Skip to content

perf: share repeated source message IDs when reading PO catalogs #1395

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.

Sign up for GitHub

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
SAY-5 wants to merge 1 commit into
base: master
Choose a base branch
from
+36 −0
Open

perf: share repeated source message IDs when reading PO catalogs #1395

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
6 changes: 6 additions & 0 deletions babel/messages/pofile.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -174,6 +174,8 @@ def __init__(
self.counter = 0
self.offset = 0
self.abort_invalid = abort_invalid
# Identical message IDs share one string object while parsing.
self._msgids: dict[str, str] = {}
self._reset_message_state()

def _reset_message_state(self) -> None:
Expand Down Expand Up @@ -210,6 +212,10 @@ def _add_message(self) -> None:
else:
msgid = self.messages[0].denormalize()
string = self.translations[0][1].denormalize()
if isinstance(msgid, tuple):
msgid = tuple(self._msgids.setdefault(part, part) for part in msgid)
else:
msgid = self._msgids.setdefault(msgid, msgid)
msgctxt = self.context.denormalize() if self.context else None
message = Message(
msgid,
Expand Down
30 changes: 30 additions & 0 deletions tests/messages/test_pofile_read.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -406,6 +406,36 @@ def test_with_context_two():
assert out_buf.getvalue().strip() == buf.getvalue().strip(), out_buf.getvalue()


def test_repeated_msgids_share_strings():
buf = StringIO(r'''msgctxt "Menu"
msgid "Open"
msgstr "Ouvrir"

msgctxt "Button"
msgid "Open"
msgstr "Ouvrir"

msgctxt "Menu"
msgid "%d file"
msgid_plural "%d files"
msgstr[0] "%d fichier"
msgstr[1] "%d fichiers"

msgctxt "Button"
msgid "%d file"
msgid_plural "%d files"
msgstr[0] "%d fichier"
msgstr[1] "%d fichiers"
''')
catalog = pofile.read_po(buf)
assert catalog.get('Open', context='Menu').id is catalog.get('Open', context='Button').id
menu_id = catalog.get('%d file', context='Menu').id
button_id = catalog.get('%d file', context='Button').id
assert menu_id == button_id == ('%d file', '%d files')
assert menu_id[0] is button_id[0]
assert menu_id[1] is button_id[1]


def test_single_plural_form():
buf = StringIO(r'''msgid "foo"
msgid_plural "foos"
Expand Down