mirror of
https://gitlab.archlinux.org/archlinux/aurweb.git
synced 2025-02-03 10:43:03 +01:00
Refactor code to comply with flake8 and isort
Signed-off-by: Filipe Laíns <lains@archlinux.org> Signed-off-by: Lukas Fleischer <lfleischer@archlinux.org>
This commit is contained in:
Filipe Laíns
Lukas Fleischer
parent
48b58b1c2f
commit
8d1be7ea8a
11 changed files with 206 additions and 197 deletions
|
|
@ -10,33 +10,32 @@ usage: gendummydata.py outputfilename.sql
|
|||
# insert these users/packages into the AUR database.
|
||||
#
|
||||
import hashlib
|
||||
import random
|
||||
import time
|
||||
import os
|
||||
import sys
|
||||
import io
|
||||
import logging
|
||||
import os
|
||||
import random
|
||||
import sys
|
||||
import time
|
||||
|
||||
LOG_LEVEL = logging.DEBUG # logging level. set to logging.INFO to reduce output
|
||||
LOG_LEVEL = logging.DEBUG # logging level. set to logging.INFO to reduce output
|
||||
SEED_FILE = "/usr/share/dict/words"
|
||||
DB_HOST = os.getenv("DB_HOST", "localhost")
|
||||
DB_NAME = os.getenv("DB_NAME", "AUR")
|
||||
DB_USER = os.getenv("DB_USER", "aur")
|
||||
DB_PASS = os.getenv("DB_PASS", "aur")
|
||||
USER_ID = 5 # Users.ID of first bogus user
|
||||
PKG_ID = 1 # Packages.ID of first package
|
||||
DB_HOST = os.getenv("DB_HOST", "localhost")
|
||||
DB_NAME = os.getenv("DB_NAME", "AUR")
|
||||
DB_USER = os.getenv("DB_USER", "aur")
|
||||
DB_PASS = os.getenv("DB_PASS", "aur")
|
||||
USER_ID = 5 # Users.ID of first bogus user
|
||||
PKG_ID = 1 # Packages.ID of first package
|
||||
MAX_USERS = 300 # how many users to 'register'
|
||||
MAX_DEVS = .1 # what percentage of MAX_USERS are Developers
|
||||
MAX_TUS = .2 # what percentage of MAX_USERS are Trusted Users
|
||||
MAX_PKGS = 900 # how many packages to load
|
||||
PKG_DEPS = (1, 15) # min/max depends a package has
|
||||
PKG_RELS = (1, 5) # min/max relations a package has
|
||||
PKG_SRC = (1, 3) # min/max sources a package has
|
||||
MAX_DEVS = .1 # what percentage of MAX_USERS are Developers
|
||||
MAX_TUS = .2 # what percentage of MAX_USERS are Trusted Users
|
||||
MAX_PKGS = 900 # how many packages to load
|
||||
PKG_DEPS = (1, 15) # min/max depends a package has
|
||||
PKG_RELS = (1, 5) # min/max relations a package has
|
||||
PKG_SRC = (1, 3) # min/max sources a package has
|
||||
PKG_CMNTS = (1, 5) # min/max number of comments a package has
|
||||
CATEGORIES_COUNT = 17 # the number of categories from aur-schema
|
||||
VOTING = (0, .30) # percentage range for package voting
|
||||
OPEN_PROPOSALS = 5 # number of open trusted user proposals
|
||||
CLOSE_PROPOSALS = 15 # number of closed trusted user proposals
|
||||
VOTING = (0, .30) # percentage range for package voting
|
||||
OPEN_PROPOSALS = 5 # number of open trusted user proposals
|
||||
CLOSE_PROPOSALS = 15 # number of closed trusted user proposals
|
||||
RANDOM_TLDS = ("edu", "com", "org", "net", "tw", "ru", "pl", "de", "es")
|
||||
RANDOM_URL = ("http://www.", "ftp://ftp.", "http://", "ftp://")
|
||||
RANDOM_LOCS = ("pub", "release", "files", "downloads", "src")
|
||||
|
|
@ -48,20 +47,20 @@ logging.basicConfig(format=logformat, level=LOG_LEVEL)
|
|||
log = logging.getLogger()
|
||||
|
||||
if len(sys.argv) != 2:
|
||||
log.error("Missing output filename argument")
|
||||
raise SystemExit
|
||||
log.error("Missing output filename argument")
