This commit is contained in:
2023-10-05 23:18:06 +03:00
parent 3d659caa6e
commit 5fedd007c7
23 changed files with 8 additions and 4488 deletions

View File

@@ -1 +0,0 @@
__all__ = (["users", "topics", "content_items", "comments"],)

View File

@@ -1,209 +0,0 @@
from datetime import datetime, timezone
from dateutil.parser import parse as date_parse
from services.db import local_session
from migration.html2text import html2text
from orm.reaction import Reaction, ReactionKind
from orm.shout import ShoutReactionsFollower
from orm.topic import TopicFollower
from orm.user import User
from orm.shout import Shout
ts = datetime.now(tz=timezone.utc)
def auto_followers(session, topics, reaction_dict):
# creating shout's reactions following for reaction author
following1 = (
session.query(ShoutReactionsFollower)
.where(ShoutReactionsFollower.follower == reaction_dict["createdBy"])
.filter(ShoutReactionsFollower.shout == reaction_dict["shout"])
.first()
)
if not following1:
following1 = ShoutReactionsFollower.create(
follower=reaction_dict["createdBy"], shout=reaction_dict["shout"], auto=True
)
session.add(following1)
# creating topics followings for reaction author
for t in topics:
tf = (
session.query(TopicFollower)
.where(TopicFollower.follower == reaction_dict["createdBy"])
.filter(TopicFollower.topic == t["id"])
.first()
)
if not tf:
topic_following = TopicFollower.create(
follower=reaction_dict["createdBy"], topic=t["id"], auto=True
)
session.add(topic_following)
def migrate_ratings(session, entry, reaction_dict):
for comment_rating_old in entry.get("ratings", []):
rater = (
session.query(User)
.filter(User.oid == comment_rating_old["createdBy"])
.first()
)
re_reaction_dict = {
"shout": reaction_dict["shout"],
"replyTo": reaction_dict["id"],
"kind": ReactionKind.LIKE
if comment_rating_old["value"] > 0
else ReactionKind.DISLIKE,
"createdBy": rater.id if rater else 1,
}
cts = comment_rating_old.get("createdAt")
if cts:
re_reaction_dict["createdAt"] = date_parse(cts)
try:
# creating reaction from old rating
rr = Reaction.create(**re_reaction_dict)
following2 = (
session.query(ShoutReactionsFollower)
.where(ShoutReactionsFollower.follower == re_reaction_dict["createdBy"])
.filter(ShoutReactionsFollower.shout == rr.shout)
.first()
)
if not following2:
following2 = ShoutReactionsFollower.create(
follower=re_reaction_dict["createdBy"], shout=rr.shout, auto=True
)
session.add(following2)
session.add(rr)
except Exception as e:
print("[migration] comment rating error: %r" % re_reaction_dict)
raise e
session.commit()
async def migrate(entry, storage):
"""
{
"_id": "hdtwS8fSyFLxXCgSC",
"body": "<p>",
"contentItem": "mnK8KsJHPRi8DrybQ",
"createdBy": "bMFPuyNg6qAD2mhXe",
"thread": "01/",
"createdAt": "2016-04-19 04:33:53+00:00",
"ratings": [
{ "createdBy": "AqmRukvRiExNpAe8C", "value": 1 },
{ "createdBy": "YdE76Wth3yqymKEu5", "value": 1 }
],
"rating": 2,
"updatedAt": "2020-05-27 19:22:57.091000+00:00",
"updatedBy": "0"
}
->
type Reaction {
id: Int!
shout: Shout!
createdAt: DateTime!
createdBy: User!
updatedAt: DateTime
deletedAt: DateTime
deletedBy: User
range: String # full / 0:2340
kind: ReactionKind!
body: String
replyTo: Reaction
stat: Stat
old_id: String
old_thread: String
}
"""
old_ts = entry.get("createdAt")
reaction_dict = {
"createdAt": (ts if not old_ts else date_parse(old_ts)),
"body": html2text(entry.get("body", "")),
"oid": entry["_id"],
}
shout_oid = entry.get("contentItem")
if shout_oid not in storage["shouts"]["by_oid"]:
if len(storage["shouts"]["by_oid"]) > 0:
return shout_oid
else:
print("[migration] no shouts migrated yet")
raise Exception
return
else:
stage = "started"
reaction = None
with local_session() as session:
author = session.query(User).filter(User.oid == entry["createdBy"]).first()
old_shout = storage["shouts"]["by_oid"].get(shout_oid)
if not old_shout:
raise Exception("no old shout in storage")
else:
stage = "author and old id found"
try:
shout = (
session.query(Shout)
.where(Shout.slug == old_shout["slug"])
.one()
)
if shout:
reaction_dict["shout"] = shout.id
reaction_dict["createdBy"] = author.id if author else 1
reaction_dict["kind"] = ReactionKind.COMMENT
# creating reaction from old comment
reaction = Reaction.create(**reaction_dict)
session.add(reaction)
# session.commit()
stage = "new reaction commited"
reaction_dict = reaction.dict()
topics = [t.dict() for t in shout.topics]
auto_followers(session, topics, reaction_dict)
migrate_ratings(session, entry, reaction_dict)
return reaction
except Exception as e:
print(e)
print(reaction)
raise Exception(stage)
return
def migrate_2stage(old_comment, idmap):
if old_comment.get("body"):
new_id = idmap.get(old_comment.get("oid"))
new_id = idmap.get(old_comment.get("_id"))
if new_id:
new_replyto_id = None
old_replyto_id = old_comment.get("replyTo")
if old_replyto_id:
new_replyto_id = int(idmap.get(old_replyto_id, "0"))
with local_session() as session:
comment = session.query(Reaction).where(Reaction.id == new_id).first()
try:
if new_replyto_id:
new_reply = (
session.query(Reaction)
.where(Reaction.id == new_replyto_id)
.first()
)
if not new_reply:
print(new_replyto_id)
raise Exception("cannot find reply by id!")
