Final version
This script lists all doubled notes (with 20 chars of subject, 20 chars of content and IDs) grouped by content
It ignores creation date / attachments while compring notes
import json
notes_path = "C:/Users/xxxxxxx/AppData/Local/Vivaldi/User Data/Default/Notes"
class Note:
def __init__(self, id, subject, content, type, url, attachments):
self.id = id
self.subject = subject
self.content = content
self.type = type
self.url = url
self.attachments = attachments
def __hash__(self):
return hash((self.subject, self.content, self.type, self.url, self.attachments))
def __eq__(self, other):
return self.__class__ == other.__class__ and (self.subject, self.content, self.type, self.url, self.attachments) == (other.subject, other.content, other.type, other.url, other.attachments)
def __ne__(self, other):
return not(self == other)
flattened_notes = {}
def load(node, path):
for item in node['children']:
if item['type'] == 'note':
process_note(item, path)
elif item['type'] == 'folder' or item['type'] == 'other' or item['type'] == 'trash':
load(item, path + item['id'] + '\\')
def process_note(note, path):
flattened_notes[note['id']] = Note(note['id'], note['subject'], note['content'], note['type'], note['url'], 0)
# 0 => Ignoring attachments!
with open(notes_path, mode='r', encoding="utf8") as file:
notes = json.load(file)
load(notes, '')
print('Loaded notes: ' + str(len(flattened_notes.keys())))
flipped_multidict = {}
for key, value in flattened_notes.items():
flipped_multidict.setdefault(value, set()).add(key)
doubles = [(key.subject[0:20], key.content[0:20], values) for key, values in flipped_multidict.items() if len(values) > 1]
for item in doubles:
print(item)
@Pesala @Ayespy @Gwen-Dragon I am not sure if this is the right category for this...
