Refactor logging statements to use f-strings for improved readability and consistency across the codebase. This change enhances the clarity of log messages by directly embedding variable values, making it easier to trace and debug application behavior.
This commit is contained in:
Richie committed
1 parent
5210f00587
commit
8f1a69529c
23 files changed
+142
-368
No files matched your search
@@ -80,12 +80,8 @@ async def judge_candidate_phrases_for_books(
|
||||
book_workers = max(1, config.phrase_judge_book_workers)
|
||||
phrase_workers = max(1, config.phrase_judge_phrase_workers)
|
||||
logger.info(
|
||||
"ebook_candidate_phrase_judgment_start books_seen=%s book_workers=%s phrase_workers=%s "
|
||||
"confidence_threshold=%.2f",
|
||||
books_seen,
|
||||
book_workers,
|
||||
phrase_workers,
|
||||
config.protected_phrase_confidence_threshold,
|
||||
f"ebook_candidate_phrase_judgment_start {books_seen=} {book_workers=} {phrase_workers=} "
|
||||
f"{config.protected_phrase_confidence_threshold=:.2f}"
|
||||
)
|
||||
|
||||
book_semaphore = asyncio.Semaphore(book_workers)
|
||||
@@ -105,14 +101,8 @@ async def judge_candidate_phrases_for_books(
|
||||
phrase_mentions=sum(outcome.mentions for outcome in outcomes),
|
||||
)
|
||||
logger.info(
|
||||
"ebook_candidate_phrase_judgment_complete books_seen=%s books_judged=%s books_failed=%s "
|
||||
"candidates_judged=%s protected=%s mentions=%s",
|
||||
result.books_seen,
|
||||
result.books_judged,
|
||||
result.books_failed,
|
||||
result.candidates_judged,
|
||||
result.protected_phrases,
|
||||
result.phrase_mentions,
|
||||
f"ebook_candidate_phrase_judgment_complete {result.books_seen=} {result.books_judged=} {result.books_failed=} "
|
||||
f"{result.candidates_judged=} {result.protected_phrases=} {result.phrase_mentions=}"
|
||||
)
|
||||
return result
|
||||
|
||||
@@ -147,7 +137,7 @@ async def judge_one_book_async(
|
||||
return BookJudgmentResult()
|
||||
return await persist_book_judgments(engine, source_id, config, judged)
|
||||
except Exception:
|
||||
logger.exception("ebook_candidate_phrase_judgment_book_failed source_id=%s", source_id)
|
||||
logger.exception(f"ebook_candidate_phrase_judgment_book_failed {source_id=}")
|
||||
return BookJudgmentResult(failed=True)
|
||||
|
||||
|
||||
@@ -173,7 +163,7 @@ async def prepare_book_judgment(
|
||||
return None
|
||||
async with AsyncSession(engine) as session:
|
||||
if not await count_unjudged_candidates(session, source_id, config):
|
||||
logger.info("ebook_candidate_phrase_judgment_book_skip_no_unjudged source_id=%s", source_id)
|
||||
logger.info(f"ebook_candidate_phrase_judgment_book_skip_no_unjudged {source_id=}")
|
||||
return None
|
||||
existing_protected = await count_protected_phrases(session, source_id)
|
||||
target_remaining: int | None = None
|
||||
@@ -181,15 +171,13 @@ async def prepare_book_judgment(
|
||||
target_remaining = max(config.phrase_target_protected_per_book - existing_protected, 0)
|
||||
if target_remaining == 0:
|
||||
logger.info(
|
||||
"ebook_candidate_phrase_judgment_skipped_target_met source_id=%s existing_protected=%s target=%s",
|
||||
source_id,
|
||||
existing_protected,
|
||||
config.phrase_target_protected_per_book,
|
||||
f"ebook_candidate_phrase_judgment_skipped_target_met {source_id=} {existing_protected=} "
|
||||
f"{config.phrase_target_protected_per_book=}"
|
||||
)
|
||||
return None
|
||||
book_text = await load_book_text(session, source_id)
|
||||
if not book_text:
|
||||
logger.warning("ebook_candidate_phrase_judgment_book_empty source_id=%s", source_id)
|
||||
logger.warning(f"ebook_candidate_phrase_judgment_book_empty {source_id=}")
|
||||
return None
|
||||
normalized_book_text = normalize_text(book_text)
|
||||
# Stored rows may predate the current junk filters and score weights, so re-filter and
|
||||
