def custom_justext(tree, stoplist):
'Customized version of JusText processing'
dom = preprocessor(tree) # tree_cleaning(tree, True)
paragraphs = ParagraphMaker.make_paragraphs(dom)
classify_paragraphs(paragraphs, stoplist, 50, 200, 0.1, 0.2, 0.2, True)
revise_paragraph_classification(paragraphs, 200)
return paragraphs
def test_length_low(self):
paragraphs = [
self._paragraph(text="0 1 2 3 4 5 6 7 8 9"*2, chars_count_in_links=0),
self._paragraph(text="0 1 2 3 4 5 6 7 8 9"*2, chars_count_in_links=20),
]
classify_paragraphs(paragraphs, (), max_link_density=1, length_low=1000)
tools.assert_equal(paragraphs[0].cf_class, "short")
tools.assert_equal(paragraphs[1].cf_class, "bad")
def test_stopwords_high(self):
paragraphs = [
self._paragraph(text="0 1 2 3 4 5 6 7 8 9"),
self._paragraph(text="0 1 2 3 4 5 6 7 8 9"*2),
]
classify_paragraphs(paragraphs, ("0",), max_link_density=1, length_low=0,
stopwords_high=0, length_high=20)
tools.assert_equal(paragraphs[0].cf_class, "neargood")
tools.assert_equal(paragraphs[1].cf_class, "good")
def test_stopwords_low(self):
paragraphs = [
self._paragraph(text="0 0 0 0 1 2 3 4 5 6 7 8 9"),
self._paragraph(text="0 1 2 3 4 5 6 7 8 9"),
self._paragraph(text="1 2 3 4 5 6 7 8 9"),
]
classify_paragraphs(paragraphs, ("0", "1",), max_link_density=1,
length_low=0, stopwords_high=1000, stopwords_low=0.2)
tools.assert_equal(paragraphs[0].cf_class, "neargood")
tools.assert_equal(paragraphs[1].cf_class, "neargood")
tools.assert_equal(paragraphs[2].cf_class, "bad")
def html2prevert(s,
justext_wordlist,
justext_level='strict',
allowshort=False):
# TODO: preclean HTML (remove tables, infoboxes, References, TOC, ...)
try:
html_root = justext.preprocess(html_text=s, encoding='utf-8')
paragraphs = justext.make_paragraphs(html_root)
except (ParserError, XMLSyntaxError):
return ('', 0, 0)
#use Justext to classify paragraphs
j_length_low = JUSTEXT_PARAMS_BY_LEVEL[justext_level]['length_low']
j_length_high = JUSTEXT_PARAMS_BY_LEVEL[justext_level]['length_high']
j_max_heading_distance = JUSTEXT_PARAMS_BY_LEVEL[justext_level][
'max_heading_distance']
if allowshort:
j_length_low = j_length_low / 3
j_length_high = j_length_high / 3
j_max_heading_distance = j_max_heading_distance / 3
justext.classify_paragraphs(
paragraphs=paragraphs,
stoplist=justext_wordlist,
length_low=j_length_low, #character count < length_low => bad or short
length_high=j_length_high, #character count > length_high => good
stopwords_low=JUSTEXT_PARAMS_BY_LEVEL[justext_level]
['stopwords_low'], #number of words frequent in the language >= stopwords_low => neargood
stopwords_high=JUSTEXT_PARAMS_BY_LEVEL[justext_level]
['stopwords_high'], #number of words frequent in the language >= stopwords_high => good or neargood
max_link_density=JUSTEXT_PARAMS_BY_LEVEL[justext_level]
['max_link_density'] #density of link words (words inside the <a> tag) > max_link_density => bad
)
justext.revise_paragraph_classification(
paragraphs=paragraphs,
max_heading_distance=
j_max_heading_distance #Short/near-good heads in the distance [chars] before a good par => good
)
#extract good paragraphs
prevert_paragraphs, paragraph_count, plaintext_len = [], 0, 0
for p in paragraphs:
#if p['class'] == 'good': # TODO find why this does not produce a good result
if p['cfclass'] in ('good',
'neargood'): #'good', 'neargood', 'short', 'bad'
p_text = justext.html_escape(p['text']).strip()
if p_text:
paragraph_count += 1
plaintext_len += len(p_text)
heading = ' heading="1"' if p['heading'] else ''
prevert_paragraphs.append('<p%s>\n%s\n</p>' %
(heading, p_text))
return ('\n'.join(prevert_paragraphs), paragraph_count, plaintext_len)
def test_max_link_density(self):
paragraphs = [
self._paragraph(text="0123456789"*2, chars_count_in_links=0),
self._paragraph(text="0123456789"*2, chars_count_in_links=20),
self._paragraph(text="0123456789"*8, chars_count_in_links=40),
self._paragraph(text="0123456789"*8, chars_count_in_links=39),
self._paragraph(text="0123456789"*8, chars_count_in_links=41),
]
classify_paragraphs(paragraphs, (), max_link_density=0.5)
tools.assert_equal(paragraphs[0].cf_class, "short")
tools.assert_equal(paragraphs[1].cf_class, "bad")
tools.assert_equal(paragraphs[2].cf_class, "bad")
tools.assert_equal(paragraphs[3].cf_class, "bad")
tools.assert_equal(paragraphs[4].cf_class, "bad")