nom nom nom nom", "Sure I summarize it, with bonus",),
            ("This is bonus test sentence with some extra words and bonus",)
        )
        summarizer = EdmundsonSummarizer()
        summarizer.bonus_words = ("nom", "bonus",)

        sentences = summarizer.key_method(document, 2)
        self.assertEqual(len(sentences), 2)
        self.assertEqual(to_unicode(sentences[0]), "Om nom nom nom nom")
        self.assertEqual(to_unicode(sentences[1]),
            "This is bonus test sentence with some extra words and bonus")

    def test_sentences_in_right_order(self):
        document = build_document_from_string("""
            # Heading one
            First sentence.
            Second sentence.
            Third sentence.
        """)
        summarizer = RandomSummarizer()

        sentences = summarizer(document, 4)
        self.assertEqual(len(sentences), 3)
        self.assertEqual(to_unicode(sentences[0]), "First sentence.")
        self.assertEqual(to_unicode(sentences[1]), "Second sentence.")
        self.assertEqual(to_unicode(sentences[2]), "Third sentence.")

def test_sentences_in_right_order():
    document = build_document_from_string("""
        # Heading one
        First sentence.
        Second sentence.
        Third sentence.
    """)
    summarizer = RandomSummarizer()

    sentences = summarizer(document, 4)
    assert len(sentences) == 3
    assert to_unicode(sentences[0]) == "First sentence."
    assert to_unicode(sentences[1]) == "Second sentence."
    assert to_unicode(sentences[2]) == "Third sentence."

    def test_key_no_bonus_words_in_document(self):
        document = build_document(
            ("wa wb wc wd", "I like music",),
            ("This is test sentence with some extra words",)
        )
        summarizer = EdmundsonSummarizer()
        summarizer.bonus_words = ("ba", "bb", "bc", "bonus",)

        sentences = summarizer.key_method(document, 10)
        self.assertEqual(len(sentences), 3)
        self.assertEqual(to_unicode(sentences[0]), "wa wb wc wd")
        self.assertEqual(to_unicode(sentences[1]), "I like music")
        self.assertEqual(to_unicode(sentences[2]),
            "This is test sentence with some extra words")

    def test_title_method_without_title(self):
        document = build_document(
            ("This is sentence", "This is another one",),
            ("And some next sentence but no heading",)
        )

        summarizer = EdmundsonSummarizer()
        summarizer.null_words = ("this", "is", "some", "and",)

        sentences = summarizer.title_method(document, 10)
        self.assertEqual(len(sentences), 3)
        self.assertEqual(to_unicode(sentences[0]), "This is sentence")
        self.assertEqual(to_unicode(sentences[1]), "This is another one")
        self.assertEqual(to_unicode(sentences[2]), "And some next sentence but no heading")

    def test_cue_letters_case(self):
        document = build_document(
            ("X X X", "x x x x",),
            ("w w w", "W W W W",)
        )

        summarizer = EdmundsonSummarizer()
        summarizer.bonus_words = ("X", "w",)
        summarizer.stigma_words = ("stigma",)

        sentences = summarizer.cue_method(document, 2)
        self.assertEqual(len(sentences), 2)
        self.assertEqual(to_unicode(sentences[0]), "x x x x")
        self.assertEqual(to_unicode(sentences[1]), "W W W W")

    def test_sentences(self):
        document = build_document_from_string("""
            Nějaký muž šel kolem naší zahrady
            Nějaký jiný muž šel kolem vaší zahrady

