Fix syntax warnings in Python 3.12+

.github/workflows/lint.yml

@@ -0,0 +1,22 @@
+name: Lint
+
+on: [push, pull_request, workflow_dispatch]
+
+permissions: {}
+
+env:
+  FORCE_COLOR: 1
+  RUFF_OUTPUT_FORMAT: github
+
+jobs:
+  lint:
+    runs-on: ubuntu-latest
+
+    steps:
+      - uses: actions/checkout@v4
+        with:
+          persist-credentials: false
+      - uses: actions/setup-python@v5
+        with:
+          python-version: "3.x"
+      - uses: tox-dev/action-pre-commit-uv@v1

.pre-commit-config.yaml

@@ -0,0 +1,6 @@
+repos:
+  - repo: https://github.com/astral-sh/ruff-pre-commit
+    rev: v0.11.3
+    hooks:
+      - id: ruff
+        args: [--exit-non-zero-on-fix]

.ruff.toml

@@ -0,0 +1,9 @@
+fix = true
+extend-exclude = [
+  "*.cgi", # Python 2 code
+]
+target-version = "py310"
+
+lint.select = [
+  "W605", # invalid-escape-sequence
+]

docs-xml/build-html-docs.py

@@ -32,7 +32,7 @@ def asText(x):
 
 import re
 
-wsRE = re.compile('\s+')
+wsRE = re.compile(r'\s+')
 
 def trimWS(s):
   s = wsRE.sub(' ', s)
@@ -43,7 +43,7 @@ def trimWS(s):
 
   return s
 
-secRe = re.compile("<div id='(\w+)'>\n(.*?\n)</div>\n", re.DOTALL)
+secRe = re.compile("<div id='(\\w+)'>\n(.*?\n)</div>\n", re.DOTALL)
 
 import codecs
 
@@ -67,7 +67,7 @@ def writeDoc(x, h):
 
 
   for (sec, txt) in secRe.findall(t):
-    r = re.compile('<h2>' + sec + '</h2>\s*<div class="docbody">\s*()</div>', re.IGNORECASE)
+    r = re.compile('<h2>' + sec + r'</h2>\s*<div class="docbody">\s*()</div>', re.IGNORECASE)
     idx = r.search(doc).start(1)
     doc = doc[:idx] + txt + doc[idx:]
 

docs-xml/mkmsgs.py

@@ -94,7 +94,7 @@ def buildTestSuite():
 if __name__ == '__main__':
   import re
   for dir, id, msg, html, xml in missing():
-    msg = re.sub("%\(\w+\)\w?", "<code>foo</code>", msg)
+    msg = re.sub(r"%\(\w+\)\w?", "<code>foo</code>", msg)
     if not path.exists(html):
       pass
     if not path.exists(xml):

src/feedvalidator/__init__.py

@@ -47,7 +47,7 @@ def _validate(aString, firstOccurrenceOnly, loggedEvents, base, encoding, selfUR
   from .base import SAXDispatcher
   from io import StringIO
 
-  if re.match("^\s+<\?xml",aString) and re.search("<generator.*wordpress.*</generator>",aString):
+  if re.match(r"^\s+<\?xml",aString) and re.search("<generator.*wordpress.*</generator>",aString):
     lt = aString.find('<'); gt = aString.find('>')
     if lt > 0 and gt > 0 and lt < gt:
       loggedEvents.append(logging.WPBlankLine({'line':1,'column':1}))
@@ -72,7 +72,7 @@ def _validate(aString, firstOccurrenceOnly, loggedEvents, base, encoding, selfUR
   # experimental RSS-Profile support
   validator.rssCharData = [s.find('&#x')>=0 for s in aString.split('\n')]
 
-  xmlver = re.match("^<\?\s*xml\s+version\s*=\s*['\"]([-a-zA-Z0-9_.:]*)['\"]",aString)
+  xmlver = re.match("^<\\?\\s*xml\\s+version\\s*=\\s*['\"]([-a-zA-Z0-9_.:]*)['\"]",aString)
   if xmlver and xmlver.group(1) != '1.0':
     validator.log(logging.BadXmlVersion({"version":xmlver.group(1)}))
 

src/feedvalidator/base.py

@@ -95,7 +95,7 @@
 
 def near_miss(ns):
   try:
-    return re.match(".*\w", ns).group().lower()
+    return re.match(r".*\w", ns).group().lower()
   except:
     return ns
 

