diff options
| author | dumpfmprod <dumpfmprod@ubuntu.(none)> | 2010-10-24 20:16:20 -0400 |
|---|---|---|
| committer | dumpfmprod <dumpfmprod@ubuntu.(none)> | 2010-10-24 20:16:20 -0400 |
| commit | fafbde26383e42858538046d4b2b3691e21bd898 (patch) | |
| tree | b8f9d164305e92d1bbc8b7f5a278c195a3903a16 /scripts/fill.image_altars.py | |
| parent | d79fb90ae279d0f46606c305688e97e73374eacc (diff) | |
Update python scripts
Diffstat (limited to 'scripts/fill.image_altars.py')
| -rw-r--r-- | scripts/fill.image_altars.py | 26 |
1 files changed, 13 insertions, 13 deletions
diff --git a/scripts/fill.image_altars.py b/scripts/fill.image_altars.py index 4b8dd91..8321ffa 100644 --- a/scripts/fill.image_altars.py +++ b/scripts/fill.image_altars.py @@ -28,10 +28,9 @@ def add_altar(message_id, user_id, content): print("skipped adding a dupe") # NOTE. hardcoded room numbers to index here... only indexing DUMPFM (1) and GIF (8) currently. -def get_messages(lower, upper): +def get_messages(): ps = db.prepare("SELECT message_id, user_id, content FROM messages WHERE message_id >= $1 AND message_id <= $2 AND room_id IN (1,8) ORDER BY message_id ASC") - rows = ps(lower, upper) - return rows + return ps.chunks def is_url_an_image(url): image_types = {"jpg", "bmp", "gif", "png"} @@ -65,16 +64,17 @@ def is_altar(content): i += 1 return True -def process_messages(messages): +def process_messages(chunks, lower, upper): num_added = 0 processed = 0 - for message in messages: - if processed % 1000 == 0: - print(processed, " processed so far") - processed += 1 - if is_altar(message[2]): - add_altar(message[0], message[1], message[2]) - num_added += 1 + for rowset in chunks(lower, upper): + for message in rowset: + if processed % 1000 == 0: + print(processed, " processed so far") + processed += 1 + if is_altar(message[2]): + add_altar(message[0], message[1], message[2]) + num_added += 1 return num_added def get_urls_from_messages(messages): @@ -100,6 +100,6 @@ if __name__ == "__main__": upper = int(sys.argv[1]) highest = get_highest_message_id_in_db() - messages = get_messages(highest, upper) - num_added = process_messages(messages) + chunks = get_messages() + num_added = process_messages(chunks, highest, upper) print("added ", num_added, " altars to db") |
