def test_shorten_html_text(self):
# truncate_html_words in utils.py
html = 'plain text'
truncate = utils.truncate_html_words(html, 10)
self.assertEqual(truncate, html)
html = 'single'
truncate = utils.truncate_html_words(html * 10, 10)
self.assertEqual(truncate, html * 10)
def _get_summary(self):
"""Returns the summary of an article, based on the summary metadata
if it is set, else truncate the content."""
if hasattr(self, "_summary"):
return self._summary
else:
return truncate_html_words(self.content, 50)
def insert_read_more_link(instance):
"""
Insert an inline "read more" link into the last element of the summary
:param instance: Content intance.
:return:
"""
if type(instance) != contents.Article:
return
site_url = instance.settings.get('SITEURL')
summary_max_length = instance.settings.get('SUMMARY_MAX_LENGTH')
link_text = instance.settings.get('READ_MORE_LINK_TEXT')
link_html_template = instance.settings.get(
'READ_MORE_LINK_TEMPLATE',
'<a class="read-more" href="{{ url }}">{{ text }}</a>',
)
summary = (getattr(instance, '_summary', None)
or truncate_html_words(instance.content, summary_max_length))
if summary != instance.content:
link_html = jinja2.Template(link_html_template).render(
url=f'{site_url}/{instance.url}',
text=link_text,
)
instance.metadata['summary'] = insert_into_last_element(
summary,
link_html,
)
def insert_read_more_link(instance):
"""
Insert an inline "read more" link into the last element of the summary
:param instance:
:return:
"""
# only deals with Article type
if type(instance) != contents.Article: return
SUMMARY_MAX_LENGTH = instance.settings.get('SUMMARY_MAX_LENGTH')
READ_MORE_LINK = instance.settings.get('READ_MORE_LINK', None)
READ_MORE_LINK_FORMAT = instance.settings.get('READ_MORE_LINK_FORMAT',
'<a class="read-more" href="/{url}">{text}</a>')
if not (SUMMARY_MAX_LENGTH and READ_MORE_LINK and READ_MORE_LINK_FORMAT): return
if hasattr(instance, '_summary') and instance._summary:
summary = instance._summary
else:
summary = truncate_html_words(instance.content, SUMMARY_MAX_LENGTH)
if summary != instance.content:
read_more_link = READ_MORE_LINK_FORMAT.format(url=instance.url, text=READ_MORE_LINK)
instance._summary = insert_into_last_element(summary, read_more_link)
def insert_read_more_link(instance):
"""
Insert an inline "read more" link into the last element of the summary
:param instance:
:return:
"""
# only deals with Article type
if type(instance) != contents.Article: return
SUMMARY_MAX_LENGTH = instance.settings.get('SUMMARY_MAX_LENGTH')
READ_MORE_LINK = instance.settings.get('READ_MORE_LINK', None)
READ_MORE_LINK_FORMAT = instance.settings.get(
'READ_MORE_LINK_FORMAT',
'<a class="read-more" href="/{url}">{text}</a>')
if not (SUMMARY_MAX_LENGTH and READ_MORE_LINK and READ_MORE_LINK_FORMAT):
return
if hasattr(instance, '_summary') and instance._summary:
summary = instance._summary
else:
summary = truncate_html_words(instance.content, SUMMARY_MAX_LENGTH)
if summary < instance.content:
read_more_link = READ_MORE_LINK_FORMAT.format(url=instance.url,
text=READ_MORE_LINK)
instance._summary = insert_into_last_element(summary, read_more_link)
def _get_summary(self):
"""Returns the summary of an article, based on the summary metadata
if it is set, else truncate the content."""
if hasattr(self, '_summary'):
return self._summary
else:
if self.settings['SUMMARY_MAX_LENGTH']:
return truncate_html_words(self.content, self.settings['SUMMARY_MAX_LENGTH'])
return self.content
def _get_summary(self):
"""Returns the summary of an article, based on the summary metadata
if it is set, else truncate the content."""
if hasattr(self, '_summary'):
return self._summary
else:
if self.settings['SUMMARY_MAX_LENGTH']:
return truncate_html_words(self.content, self.settings['SUMMARY_MAX_LENGTH'])
return self.content
def __init__(self, content, metadatas={}, settings={}, filename=None):
self._content = content
self.translations = []
self.status = "published" # default value
for key, value in metadatas.items():
setattr(self, key.lower(), value)
if not hasattr(self, 'author'):
if 'AUTHOR' in settings:
self.author = settings['AUTHOR']
default_lang = settings.get('DEFAULT_LANG').lower()
if not hasattr(self, 'lang'):
self.lang = default_lang
self.in_default_lang = (self.lang == default_lang)
if not hasattr(self, 'slug'):
self.slug = slugify(self.title)
if not hasattr(self, 'save_as'):
if self.in_default_lang:
self.save_as = '%s.html' % self.slug
clean_url = '%s/' % self.slug
else:
self.save_as = '%s-%s.html' % (self.slug, self.lang)
clean_url = '%s-%s/' % (self.slug, self.lang)
if settings.get('CLEAN_URLS', False):
self.url = clean_url
else:
self.url = self.save_as
if filename:
self.filename = filename
if not hasattr(self, 'date_format'):
if self.lang in settings['DATE_FORMATS']:
self.date_format = settings['DATE_FORMATS'][self.lang]
else:
self.date_format = settings['DEFAULT_DATE_FORMAT']
if hasattr(self, 'date'):
self.locale_date = self.date.strftime(
self.date_format.encode('ascii',
'xmlcharrefreplace')).decode('utf')
if not hasattr(self, 'summary'):
self.summary = property(
lambda self: truncate_html_words(self.content, 50)).__get__(
self, Page)