src/feedvalidator/extension.py

@@ -763,7 +763,7 @@ def validate(self):
 
 class gml_pos(text):
   def validate(self):
-    if not re.match('^[-+]?\d+\.?\d*[ ,][-+]?\d+\.?\d*$', self.value):
+    if not re.match(r'^[-+]?\d+\.?\d*[ ,][-+]?\d+\.?\d*$', self.value):
       return self.log(InvalidCoord({'value':self.value}))
     if self.value.find(',')>=0:
       self.log(CoordComma({'value':self.value}))
@@ -785,7 +785,7 @@ def validate(self):
     if len(values)<3 or len(values)%2 == 1:
       return self.log(InvalidCoordList({'value':self.value}))
     for value in values:
-      if not re.match('^[-+]?\d+\.?\d*$', value):
+      if not re.match(r'^[-+]?\d+\.?\d*$', value):
         return self.log(InvalidCoordList({'value':value}))
 
 class gml_polygon(geo_srsName):
@@ -1157,21 +1157,21 @@ class g_serviceTypeEnumeration(enumeration):
 class g_float(text):
   def validate(self):
     import re
-    if not re.match('\d+\.?\d*\s*\w*', self.value):
+    if not re.match(r'\d+\.?\d*\s*\w*', self.value):
       self.log(InvalidFloat({"parent":self.parent.name, "element":self.name,
         "attr": ':'.join(self.name.split('_',1)), "value":self.value}))
 
 class floatUnit(text):
   def validate(self):
     import re
-    if not re.match('\d+\.?\d*\s*\w*$', self.value):
+    if not re.match(r'\d+\.?\d*\s*\w*$', self.value):
       self.log(InvalidFloatUnit({"parent":self.parent.name, "element":self.name,
         "attr": ':'.join(self.name.split('_',1)), "value":self.value}))
 
 class decimal(text):
   def validate(self):
     import re
-    if not re.match('[-+]?\d+\.?\d*\s*$', self.value):
+    if not re.match(r'[-+]?\d+\.?\d*\s*$', self.value):
       self.log(InvalidFloatUnit({"parent":self.parent.name, "element":self.name,
         "attr": ':'.join(self.name.split('_',1)), "value":self.value}))
 

src/feedvalidator/image.py

@@ -70,7 +70,7 @@ def validate(self):
     rfc2396_full.validate(self)
     import re
     ext = self.value.split('.')[-1].lower()
-    if re.match("^\w+$", ext) and ext not in ['jpg','jpeg','gif','png']:
+    if re.match(r"^\w+$", ext) and ext not in ['jpg','jpeg','gif','png']:
       self.log(ImageUrlFormat({"parent":self.parent.name, "element":self.name}))
 
 class title(nonhtml):

src/feedvalidator/kml.py

@@ -1063,7 +1063,7 @@ def validate(self):
        self.log(InvalidKmlLatitude({"parent":self.parent.name, "element":self.name, "value":lat}))
       # Third coordinate value (altitude) has to be float, if present
       if len(point) == 3:
-        if not re.match('\d+\.?\d*$', point[2]):
+        if not re.match(r'\d+\.?\d*$', point[2]):
           self.log(InvalidFloat({"attr":self.name, "value":point[2]}))
 
 class angle360(text):
@@ -1079,5 +1079,5 @@ def validate(self):
 
 class FloatWithNegative(text):
   def validate(self, name=None):
-    if not re.match('-?\d+\.?\d*$', self.value):
+    if not re.match(r'-?\d+\.?\d*$', self.value):
       self.log(InvalidFloat({"attr":name or self.name, "value":self.value}))

src/feedvalidator/media.py

@@ -247,7 +247,7 @@ def validate(self):
       nonhtml.validate(self, ContainsUndeclaredHTML)
 
 class media_thumbnail(positiveInteger,rfc2396_full):
-  npt_re = re.compile("^(now)|(\d+(\.\d+)?)|(\d+:\d\d:\d\d(\.\d+)?)$")
+  npt_re = re.compile(r"^(now)|(\d+(\.\d+)?)|(\d+:\d\d:\d\d(\.\d+)?)$")
   def getExpectedAttrNames(self):
     return [(None,'height'),(None,'time'),(None,'url'),(None, 'width')]
   def validate(self):
@@ -295,7 +295,7 @@ def getExpectedAttrNames(self):
       ]
   def validate(self):
     self.value = self.attrs.get((None,'bitrate'))
-    if self.value and not re.match('\d+\.?\d*', self.value):
+    if self.value and not re.match(r'\d+\.?\d*', self.value):
       self.log(InvalidFloat({"parent":self.parent.name, "element":self.name,
         "attr": 'bitrate', "value":self.value}))
 
@@ -304,7 +304,7 @@ def validate(self):
     if self.value: nonNegativeInteger.validate(self)
 
     self.value = self.attrs.get((None,'duration'))
-    if self.value and not re.match('\d+\.?\d*', self.value):
+    if self.value and not re.match(r'\d+\.?\d*', self.value):
       self.log(InvalidFloat({"parent":self.parent.name, "element":self.name,
         "attr": 'duration', "value":self.value}))
 
@@ -317,7 +317,7 @@ def validate(self):
     if self.value: positiveInteger.validate(self)
 
     self.value = self.attrs.get((None,'framerate'))
-    if self.value and not re.match('\d+\.?\d*', self.value):
+    if self.value and not re.match(r'\d+\.?\d*', self.value):
       self.log(InvalidFloat({"parent":self.parent.name, "element":self.name,
         "attr": 'framerate', "value":self.value}))
 
@@ -336,7 +336,7 @@ def validate(self):
       self.log(InvalidMediaMedium({"parent":self.parent.name, "element":self.name, "value": self.value}))
 
     self.value = self.attrs.get((None,'samplingrate'))
-    if self.value and not re.match('\d+\.?\d*', self.value):
+    if self.value and not re.match(r'\d+\.?\d*', self.value):
       self.log(InvalidFloat({"parent":self.parent.name, "element":self.name,
         "attr": 'samplingrate', "value":self.value}))
 

src/feedvalidator/opensearch.py

@@ -63,7 +63,7 @@ def prevalidate(self):
     # self.validate_optional_attribute((None,'rel'), text)
 
 class Template(rfc2396_full):
-  tparam = re.compile("{((?:[-a-zA-Z0-9._~]|%[a-fA-F0-9]{2})+:?(?:[-a-zA-Z0-9._~]|%[a-fA-F0-9]{2})*)\??}")
+  tparam = re.compile(r"{((?:[-a-zA-Z0-9._~]|%[a-fA-F0-9]{2})+:?(?:[-a-zA-Z0-9._~]|%[a-fA-F0-9]{2})*)\??}")
   valuelist = ['searchTerms', 'count', 'startIndex', 'startPage', 'language',
     'inputEncoding', 'outputEncoding']
 
@@ -127,7 +127,7 @@ def validate(self):
     from urllib.parse import quote, unquote
     import re
     for value in self.value.split():
-      value = re.sub('%\w\w', lambda x: x.group(0).upper(), value)
+      value = re.sub(r'%\w\w', lambda x: x.group(0).upper(), value)
       if value != quote(unquote(value)):
         self.log(NotURLEncoded({}))
         break

src/feedvalidator/opml.py

@@ -76,7 +76,7 @@ def do_windowRight(self):
     return positiveInteger(), nonblank(), noduplicates()
 
 class commaSeparatedLines(text):
-  linenumbers_re=re.compile('^(\d+(,\s*\d+)*)?$')
+  linenumbers_re=re.compile(r'^(\d+(,\s*\d+)*)?$')
   def validate(self):
     if not self.linenumbers_re.match(self.value):
       self.log(InvalidExpansionState({"parent":self.parent.name, "element":self.name, "value":self.value}))

src/feedvalidator/uri.py

@@ -80,7 +80,7 @@ def _qnu(s,safe=''):
   return res
 
 # Match an optional port specification
-portRe = re.compile(':(\d*)$')
+portRe = re.compile(r':(\d*)$')
 
 def _normPort(netloc,defPort):
   nl = netloc.lower()
@@ -146,7 +146,7 @@ def _normPath(p):
   return '/'.join([_qnu(c, PCHAR) for c in l])
 
 # From RFC 2396bis, with added end-of-string marker
-uriRe = re.compile('^(([^:/?#]+):)?(//([^/?#]*))?([^?#]*)(\?([^#]*))?(#(.*))?$')
+uriRe = re.compile(r'^(([^:/?#]+):)?(//([^/?#]*))?([^?#]*)(\?([^#]*))?(#(.*))?$')
 
 def _canonical(s):
   m = uriRe.match(s)