fix ruff --preview errors

pyglossary/file_utils.py

@@ -5,6 +5,7 @@
 
 __all__ = ["fileCountLines"]
 
+
 def fileCountLines(filename: str, newline: bytes = b"\n") -> int:
 	with open(filename, "rb") as _file:
 		bufgen = takewhile(

pyglossary/glossary_v2.py

@@ -1213,7 +1213,7 @@ def convertV2(self, args: ConvertArgs) -> "str | None":
 			finalOutputFile = self._compressOutput(finalOutputFile, compression)
 
 		log.info(f"Writing file {finalOutputFile!r} done.")
-		log.info(f"Running time of convert: {now()-tm0:.1f} seconds")
+		log.info(f"Running time of convert: {now() - tm0:.1f} seconds")
 		showMemoryUsage()
 		self.cleanup()
 

pyglossary/langs/__init__.py

@@ -89,7 +89,7 @@ def load(self) -> None:
 
 		log.debug(
 			f"LangDict: loaded, {len(self)} keys, "
-			f"took {(now() - t0)*1000:.1f} ms",
+			f"took {(now() - t0) * 1000:.1f} ms",
 		)
 
 	def __getitem__(self, key: str) -> "Lang | None":

pyglossary/plugins/aard2_slob.py

@@ -273,7 +273,7 @@ def _open(self, filename: str, namePostfix: str) -> "slob.Writer":
 
 		if isfile(filename):
 			shutil.move(filename, f"{filename}.bak")
-			log.warning(f"renamed existing {filename!r} to {filename+'.bak'!r}")
+			log.warning(f"renamed existing {filename!r} to {filename + '.bak'!r}")
 		self._slobWriter = slobWriter = slob.Writer(
 			filename,
 			observer=self._slobObserver,
@@ -428,7 +428,7 @@ def write(self) -> "Generator[None, EntryType, None]":
 					fileIndex += 1
 					slobWriter = self._open(
 						f"{filenameNoExt}.{fileIndex}.slob",
-						f" (part {fileIndex+1})",
+						f" (part {fileIndex + 1})",
 					)
 					sumBlobSize = 0
 					entryCount = 0

pyglossary/plugins/babylon_bgl/bgl_reader.py

@@ -524,9 +524,7 @@ def setGlossaryInfo(self) -> None:
 				continue
 				# TODO: a bool flag to add empty value infos?
 			# leave "creationTime" and "lastUpdated" as is
-			if key in {
-				"utf8Encoding",
-			}:
+			if key == "utf8Encoding":
 				key = "bgl_" + key
 			try:
 				glos.setInfo(key, s_value)
@@ -814,7 +812,7 @@ def __iter__(self) -> "Iterator[EntryType]":
 					continue
 				pos = wordData.pos
 				# defi:
-				succeed, pos, u_defi, b_defi = self.readEntryDefi(
+				succeed, pos, u_defi, _b_defi = self.readEntryDefi(
 					block,
 					pos,
 					wordData,
@@ -993,7 +991,7 @@ def readEntry_Type11(
 			)
 			return Err
 		b_word = block.data[pos : pos + wordLen]
-		u_word, u_word_html = self.processKey(b_word)
+		u_word, _u_word_html = self.processKey(b_word)
 		pos += wordLen
 		self.wordLenMax = max(self.wordLenMax, len(u_word))
 
@@ -1219,7 +1217,7 @@ def processAlternativeKey(self, b_word: bytes, b_key: bytes) -> str:
 		b_word is a bytes instance
 		returns u_word_main, as str instance (utf-8 encoding).
 		"""
-		b_word_main, strip_count = stripDollarIndexes(b_word)
+		b_word_main, _strip_count = stripDollarIndexes(b_word)
 		# convert to unicode
 		if self._strict_string_conversion:
 			try:
@@ -1274,7 +1272,7 @@ def processDefi(self, b_defi: bytes, b_key: bytes) -> str:
 		fields.u_defi = fields.u_defi.strip()
 
 		if fields.b_title:
-			fields.u_title, singleEncoding = self.decodeCharsetTags(
+			fields.u_title, _singleEncoding = self.decodeCharsetTags(
 				fields.b_title,
 				self.sourceEncoding,
 			)
@@ -1283,7 +1281,7 @@ def processDefi(self, b_defi: bytes, b_key: bytes) -> str:
 
