add types for list vars with empty initial value

pyglossary/plugins/aard2_slob.py

@@ -158,7 +158,7 @@ def open(self, filename: str) -> None:  # noqa: PLR0912
 		if t_created_by in tags:
 			self._glos.setInfo("author", tags[t_created_by])
 
-		copyrightLines = []
+		copyrightLines: list[str] = []
 		for key in (t_copyright, t_license_name, t_license_url):
 			try:
 				value = tags.pop(key)

pyglossary/plugins/appledict/_dict.py

@@ -41,7 +41,7 @@ def base36(x: int) -> str:
 	Simplified version of int2base
 	http://stackoverflow.com/questions/2267362/convert-integer-to-a-string-in-a-given-numeric-base-in-python#2267446.
 	"""
-	digits = []
+	digits: list[str] = []
 	while x:
 		digits.append(digs[x % 36])
 		x //= 36

pyglossary/plugins/babylon_bgl/bgl_reader.py

@@ -1127,7 +1127,7 @@ def decodeCharsetTags(  # noqa: PLR0912
 		"""
 		b_parts = re_charset_decode.split(b_text)
 		u_text = ""
-		encodings = []  # stack of encodings
+		encodings: list[str] = []  # stack of encodings
 		defaultEncodingOnly = True
 		for i, b_part in enumerate(b_parts):
 			if i % 3 == 0:  # text block

pyglossary/plugins/babylon_bgl/bgl_reader_debug.py

@@ -511,7 +511,7 @@ def findAndPrintCharSamples(self, b_data: bytes, hint, encoding):
 			f"\nmarked = {res}\norig = {b_data}\n",
 		)
 
-	def findCharSamples(self, b_data):
+	def findCharSamples(self, b_data: bytes) -> list[int]:
 		"""
 		Find samples of chars in b_data.
 
@@ -520,7 +520,7 @@ def findCharSamples(self, b_data):
 		Returns a list of offsets in b_data
 		May return an empty list.
 		"""
-		res = []
+		res: list[int] = []
 		if not isinstance(b_data, bytes):
 			log.error("findCharSamples: b_data is not a bytes instance")
 			return res

pyglossary/plugins/cc_kedict.py

@@ -275,7 +275,7 @@ def _createEntry(
 	def nextBlock(self) -> EntryType:
 		if not self._file:
 			raise StopIteration
-		lines = []
+		lines: list[str] = []
 		while True:
 			line = self.readline()
 			if not line:

pyglossary/plugins/dicformids.py

@@ -13,7 +13,7 @@
 from pyglossary.plugins.tabfile import Reader as TabfileReader
 
 if TYPE_CHECKING:
-	from collections.abc import Iterator
+	from collections.abc import Generator, Iterator
 
 	from pyglossary.glossary_types import EntryType, GlossaryType
 	from pyglossary.option import Option
@@ -92,12 +92,12 @@ class Reader:
 
 	def __init__(self, glos: GlossaryType) -> None:
 		self._glos = glos
-		self._tabFileNames = []
+		self._tabFileNames: list[str] = []
 		self._tabFileReader = None
 
 	def open(self, dirname: str) -> None:
 		self._dirname = dirname
-		orderFileNames = []
+		orderFileNames: list[tuple[int, str]] = []
 		for fname in os.listdir(dirname):
 			if not fname.startswith("directory"):
 				continue
@@ -212,11 +212,11 @@ def open(self, dirname: str) -> None:
 		if not os.path.isdir(dirname):
 			os.mkdir(dirname)
 
-	def write(self) -> None:
+	def write(self) -> Generator[None, EntryType, None]:
 		self.nextIndex()
 
 		dicMaxSize = 0
-		indexData = []
+		indexData: list[tuple[str, int, int]] = []
 
 		def writeBucket(dicIndex: int, entryList: list[EntryType]) -> None:
 			nonlocal dicMaxSize
@@ -247,7 +247,7 @@ def writeBucket(dicIndex: int, entryList: list[EntryType]) -> None:
 		bucketSize = self.linesPerDirectoryFile
 		wordCount = 0
 		dicIndex = 0
-		entryList = []  # aka bucket
+		entryList: list[EntryType] = []  # aka bucket
 		while True:
 			entry = yield
 			if entry is None:
@@ -264,7 +264,7 @@ def writeBucket(dicIndex: int, entryList: list[EntryType]) -> None:
 
 		if entryList:
 			writeBucket(dicIndex, entryList)
-			entryList = None
+			entryList = []
 
 		self.dicMaxSize = dicMaxSize
 		self.wordCount = wordCount

pyglossary/plugins/dsl/__init__.py

@@ -365,8 +365,8 @@ def parseEntryBlock(  # noqa: PLR0912 Too many branches (14 > 12)
 		term_lines: list[str],
 		text_lines: list[str],
 	) -> Iterator[EntryType]:
-		terms = []
-		defiTitles = []
+		terms: list[str] = []
+		defiTitles: list[str] = []
 		for line in term_lines:
 			tr = TitleTransformer(line)
 			res, err = tr.transform()