|
||||
raise SystemExit
|
||||
|
||||
# make sure the seed file exists
|
||||
#
|
||||
if not os.path.exists(SEED_FILE):
|
||||
log.error("Please install the 'words' Arch package")
|
||||
raise SystemExit
|
||||
log.error("Please install the 'words' Arch package")
|
||||
raise SystemExit
|
||||
|
||||
# make sure comments can be created
|
||||
#
|
||||
if not os.path.exists(FORTUNE_FILE):
|
||||
log.error("Please install the 'fortune-mod' Arch package")
|
||||
raise SystemExit
|
||||
log.error("Please install the 'fortune-mod' Arch package")
|
||||
raise SystemExit
|
||||
|
||||
# track what users/package names have been used
|
||||
#
|
||||
|
|
@ -69,21 +68,28 @@ seen_users = {}
|
|||
seen_pkgs = {}
|
||||
user_keys = []
|
||||
|
||||
|
||||
# some functions to generate random data
|
||||
#
|
||||
def genVersion():
|
||||
ver = []
|
||||
ver.append("%d" % random.randrange(0,10))
|
||||
ver.append("%d" % random.randrange(0,20))
|
||||
if random.randrange(0,2) == 0:
|
||||
ver.append("%d" % random.randrange(0,100))
|
||||
return ".".join(ver) + "-%d" % random.randrange(1,11)
|
||||
ver = []
|
||||
ver.append("%d" % random.randrange(0, 10))
|
||||
ver.append("%d" % random.randrange(0, 20))
|
||||
if random.randrange(0, 2) == 0:
|
||||
ver.append("%d" % random.randrange(0, 100))
|
||||
return ".".join(ver) + "-%d" % random.randrange(1, 11)
|
||||
|
||||
|
||||
def genCategory():
|
||||
return random.randrange(1,CATEGORIES_COUNT)
|
||||
return random.randrange(1, CATEGORIES_COUNT)
|
||||
|
||||
|
||||
def genUID():
|
||||
return seen_users[user_keys[random.randrange(0,len(user_keys))]]
|
||||
return seen_users[user_keys[random.randrange(0, len(user_keys))]]
|
||||
|
||||
|
||||
def genFortune():
|
||||
return fortunes[random.randrange(0,len(fortunes))].replace("'", "")
|
||||
return fortunes[random.randrange(0, len(fortunes))].replace("'", "")
|
||||
|
||||
|
||||
# load the words, and make sure there are enough words for users/pkgs
|
||||
|
|
@ -93,25 +99,25 @@ fp = open(SEED_FILE, "r", encoding="utf-8")
|
|||
contents = fp.readlines()
|
||||
fp.close()
|
||||
if MAX_USERS > len(contents):
|
||||
MAX_USERS = len(contents)
|
||||
MAX_USERS = len(contents)
|
||||
if MAX_PKGS > len(contents):
|
||||
MAX_PKGS = len(contents)
|
||||
MAX_PKGS = len(contents)
|
||||
if len(contents) - MAX_USERS > MAX_PKGS:
|
||||
need_dupes = 0
|
||||
need_dupes = 0
|
||||
else:
|
||||
need_dupes = 1
|
||||
need_dupes = 1
|
||||
|
||||
# select random usernames
|
||||
#
|
||||
log.debug("Generating random user names...")
|
||||
user_id = USER_ID
|
||||
while len(seen_users) < MAX_USERS:
|
||||
user = random.randrange(0, len(contents))
|
||||
word = contents[user].replace("'", "").replace(".","").replace(" ", "_")
|
||||
word = word.strip().lower()
|
||||
if word not in seen_users:
|
||||
seen_users[word] = user_id
|
||||
user_id += 1
|
||||
user = random.randrange(0, len(contents))
|
||||
word = contents[user].replace("'", "").replace(".", "").replace(" ", "_")
|
||||
word = word.strip().lower()
|
||||
if word not in seen_users:
|
||||
seen_users[word] = user_id
|
||||
user_id += 1
|
||||
user_keys = list(seen_users.keys())
|
||||
|
||||
# select random package names
|
||||
|
|
@ -119,17 +125,17 @@ user_keys = list(seen_users.keys())
|
|||
log.debug("Generating random package names...")
