":
extraOptNames.append(name)
continue
- if name not in ("filename", "dirname"):
+ if name not in {"filename", "dirname"}:
extraOptNames.append(name)
if extraOptNames:
log.warning(f"{format}: {extraOptNames = }")
diff --git a/pyglossary/plugins/aard2_slob.py b/pyglossary/plugins/aard2_slob.py
index d3d8f2079..7c28e4cfb 100644
--- a/pyglossary/plugins/aard2_slob.py
+++ b/pyglossary/plugins/aard2_slob.py
@@ -181,7 +181,8 @@ def __len__(self) -> int:
return 0
return len(self._slobObj)
- def _href_sub(self, m: "re.Match") -> str:
+ @staticmethod
+ def _href_sub(m: "re.Match") -> str:
st = m.group(0)
if "//" in st:
return st
@@ -213,7 +214,7 @@ def __iter__(self) -> "Iterator[EntryType | None]":
word = blob.key
ctype = blob.content_type.split(";")[0]
- if ctype not in (MIME_HTML, MIME_TEXT):
+ if ctype not in {MIME_HTML, MIME_TEXT}:
log.debug(f"unknown {blob.content_type=} in {word=}")
word = word.removeprefix("~/")
yield self._glos.newDataEntry(word, blob.content)
@@ -278,8 +279,8 @@ def __init__(self, glos: GlossaryType) -> None:
self._resPrefix = ""
self._slobWriter: "slob.Writer | None" = None
+ @staticmethod
def _slobObserver(
- self,
event: "slob.WriterEvent", # noqa: F401, F821
) -> None:
log.debug(f"slob: {event.name}{': ' + event.data if event.data else ''}")
@@ -357,7 +358,7 @@ def addEntry(self, entry: "EntryType") -> None:
entry.detectDefiFormat()
defiFormat = entry.defiFormat
- if self._word_title and defiFormat in ("h", "m"):
+ if self._word_title and defiFormat in {"h", "m"}:
if defiFormat == "m":
defiFormat = "h"
title = self._glos.wordTitleStr(
diff --git a/pyglossary/plugins/appledict/_content.py b/pyglossary/plugins/appledict/_content.py
index 0c7967534..014add19f 100644
--- a/pyglossary/plugins/appledict/_content.py
+++ b/pyglossary/plugins/appledict/_content.py
@@ -117,7 +117,7 @@ def prepare_content_without_soup(
return content # noqa: RET504
-def _prepare_href(tag):
+def _prepare_href(tag) -> None:
href = tag["href"]
href = cleanup_link_target(href)
@@ -136,7 +136,7 @@ def _prepare_href(tag):
tag["href"] = f"x-dictionary:d:{href}"
-def _prepare_onclick(soup):
+def _prepare_onclick(soup) -> None:
for thumb in soup.find_all("div", "pic_thumb"):
thumb["onclick"] = (
'this.setAttribute("style", "display:none"); '
diff --git a/pyglossary/plugins/appledict/indexes/zh.py b/pyglossary/plugins/appledict/indexes/zh.py
index 06621f2ae..5acec475a 100644
--- a/pyglossary/plugins/appledict/indexes/zh.py
+++ b/pyglossary/plugins/appledict/indexes/zh.py
@@ -58,8 +58,7 @@ def zh(titles: "Sequence[str]", content: str) -> "set[str]":
indexes.update({title, title + "。"})
# remove all non hieroglyph
- title = nonHieroglyphPattern.sub("", title)
- indexes.add(title)
+ indexes.add(nonHieroglyphPattern.sub("", title))
indexes.update(pinyin_indexes(content))
diff --git a/pyglossary/plugins/appledict/jing/main.py b/pyglossary/plugins/appledict/jing/main.py
index 0ed897f85..20fd5513d 100644
--- a/pyglossary/plugins/appledict/jing/main.py
+++ b/pyglossary/plugins/appledict/jing/main.py
@@ -85,9 +85,9 @@ def main() -> None:
if len(sys.argv) < 2:
prog_name = path.basename(sys.argv[0])
log.info(f"usage:\n {prog_name} filename")
- exit(1)
+ sys.exit(1)
try:
run(sys.argv[1])
except JingTestError as e:
log.fatal(str(e))
- exit(e.returncode)
+ sys.exit(e.returncode)
diff --git a/pyglossary/plugins/appledict_bin/__init__.py b/pyglossary/plugins/appledict_bin/__init__.py
index 9328b45e7..0ab38bc39 100644
--- a/pyglossary/plugins/appledict_bin/__init__.py
+++ b/pyglossary/plugins/appledict_bin/__init__.py
@@ -131,12 +131,12 @@ def __init__(self, glos: GlossaryType) -> None:
self._keyTextData: "dict[ArticleAddress, list[RawKeyData]]" = {}
self._cssName = ""
+ @staticmethod
def tostring(
- self,
elem: "Element | HtmlComment | HtmlElement | "
"HtmlEntity | HtmlProcessingInstruction",
) -> str:
- from lxml.html import tostring as tostring
+ from lxml.html import tostring
return tostring(
cast("HtmlElement", elem),
@@ -255,7 +255,8 @@ def open(self, filename: str) -> "Iterator[tuple[int, int]]":
f"number of entries: {self._wordCount}",
)
- def parseMetadata(self, infoPlistPath: str) -> "dict[str, Any]":
+ @staticmethod
+ def parseMetadata(infoPlistPath: str) -> "dict[str, Any]":
import biplist
if not isfile(infoPlistPath):
@@ -361,8 +362,8 @@ def _getDefi(
return defi
+ @staticmethod
def getChunkLenOffset(
- self,
pos: int,
buffer: bytes,
) -> "tuple[int, int]":
@@ -452,11 +453,11 @@ def convertEntryBytesToXml(
def readEntryIds(self) -> None:
titleById = {}
- for entryBytes, _ in self.yieldEntryBytes(
+ for entryBytesTmp, _ in self.yieldEntryBytes(
self._file,
self._properties,
):
- entryBytes = entryBytes.strip()
+ entryBytes = entryBytesTmp.strip()
if not entryBytes:
continue
id_i = entryBytes.find(b'id="')
@@ -642,6 +643,15 @@ def readResFile(self, fname: str, fpath: str, ext: str) -> EntryType:
data = substituteAppleCSS(data)
return self._glos.newDataEntry(fname, data)
+ def fixResFilename(self, fname: str, relPath: str):
+ if fname == self._cssName:
+ fname = "style.css"
+ if relPath:
+ fname = relPath + "/" + fname
+ if os.path == "\\":
+ fname = fname.replace("\\", "/")
+ return fname
+
def readResDir(
self,
dirPath: str,
@@ -666,16 +676,13 @@ def readResDir(
relPath=join(relPath, fname),
)
continue
+
if not isfile(fpath):
continue
- if fname == self._cssName:
- fname = "style.css"
- if relPath:
- fname = relPath + "/" + fname
- if os.path == "\\":
- fname = fname.replace("\\", "/")
- core.trace(log, f"Using resource {fpath!r} as {fname!r}")
- yield self.readResFile(fname, fpath, ext)
+
+ fname2 = self.fixResFilename(fname, relPath)
+ core.trace(log, f"Using resource {fpath!r} as {fname2!r}")
+ yield self.readResFile(fname2, fpath, ext)
def __iter__(self) -> Iterator[EntryType]:
yield from self.readResDir(
diff --git a/pyglossary/plugins/babylon_bgl/bgl_info.py b/pyglossary/plugins/babylon_bgl/bgl_info.py
index 1ba739186..94aaedca5 100644
--- a/pyglossary/plugins/babylon_bgl/bgl_info.py
+++ b/pyglossary/plugins/babylon_bgl/bgl_info.py
@@ -24,7 +24,7 @@
from collections.abc import Callable
from typing import Any
-import pyglossary.gregorian as gregorian
+from pyglossary import gregorian
from pyglossary.core import log
from pyglossary.text_utils import (
uintFromBytes,
diff --git a/pyglossary/plugins/babylon_bgl/bgl_reader.py b/pyglossary/plugins/babylon_bgl/bgl_reader.py
index 878c58dfc..c0361c6e9 100644
--- a/pyglossary/plugins/babylon_bgl/bgl_reader.py
+++ b/pyglossary/plugins/babylon_bgl/bgl_reader.py
@@ -404,10 +404,10 @@ def openGzip(self) -> None:
return False
b_head = bglFile.read(6)
- if len(b_head) < 6 or b_head[:4] not in (
+ if len(b_head) < 6 or b_head[:4] not in {
b"\x12\x34\x00\x01",
b"\x12\x34\x00\x02",
- ):
+ }:
log.error(f"invalid header: {b_head[:6]!r}")
return False
@@ -442,7 +442,7 @@ def readInfo(self) -> None:
continue
if block.type == 0:
self.readType0(block)
- elif block.type in (1, 7, 10, 11, 13):
+ elif block.type in {1, 7, 10, 11, 13}:
self.numEntries += 1
elif block.type == 2:
self.numResources += 1
@@ -476,7 +476,7 @@ def readInfo(self) -> None:
for key, value in self.info.items():
if isinstance(value, bytes):
try:
- value = value.decode(encoding)
+ value = value.decode(encoding) # noqa: PLW2901
except Exception:
log.warning(f"failed to decode info value: {key} = {value}")
else:
@@ -520,13 +520,13 @@ def setGlossaryInfo(self) -> None:
# TODO: a bool flag to add empty value infos?
# leave "creationTime" and "lastUpdated" as is
if key == "utf8Encoding":
- key = "bgl_" + key
+ key = "bgl_" + key # noqa: PLW2901
try:
glos.setInfo(key, s_value)
except Exception:
log.exception(f"key = {key}")
- def isEndOfDictData(self) -> bool:
+ def isEndOfDictData(self) -> bool: # noqa: PLR6301
"""
Test for end of dictionary data.
@@ -799,7 +799,7 @@ def __iter__(self) -> "Iterator[EntryType]":
u_defi,
)
- elif block.type in (1, 7, 10, 11, 13):
+ elif block.type in {1, 7, 10, 11, 13}:
pos = 0
# word:
wordData = self.readEntryWord(block, pos)
@@ -1056,7 +1056,8 @@ def readEntry_Type11(
def charReferencesStat(self, b_text: bytes, encoding: str) -> None:
pass
- def decodeCharsetTagsBabylonReference(self, b_text: bytes, b_text2: bytes):
+ @staticmethod
+ def decodeCharsetTagsBabylonReference(b_text: bytes, b_text2: bytes):
b_refs = b_text2.split(b";")
add_text = ""
for i_ref, b_ref in enumerate(b_refs):
diff --git a/pyglossary/plugins/babylon_bgl/bgl_reader_debug.py b/pyglossary/plugins/babylon_bgl/bgl_reader_debug.py
index 2525f1bab..959c68c55 100644
--- a/pyglossary/plugins/babylon_bgl/bgl_reader_debug.py
+++ b/pyglossary/plugins/babylon_bgl/bgl_reader_debug.py
@@ -187,11 +187,11 @@ def open(
self.targetCharsArray = None
if self._raw_dump_path:
- self.rawDumpFile = open(self._raw_dump_path, "w")
+ self.rawDumpFile = open(self._raw_dump_path, "w", encoding="utf-8")
if self._char_samples_path:
- self.samplesDumpFile = open(self._char_samples_path, "w")
+ self.samplesDumpFile = open(self._char_samples_path, "w", encoding="utf-8")
if self._msg_log_path:
- self.msgLogFile = open(self._msg_log_path, "w")
+ self.msgLogFile = open(self._msg_log_path, "w", encoding="utf-8")
self.charRefStatPattern = re.compile(b"(&#\\w+;)", re.IGNORECASE)
@@ -201,10 +201,10 @@ def openGzip(self):
log.error(f"file pointer empty: {bglFile}")
return False
buf = bglFile.read(6)
- if len(buf) < 6 or buf[:4] not in (
+ if len(buf) < 6 or buf[:4] not in {
b"\x12\x34\x00\x01",
b"\x12\x34\x00\x02",
- ):
+ }:
log.error(f"invalid header: {buf[:6]!r}")
return False
self.gzipOffset = gzipOffset = uintFromBytes(buf[4:6])
@@ -376,12 +376,12 @@ def dumpBlocks(self, dumpPath):
break
self.numBlocks += 1
- if block.type in (1, 7, 10, 11, 13):
+ if block.type in {1, 7, 10, 11, 13}:
self.numEntries += 1
elif block.type == 2: # Embedded File (mostly Image or HTML)
metaData.numFiles += 1
- if block.type in (1, 2, 7, 10, 11, 13):
+ if block.type in {1, 2, 7, 10, 11, 13}:
if range_type == block.type:
range_count += 1
else:
diff --git a/pyglossary/plugins/cc_cedict/conv.py b/pyglossary/plugins/cc_cedict/conv.py
index c00d11a7b..a32496bdc 100644
--- a/pyglossary/plugins/cc_cedict/conv.py
+++ b/pyglossary/plugins/cc_cedict/conv.py
@@ -90,7 +90,7 @@ def render_article(
tones.append(tone)
f = BytesIO()
- with ET.htmlfile(f, encoding="utf-8") as hf:
+ with ET.htmlfile(f, encoding="utf-8") as hf: # noqa: PLR1702
with hf.element("div", style="border: 1px solid; padding: 5px"):
with hf.element("div"):
with hf.element("big"):
diff --git a/pyglossary/plugins/cc_cedict/pinyin.py b/pyglossary/plugins/cc_cedict/pinyin.py
index d5d3cf904..d9e10f488 100644
--- a/pyglossary/plugins/cc_cedict/pinyin.py
+++ b/pyglossary/plugins/cc_cedict/pinyin.py
@@ -41,7 +41,7 @@ def convert(word: str) -> "tuple[str, str]":
if tone == "5":
return pinyin, tone
- if tone not in ("1", "2", "3", "4"):
+ if tone not in {"1", "2", "3", "4"}:
return word, ""
for vowel in VOWELS:
diff --git a/pyglossary/plugins/cc_kedict.py b/pyglossary/plugins/cc_kedict.py
index 8f8465719..af18f9dfc 100644
--- a/pyglossary/plugins/cc_kedict.py
+++ b/pyglossary/plugins/cc_kedict.py
@@ -86,14 +86,16 @@ def __init__(
"pref": "prefix",
}
- def isInfoWord(self, _word: str) -> bool:
+ @classmethod
+ def isInfoWord(cls, _word: str) -> bool:
return False
- def fixInfoWord(self, _word: str) -> str:
+ @classmethod
+ def fixInfoWord(cls, _word: str) -> str:
return ""
+ @staticmethod
def _makeList(
- self,
hf: "lxml.etree.htmlfile",
input_objects: "list[Any]",
processor: "Callable",
@@ -117,7 +119,7 @@ def _makeList(
with hf.element("li"):
processor(hf, el, len(input_objects))
- def _processExample(
+ def _processExample( # noqa: PLR6301
self,
hf: "lxml.etree.htmlfile",
exampleDict: "dict",
@@ -170,7 +172,7 @@ def _processDef(
skip_single=False,
)
- def _processNote(
+ def _processNote( # noqa: PLR6301
self,
hf: "lxml.etree.htmlfile",
note: str,
diff --git a/pyglossary/plugins/crawler_dir.py b/pyglossary/plugins/crawler_dir.py
index 1b69c2160..e8c6a17df 100644
--- a/pyglossary/plugins/crawler_dir.py
+++ b/pyglossary/plugins/crawler_dir.py
@@ -68,7 +68,8 @@ def open(self, filename: str) -> None:
if not isdir(filename):
makedirs(filename)
- def filePathFromWord(self, b_word: bytes) -> str:
+ @staticmethod
+ def filePathFromWord(b_word: bytes) -> str:
bw = b_word.lower()
if len(bw) <= 2:
return bw.hex()
@@ -168,7 +169,8 @@ def _fromFile(self, fpath: str) -> "EntryType":
defi = _file.read()
return self._glos.newEntry(words, defi)
- def _listdirSortKey(self, name: str) -> str:
+ @staticmethod
+ def _listdirSortKey(name: str) -> str:
name_nox, ext = splitext(name)
if ext == ".d":
return name
diff --git a/pyglossary/plugins/dicformids.py b/pyglossary/plugins/dicformids.py
index e71202867..a2b633bdb 100644
--- a/pyglossary/plugins/dicformids.py
+++ b/pyglossary/plugins/dicformids.py
@@ -175,7 +175,7 @@ def writeProbs(self) -> None:
self._dirname,
"DictionaryForMIDs.properties",
)
- with open(probsPath, mode="w", newline="\n") as fileObj:
+ with open(probsPath, mode="w", newline="\n", encoding="utf-8") as fileObj:
fileObj.write(
PROP_TEMPLATE.format(
name=glos.getInfo("name"),
diff --git a/pyglossary/plugins/dict_cc.py b/pyglossary/plugins/dict_cc.py
index 36ba9e281..651cc4629 100644
--- a/pyglossary/plugins/dict_cc.py
+++ b/pyglossary/plugins/dict_cc.py
@@ -71,8 +71,8 @@ def __len__(self) -> int:
)
return self._cur.fetchone()[0]
+ @staticmethod
def makeList(
- self,
hf: "T_htmlfile",
input_elements: "list[Element]",
processor: "Callable",
@@ -93,8 +93,8 @@ def makeList(
with hf.element("li"):
processor(hf, el)
+ @staticmethod
def makeGroupsList(
- self,
hf: "T_htmlfile",
groups: "list[tuple[str, str]]",
processor: "Callable[[T_htmlfile, tuple[str, str]], None]",
@@ -115,7 +115,7 @@ def makeGroupsList(
with hf.element("li"):
processor(hf, el)
- def writeSense(
+ def writeSense( # noqa: PLR6301
self,
hf: "T_htmlfile",
row: "tuple[str, str]",
@@ -161,7 +161,7 @@ def iterRows(
log.error(f"html.unescape({term2!r}) -> {e}")
yield term1, term2, row[2]
- def parseGender(self, headword: str) -> "tuple[str | None, str]":
+ def parseGender(self, headword: str) -> "tuple[str | None, str]": # noqa: PLR6301
# {m} masc masculine German: maskulin
# {f} fem feminine German: feminin
# {n} neut neutral German: neutral
@@ -198,11 +198,11 @@ def _iterOneDirection(
from lxml import etree as ET
glos = self._glos
- for headword, groupsOrig in groupby(
+ for headwordEscaped, groupsOrig in groupby(
self.iterRows(column1, column2),
key=itemgetter(0),
):
- headword = html.unescape(headword)
+ headword = html.unescape(headwordEscaped)
groups: "list[tuple[str, str]]" = [
(term2, entry_type) for _, term2, entry_type in groupsOrig
]
diff --git a/pyglossary/plugins/dict_cc_split.py b/pyglossary/plugins/dict_cc_split.py
index 8ac2cf0a0..b3cfaacf8 100644
--- a/pyglossary/plugins/dict_cc_split.py
+++ b/pyglossary/plugins/dict_cc_split.py
@@ -97,7 +97,7 @@ def _iterOneDirection(
) -> "Iterator[EntryType]":
for word, defi, entry_type in self.iterRows(column1, column2):
if entry_type:
- word = f"{word} {{{entry_type}}}"
+ word = f"{word} {{{entry_type}}}" # noqa: PLW2901
yield self._glos.newEntry(word, defi, defiFormat="m")
def __iter__(self) -> "Iterator[EntryType]":
diff --git a/pyglossary/plugins/dictunformat.py b/pyglossary/plugins/dictunformat.py
index 4cf08db2d..19e410183 100644
--- a/pyglossary/plugins/dictunformat.py
+++ b/pyglossary/plugins/dictunformat.py
@@ -46,10 +46,12 @@ class Reader(TextGlossaryReader):
_headword_separator = "; "
# https://github.com/cheusov/dictd/blob/master/dictfmt/dictunformat.in#L14
- def isInfoWord(self, word: str) -> bool:
+ @classmethod
+ def isInfoWord(cls, word: str) -> bool:
return word.startswith("00-database-")
- def fixInfoWord(self, word: str) -> str:
+ @classmethod
+ def fixInfoWord(cls, word: str) -> str:
return word
def setInfo(self, word: str, defi: str) -> None:
diff --git a/pyglossary/plugins/dsl/__init__.py b/pyglossary/plugins/dsl/__init__.py
index c56af7cc3..77fc91244 100644
--- a/pyglossary/plugins/dsl/__init__.py
+++ b/pyglossary/plugins/dsl/__init__.py
@@ -220,7 +220,7 @@ def open(
# read header
for line in self._file:
- line = line.rstrip().lstrip("\ufeff") # noqa: B005
+ line = line.rstrip().lstrip("\ufeff") # noqa: B005, PLW2901
# \ufeff -> https://github.com/ilius/pyglossary/issues/306
if not line:
continue
@@ -270,7 +270,8 @@ def _iterLines(self) -> "Iterator[str]":
for line in self._file:
yield line
- def sub_title_line(self, m: "re.Match") -> str:
+ @staticmethod
+ def sub_title_line(m: "re.Match") -> str:
line = m.group(0)[1:-1]
line = line.replace("[']", "") # FIXME
line = line.replace("[/']", "")
diff --git a/pyglossary/plugins/dsl/lex.py b/pyglossary/plugins/dsl/lex.py
index c6215978d..dedafee06 100644
--- a/pyglossary/plugins/dsl/lex.py
+++ b/pyglossary/plugins/dsl/lex.py
@@ -155,7 +155,7 @@ def processTagClose(tr: TransformerType, tag: str) -> tuple[LexType, ErrorType]:
tr.output += ""
elif tag == "b":
tr.output += ""
- elif tag in ("u", "'"):
+ elif tag in {"u", "'"}:
tr.output += ""
elif tag == "i":
tr.output += ""
@@ -163,7 +163,7 @@ def processTagClose(tr: TransformerType, tag: str) -> tuple[LexType, ErrorType]:
tr.output += ""
elif tag == "sub":
tr.output += ""
- elif tag in ("c", "t"):
+ elif tag in {"c", "t"}:
tr.output += ""
elif tag == "p":
tr.output += ""
@@ -171,7 +171,7 @@ def processTagClose(tr: TransformerType, tag: str) -> tuple[LexType, ErrorType]:
tr.output += ""
elif tag == "ex":
tr.output += ""
- elif tag in (
+ elif tag in {
"ref",
"url",
"s",
@@ -181,7 +181,7 @@ def processTagClose(tr: TransformerType, tag: str) -> tuple[LexType, ErrorType]:
"!trs",
"lang",
"com",
- ):
+ }:
pass
else:
log.warning(f"unknown close tag {tag!r}")
@@ -296,7 +296,7 @@ def lexS(tr: TransformerType) -> tuple[LexType, ErrorType]:
_, ext = splitext(fname)
ext = ext.lstrip(".")
- if ext in ("wav", "mp3"):
+ if ext in {"wav", "mp3"}:
if tr.audio:
tr.output += (
rf'"
)
- elif ext in ("jpg", "jpeg", "gif", "tif", "tiff", "png", "bmp"):
+ elif ext in {"jpg", "jpeg", "gif", "tif", "tiff", "png", "bmp"}:
tr.output += rf'
'
else:
log.warning(f"unknown file extension in {fname!r}")
@@ -315,7 +315,7 @@ def lexS(tr: TransformerType) -> tuple[LexType, ErrorType]:
return lexRoot, None
-def processTagM(tr: TransformerType, tag: str):
+def processTagM(tr: TransformerType, tag: str) -> None:
padding = "0.3"
if len(tag) > 1:
padding = tag[1:]
@@ -324,7 +324,7 @@ def processTagM(tr: TransformerType, tag: str):
tr.output += f''
-def processTagC(tr: TransformerType):
+def processTagC(tr: TransformerType) -> None:
color = "green"
for key, value in tr.attrs.items():
if value is None:
@@ -379,14 +379,14 @@ def processTag(tr: TransformerType, tag: str) -> tuple[LexType, ErrorType]:
tr.output += ""
elif tag == "sub":
tr.output += ""
- elif tag in (
+ elif tag in {
"trn",
"!trn",
"trs",
"!trs",
"lang",
"com",
- ):
+ }:
pass
else:
log.warning(f"unknown tag {tag!r}")
diff --git a/pyglossary/plugins/ebook_kobo.py b/pyglossary/plugins/ebook_kobo.py
index c872f2ddb..1812081b1 100644
--- a/pyglossary/plugins/ebook_kobo.py
+++ b/pyglossary/plugins/ebook_kobo.py
@@ -99,7 +99,7 @@ def is_cyrillic_char(c: str) -> bool:
# U+FE2E, U+FE2F: Combining Half Marks
# U+1D2B, U+1D78: Phonetic Extensions
- return c in ("\uFE2E", "\uFE2F", "\u1D2B", "\u1D78")
+ return c in {"\uFE2E", "\uFE2F", "\u1D2B", "\u1D78"}
def fixFilename(fname: str) -> str:
@@ -113,7 +113,8 @@ class Writer:
"marisa_trie": "marisa-trie",
}
- def stripFullHtmlError(self, entry: "EntryType", error: str) -> None:
+ @staticmethod
+ def stripFullHtmlError(entry: "EntryType", error: str) -> None:
log.error(f"error in stripFullHtml: {error}, words={entry.l_word!r}")
def __init__(self, glos: "GlossaryType") -> None:
@@ -127,7 +128,7 @@ def __init__(self, glos: "GlossaryType") -> None:
# img tag has no closing
glos.stripFullHtml(errorHandler=self.stripFullHtmlError)
- def get_prefix(self, word: str) -> str:
+ def get_prefix(self, word: str) -> str: # noqa: PLR6301
if not word:
return "11"
wo = word[:2].strip().lower()
diff --git a/pyglossary/plugins/ebook_kobo_dictfile.py b/pyglossary/plugins/ebook_kobo_dictfile.py
index aa0c810bf..7d46512c3 100644
--- a/pyglossary/plugins/ebook_kobo_dictfile.py
+++ b/pyglossary/plugins/ebook_kobo_dictfile.py
@@ -104,10 +104,12 @@ def open(self, filename: str) -> None:
TextGlossaryReader.open(self, filename)
self._glos.setDefaultDefiFormat("h")
- def isInfoWord(self, _word: str) -> bool:
+ @classmethod
+ def isInfoWord(cls, _word: str) -> bool:
return False
- def fixInfoWord(self, _word: str) -> str:
+ @classmethod
+ def fixInfoWord(cls, _word: str) -> str:
raise NotImplementedError
def fixDefi(
@@ -181,7 +183,8 @@ def nextBlock(
class Writer:
_encoding: str = "utf-8"
- def stripFullHtmlError(self, entry: "EntryType", error: str) -> None:
+ @staticmethod
+ def stripFullHtmlError(entry: "EntryType", error: str) -> None:
log.error(f"error in stripFullHtml: {error}, words={entry.l_word!r}")
def __init__(self, glos: GlossaryType) -> None:
diff --git a/pyglossary/plugins/ebook_mobi.py b/pyglossary/plugins/ebook_mobi.py
index 639f3168d..2c016a5a0 100644
--- a/pyglossary/plugins/ebook_mobi.py
+++ b/pyglossary/plugins/ebook_mobi.py
@@ -289,7 +289,8 @@ def format_group_content(
infl=infl,
)
- def getLangCode(self, lang: "Lang | None") -> str:
+ @staticmethod
+ def getLangCode(lang: "Lang | None") -> str:
return lang.code if isinstance(lang, Lang) else ""
def get_opf_contents(
diff --git a/pyglossary/plugins/edlin.py b/pyglossary/plugins/edlin.py
index 776fcdbc0..003673843 100644
--- a/pyglossary/plugins/edlin.py
+++ b/pyglossary/plugins/edlin.py
@@ -211,7 +211,8 @@ def _clear(self) -> None:
self._hashSet: "set[str]" = set()
# self._wordCount = None
- def hashToPath(self, h: str) -> str:
+ @staticmethod
+ def hashToPath(h: str) -> str:
return h[:2] + "/" + h[2:]
def getEntryHash(self, entry: EntryType) -> str:
diff --git a/pyglossary/plugins/freedict.py b/pyglossary/plugins/freedict.py
index 41d3dc5e7..6bf496228 100644
--- a/pyglossary/plugins/freedict.py
+++ b/pyglossary/plugins/freedict.py
@@ -155,8 +155,8 @@ class Reader:
}
gramClass = "grammar"
+ @staticmethod
def makeList(
- self,
hf: "T_htmlfile",
input_objects: "list[Any]",
processor: "Callable",
@@ -184,13 +184,14 @@ def makeList(
with hf.element("li"):
processor(hf, el)
- def getTitleTag(self, sample: str) -> str:
+ @staticmethod
+ def getTitleTag(sample: str) -> str:
ws = getWritingSystemFromText(sample)
if ws:
return ws.titleTag
return "b"
- def writeRef(
+ def writeRef( # noqa: PLR6301
self,
hf: "T_htmlfile",
ref: "Element",
@@ -223,7 +224,7 @@ def writeTransCit(
sense = ET.Element(f"{tei}sense")
for child in elem.xpath("child::node()"):
if isinstance(child, str):
- child = child.strip()
+ child = child.strip() # noqa: PLW2901
if child:
hf.write(child)
log.warning("text directly inside ")
@@ -236,7 +237,7 @@ def writeTransCit(
quotes.append(child)
continue
- if child.tag in (f"{tei}gramGrp", f"{tei}usg", f"{tei}note"):
+ if child.tag in {f"{tei}gramGrp", f"{tei}usg", f"{tei}note"}:
sense.append(child)
continue
@@ -425,9 +426,9 @@ def writeSenseSense(
_type = child.attrib.get("type")
if not _type:
noteList.append(child)
- elif _type in ("pos", "gram"):
+ elif _type in {"pos", "gram"}:
gramList.append(child)
- elif _type in (
+ elif _type in {
"sense",
"stagr",
"stagk",
@@ -440,7 +441,7 @@ def writeSenseSense(
"infl",
"obj",
"lbl",
- ):
+ }:
noteList.append(child)
else:
log.warning(f"unknown note type {_type}")
@@ -462,7 +463,7 @@ def writeSenseSense(
self.writeLangTag(hf, child)
continue
- if child.tag in (f"{tei}sense", f"{tei}gramGrp"):
+ if child.tag in {f"{tei}sense", f"{tei}gramGrp"}:
continue
if child.tag == f"{tei}xr":
@@ -649,7 +650,7 @@ def normalizeGramGrpChild(self, elem: "Element") -> str:
return self.posMapping.get(text.lower(), text)
if tag == f"{tei}gen":
return self.genderMapping.get(text.lower(), text)
- if tag in (f"{tei}num", f"{tei}number"):
+ if tag in {f"{tei}num", f"{tei}number"}:
return self.numberMapping.get(text.lower(), text)
if tag == f"{tei}subc":
return self.subcMapping.get(text.lower(), text)
@@ -660,7 +661,7 @@ def normalizeGramGrpChild(self, elem: "Element") -> str:
return self.posMapping.get(text.lower(), text)
if _type == "gen":
return self.genderMapping.get(text.lower(), text)
- if _type in ("num", "number"):
+ if _type in {"num", "number"}:
return self.numberMapping.get(text.lower(), text)
if _type == "subc":
return self.subcMapping.get(text.lower(), text)
@@ -776,7 +777,8 @@ def setWordCount(self, header: "Element") -> None:
except Exception:
log.exception(f"unexpected {extent=}")
- def tostring(self, elem: "Element") -> str:
+ @staticmethod
+ def tostring(elem: "Element") -> str:
from lxml import etree as ET
return (
@@ -801,7 +803,7 @@ def stripParagList(
lines = []
for elem in elems:
for line in self.stripParag(elem).split("\n"):
- line = line.strip()
+ line = line.strip() # noqa: PLW2901
if not line:
continue
lines.append(line)
diff --git a/pyglossary/plugins/gettext_po.py b/pyglossary/plugins/gettext_po.py
index b0e3e345c..2f3162f3b 100644
--- a/pyglossary/plugins/gettext_po.py
+++ b/pyglossary/plugins/gettext_po.py
@@ -68,7 +68,7 @@ def clear(self) -> None:
def open(self, filename: str) -> None:
self._filename = filename
- self._file = open(filename)
+ self._file = open(filename, encoding="utf-8")
self._resDir = filename + "_res"
if isdir(self._resDir):
self._resFileNames = os.listdir(self._resDir)
@@ -106,7 +106,7 @@ def __iter__(self) -> "Iterator[EntryType]":
msgstr = False
wordCount = 0
for line in _file:
- line = line.strip()
+ line = line.strip() # noqa: PLW2901
if not line:
continue
if line.startswith("#"):
@@ -128,11 +128,10 @@ def __iter__(self) -> "Iterator[EntryType]":
log.error("msgid omitted!")
defi = po_unescape(line[7:])
msgstr = True
+ elif msgstr:
+ defi += po_unescape(line)
else:
- if msgstr:
- defi += po_unescape(line)
- else:
- word += po_unescape(line)
+ word += po_unescape(line)
if word:
yield self._glos.newEntry(word, defi)
wordCount += 1
diff --git a/pyglossary/plugins/html_dir.py b/pyglossary/plugins/html_dir.py
index 289a4da23..33dd3359f 100644
--- a/pyglossary/plugins/html_dir.py
+++ b/pyglossary/plugins/html_dir.py
@@ -110,7 +110,8 @@ class Writer:
_css: str = ""
_word_title: bool = True
- def stripFullHtmlError(self, entry: "EntryType", error: str) -> None:
+ @staticmethod
+ def stripFullHtmlError(entry: "EntryType", error: str) -> None:
log.error(f"error in stripFullHtml: {error}, words={entry.l_word!r}")
def __init__(self, glos: GlossaryType) -> None:
@@ -174,7 +175,7 @@ def fixLinks(self, linkTargetSet: "set[str]") -> None:
fileByWord: "dict[str, list[tuple[str, int]]]" = {}
for line in open(join(dirn, "index.txt"), encoding="utf-8"):
- line = line.rstrip("\n")
+ line = line.rstrip("\n") # noqa: PLW2901
if not line:
continue
entryIndexStr, wordEsc, filename, _ = line.split("\t")
@@ -201,7 +202,7 @@ def getLinksByFile(fileIndex: int) -> "io.TextIOBase":
log.info("")
for line in open(join(dirn, "links.txt"), encoding="utf-8"):
- line = line.rstrip("\n")
+ line = line.rstrip("\n") # noqa: PLW2901
if not line:
continue
target, fileIndexStr, x_start, x_size = line.split("\t")
@@ -240,8 +241,11 @@ def getLinksByFile(fileIndex: int) -> "io.TextIOBase":
with open(join(dirn, f"{filename}.new"), mode="wb") as outFile:
for linkLine in open(join(dirn, f"links{fileIndex}"), "rb"):
outFile.flush()
- linkLine = linkLine.rstrip(b"\n")
- b_x_start, b_x_size, b_target = linkLine.split(b"\t")
+ (
+ b_x_start,
+ b_x_size,
+ b_target,
+ ) = linkLine.rstrip(b"\n").split(b"\t")
outFile.write(
inFile.read(
int(b_x_start, 16) - inFile.tell(),
@@ -314,7 +318,8 @@ def writeInfo(self, filename: str, header: str) -> None:
)
_file.write("")
- def _subResSrc(self, m: "re.Match") -> str:
+ @staticmethod
+ def _subResSrc(m: "re.Match") -> str:
url = m.group(1)
if "://" in url:
return m.group(0)
diff --git a/pyglossary/plugins/info_plugin.py b/pyglossary/plugins/info_plugin.py
index 874ad74c4..af1be9a2d 100644
--- a/pyglossary/plugins/info_plugin.py
+++ b/pyglossary/plugins/info_plugin.py
@@ -119,11 +119,9 @@ def write(self) -> "Generator[None, EntryType, None]":
elif defiFormat == "h":
match = re_possible_html.search(defi)
if match is not None:
- tag = match.group().strip("< />").lower()
- firstTagCounter[tag] += 1
+ firstTagCounter[match.group().strip("< />").lower()] += 1
for tag in re_possible_html.findall(defi):
- tag = tag.strip("< />").lower()
- allTagsCounter[tag] += 1
+ allTagsCounter[tag.strip("< />").lower()] += 1
elif defiFormat == "b":
_filenameNoExt, ext = splitext(entry.s_word)
ext = ext.lstrip(".")
diff --git a/pyglossary/plugins/iupac_goldbook.py b/pyglossary/plugins/iupac_goldbook.py
index fe02eaa63..da1e5f0aa 100644
--- a/pyglossary/plugins/iupac_goldbook.py
+++ b/pyglossary/plugins/iupac_goldbook.py
@@ -141,8 +141,8 @@ def setMetadata(self, header: "Element") -> None:
if accessdate:
self.setGlosInfo("creationTime", accessdate.text)
+ @staticmethod
def tostring(
- self,
elem: "Element",
) -> str:
from lxml import etree as ET
@@ -157,7 +157,8 @@ def tostring(
.strip()
)
- def innerXML(self, elem: "Element") -> str:
+ @staticmethod
+ def innerXML(elem: "Element") -> str:
from lxml import etree as ET
elemName = elem.xpath("name(/*)")
@@ -170,7 +171,7 @@ def innerXML(self, elem: "Element") -> str:
return resultStr
- def getTerm(self, termE: "Element") -> str:
+ def getTerm(self, termE: "Element") -> str: # noqa: PLR6301
from lxml import etree as ET
term = (
@@ -200,7 +201,7 @@ def __iter__(self) -> "Iterator[EntryType]":
events=("end",),
tag="entry",
)
- for _, elem in context:
+ for _, elem in context: # noqa: PLR1702
codeE = elem.find("./code")
if codeE is None:
continue
diff --git a/pyglossary/plugins/jmdict.py b/pyglossary/plugins/jmdict.py
index 3a79d85bf..918a85eea 100644
--- a/pyglossary/plugins/jmdict.py
+++ b/pyglossary/plugins/jmdict.py
@@ -97,8 +97,8 @@ class Reader:
"word containing irregular kana usage": "irregular",
}
+ @staticmethod
def makeList(
- self,
hf: "T_htmlfile",
input_objects: "list[Element]",
processor: "Callable",
@@ -205,7 +205,8 @@ def br() -> "Element":
hf.write(br())
examples = sense.findall("example")
- if examples:
+ # TODO: move to a method
+ if examples: # noqa: PLR1702
with hf.element(
"div",
attrib={
@@ -257,7 +258,7 @@ def getEntryByElem(
def br() -> "Element":
return ET.Element("br")
- with ET.htmlfile(f, encoding="utf-8") as hf:
+ with ET.htmlfile(f, encoding="utf-8") as hf: # noqa: PLR1702
kebList: "list[str]" = []
rebList: "list[str]" = []
kebDisplayList: "list[str]" = []
@@ -365,10 +366,8 @@ def br() -> "Element":
byteProgress=byteProgress,
)
- def tostring(
- self,
- elem: "Element",
- ) -> str:
+ @staticmethod
+ def tostring(elem: "Element") -> str:
from lxml import etree as ET
return (
diff --git a/pyglossary/plugins/jmnedict.py b/pyglossary/plugins/jmnedict.py
index 3ebbeb2fa..167614a6e 100644
--- a/pyglossary/plugins/jmnedict.py
+++ b/pyglossary/plugins/jmnedict.py
@@ -75,8 +75,8 @@ class Reader:
"word containing irregular kana usage": "irregular",
}
+ @staticmethod
def makeList(
- self,
hf: "T_htmlfile",
input_objects: "list[Element]",
processor: "Callable",
@@ -153,7 +153,7 @@ def getEntryByElem(
def br() -> "Element":
return ET.Element("br")
- with ET.htmlfile(f, encoding="utf-8") as hf:
+ with ET.htmlfile(f, encoding="utf-8") as hf: # noqa: PLR1702
kebList: "list[str]" = []
rebList: "list[tuple[str, list[str]]]" = []
with hf.element("div"):
@@ -236,10 +236,8 @@ def br() -> "Element":
byteProgress=byteProgress,
)
- def tostring(
- self,
- elem: "Element",
- ) -> str:
+ @staticmethod
+ def tostring(elem: "Element") -> str:
from lxml import etree as ET
return (
diff --git a/pyglossary/plugins/lingoes_ldf.py b/pyglossary/plugins/lingoes_ldf.py
index a48efb4e8..0ced54e2a 100644
--- a/pyglossary/plugins/lingoes_ldf.py
+++ b/pyglossary/plugins/lingoes_ldf.py
@@ -69,13 +69,15 @@ def __len__(self) -> int:
)
return self._wordCount
- def isInfoWord(self, word: str) -> bool:
+ @classmethod
+ def isInfoWord(cls, word: str) -> bool:
if isinstance(word, str):
return word.startswith("#")
return False
- def fixInfoWord(self, word: str) -> str:
+ @classmethod
+ def fixInfoWord(cls, word: str) -> str:
if isinstance(word, str):
return word.lstrip("#").lower()
diff --git a/pyglossary/plugins/octopus_mdict_new/__init__.py b/pyglossary/plugins/octopus_mdict_new/__init__.py
index fd4bd7691..90d25324b 100644
--- a/pyglossary/plugins/octopus_mdict_new/__init__.py
+++ b/pyglossary/plugins/octopus_mdict_new/__init__.py
@@ -245,7 +245,7 @@ def __iter__(self) -> "Iterator[EntryType]":
dirPath = dirname(self._filename)
for fname in os.listdir(dirPath):
ext = splitext(fname)[1].lower()
- if ext in (".mdx", ".mdd"):
+ if ext in {".mdx", ".mdd"}:
continue
fpath = join(dirPath, fname)
if not isfile(fpath):
diff --git a/pyglossary/plugins/quickdic6.py b/pyglossary/plugins/quickdic6.py
index 25f86c5ff..41fb49d93 100644
--- a/pyglossary/plugins/quickdic6.py
+++ b/pyglossary/plugins/quickdic6.py
@@ -452,7 +452,7 @@ def write_entry_indexentry(
entry: IndexEntryType,
) -> None:
token, start_index, count, token_norm, html_indices = entry
- has_normalized = token_norm != ""
+ has_normalized = bool(token_norm)
write_string(fp, token)
write_int(fp, start_index)
write_int(fp, count)
@@ -509,7 +509,8 @@ def _compare_without_dash(
s2 = self._without_dash(b)
return self._comparator.compare(s1, s2)
- def _without_dash(self, a: str) -> str:
+ @staticmethod
+ def _without_dash(a: str) -> str:
return a.replace("-", "").replace("þ", "th").replace("Þ", "Th")
@@ -603,7 +604,7 @@ def add_index(
tokens = [
(t, comparator.normalize(t), ttype, tidx)
for t, ttype, tidx in tokens1
- if t != ""
+ if t
]
if len(synonyms) > 0:
@@ -616,7 +617,7 @@ def add_index(
for t in tokens
if t[0] in synonyms
for s in synonyms[t[0]]
- if s != ""
+ if s
],
)
@@ -631,26 +632,25 @@ def add_index(
prev_token = "" if len(index_entries) == 0 else index_entries[-1][0]
if prev_token == token:
(
- token,
+ token, # noqa: PLW2901
index_start,
count,
- token_norm,
+ token_norm, # noqa: PLW2901
html_indices,
) = index_entries.pop()
else:
i_entry = len(index_entries)
index_start = len(rows)
count = 0
- token_norm = "" if token == token_norm else token_norm
+ token_norm = "" if token == token_norm else token_norm # noqa: PLW2901
html_indices = []
rows.append((1, i_entry))
if ttype == 4:
if tidx not in html_indices:
html_indices.append(tidx)
- else:
- if (ttype, tidx) not in rows[index_start + 1 :]:
- rows.append((ttype, tidx))
- count += 1
+ elif (ttype, tidx) not in rows[index_start + 1 :]:
+ rows.append((ttype, tidx))
+ count += 1
index_entries.append(
(token, index_start, count, token_norm, html_indices),
)
@@ -723,7 +723,7 @@ def _extract_synonyms_from_indices(self) -> None:
if entry_id not in self._synonyms:
self._synonyms[entry_id] = set()
self._synonyms[entry_id].add(token)
- if token_norm != "":
+ if token_norm:
self._synonyms[entry_id].add(token_norm)
def _extract_rows_from_indexentry(
@@ -737,11 +737,11 @@ def _extract_rows_from_indexentry(
_, _, _, _, _, _, index_entries, _, rows = index
token, start_index, count, _, html_indices = index_entries[i_entry]
block_rows = rows[start_index : start_index + count + 1]
- assert block_rows[0][0] in (1, 3)
+ assert block_rows[0][0] in {1, 3}
assert block_rows[0][1] == i_entry
e_rows = []
for entry_type, entry_idx in block_rows[1:]:
- if entry_type in (1, 3):
+ if entry_type in {1, 3}:
# avoid an endless recursion
if entry_idx not in recurse:
e_rows.extend(
@@ -825,7 +825,7 @@ def write(self) -> "typing.Generator[None, EntryType, None]":
continue
entry.detectDefiFormat()
- if entry.defiFormat not in ("h", "m"):
+ if entry.defiFormat not in {"h", "m"}:
log.error(f"Unsupported defiFormat={entry.defiFormat}, assuming 'h'")
words = entry.l_word
@@ -841,17 +841,17 @@ def write(self) -> "typing.Generator[None, EntryType, None]":
log.info("Collecting meta data ...")
name = self._glos.getInfo("bookname")
- if name == "":
+ if not name:
name = self._glos.getInfo("description")
sourceLang = (
self._glos.sourceLang
- if self._source_lang == ""
+ if not self._source_lang
else langDict[self._source_lang]
)
targetLang = (
self._glos.targetLang
- if self._target_lang == ""
+ if not self._target_lang
else langDict[self._target_lang]
)
if sourceLang and targetLang:
@@ -872,7 +872,7 @@ def write(self) -> "typing.Generator[None, EntryType, None]":
short_name = long_name = iso = sourceLang
normalizer_rules = (
self._normalizer_rules
- if self._normalizer_rules != ""
+ if self._normalizer_rules
else ":: Lower; 'ae' > 'ä'; 'oe' > 'ö'; 'ue' > 'ü'; 'ß' > 'ss'; "
if iso == "DE"
else ":: Any-Latin; ' ' > ; :: Lower; :: NFD;"
diff --git a/pyglossary/plugins/sql.py b/pyglossary/plugins/sql.py
index 11ba5a112..852ed002b 100644
--- a/pyglossary/plugins/sql.py
+++ b/pyglossary/plugins/sql.py
@@ -120,11 +120,11 @@ def _writeInfo(self) -> None:
if self._add_extra_info:
extraInfo = glos.getExtraInfos(info_keys)
for index, (key, value) in enumerate(extraInfo.items()):
- key = key.replace("'", "''")
- value = value.replace("'", "''")
+ key2 = key.replace("'", "''")
+ value2 = value.replace("'", "''")
fileObj.write(
f"INSERT INTO dbinfo_extra VALUES({index + 1}, "
- f"'{key}', '{value}');\n",
+ f"'{key2}', '{value2}');\n",
)
def _getInfoKeys(self) -> "list[str]":
@@ -168,9 +168,8 @@ def fixStr(word: str) -> str:
f"INSERT INTO word VALUES({_id}, '{word}', '{defi}');\n",
)
for alt in words[1:]:
- alt = fixStr(alt)
fileObj.write(
- f"INSERT INTO alt VALUES({_id}, '{alt}');\n",
+ f"INSERT INTO alt VALUES({_id}, '{fixStr(alt)}');\n",
)
_id += 1
diff --git a/pyglossary/plugins/stardict.py b/pyglossary/plugins/stardict.py
index 4122e3592..0c8145aef 100644
--- a/pyglossary/plugins/stardict.py
+++ b/pyglossary/plugins/stardict.py
@@ -167,11 +167,11 @@ def transformByInnerString(self, text: str) -> str:
...
-T_SDListItem = TypeVar("T_SDListItem", contravariant=True)
+T_SDListItem_contra = TypeVar("T_SDListItem_contra", contravariant=True)
-class T_SdList(Protocol[T_SDListItem]):
- def append(self, x: T_SDListItem) -> None:
+class T_SdList(Protocol[T_SDListItem_contra]):
+ def append(self, x: T_SDListItem_contra) -> None:
...
def __len__(self) -> int:
@@ -197,7 +197,7 @@ def __len__(self) -> int:
def __iter__(self) -> "Iterator[Any]":
return iter(self._l)
- def sortKey(self, item: "tuple[bytes, Any]") -> "tuple[bytes, bytes]":
+ def sortKey(self, item: "tuple[bytes, Any]") -> "tuple[bytes, bytes]": # noqa: PLR6301
return (
item[0].lower(),
item[0],
@@ -246,7 +246,8 @@ def __init__(
)
self._con.commit()
- def getExtraColumns(self) -> "list[tuple[str, str]]":
+ @classmethod
+ def getExtraColumns(cls) -> "list[tuple[str, str]]":
# list[(columnName, dataType)]
return []
@@ -293,7 +294,8 @@ def __iter__(self) -> "Iterator[EntryType]":
class IdxSqList(BaseSqList):
- def getExtraColumns(self) -> "list[tuple[str, str]]":
+ @classmethod
+ def getExtraColumns(cls) -> "list[tuple[str, str]]":
# list[(columnName, dataType)]
return [
("idx_block", "BLOB"),
@@ -301,7 +303,8 @@ def getExtraColumns(self) -> "list[tuple[str, str]]":
class SynSqList(BaseSqList):
- def getExtraColumns(self) -> "list[tuple[str, str]]":
+ @classmethod
+ def getExtraColumns(cls) -> "list[tuple[str, str]]":
# list[(columnName, dataType)]
return [
("entry_index", "INTEGER"),
@@ -407,7 +410,7 @@ def readIfoFile(self) -> None:
mode="rb",
) as ifoFile:
for line in ifoFile:
- line = line.strip()
+ line = line.strip() # noqa: PLW2901
if not line:
continue
if line == b"StarDict's dict ifo file":
@@ -682,8 +685,8 @@ def readSynFile(self) -> "dict[int, list[str]]":
return synDict
+ @staticmethod
def parseDefiBlockCompact(
- self,
b_block: bytes,
sametypesequence: str,
) -> "list[tuple[bytes, int]] | None":
@@ -733,8 +736,8 @@ def parseDefiBlockCompact(
return res
+ @staticmethod
def parseDefiBlockGeneral(
- self,
b_block: bytes,
) -> "list[tuple[bytes, int]] | None":
"""
@@ -858,11 +861,10 @@ def write(self) -> "Generator[None, EntryType, None]":
yield from self.writeCompactMergeSyns(self._sametypesequence)
else:
yield from self.writeCompact(self._sametypesequence)
+ elif self._merge_syns:
+ yield from self.writeGeneralMergeSyns()
else:
- if self._merge_syns:
- yield from self.writeGeneralMergeSyns()
- else:
- yield from self.writeGeneral()
+ yield from self.writeGeneral()
if self._dictzip:
runDictzip(f"{self._filename}.dict")
syn_file = f"{self._filename}.syn"
@@ -1018,7 +1020,7 @@ def writeGeneral(self) -> "Generator[None, EntryType, None]":
entry.detectDefiFormat() # call no more than once
defiFormat = entry.defiFormat
defiFormatCounter[defiFormat] += 1
- if defiFormat not in ("h", "m", "x"):
+ if defiFormat not in {"h", "m", "x"}:
log.error(f"invalid {defiFormat=}, using 'm'")
defiFormat = "m"
@@ -1199,7 +1201,7 @@ def writeGeneralMergeSyns(self) -> "Generator[None, EntryType, None]":
entry.detectDefiFormat() # call no more than once
defiFormat = entry.defiFormat
defiFormatCounter[defiFormat] += 1
- if defiFormat not in ("h", "m", "x"):
+ if defiFormat not in {"h", "m", "x"}:
log.error(f"invalid {defiFormat=}, using 'm'")
defiFormat = "m"
@@ -1301,13 +1303,13 @@ def writeIfoFile(
desc = f"Publisher: {publisher}\n{desc}"
for key in infoKeys:
- if key in (
+ if key in {
"bookname",
"description",
- ):
+ }:
continue
value = glos.getInfo(key)
- if value == "":
+ if not value:
continue
value = newlinesToSpace(value)
ifo.append((key, value))
diff --git a/pyglossary/plugins/stardict_textual.py b/pyglossary/plugins/stardict_textual.py
index eecfd6019..09a880675 100644
--- a/pyglossary/plugins/stardict_textual.py
+++ b/pyglossary/plugins/stardict_textual.py
@@ -212,7 +212,7 @@ def __iter__(self) -> "Iterator[EntryType]":
for child in elem.getchildren():
if not child.text:
continue
- if child.tag in ("key", "synonym"):
+ if child.tag in {"key", "synonym"}:
words.append(child.text)
elif child.tag == "definition":
_type = child.attrib.get("type", "")
diff --git a/pyglossary/plugins/tabfile.py b/pyglossary/plugins/tabfile.py
index ed919ab03..6bfccf858 100644
--- a/pyglossary/plugins/tabfile.py
+++ b/pyglossary/plugins/tabfile.py
@@ -75,10 +75,12 @@ def __iter__(self) -> "Iterator[EntryType | None]":
_file.read(),
)
- def isInfoWord(self, word: str) -> bool:
+ @classmethod
+ def isInfoWord(cls, word: str) -> bool:
return word.startswith("#")
- def fixInfoWord(self, word: str) -> str:
+ @classmethod
+ def fixInfoWord(cls, word: str) -> str:
return word.lstrip("#")
def nextBlock(self) -> "tuple[str | list[str], str, None] | None":
diff --git a/pyglossary/plugins/wiktextract.py b/pyglossary/plugins/wiktextract.py
index a3a846922..542f2831a 100644
--- a/pyglossary/plugins/wiktextract.py
+++ b/pyglossary/plugins/wiktextract.py
@@ -18,7 +18,6 @@
from pyglossary.core import log, pip
from pyglossary.glossary_types import EntryType, GlossaryType
from pyglossary.io_utils import nullBinaryIO
-from pyglossary.langs.writing_system import getWritingSystemFromText
from pyglossary.option import (
BoolOption,
ListOption,
@@ -317,14 +316,14 @@ def writeSenseList(
self.writeSense,
)
- def writeSenseGloss(
+ def writeSenseGloss( # noqa: PLR6301
self,
hf: "T_htmlfile",
text: "str | None",
) -> None:
hf.write(text or "")
- def writeSenseCategory(
+ def writeSenseCategory( # noqa: PLR6301
self,
hf: "T_htmlfile",
category: "dict[str, Any]",
@@ -353,7 +352,7 @@ def writeSenseCategories(
hf.write("Categories: ")
self.makeList(hf, categories, self.writeSenseCategory)
- def writeSenseExample(
+ def writeSenseExample( # noqa: PLR6301
self,
hf: "T_htmlfile",
example: "dict[str, str]",
@@ -392,7 +391,7 @@ def writeSenseExamples(
):
self.writeSenseExample(hf, example)
- def writeSenseFormOf(
+ def writeSenseFormOf( # noqa: PLR6301
self,
hf: "T_htmlfile",
form_of: "dict[str, str]",
@@ -458,7 +457,7 @@ def writeTopics(
with hf.element("span", style=self.topicStyle):
hf.write(topic)
- def addWordLink(
+ def addWordLink( # noqa: PLR6301
self,
hf: "T_htmlfile",
word: str,
@@ -624,8 +623,8 @@ def writeSense(
hf.write(ET.Element("br"))
+ @staticmethod
def makeList(
- self,
hf: "T_htmlfile",
input_objects: "list[Any]",
processor: "Callable",
@@ -652,9 +651,3 @@ def makeList(
for el in input_objects:
with hf.element("li"):
processor(hf, el)
-
- def getTitleTag(self, sample: str) -> str:
- ws = getWritingSystemFromText(sample)
- if ws:
- return ws.titleTag
- return "b"
diff --git a/pyglossary/plugins/wordnet.py b/pyglossary/plugins/wordnet.py
index 32774ffb4..3eb83bd71 100644
--- a/pyglossary/plugins/wordnet.py
+++ b/pyglossary/plugins/wordnet.py
@@ -216,11 +216,12 @@ def __init__(self, wordnetdir: str) -> None:
self.wordnetdir = wordnetdir
self.collector: "dict[str, list[str]]" = defaultdict(list)
- def iterlines(self, dict_dir: str) -> Iterator[str]:
+ @staticmethod
+ def iterlines(dict_dir: str) -> Iterator[str]:
for name in os.listdir(dict_dir):
if not name.startswith("data."):
continue
- with open(os.path.join(dict_dir, name)) as f:
+ with open(os.path.join(dict_dir, name), encoding="utf-8") as f:
for line in f:
if not line.startswith(" "):
yield line
@@ -234,18 +235,18 @@ def prepare(self) -> None:
files: dict[str, io.TextIOWrapper] = {}
for name in os.listdir(dict_dir):
if name.startswith("data.") and name in file2pos:
- f = open(os.path.join(dict_dir, name)) # noqa: SIM115
+ f = open(os.path.join(dict_dir, name), encoding="utf-8") # noqa: SIM115
for key in file2pos[name]:
files[key] = f
def a(word: str) -> str:
return f'{word}'
- for i, line in enumerate(self.iterlines(dict_dir)):
- if i % 100 == 0 and i > 0:
+ for index, line in enumerate(self.iterlines(dict_dir)):
+ if index % 100 == 0 and index > 0:
sys.stdout.write(".")
sys.stdout.flush()
- if i % 5000 == 0 and i > 0:
+ if index % 5000 == 0 and index > 0:
sys.stdout.write("\n")
sys.stdout.flush()
if not line or not line.strip():
@@ -261,7 +262,7 @@ def a(word: str) -> str:
)
words = synset.words
- for i, word in enumerate(words):
+ for index2, word in enumerate(words):
# TODO: move this block to a func
synonyms = ", ".join(a(w) for w in words if w != word)
synonyms_str = (
@@ -271,10 +272,14 @@ def a(word: str) -> str:
)
pointers = defaultdict(list)
for pointer in synset.pointers:
- if pointer.source and pointer.target and pointer.source - 1 != i:
+ if (
+ pointer.source and
+ pointer.target and
+ pointer.source - 1 != index2
+ ):
continue
symbol = pointer.symbol
- if symbol and symbol[:1] in (";", "-"):
+ if symbol and symbol[:1] in {";", "-"}:
continue
try:
symbol_desc = getattr(PointerSymbols, synset.ss_type)[symbol]
diff --git a/pyglossary/plugins/wordset.py b/pyglossary/plugins/wordset.py
index 61df94a71..4d91d81c9 100644
--- a/pyglossary/plugins/wordset.py
+++ b/pyglossary/plugins/wordset.py
@@ -85,7 +85,8 @@ def open(self, filename: str) -> None:
def __len__(self) -> int:
return 0
- def fileNameSortKey(self, fname: str) -> str:
+ @staticmethod
+ def fileNameSortKey(fname: str) -> str:
fname = splitext(fname)[0]
if fname == "misc":
return "\x80"
diff --git a/pyglossary/plugins/xdxf/__init__.py b/pyglossary/plugins/xdxf/__init__.py
index 761bc9949..eadd7f8ff 100644
--- a/pyglossary/plugins/xdxf/__init__.py
+++ b/pyglossary/plugins/xdxf/__init__.py
@@ -178,7 +178,7 @@ def open(self, filename: str) -> None:
)
for _, _elem in context:
elem = cast("Element", _elem)
- if elem.tag in ("meta_info", "ar", "k", "abr", "dtrn"):
+ if elem.tag in {"meta_info", "ar", "k", "abr", "dtrn"}:
break
# every other tag before or is considered info
if elem.tag == "abbr_def":
@@ -262,8 +262,8 @@ def close(self) -> None:
self._file.close()
self._file = nullBinaryIO
+ @staticmethod
def tostring(
- self,
elem: "Element",
) -> str:
from lxml import etree as ET
@@ -301,7 +301,7 @@ def titles(self, article: "Element") -> "list[str]":
return titles
- def _mktitle(
+ def _mktitle( # noqa: PLR6301
self,
title_element: "Element",
include_opts: "Sequence | None" = None,
diff --git a/pyglossary/plugins/xdxf_lax.py b/pyglossary/plugins/xdxf_lax.py
index bdee4826d..119ea74fa 100644
--- a/pyglossary/plugins/xdxf_lax.py
+++ b/pyglossary/plugins/xdxf_lax.py
@@ -219,8 +219,8 @@ def close(self) -> None:
self._file.close()
self._file = nullBinaryIO
+ @staticmethod
def tostring(
- self,
elem: "Element",
) -> str:
from lxml.html import tostring
@@ -258,7 +258,7 @@ def titles(self, article: "Element") -> "list[str]":
return titles
- def _mktitle(
+ def _mktitle( # noqa: PLR6301
self,
title_element: "Element",
include_opts: "Sequence | None" = None,
diff --git a/pyglossary/slob.py b/pyglossary/slob.py
index 804da9873..b9b8fdd99 100644
--- a/pyglossary/slob.py
+++ b/pyglossary/slob.py
@@ -270,10 +270,10 @@ def close(self) -> None:
def closed(self) -> bool:
return len(self._ranges) == 0
- def isatty(self) -> bool:
+ def isatty(self) -> bool: # noqa: PLR6301
return False
- def readable(self) -> bool:
+ def readable(self) -> bool: # noqa: PLR6301
return True
def seek(
@@ -291,13 +291,13 @@ def seek(
raise ValueError(f"Invalid value for parameter whence: {whence!r}")
return self._offset
- def seekable(self) -> bool:
+ def seekable(self) -> bool: # noqa: PLR6301
return True
def tell(self) -> int:
return self._offset
- def writable(self) -> bool:
+ def writable(self) -> bool: # noqa: PLR6301
return False
def read(self, n: "int | None" = -1) -> bytes:
@@ -1104,9 +1104,9 @@ def tag(self, name: str, value: str = "") -> None:
self._tags[name] = value
+ @staticmethod
def _split_key(
- self,
- key: "str | tuple[str, str]",
+ key: str | tuple[str, str],
) -> "tuple[str, str]":
if isinstance(key, str):
actual_key = key
diff --git a/pyglossary/text_reader.py b/pyglossary/text_reader.py
index 3143b7339..45373f1ea 100644
--- a/pyglossary/text_reader.py
+++ b/pyglossary/text_reader.py
@@ -194,10 +194,10 @@ def loadInfo(self) -> "Generator[tuple[int, int], None, None]":
self._fileCount = int(fileCountStr)
self._glos.setInfo("file_count", "")
+ @staticmethod
def _genDataEntries(
- self,
- resList: "list[tuple[str, str]]",
- resPathSet: "set[str]",
+ resList: list[tuple[str, str]],
+ resPathSet: set[str],
) -> "Iterator[DataEntry]":
for relPath, fullPath in resList:
if relPath in resPathSet:
@@ -240,7 +240,8 @@ def __iter__(self) -> "Iterator[EntryType | None]":
def __len__(self) -> int:
return self._wordCount
- def isInfoWord(self, word: str) -> bool:
+ @classmethod
+ def isInfoWord(cls, word: str) -> bool:
raise NotImplementedError
def isInfoWords(self, arg: "str | list[str]") -> bool:
@@ -250,7 +251,8 @@ def isInfoWords(self, arg: "str | list[str]") -> bool:
return self.isInfoWord(arg[0])
raise TypeError(f"bad argument {arg}")
- def fixInfoWord(self, word: str) -> str:
+ @classmethod
+ def fixInfoWord(cls, word: str) -> str:
raise NotImplementedError
def nextBlock(self) -> nextBlockResultType:
diff --git a/pyglossary/text_writer.py b/pyglossary/text_writer.py
index dcee5fdcc..71f2b03c0 100644
--- a/pyglossary/text_writer.py
+++ b/pyglossary/text_writer.py
@@ -113,7 +113,7 @@ def _doWriteInfo(self, _file: "io.TextIOBase") -> None:
if not (key and value):
log.warning(f"skipping info {key=}, {value=}")
continue
- key = outInfoKeysAliasDict.get(key, key)
+ key = outInfoKeysAliasDict.get(key, key) # noqa: PLW2901
if not key:
continue
word = f"##{key}"
@@ -122,7 +122,7 @@ def _doWriteInfo(self, _file: "io.TextIOBase") -> None:
if not word:
continue
if defiEscapeFunc is not None:
- value = defiEscapeFunc(value)
+ value = defiEscapeFunc(value) # noqa: PLW2901
if not value:
continue
_file.write(
diff --git a/pyglossary/ui/gtk3_utils/about.py b/pyglossary/ui/gtk3_utils/about.py
index 4f904271c..1ce1734fe 100644
--- a/pyglossary/ui/gtk3_utils/about.py
+++ b/pyglossary/ui/gtk3_utils/about.py
@@ -71,8 +71,8 @@ def __init__(
self.show_all()
# Something does not work with TextView
+ @staticmethod
def newTabWidgetTextView(
- self,
text: str,
wrap: bool = False,
justification: "gtk.Justification | None" = None,
@@ -97,8 +97,8 @@ def newTabWidgetTextView(
swin.add(tv)
return swin
+ @staticmethod
def newTabLabelWidget(
- self,
text: str,
# wrap: bool = False,
# justification: "gtk.Justification | None" = None,
@@ -124,7 +124,8 @@ def newTabLabelWidget(
swin.add(box)
return swin
- def newTabTitle(self, title: str, icon: str):
+ @staticmethod
+ def newTabTitle(title: str, icon: str):
box = gtk.Box(orientation=gtk.Orientation.VERTICAL)
if icon:
box.pack_start(imageFromFile(icon), False, False, 5)
diff --git a/pyglossary/ui/gtk4_utils/about.py b/pyglossary/ui/gtk4_utils/about.py
index 033cfedbe..3787052f6 100644
--- a/pyglossary/ui/gtk4_utils/about.py
+++ b/pyglossary/ui/gtk4_utils/about.py
@@ -97,8 +97,8 @@ def __init__(
self.show()
# Something does not work with TextView
+ @staticmethod
def newTabWidgetTextView(
- self,
text: str,
wrap: bool = False,
justification: "gtk.Justification | None" = None,
@@ -121,8 +121,8 @@ def newTabWidgetTextView(
swin.set_child(tv)
return swin
+ @staticmethod
def newTabLabelWidget(
- self,
text: str,
# wrap: bool = False,
# justification: "gtk.Justification | None" = None,
@@ -148,5 +148,6 @@ def newTabLabelWidget(
swin.set_child(box)
return swin
- def newTabTitle(self, title: str, icon: str):
+ @staticmethod
+ def newTabTitle(title: str, icon: str):
return AboutTabTitleBox(title, icon)
diff --git a/pyglossary/ui/ui_cmd_interactive.py b/pyglossary/ui/ui_cmd_interactive.py
index ec0f21170..86d25a06b 100644
--- a/pyglossary/ui/ui_cmd_interactive.py
+++ b/pyglossary/ui/ui_cmd_interactive.py
@@ -107,7 +107,7 @@ def formatMessage(self):
# msg = ANSI(msg) # NOT SUPPORTED
return msg # noqa: RET504
- def __pt_formatted_text__(self):
+ def __pt_formatted_text__(self): # noqa: PLW3201
return [("", self.formatMessage())]
@@ -221,7 +221,8 @@ def __init__(
fs_action_names = []
self.fs_action_names = fs_action_names
- def file_filter(self, _filename: str) -> bool:
+ @staticmethod
+ def file_filter(_filename: str) -> bool:
# filename is full/absolute file path
return True
@@ -325,13 +326,14 @@ def __init__(
],
)
- def fs_pwd(self, args: "list[str]"):
+ @staticmethod
+ def fs_pwd(args: "list[str]"):
if args:
print(f"extra arguments: {args}")
print(os.getcwd())
+ @staticmethod
def get_ls_l(
- self,
arg: str,
st: "os.stat_result | None" = None,
parentDir: str = "",
@@ -373,8 +375,8 @@ def fs_ls(self, args: "list[str]"):
showTitle = len(args) > 1
# Note: isdir and isfile funcs follow sym links, so no worry about links
- for i, arg in enumerate(args):
- if i > 0:
+ for argI, arg in enumerate(args):
+ if argI > 0:
print()
if not isdir(arg):
@@ -395,17 +397,18 @@ def fs_ls(self, args: "list[str]"):
statList = [os.lstat(join(arg, _path)) for _path in contents]
maxFileSize = max(st.st_size for st in statList)
sizeWidth = len(str(maxFileSize))
- for i, _path in enumerate(contents):
+ for pathI, path_ in enumerate(contents):
print(
self.get_ls_l(
- _path,
+ path_,
parentDir=arg,
- st=statList[i],
+ st=statList[pathI],
sizeWidth=sizeWidth,
),
)
- def fs_cd_parent(self, args: "list[str]"):
+ @staticmethod
+ def fs_cd_parent(args: "list[str]"):
if args:
log.error("This command does not take arguments")
return
@@ -413,7 +416,8 @@ def fs_cd_parent(self, args: "list[str]"):
os.chdir(newDir)
print(f"Changed current directory to: {newDir}")
- def fs_cd(self, args: "list[str]"):
+ @staticmethod
+ def fs_cd(args: "list[str]"):
if len(args) != 1:
log.error("This command takes exactly one argument")
return
@@ -512,7 +516,8 @@ def askOutputFile(self):
False,
)
- def pluginByNameOrDesc(self, value: str) -> "PluginProp | None":
+ @staticmethod
+ def pluginByNameOrDesc(value: str) -> "PluginProp | None":
plugin = pluginByDesc.get(value)
if plugin:
return plugin
@@ -577,7 +582,8 @@ def finish(self):
# TODO: how to handle \r and \n in NewlineOption.values?
- def getOptionValueSuggestValues(self, option: "Option"):
+ @staticmethod
+ def getOptionValueSuggestValues(option: "Option"):
if option.values:
return [str(x) for x in option.values]
if option.typ == "bool":
@@ -653,7 +659,7 @@ def askReadOptions(self):
)
except (KeyboardInterrupt, EOFError):
break
- if value == "":
+ if value == "": # noqa: PLC1901
if optName in self._readOptions:
print(f"Unset read-option {optName!r}")
del self._readOptions[optName]
@@ -728,7 +734,7 @@ def askWriteOptions(self):
)
except (KeyboardInterrupt, EOFError):
break
- if value == "":
+ if value == "": # noqa: PLC1901
if optName in self._writeOptions:
print(f"Unset write-option {optName!r}")
del self._writeOptions[optName]
@@ -801,7 +807,7 @@ def askConfig(self):
value = self.askConfigValue(configKey, option)
except (KeyboardInterrupt, EOFError):
break
- if value == "":
+ if value == "": # noqa: PLC1901
if configKey in self.config:
print(f"Unset config {configKey!r}")
del self.config[configKey]
diff --git a/pyglossary/ui/ui_gtk.py b/pyglossary/ui/ui_gtk.py
index 778c18f7d..a6c85dbf2 100644
--- a/pyglossary/ui/ui_gtk.py
+++ b/pyglossary/ui/ui_gtk.py
@@ -425,7 +425,7 @@ def valueEdited(self, _cell, path, rawValue):
if not prop.customValue:
return
enable = True
- if rawValue == "" and prop.typ != "str":
+ if rawValue == "" and prop.typ != "str": # noqa: PLC1901
enable = False
elif not prop.validateRaw(rawValue):
log.error(f"invalid {prop.typ} value: {optName} = {rawValue!r}")
@@ -513,7 +513,7 @@ def valueCellClicked(self, path, forceMenu=False) -> bool:
prop = self.optionsProp[optName]
if prop.typ == "bool":
rawValue = model.get_value(itr, self.valueCol)
- if rawValue == "":
+ if rawValue == "": # noqa: PLC1901
value = False
else:
value, isValid = prop.evaluate(rawValue)
diff --git a/pyglossary/ui/ui_gtk4.py b/pyglossary/ui/ui_gtk4.py
index 752fde672..def15a974 100644
--- a/pyglossary/ui/ui_gtk4.py
+++ b/pyglossary/ui/ui_gtk4.py
@@ -428,7 +428,7 @@ def valueEdited(self, _cell, path, rawValue):
if not prop.customValue:
return
enable = True
- if rawValue == "" and prop.typ != "str":
+ if rawValue == "" and prop.typ != "str": # noqa: PLC1901
enable = False
elif not prop.validateRaw(rawValue):
log.error(f"invalid {prop.typ} value: {optName} = {rawValue!r}")
@@ -532,7 +532,7 @@ def valueCellClicked(self, path, forceMenu=False) -> bool:
prop = self.optionsProp[optName]
if prop.typ == "bool":
rawValue = model.get_value(itr, self.valueCol)
- if rawValue == "":
+ if rawValue == "": # noqa: PLC1901
value = False
else:
value, isValid = prop.evaluate(rawValue)
diff --git a/pyglossary/ui/ui_tk.py b/pyglossary/ui/ui_tk.py
index 8a841d0f8..863dc01b6 100644
--- a/pyglossary/ui/ui_tk.py
+++ b/pyglossary/ui/ui_tk.py
@@ -474,9 +474,8 @@ def onDownPress(self, _event):
nextDesc = treev.next(selection[0])
if nextDesc:
self.setActiveRow(nextDesc)
- else:
- if self.items:
- self.setActiveRow(self.items[0])
+ elif self.items:
+ self.setActiveRow(self.items[0])
treev.focus()
def onUpPress(self, _event):
@@ -642,8 +641,8 @@ def createOptionsList(self):
]
treev.insert("", "end", values=row, iid=optName) # iid should be rowId
# adjust column's width if necessary to fit each value
- for col_i, value in enumerate(row):
- value = str(value)
+ for col_i, valueTmp in enumerate(row):
+ value = str(valueTmp)
if col_i == 3:
value = value.zfill(20)
# to reserve window width, because it's hard to resize it later
@@ -749,7 +748,7 @@ def valueCellClicked(self, event, optName):
return
if prop.typ == "bool":
rawValue = treev.set(optName, self.valueCol)
- if rawValue == "":
+ if rawValue == "": # noqa: PLC1901
value = False
else:
value, isValid = prop.evaluate(rawValue)
@@ -804,8 +803,8 @@ def callback():
menu.add_cascade(label=groupName, menu=subMenu)
maxItemW = max(maxItemW, tkFont.Font().measure(groupName))
else:
- for value in propValues:
- value = str(value)
+ for valueTmp in propValues:
+ value = str(valueTmp)
menu.add_command(
label=value,
command=valueMenuItemSelectedCommand(value),
@@ -944,7 +943,7 @@ def __init__(
# rootWin.bind("", self.resized)
#######################
defaultFont = tkFont.nametofont("TkDefaultFont")
- if core.sysName in ("linux", "freebsd"):
+ if core.sysName in {"linux", "freebsd"}:
defaultFont.configure(size=int(defaultFont.cget("size") * 1.4))
####
self.biggerFont = defaultFont.copy()
diff --git a/pyglossary/xdxf/transform.py b/pyglossary/xdxf/transform.py
index 0b832f5f7..d2123fa2d 100644
--- a/pyglossary/xdxf/transform.py
+++ b/pyglossary/xdxf/transform.py
@@ -55,7 +55,8 @@ def __init__(self, encoding: str = "utf-8") -> None:
"etm": self._write_etm,
}
- def tostring(self, elem: "Element") -> str:
+ @staticmethod
+ def tostring(elem: "Element") -> str:
from lxml import etree as ET
return (
@@ -68,14 +69,15 @@ def tostring(self, elem: "Element") -> str:
.strip()
)
- def hasPrevText(self, prev: "None | str | Element") -> bool:
+ @staticmethod
+ def hasPrevText(prev: "None | str | Element") -> bool:
if isinstance(prev, str):
return True
if prev is None:
return False
if prev.tag == "k":
return False
- if prev.tag in (
+ if prev.tag in {
"dtrn",
"def",
"span",
@@ -87,7 +89,7 @@ def hasPrevText(self, prev: "None | str | Element") -> bool:
"tt",
"big",
"small",
- ):
+ }:
return True
if prev.text:
return True
@@ -112,7 +114,7 @@ def addSep() -> None:
hasPrev = self.hasPrevText(prev)
trail = False
- if parent.tag in ("ar", "font"):
+ if parent.tag in {"ar", "font"}:
if child.startswith("\n"):
child = child.lstrip("\n")
if hasPrev:
@@ -157,7 +159,7 @@ def _write_example(self, hf: "T_htmlfile", elem: "Element") -> None:
with hf.element("div"):
self._write_iref(hf, child) # NESTED 5
continue
- if child.tag in ("ex_orig", "ex_tran"):
+ if child.tag in {"ex_orig", "ex_tran"}:
with hf.element("div"):
self.writeChildrenOf(hf, child, stringSep=stringSep) # NESTED 5
continue
@@ -207,7 +209,7 @@ def _write_k(self, hf: "T_htmlfile", child: "Element") -> None:
with hf.element("b"):
self.writeChildrenOf(hf, child)
- def _write_mrkd(self, hf: "T_htmlfile", child: "Element") -> None:
+ def _write_mrkd(self, hf: "T_htmlfile", child: "Element") -> None: # noqa: PLR6301
if not child.text:
return
with hf.element("span", attrib={"class": child.tag}):
@@ -308,22 +310,22 @@ def _write_categ(self, hf: "T_htmlfile", child: "Element") -> None:
with hf.element("span", style="background-color: green;"):
self.writeChildrenOf(hf, child, stringSep=" ")
- def _write_opt(self, hf: "T_htmlfile", child: "Element") -> None:
+ def _write_opt(self, hf: "T_htmlfile", child: "Element") -> None: # noqa: PLR6301
if child.text:
hf.write(" (")
hf.write(child.text)
hf.write(")")
- def _write_img(self, hf: "T_htmlfile", child: "Element") -> None:
+ def _write_img(self, hf: "T_htmlfile", child: "Element") -> None: # noqa: PLR6301
with hf.element("img", attrib=dict(child.attrib)):
pass
- def _write_abbr(self, hf: "T_htmlfile", child: "Element") -> None:
+ def _write_abbr(self, hf: "T_htmlfile", child: "Element") -> None: # noqa: PLR6301
# FIXME: may need an space or newline before it
with hf.element("i"):
hf.write(f"{child.text}")
- def _write_etm(self, hf: "T_htmlfile", child: "Element") -> None:
+ def _write_etm(self, hf: "T_htmlfile", child: "Element") -> None: # noqa: PLR6301
# Etymology (history and origin)
# TODO: formatting?
hf.write(f"{child.text}")
@@ -374,7 +376,7 @@ def writeChild(
stringSep=stringSep,
)
- def shouldAddSep(
+ def shouldAddSep( # noqa: PLR6301
self,
child: "str | Element",
prev: "str | Element",
@@ -384,12 +386,12 @@ def shouldAddSep(
return False
return True
- if child.tag in ("sub", "sup"):
+ if child.tag in {"sub", "sup"}:
return False
if isinstance(prev, str):
pass
- elif prev.tag in ("sub", "sup"):
+ elif prev.tag in {"sub", "sup"}:
return False
return True
diff --git a/pyglossary/xdxf/xsl_transform.py b/pyglossary/xdxf/xsl_transform.py
index d9f7936ee..01915caaf 100644
--- a/pyglossary/xdxf/xsl_transform.py
+++ b/pyglossary/xdxf/xsl_transform.py
@@ -29,14 +29,18 @@ def __init__(self, encoding: str = "utf-8") -> None:
e.msg += f", run `{core.pip} install lxml` to install"
raise e
- with open(join(rootDir, "pyglossary", "xdxf", "xdxf.xsl")) as f:
+ with open(
+ join(rootDir, "pyglossary", "xdxf", "xdxf.xsl"),
+ encoding="utf-8",
+ ) as f:
xslt_txt = f.read()
xslt = ET.XML(xslt_txt)
self._transform = ET.XSLT(xslt)
self._encoding = encoding
- def tostring(self, elem: "_XSLTResultTree | Element") -> str:
+ @staticmethod
+ def tostring(elem: "_XSLTResultTree | Element") -> str:
from lxml import etree as ET
return (
diff --git a/pyproject.toml b/pyproject.toml
index ce73f4ac0..f4a47c90c 100644
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -54,7 +54,7 @@ lint.select = [
# "ERA", # eradicate
"PD", # pandas-vet
"PGH", # pygrep-hooks
- # "PL", # Pylint
+ "PL", # Pylint
# "TRY", # tryceratops, they all sound BS
# "FLY", # flynt
"NPY", # NumPy-specific rules
@@ -71,6 +71,16 @@ lint.ignore = [
"DTZ005", # The use of `datetime.datetime.now()` without `tz` argument is not allowed
"PGH003", # Use specific rule codes when ignoring type issues
+ "PLR0904", # Too many public methods (? > 20)
+ "PLR0912", # Too many branches
+ "PLR0913", # Too many arguments in function definition
+ "PLR0914", # Too many local variables
+ "PLR0915", # Too many statements
+ "PLR0917", # Too many positional arguments
+ "PLR2004", # Magic value used in comparison, consider replacing `...` with a constant variable
+
+ "PLC0415", # `import` should be at the top-level of a file
+ "PLW0603", # Using the global statement to update `mockLog` is discouraged
"PT027", # Use `pytest.raises` instead of unittest-style `assertRaises`, why?
"PD011", # Use `.to_numpy()` instead of `.values`, WTF?
"ICN001", # `tkinter` should be imported as `tk`, WTF?
@@ -119,37 +129,25 @@ lint.ignore = [
# since which Python is comma after **kwargs allowd?
# Allow autofix for all enabled rules (when `--fix`) is provided.
-lint.fixable = [
- "RUF",
- "Q",
- "UP010", # Unnecessary `__future__`"
- "SIM108", # Use ternary operator {contents} instead of if-else-block
- "C408", # Unnecessary `dict` call (rewrite as a literal)
- "F401",
- "E", "F", "W",
- "RET",
- "I",
- "COM",
- "TCH",
- "ANN",
- "W291",
- "W293",
- "D",
- "UP004",
- "UP006",
- "UP008",
- "UP015",
- "UP024",
- "UP028",
- "UP030",
- "UP031",
- "UP032",
- "UP033",
- "UP034",
- "UP039",
- "UP035", # Import from `collections.abc` instead: `Generator|Iterator`
- # "TCH003", Move standard library import `...` into a type-checking block
-]
+# lint.fixable = [
+# "ANN",
+# "C408", # Unnecessary `dict` call (rewrite as a literal)
+# "COM",
+# "D",
+# "E",
+# "F",
+# "W",
+# "F401",
+# "I",
+# "Q",
+# "PIE790",
+# "RET",
+# "RUF",
+# # "SIM",
+# "SIM108", # Use ternary operator {contents} instead of if-else-block
+# "TCH",
+# "UP",
+# ]
lint.unfixable = []
# Exclude a variety of commonly ignored directories.
@@ -214,13 +212,21 @@ lint.dummy-variable-rgx = "^(_+|(_+[a-zA-Z0-9_]*[a-zA-Z0-9]+?))$"
"PT018", # Assertion should be broken down into multiple parts
"D",
"RUF015", # Prefer `next(zip(*_list, strict=False))` over single element slice
+ "PLR2004", # Magic value used in comparison, consider replacing `...` with a constant variable
]
"scripts/wiki-formats.py" = ["E501"]
"pyglossary/io_utils.py" = ["ANN"]
"pyglossary/plugins/babylon_bgl/bgl_reader_debug.py" = ["ANN", "FURB"]
"pyglossary/ui/*.py" = ["ANN", "T201", "PERF203"]
"pyglossary/ui/*/*.py" = ["ANN", "T201", "PERF203"]
-"tests/*.py" = ["ANN", "T201"]
+"pyglossary/ui/ui_*.py" = [
+ "PLR6301", # Method `...` could be a function, class method, or static method
+]
+"tests/*.py" = [
+ "ANN",
+ "T201",
+ "PLR6301", # Method `...` could be a function, class method, or static method
+]
"*_test.py" = [
"ANN",
"T201",
diff --git a/scripts/config-doc.py b/scripts/config-doc.py
index 5308e03b5..3b6e90a2f 100755
--- a/scripts/config-doc.py
+++ b/scripts/config-doc.py
@@ -52,7 +52,7 @@
""",
)
-with open(join(rootDir, "scripts/term-colors.json")) as _file:
+with open(join(rootDir, "scripts/term-colors.json"), encoding="utf-8") as _file:
termColors = json.load(_file)
@@ -188,5 +188,5 @@ def defaultOptionValue(name, _opt, images):
for image in images:
text += "\n" + image
-with open(join(rootDir, "doc", "config.rst"), mode="w") as _file:
+with open(join(rootDir, "doc", "config.rst"), mode="w", encoding="utf-8") as _file:
_file.write(text)
diff --git a/scripts/entry-filters-doc.py b/scripts/entry-filters-doc.py
index e5416649a..c4adec41b 100755
--- a/scripts/entry-filters-doc.py
+++ b/scripts/entry-filters-doc.py
@@ -93,5 +93,9 @@ def getCommandFlagsMD(name):
text = template.render(
entryFiltersTable=entryFiltersTable,
)
-with open(join(rootDir, "doc", "entry-filters.md"), mode="w") as _file:
+with open(
+ join(rootDir, "doc", "entry-filters.md"),
+ mode="w",
+ encoding="utf-8",
+) as _file:
_file.write(text)
diff --git a/scripts/tools-py2toml.py b/scripts/tools-py2toml.py
index 9d5291067..720ef83bb 100755
--- a/scripts/tools-py2toml.py
+++ b/scripts/tools-py2toml.py
@@ -37,5 +37,5 @@
# pprint(tools)
- with open(join(toolsDir, f"{p.lname}.toml"), mode="w") as _file:
+ with open(join(toolsDir, f"{p.lname}.toml"), mode="w", encoding="utf-8") as _file:
toml.dump(tools, _file)
diff --git a/scripts/wiktextract/extract-schema.py b/scripts/wiktextract/extract-schema.py
index 2ef834191..a7efe86ba 100644
--- a/scripts/wiktextract/extract-schema.py
+++ b/scripts/wiktextract/extract-schema.py
@@ -137,7 +137,7 @@ def parseDict(data: "dict[str, Any]", path: "list[str]", node: Node):
with open(jsonl_path, encoding="utf-8") as _file:
for line in _file:
- line = line.strip()
+ line = line.strip() # noqa: PLW2901
if not line:
continue
try:
diff --git a/scripts/wiktextract/sort-jsonl.py b/scripts/wiktextract/sort-jsonl.py
index 2d36dc75d..9078a5ab0 100755
--- a/scripts/wiktextract/sort-jsonl.py
+++ b/scripts/wiktextract/sort-jsonl.py
@@ -10,7 +10,7 @@
data: "list[tuple[str, str]]" = []
for line in sys.stdin:
- line = line.strip()
+ line = line.strip() # noqa: PLW2901
if not line:
continue
row = loads(line)
diff --git a/tests/dictzip_test.py b/tests/dictzip_test.py
index 5246f2f35..1af49e9cf 100644
--- a/tests/dictzip_test.py
+++ b/tests/dictzip_test.py
@@ -23,7 +23,7 @@ def setUp(self) -> None:
self.test_file_path = Path(self.tempDir) / "test_file.txt"
filename = self.test_file_path.name + ".dz"
self.result_file_path = self.test_file_path.parent / filename
- with open(self.test_file_path, "a") as tmp_file:
+ with open(self.test_file_path, "a", encoding="utf-8") as tmp_file:
tmp_file.write(TEXT)
def skip_on_dep(self, method: str) -> None:
diff --git a/tests/g_stardict_test.py b/tests/g_stardict_test.py
index 5578f191d..588a02afb 100644
--- a/tests/g_stardict_test.py
+++ b/tests/g_stardict_test.py
@@ -335,7 +335,7 @@ def test_convert_from_stardict_invalid_sametypesequence(self):
inputFilename = self.newTempFilePath(f"{fname}.ifo")
outputFilename = self.newTempFilePath(f"{fname}.txt")
- with open(inputFilename, mode="w") as _file:
+ with open(inputFilename, mode="w", encoding="utf-8") as _file:
_file.write(
"""StarDict's dict ifo file
version=3.0.0
diff --git a/tests/glossary_errors_test.py b/tests/glossary_errors_test.py
index 2b90704bf..181f88f42 100644
--- a/tests/glossary_errors_test.py
+++ b/tests/glossary_errors_test.py
@@ -384,7 +384,7 @@ def test_convert_sameFilename(self):
def test_convert_dirExists(self):
glos = Glossary()
tempFilePath = self.newTempFilePath("test_convert_dirExists")
- with open(tempFilePath, mode="w") as _file:
+ with open(tempFilePath, mode="w", encoding="utf-8") as _file:
_file.write("")
res = glos.convert(
inputFilename="test5.txt",
diff --git a/tests/glossary_v2_errors_test.py b/tests/glossary_v2_errors_test.py
index da3644ef2..b91c5e29b 100644
--- a/tests/glossary_v2_errors_test.py
+++ b/tests/glossary_v2_errors_test.py
@@ -371,7 +371,7 @@ def test_convert_sameFilename(self):
def test_convert_dirExists(self):
glos = Glossary()
tempFilePath = self.newTempFilePath("test_convert_dirExists")
- with open(tempFilePath, mode="w") as _file:
+ with open(tempFilePath, mode="w", encoding="utf-8") as _file:
_file.write("")
res = glos.convert(
ConvertArgs(
diff --git a/tests/slob_test.py b/tests/slob_test.py
index ac9822dfe..a6433a185 100644
--- a/tests/slob_test.py
+++ b/tests/slob_test.py
@@ -134,10 +134,10 @@ def setUp(self):
for k, t, v in self.data:
if isinstance(k, str):
- k = (k,)
+ k = (k,) # noqa: PLW2901
for key in k:
if isinstance(key, tuple):
- key, fragment = key
+ key, fragment = key # noqa: PLW2901
else:
fragment = ""
self.all_keys.append(key)