            # Nová myšlenka
            Už už abych taky šel
        """)

        self.assertEqual(len(document.sentences), 3)
        self.assertEqual(to_unicode(document.sentences[0]),
            "Nějaký muž šel kolem naší zahrady")
        self.assertEqual(to_unicode(document.sentences[1]),
            "Nějaký jiný muž šel kolem vaší zahrady")
        self.assertEqual(to_unicode(document.sentences[2]),
            "Už už abych taky šel")

def test_single_sentence():
    document = build_document(("I am the sentence you like",))
    summarizer = LsaSummarizer()
    summarizer.stopwords = ("I", "am", "the",)

    sentences = summarizer(document, 10)
    assert len(sentences) == 1
    assert to_unicode(sentences[0]) == "I am the sentence you like"

    def test_single_sentence(self):
        document = build_document(("I am the sentence you like",))
        summarizer = LsaSummarizer()
        summarizer.stopwords = ("I", "am", "the",)

        sentences = summarizer(document, 10)
        self.assertEqual(len(sentences), 1)
        self.assertEqual(to_unicode(sentences[0]), "I am the sentence you like")

def test_less_sentences_than_requested():
    document = build_document_from_string("""
        This is only one sentence.
    """)
    summarizer = RandomSummarizer()

    sentences = summarizer(document, 10)
    assert len(sentences) == 1
    assert to_unicode(sentences[0]) == "This is only one sentence."

    def test_less_sentences_than_requested(self):
        document = build_document_from_string("""
            This is only one sentence.
        """)
        summarizer = RandomSummarizer()

        sentences = summarizer(document, 10)
        self.assertEqual(len(sentences), 1)
        self.assertEqual(to_unicode(sentences[0]), "This is only one sentence.")

def test_annotated_text():
    path = expand_resource_path("snippets/paragraphs.html")
    url = "http://www.snippet.org/paragraphs.html"
    parser = HtmlParser.from_file(path, url, Tokenizer("czech"))

    document = parser.document

    assert len(document.paragraphs) == 2

    assert len(document.paragraphs[0].headings) == 1
    assert len(document.paragraphs[0].sentences) == 1

    assert to_unicode(document.paragraphs[0].headings[0]) == "Toto je nadpis prvej úrovne"
    assert to_unicode(document.paragraphs[0].sentences[0]) == "Toto je prvý odstavec a to je fajn."

    assert len(document.paragraphs[1].headings) == 0
    assert len(document.paragraphs[1].sentences) == 2

    assert to_unicode(document.paragraphs[1].sentences[0]) == "Tento text je tu aby vyplnil prázdne miesto v srdci súboru."
    assert to_unicode(document.paragraphs[1].sentences[1]) == "Aj súbory majú predsa city."

    def test_real_example(self):
        """Source: http://www.prevko.cz/dite/skutecne-pribehy-deti"""
        parser = PlaintextParser.from_string(
            "Jednalo se o případ chlapce v 6. třídě, který měl problémy s učením. "
            "Přerostly až v reparát z jazyka na konci školního roku. "
            "Nedopadl bohužel dobře a tak musel opakovat 6. třídu, což se chlapci ani trochu nelíbilo. "
            "Připadal si, že je mezi malými dětmi a realizoval se tím, že si ve třídě "
            "o rok mladších dětí budoval vedoucí pozici. "
            "Dost razantně. Fyzickou převahu měl, takže to nedalo až tak moc práce.",
            Tokenizer("czech")
        )
        summarizer = LsaSummarizer(stem_word)
        summarizer.stop_words = get_stop_words("czech")

        sentences = summarizer(parser.document, 2)
        self.assertEqual(len(sentences), 2)
        self.assertEqual(to_unicode(sentences[0]),
            "Jednalo se o případ chlapce v 6. třídě, který měl problémy s učením.")
        self.assertEqual(to_unicode(sentences[1]),
            "Nedopadl bohužel dobře a tak musel opakovat 6. třídu, což se chlapci ani trochu nelíbilo.")

    def test_headings(self):
        document = build_document_from_string("""
            Nějaký muž šel kolem naší zahrady
            Nějaký jiný muž šel kolem vaší zahrady

            # Nová myšlenka
            Už už abych taky šel
        """)

        self.assertEqual(len(document.headings), 1)
        self.assertEqual(to_unicode(document.headings[0]), "Nová myšlenka")