comment.replyTo = new_reply.id
session.add(comment)
srf = (
session.query(ShoutReactionsFollower)
.where(ShoutReactionsFollower.shout == comment.shout)
.filter(ShoutReactionsFollower.follower == comment.createdBy)
.first()
)
if not srf:
srf = ShoutReactionsFollower.create(
shout=comment.shout, follower=comment.createdBy, auto=True
)
session.add(srf)
session.commit()
except Exception:
raise Exception("cannot find a comment by oldid")

View File

@@ -1,420 +0,0 @@
from datetime import datetime, timezone
import json
from dateutil.parser import parse as date_parse
from sqlalchemy.exc import IntegrityError
from transliterate import translit
from services.db import local_session
from migration.extract import extract_html, extract_media
from orm.reaction import Reaction, ReactionKind
from orm.shout import Shout, ShoutTopic, ShoutReactionsFollower
from orm.user import User
from orm.topic import TopicFollower, Topic
from services.viewed import ViewedStorage
import re
OLD_DATE = "2016-03-05 22:22:00.350000"
ts = datetime.now(tz=timezone.utc)
type2layout = {
"Article": "article",
"Literature": "literature",
"Music": "audio",
"Video": "video",
"Image": "image",
}
anondict = {"slug": "anonymous", "id": 1, "name": "Аноним"}
discours = {"slug": "discours", "id": 2, "name": "Дискурс"}
def get_shout_slug(entry):
slug = entry.get("slug", "")
if not slug:
for friend in entry.get("friendlySlugs", []):
slug = friend.get("slug", "")
if slug:
break
slug = re.sub("[^0-9a-zA-Z]+", "-", slug)
return slug
def create_author_from_app(app):
user = None
userdata = None
# check if email is used
if app["email"]:
with local_session() as session:
user = session.query(User).where(User.email == app["email"]).first()
if not user:
# print('[migration] app %r' % app)
name = app.get("name")
if name:
slug = translit(name, "ru", reversed=True).lower()
slug = re.sub("[^0-9a-zA-Z]+", "-", slug)
print("[migration] created slug %s" % slug)
# check if slug is used
if slug:
user = session.query(User).where(User.slug == slug).first()
# get slug from email
if user:
slug = app["email"].split("@")[0]
user = session.query(User).where(User.slug == slug).first()
# one more try
if user:
slug += "-author"
user = (
session.query(User).where(User.slug == slug).first()
)
# create user with application data
if not user:
userdata = {
"username": app["email"],
"email": app["email"],
"name": app.get("name", ""),
"bio": app.get("bio", ""),
"emailConfirmed": False,
"slug": slug,
"createdAt": ts,
"lastSeen": ts,
}
# print('[migration] userdata %r' % userdata)
user = User.create(**userdata)
session.add(user)
session.commit()
userdata["id"] = user.id
userdata = user.dict()
return userdata
else:
raise Exception("app is not ok", app)
async def create_shout(shout_dict):
s = Shout.create(**shout_dict)
author = s.authors[0]
with local_session() as session:
srf = (
session.query(ShoutReactionsFollower)
.where(ShoutReactionsFollower.shout == s.id)
.filter(ShoutReactionsFollower.follower == author.id)
.first()
)
if not srf:
srf = ShoutReactionsFollower.create(
shout=s.id, follower=author.id, auto=True
)
session.add(srf)
session.commit()
return s
async def get_user(entry, storage):
app = entry.get("application")
userdata = None
user_oid = None
if app:
userdata = create_author_from_app(app)
else:
user_oid = entry.get("createdBy")
if user_oid == "0":
userdata = discours
elif user_oid:
userdata = storage["users"]["by_oid"].get(user_oid)
if not userdata:
print("no userdata by oid, anonymous")
userdata = anondict
print(app)
# cleanup slug
if userdata:
slug = userdata.get("slug", "")
if slug:
slug = re.sub("[^0-9a-zA-Z]+", "-", slug)
userdata["slug"] = slug
else:
userdata = anondict
user = await process_user(userdata, storage, user_oid)
return user, user_oid
async def migrate(entry, storage):
author, user_oid = await get_user(entry, storage)
r = {
"layout": type2layout[entry["type"]],
"title": entry["title"],
"authors": [
author,
],
"slug": get_shout_slug(entry),
"cover": (
"https://assets.discours.io/unsafe/1600x/" + entry["thumborId"]
if entry.get("thumborId")
else entry.get("image", {}).get("url")
),
"visibility": "public" if entry.get("published") else "authors",
"publishedAt": date_parse(entry.get("publishedAt"))
if entry.get("published")
else None,
"deletedAt": date_parse(entry.get("deletedAt"))
if entry.get("deletedAt")
else None,
"createdAt": date_parse(entry.get("createdAt", OLD_DATE)),
"updatedAt": date_parse(entry["updatedAt"]) if "updatedAt" in entry else ts,
"topics": await add_topics_follower(entry, storage, author),
"body": extract_html(entry, cleanup=True),
}
# main topic patch
r["mainTopic"] = r["topics"][0]
# published author auto-confirm
if entry.get("published"):
with local_session() as session:
# update user.emailConfirmed if published
author.emailConfirmed = True
session.add(author)
session.commit()
# media
media = extract_media(entry)
r["media"] = json.dumps(media, ensure_ascii=True) if media else None
# ----------------------------------- copy
shout_dict = r.copy()
del shout_dict["topics"]
try:
# save shout to db
shout_dict["oid"] = entry.get("_id", "")
shout = await create_shout(shout_dict)
except IntegrityError as e:
print("[migration] create_shout integrity error", e)
shout = await resolve_create_shout(shout_dict)
except Exception as e:
raise Exception(e)
# udpate data
shout_dict = shout.dict()
shout_dict["authors"] = [
author.dict(),
]
# shout topics aftermath
shout_dict["topics"] = await topics_aftermath(r, storage)
# content_item ratings to reactions
await content_ratings_to_reactions(entry, shout_dict["slug"])
# shout views
await ViewedStorage.increment(
shout_dict["slug"], amount=entry.get("views", 1), viewer="old-discours"
)
# del shout_dict['ratings']
storage["shouts"]["by_oid"][entry["_id"]] = shout_dict
storage["shouts"]["by_slug"][shout_dict["slug"]] = shout_dict
return shout_dict
async def add_topics_follower(entry, storage, user):
topics = set([])
category = entry.get("category")
