comparison mercurial/util.py @ 46802:112826b59476 stable

re2: feed unicode string to re2 module when necessary

My previous test were using the `pyre2` Python project, that wrap the Google RE2 library
in python as a `re2` module and accept bytes as input. However the `fb-re2`
Python project is also offering a wrapping of the Google RE2 library in python
as a `re2` module ans accept only unicode on python3. So we detect this
situation and convert thing to unicode when necessary.

Hooray…

We should consider using a rust wrapping for regexp handling. We needs regexps
in Rust anyway and this give use more control with less variants and more
sanity.

Differential Revision: https://phab.mercurial-scm.org/D10284

46793:86b47ec1960a

        return True
    except OSError:
        return True


try:
    import re2  # pytype: disable=import-error

    _re2 = None
except ImportError:

class _re(object):
    def _checkre2(self):
        global _re2
        try:
            # check if match works, see issue3964
            _re2 = bool(re2.match(br'\[([^\[]+)\]', b'[ui]'))
        except ImportError:
            _re2 = False

    def compile(self, pat, flags=0):
        """Compile a regular expression, using re2 if possible

        For best performance, use only re2-compatible regexp features. The

            if flags & remod.IGNORECASE:
                pat = b'(?i)' + pat
            if flags & remod.MULTILINE:
                pat = b'(?m)' + pat
            try:
                return re2.compile(pat)
            except re2.error:
                pass
        return remod.compile(pat, flags)

    @propertycache

46802:112826b59476

        return True
    except OSError:
        return True


_re2_input = lambda x: x
try:
    import re2  # pytype: disable=import-error

    _re2 = None
except ImportError:

class _re(object):
    def _checkre2(self):
        global _re2
        global _re2_input
        try:
            # check if match works, see issue3964
            check_pattern = br'\[([^\[]+)\]'
            check_input = b'[ui]'
            _re2 = bool(re2.match(check_pattern, check_input))
        except ImportError:
            _re2 = False
        except TypeError:
            # the `pyre-2` project provides a re2 module that accept bytes
            # the `fb-re2` project provides a re2 module that acccept sysstr
            check_pattern = pycompat.sysstr(check_pattern)
            check_input = pycompat.sysstr(check_input)
            _re2 = bool(re2.match(check_pattern, check_input))
            _re2_input = pycompat.sysstr

    def compile(self, pat, flags=0):
        """Compile a regular expression, using re2 if possible

        For best performance, use only re2-compatible regexp features. The

            if flags & remod.IGNORECASE:
                pat = b'(?i)' + pat
            if flags & remod.MULTILINE:
                pat = b'(?m)' + pat
            try:
                return re2.compile(_re2_input(pat))
            except re2.error:
                pass
        return remod.compile(pat, flags)

    @propertycache