( )⚙ D10901 censor: extract the part about creating and opening new files in a function

This is an archive of the discontinued Mercurial Phabricator instance.

Differential D10901

censor: extract the part about creating and opening new files in a function
ClosedPublic

Authored by marmoute on Jun 22 2021, 7:27 PM.

Details

Reviewers
Alphare
Group Reviewers
hg-reviewers
Commits
rHGd6afe1478a2a: censor: extract the part about creating and opening new files in a function
Summary

The v2_censor function is huge, now that its content has settled a bit it is a
good time to split individual part inside dedicated function.

The last part is the file copying and opening logic. It now have its own
function.

Diff Detail

Repository
rHG Mercurial
Branch
default
Lint
No Linters Available
Unit
No Unit Test Coverage

Revision Contents
Changeset List

PathPackages
Mmercurial/revlogutils/rewrite.py (133 lines)

Diff 28680

mercurial/revlogutils/rewrite.py

# rev → (new_base, data_start, data_end, compression_mode) # rev → (new_base, data_start, data_end, compression_mode)
rewritten_entries = _precompute_rewritten_delta( rewritten_entries = _precompute_rewritten_delta(
rl, rl,
old_index, old_index,
{censor_rev}, {censor_rev},
tmp_storage, tmp_storage,
) )
old_index_filepath = rl.opener.join(docket.index_filepath()) all_files = _setup_new_files(
old_data_filepath = rl.opener.join(docket.data_filepath()) rl,
old_sidedata_filepath = rl.opener.join(docket.sidedata_filepath()) index_cutoff,
data_cutoff,
new_index_filepath = rl.opener.join(docket.new_index_file()) sidedata_cutoff,
new_data_filepath = rl.opener.join(docket.new_data_file())
new_sidedata_filepath = rl.opener.join(docket.new_sidedata_file())
util.copyfile(
old_index_filepath, new_index_filepath, nb_bytes=index_cutoff
)
util.copyfile(
old_data_filepath, new_data_filepath, nb_bytes=data_cutoff
)
util.copyfile(
old_sidedata_filepath,
new_sidedata_filepath,
nb_bytes=sidedata_cutoff,
)
rl.opener.register_file(docket.index_filepath())
rl.opener.register_file(docket.data_filepath())
rl.opener.register_file(docket.sidedata_filepath())
docket.index_end = index_cutoff
docket.data_end = data_cutoff
docket.sidedata_end = sidedata_cutoff
# reload the revlog internal information
rl.clearcaches()
rl._loadindex(docket=docket)
@contextlib.contextmanager
def all_files():
# hide opening in an helper function to please check-code, black
# and various python ersion at the same time
with open(old_data_filepath, 'rb') as old_data_file:
with open(old_sidedata_filepath, 'rb') as old_sidedata_file:
with open(new_index_filepath, 'r+b') as new_index_file:
with open(new_data_filepath, 'r+b') as new_data_file:
with open(
new_sidedata_filepath, 'r+b'
) as new_sidedata_file:
yield (
old_data_file,
old_sidedata_file,
new_index_file,
new_data_file,
new_sidedata_file,
) )
# we dont need to open the old index file since its content already # we dont need to open the old index file since its content already
# exist in a usable form in `old_index`. # exist in a usable form in `old_index`.
with all_files() as open_files: with all_files() as open_files:
( (
old_data_file, old_data_file,
old_sidedata_file, old_sidedata_file,
new_index_file, new_index_file,
new_data_file, new_data_file,
new_sidedata_file, new_sidedata_file,
) = open_files ) = open_files
new_index_file.seek(0, os.SEEK_END)
assert new_index_file.tell() == index_cutoff
new_data_file.seek(0, os.SEEK_END)
assert new_data_file.tell() == data_cutoff
new_sidedata_file.seek(0, os.SEEK_END)
assert new_sidedata_file.tell() == sidedata_cutoff
# writing the censored revision # writing the censored revision
_rewrite_censor( _rewrite_censor(
rl, rl,
old_index, old_index,
open_files, open_files,
censor_rev, censor_rev,
tombstone, tombstone,
# using `tell` is a bit lazy, but we are not here for speed # using `tell` is a bit lazy, but we are not here for speed
start = tmp_storage.tell() start = tmp_storage.tell()
tmp_storage.write(d.data[1]) tmp_storage.write(d.data[1])
end = tmp_storage.tell() end = tmp_storage.tell()
rewritten_entries[rev] = (d.base, start, end, comp_mode) rewritten_entries[rev] = (d.base, start, end, comp_mode)
return rewritten_entries return rewritten_entries
def _setup_new_files(
revlog,
index_cutoff,
data_cutoff,
sidedata_cutoff,
):
"""
return a context manager to open all the relevant files:
- old_data_file,
- old_sidedata_file,
- new_index_file,
- new_data_file,
- new_sidedata_file,
The old_index_file is not here because it is accessed through the
`old_index` object if the caller function.
"""
docket = revlog._docket
old_index_filepath = revlog.opener.join(docket.index_filepath())
old_data_filepath = revlog.opener.join(docket.data_filepath())
old_sidedata_filepath = revlog.opener.join(docket.sidedata_filepath())
new_index_filepath = revlog.opener.join(docket.new_index_file())
new_data_filepath = revlog.opener.join(docket.new_data_file())
new_sidedata_filepath = revlog.opener.join(docket.new_sidedata_file())
util.copyfile(old_index_filepath, new_index_filepath, nb_bytes=index_cutoff)
util.copyfile(old_data_filepath, new_data_filepath, nb_bytes=data_cutoff)
util.copyfile(
old_sidedata_filepath,
new_sidedata_filepath,
nb_bytes=sidedata_cutoff,
)
revlog.opener.register_file(docket.index_filepath())
revlog.opener.register_file(docket.data_filepath())
revlog.opener.register_file(docket.sidedata_filepath())
docket.index_end = index_cutoff
docket.data_end = data_cutoff
docket.sidedata_end = sidedata_cutoff
# reload the revlog internal information
revlog.clearcaches()
revlog._loadindex(docket=docket)
@contextlib.contextmanager
def all_files_opener():
# hide opening in an helper function to please check-code, black
# and various python ersion at the same time
with open(old_data_filepath, 'rb') as old_data_file:
with open(old_sidedata_filepath, 'rb') as old_sidedata_file:
with open(new_index_filepath, 'r+b') as new_index_file:
with open(new_data_filepath, 'r+b') as new_data_file:
with open(
new_sidedata_filepath, 'r+b'
) as new_sidedata_file:
new_index_file.seek(0, os.SEEK_END)
assert new_index_file.tell() == index_cutoff
new_data_file.seek(0, os.SEEK_END)
assert new_data_file.tell() == data_cutoff
new_sidedata_file.seek(0, os.SEEK_END)
assert new_sidedata_file.tell() == sidedata_cutoff
yield (
old_data_file,
old_sidedata_file,
new_index_file,
new_data_file,
new_sidedata_file,
)
return all_files_opener
def _rewrite_simple( def _rewrite_simple(
revlog, revlog,
old_index, old_index,
all_files, all_files,
rev, rev,
rewritten_entries, rewritten_entries,
tmp_storage, tmp_storage,
): ):