diff --git a/PKG-INFO b/PKG-INFO
index 378ac0f494dd962a7ca980c19da26eef0fb410e3..4cf3c64526c4b95bba733cb749fdcd3c76505946 100644
--- a/PKG-INFO
+++ b/PKG-INFO
@@ -1,6 +1,6 @@
Metadata-Version: 2.1
Name: swh.loader.cvs
-Version: 0.2.2
+Version: 0.3.0
Summary: Software Heritage CVS Loader
Home-page: https://forge.softwareheritage.org/diffusion/swh-loader-cvs
Author: Software Heritage developers
diff --git a/pytest.ini b/pytest.ini
index 3c9dea19461053b28da88b45f9472c5742e7b242..378d23aa5b1dd36f18d162e09174710497644115 100644
--- a/pytest.ini
+++ b/pytest.ini
@@ -3,3 +3,5 @@
norecursedirs = build docs .*
markers =
fs: execute tests that write to the filesystem
+
+asyncio_mode = strict
diff --git a/requirements.txt b/requirements.txt
index 1b5e575c97bfeb099014d9d321db162b9837cdbe..481a2139bd1ac86efea513d48b234413080461a1 100644
--- a/requirements.txt
+++ b/requirements.txt
@@ -2,4 +2,6 @@
# should match https://pypi.python.org/pypi names. For the full spec or
# dependency lines, see https://pip.readthedocs.org/en/1.1/requirements.html
+sentry-sdk
tenacity
+
diff --git a/swh.loader.cvs.egg-info/PKG-INFO b/swh.loader.cvs.egg-info/PKG-INFO
index 378ac0f494dd962a7ca980c19da26eef0fb410e3..4cf3c64526c4b95bba733cb749fdcd3c76505946 100644
--- a/swh.loader.cvs.egg-info/PKG-INFO
+++ b/swh.loader.cvs.egg-info/PKG-INFO
@@ -1,6 +1,6 @@
Metadata-Version: 2.1
Name: swh.loader.cvs
-Version: 0.2.2
+Version: 0.3.0
Summary: Software Heritage CVS Loader
Home-page: https://forge.softwareheritage.org/diffusion/swh-loader-cvs
Author: Software Heritage developers
diff --git a/swh.loader.cvs.egg-info/requires.txt b/swh.loader.cvs.egg-info/requires.txt
index cb67ee8332dbd6065446e7dcd9dbb41e569f217b..e131fa96b20f2fe836e31cd1edc63805ceb62658 100644
--- a/swh.loader.cvs.egg-info/requires.txt
+++ b/swh.loader.cvs.egg-info/requires.txt
@@ -1,3 +1,4 @@
+sentry-sdk
tenacity
swh.core[http]>=0.3
swh.storage>=0.11.3
diff --git a/swh/loader/cvs/loader.py b/swh/loader/cvs/loader.py
index fea1504f944e5306f55a62f68f3504b2d2a8c275..a06ff0abd1bcbf8652ff390c21303937768d479b 100644
--- a/swh/loader/cvs/loader.py
+++ b/swh/loader/cvs/loader.py
@@ -1,4 +1,4 @@
-# Copyright (C) 2015-2021 The Software Heritage developers
+# Copyright (C) 2015-2022 The Software Heritage developers
# See the AUTHORS file at the top-level directory of this distribution
# License: GNU Affero General Public License version 3, or any later version
# See top-level LICENSE file for more information
@@ -15,6 +15,7 @@ import tempfile
import time
from typing import Any, BinaryIO, Dict, Iterator, List, Optional, Sequence, Tuple, cast
+import sentry_sdk
from tenacity import retry
from tenacity.retry import retry_if_exception_type
from tenacity.stop import stop_after_attempt
@@ -141,7 +142,7 @@ class CvsLoader(BaseLoader):
else:
parents = ()
revision = self.build_swh_revision(k, logmsg, swh_dir.hash, parents)
- self.log.info("SWH revision ID: %s", hashutil.hash_to_hex(revision.id))
+ self.log.debug("SWH revision ID: %s", hashutil.hash_to_hex(revision.id))
self._last_revision = revision