# store the settings ref.
self._settings = settings
def truncate(generator):
read_more = generator.settings.get('READ_MORE_RE',
r'<!--\s*?more\s*?-->')
read_more_re = re.compile(r'^(.*?)' + read_more, re.S)
max_length = generator.settings.get('SUMMARY_MAX_LENGTH')
for article in tuple(generator.articles):
content = article.content
match = read_more_re.search(content)
if match:
article._summary = match.group(1)
else:
article._summary = truncate_html_words(content, max_length)
def test_truncate_html_words(self):
self.assertEqual(
utils.truncate_html_words('short string', 20),
'short string')
self.assertEqual(
utils.truncate_html_words('word ' * 100, 20),
'word ' * 20 + '...')
self.assertEqual(
utils.truncate_html_words('<p>' + 'word ' * 100 + '</p>', 20),
'<p>' + 'word ' * 20 + '...</p>')
self.assertEqual(
utils.truncate_html_words(
'<span\nstyle="\n...\n">' + 'word ' * 100 + '</span>', 20),
'<span\nstyle="\n...\n">' + 'word ' * 20 + '...</span>')
self.assertEqual(
utils.truncate_html_words('<br>' + 'word ' * 100, 20),
'<br>' + 'word ' * 20 + '...')
self.assertEqual(
utils.truncate_html_words('<!-- comment -->' + 'word ' * 100, 20),
'<!-- comment -->' + 'word ' * 20 + '...')
def test_truncate_html_words(self):
self.assertEqual(
utils.truncate_html_words('short string', 20),
'short string')
self.assertEqual(
utils.truncate_html_words('word ' * 100, 20),
'word ' * 20 + '...')
self.assertEqual(
utils.truncate_html_words('<p>' + 'word ' * 100 + '</p>', 20),
'<p>' + 'word ' * 20 + '...</p>')
self.assertEqual(
utils.truncate_html_words(
'<span\nstyle="\n...\n">' + 'word ' * 100 + '</span>', 20),
'<span\nstyle="\n...\n">' + 'word ' * 20 + '...</span>')
self.assertEqual(
utils.truncate_html_words('<br>' + 'word ' * 100, 20),
'<br>' + 'word ' * 20 + '...')
self.assertEqual(
utils.truncate_html_words('<!-- comment -->' + 'word ' * 100, 20),
'<!-- comment -->' + 'word ' * 20 + '...')
def test_summary_max_length(self):
# If a :SUMMARY_MAX_LENGTH: is set, and there is no other summary,
# generated summary should not exceed the given length.
page_kwargs = self._copy_page_kwargs()
settings = _DEFAULT_CONFIG.copy()
page_kwargs['settings'] = settings
del page_kwargs['metadata']['summary']
settings['SUMMARY_MAX_LENGTH'] = None
page = Page(**page_kwargs)
self.assertEqual(page.summary, TEST_CONTENT)
settings['SUMMARY_MAX_LENGTH'] = 10
page = Page(**page_kwargs)
self.assertEqual(page.summary, truncate_html_words(TEST_CONTENT, 10))
def test_summary_max_length(self):
"""If a :SUMMARY_MAX_LENGTH: is set, and there is no other summary, generated summary
should not exceed the given length."""
page_kwargs = self._copy_page_kwargs()
settings = _DEFAULT_CONFIG.copy()
page_kwargs['settings'] = settings
del page_kwargs['metadata']['summary']
settings['SUMMARY_MAX_LENGTH'] = None
page = Page(**page_kwargs)
self.assertEqual(page.summary, TEST_CONTENT)
settings['SUMMARY_MAX_LENGTH'] = 10
page = Page(**page_kwargs)
self.assertEqual(page.summary, truncate_html_words(TEST_CONTENT, 10))
def redo_summary(instance):
summary = ""
if 'summary' in instance.metadata:
summary = instance.metadata.get('summary')
elif hasattr(instance, "_summary") and instance._summary is not None:
summary = instance._summary
elif hasattr(instance, "_content") and instance._content is not None:
summary_max_length = instance._context.get("SUMMARY_MAX_LENGTH", SUMMARY_MAX_LENGTH)
summary = truncate_html_words(instance._content, summary_max_length)
soup = BeautifulSoup(summary, from_encoding='utf-8')
[s.extract() for s in soup('img')]
instance.text_summary = soup
def test_summary_end_marker(self):
# If a :SUMMARY_END_MARKER: is set, and there is no other summary,
# generated summary should contain the specified marker at the end.
page_kwargs = self._copy_page_kwargs()
settings = get_settings()
page_kwargs['settings'] = settings
del page_kwargs['metadata']['summary']
settings['SUMMARY_END_MARKER'] = 'test_marker'
settings['SUMMARY_MAX_LENGTH'] = 10
page = Page(**page_kwargs)
self.assertEqual(page.summary,
truncate_html_words(TEST_CONTENT, 10, 'test_marker'))
self.assertIn('test_marker', page.summary)
def get_summary(self, siteurl):
"""Returns the summary of an article.
This is based on the summary metadata if set, otherwise truncate the
content.