 		if fields.b_title_trans:
 			# sourceEncoding or targetEncoding ?
-			fields.u_title_trans, singleEncoding = self.decodeCharsetTags(
+			fields.u_title_trans, _singleEncoding = self.decodeCharsetTags(
 				fields.b_title_trans,
 				self.sourceEncoding,
 			)
@@ -1298,7 +1296,7 @@ def processDefi(self, b_defi: bytes, b_key: bytes) -> str:
 				# what is this?
 				pass
 			elif fields.code_transcription_50 == 0x1B:
-				fields.u_transcription_50, singleEncoding = self.decodeCharsetTags(
+				fields.u_transcription_50, _singleEncoding = self.decodeCharsetTags(
 					fields.b_transcription_50,
 					self.sourceEncoding,
 				)
@@ -1323,7 +1321,7 @@ def processDefi(self, b_defi: bytes, b_key: bytes) -> str:
 
 		if fields.b_transcription_60:
 			if fields.code_transcription_60 == 0x1B:
-				fields.u_transcription_60, singleEncoding = self.decodeCharsetTags(
+				fields.u_transcription_60, _singleEncoding = self.decodeCharsetTags(
 					fields.b_transcription_60,
 					self.sourceEncoding,
 				)
@@ -1341,7 +1339,7 @@ def processDefi(self, b_defi: bytes, b_key: bytes) -> str:
 				)
 
 		if fields.b_field_1a:
-			fields.u_field_1a, singleEncoding = self.decodeCharsetTags(
+			fields.u_field_1a, _singleEncoding = self.decodeCharsetTags(
 				fields.b_field_1a,
 				self.sourceEncoding,
 			)

pyglossary/plugins/babylon_bgl/bgl_reader_debug.py

@@ -262,14 +262,14 @@ def __del__(self) -> None:
 		BglReader.__del__(self)
 
 	def readEntryWord(self, block, pos):
-		succeed, pos, u_word, b_word = BglReader.readEntryWord(self, block, pos)
+		succeed, pos, _u_word, b_word = BglReader.readEntryWord(self, block, pos)
 		if not succeed:
 			return
 		self.rawDumpFileWriteText(f"\n\nblock type = {block.type}\nkey = ")
 		self.rawDumpFileWriteData(b_word)
 
 	def readEntryDefi(self, block, pos, b_key):
-		succeed, pos, u_defi, b_defi = BglReader.readEntryDefi(self, block, pos, b_key)
+		succeed, pos, _u_defi, b_defi = BglReader.readEntryDefi(self, block, pos, b_key)
 		if not succeed:
 			return
 		self.rawDumpFileWriteText("\ndefi = ")

pyglossary/plugins/dicformids.py

@@ -206,7 +206,7 @@ def writeBucket(dicIndex: int, entryList: "list[EntryType]") -> None:
 			dicFp = open(
 				join(
 					self._dirname,
-					f"directory{self.directoryPostfix}{dicIndex+1}.csv",
+					f"directory{self.directoryPostfix}{dicIndex + 1}.csv",
 				),
 				mode="w",
 				encoding="utf-8",

pyglossary/plugins/dsl/lex.py

@@ -248,7 +248,7 @@ def lexRefText(tr: TransformerType) -> tuple[LexType, ErrorType]:
 	if not target:
 		target = text
 
-	tr.output += f'<a href={quoteattr("bword://"+target)}>{escape(text)}</a>'
+	tr.output += f'<a href={quoteattr("bword://" + target)}>{escape(text)}</a>'
 	tr.resetBuf()
 	return lexRoot, None
 

pyglossary/plugins/html_dir.py

@@ -423,8 +423,8 @@ def addLinks(text: str, pos: int) -> None:
 				b_size = len(text[start : m.end()].encode(encoding))
 				linksTxtFileObj.write(
 					f"{escapeNTB(target)}\t"
-					f"{len(self._filenameList)-1}\t"
-					f"{pos+b_start:x}\t"
+					f"{len(self._filenameList) - 1}\t"
+					f"{pos + b_start:x}\t"
 					f"{b_size:x}\n",
 				)
 				linksTxtFileObj.flush()

