Richie/dotfiles
1
0
Fork 0
Code Issues 1 Pull Requests 2 Actions Packages Projects Releases Wiki Activity

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.

Browse Source
This commit is contained in:
Richie
2026-07-24 11:38:51 -04:00
parent 5210f00587
commit 8f1a69529c
23 changed files with 142 additions and 368 deletions
Download Patch File Download Diff File Expand all files Collapse all files
python/ebook_search/protected_phrases/extraction.py
+13 -32
View File
@@ -682,33 +682,26 @@ def extract_phrase_candidates_for_book(
"""
started_at = perf_counter()
logger.info(
"ebook_phrase_candidate_extract_start chapters=%s chars=%s min_tokens=%s max_tokens=%s max_candidates=%s",
len(chapters),
len(book_text),
config.phrase_min_tokens,
config.phrase_max_tokens,
config.protected_phrase_max_candidates_per_book,
f"ebook_phrase_candidate_extract_start chapters={len(chapters)} chars={len(book_text)} "
f"{config.phrase_min_tokens=} {config.phrase_max_tokens=} {config.protected_phrase_max_candidates_per_book=}"
)
raw_started_at = perf_counter()
raw = extract_raw_ngrams_by_chapter(chapters, config)
logger.info(
"ebook_phrase_candidate_extract_raw_complete candidates=%s duration_ms=%.1f",
len(raw),
(perf_counter() - raw_started_at) * 1000,
f"ebook_phrase_candidate_extract_raw_complete candidates={len(raw)} duration_ms={(perf_counter() - "
f"raw_started_at) * 1000:.1f}"
)
yake_started_at = perf_counter()
yake_candidates = extract_yake_candidates(book_text, config)
logger.info(
"ebook_phrase_candidate_extract_yake_complete candidates=%s duration_ms=%.1f",
len(yake_candidates),
(perf_counter() - yake_started_at) * 1000,
f"ebook_phrase_candidate_extract_yake_complete candidates={len(yake_candidates)} duration_ms={(perf_counter() - "
f"yake_started_at) * 1000:.1f}"
)
capitalized_started_at = perf_counter()
capitalized = extract_capitalized_phrases(book_text, config)
logger.info(
"ebook_phrase_candidate_extract_capitalized_complete candidates=%s duration_ms=%.1f",
len(capitalized),
(perf_counter() - capitalized_started_at) * 1000,
f"ebook_phrase_candidate_extract_capitalized_complete candidates={len(capitalized)} "
f"duration_ms={(perf_counter() - capitalized_started_at) * 1000:.1f}"
)
metadata_candidates = extract_metadata_candidates(metadata, config)
@@ -732,22 +725,10 @@ def extract_phrase_candidates_for_book(
: config.protected_phrase_max_candidates_per_book
]
logger.info(
"ebook_phrase_candidate_extract_complete raw=%s yake=%s capitalized=%s metadata=%s "
"merged=%s filtered_too_short=%s filtered_too_rare=%s filtered_too_common=%s filtered_junk=%s "
"min_uses=%s storable=%s limited=%s enrich_score_ms=%.1f duration_ms=%.1f",
len(raw),
len(yake_candidates),
len(capitalized),
len(metadata_candidates),
pre_filter_count,
filtered_too_short,
filtered_too_rare,
filtered_too_common,
filtered_junk,
minimum_candidate_raw_count(config),
len(candidates),
len(limited),
(perf_counter() - enriched_started_at) * 1000,
(perf_counter() - started_at) * 1000,
f"ebook_phrase_candidate_extract_complete raw={len(raw)} yake={len(yake_candidates)} "
f"capitalized={len(capitalized)} metadata={len(metadata_candidates)} {pre_filter_count=} {filtered_too_short=} "
f"{filtered_too_rare=} {filtered_too_common=} {filtered_junk=} min_uses={minimum_candidate_raw_count(config)} "
f"storable={len(candidates)} limited={len(limited)} enrich_score_ms={(perf_counter() - enriched_started_at) * "
f"1000:.1f} duration_ms={(perf_counter() - started_at) * 1000:.1f}"
)
return limited