|
||||
num_pkgs = PKG_ID
|
||||
while len(seen_pkgs) < MAX_PKGS:
|
||||
pkg = random.randrange(0, len(contents))
|
||||
word = contents[pkg].replace("'", "").replace(".","").replace(" ", "_")
|
||||
word = word.strip().lower()
|
||||
if not need_dupes:
|
||||
if word not in seen_pkgs and word not in seen_users:
|
||||
seen_pkgs[word] = num_pkgs
|
||||
num_pkgs += 1
|
||||
else:
|
||||
if word not in seen_pkgs:
|
||||
seen_pkgs[word] = num_pkgs
|
||||
num_pkgs += 1
|
||||
pkg = random.randrange(0, len(contents))
|
||||
word = contents[pkg].replace("'", "").replace(".", "").replace(" ", "_")
|
||||
word = word.strip().lower()
|
||||
if not need_dupes:
|
||||
if word not in seen_pkgs and word not in seen_users:
|
||||
seen_pkgs[word] = num_pkgs
|
||||
num_pkgs += 1
|
||||
else:
|
||||
if word not in seen_pkgs:
|
||||
seen_pkgs[word] = num_pkgs
|
||||
num_pkgs += 1
|
||||
|
||||
# free up contents memory
|
||||
#
|
||||
|
|
@ -151,32 +157,32 @@ out.write("BEGIN;\n")
|
|||
#
|
||||
log.debug("Creating SQL statements for users.")
|
||||
for u in user_keys:
|
||||
account_type = 1 # default to normal user
|
||||
if not has_devs or not has_tus:
|
||||
account_type = random.randrange(1, 4)
|
||||
if account_type == 3 and not has_devs:
|
||||
# this will be a dev account
|
||||
#
|
||||
developers.append(seen_users[u])
|
||||
if len(developers) >= MAX_DEVS * MAX_USERS:
|
||||
has_devs = 1
|
||||
elif account_type == 2 and not has_tus:
|
||||
# this will be a trusted user account
|
||||
#
|
||||
trustedusers.append(seen_users[u])
|
||||
if len(trustedusers) >= MAX_TUS * MAX_USERS:
|
||||
has_tus = 1
|
||||
else:
|
||||
# a normal user account
|
||||
#
|
||||
pass
|
||||
account_type = 1 # default to normal user
|
||||
if not has_devs or not has_tus:
|
||||
account_type = random.randrange(1, 4)
|
||||
if account_type == 3 and not has_devs:
|
||||
# this will be a dev account
|
||||
#
|
||||
developers.append(seen_users[u])
|
||||
if len(developers) >= MAX_DEVS * MAX_USERS:
|
||||
has_devs = 1
|
||||
elif account_type == 2 and not has_tus:
|
||||
# this will be a trusted user account
|
||||
#
|
||||
trustedusers.append(seen_users[u])
|
||||
if len(trustedusers) >= MAX_TUS * MAX_USERS:
|
||||
has_tus = 1
|
||||
else:
|
||||
# a normal user account
|
||||
#
|
||||
pass
|
||||
|
||||
h = hashlib.new('md5')
|
||||
h.update(u.encode());
|
||||
s = ("INSERT INTO Users (ID, AccountTypeID, Username, Email, Passwd)"
|
||||
" VALUES (%d, %d, '%s', '%s@example.com', '%s');\n")
|
||||
s = s % (seen_users[u], account_type, u, u, h.hexdigest())
|
||||
out.write(s)
|
||||
h = hashlib.new('md5')
|
||||
h.update(u.encode())
|
||||
s = ("INSERT INTO Users (ID, AccountTypeID, Username, Email, Passwd)"
|
||||
" VALUES (%d, %d, '%s', '%s@example.com', '%s');\n")
|
||||
s = s % (seen_users[u], account_type, u, u, h.hexdigest())
|
||||
out.write(s)
|
||||
|
||||
log.debug("Number of developers: %d" % len(developers))
|
||||
log.debug("Number of trusted users: %d" % len(trustedusers))
|
||||
|
|
@ -193,123 +199,123 @@ fp.close()
|
|||
log.debug("Creating SQL statements for packages.")