pyglossary/plugins/info_plugin.py

@@ -109,7 +109,7 @@ def write(self) -> "Generator[None, EntryType, None]":
 						tag = tag.strip("< />").lower()
 						allTagsCounter[tag] += 1
 			elif defiFormat == "b":
-				filenameNoExt, ext = splitext(entry.s_word)
+				_filenameNoExt, ext = splitext(entry.s_word)
 				ext = ext.lstrip(".")
 				dataEntryExtCounter[ext] += 1
 

pyglossary/plugins/octopus_mdict_new/__init__.py

@@ -111,7 +111,7 @@ def open(self, filename: str) -> None:
 				FILE.3.mdd
 		"""
 
-		filenameNoExt, ext = splitext(self._filename)
+		filenameNoExt, _ext = splitext(self._filename)
 		mddBase = "".join([filenameNoExt, extsep])
 		for fname in (f"{mddBase}mdd", f"{mddBase}1.mdd"):
 			if isfile(fname):

pyglossary/plugins/quickdic6.py

@@ -206,8 +206,10 @@ def write_hashset(
 	write_byte(fp, 0x78)
 	return fp.tell() - write_start_offset
 
+
 T = TypeVar("T")
 
+
 def read_list(
 	fp: IO[bytes],
 	fun: "Callable[[IO[bytes]], T]",
@@ -689,7 +691,7 @@ def _extract_synonyms_from_indices(self) -> None:
 		self._synonyms: dict[tuple[int, int], set[str]] = {}
 		assert self._dic is not None
 		for index in self._dic.indices:
-			_, _, _, _, swap_flag, _, index_entries, _, rows = index
+			_, _, _, _, swap_flag, _, index_entries, _, _ = index
 
 			# Note that we ignore swapped indices because pyglossary assumes
 			# uni-directional dictionaries.

pyglossary/plugins/sql.py

@@ -108,7 +108,7 @@ def _writeInfo(self) -> None:
 				key = key.replace("'", "''")
 				value = value.replace("'", "''")
 				fileObj.write(
-					f"INSERT INTO dbinfo_extra VALUES({index+1}, "
+					f"INSERT INTO dbinfo_extra VALUES({index + 1}, "
 					f"'{key}', '{value}');\n",
 				)
 

pyglossary/plugins/stardict.py

@@ -968,7 +968,7 @@ def writeCompact(self, defiFormat: str) -> "Generator[None, EntryType, None]":
 		idxFile.close()
 		if not os.listdir(self._resDir):
 			os.rmdir(self._resDir)
-		log.info(f"Writing dict file took {now()-t0:.2f} seconds")
+		log.info(f"Writing dict file took {now() - t0:.2f} seconds")
 
 		self.writeSynFile(altIndexList)
 		self.writeIfoFile(
@@ -1049,7 +1049,7 @@ def writeGeneral(self) -> "Generator[None, EntryType, None]":
 		idxFile.close()
 		if not os.listdir(self._resDir):
 			os.rmdir(self._resDir)
-		log.info(f"Writing dict file took {now()-t0:.2f} seconds")
+		log.info(f"Writing dict file took {now() - t0:.2f} seconds")
 		log.debug("defiFormatsCount = " + pformat(defiFormatCounter.most_common()))
 
 		self.writeSynFile(altIndexList)
@@ -1073,7 +1073,7 @@ def writeSynFile(self, altIndexList: "T_SdList[tuple[bytes, int]]") -> None:
 		# 0.20 seconds without key function (default sort)
 
 		log.info(
-			f"Sorting {len(altIndexList)} synonyms took {now()-t0:.2f} seconds",
+			f"Sorting {len(altIndexList)} synonyms took {now() - t0:.2f} seconds",
 		)
 		log.info(f"Writing {len(altIndexList)} synonyms...")
 		t0 = now()
@@ -1085,7 +1085,7 @@ def writeSynFile(self, altIndexList: "T_SdList[tuple[bytes, int]]") -> None:
 				),
 			)
 		log.info(
-			f"Writing {len(altIndexList)} synonyms took {now()-t0:.2f} seconds",
+			f"Writing {len(altIndexList)} synonyms took {now() - t0:.2f} seconds",
 		)
 