"""
if hasattr(self, "_summary"):
return self._update_content(self._summary, siteurl)
if self.settings["SUMMARY_MAX_LENGTH"] is None:
return self.content
return truncate_html_words(self.content, self.settings["SUMMARY_MAX_LENGTH"])
def __init__(self, content, metadatas={}, settings={}, filename=None):
self._content = content
self.translations = []
self.status = "published" # default value
for key, value in metadatas.items():
setattr(self, key.lower(), value)
if not hasattr(self, "author"):
if "AUTHOR" in settings:
self.author = settings["AUTHOR"]
default_lang = settings.get("DEFAULT_LANG").lower()
if not hasattr(self, "lang"):
self.lang = default_lang
self.in_default_lang = self.lang == default_lang
if not hasattr(self, "slug"):
self.slug = slugify(self.title)
if not hasattr(self, "save_as"):
if self.in_default_lang:
self.save_as = "%s.html" % self.slug
clean_url = "%s/" % self.slug
else:
self.save_as = "%s-%s.html" % (self.slug, self.lang)
clean_url = "%s-%s/" % (self.slug, self.lang)
if settings.get("CLEAN_URLS", False):
self.url = clean_url
else:
self.url = self.save_as
if filename:
self.filename = filename
if not hasattr(self, "date_format"):
if self.lang in settings["DATE_FORMATS"]:
self.date_format = settings["DATE_FORMATS"][self.lang]
else:
self.date_format = settings["DEFAULT_DATE_FORMAT"]
if hasattr(self, "date"):
self.locale_date = self.date.strftime(self.date_format.encode("ascii", "xmlcharrefreplace")).decode("utf")
if not hasattr(self, "summary"):
self.summary = property(lambda self: truncate_html_words(self.content, 50)).__get__(self, Page)
# store the settings ref.
self._settings = settings
def __init__(self, content, metadatas={}, settings={}, filename=None):
self._content = content
self.translations = []
self.status = "published" # default value
for key, value in metadatas.items():
setattr(self, key.lower(), value)
if not hasattr(self, 'author'):
if 'AUTHOR' in settings:
self.author = settings['AUTHOR']
default_lang = settings.get('DEFAULT_LANG').lower()
if not hasattr(self, 'lang'):
self.lang = default_lang
self.in_default_lang = (self.lang == default_lang)
if not hasattr(self, 'slug'):
self.slug = slugify(self.title)
if not hasattr(self, 'save_as'):
if self.in_default_lang:
self.save_as = '%s.html' % self.slug
clean_url = '%s/' % self.slug
else:
self.save_as = '%s-%s.html' % (self.slug, self.lang)
clean_url = '%s-%s/' % (self.slug, self.lang)
if settings.get('CLEAN_URLS', False):
self.url = clean_url
else:
self.url = self.save_as
if filename:
self.filename = filename
if not hasattr(self, 'date_format'):
if self.lang in settings['DATE_FORMATS']:
self.date_format = settings['DATE_FORMATS'][self.lang]
else:
self.date_format = settings['DEFAULT_DATE_FORMAT']
if hasattr(self, 'date'):
self.locale_date = self.date.strftime(self.date_format.encode('ascii','xmlcharrefreplace')).decode('utf')
if not hasattr(self, 'summary'):
self.summary = property(lambda self: truncate_html_words(self.content, 50))
# store the settings ref.
self._settings = settings
def _get_summary(self):
"""Returns the summary of an article.
This is based on the summary metadata if set, otherwise truncate the
content.
"""
if hasattr(self, '_summary'):
return self._summary
if self.settings['SUMMARY_MAX_LENGTH'] is None:
return self.content
return truncate_html_words(self.content,
self.settings['SUMMARY_MAX_LENGTH'])
def get_summary(self, siteurl):
"""Returns the summary of an article.
This is based on the summary metadata if set, otherwise truncate the
content.
"""
if hasattr(self, '_summary'):
return self._update_content(self._summary, siteurl)
if self.settings['SUMMARY_MAX_LENGTH'] is None:
return self.content
return truncate_html_words(self.content,
self.settings['SUMMARY_MAX_LENGTH'])
def get_summary(self, siteurl):
"""Returns the summary of an article.
This is based on the summary metadata if set, otherwise truncate the
content.
"""
if 'summary' in self.metadata:
return self.metadata['summary']
if self.settings['SUMMARY_MAX_LENGTH'] is None:
return self.content
return truncate_html_words(self.content,
self.settings['SUMMARY_MAX_LENGTH'])
def get_summary(self, siteurl):
"""Returns the summary of an article.
This is based on the summary metadata if set, otherwise truncate the
content.
"""
if 'summary' in self.metadata:
return self.metadata['summary']
if self.settings['SUMMARY_MAX_LENGTH'] is None:
return self.content
return truncate_html_words(self.content,
self.settings['SUMMARY_MAX_LENGTH'])
def test_summary_max_length(self):
# If a :SUMMARY_MAX_LENGTH: is set, and there is no other summary,
# generated summary should not exceed the given length.
page_kwargs = self._copy_page_kwargs()
settings = get_settings()
page_kwargs["settings"] = settings
del page_kwargs["metadata"]["summary"]
settings["SUMMARY_MAX_LENGTH"] = None
page = Page(**page_kwargs)
self.assertEqual(page.summary, TEST_CONTENT)
settings["SUMMARY_MAX_LENGTH"] = 10
page = Page(**page_kwargs)
self.assertEqual(page.summary, truncate_html_words(TEST_CONTENT, 10))
settings["SUMMARY_MAX_LENGTH"] = 0
page = Page(**page_kwargs)
self.assertEqual(page.summary, "")
def fix_summary_ellipsis(instance):
"""
Pelican uses '...' as the ellipsis when creating a summary.
We want a proper ellipsis though, coupled with a non-breaking space.