|
||||
count = 0
|
||||
for p in list(seen_pkgs.keys()):
|
||||
NOW = int(time.time())
|
||||
if count % 2 == 0:
|
||||
muid = developers[random.randrange(0,len(developers))]
|
||||
puid = developers[random.randrange(0,len(developers))]
|
||||
else:
|
||||
muid = trustedusers[random.randrange(0,len(trustedusers))]
|
||||
puid = trustedusers[random.randrange(0,len(trustedusers))]
|
||||
if count % 20 == 0: # every so often, there are orphans...
|
||||
muid = "NULL"
|
||||
NOW = int(time.time())
|
||||
if count % 2 == 0:
|
||||
muid = developers[random.randrange(0, len(developers))]
|
||||
puid = developers[random.randrange(0, len(developers))]
|
||||
else:
|
||||
muid = trustedusers[random.randrange(0, len(trustedusers))]
|
||||
puid = trustedusers[random.randrange(0, len(trustedusers))]
|
||||
if count % 20 == 0: # every so often, there are orphans...
|
||||
muid = "NULL"
|
||||
|
||||
uuid = genUID() # the submitter/user
|
||||
uuid = genUID() # the submitter/user
|
||||
|
||||
s = ("INSERT INTO PackageBases (ID, Name, FlaggerComment, SubmittedTS, ModifiedTS, "
|
||||
s = ("INSERT INTO PackageBases (ID, Name, FlaggerComment, SubmittedTS, ModifiedTS, "
|
||||
"SubmitterUID, MaintainerUID, PackagerUID) VALUES (%d, '%s', '', %d, %d, %d, %s, %s);\n")
|
||||
s = s % (seen_pkgs[p], p, NOW, NOW, uuid, muid, puid)
|
||||
out.write(s)
|
||||
s = s % (seen_pkgs[p], p, NOW, NOW, uuid, muid, puid)
|
||||
out.write(s)
|
||||
|
||||
s = ("INSERT INTO Packages (ID, PackageBaseID, Name, Version) VALUES "
|
||||
s = ("INSERT INTO Packages (ID, PackageBaseID, Name, Version) VALUES "
|
||||
"(%d, %d, '%s', '%s');\n")
|
||||
s = s % (seen_pkgs[p], seen_pkgs[p], p, genVersion())
|
||||
out.write(s)
|
||||
s = s % (seen_pkgs[p], seen_pkgs[p], p, genVersion())
|
||||
out.write(s)
|
||||
|
||||
count += 1
|
||||
count += 1
|
||||
|
||||
# create random comments for this package
|
||||
#
|
||||
num_comments = random.randrange(PKG_CMNTS[0], PKG_CMNTS[1])
|
||||
for i in range(0, num_comments):
|
||||
now = NOW + random.randrange(400, 86400*3)
|
||||
s = ("INSERT INTO PackageComments (PackageBaseID, UsersID,"
|
||||
" Comments, RenderedComment, CommentTS) VALUES (%d, %d, '%s', '', %d);\n")
|
||||
s = s % (seen_pkgs[p], genUID(), genFortune(), now)
|
||||
out.write(s)
|
||||
# create random comments for this package
|
||||
#
|
||||
num_comments = random.randrange(PKG_CMNTS[0], PKG_CMNTS[1])
|
||||
for i in range(0, num_comments):
|
||||
now = NOW + random.randrange(400, 86400*3)
|
||||
s = ("INSERT INTO PackageComments (PackageBaseID, UsersID,"
|
||||
" Comments, RenderedComment, CommentTS) VALUES (%d, %d, '%s', '', %d);\n")
|
||||
s = s % (seen_pkgs[p], genUID(), genFortune(), now)
|
||||
out.write(s)
|
||||
|
||||
# Cast votes
|
||||
#
|
||||
track_votes = {}
|
||||
log.debug("Casting votes for packages.")
