Skip to content

[FIX] spreadsheet: batch process spreadsheet_revision.commands #284

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
wants to merge 1 commit into
base: master
Choose a base branch
from
Open
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
72 changes: 49 additions & 23 deletions src/util/spreadsheet/misc.py
Original file line number Diff line number Diff line change
@@ -1,32 +1,58 @@
from .. import json
from .. import json, pg

MEMORY_CAP = 2 * 10**8 # 200MB


def iter_commands(cr, like_all=(), like_any=()):
if not (bool(like_all) ^ bool(like_any)):
raise ValueError("Please specify `like_all` or `like_any`, not both")
cr.execute(
"""
SELECT id,
commands
FROM spreadsheet_revision
WHERE commands LIKE {}(%s::text[])
""".format("ALL" if like_all else "ANY"),
[list(like_all or like_any)],
)
for revision_id, data in cr.fetchall():
data_loaded = json.loads(data)
if "commands" not in data_loaded:
continue
data_old = json.dumps(data_loaded, sort_keys=True)

changed = yield data_loaded["commands"]
if changed is None:
changed = data_old != json.dumps(data_loaded, sort_keys=True)

if changed:
cr.execute(
"UPDATE spreadsheet_revision SET commands=%s WHERE id=%s", [json.dumps(data_loaded), revision_id]

with pg.named_cursor(cr, itersize=1) as ncr:
ncr.execute(
"""
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Use format_query. The query is becoming increasingly complex, better use the right formatting tool to avoid issues later.

Suggested change
"""
util.format_query(
cr,
"""

WITH filtered AS (
SELECT id,
commands,
LENGTH(commands) AS commands_length
FROM spreadsheet_revision
WHERE commands LIKE {condition} (%s::text[])
), smaller AS (
SELECT id,
commands,
sum(commands_length) OVER (ORDER BY id) / %s AS num
FROM filtered
WHERE commands_length <= %s
)
SELECT array_agg(id ORDER BY id),
array_agg(commands ORDER BY id)
FROM smaller
GROUP BY num

UNION ALL

SELECT ARRAY[id],
ARRAY[commands]
FROM filtered
WHERE commands_length > %s
""".format(condition=pg.SQLStr("ALL" if like_all else "ANY")),
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Suggested change
""".format(condition=pg.SQLStr("ALL" if like_all else "ANY")),
""",
condition=pg.SQLStr("ALL" if like_all else "ANY"),
) # close format_query

[list(like_any or like_all), MEMORY_CAP, MEMORY_CAP, MEMORY_CAP],
)
for ids, commands in ncr:
for revision_id, data in zip(ids, commands):
data_loaded = json.loads(data)
if "commands" not in data_loaded:
continue
data_old = json.dumps(data_loaded, sort_keys=True)

changed = yield data_loaded["commands"]
if changed is None:
changed = data_old != json.dumps(data_loaded, sort_keys=True)

if changed:
cr.execute(
"UPDATE spreadsheet_revision SET commands=%s WHERE id=%s",
[json.dumps(data_loaded), revision_id],
)


def process_commands(cr, callback, *args, **kwargs):
Expand Down