:param instance:
:return:
"""
# only deals with Article type
if type(instance) != contents.Article: return
SUMMARY_MAX_LENGTH = instance.settings.get('SUMMARY_MAX_LENGTH')
if not (SUMMARY_MAX_LENGTH): return
if not (hasattr(instance, '_summary') and instance._summary):
summary = truncate_html_words(instance.content, SUMMARY_MAX_LENGTH,
'…')
instance._summary = summary.replace(' …', ' …')
def summary_remove_elements(instance):
if type(instance) == contents.Article:
summary = None
SUMMARY_MAX_LENGTH = instance.settings.get('SUMMARY_MAX_LENGTH')
if hasattr(instance, '_summary') and instance._summary:
summary = instance._summary
else:
summary = truncate_html_words(instance.content, SUMMARY_MAX_LENGTH)
summary = BeautifulSoup(summary, 'html.parser')
for tag in summary.findAll(True):
if tag.name in invalid_tags:
s = ""
for c in tag.contents:
if not isinstance(c, NavigableString):
c = strip_tags(unicode(c), invalid_tags)
s += unicode(c)
tag.replaceWith(s)
instance._summary = text_type(summary)
def process_summary(article):
"""Ensures summaries are not cut off. Also inserts
mathjax script so that math will be rendered"""
if (hasattr(article, '_summary')):
summary = article._update_content(article._summary, article.get_siteurl())
elif article.settings['SUMMARY_MAX_LENGTH'] is None:
summary = article.content
else:
summary = truncate_html_words(article.content, article.settings['SUMMARY_MAX_LENGTH'])
summary_parsed = BeautifulSoup(summary, 'html.parser')
math = summary_parsed.find_all(class_='math')
if len(math) > 0:
last_math_text = math[-1].get_text()
if len(last_math_text) > 3 and last_math_text[-3:] == '...':
content_parsed = BeautifulSoup(article._content, 'html.parser')
full_text = content_parsed.find_all(class_='math')[len(math)-1].get_text()
math[-1].string = "%s ..." % full_text
summary = summary_parsed.decode()
article._summary = "%s<script type='text/javascript'>%s</script>" % (summary, process_summary.mathjax_script)
def get_entry_summary(entry):
# https://stackoverflow.com/a/12982689/11441
def cleanhtml(raw_html):
cleanr = re.compile("<.*?>")
cleantext = re.sub(cleanr, "", raw_html)
return cleantext
try:
# this will get the first of 'summary' and 'subtitle'
summary = entry["description"]
except KeyError:
summary = ""
if settings[WEBRING_CLEAN_SUMMARY_HTML_STR] > 0:
summary = utils.truncate_html_words(
summary, settings[WEBRING_SUMMARY_WORDS_STR]
)
# feedparser sanitizes html by default, but it can still contain html tags.
if settings[WEBRING_CLEAN_SUMMARY_HTML_STR]:
summary = cleanhtml(summary)
return summary
def __init__(self, content, metadata=None, settings=None, filename=None, source=None):
# init parameters
if not metadata:
metadata = {}
if not settings:
settings = _DEFAULT_CONFIG
self._content = content
self.translations = []
self.source = source
local_metadata = dict(settings.get('DEFAULT_METADATA', ()))
local_metadata.update(metadata)
# set metadata as attributes
for key, value in local_metadata.items():
setattr(self, key.lower(), value)
# default author to the one in settings if not defined
if not hasattr(self, 'author'):
if 'AUTHOR' in settings:
self.author = settings['AUTHOR']
else:
self.author = getenv('USER', 'John Doe')
warning(u"Author of `{0}' unknow, assuming that his name is `{1}'".format(filename, self.author))
# manage languages
self.in_default_lang = True
if 'DEFAULT_LANG' in settings:
default_lang = settings['DEFAULT_LANG'].lower()
if not hasattr(self, 'lang'):
self.lang = default_lang
self.in_default_lang = (self.lang == default_lang)
# create the slug if not existing, from the title
if not hasattr(self, 'slug') and hasattr(self, 'title'):
self.slug = slugify(self.title)
# create save_as from the slug (+lang)
if not hasattr(self, 'save_as') and hasattr(self, 'slug'):
if not self.in_default_lang:
self.url = '%s-%s' % (self.slug, self.lang)
if settings.get('CLEAN_URLS', False):
self.save_as = '%s/index.html' % self.slug
self.url = '%s/' % self.slug
self.source_url = '%s.txt' % self.slug
else:
self.save_as = '%s.html' % self.slug
self.url = self.save_as
self.source_url = '%s.txt' % self.slug
elif hasattr(self, 'save_as'):
self.url = self.save_as
self.source_url = self.save_as
if filename:
self.filename = filename
# manage the date format
if not hasattr(self, 'date_format'):
if hasattr(self, 'lang') and self.lang in settings['DATE_FORMATS']:
self.date_format = settings['DATE_FORMATS'][self.lang]
else:
self.date_format = settings['DEFAULT_DATE_FORMAT']
if hasattr(self, 'date'):
if platform == 'win32':
self.locale_date = self.date.strftime(self.date_format.encode('ascii','xmlcharrefreplace')).decode(stdin.encoding)
else:
self.locale_date = self.date.strftime(self.date_format.encode('ascii','xmlcharrefreplace')).decode('utf')
# manage status
if not hasattr(self, 'status'):
self.status = settings['DEFAULT_STATUS']
if not settings['WITH_FUTURE_DATES']:
if hasattr(self, 'date') and self.date > datetime.now():
