Skip to content

Fixes issue #22: Now using Python native bz2 decompression #23

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
wants to merge 1 commit into
base: main
Choose a base branch
from
Open

Fixes issue #22: Now using Python native bz2 decompression #23

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
21 changes: 3 additions & 18 deletions wiktionary_de_parser/dump_processor/__init__.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,3 +1,4 @@
import bz2
import shutil
import subprocess
from pathlib import Path
Expand Down Expand Up @@ -61,22 +62,6 @@ def download_dump(self):
size = f.write(chunk)
bar.update(size)

@staticmethod
def decompress_dump_file(dump_path: Path) -> subprocess.Popen:
if str(dump_path).endswith(".bz2"):
decompress_command = (
"lbzcat" if shutil.which("lbzcat") is not None else "bzcat"
)
p = subprocess.Popen(
[decompress_command, str(dump_path)], stdout=subprocess.PIPE
)
if p.stdout is not None:
return p
else:
raise Exception(f"No stdout from command {decompress_command}")
else:
raise ValueError("Dump file extension is not .bz2")

@staticmethod
def process_page_data(
page_element, namespaces: dict[None, str], namespace_ids: set[int]
Expand Down Expand Up @@ -132,12 +117,12 @@ def pages(self):
0
} # see https://de.wiktionary.org/wiki/Hilfe:Namensr%C3%A4ume

with self.decompress_dump_file(self.dump_file_path) as p:
with bz2.open(self.dump_file_path) as p:
namespace_str = "http://www.mediawiki.org/xml/export-0.11/"
namespaces = {None: namespace_str}

for _, page_element in etree.iterparse(
p.stdout, tag=f"{{{namespace_str}}}page"
p, tag=f"{{{namespace_str}}}page"
):
page = self.process_page_data(
page_element, namespaces, namespace_ids
Expand Down