|
||||
for u in user_keys:
|
||||
num_votes = random.randrange(int(len(seen_pkgs)*VOTING[0]),
|
||||
int(len(seen_pkgs)*VOTING[1]))
|
||||
pkgvote = {}
|
||||
for v in range(num_votes):
|
||||
pkg = random.randrange(1, len(seen_pkgs) + 1)
|
||||
if pkg not in pkgvote:
|
||||
s = ("INSERT INTO PackageVotes (UsersID, PackageBaseID)"
|
||||
" VALUES (%d, %d);\n")
|
||||
s = s % (seen_users[u], pkg)
|
||||
pkgvote[pkg] = 1
|
||||
if pkg not in track_votes:
|
||||
track_votes[pkg] = 0
|
||||
track_votes[pkg] += 1
|
||||
out.write(s)
|
||||
num_votes = random.randrange(int(len(seen_pkgs)*VOTING[0]),
|
||||
int(len(seen_pkgs)*VOTING[1]))
|
||||
pkgvote = {}
|
||||
for v in range(num_votes):
|
||||
pkg = random.randrange(1, len(seen_pkgs) + 1)
|
||||
if pkg not in pkgvote:
|
||||
s = ("INSERT INTO PackageVotes (UsersID, PackageBaseID)"
|
||||
" VALUES (%d, %d);\n")
|
||||
s = s % (seen_users[u], pkg)
|
||||
pkgvote[pkg] = 1
|
||||
if pkg not in track_votes:
|
||||
track_votes[pkg] = 0
|
||||
track_votes[pkg] += 1
|
||||
out.write(s)
|
||||
|
||||
# Update statements for package votes
|
||||
#
|
||||
for p in list(track_votes.keys()):
|
||||
s = "UPDATE PackageBases SET NumVotes = %d WHERE ID = %d;\n"
|
||||
s = s % (track_votes[p], p)
|
||||
out.write(s)
|
||||
s = "UPDATE PackageBases SET NumVotes = %d WHERE ID = %d;\n"
|
||||
s = s % (track_votes[p], p)
|
||||
out.write(s)
|
||||
|
||||
# Create package dependencies and sources
|
||||
#
|
||||
log.debug("Creating statements for package depends/sources.")
|
||||
for p in list(seen_pkgs.keys()):
|
||||
num_deps = random.randrange(PKG_DEPS[0], PKG_DEPS[1])
|
||||
for i in range(0, num_deps):
|
||||
dep = random.choice([k for k in seen_pkgs])
|
||||
deptype = random.randrange(1, 5)
|
||||
if deptype == 4:
|
||||
dep += ": for " + random.choice([k for k in seen_pkgs])
|
||||
s = "INSERT INTO PackageDepends(PackageID, DepTypeID, DepName) VALUES (%d, %d, '%s');\n"
|
||||
s = s % (seen_pkgs[p], deptype, dep)
|
||||
out.write(s)
|
||||
num_deps = random.randrange(PKG_DEPS[0], PKG_DEPS[1])
|
||||
for i in range(0, num_deps):
|
||||
dep = random.choice([k for k in seen_pkgs])
|
||||
deptype = random.randrange(1, 5)
|
||||
if deptype == 4:
|
||||
dep += ": for " + random.choice([k for k in seen_pkgs])
|
||||
s = "INSERT INTO PackageDepends(PackageID, DepTypeID, DepName) VALUES (%d, %d, '%s');\n"
|
||||
s = s % (seen_pkgs[p], deptype, dep)
|
||||
out.write(s)
|
||||
|
||||
num_rels = random.randrange(PKG_RELS[0], PKG_RELS[1])
|
||||
for i in range(0, num_deps):
|
||||
rel = random.choice([k for k in seen_pkgs])
|
||||
reltype = random.randrange(1, 4)
|
||||
s = "INSERT INTO PackageRelations(PackageID, RelTypeID, RelName) VALUES (%d, %d, '%s');\n"
|
||||
s = s % (seen_pkgs[p], reltype, rel)
|
||||
out.write(s)
|
||||
num_rels = random.randrange(PKG_RELS[0], PKG_RELS[1])
|
||||
for i in range(0, num_deps):
|
||||
rel = random.choice([k for k in seen_pkgs])
|
||||
reltype = random.randrange(1, 4)
|
||||