self.status = 'draft'
# set summary
if not hasattr(self, 'summary'):
self.summary = truncate_html_words(self.content, 50)
def truncate_html_words(html, max_length=15):
return pelican_utils.truncate_html_words(html, max_length)
def __init__(self, content, metadata=None, settings=None,
filename=None):
# init parameters
if not metadata:
metadata = {}
if not settings:
settings = _DEFAULT_CONFIG
self.settings = settings
self._content = content
self.translations = []
local_metadata = dict(settings.get('DEFAULT_METADATA', ()))
local_metadata.update(metadata)
# set metadata as attributes
for key, value in local_metadata.items():
setattr(self, key.lower(), value)
# default author to the one in settings if not defined
if not hasattr(self, 'author'):
if 'AUTHOR' in settings:
self.author = Author(settings['AUTHOR'], settings)
else:
self.author = Author(getenv('USER', 'John Doe'), settings)
warning(u"Author of `{0}' unknow, assuming that his name is "
"`{1}'".format(filename or self.title, self.author))
# manage languages
self.in_default_lang = True
if 'DEFAULT_LANG' in settings:
default_lang = settings['DEFAULT_LANG'].lower()
if not hasattr(self, 'lang'):
self.lang = default_lang
self.in_default_lang = (self.lang == default_lang)
# create the slug if not existing, fro mthe title
if not hasattr(self, 'slug') and hasattr(self, 'title'):
self.slug = slugify(self.title)
if filename:
self.filename = filename
# manage the date format
if not hasattr(self, 'date_format'):
if hasattr(self, 'lang') and self.lang in settings['DATE_FORMATS']:
self.date_format = settings['DATE_FORMATS'][self.lang]
else:
self.date_format = settings['DEFAULT_DATE_FORMAT']
if isinstance(self.date_format, tuple):
locale.setlocale(locale.LC_ALL, self.date_format[0])
self.date_format = self.date_format[1]
if hasattr(self, 'date'):
encoded_date = self.date.strftime(
self.date_format.encode('ascii', 'xmlcharrefreplace'))
if platform == 'win32':
self.locale_date = encoded_date.decode(stdin.encoding)
else:
self.locale_date = encoded_date.decode('utf')
# manage status
if not hasattr(self, 'status'):
self.status = settings['DEFAULT_STATUS']
if not settings['WITH_FUTURE_DATES']:
if hasattr(self, 'date') and self.date > datetime.now():
self.status = 'draft'
# set summary
if not hasattr(self, 'summary'):
self.summary = truncate_html_words(self.content, 50)
def _get_summary(self):
"""Returns the summary of an article, based on to the content"""
return truncate_html_words(self.content, 50)
def _get_summary(self):
"""Returns the summary of an article, based on to the content"""
return truncate_html_words(self.content, 50)
def __init__(self, content, metadata=None, settings=None, filename=None):
# init parameters
if not metadata:
metadata = {}
if not settings:
settings = _DEFAULT_CONFIG
self._content = content
self.translations = []
local_metadata = dict(settings.get('DEFAULT_METADATA', ()))
local_metadata.update(metadata)
# set metadata as attributes
for key, value in local_metadata.items():
setattr(self, key.lower(), value)
# default author to the one in settings if not defined
if not hasattr(self, 'author'):
if 'AUTHOR' in settings:
self.author = settings['AUTHOR']
else:
self.author = getenv('USER', 'John Doe')
warning(u"Author of `{0}' unknow, assuming that his name is `{1}'".format(filename or self.title, self.author))
# manage languages
self.in_default_lang = True
if 'DEFAULT_LANG' in settings:
default_lang = settings['DEFAULT_LANG'].lower()
if not hasattr(self, 'lang'):
self.lang = default_lang
self.in_default_lang = (self.lang == default_lang)
# create the slug if not existing, fro mthe title
if not hasattr(self, 'slug') and hasattr(self, 'title'):
self.slug = slugify(self.title)
# create save_as from the slug (+lang)
if not hasattr(self, 'save_as') and hasattr(self, 'slug'):
if self.in_default_lang:
if settings.get('CLEAN_URLS', False):
self.save_as = '%s/index.html' % self.slug
else:
self.save_as = '%s.html' % self.slug
clean_url = '%s/' % self.slug
else:
if settings.get('CLEAN_URLS', False):
self.save_as = '%s-%s/index.html' % (self.slug, self.lang)
else:
self.save_as = '%s-%s.html' % (self.slug, self.lang)
clean_url = '%s-%s/' % (self.slug, self.lang)
# change the save_as regarding the settings
if settings.get('CLEAN_URLS', False):
self.url = clean_url
elif hasattr(self, 'save_as'):
self.url = self.save_as
if filename:
self.filename = filename
# manage the date format
if not hasattr(self, 'date_format'):
if hasattr(self, 'lang') and self.lang in settings['DATE_FORMATS']:
self.date_format = settings['DATE_FORMATS'][self.lang]
else:
self.date_format = settings['DEFAULT_DATE_FORMAT']
if hasattr(self, 'date'):
if platform == 'win32':
self.locale_date = self.date.strftime(self.date_format.encode('ascii','xmlcharrefreplace')).decode(stdin.encoding)
else:
self.locale_date = self.date.strftime(self.date_format.encode('ascii','xmlcharrefreplace')).decode('utf')
