diff options
Diffstat (limited to 'tools/lib/python/kdoc/kdoc_re.py')
| -rw-r--r-- | tools/lib/python/kdoc/kdoc_re.py | 205 |
1 files changed, 37 insertions, 168 deletions
diff --git a/tools/lib/python/kdoc/kdoc_re.py b/tools/lib/python/kdoc/kdoc_re.py index 0bf9e01cdc57..28292efe25a2 100644 --- a/tools/lib/python/kdoc/kdoc_re.py +++ b/tools/lib/python/kdoc/kdoc_re.py @@ -52,7 +52,33 @@ class KernRe: return self.regex.pattern def __repr__(self): - return f're.compile("{self.regex.pattern}")' + """ + Returns a displayable version of the class init. + """ + + flag_map = { + re.IGNORECASE: "re.I", + re.MULTILINE: "re.M", + re.DOTALL: "re.S", + re.VERBOSE: "re.X", + } + + flags = [] + for flag, name in flag_map.items(): + if self.regex.flags & flag: + flags.append(name) + + flags_name = " | ".join(flags) + + max_len = 60 + pattern = "" + for pos in range(0, len(self.regex.pattern), max_len): + pattern += '"' + self.regex.pattern[pos:max_len + pos] + '" ' + + if flags_name: + return f'KernRe({pattern}, {flags_name})' + else: + return f'KernRe({pattern})' def __add__(self, other): """ @@ -78,6 +104,13 @@ class KernRe: self.last_match = self.regex.search(string) return self.last_match + def finditer(self, string): + """ + Alias to re.finditer. + """ + + return self.regex.finditer(string) + def findall(self, string): """ Alias to re.findall. @@ -106,173 +139,9 @@ class KernRe: return self.last_match.group(num) - -class NestedMatch: - """ - Finding nested delimiters is hard with regular expressions. It is - even harder on Python with its normal re module, as there are several - advanced regular expressions that are missing. - - This is the case of this pattern:: - - '\\bSTRUCT_GROUP(\\(((?:(?>[^)(]+)|(?1))*)\\))[^;]*;' - - which is used to properly match open/close parentheses of the - string search STRUCT_GROUP(), - - Add a class that counts pairs of delimiters, using it to match and - replace nested expressions. - - The original approach was suggested by: - - https://stackoverflow.com/questions/5454322/python-how-to-match-nested-parentheses-with-regex - - Although I re-implemented it to make it more generic and match 3 types - of delimiters. The logic checks if delimiters are paired. If not, it - will ignore the search string. - """ - - # TODO: make NestedMatch handle multiple match groups - # - # Right now, regular expressions to match it are defined only up to - # the start delimiter, e.g.: - # - # \bSTRUCT_GROUP\( - # - # is similar to: STRUCT_GROUP\((.*)\) - # except that the content inside the match group is delimiter-aligned. - # - # The content inside parentheses is converted into a single replace - # group (e.g. r`\1'). - # - # It would be nice to change such definition to support multiple - # match groups, allowing a regex equivalent to: - # - # FOO\((.*), (.*), (.*)\) - # - # it is probably easier to define it not as a regular expression, but - # with some lexical definition like: - # - # FOO(arg1, arg2, arg3) - - DELIMITER_PAIRS = { - '{': '}', - '(': ')', - '[': ']', - } - - RE_DELIM = re.compile(r'[\{\}\[\]\(\)]') - - def _search(self, regex, line): - """ - Finds paired blocks for a regex that ends with a delimiter. - - The suggestion of using finditer to match pairs came from: - https://stackoverflow.com/questions/5454322/python-how-to-match-nested-parentheses-with-regex - but I ended using a different implementation to align all three types - of delimiters and seek for an initial regular expression. - - The algorithm seeks for open/close paired delimiters and places them - into a stack, yielding a start/stop position of each match when the - stack is zeroed. - - The algorithm should work fine for properly paired lines, but will - silently ignore end delimiters that precede a start delimiter. - This should be OK for kernel-doc parser, as unaligned delimiters - would cause compilation errors. So, we don't need to raise exceptions - to cover such issues. - """ - - stack = [] - - for match_re in regex.finditer(line): - start = match_re.start() - offset = match_re.end() - - d = line[offset - 1] - if d not in self.DELIMITER_PAIRS: - continue - - end = self.DELIMITER_PAIRS[d] - stack.append(end) - - for match in self.RE_DELIM.finditer(line[offset:]): - pos = match.start() + offset - - d = line[pos] - - if d in self.DELIMITER_PAIRS: - end = self.DELIMITER_PAIRS[d] - - stack.append(end) - continue - - # Does the end delimiter match what is expected? - if stack and d == stack[-1]: - stack.pop() - - if not stack: - yield start, offset, pos + 1 - break - - def search(self, regex, line): + def groups(self): """ - This is similar to re.search: - - It matches a regex that it is followed by a delimiter, - returning occurrences only if all delimiters are paired. + Returns the group results of the last match """ - for t in self._search(regex, line): - - yield line[t[0]:t[2]] - - def sub(self, regex, sub, line, count=0): - r""" - This is similar to re.sub: - - It matches a regex that it is followed by a delimiter, - replacing occurrences only if all delimiters are paired. - - if the sub argument contains:: - - r'\1' - - it will work just like re: it places there the matched paired data - with the delimiter stripped. - - If count is different than zero, it will replace at most count - items. - """ - out = "" - - cur_pos = 0 - n = 0 - - for start, end, pos in self._search(regex, line): - out += line[cur_pos:start] - - # Value, ignoring start/end delimiters - value = line[end:pos - 1] - - # replaces \1 at the sub string, if \1 is used there - new_sub = sub - new_sub = new_sub.replace(r'\1', value) - - out += new_sub - - # Drop end ';' if any - if line[pos] == ';': - pos += 1 - - cur_pos = pos - n += 1 - - if count and count >= n: - break - - # Append the remaining string - l = len(line) - out += line[cur_pos:l] - - return out + return self.last_match.groups() |