@@ -211,15 +199,8 @@ async def prepare_book_judgment(
|
||||
normalized_book_text, candidate.phrase_norm
|
||||
)
|
||||
logger.info(
|
||||
"ebook_candidate_phrase_judgment_candidates_loaded source_id=%s candidates=%s skipped_junk=%s "
|
||||
"unjudged_rows=%s existing_protected=%s target_remaining=%s judgment_limit=%s",
|
||||
source_id,
|
||||
len(work_items),
|
||||
skipped_junk,
|
||||
len(rows),
|
||||
existing_protected,
|
||||
target_remaining,
|
||||
judgment_limit,
|
||||
f"ebook_candidate_phrase_judgment_candidates_loaded {source_id=} candidates={len(work_items)} {skipped_junk=} "
|
||||
f"unjudged_rows={len(rows)} {existing_protected=} {target_remaining=} {judgment_limit=}"
|
||||
)
|
||||
return work_items, target_remaining
|
||||
|
||||
@@ -313,31 +294,20 @@ async def persist_book_judgments(
|
||||
await upsert_protected_phrase(session, source_id, None, candidate, judgment, candidate_row)
|
||||
)
|
||||
logger.info(
|
||||
"ebook_candidate_phrase_judgment_candidate_complete source_id=%s candidate_id=%s phrase=%r "
|
||||
"keep=%s confidence=%.3f category=%r promoted=%s",
|
||||
source_id,
|
||||
candidate_id,
|
||||
candidate.phrase_norm,
|
||||
judgment.keep,
|
||||
judgment.confidence,
|
||||
judgment.category,
|
||||
promote,
|
||||
f"ebook_candidate_phrase_judgment_candidate_complete {source_id=} {candidate_id=} "
|
||||
f"{candidate.phrase_norm=} {judgment.keep=} {judgment.confidence=:.3f} {judgment.category=} "
|
||||
f"{promote=}"
|
||||
)
|
||||
await session.flush()
|
||||
mentions = await index_chunk_phrase_mentions_for_book(session, source_id, config) if protected else 0
|
||||
await session.commit()
|
||||
except Exception:
|
||||
await session.rollback()
|
||||
logger.exception("ebook_candidate_phrase_judgment_book_persist_failed source_id=%s", source_id)
|
||||
logger.exception(f"ebook_candidate_phrase_judgment_book_persist_failed {source_id=}")
|
||||
return BookJudgmentResult(failed=True)
|
||||
logger.info(
|
||||
"ebook_candidate_phrase_judgment_book_committed source_id=%s judged=%s protected=%s mentions=%s "
|
||||
"duration_ms=%.1f",
|
||||
source_id,
|
||||
len(judged),
|
||||
len(protected),
|
||||
mentions,
|
||||
(perf_counter() - book_started_at) * 1000,
|
||||
f"ebook_candidate_phrase_judgment_book_committed {source_id=} judged={len(judged)} protected={len(protected)} "
|
||||
f"{mentions=} duration_ms={(perf_counter() - book_started_at) * 1000:.1f}"
|
||||
)
|
||||
return BookJudgmentResult(judged=len(judged), protected=len(protected), mentions=mentions, committed=True)
|
||||
|
||||
@@ -369,24 +339,14 @@ def should_protect_judged_candidate(
|
||||
accepted_token_count = len(accepted_tokens)
|
||||
if accepted_token_count < config.phrase_min_tokens:
|
||||
logger.info(
|
||||
"ebook_candidate_phrase_judgment_candidate_skip_short_canonical book_id=%s candidate_id=%s "
|
||||
"phrase=%r canonical=%r token_count=%s min_tokens=%s",
|
||||
book_id,
|
||||
candidate_id,
|
||||
candidate.phrase_norm,
|
||||
accepted_norm,
|
||||
accepted_token_count,
|
||||
config.phrase_min_tokens,
|
||||
f"ebook_candidate_phrase_judgment_candidate_skip_short_canonical {book_id=} {candidate_id=} "
|
||||
f"{candidate.phrase_norm=} {accepted_norm=} {accepted_token_count=} {config.phrase_min_tokens=}"
|
||||
)
|
||||
return False
|
||||
if is_most_common_word_phrase(accepted_tokens):
|
||||
logger.info(
|
||||
"ebook_candidate_phrase_judgment_candidate_skip_common_canonical book_id=%s candidate_id=%s "
|
||||
"phrase=%r canonical=%r",
|
||||
book_id,
|
||||
candidate_id,
|
||||
candidate.phrase_norm,
|
||||
accepted_norm,
|
||||
f"ebook_candidate_phrase_judgment_candidate_skip_common_canonical {book_id=} {candidate_id=} "
|
||||
f"{candidate.phrase_norm=} {accepted_norm=}"
|
||||
)
|
||||
return False
|
||||
return True
|
||||
|
||||
Reference in new issue
Block a user