def add_tag():
""" Add tag from a given document. This function
uses Elasticsearch's scripting language."""
index = request.form.get('index','projects')
doc_id = request.form.get('doc_id')
tag_added = request.form.get('tag')
# construct script based on if tag_added is topic or element
if tag_added in topics:
script = {"script": f"if (ctx._source.tags != null) {{ctx._source.tags.add('{tag_added}')}} else {{ ctx._source.tags = ['{tag_added}'] }}"}
elif tag_added in element_tags:
script = {"script": f"if (ctx._source.element_tags != null) {{ctx._source.element_tags.add('{tag_added}')}} else {{ ctx._source.element_tags = ['{tag_added}'] }}"}
# use the update API to run Elasticsearch script that removes the tag
client.update(index=index, doc_type='doc', id=doc_id, body=script, refresh=True)
# construct script to add tag to added_tags field if it does not already exist or append tag_added
script = {
"script" : f"if (ctx._source.containsKey('added_tags')) {{ctx._source.added_tags.add('{tag_added}');}} else {{ctx._source.added_tags = ['{tag_added}']}}"
}
# add tag to "added_tags" field
client.update(index=index, doc_type='doc', id=doc_id, body=script, refresh=True)
return 'doc updated'
def bookmark():
index = request.form.get('index','projects')
doc_id = request.form.get('doc_id')
marked = request.form.get('marked')
# update objectives and notes field for doc in database
client.update(index=index,
doc_type='doc',
id=doc_id,
body={"doc": {"bookmarked":marked}})
return 'doc updated'
def update_database():
now = datetime.datetime.now()
year, month, day = now.year, now.month, now.day
# create temporary directory for downloading files
CWD = os.getcwd()
TMP_DIRECTORY = os.path.join(CWD, r'.tmp')
DOWNLOADS_FOLDER = os.path.join(TMP_DIRECTORY,
f"{year:04}{month:02}{day:02}")
XML_PATH = os.path.join(DOWNLOADS_FOLDER, "xml")
JSON_PATH = os.path.join(DOWNLOADS_FOLDER, "json")
PROJECT_FILES_PATH = os.path.join(JSON_PATH, "projects")
PUB_FILES_PATH = os.path.join(JSON_PATH, "publications")
try:
shutil.rmtree(TMP_DIRECTORY)
except:
pass
os.makedirs(DOWNLOADS_FOLDER)
os.makedirs(XML_PATH)
os.makedirs(JSON_PATH)
os.makedirs(PROJECT_FILES_PATH)
os.makedirs(PUB_FILES_PATH)
# scrape TRID site
webscrapper.scrape_trid(TMP_DIRECTORY, DOWNLOADS_FOLDER)
# index documents
index.index_documents("projects", PROJECT_FILES_PATH)
index.tag_documents("projects", topics, element_tags)
index.index_documents("publications", PUB_FILES_PATH)
index.tag_documents("publications", topics, element_tags)
# delete temporary downloads directory
shutil.rmtree(TMP_DIRECTORY)
# update appData index
today = str(datetime.date.today())
client.update(index='appdata',
doc_type='doc',
id=1,
body={'doc': {
'last_update': today
}})
return "database updated"
def annotate():
if request.method == 'POST':
# update record from form submission
search_type = request.form.get('type', 'search')
search_query = request.form.get('query')
index = request.form.get('index', 'projects')
filter_topic = request.form.get('topic', 'all')
filter_element = request.form.get('element', 'all')
filter_status = request.form.get('status', 'all')
date_range = request.form.get('dateRange', '50')
sort_by = request.form.get('sortBy', 'date')
doc_type = index[:-1]
objectives = []
notes = None
for key in request.form:
if key in {'index', 'doc_id'}:
continue
if 'objective' in key:
# store objectives
objectives.append(key)
if 'notes' in key and request.form.get(key):
# store notes
notes = request.form.get(key)
# notes = notes.strip()
doc_id = request.form.get('doc_id')
# update objectives and notes field for doc in database
client.update(index=index,
doc_type='doc',
id=doc_id,
body={"doc": {
"objectives": objectives,
"notes": notes
}})
args = dict(type=search_type,
query=search_query,
index=index,
topic=filter_topic,
element=filter_element,
status=filter_status,
dateRange=date_range,
sortBy=sort_by)
return 'form submitted'
