remove duplicated tags from Joplin

remove_duplicated_tags.py

from api import get_api

import time

start_time = time.time()

api = get_api()

f = open('duplicates-logs.txt', 'w')

all_tags = api.get_all_tags()
duplicated_tags = {}

# extract tags that are duplicated
unique_titles = {}
for tag in all_tags:
    if tag.title in unique_titles:
        if tag.title in duplicated_tags:
            duplicated_tags[tag.title] += [tag]
        else:
            duplicated_tags[tag.title] = unique_titles[tag.title]
            duplicated_tags[tag.title] += [tag]
    else:
        unique_titles[tag.title] = [tag]

for title, tags in duplicated_tags.items():
    main_tag = tags[0]
    tags_to_remove = tags[1:]

    tagged_notes = []
    for tag in tags:
        tag_id = tag.id

        tagged_notes += api.get_all_notes(tag_id=tag_id)

    for note in tagged_notes:
        note_tags = api.get_all_tags(note_id=note.id)
        if not main_tag in note_tags:
            print(f"adding tag {main_tag.title}, id {main_tag.id} to note {note.title}, id {note.id}", file=f)
            api.add_tag_to_note(main_tag.id, note.id)

    for tag in tags_to_remove:
        print(f"deleting tag {tag.title}, id {tag.id}", file=f)
        api.delete_tag(tag.id)

print(file=f)
print(f"duplicated tags: {duplicated_tags}", file=f)
print(f"total of titles: {len(duplicated_tags)}", file=f)
print(f"total of removed tags: {sum([len(tags) for tags in duplicated_tags.values()]) - len(duplicated_tags)}", file=f)

print(file=f)
print("--- %.2f seconds ---" % (time.time() - start_time), file=f)

f.close()

total of removed tags: 471

--- 528.98 seconds ---

from joppy.api import Api

API_TOKEN = "token"


def get_api():
    # Create a new Api instance.
    api = Api(token=API_TOKEN)

    return api

Nice script. Please note, if you use a newer version of joppy (from 0.1.0 on), the API responses are objects and not dicts anymore. You can use for example tag.title instead of tag['title'].

@marph91 thanks, I updated the script