| Message ID | 20230814060704.79655-3-bgray@linux.ibm.com (mailing list archive) |
|---|---|
| State | Handled Elsewhere, archived |
| Headers | show |
| Series | Fix Python string escapes | expand |
Benjamin Gray <bgray@linux.ibm.com> writes: > Python 3.6 introduced a DeprecationWarning for invalid escape sequences. > This is upgraded to a SyntaxWarning in Python 3.12, and will eventually > be a syntax error. > > Fix these now to get ahead of it before it's an error. > > Signed-off-by: Benjamin Gray <bgray@linux.ibm.com> > --- > Documentation/sphinx/cdomain.py | 2 +- > Documentation/sphinx/kernel_abi.py | 2 +- > Documentation/sphinx/kernel_feat.py | 2 +- > Documentation/sphinx/kerneldoc.py | 2 +- > Documentation/sphinx/maintainers_include.py | 8 ++++---- > 5 files changed, 8 insertions(+), 8 deletions(-) So I am the maintainer for this stuff...is there a reason you didn't copy me on this work? > diff --git a/Documentation/sphinx/cdomain.py b/Documentation/sphinx/cdomain.py > index ca8ac9e59ded..dbdc74bd0772 100644 > --- a/Documentation/sphinx/cdomain.py > +++ b/Documentation/sphinx/cdomain.py > @@ -93,7 +93,7 @@ def markup_ctype_refs(match): > # > RE_expr = re.compile(r':c:(expr|texpr):`([^\`]+)`') > def markup_c_expr(match): > - return '\ ``' + match.group(2) + '``\ ' > + return '\\ ``' + match.group(2) + '``\\ ' I have to wonder about this one; I doubt the intent was to insert a literal backslash. I have to fire up my ancient build environment to even try this, but even if it's right... > # > # Parse Sphinx 3.x C markups, replacing them by backward-compatible ones > diff --git a/Documentation/sphinx/kernel_abi.py b/Documentation/sphinx/kernel_abi.py > index b5feb5b1d905..b9f026f016fd 100644 > --- a/Documentation/sphinx/kernel_abi.py > +++ b/Documentation/sphinx/kernel_abi.py > @@ -138,7 +138,7 @@ class KernelCmd(Directive): > code_block += "\n " + l > lines = code_block + "\n\n" > > - line_regex = re.compile("^\.\. LINENO (\S+)\#([0-9]+)$") > + line_regex = re.compile("^\\.\\. LINENO (\\S+)\\#([0-9]+)$") All of these really just want to be raw strings - a much more minimal fix that makes the result quite a bit more readable: line_regex = re.compile(r"^\.\. LINENO (\S+)\#([0-9]+)$") ^ | ---------------------------+ That, I think, is how these should be fixed. Thanks, jon
On 14/8/23 11:35 pm, Jonathan Corbet wrote: > Benjamin Gray <bgray@linux.ibm.com> writes: > >> Python 3.6 introduced a DeprecationWarning for invalid escape sequences. >> This is upgraded to a SyntaxWarning in Python 3.12, and will eventually >> be a syntax error. >> >> Fix these now to get ahead of it before it's an error. >> >> Signed-off-by: Benjamin Gray <bgray@linux.ibm.com> >> --- >> Documentation/sphinx/cdomain.py | 2 +- >> Documentation/sphinx/kernel_abi.py | 2 +- >> Documentation/sphinx/kernel_feat.py | 2 +- >> Documentation/sphinx/kerneldoc.py | 2 +- >> Documentation/sphinx/maintainers_include.py | 8 ++++---- >> 5 files changed, 8 insertions(+), 8 deletions(-) > > So I am the maintainer for this stuff...is there a reason you didn't > copy me on this work? Sorry, I thought the list linux-doc@vger.kernel.org itself was enough. I haven't done a cross tree series before, I was a bit adverse to CC'ing everyone that appears as a maintainer for every patch. > >> diff --git a/Documentation/sphinx/cdomain.py b/Documentation/sphinx/cdomain.py >> index ca8ac9e59ded..dbdc74bd0772 100644 >> --- a/Documentation/sphinx/cdomain.py >> +++ b/Documentation/sphinx/cdomain.py >> @@ -93,7 +93,7 @@ def markup_ctype_refs(match): >> # >> RE_expr = re.compile(r':c:(expr|texpr):`([^\`]+)`') >> def markup_c_expr(match): >> - return '\ ``' + match.group(2) + '``\ ' >> + return '\\ ``' + match.group(2) + '``\\ ' > > I have to wonder about this one; I doubt the intent was to insert a > literal backslash. I have to fire up my ancient build environment to > even try this, but even if it's right... Yeah, there is even a file that just has a syntax error. I don't have a way to verify the original script was correct, but I have verified this series doesn't change the parsed AST. In this case though, it's generating reST, so it might just be conservatively guarding against generating bad markup[1] [1]: https://www.sphinx-doc.org/en/master/usage/restructuredtext/basics.html#inline-markup >> # >> # Parse Sphinx 3.x C markups, replacing them by backward-compatible ones >> diff --git a/Documentation/sphinx/kernel_abi.py b/Documentation/sphinx/kernel_abi.py >> index b5feb5b1d905..b9f026f016fd 100644 >> --- a/Documentation/sphinx/kernel_abi.py >> +++ b/Documentation/sphinx/kernel_abi.py >> @@ -138,7 +138,7 @@ class KernelCmd(Directive): >> code_block += "\n " + l >> lines = code_block + "\n\n" >> >> - line_regex = re.compile("^\.\. LINENO (\S+)\#([0-9]+)$") >> + line_regex = re.compile("^\\.\\. LINENO (\\S+)\\#([0-9]+)$") > > All of these really just want to be raw strings - a much more minimal > fix that makes the result quite a bit more readable: > > line_regex = re.compile(r"^\.\. LINENO (\S+)\#([0-9]+)$") > ^ > | > ---------------------------+ > > That, I think, is how these should be fixed. Yup, I mentioned that at the end of the cover letter. I can automate and verify the conversion, but automating what _should_ be treated as a 'regex' string is fuzzier. Checking if there's a `re.*(` prefix on the string should work for most though. I'll give it a shot. > Thanks, > > jon
diff --git a/Documentation/sphinx/cdomain.py b/Documentation/sphinx/cdomain.py index ca8ac9e59ded..dbdc74bd0772 100644 --- a/Documentation/sphinx/cdomain.py +++ b/Documentation/sphinx/cdomain.py @@ -93,7 +93,7 @@ def markup_ctype_refs(match): # RE_expr = re.compile(r':c:(expr|texpr):`([^\`]+)`') def markup_c_expr(match): - return '\ ``' + match.group(2) + '``\ ' + return '\\ ``' + match.group(2) + '``\\ ' # # Parse Sphinx 3.x C markups, replacing them by backward-compatible ones diff --git a/Documentation/sphinx/kernel_abi.py b/Documentation/sphinx/kernel_abi.py index b5feb5b1d905..b9f026f016fd 100644 --- a/Documentation/sphinx/kernel_abi.py +++ b/Documentation/sphinx/kernel_abi.py @@ -138,7 +138,7 @@ class KernelCmd(Directive): code_block += "\n " + l lines = code_block + "\n\n" - line_regex = re.compile("^\.\. LINENO (\S+)\#([0-9]+)$") + line_regex = re.compile("^\\.\\. LINENO (\\S+)\\#([0-9]+)$") ln = 0 n = 0 f = fname diff --git a/Documentation/sphinx/kernel_feat.py b/Documentation/sphinx/kernel_feat.py index 27b701ed3681..d17adc1a367a 100644 --- a/Documentation/sphinx/kernel_feat.py +++ b/Documentation/sphinx/kernel_feat.py @@ -104,7 +104,7 @@ class KernelFeat(Directive): lines = self.runCmd(cmd, shell=True, cwd=cwd, env=shell_env) - line_regex = re.compile("^\.\. FILE (\S+)$") + line_regex = re.compile("^\\.\\. FILE (\\S+)$") out_lines = "" diff --git a/Documentation/sphinx/kerneldoc.py b/Documentation/sphinx/kerneldoc.py index 9395892c7ba3..d6ec34ce2232 100644 --- a/Documentation/sphinx/kerneldoc.py +++ b/Documentation/sphinx/kerneldoc.py @@ -130,7 +130,7 @@ class KernelDocDirective(Directive): result = ViewList() lineoffset = 0; - line_regex = re.compile("^\.\. LINENO ([0-9]+)$") + line_regex = re.compile("^\\.\\. LINENO ([0-9]+)$") for line in lines: match = line_regex.search(line) if match: diff --git a/Documentation/sphinx/maintainers_include.py b/Documentation/sphinx/maintainers_include.py index 328b3631a585..73be47963153 100755 --- a/Documentation/sphinx/maintainers_include.py +++ b/Documentation/sphinx/maintainers_include.py @@ -77,7 +77,7 @@ class MaintainersInclude(Include): line = line.rstrip() # Linkify all non-wildcard refs to ReST files in Documentation/. - pat = '(Documentation/([^\s\?\*]*)\.rst)' + pat = '(Documentation/([^\\s\\?\\*]*)\\.rst)' m = re.search(pat, line) if m: # maintainers.rst is in a subdirectory, so include "../". @@ -90,11 +90,11 @@ class MaintainersInclude(Include): output = "| %s" % (line.replace("\\", "\\\\")) # Look for and record field letter to field name mappings: # R: Designated *reviewer*: FullName <address@domain> - m = re.search("\s(\S):\s", line) + m = re.search("\\s(\\S):\\s", line) if m: field_letter = m.group(1) if field_letter and not field_letter in fields: - m = re.search("\*([^\*]+)\*", line) + m = re.search("\\*([^\\*]+)\\*", line) if m: fields[field_letter] = m.group(1) elif subsystems: @@ -112,7 +112,7 @@ class MaintainersInclude(Include): field_content = "" # Collapse whitespace in subsystem name. - heading = re.sub("\s+", " ", line) + heading = re.sub("\\s+", " ", line) output = output + "%s\n%s" % (heading, "~" * len(heading)) field_prev = "" else:
Python 3.6 introduced a DeprecationWarning for invalid escape sequences. This is upgraded to a SyntaxWarning in Python 3.12, and will eventually be a syntax error. Fix these now to get ahead of it before it's an error. Signed-off-by: Benjamin Gray <bgray@linux.ibm.com> --- Documentation/sphinx/cdomain.py | 2 +- Documentation/sphinx/kernel_abi.py | 2 +- Documentation/sphinx/kernel_feat.py | 2 +- Documentation/sphinx/kerneldoc.py | 2 +- Documentation/sphinx/maintainers_include.py | 8 ++++---- 5 files changed, 8 insertions(+), 8 deletions(-)