return (revision, swh_dir)
@@ -168,7 +169,7 @@ class CvsLoader(BaseLoader):
wtpath = os.path.join(self.tempdir_path, path)
if not self.file_path_is_safe(wtpath):
raise BadPathException(f"unsafe path found in RCS file: {f.path}")
- self.log.info("rev %s state %s file %s", f.rev, f.state, f.path)
+ self.log.debug("rev %s state %s file %s", f.rev, f.state, f.path)
if f.state == "dead":
# remove this file from work tree
try:
@@ -217,7 +218,7 @@ class CvsLoader(BaseLoader):
wtpath = os.path.join(self.tempdir_path, path)
if not self.file_path_is_safe(wtpath):
raise BadPathException(f"unsafe path found in cvs rlog output: {f.path}")
- self.log.info("rev %s state %s file %s", f.rev, f.state, f.path)
+ self.log.debug("rev %s state %s file %s", f.rev, f.state, f.path)
if f.state == "dead":
# remove this file from work tree
try:
@@ -254,7 +255,7 @@ class CvsLoader(BaseLoader):
"""
for k in cvs_changesets:
tstr = time.strftime("%c", time.gmtime(k.max_time))
- self.log.info(
+ self.log.debug(
"changeset from %s by %s on branch %s", tstr, k.author, k.branch
)
logmsg: Optional[bytes] = b""
@@ -295,7 +296,7 @@ class CvsLoader(BaseLoader):
)
def cleanup(self) -> None:
- self.log.info("cleanup")
+ self.log.debug("cleanup")
def configure_custom_id_keyword(self, cvsconfig):
"""Parse CVSROOT/config and look for a custom keyword definition.
@@ -467,10 +468,10 @@ class CvsLoader(BaseLoader):
# will need to be modified such that it spools the list of changesets
# to disk instead.
cvs = CvsConv(self.cvsroot_path, RcsKeywords(), False, CHANGESET_FUZZ_SEC)
- self.log.info("Walking CVS module %s", self.cvs_module_name)
+ self.log.debug("Walking CVS module %s", self.cvs_module_name)
cvs.walk(self.cvs_module_name)
cvs_changesets = sorted(cvs.changesets)
- self.log.info(
+ self.log.debug(
"CVS changesets found in %s: %d",
self.cvs_module_name,
len(cvs_changesets),
@@ -484,7 +485,7 @@ class CvsLoader(BaseLoader):
self.cvsroot_path = os.path.dirname(url.path)
self.cvsclient = CVSClient(url)
cvsroot_path = os.path.dirname(url.path)
- self.log.info(
+ self.log.debug(
"Fetching CVS rlog from %s:%s/%s",
url.host,
cvsroot_path,
@@ -537,7 +538,7 @@ class CvsLoader(BaseLoader):
self.rlog.parse_rlog(cast(BinaryIO, fp))
self.rlog_file = cast(BinaryIO, fp)
cvs_changesets = sorted(self.rlog.changesets)
- self.log.info(
+ self.log.debug(
"CVS changesets found for %s: %d",
self.cvs_module_name,
len(cvs_changesets),
@@ -555,12 +556,15 @@ class CvsLoader(BaseLoader):
except StopIteration:
assert self._last_revision is not None
self.snapshot = self.generate_and_load_snapshot(self._last_revision)
- self.log.info("SWH snapshot ID: %s", hashutil.hash_to_hex(self.snapshot.id))
+ self.log.debug(
+ "SWH snapshot ID: %s", hashutil.hash_to_hex(self.snapshot.id)
+ )
self.flush()
self.loaded_snapshot_id = self.snapshot.id
return False
except Exception:
self.log.exception("Exception in fetch_data:")
+ sentry_sdk.capture_exception()
self._visit_status = "failed"
return False # Stopping iteration
self._contents, self._skipped_contents, self._directories, rev = data