pyglossary/plugins/ebook_epub2.py

@@ -257,7 +257,7 @@ def write_ncx(self, group_labels: list[str]) -> None:
 		write_ncx
 		only for epub.
 		"""
-		ncx_items = []
+		ncx_items: list[str] = []
 		index = 1
 		if self._include_index_page:
 			ncx_items.append(

pyglossary/plugins/ebook_kobo.py

@@ -179,8 +179,9 @@ def writeGroup(lastPrefix: str) -> None:
 				gzipFile.write(htmlContents.encode("utf-8"))
 			htmlContents = htmlHeader
 
-		allWords = []
-		data = []
+		allWords: list[str] = []
+		# TODO: switch to SQLite, like StarDict writer
+		data: list[tuple[str, bytes]] = []
 
 		while True:
 			entry = yield

pyglossary/plugins/freedict/reader.py

@@ -152,7 +152,7 @@ def writeTransCit(
 	) -> None:
 		from lxml import etree as ET
 
-		quotes = []
+		quotes: list[Element] = []
 		sense = ET.Element(f"{TEI}sense")
 		for child in elem.xpath("child::node()"):
 			if isinstance(child, str):
@@ -482,7 +482,7 @@ def writeGramGroups(
 			attrib["color"] = color
 
 		for gramGrp in gramGrpList:
-			parts = []
+			parts: list[str] = []
 			for child in gramGrp.iterchildren():
 				part = self.normalizeGramGrpChild(child)
 				if part:
@@ -596,7 +596,7 @@ def getEntryByElem(  # noqa: PLR0912
 		from lxml import etree as ET
 
 		glos = self._glos
-		keywords = []
+		keywords: list[str] = []
 		buff = BytesIO()
 		pron_color = self._pron_color
 
@@ -608,7 +608,7 @@ def getEntryByElem(  # noqa: PLR0912
 		def br() -> Element:
 			return ET.Element("br")
 
-		inflectedKeywords = []
+		inflectedKeywords: list[str] = []
 
 		for form in entry.findall("form", NAMESPACE):
 			inflected = form.get("type") == "infl"
@@ -692,7 +692,7 @@ def stripParagList(
 		self,
 		elems: list[Element],
 	) -> str:
-		lines = []
+		lines: list[str] = []
 		for elem in elems:
 			for line in self.stripParag(elem).split("\n"):
 				line = line.strip()  # noqa: PLW2901
@@ -731,14 +731,14 @@ def replaceRefLink(self, text: str) -> str:
 		return self._ref_pattern.sub('<a href="\\1">\\2</a>', text)
 
 	def setDescription(self, header: Element) -> None:
-		elems = []
+		elems: list[Element] = []
 		for tag in ("sourceDesc", "projectDesc"):
 			elems += header.findall(f".//{tag}//p", NAMESPACE)
 		desc = self.stripParagList(elems)
 		if not desc:
 			return
 
-		website_list = []
+		website_list: list[str] = []
 		for match in self._website_pattern.findall(desc):
 			if not match[1]:
 				continue

pyglossary/plugins/html_dir.py

@@ -389,7 +389,7 @@ def pageHeader(n: int) -> str:
 			)
 
 		def navBar() -> str:
-			links = []
+			links: list[str] = []
 			if len(self._filenameList) > 1:
 				links.append(f'<a href="./{self._filenameList[-2]}">&#9664;</a>')
 			links.extend(

pyglossary/plugins/iupac_goldbook.py

@@ -217,7 +217,7 @@ def __iter__(self) -> Iterator[EntryType]:  # noqa: PLR0912
 
 			term = self.getTerm(termE)
 
-			words = []
+			words: list[str] = []
 			if term:
 				words.append(term)
 			if code:
@@ -234,7 +234,7 @@ def __iter__(self) -> Iterator[EntryType]:  # noqa: PLR0912
 			if identifierSynonym is not None and identifierSynonym.text:
 				words.append(identifierSynonym.text)
 
-			defiParts = []
+			defiParts: list[str] = []
 
 			definition = elem.find("./definition")
 			if definition is None or not definition.text:
@@ -269,7 +269,7 @@ def __iter__(self) -> Iterator[EntryType]:  # noqa: PLR0912
 
 			relatedList = elem.findall("./related/entry")
 			if relatedList:
-				relatedLinkList = []
+				relatedLinkList: list[str] = []
 				for related in relatedList:
 					relatedURL = related.text
 					relatedCode = relatedURL.split("/")[-1]

pyglossary/plugins/jmdict.py

@@ -150,7 +150,7 @@ def br() -> Element:
 				hf.write(gloss)
 			hf.write(br())
 
