migration api upgraded

This commit is contained in:
Untone 2021-10-04 20:06:05 +03:00
parent 633c07d58d
commit 3efba57cf3
13 changed files with 77 additions and 47 deletions

2
.gitignore vendored
View File

@ -135,4 +135,4 @@ discours.crt
Pipfile.lock
migration/data
migration/content
migration/content/**/*.md

View File

@ -3,16 +3,27 @@ from migration.tables.users import migrate as migrateUser
from migration.tables.content_items import migrate as migrateShout
from migration.tables.content_item_categories import migrate as migrateTopic
from migration.utils import DateTimeEncoder
from orm import Community
def users(limit):
print('migrating users...')
data = json.loads(open('migration/data/users.json').read())
newdata = {}
exportData = {}
counter = 0
# limit = 100
#try:
for entry in data:
oid = entry['_id']
newdata[oid] = migrateUser(entry)
user = migrateUser(entry)
newdata[oid] = user
del user['password']
del user['notifications']
# del user['oauth']
del user['emailConfirmed']
del user['username']
del user['email']
exportData[user['slug']] = user
counter += 1
if counter > limit:
break
@ -20,25 +31,27 @@ def users(limit):
# print(str(counter) + '/' + str(len(data)) + ' users entries were migrated')
# print('try to remove database first')
open('migration/data/users.dict.json','w').write( json.dumps(newdata, cls=DateTimeEncoder) )
open('../src/data/authors.json','w').write( json.dumps(exportData, cls=DateTimeEncoder) )
print(str(counter) + ' users entries were migrated')
def topics(limit):
def topics():
print('migrating topics...')
data = json.loads(open('migration/data/content_item_categories.json').read())
newdata = {}
exportData = {}
counter = 0
try:
for entry in data:
oid = entry['_id']
newdata[oid] = migrateTopic(entry)
exportData[entry['slug']] = newdata[oid]
counter += 1
if counter > limit:
break
except Exception:
print(str(counter) + '/' + str(len(data)) + ' topics were migrated')
print('try to remove database first')
open('migration/data/topics.dict.json','w').write( json.dumps(newdata, cls=DateTimeEncoder) )
open('../src/data/topics.json','w').write( json.dumps(exportData, cls=DateTimeEncoder) )
print(str(counter) + ' topics were migrated')
def shouts(limit):
@ -47,20 +60,23 @@ def shouts(limit):
discoursAuthor = 0
data = json.loads(open('migration/data/content_items.json').read())
newdata = {}
print(str(len(data)) + ' entries was loaded. now migrating...')
print(str(len(data)) + ' entries loaded. now migrating...')
errored = []
exportData = {}
for entry in data:
try:
oid = entry['_id']
newdata[oid] = migrateShout(entry)
counter += 1
shout = migrateShout(entry)
newdata[oid] = shout
author = newdata[oid]['authors'][0]['slug']
if author == 'discours':
discoursAuthor += 1
line = str(counter) + ': ' + newdata[oid]['slug'] + " @" + str(author)
if shout['layout'] == 'article':
counter += 1
exportData[shout['slug']] = shout
print(line)
# counter += 1
if author == 'discours.io':
discoursAuthor += 1
open('./shouts.id.log','a').write(line + '\n')
if counter > limit:
break
@ -70,29 +86,33 @@ def shouts(limit):
raise Exception
open('migration/data/shouts.dict.json','w').write( json.dumps(newdata, cls=DateTimeEncoder) )
open('../src/data/articles.json','w').write( json.dumps(exportData, cls=DateTimeEncoder) )
print(str(counter) + ' shouts were migrated')
print(str(discoursAuthor) + ' from them by @discours')
print(str(discoursAuthor) + ' from them by @discours.io')
print(str(len(errored)) + ' shouts without authors')
if __name__ == '__main__':
import sys
if len(sys.argv) > 1:
limit = int(sys.argv[2])
if sys.argv[1] == "users":
users(limit)
users(668)
elif sys.argv[1] == "topics":
topics(limit)
topics()
elif sys.argv[1] == "shouts":
shouts(limit)
elif sys.argv[1] == "comments":
comments(limit)
pass
Community.create(**{
'slug': 'discours.io',
'name': 'Дискурс',
'pic': 'https://discours.io/images/logo-min.svg',
'createdBy': '0',
'createdAt': ts
})
shouts(3626)
elif sys.argv[1] == "all":
topics(limit)
users(limit)
shouts(limit)
topics()
users(668)
shouts(3626)
elif sys.argv[1] == "bson":
import migration.bson2json
bson2json.json_tables()
else:
print('usage: python migrate.py <all|topics|users|shouts|comments> <stop_index>')
print('usage: python migrate.py <all|topics|users|shouts|comments>')

BIN
migration/.DS_Store vendored Normal file

Binary file not shown.