 	def writeCompactMergeSyns(
@@ -1150,7 +1150,7 @@ def writeCompactMergeSyns(
 		dictFile.close()
 		if not os.listdir(self._resDir):
 			os.rmdir(self._resDir)
-		log.info(f"Writing dict file took {now()-t0:.2f} seconds")
+		log.info(f"Writing dict file took {now() - t0:.2f} seconds")
 
 		self.writeIfoFile(
 			wordCount,
@@ -1223,7 +1223,7 @@ def writeGeneralMergeSyns(self) -> "Generator[None, EntryType, None]":
 		dictFile.close()
 		if not os.listdir(self._resDir):
 			os.rmdir(self._resDir)
-		log.info(f"Writing dict file took {now()-t0:.2f} seconds")
+		log.info(f"Writing dict file took {now() - t0:.2f} seconds")
 		log.debug("defiFormatsCount = " + pformat(defiFormatCounter.most_common()))
 
 		self.writeIfoFile(
@@ -1242,14 +1242,14 @@ def writeIdxFile(self, indexList: "T_SdList[tuple[bytes, bytes]]") -> int:
 
 		indexList.sort()
 		log.info(
-			f"Sorting {len(indexList)} {filename} took {now()-t0:.2f} seconds",
+			f"Sorting {len(indexList)} {filename} took {now() - t0:.2f} seconds",
 		)
 		log.info(f"Writing {len(indexList)} index entries...")
 		t0 = now()
 		with open(filename, mode="wb") as indexFile:
 			indexFile.write(b"".join(key + b"\x00" + value for key, value in indexList))
 		log.info(
-			f"Writing {len(indexList)} {filename} took {now()-t0:.2f} seconds",
+			f"Writing {len(indexList)} {filename} took {now() - t0:.2f} seconds",
 		)
 		return len(indexList)
 

pyglossary/plugins/yomichan.py

@@ -365,7 +365,7 @@ def flushTerms() -> None:
 					return
 
 				with open(
-					f"term_bank_{termBankIndex+1}.json",
+					f"term_bank_{termBankIndex + 1}.json",
 					mode="w",
 					encoding="utf-8",
 				) as _file:

pyproject.toml

@@ -24,6 +24,7 @@ lint.select = [
     "W", # pycodestyle Warning
     "YTT", # flake8-2020
     "ARG", # flake8-unused-arguments: ARG001 Unused function argument
+    # "FURB",
 
     # "C90", # mccabe: C901: {name} is too complex ({complexity})
     # "N", # pep8-naming
@@ -32,6 +33,7 @@ lint.select = [
     # "ANN", # flake8-annotationsq, still gives errors for `self`
 ]
 lint.ignore = [
+    "FURB101", # `open` and `read` should be replaced by `Path(rootConfJsonFile).read_text()`
 	"PGH003", # Use specific rule codes when ignoring type issues
     "B019", # Use of `functools.lru_cache` or `functools.cache` on methods can lead to memory leaks
     "D100", # Missing docstring in public module
@@ -137,7 +139,7 @@ lint.dummy-variable-rgx = "^(_+|(_+[a-zA-Z0-9_]*[a-zA-Z0-9]+?))$"
 "scripts/wiki-formats.py" = ["E501"]
 "pyglossary/io_utils.py" = ["ANN"]
 "pyglossary/plugin_lib/*.py" = ["ANN"]
-"pyglossary/plugins/babylon_bgl/bgl_reader_debug.py" = ["ANN"]
+"pyglossary/plugins/babylon_bgl/bgl_reader_debug.py" = ["ANN", "FURB"]
 "pyglossary/ui/*.py" = ["ANN"]
 "pyglossary/ui/*/*.py" = ["ANN"]
 "tests/*.py" = ["ANN"]

scripts/wiktextract/extract-schema.py

@@ -163,7 +163,7 @@ def parseDict(data: "dict[str, Any]", path: "list[str]", node: Node):
 
 
 def commonValuesSortKey(item):
-	key, values = item
+	_key, values = item
 	return abs(len(values) - 5)