Skip to content

fix(harvester): parse numeric INSPIRE id from combined log prefixes #867

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
TahaKhan998 wants to merge 1 commit into
base: master
Choose a base branch
from
Open

fix(harvester): parse numeric INSPIRE id from combined log prefixes #867

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
13 changes: 12 additions & 1 deletion site/cds_rdm/inspire_harvester/reports/runs/logs.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -32,7 +32,13 @@
HARVESTER_RUN_LOGS_MAX_PAGES = 50

_GROUPABLE_LEVELS = frozenset({"ERROR", "WARNING"})
_RECORD_ID_PATTERN = re.compile(r"\[(?:INSPIRE#|inspire_id=)(?P<id>[^\]]+)\]")
# Numeric INSPIRE id only — logger prefixes may also include CDS#… in the same
# brackets, e.g. [INSPIRE#1642662 CDS#c42kw-9f710].
_RECORD_ID_PATTERN = re.compile(r"(?:INSPIRE#|inspire_id=)(?P<id>\d+)")
# Full bracketed logger prefix used when normalizing grouping reasons.
_RECORD_PREFIX_PATTERN = re.compile(
r"\[(?:INSPIRE#\d+|inspire_id=\d+)[^\]]*\]\s*"
)
_SKIP_SUMMARY_SUFFIX = " transformed entries with errors."
_WRITER_PREFIXES = (
"Error while processing entry:",
Expand Down Expand Up @@ -140,6 +146,9 @@ def _extract_record_id(message):
Input: "[INSPIRE#12345] Multiple records match."
Output: "12345"

Input: "[INSPIRE#1642662 CDS#c42kw-9f710] File checksum mismatch."
Output: "1642662"

Input: "Multiple records match."
Output: None
"""
Expand Down Expand Up @@ -228,6 +237,8 @@ def _unwrap_message(message):
reason = compact_text(reason.split(marker, 1)[1])

reason = _peel_string_list(reason)
# Drop the full [INSPIRE#… optional CDS#…] prefix, then any bare id markers.
reason = _RECORD_PREFIX_PATTERN.sub("", reason).strip()
reason = _RECORD_ID_PATTERN.sub("", reason).strip()

for prefix in _WRITER_PREFIXES:
Expand Down
Loading