runbot/mergebot_test_utils/utils.py

234 lines
8.0 KiB
Python
Raw Permalink Normal View History

# -*- coding: utf-8 -*-
import contextlib
import itertools
import re
import time
import typing
from lxml import html
MESSAGE_TEMPLATE = """{message}
closes {repo}#{number}
{headers}Signed-off-by: {name} <{email}>"""
# target branch '-' source branch '-' batch id '-fw'
REF_PATTERN = r'{target}-{source}-\d+-fw'
class Commit:
def __init__(self, message, *, author=None, committer=None, tree, reset=False):
self.id = None
self.message = message
self.author = author
self.committer = committer
self.tree = tree
self.reset = reset
def validate_all(repos, refs, contexts=('default',)):
""" Post a "success" status for each context on each ref of each repo
"""
for repo, branch, context in itertools.product(repos, refs, contexts):
repo.post_status(branch, 'success', context)
def get_partner(env, gh_login):
return env['res.partner'].search([('github_login', '=', gh_login)])
def _simple_init(repo):
""" Creates a very simple initialisation: a master branch with a commit,
and a PR by 'user' with two commits, targeted to the master branch
"""
m = repo.make_commit(None, 'initial', None, tree={'m': 'm'})
repo.make_ref('heads/master', m)
c1 = repo.make_commit(m, 'first', None, tree={'m': 'c1'})
c2 = repo.make_commit(c1, 'second', None, tree={'m': 'c2'})
prx = repo.make_pr(title='title', body='body', target='master', head=c2)
return prx
class matches(str):
# necessary so str.__new__ does not freak out on `flags`
def __new__(cls, pattern, flags=0):
return super().__new__(cls, pattern)
def __init__(self, pattern, flags=0):
p, n = re.subn(
# `re.escape` will escape the `$`, so we need to handle that...
# maybe it should not be $?
r'\\\$(\w*?)\\\$',
lambda m: f'(?P<{m[1]}>.*?)' if m[1] else '(.*?)',
re.escape(self),
)
assert n, f"matches' pattern should have at least one placeholder, found none in\n{pattern}"
self._r = re.compile(p, flags | re.DOTALL)
def __eq__(self, text):
if not isinstance(text, str):
return NotImplemented
return self._r.search(text)
def seen(env, pr, users):
url = to_pr(env, pr).url
return users['user'], f'[![Pull request status dashboard]({url}.png)]({url})'
def make_basic(
env,
config,
make_repo,
*,
project_name='myproject',
reponame='proj',
statuses,
fp_token=True,
fp_remote=True,
):
""" Creates a project ``project_name`` **if none exists**, otherwise
retrieves the existing one and adds a new repository and its fork.
Repositories are setup with three forking branches:
::
f = 0 -- 1 -- 2 -- 3 -- 4 : a
|
g = `-- 11 -- 22 : b
|
h = `-- 111 : c
each branch just adds and modifies a file (resp. f, g and h) through the
contents sequence a b c d e
:param env: Environment, for odoo model interactions
:param config: pytest project config thingie
:param make_repo: repo maker function, normally the fixture, should be a
``Callable[[str], Repo]``
:param project_name: internal project name, can be used to recover the
project object afterward, matches exactly since it's
unique per odoo db (and thus test)
:param reponame: the base name of the repository, for identification, for
concurrency reasons the actual repository name *will* be
different
:param statuses: required statuses for the repository, stupidly default to
the old Odoo statuses, should be moved to ``default`` over
time for simplicity (unless the test specifically calls for
multiple statuses)
:param fp_token: whether to set the ``fp_github_token`` on the project if
/ when creating it
:param fp_remote: whether to create a fork repo and set it as the
repository's ``fp_remote_target``
"""
Projects = env['runbot_merge.project']
project = Projects.search([('name', '=', project_name)])
if not project:
project = env['runbot_merge.project'].create({
'name': project_name,
'github_token': config['github']['token'],
'github_prefix': 'hansen',
'github_name': config['github']['name'],
'github_email': "foo@example.org",
'fp_github_token': fp_token and config['github']['token'],
'fp_github_name': 'herbert',
'branch_ids': [
(0, 0, {'name': 'a', 'sequence': 100}),
(0, 0, {'name': 'b', 'sequence': 80}),
(0, 0, {'name': 'c', 'sequence': 60}),
],
})
prod = make_repo(reponame)
env['runbot_merge.events_sources'].create({'repository': prod.name})
with prod:
_0, _1, a_2, _3, _4, = prod.make_commits(
None,
Commit("0", tree={'f': 'a'}),
Commit("1", tree={'f': 'b'}),
Commit("2", tree={'f': 'c'}),
Commit("3", tree={'f': 'd'}),
Commit("4", tree={'f': 'e'}),
ref='heads/a',
)
b_1, _2 = prod.make_commits(
a_2,
Commit('11', tree={'g': 'a'}),
Commit('22', tree={'g': 'b'}),
ref='heads/b',
)
prod.make_commits(
b_1,
Commit('111', tree={'h': 'a'}),
ref='heads/c',
)
other = prod.fork() if fp_remote else None
repo = env['runbot_merge.repository'].create({
'project_id': project.id,
'name': prod.name,
'required_statuses': statuses,
'fp_remote_target': other.name if other else False,
'group_id': False,
})
env['res.partner'].search([
('github_login', '=', config['role_reviewer']['user'])
]).write({
'review_rights': [(0, 0, {'repository_id': repo.id, 'review': True})]
