def test_map_priority(self):
self.assertEqual('f', map_priority(1))
self.assertEqual('u', map_priority(2))
self.assertEqual('b', map_priority(3))
self.assertEqual('r', map_priority(4))
self.assertEqual('r', map_priority(5))
self.assertEqual('r', map_priority(6))
self.assertEqual('r', map_priority(None))
self.assertEqual('r', map_priority(7))
self.assertEqual('r', map_priority(''))
def test_map_priority(self):
self.assertEqual('f', map_priority(1))
self.assertEqual('u', map_priority(2))
self.assertEqual('b', map_priority(3))
self.assertEqual('r', map_priority(4))
self.assertEqual('r', map_priority(5))
self.assertEqual('r', map_priority(6))
self.assertEqual('r', map_priority(None))
self.assertEqual('r', map_priority(7))
self.assertEqual('r', map_priority(''))
def test_map_priority(self):
self.assertEqual("f", map_priority(1))
self.assertEqual("u", map_priority(2))
self.assertEqual("b", map_priority(3))
self.assertEqual("r", map_priority(4))
self.assertEqual("r", map_priority(5))
self.assertEqual("r", map_priority(6))
self.assertEqual("r", map_priority(None))
self.assertEqual("r", map_priority(7))
self.assertEqual("r", map_priority(""))
def format(self, article, subscriber):
"""
Constructs a dictionary that represents the parameters passed to the SMS InsertAlerts stored procedure
:return: returns the sequence number of the subscriber and the constructed parameter dictionary
"""
try:
pub_seq_num = superdesk.get_resource_service(
'subscribers').generate_sequence_number(subscriber)
odbc_item = {
'Sequence': pub_seq_num,
'Category': article.get('anpa_category', [{}])[0].get('qcode'),
'Headline': article.get('headline', '').replace('\'', '\'\''),
'Priority': map_priority(article.get('priority'))
}
if article.get(EMBARGO):
embargo = '{}{}'.format('Embargo Content. Timestamp: ',
article.get(EMBARGO).isoformat())
article['body_html'] = embargo + article['body_html']
if article[ITEM_TYPE] == CONTENT_TYPE.PREFORMATTED:
odbc_item['StoryText'] = article.get('body_html', '').replace(
'\'', '\'\'') # @article_text
elif article[ITEM_TYPE] == CONTENT_TYPE.TEXT:
soup = BeautifulSoup(article.get('body_html', ''))
odbc_item['StoryText'] = soup.text.replace('\'', '\'\'')
odbc_item['ident'] = '0'
return [(pub_seq_num, odbc_item)]
except Exception as ex:
raise FormatterError.AAPSMSFormatterError(ex, subscriber)
def format(self, article, subscriber):
"""
Constructs a dictionary that represents the parameters passed to the SMS InsertAlerts stored procedure
:return: returns the sequence number of the subscriber and the constructed parameter dictionary
"""
try:
pub_seq_num = superdesk.get_resource_service('subscribers').generate_sequence_number(subscriber)
odbc_item = {'Sequence': pub_seq_num, 'Category': article.get('anpa_category', [{}])[0].get('qcode'),
'Headline': article.get('headline', '').replace('\'', '\'\''),
'Priority': map_priority(article.get('priority'))}
if article.get(EMBARGO):
embargo = '{}{}'.format('Embargo Content. Timestamp: ', article.get(EMBARGO).isoformat())
article['body_html'] = embargo + article['body_html']
if article[ITEM_TYPE] == CONTENT_TYPE.PREFORMATTED:
odbc_item['StoryText'] = article.get('body_html', '').replace('\'', '\'\'') # @article_text
elif article[ITEM_TYPE] == CONTENT_TYPE.TEXT:
soup = BeautifulSoup(article.get('body_html', ''))
odbc_item['StoryText'] = soup.text.replace('\'', '\'\'')
odbc_item['ident'] = '0'
return [(pub_seq_num, odbc_item)]
except Exception as ex:
raise FormatterError.AAPSMSFormatterError(ex, subscriber)
