mirror of
https://github.com/ail-project/ail-framework.git
synced 2024-11-22 14:17:16 +00:00
chg: [mail exporter] add obj content extract for each regex match
This commit is contained in:
parent
c01b806ae3
commit
546d6538fd
2 changed files with 45 additions and 7 deletions
|
@ -145,5 +145,6 @@ class MailExporterTracker(MailExporter):
|
|||
body = f"AIL Framework, New occurrence for {tracker_type} tracker: {tracker_name}\n"
|
||||
body += f'Item: {obj.id}\nurl:{obj.get_link()}'
|
||||
|
||||
# print(body)
|
||||
for mail in tracker.get_mails():
|
||||
self._export(mail, subject, body)
|
||||
|
|
|
@ -41,6 +41,8 @@ class Tracker_Regex(AbstractModule):
|
|||
self.tracked_regexs = Tracker.get_tracked_regexs()
|
||||
self.last_refresh = time.time()
|
||||
|
||||
self.obj = None
|
||||
|
||||
# Exporter
|
||||
self.exporters = {'mail': MailExporterTracker(),
|
||||
'webhook': WebHookExporterTracker()}
|
||||
|
@ -56,6 +58,7 @@ class Tracker_Regex(AbstractModule):
|
|||
print('Tracked regex refreshed')
|
||||
|
||||
obj = ail_objects.get_object(obj_type, subtype, obj_id)
|
||||
self.obj = obj
|
||||
obj_id = obj.get_id()
|
||||
obj_type = obj.get_type()
|
||||
|
||||
|
@ -66,12 +69,46 @@ class Tracker_Regex(AbstractModule):
|
|||
content = obj.get_content()
|
||||
|
||||
for dict_regex in self.tracked_regexs[obj_type]:
|
||||
matched = self.regex_findall(dict_regex['regex'], obj_id, content)
|
||||
if matched:
|
||||
self.new_tracker_found(dict_regex['tracked'], 'regex', obj)
|
||||
matches = self.regex_finditer(dict_regex['regex'], obj_id, content)
|
||||
if matches:
|
||||
self.new_tracker_found(dict_regex['tracked'], 'regex', obj, matches)
|
||||
|
||||
def new_tracker_found(self, tracker_name, tracker_type, obj):
|
||||
def extract_matches(self, re_matches, limit=500, lines=5):
|
||||
matches = []
|
||||
content = self.obj.get_content()
|
||||
l_content = len(content)
|
||||
for match in re_matches:
|
||||
start = match[0]
|
||||
value = match[2]
|
||||
end = match[1]
|
||||
|
||||
# Start
|
||||
if start > limit:
|
||||
i_start = start - limit
|
||||
else:
|
||||
i_start = 0
|
||||
str_start = content[i_start:start].splitlines()
|
||||
if len(str_start) > lines:
|
||||
str_start = '\n'.join(str_start[-lines + 1:])
|
||||
else:
|
||||
str_start = content[i_start:start]
|
||||
|
||||
# End
|
||||
if end + limit > l_content:
|
||||
i_end = l_content
|
||||
else:
|
||||
i_end = end + limit
|
||||
str_end = content[end:i_end].splitlines()
|
||||
if len(str_end) > lines:
|
||||
str_end = '\n'.join(str_end[:lines + 1])
|
||||
else:
|
||||
str_end = content[end:i_end]
|
||||
matches.append((value, f'{str_start}{value}{str_end}'))
|
||||
return matches
|
||||
|
||||
def new_tracker_found(self, tracker_name, tracker_type, obj, re_matches):
|
||||
obj_id = obj.get_id()
|
||||
matches = None
|
||||
for tracker_uuid in Tracker.get_trackers_by_tracked_obj_type(tracker_type, obj.get_type(), tracker_name):
|
||||
tracker = Tracker.Tracker(tracker_uuid)
|
||||
|
||||
|
@ -93,8 +130,9 @@ class Tracker_Regex(AbstractModule):
|
|||
obj.add_tag(tag)
|
||||
|
||||
if tracker.mail_export():
|
||||
# TODO add matches + custom subjects
|
||||
self.exporters['mail'].export(tracker, obj)
|
||||
if not matches:
|
||||
matches = self.extract_matches(re_matches)
|
||||
self.exporters['mail'].export(tracker, obj, matches)
|
||||
|
||||
if tracker.webhook_export():
|
||||
self.exporters['webhook'].export(tracker, obj)
|
||||
|
@ -103,4 +141,3 @@ class Tracker_Regex(AbstractModule):
|
|||
if __name__ == "__main__":
|
||||
module = Tracker_Regex()
|
||||
module.run()
|
||||
# module.compute('submitted/2023/05/02/submitted_b1e518f1-703b-40f6-8238-d1c22888197e.gz')
|
||||
|
|
Loading…
Reference in a new issue