# stringutil.py - utility for generic string formatting, parsing, etc.

#

#  Copyright 2005 K. Thananchayan <thananck@yahoo.com>

#  Copyright 2005-2007 Matt Mackall <mpm@selenic.com>

#  Copyright 2006 Vadim Gelfer <vadim.gelfer@gmail.com>

#

# This software may be used and distributed according to the terms of the

# GNU General Public License version 2 or any later version.

from __future__ import absolute_import

import codecs

import re as remod

import textwrap

from ..i18n import _

from ..thirdparty import attr

from .. import (

    encoding,

    error,

    pycompat,

)

_DATA_ESCAPE_MAP = {pycompat.bytechr(i): br'\x%02x' % i for i in range(256)}

_DATA_ESCAPE_MAP.update({

    b'\\': b'\\\\',

    b'\r': br'\r',

    b'\n': br'\n',

})

_DATA_ESCAPE_RE = remod.compile(br'[\x00-\x08\x0a-\x1f\\\x7f-\xff]')

def escapedata(s):

    if isinstance(s, bytearray):

        s = bytes(s)

    return _DATA_ESCAPE_RE.sub(lambda m: _DATA_ESCAPE_MAP[m.group(0)], s)

def binary(s):

    """return true if a string is binary data"""

    return bool(s and '\0' in s)

def stringmatcher(pattern, casesensitive=True):

    """

    accepts a string, possibly starting with 're:' or 'literal:' prefix.

    returns the matcher name, pattern, and matcher function.

    missing or unknown prefixes are treated as literal matches.

    helper for tests:

    >>> def test(pattern, *tests):

    ...     kind, pattern, matcher = stringmatcher(pattern)

    ...     return (kind, pattern, [bool(matcher(t)) for t in tests])

    >>> def itest(pattern, *tests):

    ...     kind, pattern, matcher = stringmatcher(pattern, casesensitive=False)

    ...     return (kind, pattern, [bool(matcher(t)) for t in tests])

    exact matching (no prefix):

    >>> test(b'abcdefg', b'abc', b'def', b'abcdefg')

    ('literal', 'abcdefg', [False, False, True])

    regex matching ('re:' prefix)

    >>> test(b're:a.+b', b'nomatch', b'fooadef', b'fooadefbar')

    ('re', 'a.+b', [False, False, True])

    force exact matches ('literal:' prefix)

    >>> test(b'literal:re:foobar', b'foobar', b're:foobar')

    ('literal', 're:foobar', [False, True])

    unknown prefixes are ignored and treated as literals

    >>> test(b'foo:bar', b'foo', b'bar', b'foo:bar')

    ('literal', 'foo:bar', [False, False, True])

    case insensitive regex matches

    >>> itest(b're:A.+b', b'nomatch', b'fooadef', b'fooadefBar')

    ('re', 'A.+b', [False, False, True])

    case insensitive literal matches

    >>> itest(b'ABCDEFG', b'abc', b'def', b'abcdefg')

    ('literal', 'ABCDEFG', [False, False, True])

    """

    if pattern.startswith('re:'):

        pattern = pattern[3:]

        try:

            flags = 0

            if not casesensitive:

                flags = remod.I

            regex = remod.compile(pattern, flags)

        except remod.error as e:

            raise error.ParseError(_('invalid regular expression: %s')

                                   % e)

        return 're', pattern, regex.search

    elif pattern.startswith('literal:'):

        pattern = pattern[8:]

    match = pattern.__eq__

    if not casesensitive:

        ipat = encoding.lower(pattern)

        match = lambda s: ipat == encoding.lower(s)

    return 'literal', pattern, match

def shortuser(user):

    """Return a short representation of a user name or email address."""

    f = user.find('@')

    if f >= 0:

        user = user[:f]

    f = user.find('<')

    if f >= 0:

        user = user[f + 1:]

    f = user.find(' ')

    if f >= 0:

        user = user[:f]

    f = user.find('.')

    if f >= 0:

        user = user[:f]

    return user

def emailuser(user):

    """Return the user portion of an email address."""

    f = user.find('@')

    if f >= 0:

        user = user[:f]

    f = user.find('<')

    if f >= 0:

        user = user[f + 1:]

    return user

def email(author):

    '''get email of author.'''

    r = author.find('>')

    if r == -1:

        r = None

    return author[author.find('<') + 1:r]

def person(author):

    """Returns the name before an email address,

    interpreting it as per RFC 5322

    >>> person(b'foo@bar')

    'foo'

    >>> person(b'Foo Bar <foo@bar>')

    'Foo Bar'

    >>> person(b'"Foo Bar" <foo@bar>')

    'Foo Bar'

    >>> person(b'"Foo \"buz\" Bar" <foo@bar>')

    'Foo "buz" Bar'

    >>> # The following are invalid, but do exist in real-life

    ...