topics_by_oid = storage["topics"]["by_oid"]
oids = [
category,
] + entry.get("tags", [])
for toid in oids:
tslug = topics_by_oid.get(toid, {}).get("slug")
if tslug:
topics.add(tslug)
ttt = list(topics)
# add author as TopicFollower
with local_session() as session:
for tpcslug in topics:
try:
tpc = session.query(Topic).where(Topic.slug == tpcslug).first()
if tpc:
tf = (
session.query(TopicFollower)
.where(TopicFollower.follower == user.id)
.filter(TopicFollower.topic == tpc.id)
.first()
)
if not tf:
tf = TopicFollower.create(
topic=tpc.id, follower=user.id, auto=True
)
session.add(tf)
session.commit()
except IntegrityError:
print("[migration.shout] hidden by topic " + tpc.slug)
# main topic
maintopic = storage["replacements"].get(topics_by_oid.get(category, {}).get("slug"))
if maintopic in ttt:
ttt.remove(maintopic)
ttt.insert(0, maintopic)
return ttt
async def process_user(userdata, storage, oid):
with local_session() as session:
uid = userdata.get("id") # anonymous as
if not uid:
print(userdata)
print("has no id field, set it @anonymous")
userdata = anondict
uid = 1
user = session.query(User).filter(User.id == uid).first()
if not user:
try:
slug = userdata["slug"].lower().strip()
slug = re.sub("[^0-9a-zA-Z]+", "-", slug)
userdata["slug"] = slug
user = User.create(**userdata)
session.add(user)
session.commit()
except IntegrityError:
print(f"[migration] user creating with slug {userdata['slug']}")
print("[migration] from userdata")
print(userdata)
raise Exception(
"[migration] cannot create user in content_items.get_user()"
)
if user.id == 946:
print("[migration] ***************** ALPINA")
if user.id == 2:
print("[migration] +++++++++++++++++ DISCOURS")
userdata["id"] = user.id
userdata["createdAt"] = user.createdAt
storage["users"]["by_slug"][userdata["slug"]] = userdata
storage["users"]["by_oid"][oid] = userdata
if not user:
raise Exception("could not get a user")
return user
async def resolve_create_shout(shout_dict):
with local_session() as session:
s = session.query(Shout).filter(Shout.slug == shout_dict["slug"]).first()
bump = False
if s:
if s.createdAt != shout_dict["createdAt"]:
# create new with different slug
shout_dict["slug"] += "-" + shout_dict["layout"]
try:
await create_shout(shout_dict)
except IntegrityError as e:
print(e)
bump = True
else:
# update old
for key in shout_dict:
if key in s.__dict__:
if s.__dict__[key] != shout_dict[key]:
print(
"[migration] shout already exists, but differs in %s"
% key
)
bump = True
else:
print("[migration] shout already exists, but lacks %s" % key)
bump = True
if bump:
s.update(shout_dict)
else:
print("[migration] something went wrong with shout: \n%r" % shout_dict)
raise Exception("")
session.commit()
return s
async def topics_aftermath(entry, storage):
r = []
for tpc in filter(lambda x: bool(x), entry["topics"]):
oldslug = tpc
newslug = storage["replacements"].get(oldslug, oldslug)
if newslug:
with local_session() as session:
shout = session.query(Shout).where(Shout.slug == entry["slug"]).first()
new_topic = session.query(Topic).where(Topic.slug == newslug).first()
shout_topic_old = (
session.query(ShoutTopic)
.join(Shout)
.join(Topic)
.filter(Shout.slug == entry["slug"])
.filter(Topic.slug == oldslug)
.first()
)
if shout_topic_old:
shout_topic_old.update({"topic": new_topic.id})
else:
shout_topic_new = (
session.query(ShoutTopic)
.join(Shout)
.join(Topic)
.filter(Shout.slug == entry["slug"])
.filter(Topic.slug == newslug)
.first()
)
if not shout_topic_new:
try:
ShoutTopic.create(
**{"shout": shout.id, "topic": new_topic.id}
)
except Exception:
print("[migration] shout topic error: " + newslug)
session.commit()
if newslug not in r:
r.append(newslug)
else:
print("[migration] ignored topic slug: \n%r" % tpc["slug"])
# raise Exception
return r
async def content_ratings_to_reactions(entry, slug):
try:
with local_session() as session:
for content_rating in entry.get("ratings", []):
rater = (
session.query(User)
.filter(User.oid == content_rating["createdBy"])
.first()
) or User.default_user
shout = session.query(Shout).where(Shout.slug == slug).first()
cts = content_rating.get("createdAt")
reaction_dict = {
"createdAt": date_parse(cts) if cts else None,
"kind": ReactionKind.LIKE
if content_rating["value"] > 0
else ReactionKind.DISLIKE,
"createdBy": rater.id,
"shout": shout.id,
}
reaction = (
session.query(Reaction)
.filter(Reaction.shout == reaction_dict["shout"])
.filter(Reaction.createdBy == reaction_dict["createdBy"])
.filter(Reaction.kind == reaction_dict["kind"])
.first()
)
if reaction:
k = (
ReactionKind.AGREE
if content_rating["value"] > 0
else ReactionKind.DISAGREE
)
reaction_dict["kind"] = k
reaction.update(reaction_dict)
session.add(reaction)
else:
rea = Reaction.create(**reaction_dict)
session.add(rea)
# shout_dict['ratings'].append(reaction_dict)
session.commit()
except Exception:
print("[migration] content_item.ratings error: \n%r" % content_rating)

View File

@@ -1,34 +0,0 @@
from services.db import local_session
from migration.extract import extract_md
from migration.html2text import html2text
from orm.reaction import Reaction, ReactionKind
def migrate(entry, storage):
post_oid = entry["contentItem"]
print(post_oid)
shout_dict = storage["shouts"]["by_oid"].get(post_oid)
if shout_dict:
print(shout_dict["body"])
remark = {
"shout": shout_dict["id"],
"body": extract_md(html2text(entry["body"]), shout_dict),
"kind": ReactionKind.REMARK,
}
if entry.get("textBefore"):
remark["range"] = (
str(shout_dict["body"].index(entry["textBefore"] or ""))
+ ":"
+ str(
shout_dict["body"].index(entry["textAfter"] or "")
+ len(entry["textAfter"] or "")
)
)
with local_session() as session:
rmrk = Reaction.create(**remark)
session.commit()
del rmrk["_sa_instance_state"]
return rmrk
return

View File

@@ -1,828 +0,0 @@
{
"207": "207",
"1990-e": "90s",
"2000-e": "2000s",
"90-e": "90s",
"Georgia": "georgia",
"Japan": "japan",
"Sweden": "sweden",
"abstraktsiya": "abstract",
"absurdism": "absurdism",