-		relatedWords = []
+		relatedWords: list[str] = []
 		for elem in sense.findall("xref"):
 			if not elem.text:
 				continue
@@ -168,7 +168,7 @@ def br() -> Element:
 					hf.write(word)
 			hf.write(br())
 
-		antonymWords = []
+		antonymWords: list[str] = []
 		for elem in sense.findall("ant"):
 			if not elem.text:
 				continue
@@ -257,7 +257,7 @@ def getEntryByElem(  # noqa: PLR0912
 		from lxml import etree as ET
 
 		glos = self._glos
-		keywords = []
+		keywords: list[str] = []
 		f = BytesIO()
 		translit = self._translitation
 
@@ -300,7 +300,7 @@ def br() -> Element:
 						continue
 					if not reb.text:
 						continue
-					props = []
+					props: list[str] = []
 					if r_ele.find("re_nokanji") is not None:
 						props.append("no kanji")
 					inf = r_ele.find("re_inf")

pyglossary/plugins/jmnedict.py

@@ -124,7 +124,7 @@ def br() -> Element:
 			hf.write(desc)
 			hf.write(br())
 
-		relatedWords = []
+		relatedWords: list[str] = []
 		for elem in trans.findall("xref"):
 			if not elem.text:
 				continue
@@ -149,7 +149,7 @@ def getEntryByElem(  # noqa: PLR0912
 		from lxml import etree as ET
 
 		glos = self._glos
-		keywords = []
+		keywords: list[str] = []
 		f = BytesIO()
 
 		def br() -> Element:
@@ -176,7 +176,7 @@ def br() -> Element:
 						continue
 					if not reb.text:
 						continue
-					props = []
+					props: list[str] = []
 					if r_ele.find("re_nokanji") is not None:
 						props.append("no kanji")
 					inf = r_ele.find("re_inf")

pyglossary/plugins/lingoes_ldf.py

@@ -91,7 +91,7 @@ def fixInfoWord(cls, word: str) -> str:
 	def nextBlock(self) -> nextBlockResultType:
 		if not self._file:
 			raise StopIteration
-		entryLines = []
+		entryLines: list[str] = []
 		while True:
 			line = self.readline()
 			if not line:

pyglossary/plugins/quickdic6/quickdic.py

@@ -107,7 +107,7 @@ def add_index(  # noqa: PLR0913
 				index_start = len(rows)
 				count = 0
 				token_norm = "" if token == token_norm else token_norm  # noqa: PLW2901
-				html_indices = []
+				html_indices: list[int] = []
 				rows.append((1, i_entry))
 			if ttype == 4:
 				if tidx not in html_indices:

pyglossary/plugins/quickdic6/read_funcs.py

@@ -81,7 +81,7 @@ def read_list(
 ) -> list[T]:
 	size = read_int(fp)
 	toc = struct.unpack(f">{size + 1}q", fp.read(8 * (size + 1)))
-	entries = []
+	entries: list[T] = []
 	for offset in toc[:-1]:
 		fp.seek(offset)
 		entries.append(fun(fp))

pyglossary/plugins/quickdic6/reader.py

@@ -114,7 +114,7 @@ def _extract_rows_from_indexentry(
 		block_rows = rows[start_index : start_index + count + 1]
 		assert block_rows[0][0] in {1, 3}
 		assert block_rows[0][1] == i_entry
-		e_rows = []
+		e_rows: list[tuple[int, int]] = []
 		for entry_type, entry_idx in block_rows[1:]:
 			if entry_type in {1, 3}:
 				# avoid an endless recursion

pyglossary/plugins/quickdic6/writer.py

@@ -66,7 +66,7 @@ def write_quickdic(dic: QuickDic, path: str) -> None:
 
 	def write(self) -> typing.Generator[None, EntryType, None]:
 		synonyms: dict[str, list[str]] = {}
-		htmls = []
+		htmls: list[tuple[int, str, str]] = []
 		log.info("Converting individual entries ...")
 		while True:
 			entry = yield
@@ -111,8 +111,6 @@ def write(self) -> typing.Generator[None, EntryType, None]:
 		log.info(f"QuickDic: {langs = }, {name = }")
 
 		sources = [("", len(htmls))]
-		pairs = []
-		texts = []
 
 		created = None
 		createdStr = os.getenv("QUICKDIC_CREATION_TIME")
@@ -123,8 +121,8 @@ def write(self) -> typing.Generator[None, EntryType, None]:
 		self._dic = QuickDic(
 			name=name,
 			sources=sources,
-			pairs=pairs,
-			texts=texts,
+			pairs=[],
+			texts=[],
 			htmls=htmls,
 			created=created,
 			# version: int = 6,

pyglossary/plugins/sql.py

@@ -81,7 +81,7 @@ def _writeInfo(self) -> None:
 		newline = self._newline
 		info_keys = self._getInfoKeys()
 		infoDefLine = "CREATE TABLE dbinfo ("
-		infoValues = []
+		infoValues: list[str] = []
 		glos = self._glos
 
 		for key in info_keys: