- make the sql nicer and more readable
- convert to spaces. who uses tabs in python!?
---
support/schema/gendummydata.py | 248
1 files changed, 124 insertions(+), 124 deletions(-)
diff --git a/support/schema/gendummydata.py b/support/schema/gendummydata.py
index d424564..6ad4fb2 100755
--- a/support/schema/gendummydata.py
+++ b/support/schema/gendummydata.py
@@ -37,10 +37,10 @@ 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
RANDOM_PATHS = ( # random path locations for package files
- /usr/bin, /usr/lib, /etc, /etc/rc.d, /usr/share, /lib,
- /var/spool, /var/log, /usr/sbin, /opt, /usr/X11R6/bin,
- /usr/X11R6/lib, /usr/libexec, /usr/man/man1, /usr/man/man3,
- /usr/man/man5, /usr/X11R6/man/man1, /etc/profile.d
+/usr/bin, /usr/lib, /etc, /etc/rc.d, /usr/share, /lib,
+/var/spool, /var/log, /usr/sbin, /opt, /usr/X11R6/bin,
+/usr/X11R6/lib, /usr/libexec, /usr/man/man1, /usr/man/man3,
+/usr/man/man5, /usr/X11R6/man/man1, /etc/profile.d
)
RANDOM_TLDS = (edu, com, org, net, tw, ru, pl, de, es)
RANDOM_URL = (http://www.;, ftp://ftp.;, http://;, ftp://;)
@@ -57,14 +57,14 @@ logging.basicConfig(format=logformat, level=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
# track what users/package names have been used
#
@@ -75,16 +75,16 @@ 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) + -u%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) + -u%d % random.randrange(1,11)
def genCategory():
- return random.randrange(0,CATEGORIES_COUNT)
+return random.randrange(0,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))]]
# load the words, and make sure there are enough words for users/pkgs
@@ -94,25 +94,25 @@ fp = open(SEED_FILE, r)
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 not seen_users.has_key(word):
- 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 not seen_users.has_key(word):
+seen_users[word] = user_id
+user_id += 1
user_keys = seen_users.keys()
# select random package names
@@ -120,17 +120,17 @@ user_keys = 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 not seen_pkgs.has_key(word) and not seen_users.has_key(word):
- seen_pkgs[word] = num_pkgs
- num_pkgs += 1
- else:
- if not seen_pkgs.has_key(word):
- 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 not seen_pkgs.has_key(word) and not seen_users.has_key(word):
+seen_pkgs[word] = num_pkgs
+num_pkgs += 1
+else:
+if not seen_pkgs.has_key(word):
+seen_pkgs[word] = num_pkgs
+