# manage status
if not hasattr(self, 'status'):
self.status = settings['DEFAULT_STATUS']
if not settings['WITH_FUTURE_DATES']:
if hasattr(self, 'date') and self.date > datetime.now():
self.status = 'draft'
# set summary
if not hasattr(self, 'summary'):
self.summary = truncate_html_words(self.content, 50)
def summary(self):
return truncate_html_words(self.content, 50)
def make_summary(text, max_words=None):
if max_words is None:
return text
return truncate_html_words(text, max_words, end_text='…')
def __init__(self, content, metadata=None, settings=None, filename=None):
# init parameters
if not metadata:
metadata = {}
if not settings:
settings = _DEFAULT_CONFIG
self._content = content
self.translations = []
self.status = "published" # default value
local_metadata = dict(settings.get('DEFAULT_METADATA', ()))
local_metadata.update(metadata)
# set metadata as attributes
for key, value in local_metadata.items():
setattr(self, key.lower(), value)
# default author to the one in settings if not defined
if not hasattr(self, 'author'):
if 'AUTHOR' in settings:
self.author = settings['AUTHOR']
# manage languages
self.in_default_lang = True
if 'DEFAULT_LANG' in settings:
default_lang = settings['DEFAULT_LANG'].lower()
if not hasattr(self, 'lang'):
self.lang = default_lang
self.in_default_lang = (self.lang == default_lang)
# create the slug if not existing, fro mthe title
if not hasattr(self, 'slug') and hasattr(self, 'title'):
self.slug = slugify(self.title)
# create save_as from the slug (+lang)
if not hasattr(self, 'save_as') and hasattr(self, 'slug'):
if self.in_default_lang:
self.save_as = '%s.html' % self.slug
clean_url = '%s/' % self.slug
else:
self.save_as = '%s-%s.html' % (self.slug, self.lang)
clean_url = '%s-%s/' % (self.slug, self.lang)
# change the save_as regarding the settings
if settings.get('CLEAN_URLS', False):
self.url = clean_url
elif hasattr(self, 'save_as'):
self.url = self.save_as
if filename:
self.filename = filename
# manage the date format
if not hasattr(self, 'date_format'):
if hasattr(self, 'lang') and self.lang in settings['DATE_FORMATS']:
self.date_format = settings['DATE_FORMATS'][self.lang]
else:
self.date_format = settings['DEFAULT_DATE_FORMAT']
if hasattr(self, 'date'):
self.locale_date = self.date.strftime(self.date_format.encode('ascii','xmlcharrefreplace')).decode('utf')
# manage summary
if not hasattr(self, 'summary'):
self.summary = property(lambda self: truncate_html_words(self.content, 50)).__get__(self, Page)
# manage status
if not hasattr(self, 'status'):
self.status = settings['DEFAULT_STATUS']
def test_truncate_html_words(self):
# Plain text.
self.assertEqual(utils.truncate_html_words('short string', 20),
'short string')
self.assertEqual(utils.truncate_html_words('word ' * 100, 20),
'word ' * 20 + '…')
# Words enclosed or intervaled by HTML tags.
self.assertEqual(
utils.truncate_html_words('<p>' + 'word ' * 100 + '</p>', 20),
'<p>' + 'word ' * 20 + '…</p>')
self.assertEqual(
utils.truncate_html_words(
'<span\nstyle="\n…\n">' + 'word ' * 100 + '</span>', 20),
'<span\nstyle="\n…\n">' + 'word ' * 20 + '…</span>')
self.assertEqual(utils.truncate_html_words('<br>' + 'word ' * 100, 20),
'<br>' + 'word ' * 20 + '…')
self.assertEqual(
utils.truncate_html_words('<!-- comment -->' + 'word ' * 100, 20),
'<!-- comment -->' + 'word ' * 20 + '…')
# Words with hypens and apostrophes.
self.assertEqual(utils.truncate_html_words("a-b " * 100, 20),
"a-b " * 20 + '…')
self.assertEqual(utils.truncate_html_words("it's " * 100, 20),
"it's " * 20 + '…')
# Words with HTML entity references.
self.assertEqual(utils.truncate_html_words("é " * 100, 20),
"é " * 20 + '…')
self.assertEqual(utils.truncate_html_words("café " * 100, 20),
"café " * 20 + '…')
self.assertEqual(utils.truncate_html_words("èlite " * 100, 20),
"èlite " * 20 + '…')
self.assertEqual(
utils.truncate_html_words("cafetiére " * 100, 20),
"cafetiére " * 20 + '…')
self.assertEqual(utils.truncate_html_words("∫dx " * 100, 20),
"∫dx " * 20 + '…')
# Words with HTML character references inside and outside
# the ASCII range.
self.assertEqual(utils.truncate_html_words("é " * 100, 20),
"é " * 20 + '…')
self.assertEqual(utils.truncate_html_words("∫dx " * 100, 20),
"∫dx " * 20 + '…')
# Words with invalid or broken HTML references.
self.assertEqual(utils.truncate_html_words('&invalid;', 20),
'&invalid;')
self.assertEqual(utils.truncate_html_words('�', 20),
'�')
self.assertEqual(utils.truncate_html_words('�', 20),
'�')
self.assertEqual(utils.truncate_html_words('&mdash text', 20),
'&mdash text')
self.assertEqual(utils.truncate_html_words('Ӓ text', 20),
'Ӓ text')
self.assertEqual(utils.truncate_html_words('઼ text', 20),
'઼ text')
def test_truncate_html_words(self):
# Plain text.
self.assertEqual(utils.truncate_html_words('short string', 20),
'short string')
self.assertEqual(utils.truncate_html_words('word ' * 100, 20),
'word ' * 20 + '...')
