def _add_code_ref(self, index, code_ref_element, page, load,
s_code_references):
text = self.xcoderef.get_text(code_ref_element)
text = clean_breaks(text).strip()
# Not significant
if len(text) < 2 or text.isdigit():
return
text_context = get_text_context(code_ref_element)
sentence = get_sentence(code_ref_element, text, text_context)
(text, kind_hint) = self._get_code_ref_kind(code_ref_element, text)
xpath = load.tree.getpath(code_ref_element)
for code in parse_single_code_references(text, kind_hint,
self.kind_strategies, self.kinds):
code.xpath = xpath
code.file_path = page.file_path
code.source = DOCUMENT_SOURCE
code.index = index
code.sentence = sentence
code.paragraph = text_context
code.project = self.document.project_release.project
code.project_release = self.document.project_release
code.save()
s_code_references.append(code)
def _add_code_ref(self, index, code_ref_element, page, load,
s_code_references):
text = self.xcoderef.get_text(code_ref_element)
text = clean_breaks(text).strip()
# Not significant
if len(text) < 2 or text.isdigit():
return
text_context = get_text_context(code_ref_element)
sentence = get_sentence(code_ref_element, text, text_context)
(text, kind_hint) = self._get_code_ref_kind(code_ref_element, text)
xpath = load.tree.getpath(code_ref_element)
for code in parse_single_code_references(text, kind_hint,
self.kind_strategies,
self.kinds):
code.xpath = xpath
code.file_path = page.file_path
code.source = DOCUMENT_SOURCE
code.index = index
code.sentence = sentence
code.paragraph = text_context
code.project = self.document.project_release.project
code.project_release = self.document.project_release
code.save()
s_code_references.append(code)
def test_get_text_context(self):
encoding = cc.get_encoding(page_test2)
parser = etree.HTMLParser(remove_comments=True, encoding=encoding)
tree = etree.fromstring(page_test2, parser).getroottree()
eu.clean_tree(tree)
tt = tree.xpath("//tt[1]")[0]
text_context = eu.get_text_context(tt)
self.assertEqual("Hello World foobar. This is nice. Yo.", text_context)
def test_get_text_context(self):
encoding = cc.get_encoding(page_test2)
parser = etree.HTMLParser(remove_comments=True, encoding=encoding)
tree = etree.fromstring(page_test2, parser).getroottree()
eu.clean_tree(tree)
tt = tree.xpath('//tt[1]')[0]
text_context = eu.get_text_context(tt)
self.assertEqual('Hello World foobar. This is nice. Yo.', text_context)
def test_get_sentence(self):
encoding = cc.get_encoding(page_test2)
parser = etree.HTMLParser(remove_comments=True, encoding=encoding)
tree = etree.fromstring(page_test2, parser).getroottree()
eu.clean_tree(tree)
tt = tree.xpath("//tt[1]")[0]
text_context = eu.get_text_context(tt)
sentence = eu.get_sentence(tt, "foobar", text_context)
self.assertEqual("Hello World foobar.", sentence)
# Test when there are more than one match!
code = tree.xpath("//code[2]")[0]
text_context = eu.get_text_context(code)
sentence = eu.get_sentence(code, "foo", text_context)
self.assertEqual("This is foo.", sentence)
# Test when there are more than one match, but wrong markup (sorry...)
b = tree.xpath("//b[1]")[0]
text_context = eu.get_text_context(b)
sentence = eu.get_sentence(b, "foo", text_context)
self.assertEqual("Hello World foo.", sentence)
def test_get_sentence(self):
encoding = cc.get_encoding(page_test2)
parser = etree.HTMLParser(remove_comments=True, encoding=encoding)
tree = etree.fromstring(page_test2, parser).getroottree()
eu.clean_tree(tree)
tt = tree.xpath('//tt[1]')[0]
text_context = eu.get_text_context(tt)
sentence = eu.get_sentence(tt, 'foobar', text_context)
self.assertEqual('Hello World foobar.', sentence)
# Test when there are more than one match!
code = tree.xpath('//code[2]')[0]
text_context = eu.get_text_context(code)
sentence = eu.get_sentence(code, 'foo', text_context)
self.assertEqual('This is foo.', sentence)
# Test when there are more than one match, but wrong markup (sorry...)
b = tree.xpath('//b[1]')[0]
text_context = eu.get_text_context(b)
sentence = eu.get_sentence(b, 'foo', text_context)
self.assertEqual('Hello World foo.', sentence)