Message ID | 20230915094038.1178807-1-mfabian@redhat.com |
---|---|
State | New |
Headers | show |
Series | [1/3] Fix regexp syntax warnings in localedata/unicode-gen/ctype_compatibility.py | expand |
On 9/15/23 05:40, Mike FABIAN wrote: > Fix these: LGTM. Please commit. Reviewed-by: Carlos O'Donell <carlos@redhat.com> > $ python -m py_compile ./ctype_compatibility.py > ./ctype_compatibility.py:146: SyntaxWarning: invalid escape sequence '\)' > --- > localedata/unicode-gen/ctype_compatibility.py | 26 +++++++++---------- > 1 file changed, 13 insertions(+), 13 deletions(-) > > diff --git a/localedata/unicode-gen/ctype_compatibility.py b/localedata/unicode-gen/ctype_compatibility.py > index a22ea2bbc9..09eac2fbc3 100755 > --- a/localedata/unicode-gen/ctype_compatibility.py > +++ b/localedata/unicode-gen/ctype_compatibility.py > @@ -89,12 +89,12 @@ def extract_character_classes(filename): > 'tolower', > 'totitle']: > match = re.match(r'^(' > - +'(?:(?:class|map)\s+")' > + r'(?:(?:class|map)\s+")' > +re.escape(char_class)+ > - '(?:";)\s+' > - +'|' > - +re.escape(char_class)+'\s+' > - +')', line) > + r'(?:";)\s+' > + r'|' > + +re.escape(char_class)+r'\s+'+ > + r')', line) > if match: > if char_class not in ctype_dict: > ctype_dict[char_class] = [] > @@ -117,8 +117,8 @@ def process_chars(char_class_list, code_point_line): > continue > match = re.match( > r'^<U(?P<codepoint1>[0-9A-F]{4,8})>' > - +'\.\.'+ > - '<U(?P<codepoint2>[0-9A-F]{4,8})>$', > + r'\.\.' > + r'<U(?P<codepoint2>[0-9A-F]{4,8})>$', > code_points) > if match: # <Uxxxx>..<Uxxxx> > for codepoint in range( > @@ -128,8 +128,8 @@ def process_chars(char_class_list, code_point_line): > continue > match = re.match( > r'^<U(?P<codepoint1>[0-9A-F]{4,8})>' > - +'\.\.\(2\)\.\.'+ > - '<U(?P<codepoint2>[0-9A-F]{4,8})>$', > + r'\.\.\(2\)\.\.' > + r'<U(?P<codepoint2>[0-9A-F]{4,8})>$', > code_points) > if match: # <Uxxxx>..(2)..<Uxxxx> > for codepoint in range( > @@ -140,10 +140,10 @@ def process_chars(char_class_list, code_point_line): > continue > match = re.match( > r'^\(' > - +'<U(?P<codepoint1>[0-9A-F]{4,8})>' > - +','+ > - '<U(?P<codepoint2>[0-9A-F]{4,8})>' > - +'\)$', > + r'<U(?P<codepoint1>[0-9A-F]{4,8})>' > + r',' > + r'<U(?P<codepoint2>[0-9A-F]{4,8})>' > + r'\)$', > code_points) > if match: # (<Uxxxx>,<Uxxxx>) > char_class_list.append((
diff --git a/localedata/unicode-gen/ctype_compatibility.py b/localedata/unicode-gen/ctype_compatibility.py index a22ea2bbc9..09eac2fbc3 100755 --- a/localedata/unicode-gen/ctype_compatibility.py +++ b/localedata/unicode-gen/ctype_compatibility.py @@ -89,12 +89,12 @@ def extract_character_classes(filename): 'tolower', 'totitle']: match = re.match(r'^(' - +'(?:(?:class|map)\s+")' + r'(?:(?:class|map)\s+")' +re.escape(char_class)+ - '(?:";)\s+' - +'|' - +re.escape(char_class)+'\s+' - +')', line) + r'(?:";)\s+' + r'|' + +re.escape(char_class)+r'\s+'+ + r')', line) if match: if char_class not in ctype_dict: ctype_dict[char_class] = [] @@ -117,8 +117,8 @@ def process_chars(char_class_list, code_point_line): continue match = re.match( r'^<U(?P<codepoint1>[0-9A-F]{4,8})>' - +'\.\.'+ - '<U(?P<codepoint2>[0-9A-F]{4,8})>$', + r'\.\.' + r'<U(?P<codepoint2>[0-9A-F]{4,8})>$', code_points) if match: # <Uxxxx>..<Uxxxx> for codepoint in range( @@ -128,8 +128,8 @@ def process_chars(char_class_list, code_point_line): continue match = re.match( r'^<U(?P<codepoint1>[0-9A-F]{4,8})>' - +'\.\.\(2\)\.\.'+ - '<U(?P<codepoint2>[0-9A-F]{4,8})>$', + r'\.\.\(2\)\.\.' + r'<U(?P<codepoint2>[0-9A-F]{4,8})>$', code_points) if match: # <Uxxxx>..(2)..<Uxxxx> for codepoint in range( @@ -140,10 +140,10 @@ def process_chars(char_class_list, code_point_line): continue match = re.match( r'^\(' - +'<U(?P<codepoint1>[0-9A-F]{4,8})>' - +','+ - '<U(?P<codepoint2>[0-9A-F]{4,8})>' - +'\)$', + r'<U(?P<codepoint1>[0-9A-F]{4,8})>' + r',' + r'<U(?P<codepoint2>[0-9A-F]{4,8})>' + r'\)$', code_points) if match: # (<Uxxxx>,<Uxxxx>) char_class_list.append((