# Words enclosed or intervaled by HTML tags.
self.assertEqual(
utils.truncate_html_words('<p>' + 'word ' * 100 + '</p>', 20),
'<p>' + 'word ' * 20 + '...</p>')
self.assertEqual(
utils.truncate_html_words(
'<span\nstyle="\n...\n">' + 'word ' * 100 + '</span>', 20),
'<span\nstyle="\n...\n">' + 'word ' * 20 + '...</span>')
self.assertEqual(utils.truncate_html_words('<br>' + 'word ' * 100, 20),
'<br>' + 'word ' * 20 + '...')
self.assertEqual(
utils.truncate_html_words('<!-- comment -->' + 'word ' * 100, 20),
'<!-- comment -->' + 'word ' * 20 + '...')
# Words with hypens and apostrophes.
self.assertEqual(utils.truncate_html_words("a-b " * 100, 20),
"a-b " * 20 + '...')
self.assertEqual(utils.truncate_html_words("it's " * 100, 20),
"it's " * 20 + '...')
# Words with HTML entity references.
self.assertEqual(utils.truncate_html_words("é " * 100, 20),
"é " * 20 + '...')
self.assertEqual(utils.truncate_html_words("café " * 100, 20),
"café " * 20 + '...')
self.assertEqual(utils.truncate_html_words("èlite " * 100, 20),
"èlite " * 20 + '...')
self.assertEqual(
utils.truncate_html_words("cafetiére " * 100, 20),
"cafetiére " * 20 + '...')
def test_truncate_html_words(self):
# Plain text.
self.assertEqual(utils.truncate_html_words('short string', 20),
'short string')
self.assertEqual(utils.truncate_html_words('word ' * 100, 20),
'word ' * 20 + '…')
# Plain text with Unicode content.
self.assertEqual(
utils.truncate_html_words(
'我愿意这样，朋友——我独自远行，不但没有你，\
并且再没有别的影在黑暗里。', 12), '我愿意这样，朋友——我独自远行' + ' …')
self.assertEqual(
utils.truncate_html_words(
'Ты мелькнула, ты предстала, Снова сердце задрожало,', 3),
'Ты мелькнула, ты' + ' …')
self.assertEqual(
utils.truncate_html_words('Trong đầm gì đẹp bằng sen', 4),
'Trong đầm gì đẹp' + ' …')
# Words enclosed or intervaled by HTML tags.
self.assertEqual(
utils.truncate_html_words('<p>' + 'word ' * 100 + '</p>', 20),
'<p>' + 'word ' * 20 + '…</p>')
self.assertEqual(
utils.truncate_html_words(
'<span\nstyle="\n…\n">' + 'word ' * 100 + '</span>', 20),
'<span\nstyle="\n…\n">' + 'word ' * 20 + '…</span>')
self.assertEqual(utils.truncate_html_words('<br>' + 'word ' * 100, 20),
'<br>' + 'word ' * 20 + '…')
self.assertEqual(
utils.truncate_html_words('<!-- comment -->' + 'word ' * 100, 20),
'<!-- comment -->' + 'word ' * 20 + '…')
# Words with hypens and apostrophes.
self.assertEqual(utils.truncate_html_words("a-b " * 100, 20),
"a-b " * 20 + '…')
self.assertEqual(utils.truncate_html_words("it's " * 100, 20),
"it's " * 20 + '…')
# Words with HTML entity references.
self.assertEqual(utils.truncate_html_words("é " * 100, 20),
"é " * 20 + '…')
self.assertEqual(utils.truncate_html_words("café " * 100, 20),
"café " * 20 + '…')
self.assertEqual(utils.truncate_html_words("èlite " * 100, 20),
"èlite " * 20 + '…')
self.assertEqual(
utils.truncate_html_words("cafetiére " * 100, 20),
"cafetiére " * 20 + '…')
self.assertEqual(utils.truncate_html_words("∫dx " * 100, 20),
"∫dx " * 20 + '…')
# Words with HTML character references inside and outside
# the ASCII range.
self.assertEqual(utils.truncate_html_words("é " * 100, 20),
"é " * 20 + '…')
self.assertEqual(utils.truncate_html_words("∫dx " * 100, 20),
"∫dx " * 20 + '…')
# Words with invalid or broken HTML references.
self.assertEqual(utils.truncate_html_words('&invalid;', 20),
'&invalid;')
self.assertEqual(utils.truncate_html_words('�', 20),
'�')
self.assertEqual(utils.truncate_html_words('�', 20),
'�')
self.assertEqual(utils.truncate_html_words('&mdash text', 20),
'&mdash text')
self.assertEqual(utils.truncate_html_words('Ӓ text', 20),
'Ӓ text')
self.assertEqual(utils.truncate_html_words('઼ text', 20),
'઼ text')
def test_truncate_html_words(self):
# Plain text.
self.assertEqual(
utils.truncate_html_words('short string', 20),
'short string')
self.assertEqual(
utils.truncate_html_words('word ' * 100, 20),
'word ' * 20 + '…')
# Words enclosed or intervaled by HTML tags.
self.assertEqual(
utils.truncate_html_words('<p>' + 'word ' * 100 + '</p>', 20),
'<p>' + 'word ' * 20 + '…</p>')
self.assertEqual(
utils.truncate_html_words(
'<span\nstyle="\n…\n">' + 'word ' * 100 + '</span>', 20),
'<span\nstyle="\n…\n">' + 'word ' * 20 + '…</span>')
self.assertEqual(
utils.truncate_html_words('<br>' + 'word ' * 100, 20),
'<br>' + 'word ' * 20 + '…')
self.assertEqual(
utils.truncate_html_words('<!-- comment -->' + 'word ' * 100, 20),
'<!-- comment -->' + 'word ' * 20 + '…')
# Words with hypens and apostrophes.
self.assertEqual(
utils.truncate_html_words("a-b " * 100, 20),
"a-b " * 20 + '…')
self.assertEqual(
utils.truncate_html_words("it's " * 100, 20),
"it's " * 20 + '…')
