admin/mcp-nextcloud
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

refactor: convert f-string logging to lazy %-style format (G004)

Browse Source 
Sweep all 1676 G004 violations across 112 files, converting
`logger.<level>(f"…{x}…")` to `logger.<level>("…%s…", x)`.

Why: ruff rule G004 was added to pyproject.toml to enforce lazy
%-style logging — defers formatting until the log level is enabled
and lets structured log tooling match the unformatted template.

Conversion preserves rendered output byte-for-byte:
- `{x}` → `%s` + `x`
- `{x!r}` / `{x!s}` / `{x!a}` → `%r` / `%s` / `%a`
- Format specs (`{x:.2f}`, `{x:>10}`) → `%s` + `format(x, 'spec')`
  (printf-style specs aren't 1:1 with Python format specs, so we
  delegate to `format()` to keep identical output)
- Literal `%` → `%%`
- Concatenated f-strings (`f"a {x} " "b"`) flattened
- Trailing kwargs (`exc_info=True`) preserved

Verified:
- `uv run ruff check --select G004` → 0 violations
- `uv run ty check -- nextcloud_mcp_server` → passes
- `uv run pytest tests/unit/` → 1010 passed

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
This commit is contained in:
Chris Coutinho
2026-05-13 01:12:17 +02:00
co-authored by Claude Opus 4.7
parent a4e6125d28
commit 665cb9b1eb
112 changed files with 2534 additions and 1859 deletions
Download Patch File Download Diff File Expand all files Collapse all files
nextcloud_mcp_server/search/algorithms.py
+2 -2
View File
@@ -120,11 +120,11 @@ async def get_indexed_doc_types(user_id: str) -> set[str]:
if point.payload and point.payload.get("doc_type")
}
logger.debug(f"Found indexed document types for user {user_id}: {doc_types}")
logger.debug("Found indexed document types for user %s: %s", user_id, doc_types)
return doc_types
except Exception as e:
logger.warning(f"Failed to query Qdrant for doc_types: {e}")
logger.warning("Failed to query Qdrant for doc_types: %s", e)
return set()
nextcloud_mcp_server/search/bm25_hybrid.py
+16 -11
View File
@@ -100,9 +100,13 @@ class BM25HybridSearchAlgorithm(SearchAlgorithm):
score_threshold = kwargs.get("score_threshold", self.score_threshold)
logger.info(
f"BM25 hybrid search: query='{query}', user={user_id}, "
f"limit={limit}, score_threshold={score_threshold}, doc_type={doc_type}, "
f"fusion={self.fusion_name}"
"BM25 hybrid search: query='%s', user=%s, limit=%s, score_threshold=%s, doc_type=%s, fusion=%s",
query,
user_id,
limit,
score_threshold,
doc_type,
self.fusion_name,
)
# Generate dense embedding for semantic search
@@ -112,7 +116,7 @@ class BM25HybridSearchAlgorithm(SearchAlgorithm):
dense_embedding = await embedding_service.embed(query)
# Store for reuse by callers (e.g., viz_routes PCA visualization)
self.query_embedding = dense_embedding
logger.debug(f"Generated dense embedding (dimension={len(dense_embedding)})")
logger.debug("Generated dense embedding (dimension=%s)", len(dense_embedding))
# Generate sparse embedding for BM25 keyword search
with trace_operation("search.get_bm25_service"):
@@ -120,8 +124,8 @@ class BM25HybridSearchAlgorithm(SearchAlgorithm):
with trace_operation("search.sparse_embedding_bm25"):
sparse_embedding = await bm25_service.encode_async(query)
logger.debug(
f"Generated sparse embedding "
f"({len(sparse_embedding['indices'])} non-zero terms)"
"Generated sparse embedding (%s non-zero terms)",
len(sparse_embedding["indices"]),
)
# Build Qdrant filter
@@ -189,15 +193,16 @@ class BM25HybridSearchAlgorithm(SearchAlgorithm):
raise
logger.info(
f"Qdrant {self.fusion_name.upper()} fusion returned {len(search_response.points)} results "
f"(before deduplication)"
"Qdrant %s fusion returned %s results (before deduplication)",
self.fusion_name.upper(),
len(search_response.points),
)
if search_response.points:
# Log top 3 fusion scores to help with threshold tuning
top_scores = [p.score for p in search_response.points[:3]]
logger.debug(
f"Top 3 {self.fusion_name.upper()} fusion scores: {top_scores}"
"Top 3 %s fusion scores: %s", self.fusion_name.upper(), top_scores
)
# Deduplicate by (doc_id, doc_type, chunk_start, chunk_end)
@@ -233,12 +238,12 @@ class BM25HybridSearchAlgorithm(SearchAlgorithm):
if len(results) >= limit:
break
logger.info(f"Returning {len(results)} unverified results after deduplication")
logger.info("Returning %s unverified results after deduplication", len(results))
if results:
result_details = [
f"{r.doc_type}_{r.id} (score={r.score:.3f}, title='{r.title}')"
for r in results[:5] # Show top 5
]
logger.debug(f"Top results: {', '.join(result_details)}")
logger.debug("Top results: %s", ", ".join(result_details))
return results
nextcloud_mcp_server/search/context.py
+64 -32
View File
@@ -67,20 +67,26 @@ async def _get_chunk_from_qdrant(
excerpt = point.payload.get("excerpt")
if excerpt:
logger.debug(
f"Retrieved chunk from Qdrant for {doc_type} {doc_id}: "
f"{len(excerpt)} chars"
"Retrieved chunk from Qdrant for %s %s: %s chars",
doc_type,
doc_id,
len(excerpt),
)
return str(excerpt)
logger.debug(
f"Chunk not found in Qdrant for {doc_type} {doc_id}, "
f"chunk [{chunk_start}:{chunk_end}]. Will fall back to document fetch."
"Chunk not found in Qdrant for %s %s, chunk [%s:%s]. Will fall back to document fetch.",
doc_type,
doc_id,
chunk_start,
chunk_end,
)
return None
except Exception as e:
logger.error(
f"Error querying Qdrant for chunk: {e}. Falling back to document fetch.",
"Error querying Qdrant for chunk: %s. Falling back to document fetch.",
e,
exc_info=True,
)
return None
@@ -129,8 +135,11 @@ async def _get_chunk_by_index_from_qdrant(
excerpt = point.payload.get("excerpt")
if excerpt:
logger.debug(
f"Retrieved adjacent chunk {chunk_index} from Qdrant for "
f"{doc_type} {doc_id}: {len(excerpt)} chars"
"Retrieved adjacent chunk %s from Qdrant for %s %s: %s chars",
chunk_index,
doc_type,
doc_id,
len(excerpt),
)
return str(excerpt)
@@ -138,8 +147,11 @@ async def _get_chunk_by_index_from_qdrant(
except Exception as e:
logger.debug(
f"Could not retrieve adjacent chunk {chunk_index} for "
f"{doc_type} {doc_id}: {e}"
"Could not retrieve adjacent chunk %s for %s %s: %s",
chunk_index,
doc_type,
doc_id,
e,
)
return None
@@ -181,19 +193,21 @@ async def _get_deck_metadata_from_qdrant(
stack_id = point.payload.get("stack_id")
if board_id is not None and stack_id is not None:
logger.debug(
f"Retrieved deck metadata for card {card_id}: "
f"board_id={board_id}, stack_id={stack_id}"
"Retrieved deck metadata for card %s: board_id=%s, stack_id=%s",
card_id,
board_id,
stack_id,
)
return {"board_id": int(board_id), "stack_id": int(stack_id)}
logger.debug(
f"Could not find deck metadata in Qdrant for card {card_id} "
f"(might be legacy data without board_id/stack_id)"
"Could not find deck metadata in Qdrant for card %s (might be legacy data without board_id/stack_id)",
card_id,
)
return None
except Exception as e:
logger.debug(f"Error querying Qdrant for deck metadata: {e}")
logger.debug("Error querying Qdrant for deck metadata: %s", e)
return None
@@ -389,8 +403,9 @@ async def get_chunk_with_context(
if chunk_text:
logger.info(
f"Retrieved chunk from Qdrant cache for {doc_type} {doc_id} "
f"(avoids document re-fetch/re-parse)"
"Retrieved chunk from Qdrant cache for %s %s (avoids document re-fetch/re-parse)",
doc_type,
doc_id,
)
# Fetch adjacent chunks for context expansion
@@ -495,24 +510,30 @@ async def get_chunk_with_context(
return None
logger.info(
f"Falling back to document fetch for {doc_type} {doc_id} "
f"(Qdrant cache miss, possibly legacy data)"
"Falling back to document fetch for %s %s (Qdrant cache miss, possibly legacy data)",
doc_type,
doc_id,
)
