scripts: Fix risky uses of non-raw regex strings in Python scripts

Fixes pylint warnings like this one:

    doc/conf.py:325:0: W1401: Anomalous backslash in string: '\s'.
    String constant might be missing an r prefix.
    (anomalous-backslash-in-string)

The reason for this warning is that backslash escapes are interpreted in
non-raw (non-r-prefixed) strings. For example, '\a' and r'\a' are not
the same string (first one has a single ASCII bell character, second one
has two characters).

It just happens that there's no \s (or \., or \/) escape for example,
and '\s' turns into two characters (as needed for a regex). It's risky
to rely on stuff like that regexes though. Best to make them raw strings
unless they're super trivial.

Also note that '\s' and '\\s' turn into the same string.

Another tip: A literal ' can be put into a string with "blah'blah"
instead of 'blah\'blah'.

Signed-off-by: Ulf Magnusson <[email protected]>

Author: ulfalizer

doc/conf.py

@@ -322,7 +322,7 @@
 #'pointsize': '10pt',
 
 # Additional stuff for the LaTeX preamble.
-'preamble': '\setcounter{tocdepth}{2}',
+'preamble': r'\setcounter{tocdepth}{2}',
 
 # Latex figure (float) alignment
 #'figure_align': 'htbp',

doc/extensions/zephyr/application.py

@@ -14,7 +14,7 @@
 # This could be as simple as generating a couple of sets of instructions, one
 # for Unix environments, and another for Windows.
 class ZephyrAppCommandsDirective(Directive):
-    '''
+    r'''
     This is a Zephyr directive for generating consistent documentation
     of the shell commands needed to manage (build, flash, etc.) an application.
 

doc/extensions/zephyr/link-roles.py

@@ -30,7 +30,7 @@ def setup(app):
 
 def autolink(pattern):
     def role(name, rawtext, text, lineno, inliner, options={}, content=[]):
-        m = re.search('(.*)\s*<(.*)>', text)  # noqa: W605 - regular expression
+        m = re.search(r'(.*)\s*<(.*)>', text)
         if m:
             link_text = m.group(1)
             link = m.group(2)

doc/scripts/extract_content.py

@@ -81,7 +81,7 @@ def src_deps(zephyr_base, src_file, dest):
     # argument, which is a (relative) path to the additional
     # dependency file.
     directives = "|".join(DIRECTIVES)
-    pattern = re.compile("\.\.\s+(?P<directive>%s)::\s+(?P<dep_rel>.*)" %
+    pattern = re.compile(r"\.\.\s+(?P<directive>%s)::\s+(?P<dep_rel>.*)" %
                          directives)
     deps = []
     for l in content:

scripts/check_link_map.py

@@ -22,10 +22,10 @@
 # to write a valid linker script that will fail this script, but we
 # don't have such a use case and one isn't forseen.
 
-section_re = re.compile('(?x)'                    # (allow whitespace)
-                        '^([a-zA-Z0-9_\.]+) \s+'  # name
-                        ' (0x[0-9a-f]+)     \s+'  # addr
-                        ' (0x[0-9a-f]+)\s*')      # size
+section_re = re.compile(r'(?x)'                    # (allow whitespace)
+                        r'^([a-zA-Z0-9_\.]+) \s+'  # name
+                        r' (0x[0-9a-f]+)     \s+'  # addr
+                        r' (0x[0-9a-f]+)\s*')      # size
 
 load_addr_re = re.compile('load address (0x[0-9a-f]+)')
 

scripts/ci/get_modified_boards.py

@@ -60,7 +60,7 @@ def main():
     for f in files:
         if f.endswith(".rst") or f.endswith(".png") or f.endswith(".jpg"):
             continue
-        p = re.match("^boards\/[^/]+\/([^/]+)\/", f)
+        p = re.match(r"^boards\/[^/]+\/([^/]+)\/", f)
         if p and p.groups():
             boards.add(p.group(1))
 

scripts/filter-known-issues.py

@@ -43,7 +43,7 @@
 # first is a list of one or more comment lines
 # followed by a list of non-comments which describe a multiline regex
 config_regex = \
-    b"(?P<comment>(^\s*#.*\n)+)" \
+    b"(?P<comment>(^\\s*#.*\n)+)" \
     b"(?P<regex>(^[^#].*\n)+)"
 
 
@@ -87,7 +87,7 @@ def config_import_path(path):
     """
     Imports regular expresions from any file *.conf in the given path
     """
-    file_regex = re.compile(".*\.conf$")
+    file_regex = re.compile(r".*\.conf$")
     try:
         for dirpath, _, filenames in os.walk(path):
             for _filename in sorted(filenames):

scripts/gen_app_partitions.py

@@ -126,7 +126,7 @@ def parse_obj_files(partitions):
     # Iterate over all object files to find partitions
     for dirpath, _, files in os.walk(args.directory):
         for filename in files:
-            if re.match(".*\.obj$",filename):
+            if re.match(r".*\.obj$",filename):
                 fullname = os.path.join(dirpath, filename)
                 find_obj_file_partitions(fullname, partitions)
 

scripts/gitlint/zephyr_commit_rules.py

@@ -66,7 +66,7 @@ def validate(self, commit):
         flags |= re.IGNORECASE
         for line in commit.message.body:
             if line.lower().startswith("signed-off-by"):
-                if not re.search('(^)Signed-off-by: ([-\'\w.]+) ([-\'\w.]+) (.*)', line, flags=flags):
+                if not re.search(r"(^)Signed-off-by: ([-'\w.]+) ([-'\w.]+) (.*)", line, flags=flags):
                     return [RuleViolation(self.id, "Signed-off-by: must have a full name", line_nr=1)]
                 else:
                     return
@@ -106,7 +106,7 @@ class MaxLineLengthExceptions(LineRule):
 
     def validate(self, line, _commit):
         max_length = self.options['line-length'].value
-        urls = re.findall('http[s]?://(?:[a-zA-Z]|[0-9]|[$-_@.&+]|[!*\(\),]|(?:%[0-9a-fA-F][0-9a-fA-F]))+', line)
+        urls = re.findall(r'http[s]?://(?:[a-zA-Z]|[0-9]|[$-_@.&+]|[!*\(\),]|(?:%[0-9a-fA-F][0-9a-fA-F]))+', line)
         if line.startswith('Signed-off-by'):
             return
 

scripts/kconfig/checkconfig.py

@@ -105,9 +105,9 @@ def search_config_in_file(tree, items, completelog, exclude):
                 with open(os.path.join(dirName, fname), "r", encoding="utf-8", errors="ignore") as f:
                     searchConf = f.readlines()
                 for line in searchConf:
-                    if re.search('(^|[\s|(])CONFIG_([a-zA-Z0-9_]+)', line) :
-                        configName = re.search('(^|[\s|(])'
-                                               +'CONFIG_([a-zA-Z0-9_]+)', line)
+                    if re.search(r'(^|[\s|(])CONFIG_([a-zA-Z0-9_]+)', line) :
+                        configName = re.search(r'(^|[\s|(])'
+                                               + r'CONFIG_([a-zA-Z0-9_]+)', line)
                         configs = configs + 1
                         if completelog:
                             print('\n' + configName.group(2) + ' at '