"acclimatization": "acclimatisation",
"activism": "activism",
"adolf-gitler": "adolf-hitler",
"afrika": "africa",
"agata-kristi": "agatha-christie",
"agressivnoe-povedenie": "agression",
"agressiya": "agression",
"aktsii": "actions",
"aktsionizm": "actionism",
"alber-kamyu": "albert-kamus",
"albomy": "albums",
"aleksandr-griboedov": "aleksander-griboedov",
"aleksandr-pushkin": "aleksander-pushkin",
"aleksandr-solzhenitsyn": "aleksander-solzhenitsyn",
"aleksandr-vvedenskiy": "aleksander-vvedensky",
"aleksey-navalnyy": "alexey-navalny",
"alfavit": "alphabet",
"alkogol": "alcohol",
"alternativa": "alternative",
"alternative": "alternative",
"alternativnaya-istoriya": "alternative-history",
"amerika": "america",
"anarhizm": "anarchism",
"anatoliy-mariengof": "anatoly-mariengof",
"ancient-russia": "ancient-russia",
"andegraund": "underground",
"andrey-platonov": "andrey-platonov",
"andrey-rodionov": "andrey-rodionov",
"andrey-tarkovskiy": "andrey-tarkovsky",
"angliyskie-istorii": "english-stories",
"angliyskiy-yazyk": "english-langugae",
"ango": "ango",
"animation": "animation",
"animatsiya": "animation",
"anime": "anime",
"anri-volohonskiy": "anri-volohonsky",
"antifashizm": "anti-faschism",
"antiquity": "antiquity",
"antiutopiya": "dystopia",
"anton-dolin": "anton-dolin",
"antropology": "antropology",
"antropotsen": "antropocenus",
"architecture": "architecture",
"arheologiya": "archeology",
"arhetipy": "archetypes",
"arhiv": "archive",
"aristokraty": "aristocracy",
"aristotel": "aristotle",
"arktika": "arctic",
"armiya": "army",
"armiya-1": "army",
"art": "art",
"art-is": "art-is",
"artists": "artists",
"ateizm": "atheism",
"audio-poetry": "audio-poetry",
"audiopoeziya": "audio-poetry",
"audiospektakl": "audio-spectacles",
"auktsyon": "auktsyon",
"avangard": "avantgarde",
"avtofikshn": "autofiction",
"avtorskaya-pesnya": "bardsongs",
"azbuka-immigratsii": "immigration-basics",
"aziatskiy-kinematograf": "asian-cinema",
"b-movie": "b-movie",
"bannye-chteniya": "sauna-reading",
"bardsongs": "bardsongs",
"bdsm": "bdsm",
"beecake": "beecake",
"belarus": "belarus",
"belgiya": "belgium",
"bertold-breht": "berttold-brecht",
"bezumie": "madness",
"biography": "biography",
"biologiya": "biology",
"bipolyarnoe-rasstroystvo": "bipolar-disorder",
"bitniki": "beatnics",
"biznes": "business",
"blizhniy-vostok": "middle-east",
"blizost": "closeness",
"blocked-in-russia": "blocked-in-russia",
"blokada": "blockade",
"bob-dilan": "bob-dylan",
"bog": "god",
"bol": "pain",
"bolotnoe-delo": "bolotnaya-case",
"books": "books",
"boris-eltsin": "boris-eltsin",
"boris-godunov": "boris-godunov",
"boris-grebenschikov": "boris-grebenschikov",
"boris-nemtsov": "boris-nemtsov",
"boris-pasternak": "boris-pasternak",
"brak": "marriage",
"bret-iston-ellis": "bret-iston-ellis",
"buddizm": "buddhism",
"bullying": "bullying",
"bunt": "riot",
"burning-man": "burning-man",
"bytie": "being",
"byurokratiya": "bureaucracy",
"capitalism": "capitalism",
"censored-in-russia": "censored-in-russia",
"ch-rno-beloe": "black-and-white",
"ch-rnyy-yumor": "black-humour",
"chapters": "chapters",
"charity": "charity",
"chayldfri": "childfree",
"chechenskaya-voyna": "chechen-war",
"chechnya": "chechnya",
"chelovek": "male",
"chernobyl": "chernobyl",
"chernyy-yumor": "black-humour",
"children": "children",
"china": "china",
"chinovniki": "bureaucracy",
"chukotka": "chukotka",
"chuma": "plague",
"church": "church",
"cinema": "cinema",
"city": "city",
"civil-position": "civil-position",
"clips": "clips",
"collage": "collage",
"comics": "comics",
"conspiracy-theory": "conspiracy-theory",
"contemporary-art": "contemporary-art",
"contemporary-poetry": "poetry",
"contemporary-prose": "prose",
"coronavirus": "coronavirus",
"corruption": "corruption",
"creative-writing-school": "creative-writing-school",
"crime": "crime",
"criticism": "criticism",
"critiques": "reviews",
"culture": "culture",
"dadaizm": "dadaism",
"daniel-defo": "daniel-defoe",
"daniil-harms": "daniil-kharms",
"dante-aligeri": "dante-alighieri",
"darkveyv": "darkwave",
"death": "death",
"debaty": "debats",
"delo-seti": "seti-case",
"democracy": "democracy",
"demografiya": "demographics",
"demonstrations": "demonstrations",
"depression": "depression",
"derevnya": "village",
"derrida": "derrida",
"design": "design",
"detskie-doma": "orphanages",
"detstvo": "childhood",
"devid-linch": "david-linch",
"devyanostye": "90s",
"dialog": "dialogue",
"digital": "digital",
"digital-art": "digital-art",
"dinozavry": "dinosaurs",
"directing": "directing",
"diskurs": "discours",
"diskurs-1": "discourse",
"diskurs-analiz": "discourse-analytics",
"dissidenty": "dissidents",
"diy": "diy",
"dmitriy-donskoy": "dmitriy-donskoy",
"dmitriy-prigov": "dmitriy-prigov",
"dnevnik-1": "dairy",
"dnevniki": "dairies",
"documentary": "documentary",
"dokumentalnaya-poema": "documentary-poem",
"dokumentalnaya-poeziya": "documentary-poetry",
"dokumenty": "doсuments",
"domashnee-nasilie": "home-terror",
"donald-tramp": "donald-trump",
"donbass": "donbass",
"donbass-diary": "donbass-diary",
"donorstvo": "donation",
"dozhd": "rain",
"drama": "drama",
"dramaturgy": "dramaturgy",
"drawing": "drawing",
"drevo-zhizni": "tree-of-life",
"drugs": "drugs",
"duh": "spirit",
"dzhaz": "jazz",
"dzhek-keruak": "jack-keruak",
"dzhim-morrison": "jim-morrison",
"dzhordzh-romero": "george-romero",
"dzhordzho-agamben": "giorgio-agamben",
"ecology": "ecology",
"economics": "economics",
"eda": "food",
"editorial-statements": "editorial-statements",
"eduard-limonov": "eduard-limonov",
"education": "education",
"egor-letov": "egor-letov",
"ekspat": "expat",
"eksperiment": "experiments",
"eksperimentalnaya-muzyka": "experimental-music",
"ekspressionizm": "expressionism",
"ekstremizm": "extremism",
"ekzistentsializm-1": "existentialism",
"ekzistentsiya": "existence",
"elections": "elections",
"electronic": "electronics",
"electronics": "electronics",
"elena-glinskaya": "elena-glinskaya",