def format(self, article, subscriber):
"""
Constructs a dictionary that represents the parameters passed to the SMS InsertAlerts stored procedure
:return: returns the sequence number of the subscriber and the constructed parameter dictionary
"""
try:
pub_seq_num = superdesk.get_resource_service(
'subscribers').generate_sequence_number(subscriber)
sms_message = article.get('sms_message',
article.get('headline',
'')).replace('\'', '\'\'')
odbc_item = {
'Sequence': pub_seq_num,
'Category': article.get('anpa_category', [{}])[0].get('qcode'),
'Headline': sms_message,
'Priority': map_priority(article.get('priority'))
}
body = self.append_body_footer(article)
if article.get(EMBARGO):
embargo = '{}{}'.format(
'Embargo Content. Timestamp: ',
get_utc_schedule(article, EMBARGO).isoformat())
body = embargo + body
if article[ITEM_TYPE] == CONTENT_TYPE.TEXT:
body = BeautifulSoup(body, "html.parser").text
odbc_item['StoryText'] = body.replace('\'',
'\'\'') # @article_text
odbc_item['ident'] = '0'
return [(pub_seq_num, json.dumps(odbc_item))]
except Exception as ex:
raise FormatterError.AAPSMSFormatterError(ex, subscriber)
def format(self, article, subscriber):
try:
docs = []
for category in article.get('anpa_category'):
pub_seq_num = superdesk.get_resource_service('subscribers').generate_sequence_number(subscriber)
anpa = []
# selector codes are only injected for those subscribers that are defined
# in the mapper
selectors = dict()
SelectorcodeMapper().map(article, category.get('qcode').upper(),
subscriber=subscriber,
formatted_item=selectors)
if 'selector_codes' in selectors and selectors['selector_codes']:
anpa.append(b'\x05')
anpa.append(selectors['selector_codes'].encode('ascii'))
anpa.append(b'\x0D\x0A')
# start of message header (syn syn soh)
anpa.append(b'\x16\x16\x01')
anpa.append(article.get('service_level', 'a').lower().encode('ascii'))
# story number
anpa.append(str(pub_seq_num).zfill(4).encode('ascii'))
# field seperator
anpa.append(b'\x0A') # -LF
anpa.append(map_priority(article.get('priority')).encode('ascii'))
anpa.append(b'\x20')
anpa.append(category['qcode'].encode('ascii'))
anpa.append(b'\x13')
# format identifier
if article[ITEM_TYPE] == CONTENT_TYPE.PREFORMATTED:
anpa.append(b'\x12')
else:
anpa.append(b'\x11')
anpa.append(b'\x20')
# keyword
keyword = 'bc-{}'.format(self.append_legal(article=article, truncate=True)).replace(' ', '-')
keyword = keyword[:24] if len(keyword) > 24 else keyword
anpa.append(keyword.encode('ascii'))
anpa.append(b'\x20')
# version field
anpa.append(b'\x20')
# reference field
anpa.append(b'\x20')
# filing date
anpa.append('{}-{}'.format(article['_updated'].strftime('%m'),
article['_updated'].strftime('%d')).encode('ascii'))
anpa.append(b'\x20')
# add the word count
anpa.append(str(article.get('word_count', '0000')).zfill(4).encode('ascii'))
anpa.append(b'\x0D\x0A')
anpa.append(b'\x02') # STX
self._process_headline(anpa, article, category['qcode'].encode('ascii'))
keyword = self.append_legal(article=article, truncate=True).encode('ascii', 'ignore')
anpa.append(keyword)
take_key = article.get('anpa_take_key', '').encode('ascii', 'ignore')
anpa.append((b'\x20' + take_key) if len(take_key) > 0 else b'')
anpa.append(b'\x0D\x0A')
if BYLINE in article:
anpa.append(article.get(BYLINE).encode('ascii', 'ignore'))
anpa.append(b'\x0D\x0A')
if article.get('dateline', {}).get('text'):
anpa.append(article.get('dateline').get('text').encode('ascii', 'ignore'))
body = self.append_body_footer(article)
if article.get(EMBARGO):
embargo = '{}{}'.format('Embargo Content. Timestamp: ',
get_utc_schedule(article, EMBARGO).isoformat())
body = embargo + body
if article[ITEM_TYPE] == CONTENT_TYPE.PREFORMATTED:
anpa.append(body.encode('ascii', 'replace'))
else:
anpa.append(BeautifulSoup(body, "html.parser").text.encode('ascii', 'replace'))
anpa.append(b'\x0D\x0A')
if article.get('more_coming', False):
anpa.append('MORE'.encode('ascii'))
else:
anpa.append(article.get('source', '').encode('ascii'))
sign_off = article.get('sign_off', '').encode('ascii')
anpa.append((b'\x20' + sign_off) if len(sign_off) > 0 else b'')
anpa.append(b'\x0D\x0A')
anpa.append(b'\x03') # ETX
# time and date
anpa.append(datetime.datetime.now().strftime('%d-%m-%y %H-%M-%S').encode('ascii'))
anpa.append(b'\x04') # EOT
anpa.append(b'\x0D\x0A\x0D\x0A\x0D\x0A\x0D\x0A\x0D\x0A\x0D\x0A\x0D\x0A\x0D\x0A')
docs.append((pub_seq_num, b''.join(anpa)))
return docs
except Exception as ex:
raise FormatterError.AnpaFormatterError(ex, subscriber)
def format(self, article, subscriber):
try:
docs = []
for category in article.get('anpa_category'):
pub_seq_num = superdesk.get_resource_service(
'subscribers').generate_sequence_number(subscriber)
anpa = []
# selector codes are only injected for those subscribers that are defined
# in the mapper
selectors = dict()
SelectorcodeMapper().map(article,
category.get('qcode').upper(),
subscriber=subscriber,
formatted_item=selectors)
if 'selector_codes' in selectors and selectors[
'selector_codes']:
anpa.append(b'\x05')
anpa.append(selectors['selector_codes'].encode('ascii'))
anpa.append(b'\x0D\x0A')
# start of message header (syn syn soh)
anpa.append(b'\x16\x16\x01')
anpa.append(
article.get('service_level', 'a').lower().encode('ascii'))
# story number
anpa.append(str(pub_seq_num).zfill(4).encode('ascii'))
# field seperator
anpa.append(b'\x0A') # -LF
anpa.append(
map_priority(article.get('priority')).encode('ascii'))
anpa.append(b'\x20')
anpa.append(category['qcode'].encode('ascii'))
anpa.append(b'\x13')
# format identifier
if article[ITEM_TYPE] == CONTENT_TYPE.PREFORMATTED:
anpa.append(b'\x12')
else:
anpa.append(b'\x11')
anpa.append(b'\x20')
# keyword
keyword = 'bc-{}'.format(
self.append_legal(article=article,
truncate=True)).replace(' ', '-')
keyword = keyword[:24] if len(keyword) > 24 else keyword
anpa.append(keyword.encode('ascii'))
anpa.append(b'\x20')
# version field
anpa.append(b'\x20')
# reference field
anpa.append(b'\x20')
# filing date
anpa.append('{}-{}'.format(
article['_updated'].strftime('%m'),
article['_updated'].strftime('%d')).encode('ascii'))
anpa.append(b'\x20')
# add the word count
anpa.append(
str(article.get('word_count',
'0000')).zfill(4).encode('ascii'))
anpa.append(b'\x0D\x0A')
anpa.append(b'\x02') # STX
self._process_headline(anpa, article,
category['qcode'].encode('ascii'))
keyword = self.append_legal(article=article,
truncate=True).encode(
'ascii', 'ignore')
anpa.append(keyword)
take_key = article.get('anpa_take_key',
'').encode('ascii', 'ignore')
anpa.append((b'\x20' + take_key) if len(take_key) > 0 else b'')
anpa.append(b'\x0D\x0A')
if BYLINE in article:
anpa.append(article.get(BYLINE).encode('ascii', 'ignore'))
anpa.append(b'\x0D\x0A')
if article.get('dateline', {}).get('text'):
anpa.append(
article.get('dateline').get('text').encode(
'ascii', 'ignore'))
body = self.append_body_footer(article)
if article.get(EMBARGO):
embargo = '{}{}'.format(
'Embargo Content. Timestamp: ',
get_utc_schedule(article, EMBARGO).isoformat())
body = embargo + body
