add codespell to pyproject.toml

calibre will probably never fully compliant with codespell
this setting is only to easily find common typo errors
by filtring a great range of false-positives, but not all

Changelog.txt

@@ -496,7 +496,7 @@
 
 :: improved recipes
 - Jot Down
-- Various Russian and Ukranian news sources
+- Various Russian and Ukrainian news sources
 - Nautilus Magazine
 - Süddeutsche Zeitung
 - The India Forum
@@ -974,7 +974,7 @@
 
 - Fix a regression in 7.0 caused by a regression in Qt that would result in calibre hanging rarely when using the cover browser view
 
-- [2049992] Fix custom template functions not useable in save to disk templates
+- [2049992] Fix custom template functions not usable in save to disk templates
 
 - Fix a regression in 7.2 that caused the popup used for editing fields in the book list to be mis-positioned on very wide monitors
 

format_docs/compression/zip.txt

@@ -402,7 +402,7 @@ V. General Format of a .ZIP file
          13 - Acorn Risc               14 - VFAT
          15 - alternate MVS            16 - BeOS
          17 - Tandem                   18 - OS/400
-         19 - OS/X (Darwin)            20 thru 255 - unused
+         19 - OS/X (Darwin)            20 through 255 - unused
 
           The lower byte indicates the ZIP specification version 
           (the version of this document) supported by the software 
@@ -719,7 +719,7 @@ V. General Format of a .ZIP file
           The Header ID field indicates the type of data that is in
           the following data block.
 
-          Header ID's of 0 thru 31 are reserved for use by PKWARE.
+          Header ID's of 0 through 31 are reserved for use by PKWARE.
           The remaining ID's can be used by third party vendors for
           proprietary usage.
 
@@ -1769,7 +1769,7 @@ Example:   0x02, 0x42, 0x01, 0x13
     This would generate the original bit length array of:
     (3, 3, 3, 3, 3, 2, 4, 4)
 
-    There are 8 codes in this table for the values 0 thru 7.  Using 
+    There are 8 codes in this table for the values 0 through 7.  Using 
     the algorithm to obtain the Shannon-Fano codes produces:
 
                                   Reversed     Order     Original
@@ -1909,8 +1909,8 @@ The bit lengths for the literal tables are sent first with the number
 of entries sent described by the 5 bits sent earlier.  There are up
 to 286 literal characters; the first 256 represent the respective 8
 bit character, code 256 represents the End-Of-Block code, the remaining
-29 codes represent copy lengths of 3 thru 258.  There are up to 30
+29 codes represent copy lengths of 3 through 258.  There are up to 30
-distance codes representing distances from 1 thru 32k as described
+distance codes representing distances from 1 through 32k as described
 below.
 
                              Length Codes
@@ -2221,7 +2221,7 @@ keys, based on random data, to render a plaintext attack on the
 data ineffective.
 
 Read the 12-byte encryption header into Buffer, in locations
-Buffer(0) thru Buffer(11).
+Buffer(0) through Buffer(11).
 
 loop for i <- 0 to 11
     C <- buffer(i) ^ decrypt_byte()

pyproject.toml

@@ -74,6 +74,93 @@ docstring-quotes = 'single'
 inline-quotes = 'single'
 multiline-quotes = 'single'
 
+[tool.codespell]
+# calibre will probably never fully compliant with codespell
+# this setting is only to easily find common typo errors
+# by filtring a great range of false-positives, but not all
+# (if codespell could per-file-ignores words, its be nicer)
+count = false
+summary = false
+quiet-level = 3
+regex = '''\b(?<!&)(?<!&amp;)[\w\-']+(?!&(amp;)?)\b'''
+builtin = [
+    'clear',
+    'rare',
+    'informal',
+]
+ignore-words-list = [
+    "alo",
+    "ans",
+    "clen",
+    "eto",
+    "fo",
+    "nam",
+    "nd",
+    "som",
+    "te",
+    "atLeast",
+    "Implementor",
+    "implementor",
+    "Implementors",
+    "implementors",
+    "missings",
+    "re-use",
+    "re-used",
+    "re-using",
+    "succeded",
+]
+uri-ignore-words-list = '*'
+skip = [
+    "*.svg",
+    "*.rcc",
+    "*_ui.py",
+    "./src/calibre/ebooks/rtf2xml/char_set.py",
+    "./src/calibre/ebooks/unihandecode/*",
+    "./src/calibre/ebooks/html_entities.h",
+    "./src/calibre/ebooks/html_entities.py",
+    "./src/calibre/utils/icu_test.py",
+    "./src/calibre/utils/search_query_parser_test.py",
+    "./Changelog.old.txt",
+    "./COPYRIGHT",
+    "./LICENSE",
+    "./LICENSE.rtf",
+    "./pyproject.toml",
+    "./session.vim",
+    "./build/*",
+    "./docs/*",
+    "./nbproject/*",
+    "./recipes/*",
+    "./translations/*",
+    "./tags/*",
+    "./manual/generated/*",
+    "./manual/locale/*",
+    "./resources/dictionaries/*",
+    "./resources/localization/*",
+    "./resources/hyphenation/*",
+    "./resources/mathjax/*",
+    "./resources/builtin_recipes.xml",
+    "./resources/changelog.json",
+    "./resources/editor.js",
+    "./resources/editor-functions.json",
+    "./resources/mime.types",
+    "./resources/piper-voices.json",
+    "./resources/stylelint-bundle.min.js",
+    "./resources/user-manual-translation-stats.json",
+    "./resources/template-functions.json",
+    "./resources/viewer.js",
+    "./resources/viewer.html",
+    "./resources/content-server/index-generated.html",
+    "./setup/installer/*",
+    "./setup/pyqt_enums/*",
+    "./setup/lc_data.py",
+    "./setup/linux-installer.py",
+    "./src/css_selectors/*",
+    "./src/polyglot/*",
+    "./src/templite/*",
+    "./src/tinycss/*",
+    "./src/unicode_names/*",
+]
+
 [tool.flynt]
 line-length = 400  # over value to catch every case
 transform-format = false  # don't transform already existing format call

recipes/espn.recipe

@@ -61,7 +61,7 @@ class ESPN(BasicNewsRecipe):
     def get_browser(self):
         br = BasicNewsRecipe.get_browser(self)
         if False and self.username and self.password:
-            # ESPN has changed to a JS based login system, cant be bothered
+            # ESPN has changed to a JS based login system, can't be bothered
             # revering it
             br.set_handle_refresh(False)
             url = ('https://r.espn.go.com/members/v3_1/login')

recipes/financial_times.recipe

@@ -71,7 +71,7 @@ class ft(BasicNewsRecipe):
     # def get_browser(self, *args, **kw):
     #     br = super().get_browser(*args, **kw)
     #     if self.username and self.password:
-    #         # ft.com uses a CAPTCHA on its login page so this sadly doesnt work
+    #         # ft.com uses a CAPTCHA on its login page so this sadly doesn't work
     #         br.open('https://accounts.ft.com/login?location=https%3A%2F%2Fwww.ft.com')
     #         br.select_form(id='email-form')
     #         br['email'] = self.username

recipes/independent_australia.recipe

@@ -77,7 +77,7 @@ class IndependentAustralia(BasicNewsRecipe):
         businessArticles = []
         lifeArticles = []
         australiaArticles = []
-        # Loop thru the articles in all feeds to find articles with base categories in it
+        # Loop through the articles in all feeds to find articles with base categories in it
         for curfeed in feeds:
             delList = []
             for a, curarticle in enumerate(curfeed.articles):

recipes/satmagazine.recipe

@@ -107,7 +107,7 @@ class SatMagazine(BasicNewsRecipe):
 
         title_number = 0
 
-        # Goes thru all the articles one by one and sort them out
+        # Goes through all the articles one by one and sort them out
         for article in articles:
 
             title = self.tag_to_string(article)

setup/installers.py

@@ -57,7 +57,7 @@ def get_dist(base, which, bitness):
 
 def shutdown_allowed(which, bitness):
     # The ARM64 VM is extremely flakey often booting up to a non-functional
-    # state so dont shut it down as it seems to be more stable once bootup is
+    # state so dont shut it down as it seems to be more stable once boot-up is
     # done.
     return bitness != 'arm64'
 

src/calibre/db/cache.py

@@ -3474,7 +3474,7 @@ class Cache:
                         self._add_extra_files(dest_id, {q: BytesIO(cdata)}, replace=False, auto_rename=True)
                         break
 
-        for key in self.field_metadata:  # loop thru all defined fields
+        for key in self.field_metadata:  # loop through all defined fields
             fm = self.field_metadata[key]
             if not fm['is_custom']:
                 continue

src/calibre/db/notes/connect.py

@@ -119,7 +119,7 @@ class Notes:
     def path_for_resource(self, resource_hash: str) -> str:
         hashalg, digest = resource_hash.split(':', 1)
         prefix = digest[:2]
-        # Cant use colons in filenames on windows safely
+        # Can't use colons in filenames on windows safely
         return os.path.join(self.resources_dir, prefix, f'{hashalg}-{digest}')
 
     def remove_resources(self, conn, note_id, resources_to_potentially_remove, delete_from_link_table=True):

src/calibre/devices/mtp/unix/upstream/music-players.h

@@ -299,7 +299,7 @@
      DEVICE_FLAG_BROKEN_MTPGETOBJPROPLIST |
      DEVICE_FLAG_PLAYLIST_SPL_V1 },
   // YP-F3 is NOT MTP - USB mass storage
-  // From a rouge .INF file
+  // From a rogue .INF file
   // this device ID seems to have been recycled for:
   // the Samsung SGH-A707 Cingular cellphone
   // the Samsung L760-V cellphone
@@ -1183,7 +1183,7 @@
       DEVICE_FLAG_BROKEN_MTPGETOBJPROPLIST_ALL },
   // From: Willy Gardiol (web) <willy@gardiol.org>
   // Spurious errors for getting all objects, lead me to believe
-  // this flag atleast is needed
+  // this flag at least is needed
   { "Nokia", 0x0421, "5800 XpressMusic v2", 0x0155,
       DEVICE_FLAG_BROKEN_MTPGETOBJPROPLIST_ALL },
   // Yet another version... I think

src/calibre/ebooks/mobi/debug/index.py

@@ -51,7 +51,7 @@ def read_variable_len_data(data, header):
         header['tagx_block_size'] = 0
     trailing_bytes = data[idxt_offset+idxt_size:]
     if trailing_bytes.rstrip(b'\0'):
-        raise ValueError('Traling bytes after last IDXT entry: {!r}'.format(trailing_bytes.rstrip(b'\0')))
+        raise ValueError('Trailing bytes after last IDXT entry: {!r}'.format(trailing_bytes.rstrip(b'\0')))
     header['indices'] = indices
 
 

src/calibre/ebooks/oeb/polish/tests/kepubify.py

@@ -101,7 +101,7 @@ div#book-inner {{ margin-top: 0; margin-bottom: 0; }}</style><script type="text/
             # encoding quirks
             '<p>A\xa0nbsp;&nbsp;':
             '<p><span class="koboSpan" id="kobo.1.1">A&#160;nbsp;&#160;</span></p>',
-            '<div><script>1 < 2 & 3</script>':  # escaping with cdata note that kepubify doesnt do this
+            '<div><script>1 < 2 & 3</script>':  # escaping with cdata note that kepubify doesn't do this
             '<div><script><![CDATA[1 < 2 & 3]]></script></div>',
 
             # CSS filtering

src/calibre/ebooks/pdf/reflow.py

@@ -732,21 +732,21 @@ class Region:
 class Page:
 
     def __init__(self, page, font_map, opts, log, idc):
-        def text_cmp(frst, secnd):
+        def text_cmp(first, second):
             # Compare 2 text objects.
             # Order by line (top/bottom) then left
-            if (frst.top <= secnd.top and frst.bottom >= secnd.bottom-BOTTOM_FACTOR) \
+            if (first.top <= second.top and first.bottom >= second.bottom-BOTTOM_FACTOR) \
-              or (secnd.top <= frst.top and secnd.bottom >= frst.bottom-BOTTOM_FACTOR):
+              or (second.top <= first.top and second.bottom >= first.bottom-BOTTOM_FACTOR):
                 # Overlap = same line
-                if frst.left < secnd.left:
+                if first.left < second.left:
                     return -1
-                elif frst.left == secnd.left:
+                elif first.left == second.left:
                     return 0
                 return 1
             # Different line so sort into line number
-            if frst.bottom < secnd.bottom:
+            if first.bottom < second.bottom:
                 return -1
-            elif frst.bottom == secnd.bottom:
+            elif first.bottom == second.bottom:
                 return 0
             return 1
 

src/calibre/ebooks/rtf2xml/list_numbers.py

@@ -121,7 +121,7 @@ class ListNumbers:
             return 'ordered'
         # sys.stderr.write('module is list_numbers\n')
         # sys.stderr.write('method is __determine type\n')
-        # sys.stderr.write('Couldn\'t get type of list\n')
+        # sys.stderr.write("Couldn't get type of list\n")
         # must be some type of ordered list -- just a guess!
         return 'unordered'
 

src/calibre/gui2/__init__.py

@@ -1776,7 +1776,7 @@ def raise_and_focus(self: QWidget) -> None:
 
 def raise_without_focus(self: QWidget) -> None:
     if QApplication.instance().platformName() == 'wayland':
-        # On fucking Wayland, we cant raise a dialog without also giving it
+        # On fucking Wayland, we can't raise a dialog without also giving it
         # keyboard focus. What a joke.
         self.raise_and_focus()
     else:

src/calibre/gui2/auto_add.py

@@ -288,10 +288,10 @@ class AutoAdder(QObject):
 
         if duplicates:
             paths, formats, metadata = [], [], []
-            for p, f, mis in duplicates:
+            for p, f, mi in duplicates:
                 paths.extend(p)
                 formats.extend(f)
-                metadata.extend(mis)
+                metadata.extend(mi)
             dups = [(mic, mic.cover, [p]) for mic, p in zip(metadata, paths)]
             d = DuplicatesQuestion(m.db, dups, parent=gui)
             dups = tuple(d.duplicates)

src/calibre/gui2/central.py

@@ -485,7 +485,7 @@ class CentralContainer(QWidget):
 
     def read_settings(self):
         before = self.serialized_settings()
-        # sadly self.size() doesnt always return sensible values so look at
+        # sadly self.size() doesn't always return sensible values so look at
         # the size of the main window which works perfectly for width, not so
         # perfectly for height
         sz = self.size()

src/calibre/gui2/dialogs/edit_category_notes.py

@@ -287,7 +287,7 @@ class NoteEditorWidget(EditorWidget):
 
     def do_insert_image(self):
         # See https://bugreports.qt.io/browse/QTBUG-118537
-        # for why we cant have a nice margin for floating images
+        # for why we can't have a nice margin for floating images
         d = AskImage(self.images, self.db)
         if d.exec() == QDialog.DialogCode.Accepted and d.current_digest:
             ir = self.images[d.current_digest]

src/calibre/gui2/email.py

@@ -153,14 +153,14 @@ def send_mails(jobnames, callback, attachments, to_s, subjects,
             attachments, to_s, subjects, texts, attachment_names):
         description = _('Email %(name)s to %(to)s') % dict(name=name, to=to)
         if isinstance(to, str) and (is_for_kindle(to) or '@pbsync.com' in to):
-            # The PocketBook service is a total joke. It cant handle
+            # The PocketBook service is a total joke. It can't handle
             # non-ascii, filenames that are long enough to be split up, commas, and
             # the good lord alone knows what else. So use a random filename
             # containing only 22 English letters and numbers
             #
             # And since this email is only going to be processed by automated
             # services, make the subject+text random too as at least the amazon
-            # service cant handle non-ascii text. I dont know what baboons
+            # service can't handle non-ascii text. I dont know what baboons
             # these companies employ to write their code. It's the height of
             # irony that they are called "tech" companies.
             # https://bugs.launchpad.net/calibre/+bug/1989282

src/calibre/gui2/fts/dialog.py

@@ -36,7 +36,7 @@ class FTSDialog(Dialog):
         l = QVBoxLayout(self)
         self.fat_warning = fw = QLabel(
             f'<span style="color:red; font-weight: bold">{_("WARNING")}:</span> ' +
-            _('The calibre library is on a FAT drive, indexing more than a few hundred books wont work.') +
+            _("The calibre library is on a FAT drive, indexing more than a few hundred books won't work.") +
             f' <a href="xxx" style="text-decoration: none">{_("Learn more")}</a>')
         # fw.setVisible(False)
         fw.linkActivated.connect(self.show_fat_details)

src/calibre/gui2/init.py

@@ -359,7 +359,7 @@ class VLTabs(QTabBar):  # {{{
     def lock_tab(self):
         gprefs['vl_tabs_closable'] = False
         self.setTabsClosable(False)
-        # Workaround for Qt bug where it doesnt recalculate the tab size after locking
+        # Workaround for Qt bug where it doesn't recalculate the tab size after locking
         for idx in range(self.count()):
             self.setTabButton(idx, QTabBar.ButtonPosition.RightSide, None)
             self.setTabButton(idx, QTabBar.ButtonPosition.LeftSide, None)

src/calibre/gui2/markdown_syntax_highlighter.py

@@ -268,7 +268,7 @@ class MarkdownHighlighter(QSyntaxHighlighter):
             elif emphasis:
                 self.setFormat(self.offset+offset+ match.start(), match.end() - match.start(), self.MARKDOWN_KWS_FORMAT['Italic'])
 
-        def recusive(match, extra_offset, bold, emphasis):
+        def recursive(match, extra_offset, bold, emphasis):
             apply(match, bold, emphasis)
             if bold and emphasis:
                 return  # max deep => return, do not process extra Bold/Italic
@@ -278,17 +278,17 @@ class MarkdownHighlighter(QSyntaxHighlighter):
             self._highlightBoldEmphasis(sub_txt, cursor, bf, sub_offset, bold, emphasis)
 
         for mo in re.finditer(self.MARKDOWN_KEYS_REGEX['Italic'],text):
-            recusive(mo, 1, bold, True)
+            recursive(mo, 1, bold, True)
             found = True
         for mo in re.finditer(self.MARKDOWN_KEYS_REGEX['uItalic'],text):
-            recusive(mo, 1, bold, True)
+            recursive(mo, 1, bold, True)
             found = True
 
         for mo in re.finditer(self.MARKDOWN_KEYS_REGEX['Bold'],text):
-            recusive(mo, 2, True, emphasis)
+            recursive(mo, 2, True, emphasis)
             found = True
         for mo in re.finditer(self.MARKDOWN_KEYS_REGEX['uBold'],text):
-            recusive(mo, 2, True, emphasis)
+            recursive(mo, 2, True, emphasis)
             found = True
 
         for mo in re.finditer(self.MARKDOWN_KEYS_REGEX['BoldItalic'],text):

src/calibre/gui2/tweak_book/editor/syntax/javascript.py

@@ -25,7 +25,7 @@ JS_IDENT = JS_IDENT_START + '(?:' + JS_IDENT_PART + ')*'
 class JavascriptLexer(RegexLexer):
     '''
     For JavaScript source code. This is based on the pygments JS highlighter,
-    bu that does not handle multi-line comments in streaming mode, so we had to
+    but that does not handle multi-line comments in streaming mode, so we had to
     modify it.
     '''
 

src/calibre/srv/http_request.py

@@ -83,7 +83,7 @@ def parse_uri(uri, parse_query=True, unquote_func=unquote):
         try:
             query = MultiDict.create_from_query_string(qs)
         except Exception:
-            raise HTTPSimpleResponse(http_client.BAD_REQUEST, 'Unparseable query string')
+            raise HTTPSimpleResponse(http_client.BAD_REQUEST, 'Unparsable query string')
     else:
         query = None
 

src/calibre/utils/formatter.py

@@ -192,7 +192,7 @@ class SetGlobalsNode(Node):
 
 class StringCompareNode(Node):
     def __init__(self, line_number, operator, left, right):
-        Node.__init__(self, line_number, 'comparision: ' + operator)
+        Node.__init__(self, line_number, 'comparison: ' + operator)
         self.node_type = self.NODE_COMPARE_STRING
         self.operator = operator
         self.left = left

src/calibre/utils/smtplib.py

@@ -743,7 +743,7 @@ class SMTP:
          >>> tolist=["one@one.org","two@two.org","three@three.org","four@four.org"]
          >>> msg = '''\\
          ... From: Me@my.org
-         ... Subject: testin'...
+         ... Subject: testing...
          ...
          ... This is a test '''
          >>> s.sendmail("me@my.org",tolist,msg)

src/pyj/read_book/paged_mode.pyj

@@ -446,7 +446,7 @@ def next_screen_location():
         current_pos = Math.ceil(current_scroll_offset())
         ans = limit if current_pos < limit else -1
         if cols_per_screen is 1 and ans is not -1 and ans - current_pos < col_size:
-            ans = -1  # cant scroll partial columns
+            ans = -1  # can't scroll partial columns
     return ans
 
 

src/pyj/read_book/ui.pyj

@@ -145,7 +145,7 @@ class ReadUI:
                 try:
                     result = JSON.parse(xhr.responseText)
                 except Exception:
-                    return self.show_error(_('Failed to parse profiles'), _('Unparseable data received for profiles'))
+                    return self.show_error(_('Failed to parse profiles'), _('Unparsable data received for profiles'))
                 proceed(result)
             ).send()
 

src/pyj/select.pyj

@@ -134,7 +134,7 @@ def range_extents(q, in_flow_mode):
                         rect = boundary_node.getBoundingClientRect()
                         if not is_start:
                             ans.selected_prev = True
-                # we cant use getBoundingClientRect as the node might be split
+                # we can't use getBoundingClientRect as the node might be split
                 # among multiple columns
                 else if node.getClientRects:
                     rects = node.getClientRects()