"elena-guro": "elena-guro",
"elizaveta-mnatsakanova": "elizaveta-mnatsakanova",
"embient": "ambient",
"emigration": "emigration",
"emil-dyurkgeym": "emile-durkheim",
"emotsii": "emotions",
"empiric": "empiric",
"epidemiya": "pandemic",
"erich-von-neff": "erich-von-neff",
"erotika": "erotics",
"essay": "essay",
"estetika": "aestetics",
"etika": "ethics",
"etno": "ethno",
"etnos": "ethnics",
"everyday-life": "everyday-life",
"evgeniy-onegin": "eugene-onegin",
"evolyutsiya": "evolution",
"exhibitions": "exhibitions",
"experience": "experiences",
"experimental": "experimental",
"experimental-music": "experimental-music",
"explanation": "explanation",
"faktcheking": "fact-checking",
"falsifikatsii": "falsifications",
"family": "family",
"fanfiki": "fan-fiction",
"fantastika": "sci-fi",
"fatalizm": "fatalism",
"fedor-dostoevskiy": "fedor-dostoevsky",
"fedor-ioannovich": "fedor-ioannovich",
"feleton": "feuilleton",
"feminism": "feminism",
"fenomenologiya": "phenomenology",
"fentezi": "fantasy",
"festival": "festival",
"festival-territoriya": "festival-territory",
"folk": "folk",
"folklor": "folklore",
"fotoreportazh": "photoreports",
"france": "france",
"frants-kafka": "franz-kafka",
"frederik-begbeder": "frederick-begbeder",
"freedom": "freedom",
"friendship": "friendship",
"fsb": "fsb",
"futbol": "footbool",
"future": "future",
"futuristy": "futurists",
"futurizm": "futurism",
"galereya": "gallery",
"galereya-anna-nova": "gallery-anna-nova",
"gdr": "gdr",
"gender": "gender",
"gendernyy-diskurs": "gender",
"gennadiy-aygi": "gennadiy-aygi",
"gerhard-rihter": "gerhard-rihter",
"germaniya": "germany",
"germenevtika": "hermeneutics",
"geroi": "heroes",
"girls": "girls",
"gkchp": "gkchp",
"glitch": "glitch",
"globalizatsiya": "globalisation",
"gollivud": "hollywood",
"gonzo": "gonzo",
"gore-ot-uma": "woe-from-wit",
"graffiti": "graffiti",
"graficheskaya-novella": "graphic-novell",
"graphics": "graphics",
"gravyura": "engraving",
"grazhdanskaya-oborona": "grazhdanskaya-oborona",
"gretsiya": "greece",
"griby": "mushrooms",
"gruziya-2": "georgia",
"gulag": "gulag",
"han-batyy": "khan-batyy",
"hayku": "haiku",
"health": "health",
"himiya": "chemistry",
"hip-hop": "hip-hop",
"history": "history",
"history-of-russia": "history-of-russia",
"holokost": "holocaust",
"horeografiya": "choreography",
"horror": "horror",
"hospis": "hospice",
"hristianstvo": "christianity",
"humans": "humans",
"humour": "humour",
"ideologiya": "ideology",
"idm": "idm",
"igil": "isis",
"igor-pomerantsev": "igor-pomerantsev",
"igra": "game",
"igra-prestolov": "game-of-throne",
"igry": "games",
"iisus-hristos": "jesus-christ",
"illness": "illness",
"illustration-history": "illustration-history",
"illustrations": "illustrations",
"imazhinizm": "imagism",
"immanuil-kant": "immanuel-kant",
"impressionizm": "impressionism",
"improvizatsiya": "improvisation",
"indi": "indie",
"individualizm": "individualism",
"infografika": "infographics",
"informatsiya": "information",
"ingmar-bergman": "ingmar-bergman",
"inklyuziya": "inclusion",
"installyatsiya": "installation",
"internet": "internet",
"interview": "interview",
"invalidnost": "disability",
"investigations": "investigations",
"iosif-brodskiy": "joseph-brodsky",
"iosif-stalin": "joseph-stalin",
"iskusstvennyy-intellekt": "artificial-intelligence",
"islam": "islam",
"istoriya-moskvy": "moscow-history",
"istoriya-nauki": "history-of-sceince",
"istoriya-o-medsestre": "nurse-story",
"istoriya-teatra": "theatre-history",
"italiya": "italy",
"italyanskiy-yazyk": "italian-language",
"iudaika": "judaica",
"ivan-groznyy": "ivan-grozny",
"ivan-iii-gorbatyy": "ivan-iii-gorbaty",
"ivan-kalita": "ivan-kalita",
"ivan-krylov": "ivan-krylov",
"izobreteniya": "inventions",
"izrail-1": "israel",
"jazz": "jazz",
"john-lennon": "john-lennon",
"journalism": "journalism",
"justice": "justice",
"k-pop": "k-pop",
"kalligrafiya": "calligraphy",
"karikatura": "caricatures",
"kartochki-rubinshteyna": "rubinstein-cards",
"katrin-nenasheva": "katrin-nenasheva",
"kavarga": "kavarga",
"kavkaz": "caucasus",
"kazan": "kazan",
"kiberbezopasnost": "cybersecurity",
"kinoklub": "cinema-club",
"kinokritika": "film-criticism",
"kirill-serebrennikov": "kirill-serebrennikov",
"kladbische": "cemetery",
"klassika": "classic",
"kollektivnoe-bessoznatelnoe": "сollective-unconscious",
"komediya": "comedy",
"kommunikatsii": "communications",
"kommunizm": "communism",
"kommuny": "communes",
"kompyuternye-igry": "computer-games",
"konets-vesny": "end-of-spring",
"konservatizm": "conservatism",
"kontrkultura": "counter-culture",
"kontseptualizm": "conceptualism",
"korotkometrazhka": "cinema-shorts",
"kosmos": "cosmos",
"kraudfanding": "crowdfunding",
"kriptovalyuty": "cryptocurrencies",
"krizis": "crisis",
"krov": "blood",
"krym": "crimea",
"kulturologiya": "culturology",
"kulty": "cults",
"kurdistan": "kurdistan",
"kurt-kobeyn": "kurt-cobain",
"kurt-vonnegut": "kurt-vonnegut",
"kvir": "queer",
"laboratoriya": "lab",
"language": "languages",
"lars-fon-trier": "lars-fon-trier",
"laws": "laws",
"lectures": "lectures",
"leto": "summer",
"lev-tolstoy": "leo-tolstoy",
"lgbt": "lgbt",
"liberalizm": "liberalism",
"libertarianstvo": "libertarianism",
"life": "life",
"likbez": "likbez",
"lingvistika": "linguistics",
"lirika": "lirics",
"literary-studies": "literary-studies",
"literature": "literature",
"literaturnyykaver": "literature-cover",
"lo-fi": "lo-fi",
"lomonosov": "lomonosov",
"love": "love",
"luzha-goluboy-krovi": "luzha-goluboy-krovi",
"lyudvig-vitgenshteyn": "ludwig-wittgenstein",
"lzhedmitriy": "false-dmitry",
"lzhenauka": "pseudoscience",
"magiya": "magic",
"maks-veber": "max-weber",
"manifests": "manifests",
"manipulyatsii-soznaniem": "mind-manipulation",
"marina-abramovich": "marina-abramovich",
"marketing": "marketing",
"marksizm": "marxism",
"marsel-dyushan": "marchel-duchamp",
"marsel-prust": "marcel-proust",
"martin-haydegger": "martin-hidegger",
"matematika": "maths",