if article[ITEM_TYPE] == CONTENT_TYPE.PREFORMATTED:
anpa.append(body.encode('ascii', 'replace'))
else:
anpa.append(
BeautifulSoup(body, "html.parser").text.encode(
'ascii', 'replace'))
anpa.append(b'\x0D\x0A')
if article.get('more_coming', False):
anpa.append('MORE'.encode('ascii'))
else:
anpa.append(article.get('source', '').encode('ascii'))
sign_off = article.get('sign_off', '').encode('ascii')
anpa.append((b'\x20' + sign_off) if len(sign_off) > 0 else b'')
anpa.append(b'\x0D\x0A')
anpa.append(b'\x03') # ETX
# time and date
anpa.append(datetime.datetime.now().strftime(
'%d-%m-%y %H-%M-%S').encode('ascii'))
anpa.append(b'\x04') # EOT
anpa.append(
b'\x0D\x0A\x0D\x0A\x0D\x0A\x0D\x0A\x0D\x0A\x0D\x0A\x0D\x0A\x0D\x0A'
)
docs.append((pub_seq_num, b''.join(anpa)))
return docs
except Exception as ex:
raise FormatterError.AnpaFormatterError(ex, subscriber)
def format(self, article, subscriber):
"""
Constructs a dictionary that represents the parameters passed to the IPNews InsertNews stored procedure
:return: returns the sequence number of the subscriber and the constructed parameter dictionary
"""
try:
docs = []
for category in article.get('anpa_category'):
pub_seq_num = superdesk.get_resource_service('subscribers').generate_sequence_number(subscriber)
odbc_item = {'originator': article.get('source', None), 'sequence': pub_seq_num,
'category': category.get('qcode'),
'headline': article.get('headline', '').replace('\'', '\'\''),
'author': article.get('byline', '').replace('\'', '\'\''),
'keyword': article.get('slugline', None).replace('\'', '\'\''),
'subject_reference': set_subject(category, article)}
if 'subject_reference' in odbc_item and odbc_item['subject_reference'] is not None \
and odbc_item['subject_reference'] != '00000000':
odbc_item['subject'] = subject_codes[odbc_item['subject_reference'][:2] + '000000']
if odbc_item['subject_reference'][2:5] != '000':
odbc_item['subject_matter'] = subject_codes[odbc_item['subject_reference'][:5] + '000']
else:
odbc_item['subject_matter'] = ''
if not odbc_item['subject_reference'].endswith('000'):
odbc_item['subject_detail'] = subject_codes[odbc_item['subject_reference']]
else:
odbc_item['subject_detail'] = ''
else:
odbc_item['subject_reference'] = '00000000'
odbc_item['take_key'] = article.get('anpa_take_key', None) # @take_key
odbc_item['usn'] = article.get('unique_id', None) # @usn
if article[ITEM_TYPE] == CONTENT_TYPE.PREFORMATTED:
odbc_item['article_text'] = article.get('body_html', '').replace('\'', '\'\'') # @article_text
elif article[ITEM_TYPE] == CONTENT_TYPE.TEXT:
soup = BeautifulSoup(article.get('body_html', ''))
text = StringIO()
for p in soup.findAll('p'):
text.write('\x19\r\n')
ptext = p.get_text('\n')
for l in ptext.split('\n'):
if len(l) > 80:
text.write(textwrap.fill(l, 80).replace('\n', ' \r\n'))
else:
text.write(l + ' \r\n')
odbc_item['article_text'] = text.getvalue().replace('\'', '\'\'')
if 'genre' in article:
odbc_item['genre'] = article['genre'][0].get('name', None)
else:
odbc_item['genre'] = 'Current' # @genre
if article.get(ITEM_TYPE, CONTENT_TYPE.TEXT) == CONTENT_TYPE.TEXT:
odbc_item['texttab'] = 'x'
elif article.get(ITEM_TYPE, None) == CONTENT_TYPE.PREFORMATTED:
odbc_item['texttab'] = 't'
odbc_item['wordcount'] = article.get('word_count', None) # @wordcount
odbc_item['news_item_type'] = 'News'
odbc_item['priority'] = map_priority(article.get('priority')) # @priority
odbc_item['service_level'] = 'a' # @service_level
odbc_item['fullStory'] = 1
odbc_item['ident'] = '0' # @ident