BIN
migration/content/.DS_Store vendored Normal file

Binary file not shown.

View File

View File

View File

View File

View File

View File

@ -1 +1 @@
__all__ = ["users"]
__all__ = ["users", "tags", "content_items", "comments"],

View File

@ -13,7 +13,7 @@ def migrate(entry):
'slug': entry['slug'],
'createdBy': entry['createdBy'], # NOTE: uses an old user id
'createdAt': entry['createdAt'],
'value': entry['title'].lower(),
'title': entry['title'].lower(),
'parents': [],
'children': [],
'old_id': entry['_id']

View File

@ -14,7 +14,7 @@ from orm.base import local_session
users_dict = json.loads(open(abspath('migration/data/users.dict.json')).read())
users_dict['0'] = {
'id': 9999999,
'slug': 'discours',
'slug': 'discours.io',
'name': 'Дискурс',
'userpic': 'https://discours.io/images/logo-mini.svg'
}
@ -56,6 +56,7 @@ def migrate(entry, limit=3626, start=0):
r = {
'layout': type2layout[entry['type']],
'title': entry['title'],
'community': 0,
'authors': [],
'topics': [],
'published': entry.get('published', False),
@ -87,10 +88,9 @@ def migrate(entry, limit=3626, start=0):
if body_orig == '':
print('EMPTY BODY!')
else:
# body_html = str(BeautifulSoup(body_orig, features="html.parser"))
# body = html2text(body_orig).replace('****', '**')
body_html = str(BeautifulSoup(body_orig, features="html.parser"))
r['body'] = html2text(body_html).replace('****', '**')
r['old_id'] = entry.get('_id')
r['body'] = body_orig
else:
print(r['slug'] + ': literature has no media')
elif entry.get('type') == 'Video':
@ -109,8 +109,8 @@ def migrate(entry, limit=3626, start=0):
if r.get('body') is None:
body_orig = entry.get('body', '')
body_html = BeautifulSoup(body_orig, features="html.parser")
r['body'] = body_html # html2text(body_orig).replace('****', '**')
body_html = str(BeautifulSoup(body_orig, features="html.parser"))
r['body'] = html2text(body_html).replace('****', '**')
r['old_id'] = entry.get('_id')
body = r.get('body')
@ -141,12 +141,12 @@ def migrate(entry, limit=3626, start=0):
if user is None:
user = session.query(User).filter(User.slug == authordata['slug']).first()
slug = user.slug
name = user.name
slug = user['slug']
name = user['name']
userpic = user.userpic
else:
# no application, no author!
slug = 'discours'
slug = 'discours.io'
name = 'Дискурс'
userpic = 'https://discours.io/images/logo-mini.svg'
with local_session() as session:
@ -160,19 +160,22 @@ def migrate(entry, limit=3626, start=0):
metadata = {}
metadata['title'] = r.get('title')
metadata['authors'] = r.get('authors')
metadata['createdAt'] = entry.get('createdAt', ts)
metadata['layout'] = type2layout[entry['type']]
if r.get('cover', False):
metadata['cover'] = r.get('cover')
post = frontmatter.Post(body, **metadata)
dumped = frontmatter.dumps(post)
if entry['published']:
if r.get('old_id', None):
ext = 'html'
content = str(body).replace('<p></p>', '').replace('<p> </p>', '')
else:
#if r.get('old_id', None):
# ext = 'html'
# content = str(body).replace('<p></p>', '').replace('<p> </p>', '')
#else:
ext = 'md'
content = dumped
open('migration/content/' + entry['type'].lower() + '/' + r['slug'] + '.' + ext, 'w').write(content)
open('migration/content/' + metadata['layout'] + '/' + r['slug'] + '.' + ext, 'w').write(content)
try:
shout_dict = r.copy()
@ -186,8 +189,15 @@ def migrate(entry, limit=3626, start=0):
shout_dict['publishedAt'] = parse(entry.get('publishedAt'))
else:
shout_dict['publishedAt'] = ts
del shout_dict['published']
del shout_dict['views'] # FIXME
del shout_dict['rating'] # FIXME
del shout_dict['ratings']
try:
s = Shout.create(**shout_dict)
r['id'] = s.id
except:
pass
except:
r['body'] = 'body moved'
print(r)

View File

@ -9,12 +9,12 @@ def migrate(entry):
children: [String] # and children
}
```
creator = get_new_user_id(entry['cratedBy'])
creator = get_new_user_id(entry['createdBy'])
return {
'slug': entry['slug'],
'createdBy': creator_id, # NOTE: uses an old user id
'createdAt': entry['createdAt'],
'value': entry['value'].lower(),
'title': entry['value'].lower(),
'parents': [],
'children': []
}