})
env['res.partner'].search([
('github_login', '=', config['role_self_reviewer']['user'])
]).write({
'review_rights': [(0, 0, {'repository_id': repo.id, 'self_review': True})]
})
return prod, other
def pr_page(page, pr):
return html.fromstring(page(f'/{pr.repo.name}/pull/{pr.number}'))
def to_pr(env, pr, *, attempts=5):
for _ in range(attempts):
pr_id = env['runbot_merge.pull_requests'].search([
('repository.name', '=', pr.repo.name),
('number', '=', pr.number),
])
if pr_id:
assert len(pr_id) == 1, f"Expected to find {pr.repo.name}#{pr.number}, got {pr_id}."
return pr_id
time.sleep(1)
raise TimeoutError(f"Unable to find {pr.repo.name}#{pr.number}")
def part_of(label, pr_id, *, separator='\n\n'):
""" Adds the "part-of" pseudo-header in the footer.
"""
return f"""\
{label}{separator}\
Part-of: {pr_id.display_name}
Signed-off-by: {pr_id.reviewed_by.formatted_email}"""
[CHG] *: rewrite commands set, rework status management This commit revisits the commands set in order to make it more regular, and limit inconsistent command-sets, although it includes pseudo-command aliases for common tasks now removed from the core set. Hard Errors =========== The previous iteration of the commands set would ignore any non-command term in a command line. This has been changed to hard error (and ignoring the entire thing) if any command is unknown or invalid. This fixes inconsistent / unexpected interpretations where a user sends a command, then writes a novel on the same line some words of which happen to *also* be commands, leading to merge states they did not expect. They should now be told to fuck off. Priority Restructuring ---------------------- The numerical priority system was pretty messy in that it confused "staging priority" (in ways which were not entirely straightforward) with overrides to other concerns. This has now being split along all the axis, with separate command subsets for: - staging prioritisation, now separated between `default`, `priority`, and `alone`, - `default` means PRs are picked by an unspecified order when creating a staging, if nothing better is available - `priority` means PRs are picked first when staging, however if `priority` PRs don't fill the staging the rest will be filled with `default`, this mode did not previously exist - `alone` means the PRs are picked first, before splits, and only `alone` PRs can be part of the staging (which usually matches the modename) - `skipchecks` overrides both statuses and approval checks, for the batch, something previously implied in `p=0`, but now independent. Setting `skipchecks` basically makes the entire batch `ready`. For consistency this also sets the reviewer implicitly: since skipchecks overrides both statuses *and approval*, whoever enables this mode is essentially the reviewer. - `cancel` cancels any ongoing staging when the marked PR becomes ready again, previously this was also implied (in a more restricted form) by setting `p=0` FWBot removal ============= While the "forwardport bot" still exists as an API level (to segregate access rights between tokens) it has been removed as an interaction point, as part of the modules merge plan. As a result, fwbot stops responding ---------------------- Feedback messages are now always sent by the mergebot, the forward-porting bot should not send any message or notification anymore. commands moved to the merge bot ------------------------------- - `ignore`/`up to` simply changes bot - `close` as well - `skipci` is now a choice / flag of an `fw` command, which denotes the forward-port policy, - `fw=default` is the old `ci` and resets the policy to default, that is wait for the PR to be merged to create forward ports, and for the required statuses on each forward port to be received before creating the next - `fw=skipci` is the old `skipci`, it waits for the merge of the base PR but then creates all the forward ports immediately (unless it gets a conflict) - `fw=skipmerge` immediately creates all the forward ports, without even waiting for the PR to be merged This is a completely new mode, and may be rather broken as until now the 'bot has always assumed the source PR had been merged. approval rework --------------- Because of the previous section, there is no distinguishing feature between `mergebot r+` = "merge this PR" and `forwardbot r+` = "merge this PR and all its parent with different access rights". As a result, the two have been merged under a single `mergebot r+` with heuristics attempting to provide the best experience: - if approving a non-forward port, the behavior does not change - else, with review rights on the source, all ancestors are approved - else, as author of the original, approves all ancestors which descend from a merged PR - else, approves all ancestors up to and including the oldest ancestor to which we have review rights Most notably, the source's author is not delegated on the source or any of its descendants anymore. This might need to be revisited if it provides too restrictive. For the very