SelectorcodeMapper().map(article, category.get('qcode').upper(),
subscriber=subscriber,
formatted_item=odbc_item)
headline_prefix = LocatorMapper().map(article, category.get('qcode').upper())
if headline_prefix:
odbc_item['headline'] = '{}:{}'.format(headline_prefix, odbc_item['headline'])
if article.get(EMBARGO):
embargo = '{}{}'.format('Embargo Content. Timestamp: ', article.get(EMBARGO).isoformat())
odbc_item['article_text'] = embargo + odbc_item['article_text']
docs.append((pub_seq_num, odbc_item))
return docs
except Exception as ex:
raise FormatterError.AAPIpNewsFormatterError(ex, subscriber)
def format(self, article, subscriber):
"""
Constructs a dictionary that represents the parameters passed to the IPNews InsertNews stored procedure
:return: returns the sequence number of the subscriber and the constructed parameter dictionary
"""
try:
docs = []
for category in article.get("anpa_category"):
pub_seq_num = superdesk.get_resource_service("subscribers").generate_sequence_number(subscriber)
odbc_item = {
"originator": article.get("source", None),
"sequence": pub_seq_num,
"category": category.get("qcode"),
"headline": article.get("headline", "").replace("'", "''"),
"author": article.get("byline", "").replace("'", "''"),
"keyword": self.append_legal(article=article, truncate=True).replace("'", "''"),
"subject_reference": set_subject(category, article),
}
if (
"subject_reference" in odbc_item
and odbc_item["subject_reference"] is not None
and odbc_item["subject_reference"] != "00000000"
):
odbc_item["subject"] = subject_codes[odbc_item["subject_reference"][:2] + "000000"]
if odbc_item["subject_reference"][2:5] != "000":
odbc_item["subject_matter"] = subject_codes[odbc_item["subject_reference"][:5] + "000"]
else:
odbc_item["subject_matter"] = ""
if not odbc_item["subject_reference"].endswith("000"):
odbc_item["subject_detail"] = subject_codes[odbc_item["subject_reference"]]
else:
odbc_item["subject_detail"] = ""
else:
odbc_item["subject_reference"] = "00000000"
odbc_item["take_key"] = article.get("anpa_take_key", None) # @take_key
odbc_item["usn"] = article.get("unique_id", None) # @usn
if article[ITEM_TYPE] == CONTENT_TYPE.PREFORMATTED: # @article_text
odbc_item["article_text"] = self.append_body_footer(article).replace("'", "''")
elif article[ITEM_TYPE] == CONTENT_TYPE.TEXT:
soup = BeautifulSoup(self.append_body_footer(article), "html.parser")
text = StringIO()
for p in soup.findAll("p"):
text.write("\x19\r\n")
ptext = p.get_text("\n")
for l in ptext.split("\n"):
if len(l) > 80:
text.write(textwrap.fill(l, 80).replace("\n", " \r\n"))
else:
text.write(l + " \r\n")
odbc_item["article_text"] = text.getvalue().replace("'", "''")
if "genre" in article:
odbc_item["genre"] = article["genre"][0].get("name", None)
else:
odbc_item["genre"] = "Current" # @genre
if article.get(ITEM_TYPE, CONTENT_TYPE.TEXT) == CONTENT_TYPE.TEXT:
odbc_item["texttab"] = "x"
elif article.get(ITEM_TYPE, None) == CONTENT_TYPE.PREFORMATTED:
odbc_item["texttab"] = "t"
odbc_item["wordcount"] = article.get("word_count", None) # @wordcount
odbc_item["news_item_type"] = "News"
odbc_item["priority"] = map_priority(article.get("priority")) # @priority
odbc_item["service_level"] = "a" # @service_level
odbc_item["fullStory"] = 1
odbc_item["ident"] = "0" # @ident
SelectorcodeMapper().map(
article, category.get("qcode").upper(), subscriber=subscriber, formatted_item=odbc_item
)
headline_prefix = LocatorMapper().map(article, category.get("qcode").upper())
if headline_prefix:
odbc_item["headline"] = "{}:{}".format(headline_prefix, odbc_item["headline"])
if article.get(EMBARGO):
embargo = "{}{}".format("Embargo Content. Timestamp: ", article.get(EMBARGO).isoformat())
odbc_item["article_text"] = embargo + odbc_item["article_text"]
docs.append((pub_seq_num, odbc_item))
return docs
except Exception as ex:
raise FormatterError.AAPIpNewsFormatterError(ex, subscriber)
def format(self, article, subscriber):
try:
docs = []
for category in article.get("anpa_category"):
pub_seq_num = superdesk.get_resource_service("subscribers").generate_sequence_number(subscriber)
anpa = []
# selector codes are only injected for those subscribers that are defined
# in the mapper
selectors = dict()
SelectorcodeMapper().map(
article, category.get("qcode").upper(), subscriber=subscriber, formatted_item=selectors
)
if "selector_codes" in selectors and selectors["selector_codes"]:
anpa.append(b"\x05")
anpa.append(selectors["selector_codes"].encode("ascii"))
anpa.append(b"\x0D\x0A")
# start of message header (syn syn soh)
anpa.append(b"\x16\x16\x01")
anpa.append(article.get("service_level", "a").lower().encode("ascii"))
# story number
anpa.append(str(pub_seq_num).zfill(4).encode("ascii"))
# field seperator
anpa.append(b"\x0A") # -LF
anpa.append(map_priority(article.get("priority")).encode("ascii"))
anpa.append(b"\x20")
anpa.append(category["qcode"].encode("ascii"))
anpa.append(b"\x13")
# format identifier
if article[ITEM_TYPE] == CONTENT_TYPE.PREFORMATTED:
anpa.append(b"\x12")
else:
anpa.append(b"\x11")
anpa.append(b"\x20")
# keyword
keyword = "bc-{}".format(article.get("slugline", "")).replace(" ", "-")
keyword = keyword[:24] if len(keyword) > 24 else keyword
anpa.append(keyword.encode("ascii"))
anpa.append(b"\x20")
# version field
anpa.append(b"\x20")
# reference field
anpa.append(b"\x20")
# filing date
anpa.append(
"{}-{}".format(article["_updated"].strftime("%m"), article["_updated"].strftime("%d")).encode(
"ascii"
)
)
anpa.append(b"\x20")
# add the word count
anpa.append(str(article.get("word_count", "0000")).zfill(4).encode("ascii"))
anpa.append(b"\x0D\x0A")
anpa.append(b"\x02") # STX
self._process_headline(anpa, article, category["qcode"].encode("ascii"))
keyword = article.get("slugline", "").encode("ascii", "ignore")
anpa.append(keyword)
take_key = article.get("anpa_take_key", "").encode("ascii", "ignore")
anpa.append((b"\x20" + take_key) if len(take_key) > 0 else b"")
anpa.append(b"\x0D\x0A")
if BYLINE in article:
anpa.append(article.get(BYLINE).encode("ascii", "ignore"))
anpa.append(b"\x0D\x0A")
if "dateline" in article and "text" in article["dateline"]:
anpa.append(article.get("dateline").get("text").encode("ascii", "ignore"))
body = self.append_body_footer(article)
if article.get(EMBARGO):
embargo = "{}{}".format("Embargo Content. Timestamp: ", article.get(EMBARGO).isoformat())
body = embargo + body
if article[ITEM_TYPE] == CONTENT_TYPE.PREFORMATTED:
anpa.append(body.encode("ascii", "replace"))
else:
anpa.append(BeautifulSoup(body, "html.parser").text.encode("ascii", "replace"))
anpa.append(b"\x0D\x0A")
if article.get("more_coming", False):
anpa.append("MORE".encode("ascii"))
else:
anpa.append(article.get("source", "").encode("ascii"))
sign_off = article.get("sign_off", "").encode("ascii")
anpa.append((b"\x20" + sign_off) if len(sign_off) > 0 else b"")
anpa.append(b"\x0D\x0A")
anpa.append(b"\x03") # ETX
# time and date
anpa.append(datetime.datetime.now().strftime("%d-%m-%y %H-%M-%S").encode("ascii"))
anpa.append(b"\x04") # EOT
