def firstline(html):
"""
Returns the first line from a HTML blob as plain text
"""
result = text_blocks(html)
if result:
return result[0]
def firstline(html):
"""
Returns the first line from a HTML blob as plain text
"""
result = text_blocks(html)
if result:
return result[0]
def preview(html: str, min: int = 50, max: int = 158) -> str: # NOQA: A002
"""
Return a preview of a HTML blob as plain text, for use as a description tag.
This function will attempt to return a HTML paragraph at a time, to avoid truncating
sentences. Multiple paragraphs will be used if they are under min characters.
:param str html: HTML text to generate a preview from
:param int min: Minimum number of characters in the preview (default 50)
:param int max: Maximum number of characters in the preview (default 158,
recommended for Google)
"""
# Get the max length we're interested in, for efficiency in grapheme counts. A large
# blob of text can impair performance if we're only interested in a small preview.
# `max` can be < `min` when the caller specifies a custom `max` without `min`
max_length = (max if max > min else min) + 1
blocks = text_blocks(html)
if blocks:
text = compress_whitespace(blocks.pop(0))
length = grapheme.length(text, max_length)
while blocks and length < min:
text += ' ' + compress_whitespace(blocks.pop(0))
length = grapheme.length(text, max_length)
if length > max:
text = grapheme.slice(text, 0, max - 1) + '…'
return text
return ''
def firstline(html: str) -> str:
"""
Return the first line from a HTML blob as plain text.
.. deprecated: 2021-03-25
Use :func:`preview` instead.
"""
result = text_blocks(html)
if result:
return compress_whitespace(result[0])
return ''
def tag_named_entities(post):
entities = extract_named_entities(text_blocks(post.tag_content()))
links = set()
for entity in entities:
tag = Tag.get(entity, create=True)
link = JobPostTag.get(post, tag)
if not link:
link = JobPostTag(jobpost=post, tag=tag, status=TAG_TYPE.AUTO)
post.taglinks.append(link)
links.add(link)
for link in post.taglinks:
if link.status == TAG_TYPE.AUTO and link not in links:
link.status = TAG_TYPE.REMOVED
def tag_named_entities(post):
entities = extract_named_entities(text_blocks(post.tag_content()))
links = set()
for entity in entities:
tag = Tag.get(entity, create=True)
link = JobPostTag.get(post, tag)
if not link:
link = JobPostTag(jobpost=post, tag=tag, status=TAG_TYPE.AUTO)
post.taglinks.append(link)
links.add(link)
for link in post.taglinks:
if link.status == TAG_TYPE.AUTO and link not in links:
link.status = TAG_TYPE.REMOVED
def test_extract_text(self):
tb = text_blocks(sample_html, skip_pre=True)
assert tb == sample_text_blocks
def test_extract_text(self):
tb = text_blocks(sample_html, skip_pre=True)
self.assertEqual(tb, sample_text_blocks)
def test_extract_text(self):
tb = text_blocks(sample_html, skip_pre=True)
self.assertEqual(tb, sample_text_blocks)