specialized need of approving a forward-port *and none of its ancestors*, `review=` can now take a comma (`,`) separated list of pull request numbers (github numbers, not mergebot ids). Computed State ============== The `state` field of pull requests is now computed. Hopefully this makes the status more consistent and predictable in the long run, and importantly makes status management more reliable (because reference datum get updated naturally flowing to the state). For now however it makes things more complicated as some of the states have to be separately signaled or updated: - `closed` and `error` are now separate flags - `merge_date` is pulled down from forwardport and becomes the transition signal for ready -> merged - `reviewed_by` becomes the transition signal for approval (might be a good idea to rename it...) - `status` is computed from the head's statuses and overrides, and *that* becomes the validation state Ideally, batch-level flags like `skipchecks` should be on, well, the batch, and `state` should have a dependency on the batch. However currently the batch is not a durable / permanent member of the system, so it's a PR-level flag and a messy pile. On notable change is that *forcing* the state to `ready` now does that but also sets the reviewer, `skipchecks`, and overrides to ensure the API-mediated readying does not get rolled back by e.g. the runbot sending a status. This is useful for a few types of automated / programmatic PRs e.g. translation exports, where we set the state programmatically to limit noise. recursive dependency hack ------------------------- Given a sequence of PRs with an override of the source, if one of the PRs is updated its descendants should not have the override anymore. However if the updated PR gets overridden, its descendants should have *that* override. This requires some unholy manipulations via an override of `modified`, as the ORM supports recursive fields but not recursive dependencies (on a different field). unconditional followup scheduling --------------------------------- Previously scheduling forward-port followup was contigent on the FW policy, but it's not actually correct if the new PR is *immediately* validated (which can happen now that the field is computed, if there are no required statuses *or* all of the required statuses are overridden by an ancestor) as nothing will trigger the state change and thus scheduling of the fp followup. The followup function checks all the properties of the batch to port, so this should not result on incorrect ports. Although it's a bit more expensive, and will lead to more spam. Previously this would not happen because on creation of a PR the validation task (commit -> PR) would still have to execute. Misc Changes ============ - If a PR is marked as overriding / canceling stagings, it now does so on retry not just when setting initially. This was not handled at all previously, so a PR in P0 going into error due to e.g. a non-deterministic bug would be retried and still p=0, but a current staging would not get cancelled. Same when a PR in p=0 goes into error because something was failed, then is updated with a fix. - Add tracking to a bunch of relevant PR fields. Post-mortem analysis currently generally requires going through the text logs to see what happened, which is annoying. There is a nondeterminism / inconsistency in the tracking which sometimes leads the admin user to trigger tracking before the bot does, leading to the staging tracking being attributed to them during tests, shove under the carpet by ignoring the user to whom that tracking is attributed. When multiple users update tracked fields in the same transaction all the changes are attributed to the first one having triggered tracking (?), I couldn't find why the admin sometimes takes over. - added and leveraged support for enum-backed selection fields - moved variuous fields from forwardport to runbot_merge - fix a migration which had never worked and which never run (because I forgot to bump the version on the module) - remove some unnecessary intermediate de/serialisation fixes #673, fixes #309, fixes #792, fixes #846 (probably)
2023-10-31 13:42:07 +07:00
def ensure_one(records):
assert len(records) == 1
return records
@contextlib.contextmanager
def prevent_unstaging(st) -> None:
# hack: `Stagings.cancel` only cancels *active* stagings,
# so if we disable the staging, do a thing, then re-enable
# then things should work out
assert st and st.active, "preventing unstaging of not-a-staging is not useful"
st.active = False
try:
yield
finally:
st.active = True
TYPE_MAPPING = {
'boolean': 'integer',
'date': 'datetime',
'monetary': 'float',
'selection': 'char',
'many2one': 'char',
}
def read_tracking_value(tv) -> tuple[str, typing.Any, typing.Any]:
field_id = tv.field_id if 'field_id' in tv else tv.field
field_type = field_id.field_type if 'field_type' in field_id else field_id.ttype
t = TYPE_MAPPING.get(field_type) or field_type
return field_id.name, tv[f"old_value_{t}"], tv[f"new_value_{t}"]