# Fetch full document text (notes, deck cards, news items, etc.)
full_text = await _fetch_document_text(nc_client, doc_id, doc_type, user_id)
if full_text is None:
logger.warning(
f"Could not fetch document text for {doc_type} {doc_id}, "
"skipping context expansion"
"Could not fetch document text for %s %s, skipping context expansion",
doc_type,
doc_id,
)
return None
# Validate offsets
if chunk_start < 0 or chunk_end > len(full_text) or chunk_start >= chunk_end:
logger.warning(
f"Invalid chunk offsets for {doc_type} {doc_id}: "
f"start={chunk_start}, end={chunk_end}, doc_len={len(full_text)}"
"Invalid chunk offsets for %s %s: start=%s, end=%s, doc_len=%s",
doc_type,
doc_id,
chunk_start,
chunk_end,
len(full_text),
)
return None
@@ -650,13 +671,18 @@ async def _fetch_document_text(
board_id=board_id, stack_id=stack_id, card_id=int(doc_id)
)
logger.debug(
f"Retrieved deck card {doc_id} using metadata "
f"(board_id={board_id}, stack_id={stack_id})"
"Retrieved deck card %s using metadata (board_id=%s, stack_id=%s)",
doc_id,
board_id,
stack_id,
)
except Exception as e:
logger.warning(
f"Failed to fetch card with metadata (board_id={board_id}, "
f"stack_id={stack_id}, card_id={doc_id}): {e}, falling back to iteration"
"Failed to fetch card with metadata (board_id=%s, stack_id=%s, card_id=%s): %s, falling back to iteration",
board_id,
stack_id,
doc_id,
e,
)
# Fallback: Iterate through all boards/stacks (for legacy data or if fast path failed)
@@ -671,7 +697,9 @@ async def _fetch_document_text(
# Skip deleted boards (soft delete: deletedAt > 0)
if board.deletedAt > 0:
logger.debug(
f"Skipping deleted board {board.id} while searching for card {doc_id}"
"Skipping deleted board %s while searching for card %s",
board.id,
doc_id,
)
continue
@@ -686,13 +714,15 @@ async def _fetch_document_text(
card = c
card_found = True
logger.debug(
f"Found deck card {doc_id} in board {board.id}, "
f"stack {stack.id} (fallback iteration)"
"Found deck card %s in board %s, stack %s (fallback iteration)",
doc_id,
board.id,
stack.id,
)
break
if not card_found:
logger.warning(f"Deck card {doc_id} not found in any board/stack")
logger.warning("Deck card %s not found in any board/stack", doc_id)
return None
# Type narrowing: card is set if we reach here
@@ -705,10 +735,12 @@ async def _fetch_document_text(
content_parts.append(card.description)
return "\n\n".join(content_parts)
else:
logger.warning(f"Unsupported doc_type for context expansion: {doc_type}")
