def main(target_file=None, keep_alive='False'):
""" language tool based grammar checker """
keep_alive = keep_alive.lower() == 'true'
pages = convert_pdf_to_text(target_file)
rez = []
with LanguagetoolServer(LT_PATH, keep_alive) as grammar_checker:
for num, page in enumerate(pages):
for paragraph in page:
# fixing new-lines and spaces for languagetool
for error in grammar_checker(new_lines_replaser(paragraph)):
rule_id = error.get('ruleId')
cur_msg = MESSAGES_BY_RULES.get(
rule_id, MESSAGES_BY_RULES['language-tool'])
rez.append({
'id':
cur_msg['id'],
'page':
'Slide %s' % (num + 1),
'msg_name':
rule_id,
'msg':
'%s - %s' %
(error.get('locqualityissuetype'), error.get('msg')),
'help':
error.get('context')
})
return rez
def main(target_file=None, ):
""" No text found checker """
for page in convert_pdf_to_text(target_file):
for paragraph in page:
if paragraph:
return []
return [dict(id='W1001',
msg_name='no-text-found',
msg='No text found',
page='',
help="No text found: No text found in presentation file"), ]
def main(target_file=None, ):
""" No text found checker """
for page in convert_pdf_to_text(target_file):
for paragraph in page:
if paragraph:
return []
return [
dict(id='W1001',
msg_name='no-text-found',
msg='No text found',
page='',
help="No text found: No text found in presentation file"),
]
def main(target_file=None, keep_alive='False'):
""" language tool based grammar checker """
keep_alive = keep_alive.lower() == 'true'
pages = convert_pdf_to_text(target_file)
rez = []
with LanguagetoolServer(LT_PATH, keep_alive) as grammar_checker:
for num, page in enumerate(pages):
for paragraph in page:
# fixing new-lines and spaces for languagetool
for error in grammar_checker(new_lines_replaser(paragraph)):
rule_id = error.get('ruleId')
cur_msg = MESSAGES_BY_RULES.get(
rule_id,
MESSAGES_BY_RULES['language-tool'])
rez.append({
'id': cur_msg['id'],
'page': 'Slide %s' % (num + 1),
'msg_name': rule_id,
'msg': '%s - %s' % (error.get('locqualityissuetype'),
error.get('msg')),
'help': error.get('context')})
return rez
def main(target_file=None, source_file=None, re_options=None, msg_id=None,
msg_name=None, msg=None, msg_help=None, msg_info=None):
""" Runner for regexp config files. Takes rules_source file """
pattern = open(get_file_path(source_file), 'rb').read()
options = [getattr(re, o) for o in re_options.split('\n') if o]
regexp = re.compile(pattern, *options)
if msg_info:
message = dict(id=msg_id, msg_name=msg_name, msg=msg, help=msg_help)
return help_msg_formatter((message,), msg_info)
pages = convert_pdf_to_text(target_file)
rez = []
for num, page in enumerate(pages):
for paragraph in page:
match = regexp.search(paragraph)
if match:
rez.append({
'id': msg_id,
'page': 'Slide %s' % (num + 1),
'msg_name': msg_name,
'msg': '%s: "%s" mentioned in "%s"' % (
msg, str(match.group()), paragraph),
'help': msg_help})
return rez