anpa.append(b"\x0D\x0A\x0D\x0A\x0D\x0A\x0D\x0A\x0D\x0A\x0D\x0A\x0D\x0A\x0D\x0A")
docs.append((pub_seq_num, b"".join(anpa)))
return docs
except Exception as ex:
raise FormatterError.AnpaFormatterError(ex, subscriber)
def format(self, article, subscriber):
"""
Constructs a dictionary that represents the parameters passed to the IPNews InsertNews stored procedure
:return: returns the sequence number of the subscriber and the constructed parameter dictionary
"""
try:
docs = []
for category in article.get('anpa_category'):
pub_seq_num = superdesk.get_resource_service('subscribers').generate_sequence_number(subscriber)
odbc_item = {'originator': article.get('source', None), 'sequence': pub_seq_num,
'category': category.get('qcode'),
'headline': article.get('headline', '').replace('\'', '\'\''),
'author': article.get('byline', '').replace('\'', '\'\''),
'keyword': self.append_legal(article=article, truncate=True).replace('\'', '\'\''),
'subject_reference': set_subject(category, article)}
if 'subject_reference' in odbc_item and odbc_item['subject_reference'] is not None \
and odbc_item['subject_reference'] != '00000000':
odbc_item['subject'] = subject_codes[odbc_item['subject_reference'][:2] + '000000']
if odbc_item['subject_reference'][2:5] != '000':
odbc_item['subject_matter'] = subject_codes[odbc_item['subject_reference'][:5] + '000']
else:
odbc_item['subject_matter'] = ''
if not odbc_item['subject_reference'].endswith('000'):
odbc_item['subject_detail'] = subject_codes[odbc_item['subject_reference']]
else:
odbc_item['subject_detail'] = ''
else:
odbc_item['subject_reference'] = '00000000'
odbc_item['take_key'] = article.get('anpa_take_key', None) # @take_key
odbc_item['usn'] = article.get('unique_id', None) # @usn
if article[ITEM_TYPE] == CONTENT_TYPE.PREFORMATTED: # @article_text
odbc_item['article_text'] = self.append_body_footer(article).replace('\'', '\'\'')
elif article[ITEM_TYPE] == CONTENT_TYPE.TEXT:
soup = BeautifulSoup(self.append_body_footer(article), "html.parser")
text = StringIO()
for p in soup.findAll('p'):
text.write('\x19\r\n')
ptext = p.get_text('\n')
for l in ptext.split('\n'):
if len(l) > 80:
text.write(textwrap.fill(l, 80).replace('\n', ' \r\n'))
else:
text.write(l + ' \r\n')
odbc_item['article_text'] = text.getvalue().replace('\'', '\'\'')
if 'genre' in article:
odbc_item['genre'] = article['genre'][0].get('name', None)
else:
odbc_item['genre'] = 'Current' # @genre
if article.get(ITEM_TYPE, CONTENT_TYPE.TEXT) == CONTENT_TYPE.TEXT:
odbc_item['texttab'] = 'x'
elif article.get(ITEM_TYPE, None) == CONTENT_TYPE.PREFORMATTED:
odbc_item['texttab'] = 't'
odbc_item['wordcount'] = article.get('word_count', None) # @wordcount
odbc_item['news_item_type'] = 'News'
odbc_item['priority'] = map_priority(article.get('priority')) # @priority
odbc_item['service_level'] = 'a' # @service_level
odbc_item['fullStory'] = 1
odbc_item['ident'] = '0' # @ident
SelectorcodeMapper().map(article, category.get('qcode').upper(),
subscriber=subscriber,
formatted_item=odbc_item)
headline_prefix = LocatorMapper().map(article, category.get('qcode').upper())
if headline_prefix:
odbc_item['headline'] = '{}:{}'.format(headline_prefix, odbc_item['headline'])
if article.get(EMBARGO):
embargo = '{}{}'.format('Embargo Content. Timestamp: ', article.get(EMBARGO).isoformat())
odbc_item['article_text'] = embargo + odbc_item['article_text']
docs.append((pub_seq_num, odbc_item))
return docs
except Exception as ex:
raise FormatterError.AAPIpNewsFormatterError(ex, subscriber)