logger.warning("Unsupported doc_type for context expansion: %s", doc_type)
return None
except Exception as e:
logger.error(f"Error fetching document {doc_type} {doc_id}: {e}", exc_info=True)
logger.error(
"Error fetching document %s %s: %s", doc_type, doc_id, e, exc_info=True
)
return None
nextcloud_mcp_server/search/pdf_highlighter.py
+64 -37
View File
@@ -118,7 +118,7 @@ class PDFHighlighter:
try:
shutil.rmtree(temp_dir)
except Exception as e:
logger.warning(f"Failed to clean up temp directory {temp_dir}: {e}")
logger.warning("Failed to clean up temp directory %s: %s", temp_dir, e)
return full_text, page_boundaries
@@ -202,7 +202,7 @@ class PDFHighlighter:
try:
page_words = page.get_text("words")
except Exception as e:
logger.error(f"Failed to extract words from page: {e}")
logger.error("Failed to extract words from page: %s", e)
return 0
if not page_words:
@@ -225,8 +225,12 @@ class PDFHighlighter:
)
]
logger.debug(
f"Filtered to {len(page_words)} words in region "
f"({rx0:.0f}, {ry0:.0f}, {rx1:.0f}, {ry1:.0f})"
"Filtered to %s words in region (%s, %s, %s, %s)",
len(page_words),
format(rx0, ".0f"),
format(ry0, ".0f"),
format(rx1, ".0f"),
format(ry1, ".0f"),
)
if not page_words:
@@ -286,17 +290,19 @@ class PDFHighlighter:
if len(current_matches) >= len(chunk_words) * 0.5:
matches = current_matches
logger.debug(
f"Found match at position {start_pos}: "
f"{len(matches)}/{len(chunk_words)} words"
"Found match at position %s: %s/%s words",
start_pos,
len(matches),
len(chunk_words),
)
break # Take FIRST match, not best/longest
if not matches:
logger.debug(f"No word matches found (chunk has {len(chunk_words)} words)")
logger.debug("No word matches found (chunk has %s words)", len(chunk_words))
return 0
logger.debug(
f"Matched {len(matches)} words out of {len(chunk_words)} chunk words"
"Matched %s words out of %s chunk words", len(matches), len(chunk_words)
)
# Build rectangles from matched words
@@ -324,8 +330,9 @@ class PDFHighlighter:
# A chunk should be mostly contiguous text
if large_gaps > len(matches) * 0.3: # More than 30% have gaps
logger.debug(
f"Rejecting scattered matches: {large_gaps} large gaps "
f"out of {len(matches)} matches"
"Rejecting scattered matches: %s large gaps out of %s matches",
large_gaps,
len(matches),
)
return 0
@@ -512,12 +519,12 @@ class PDFHighlighter:
rects = page.search_for(phrase.strip())
if rects:
anchor_rect = rects[0] # Use first match
logger.debug(f"Found chunk anchor using phrase: '{phrase[:30]}...'")