# Words with HTML entity references.
self.assertEqual(
utils.truncate_html_words("é " * 100, 20),
"é " * 20 + '…')
self.assertEqual(
utils.truncate_html_words("café " * 100, 20),
"café " * 20 + '…')
self.assertEqual(
utils.truncate_html_words("èlite " * 100, 20),
"èlite " * 20 + '…')
self.assertEqual(
utils.truncate_html_words("cafetiére " * 100, 20),
"cafetiére " * 20 + '…')
self.assertEqual(
utils.truncate_html_words("∫dx " * 100, 20),
"∫dx " * 20 + '…')
# Words with HTML character references inside and outside
# the ASCII range.
self.assertEqual(
utils.truncate_html_words("é " * 100, 20),
"é " * 20 + '…')
self.assertEqual(
utils.truncate_html_words("∫dx " * 100, 20),
"∫dx " * 20 + '…')
def __init__(self, content, metadata=None, settings=None, filename=None):
# init parameters
if not metadata:
metadata = {}
if not settings:
settings = _DEFAULT_CONFIG
self._content = content
self.translations = []
local_metadata = dict(settings.get("DEFAULT_METADATA", ()))
local_metadata.update(metadata)
# set metadata as attributes
for key, value in local_metadata.items():
setattr(self, key.lower(), value)
# default author to the one in settings if not defined
if not hasattr(self, "author"):
if "AUTHOR" in settings:
self.author = settings["AUTHOR"]
else:
self.author = getenv("USER", "John Doe")
warning(
u"Author of `{0}' unknow, assuming that his name is `{1}'".format(
filename or self.title, self.author
)
)
# manage languages
self.in_default_lang = True
if "DEFAULT_LANG" in settings:
default_lang = settings["DEFAULT_LANG"].lower()
if not hasattr(self, "lang"):
self.lang = default_lang
self.in_default_lang = self.lang == default_lang
# create the slug if not existing, fro mthe title
if not hasattr(self, "slug") and hasattr(self, "title"):
self.slug = slugify(self.title)
# create save_as from the slug (+lang)
if not hasattr(self, "save_as") and hasattr(self, "slug"):
if self.in_default_lang:
self.save_as = "%s.html" % self.slug
clean_url = "%s/" % self.slug
else:
self.save_as = "%s-%s.html" % (self.slug, self.lang)
clean_url = "%s-%s/" % (self.slug, self.lang)
# change the save_as regarding the settings
if settings.get("CLEAN_URLS", False):
self.url = clean_url
elif hasattr(self, "save_as"):
self.url = self.save_as
if filename:
self.filename = filename
# manage the date format
if not hasattr(self, "date_format"):
if hasattr(self, "lang") and self.lang in settings["DATE_FORMATS"]:
self.date_format = settings["DATE_FORMATS"][self.lang]
else:
self.date_format = settings["DEFAULT_DATE_FORMAT"]
if hasattr(self, "date"):
if platform == "win32":
self.locale_date = self.date.strftime(self.date_format.encode("ascii", "xmlcharrefreplace")).decode(
stdin.encoding
)
else:
self.locale_date = self.date.strftime(self.date_format.encode("ascii", "xmlcharrefreplace")).decode(
"utf"
)
# manage status
if not hasattr(self, "status"):
self.status = settings["DEFAULT_STATUS"]
if not settings["WITH_FUTURE_DATES"]:
if hasattr(self, "date") and self.date > datetime.now():
self.status = "draft"
# set summary
if not hasattr(self, "summary"):
self.summary = truncate_html_words(self.content, 50)
def truncate(self, html: str, max_length: int, without_tag: bool) -> str:
summary = pelican_utils.truncate_html_words(html, max_length)
if without_tag:
summary = re.sub(r'<[^>]+>', "", summary)
return summary
def test_truncate_html_words(self):
# Plain text.
self.assertEqual(
utils.truncate_html_words('short string', 20),
'short string')
self.assertEqual(
utils.truncate_html_words('word ' * 100, 20),
'word ' * 20 + '...')
# Words enclosed or intervaled by HTML tags.
self.assertEqual(
utils.truncate_html_words('<p>' + 'word ' * 100 + '</p>', 20),
'<p>' + 'word ' * 20 + '...</p>')
self.assertEqual(
utils.truncate_html_words(
'<span\nstyle="\n...\n">' + 'word ' * 100 + '</span>', 20),
'<span\nstyle="\n...\n">' + 'word ' * 20 + '...</span>')
self.assertEqual(
utils.truncate_html_words('<br>' + 'word ' * 100, 20),
'<br>' + 'word ' * 20 + '...')
self.assertEqual(
utils.truncate_html_words('<!-- comment -->' + 'word ' * 100, 20),
'<!-- comment -->' + 'word ' * 20 + '...')
# Words with hypens and apostrophes.
self.assertEqual(
utils.truncate_html_words("a-b " * 100, 20),
"a-b " * 20 + '...')
self.assertEqual(
utils.truncate_html_words("it's " * 100, 20),
"it's " * 20 + '...')
# Words with HTML entity references.
self.assertEqual(
utils.truncate_html_words("é " * 100, 20),
"é " * 20 + '...')
self.assertEqual(
utils.truncate_html_words("café " * 100, 20),
"café " * 20 + '...')
self.assertEqual(
utils.truncate_html_words("èlite " * 100, 20),
"èlite " * 20 + '...')
self.assertEqual(
utils.truncate_html_words("cafetiére " * 100, 20),
"cafetiére " * 20 + '...')