"mayakovskiy": "vladimir-mayakovsky",
"media": "media",
"medicine": "medicine",
"memuary": "memoirs",
"menedzhment": "management",
"menty": "police",
"merab-mamardashvili": "merab-mamardashvili",
"mest": "revenge",
"metamodernizm": "metamodern",
"metavselennaya": "metaverse",
"metro": "metro",
"mifologiya": "mythology",
"mify": "myth",
"mihael-haneke": "michael-haneke",
"mihail-baryshnikov": "mihail-baryshnikov",
"mihail-bulgakov": "mihail-bulgakov",
"mikrotonalnaya-muzyka": "mikrotone-muzyka",
"minimalizm": "minimalism",
"minkult-privet": "minkult-privet",
"mir": "world",
"mirovozzrenie": "mindsets",
"mishel-fuko": "michel-foucault",
"mistika": "mystics",
"mitropolit-makariy": "mitropolit-makariy",
"mlm": "mlm",
"mobilizatsiya": "mobilisation",
"moda": "fashion",
"modernizm": "modernism",
"mokyumentari": "mockumentary",
"molodezh": "youth",
"moloko-plus": "moloko-plus",
"money": "money",
"monologs": "monologues",
"monstratsiya": "monstration",
"moralnaya-otvetstvennost": "moral-responsibility",
"more": "sea",
"moscow": "moscow",
"moshennichestvo": "frauds",
"moskovskiy-romanticheskiy-kontseptualizm": "moscow-romantic-conceptualism",
"moskovskoe-delo": "moscow-case",
"movies": "movies",
"mozg": "brain",
"multiplikatsiya": "animation",
"music": "music",
"musulmanstvo": "islam",
"muzei": "museum",
"muzey": "museum",
"muzhchiny": "man",
"myshlenie": "thinking",
"nagornyy-karabah": "nagorno-karabakh",
"nasilie-1": "violence",
"natsionalizm": "nationalism",
"natsionalnaya-ideya": "national-idea",
"natsizm": "nazism",
"natyurmort": "nature-morte",
"nauchpop": "pop-science",
"nbp": "nbp",
"nenavist": "hate",
"neofitsialnaya-literatura": "unofficial-literature",
"neoklassika": "neoclassic",
"neprozrachnye-smysly": "hidden-meanings",
"neravenstvo": "inequality",
"net-voyne": "no-war",
"new-year": "new-year",
"neyronauka": "neuro-science",
"neyroseti": "neural-networks",
"niu-vshe": "hse",
"nizhniy-novgorod": "nizhny-novgorod",
"nko": "nonprofits",
"nlo": "ufo",
"nobelevskaya-premiya": "nobel-prize",
"noize-mc": "noize-mc",
"nonkonformizm": "nonconformism",
"notforall": "notforall",
"novaya-drama": "new-drama",
"novosti": "news",
"noyz": "noise",
"nuar": "noir",
"oberiu": "oberiu",
"ocherk": "etudes",
"ochevidnyy-nuar": "ochevidnyy-nuar",
"odinochestvo": "loneliness",
"odna-kniga-odna-istoriya": "one-book-one-story",
"okrainy": "outskirts",
"omon": "swat",
"opinions": "opinions",
"oppozitsiya": "opposition",
"orhan-pamuk": "orhan-pamuk",
"ornitologiya": "ornitology",
"osen": "autumn",
"osip-mandelshtam": "osip-mandelshtam",
"oskar-uayld": "oscar-wilde",
"osoznanie": "awareness",
"otnosheniya": "relationship",
"pablo-pikasso": "pablo-picasso",
"painting": "painting",
"paintings": "painting",
"pamyat": "memory",
"pandemiya": "pandemic",
"parizh": "paris",
"patriotizm": "patriotism",
"patsifizm": "pacifism",
"paul-tselan": "paul-tselan",
"per-burd": "pierre-bourdieu",
"perezhivaniya": "worries",
"performance": "performance",
"peyzazh": "landscape",
"philology": "philology",
"philosophy": "philosophy",
"photo": "photography",
"photography": "photography",
"photoprojects": "photoprojects",
"plakaty": "posters",
"plastilin": "plasticine",
"plays": "plays",
"podrostki": "teenagers",
"poema": "poem",
"poems": "poems",
"poeticheskaya-proza": "poetic-prose",
"poetry": "poetry",
"poetry-of-squares": "poetry-of-squares",
"poetry-slam": "poetry-slam",
"pokoy": "peace",
"police": "police",
"politicheskoe-fentezi": "political-fantasy",
"politics": "politics",
"politzaklyuchennye": "political-prisoners",
"polsha": "poland",
"pomosch": "help",
"pop-art": "pop-art",
"pop-culture": "pop-culture",
"populyarnaya-psihologiya": "popular-psychology",
"pornografiya": "pornography",
"portret": "portrait",
"poslovitsy": "proverbs",
"post-pank": "post-punk",
"post-rok": "post-rock",
"postmodernism": "postmodernism",
"povest": "novells",
"povsednevnost": "everyday-life",
"power": "power",
"pravo": "right",
"pravoslavie": "orthodox",
"pravozaschitniki": "human-rights-activism",
"prazdnik": "holidays",
"predatelstvo": "betrayal",
"predprinimatelstvo": "entrepreneurship",
"premera": "premier",
"premiya-oskar": "oscar-prize",
"pribaltika-1": "baltic",
"priroda": "nature",
"prison": "prison",
"pritcha": "parable",
"privatnost": "privacy",
"progress": "progress",
"projects": "projects",
"prokrastinatsiya": "procrastination",
"propaganda": "propaganda",
"proschenie": "forgiveness",
"prose": "prose",
"proshloe": "past",
"prostitutsiya": "prostitution",
"prosveschenie": "enlightenment",
"protests": "protests",
"psalmy": "psalms",
"psihoanaliz": "psychoanalysis",
"psihodeliki": "psychodelics",
"pskov": "pskov",
"psychiatry": "psychiatry",
"psychology": "psychology",
"ptitsy": "birds",
"punk": "punk",
"r-b": "rnb",
"rasizm": "racism",
"realizm": "realism",
"redaktura": "editing",
"refleksiya": "reflection",
"reggi": "reggae",
"religion": "religion",
"rene-zhirar": "rene-girard",
"renesanss": "renessance",
"renovatsiya": "renovation",
"rep": "rap",
"reportage": "reportage",
"reportazh-1": "reportage",
"repressions": "repressions",
"research": "research",
"retroveyv": "retrowave",
"review": "review",
"revolution": "revolution",
"rezo-gabriadze": "rezo-gabriadze",
"risunki": "painting",
"roboty": "robots",
"rock": "rock",
"roditeli": "parents",
"romantizm": "romantism",
"romany": "novell",
"ronald-reygan": "ronald-reygan",
"roskomnadzor": "roskomnadzor",
"rossiyskoe-kino": "russian-cinema",
"rouling": "rowling",
"rozhava": "rojava",
"rpts": "rpts",
"rus-na-grani-sryva": "rus-na-grani-sryva",
"russia": "russia",
"russian-language": "russian-language",
"russian-literature": "russian-literature",
"russkaya-toska": "russian-toska",
"russkiy-mir": "russkiy-mir",
"salo": "lard",
"salvador-dali": "salvador-dali",
"samoidentifikatsiya": "self-identity",
"samoopredelenie": "self-definition",
"sankt-peterburg": "saint-petersburg",
"sasha-skochilenko": "sasha-skochilenko",
"satira": "satiric",