s = "INSERT INTO PackageRelations(PackageID, RelTypeID, RelName) VALUES (%d, %d, '%s');\n"
|
||||
s = s % (seen_pkgs[p], reltype, rel)
|
||||
out.write(s)
|
||||
|
||||
num_sources = random.randrange(PKG_SRC[0], PKG_SRC[1])
|
||||
for i in range(num_sources):
|
||||
src_file = user_keys[random.randrange(0, len(user_keys))]
|
||||
src = "%s%s.%s/%s/%s-%s.tar.gz" % (
|
||||
RANDOM_URL[random.randrange(0,len(RANDOM_URL))],
|
||||
p, RANDOM_TLDS[random.randrange(0,len(RANDOM_TLDS))],
|
||||
RANDOM_LOCS[random.randrange(0,len(RANDOM_LOCS))],
|
||||
src_file, genVersion())
|
||||
s = "INSERT INTO PackageSources(PackageID, Source) VALUES (%d, '%s');\n"
|
||||
s = s % (seen_pkgs[p], src)
|
||||
out.write(s)
|
||||
num_sources = random.randrange(PKG_SRC[0], PKG_SRC[1])
|
||||
for i in range(num_sources):
|
||||
src_file = user_keys[random.randrange(0, len(user_keys))]
|
||||
src = "%s%s.%s/%s/%s-%s.tar.gz" % (
|
||||
RANDOM_URL[random.randrange(0, len(RANDOM_URL))],
|
||||
p, RANDOM_TLDS[random.randrange(0, len(RANDOM_TLDS))],
|
||||
RANDOM_LOCS[random.randrange(0, len(RANDOM_LOCS))],
|
||||
src_file, genVersion())
|
||||
s = "INSERT INTO PackageSources(PackageID, Source) VALUES (%d, '%s');\n"
|
||||
s = s % (seen_pkgs[p], src)
|
||||
out.write(s)
|
||||
|
||||
# Create trusted user proposals
|
||||
#
|
||||
log.debug("Creating SQL statements for trusted user proposals.")
|
||||
count=0
|
||||
count = 0
|
||||
for t in range(0, OPEN_PROPOSALS+CLOSE_PROPOSALS):
|
||||
now = int(time.time())
|
||||
if count < CLOSE_PROPOSALS:
|
||||
start = now - random.randrange(3600*24*7, 3600*24*21)
|
||||
end = now - random.randrange(0, 3600*24*7)
|
||||
else:
|
||||
start = now
|
||||
end = now + random.randrange(3600*24, 3600*24*7)
|
||||
if count % 5 == 0: # Don't make the vote about anyone once in a while
|
||||
user = ""
|
||||
else:
|
||||
user = user_keys[random.randrange(0,len(user_keys))]
|
||||
suid = trustedusers[random.randrange(0,len(trustedusers))]
|
||||
s = ("INSERT INTO TU_VoteInfo (Agenda, User, Submitted, End,"
|
||||
" Quorum, SubmitterID) VALUES ('%s', '%s', %d, %d, 0.0, %d);\n")
|
||||
s = s % (genFortune(), user, start, end, suid)
|
||||
out.write(s)
|
||||
count += 1
|
||||
now = int(time.time())
|
||||
if count < CLOSE_PROPOSALS:
|
||||
start = now - random.randrange(3600*24*7, 3600*24*21)
|
||||
end = now - random.randrange(0, 3600*24*7)
|
||||
else:
|
||||
start = now
|
||||
end = now + random.randrange(3600*24, 3600*24*7)
|
||||
if count % 5 == 0: # Don't make the vote about anyone once in a while
|
||||
user = ""
|
||||
else:
|
||||
user = user_keys[random.randrange(0, len(user_keys))]
|
||||
suid = trustedusers[random.randrange(0, len(trustedusers))]
|
||||
s = ("INSERT INTO TU_VoteInfo (Agenda, User, Submitted, End,"
|
||||
" Quorum, SubmitterID) VALUES ('%s', '%s', %d, %d, 0.0, %d);\n")
|
||||
s = s % (genFortune(), user, start, end, suid)
|
||||
out.write(s)
|
||||
count += 1
|
||||
|
||||
# close output file
|
||||
#
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue