Re: [PATCH v2 5/7] tools/perf: fix Python string escapes

On 12/9/23 8:56 pm, Adrian Hunter wrote:
> On 12/09/23 09:07, Benjamin Gray wrote:
>> diff --git a/tools/perf/pmu-events/jevents.py b/tools/perf/pmu-events/jevents.py
>> index a7e88332276d..980f080a5a2c 100755
>> --- a/tools/perf/pmu-events/jevents.py
>> +++ b/tools/perf/pmu-events/jevents.py
>> @@ -83,7 +83,7 @@ def c_len(s: str) -> int:
>>     """Return the length of s a C string
>>   
>>     This doesn't handle all escape characters properly. It first assumes
>> -  all \ are for escaping, it then adjusts as it will have over counted
>> +  all \\ are for escaping, it then adjusts as it will have over counted
> 
> It looks like the whole string should be a raw string
> 
...
>> -				s = value.replace("%", "\%")
>> -				s = s.replace("_", "\_")
>> +				s = value.replace("%", "\\%")
>> +				s = s.replace("_", "\\_")
> 
> Raw strings seem more readable, so could be
> used here too

Yeah, sounds good. I normally use r strings only for regex, but there 
shouldn't be any ambiguity here (it might have been misleading if the 
search argument to replace looked like a regex).

Having the docstring be an r string is a good catch. There's probably a 
few like that in the kernel, but finding them is a little more 
complicated because they might be 'valid' syntax (e.g., the '\000' just 
becomes a null byte. This series is focused on the syntax errors though, 
so I'll just leave it be.

How is the following?
---
Subject: [PATCH] tools/perf: fix Python string escapes

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 <[email protected]>
---
  tools/perf/pmu-events/jevents.py                 | 2 +-
  tools/perf/scripts/python/arm-cs-trace-disasm.py | 4 ++--
  tools/perf/scripts/python/compaction-times.py    | 2 +-
  tools/perf/scripts/python/exported-sql-viewer.py | 4 ++--
  4 files changed, 6 insertions(+), 6 deletions(-)

diff --git a/tools/perf/pmu-events/jevents.py 
b/tools/perf/pmu-events/jevents.py
index a7e88332276d..1b4519333a28 100755
--- a/tools/perf/pmu-events/jevents.py
+++ b/tools/perf/pmu-events/jevents.py
@@ -80,7 +80,7 @@ def file_name_to_table_name(prefix: str, parents: 
Sequence[str],


  def c_len(s: str) -> int:
-  """Return the length of s a C string
+  r"""Return the length of s a C string

    This doesn't handle all escape characters properly. It first assumes
    all \ are for escaping, it then adjusts as it will have over counted
diff --git a/tools/perf/scripts/python/arm-cs-trace-disasm.py 
b/tools/perf/scripts/python/arm-cs-trace-disasm.py
index d59ff53f1d94..de58991c78bb 100755
--- a/tools/perf/scripts/python/arm-cs-trace-disasm.py
+++ b/tools/perf/scripts/python/arm-cs-trace-disasm.py
@@ -45,8 +45,8 @@ parser = OptionParser(option_list=option_list)
  # Initialize global dicts and regular expression
  disasm_cache = dict()
  cpu_data = dict()
-disasm_re = re.compile("^\s*([0-9a-fA-F]+):")
-disasm_func_re = re.compile("^\s*([0-9a-fA-F]+)\s.*:")
+disasm_re = re.compile(r"^\s*([0-9a-fA-F]+):")
+disasm_func_re = re.compile(r"^\s*([0-9a-fA-F]+)\s.*:")
  cache_size = 64*1024

  glb_source_file_name	= None
diff --git a/tools/perf/scripts/python/compaction-times.py 
b/tools/perf/scripts/python/compaction-times.py
index 2560a042dc6f..9401f7c14747 100644
--- a/tools/perf/scripts/python/compaction-times.py
+++ b/tools/perf/scripts/python/compaction-times.py
@@ -260,7 +260,7 @@ def pr_help():

  comm_re = None
  pid_re = None
-pid_regex = "^(\d*)-(\d*)$|^(\d*)$"
+pid_regex = r"^(\d*)-(\d*)$|^(\d*)$"

  opt_proc = popt.DISP_DFL
  opt_disp = topt.DISP_ALL
diff --git a/tools/perf/scripts/python/exported-sql-viewer.py 
b/tools/perf/scripts/python/exported-sql-viewer.py
index 13f2d8a81610..78763531fe5a 100755
--- a/tools/perf/scripts/python/exported-sql-viewer.py
+++ b/tools/perf/scripts/python/exported-sql-viewer.py
@@ -677,8 +677,8 @@ class CallGraphModelBase(TreeModel):
  			#   sqlite supports GLOB (text only) which uses * and ? and is case 
sensitive
  			if not self.glb.dbref.is_sqlite3:
  				# Escape % and _
-				s = value.replace("%", "\%")
-				s = s.replace("_", "\_")
+				s = value.replace("%", r"\%")
+				s = s.replace("_", r"\_")
  				# Translate * and ? into SQL LIKE pattern characters % and _
  				trans = string.maketrans("*?", "%_")
  				match = " LIKE '" + str(s).translate(trans) + "'"
-- 
2.41.0