"saund-art": "sound-art",
"schaste": "happiness",
"school": "school",
"science": "science",
"sculpture": "sculpture",
"second-world-war": "second-world-war",
"sekond-hend": "second-hand",
"seksprosvet": "sex-education",
"seksualizirovannoe-nasilie": "sexualized-violence",
"seksualnoe-nasilie": "sexualized-violence",
"sekty": "sects",
"semi": "semi",
"semiotics": "semiotics",
"serbiya": "serbia",
"sergey-bodrov-mladshiy": "sergey-bodrov-junior",
"sergey-solov-v": "sergey-solovyov",
"serialy": "series",
"sever": "north",
"severnaya-koreya": "north-korea",
"sex": "sex",
"shotlandiya": "scotland",
"shugeyz": "shoegaze",
"siloviki": "siloviki",
"simeon-bekbulatovich": "simeon-bekbulatovich",
"simvolizm": "simbolism",
"siriya": "siria",
"skulptura": "sculpture",
"slavoy-zhizhek": "slavoj-zizek",
"smert-1": "death",
"smysl": "meaning",
"sny": "dreams",
"sobytiya": "events",
"social": "society",
"society": "society",
"sociology": "sociology",
"sofya-paleolog": "sofya-paleolog",
"sofya-vitovtovna": "sofya-vitovtovna",
"soobschestva": "communities",
"soprotivlenie": "resistence",
"sotsializm": "socialism",
"sotsialnaya-filosofiya": "social-philosophy",
"sotsiologiya-1": "sociology",
"sotsseti": "social-networks",
"sotvorenie-tretego-rima": "third-rome",
"sovremennost": "modernity",
"spaces": "spaces",
"spektakl": "spectacles",
"spetseffekty": "special-fx",
"spetsoperatsiya": "special-operation",
"spetssluzhby": "special-services",
"sport": "sport",
"srednevekove": "middle-age",
"state": "state",
"statistika": "statistics",
"stendap": "stand-up",
"stihi": "poetry",
"stoitsizm": "stoicism",
"stories": "stories",
"stoyanie-na-ugre": "stoyanie-na-ugre",
"strah": "fear",
"street-art": "street-art",
"stsenarii": "scenarios",
"sud": "court",
"summary": "summary",
"supergeroi": "superheroes",
"svetlana-aleksievich": "svetlana-aleksievich",
"svobodu-ivanu-golunovu": "free-ivan-golunov",
"syurrealizm": "surrealism",
"tales": "tales",
"tanets": "dance",
"tataro-mongolskoe-igo": "mongol-tatar-yoke",
"tatuirovki": "tattoo",
"technology": "technology",
"televidenie": "television",
"telo": "body",
"telo-kak-iskusstvo": "body-as-art",
"terrorizm": "terrorism",
"tests": "tests",
"text": "texts",
"the-beatles": "the-beatles",
"theater": "theater",
"theory": "theory",
"tokio": "tokio",
"torture": "torture",
"totalitarizm": "totalitarism",
"traditions": "traditions",
"tragicomedy": "tragicomedy",
"transgendernost": "transgender",
"translation": "translation",
"transport": "transport",
"travel": "travel",
"travma": "trauma",
"trendy": "trends",
"tretiy-reyh": "third-reich",
"triller": "thriller",
"tsar": "central-african-republic",
"tsar-edip": "oedipus",
"tsarevich-dmitriy": "tsarevich-dmitry",
"tsennosti": "values",
"tsenzura": "censorship",
"tseremonii": "ceremonies",
"turizm": "tourism",
"tvorchestvo": "creativity",
"ugnetennyy-zhilischnyy-klass": "oppressed-housing-class",
"uilyam-shekspir": "william-shakespeare",
"ukraina-2": "ukraine",
"ukraine": "ukraine",
"university": "university",
"urban-studies": "urban-studies",
"uroki-literatury": "literature-lessons",
"usa": "usa",
"ussr": "ussr",
"utopiya": "utopia",
"utrata": "loss",
"valter-benyamin": "valter-benyamin",
"varlam-shalamov": "varlam-shalamov",
"vasiliy-ii-temnyy": "basil-ii-temnyy",
"vasiliy-iii": "basil-iii",
"vdnh": "vdnh",
"vechnost": "ethernety",
"velikobritaniya": "great-britain",
"velimir-hlebnikov": "velimir-hlebnikov",
"velkom-tu-greyt-britn": "welcome-to-great-britain",
"venedikt-erofeev": "venedikt-erofeev",
"venetsiya": "veneece",
"vengriya": "hungary",
"verlibry": "free-verse",
"veschi": "things",
"vessels": "vessels",
"veterany": "veterans",
"video": "video",
"videoart": "videoart",
"videoklip": "clips",
"videopoeziya": "video-poetry",
"viktor-astafev": "viktor-astafev",
"viktor-pelevin": "viktor-pelevin",
"vilgelm-rayh": "wilhelm-reich",
"vinzavod": "vinzavod",
"violence": "violence",
"visual-culture": "visual-culture",
"vizualnaya-poeziya": "visual-poetry",
"vladimir-lenin": "vladimir-lenin",
"vladimir-mayakovskiy": "vladimir-mayakovsky",
"vladimir-nabokov": "vladimir-nabokov",
"vladimir-putin": "vladimir-putin",
"vladimir-sorokin": "vladimir-sorokin",
"vladimir-voynovich": "vladimir-voynovich",
"vnutrenniy-opyt": "inner-expirience",
"volga": "volga",
"volontery": "volonteurs",
"vong-karvay": "wong-karwai",
"vospominaniya": "memories",
"vostok": "east",
"voyna-na-ukraine": "war-in-ukraine",
"voyna-v-ukraine": "war-in-ukraine",
"vremya": "time",
"vudi-allen": "woody-allen",
"vynuzhdennye-otnosheniya": "forced-relationship",
"war": "war",
"war-in-ukraine-images": "war-in-ukrahine-images",
"women": "women",
"work": "work",
"writers": "writers",
"xx-century": "xx-century",
"yakob-yordans": "yakob-yordans",
"yan-vermeer": "yan-vermeer",
"yanka-dyagileva": "yanka-dyagileva",
"yaponskaya-literatura": "japan-literature",
"yazychestvo": "paganism",
"youth": "youth",
"yozef-rot": "yozef-rot",
"yurgen-habermas": "jorgen-habermas",
"za-liniey-mannergeyma": "behind-mannerheim-line",
"zabota": "care",
"zahar-prilepin": "zahar-prilepin",
"zakonodatelstvo": "laws",
"zakony-mira": "world-laws",
"zametki": "notes",
"zhelanie": "wish",
"zhivotnye": "animals",
"zhoze-saramago": "jose-saramago",
"zigmund-freyd": "sigmund-freud",
"zolotaya-orda": "golden-horde",
"zombi": "zombie",
"zombi-simpsony": "zombie-simpsons"
}

View File

@@ -1,32 +0,0 @@
from services.db import local_session
from migration.extract import extract_md
from migration.html2text import html2text
from orm import Topic
def migrate(entry):
body_orig = entry.get("description", "").replace("&nbsp;", " ")
topic_dict = {
"slug": entry["slug"],
"oid": entry["_id"],
"title": entry["title"].replace("&nbsp;", " "),
"body": extract_md(html2text(body_orig)),
}
with local_session() as session:
slug = topic_dict["slug"]
topic = session.query(Topic).filter(Topic.slug == slug).first() or Topic.create(
**topic_dict
)
if not topic:
raise Exception("no topic!")
if topic:
if len(topic.title) > len(topic_dict["title"]):
Topic.update(topic, {"title": topic_dict["title"]})
if len(topic.body) < len(topic_dict["body"]):
Topic.update(topic, {"body": topic_dict["body"]})
session.commit()
# print(topic.__dict__)
rt = topic.__dict__.copy()
del rt["_sa_instance_state"]
return rt

View File

@@ -1,167 +0,0 @@
import re
from bs4 import BeautifulSoup
from dateutil.parser import parse
from sqlalchemy.exc import IntegrityError
from services.db import local_session
from orm.user import AuthorFollower, User, UserRating
def migrate(entry):
if "subscribedTo" in entry:
del entry["subscribedTo"]
email = entry["emails"][0]["address"]
user_dict = {
"oid": entry["_id"],
"roles": [],
"ratings": [],
"username": email,
"email": email,
"createdAt": parse(entry["createdAt"]),
"emailConfirmed": ("@discours.io" in email)
or bool(entry["emails"][0]["verified"]),
"muted": False, # amnesty
"bio": entry["profile"].get("bio", ""),
"links": [],
"name": "anonymous",
"password": entry["services"]["password"].get("bcrypt"),
}
if "updatedAt" in entry:
user_dict["updatedAt"] = parse(entry["updatedAt"])
if "wasOnineAt" in entry:
user_dict["lastSeen"] = parse(entry["wasOnlineAt"])
if entry.get("profile"):
# slug
slug = entry["profile"].get("path").lower()
slug = re.sub("[^0-9a-zA-Z]+", "-", slug).strip()
user_dict["slug"] = slug
bio = (
(entry.get("profile", {"bio": ""}).get("bio") or "")
.replace("\(", "(")
.replace("\)", ")")
)
bio_text = BeautifulSoup(bio, features="lxml").text
if len(bio_text) > 120:
user_dict["about"] = bio_text
else:
user_dict["bio"] = bio_text
# userpic
try:
user_dict["userpic"] = (
"https://assets.discours.io/unsafe/100x/"
+ entry["profile"]["thumborId"]
)
except KeyError:
try:
user_dict["userpic"] = entry["profile"]["image"]["url"]
except KeyError:
user_dict["userpic"] = ""
# name
fn = entry["profile"].get("firstName", "")
ln = entry["profile"].get("lastName", "")
name = fn if fn else ""
name = (name + " " + ln) if ln else name
if not name:
name = slug if slug else "anonymous"
name = (
entry["profile"]["path"].lower().strip().replace(" ", "-")
if len(name) < 2
else name
)
user_dict["name"] = name
# links
fb = entry["profile"].get("facebook", False)
if fb:
user_dict["links"].append(fb)
vk = entry["profile"].get("vkontakte", False)
if vk:
user_dict["links"].append(vk)
tr = entry["profile"].get("twitter", False)
if tr:
user_dict["links"].append(tr)
ws = entry["profile"].get("website", False)
if ws:
user_dict["links"].append(ws)
# some checks
if not user_dict["slug"] and len(user_dict["links"]) > 0:
user_dict["slug"] = user_dict["links"][0].split("/")[-1]
user_dict["slug"] = user_dict.get("slug", user_dict["email"].split("@")[0])
oid = user_dict["oid"]
user_dict["slug"] = user_dict["slug"].lower().strip().replace(" ", "-")
try:
user = User.create(**user_dict.copy())
except IntegrityError:
print("[migration] cannot create user " + user_dict["slug"])
with local_session() as session:
old_user = (
session.query(User).filter(User.slug == user_dict["slug"]).first()
)
old_user.oid = oid
old_user.password = user_dict["password"]
session.commit()
user = old_user
if not user:
print("[migration] ERROR: cannot find user " + user_dict["slug"])
raise Exception
user_dict["id"] = user.id
return user_dict
def post_migrate():
old_discours_dict = {
"slug": "old-discours",
"username": "old-discours",
"email": "old@discours.io",
"name": "Просмотры на старой версии сайта",
}
with local_session() as session:
old_discours_user = User.create(**old_discours_dict)
session.add(old_discours_user)
session.commit()
def migrate_2stage(entry, id_map):
ce = 0
for rating_entry in entry.get("ratings", []):
rater_oid = rating_entry["createdBy"]
rater_slug = id_map.get(rater_oid)
if not rater_slug:
ce += 1
# print(rating_entry)
continue
oid = entry["_id"]
author_slug = id_map.get(oid)
with local_session() as session:
try:
rater = session.query(User).where(User.slug == rater_slug).one()
user = session.query(User).where(User.slug == author_slug).one()
user_rating_dict = {
"value": rating_entry["value"],
"rater": rater.id,
"user": user.id,
}
user_rating = UserRating.create(**user_rating_dict)
if user_rating_dict["value"] > 0:
af = AuthorFollower.create(
author=user.id, follower=rater.id, auto=True
)
session.add(af)
session.add(user_rating)
session.commit()
except IntegrityError:
print("[migration] cannot rate " + author_slug + "`s by " + rater_slug)
except Exception as e:
print(e)
return ce