logger.debug("Found chunk anchor using phrase: '%s...'", phrase[:30])
break
if not anchor_rect:
page_num = page.number + 1 if page.number is not None else "unknown"
logger.warning(f"Could not find chunk text on page {page_num}")
logger.warning("Could not find chunk text on page %s", page_num)
return 0
# Calculate chunk height based on character count
@@ -558,8 +565,10 @@ class PDFHighlighter:
fill_shape.commit()
logger.debug(
f"Added bounding box at y={chunk_rect.y0:.0f}-{chunk_rect.y1:.0f} "
f"(estimated {estimated_lines:.1f} lines)"
"Added bounding box at y=%s-%s (estimated %s lines)",
format(chunk_rect.y0, ".0f"),
format(chunk_rect.y1, ".0f"),
format(estimated_lines, ".1f"),
)
return 1
@@ -626,7 +635,9 @@ class PDFHighlighter:
# Log if page differs from stored metadata
if stored_page_number and stored_page_number != page_num:
logger.info(
f"Chunk primarily on page {page_num}, metadata says {stored_page_number}"
"Chunk primarily on page %s, metadata says %s",
page_num,
stored_page_number,
)
# Extract page text
@@ -644,8 +655,12 @@ class PDFHighlighter:
page_text_length = page_end - page_start
logger.debug(
f"Extracted {len(chunk_text)} chars on page {page_num} "
f"(offsets {page_relative_start}-{page_relative_end} of {page_text_length})"
"Extracted %s chars on page %s (offsets %s-%s of %s)",
len(chunk_text),
page_num,
page_relative_start,
page_relative_end,
page_text_length,
)
# Get page and add highlights
@@ -672,13 +687,15 @@ class PDFHighlighter:
doc.close()
logger.info(
f"Generated {len(png_bytes):,} byte image with {highlight_count} highlights"
"Generated %s byte image with %s highlights",
format(len(png_bytes), ","),
highlight_count,
)
return (png_bytes, page_num, highlight_count)
except Exception as e:
logger.error(f"Error highlighting chunk: {e}", exc_info=True)
logger.error("Error highlighting chunk: %s", e, exc_info=True)
return None
finally:
@@ -688,7 +705,9 @@ class PDFHighlighter:
shutil.rmtree(temp_pdf_path.parent)
except Exception as e:
logger.warning(
f"Failed to delete temp directory {temp_pdf_path.parent}: {e}"
"Failed to delete temp directory %s: %s",
temp_pdf_path.parent,
e,
)
@staticmethod
@@ -791,11 +810,11 @@ class PDFHighlighter:
)
results[chunk_index] = ([normalized], page_num)
logger.info(f"Computed bboxes for {len(results)}/{len(chunks)} chunks")
logger.info("Computed bboxes for %s/%s chunks", len(results), len(chunks))
return results
except Exception as e:
logger.error(f"Error computing chunk bboxes: {e}", exc_info=True)
logger.error("Error computing chunk bboxes: %s", e, exc_info=True)
return results
finally:
@@ -805,7 +824,7 @@ class PDFHighlighter:
try:
shutil.rmtree(temp_pdf_path.parent)
except Exception as e:
logger.warning(f"Failed to clean up temp dir: {e}")
logger.warning("Failed to clean up temp dir: %s", e)
@staticmethod
def highlight_chunks_batch(
@@ -853,8 +872,9 @@ class PDFHighlighter:
doc = pymupdf.open(temp_pdf_path)
logger.debug(
f"Batch highlighting: {len(chunks)} chunks, "
f"{len(page_boundaries)} pages"
"Batch highlighting: %s chunks, %s pages",
len(chunks),
len(page_boundaries),
)
# Group chunks by their target page for efficient rendering
@@ -873,7 +893,7 @@ class PDFHighlighter:
)
if not chunk_page_info:
logger.warning(f"Chunk {chunk_index}: not found on any page")
logger.warning("Chunk %s: not found on any page", chunk_index)
continue
page_num = chunk_page_info["page_num"]
@@ -881,8 +901,10 @@ class PDFHighlighter:
# Log if page differs from stored metadata
if stored_page_num and stored_page_num != page_num:
logger.debug(
f"Chunk {chunk_index}: found on page {page_num}, "
f"metadata says {stored_page_num}"
"Chunk %s: found on page %s, metadata says %s",
chunk_index,
page_num,
stored_page_num,
)
# Extract page-relative portion of chunk text
@@ -905,7 +927,7 @@ class PDFHighlighter:
)
logger.debug(
f"Chunks distributed across {len(chunks_by_page)} unique pages"
"Chunks distributed across %s unique pages", len(chunks_by_page)
)
# OPTIMIZATION: Render each page ONCE, then draw highlights using PIL
@@ -929,7 +951,9 @@ class PDFHighlighter:
page_rect = page.rect
logger.debug(
f"Page {page_num}: rendered once, processing {len(page_chunks)} chunks"
"Page %s: rendered once, processing %s chunks",
page_num,
len(page_chunks),
)
for (
@@ -949,7 +973,7 @@ class PDFHighlighter:
)
if bbox is None:
logger.warning(f"Chunk {chunk_index}: could not find bbox")
logger.warning("Chunk %s: could not find bbox", chunk_index)
continue
# Copy base image for this chunk
@@ -985,24 +1009,27 @@ class PDFHighlighter:
results[chunk_index] = (png_bytes, page_num, 1)
logger.debug(
f"Chunk {chunk_index}: {len(png_bytes):,} bytes, "
f"page {page_num}, bbox {pil_bbox}"
"Chunk %s: %s bytes, page %s, bbox %s",
chunk_index,
format(len(png_bytes), ","),
page_num,
pil_bbox,
)
except Exception as e:
logger.error(f"Chunk {chunk_index}: error - {e}")
logger.error("Chunk %s: error - %s", chunk_index, e)
continue
doc.close()
logger.info(
f"Batch highlighted {len(results)}/{len(chunks)} chunks successfully"
"Batch highlighted %s/%s chunks successfully", len(results), len(chunks)
)
return results
except Exception as e:
logger.error(f"Error in batch highlighting: {e}", exc_info=True)
logger.error("Error in batch highlighting: %s", e, exc_info=True)
return results
finally:
@@ -1011,4 +1038,4 @@ class PDFHighlighter:
try:
shutil.rmtree(temp_pdf_path.parent)
except Exception as e:
logger.warning(f"Failed to clean up temp dir: {e}")
logger.warning("Failed to clean up temp dir: %s", e)
nextcloud_mcp_server/search/semantic.py
+12 -8
View File
@@ -77,8 +77,12 @@ class SemanticSearchAlgorithm(SearchAlgorithm):
score_threshold = kwargs.get("score_threshold", self.score_threshold)
logger.info(
f"Semantic search: query='{query}', user={user_id}, "
f"limit={limit}, score_threshold={score_threshold}, doc_type={doc_type}"
"Semantic search: query='%s', user=%s, limit=%s, score_threshold=%s, doc_type=%s",
query,
user_id,
limit,
score_threshold,
doc_type,
)
# Generate embedding for query
@@ -87,7 +91,7 @@ class SemanticSearchAlgorithm(SearchAlgorithm):
# Store for reuse by callers (e.g., viz_routes PCA visualization)
self.query_embedding = query_embedding
logger.debug(
f"Generated embedding for query (dimension={len(query_embedding)})"
"Generated embedding for query (dimension=%s)", len(query_embedding)
)
# Build Qdrant filter
@@ -127,14 +131,14 @@ class SemanticSearchAlgorithm(SearchAlgorithm):
raise
logger.info(
f"Qdrant returned {len(search_response.points)} results "
f"(before deduplication)"
"Qdrant returned %s results (before deduplication)",
len(search_response.points),
)
if search_response.points:
# Log top 3 scores to help with threshold tuning
top_scores = [p.score for p in search_response.points[:3]]
logger.debug(f"Top 3 similarity scores: {top_scores}")
logger.debug("Top 3 similarity scores: %s", top_scores)
# Deduplicate by (doc_id, doc_type, chunk_start, chunk_end)
# This allows multiple chunks from same doc, but removes duplicate chunks
@@ -155,12 +159,12 @@ class SemanticSearchAlgorithm(SearchAlgorithm):
if len(results) >= limit:
break
logger.info(f"Returning {len(results)} unverified results after deduplication")
logger.info("Returning %s unverified results after deduplication", len(results))
if results:
result_details = [
f"{r.doc_type}_{r.id} (score={r.score:.3f}, title='{r.title}')"
for r in results[:5] # Show top 5
]
logger.debug(f"Top results: {', '.join(result_details)}")
logger.debug("Top results: %s", ", ".join(result_details))
return results