    >>> person(b'Foo "buz" Bar <foo@bar>')

    'Foo "buz" Bar'

    >>> person(b'"Foo Bar <foo@bar>')

    'Foo Bar'

    """

    if '@' not in author:

        return author

    f = author.find('<')

    if f != -1:

        return author[:f].strip(' "').replace('\\"', '"')

    f = author.find('@')

    return author[:f].replace('.', ' ')

@attr.s(hash=True)

class mailmapping(object):

    '''Represents a username/email key or value in

    a mailmap file'''

    email = attr.ib()

    name = attr.ib(default=None)

def parsemailmap(mailmapcontent):

    """Parses data in the .mailmap format

    >>> mmdata = b"\\n".join([

    ... b'# Comment',

    ... b'Name <commit1@email.xx>',

    ... b'<name@email.xx> <commit2@email.xx>',

    ... b'Name <proper@email.xx> <commit3@email.xx>',

    ... b'Name <proper@email.xx> Commit <commit4@email.xx>',

    ... ])

    >>> mm = parsemailmap(mmdata)

    >>> for key in sorted(mm.keys()):

    ...     print(key)

    mailmapping(email='commit1@email.xx', name=None)

    mailmapping(email='commit2@email.xx', name=None)

    mailmapping(email='commit3@email.xx', name=None)

    mailmapping(email='commit4@email.xx', name='Commit')

    >>> for val in sorted(mm.values()):

    ...     print(val)

    mailmapping(email='commit1@email.xx', name='Name')

    mailmapping(email='name@email.xx', name=None)

    mailmapping(email='proper@email.xx', name='Name')

    mailmapping(email='proper@email.xx', name='Name')

    """

    mailmap = {}

    if mailmapcontent is None:

        return mailmap

    for line in mailmapcontent.splitlines():

        # Don't bother checking the line if it is a comment or

        # is an improperly formed author field

            continue

        # names, emails hold the parsed emails and names for each line

        # name_builder holds the words in a persons name

        names, emails = [], []

        namebuilder = []

        for element in line.split():

            if element.startswith('#'):

                # If we reach a comment in the mailmap file, move on

                break

            elif element.startswith('<') and element.endswith('>'):

                # We have found an email.

                # Parse it, and finalize any names from earlier

                emails.append(element[1:-1])  # Slice off the "<>"

                if namebuilder:

                    names.append(' '.join(namebuilder))

                    namebuilder = []

                # Break if we have found a second email, any other

                # data does not fit the spec for .mailmap

                if len(emails) > 1:

                    break

            else:

                # We have found another word in the committers name

                namebuilder.append(element)

        mailmapkey = mailmapping(

            email=emails[-1],

            name=names[-1] if len(names) == 2 else None,

        )

        mailmap[mailmapkey] = mailmapping(

            email=emails[0],

            name=names[0] if names else None,

        )

    return mailmap

def mapname(mailmap, author):

    """Returns the author field according to the mailmap cache, or

    the original author field.

    >>> mmdata = b"\\n".join([

    ...     b'# Comment',

    ...     b'Name <commit1@email.xx>',

    ...     b'<name@email.xx> <commit2@email.xx>',

    ...     b'Name <proper@email.xx> <commit3@email.xx>',

    ...     b'Name <proper@email.xx> Commit <commit4@email.xx>',

    ... ])

    >>> m = parsemailmap(mmdata)

    >>> mapname(m, b'Commit <commit1@email.xx>')

    'Name <commit1@email.xx>'

    >>> mapname(m, b'Name <commit2@email.xx>')

    'Name <name@email.xx>'

    >>> mapname(m, b'Commit <commit3@email.xx>')

    'Name <proper@email.xx>'

    >>> mapname(m, b'Commit <commit4@email.xx>')

    'Name <proper@email.xx>'

    >>> mapname(m, b'Unknown Name <unknown@email.com>')

    'Unknown Name <unknown@email.com>'

    """

    # If the author field coming in isn't in the correct format,

    # or the mailmap is empty just return the original author field

    if not isauthorwellformed(author) or not mailmap:

        return author

    # Turn the user name into a mailmaptup

    commit = mailmapping(name=person(author), email=email(author))

    try:

        # Try and use both the commit email and name as the key

        proper = mailmap[commit]

    except KeyError:

        # If the lookup fails, use just the email as the key instead

        # We call this commit2 as not to erase original commit fields

        commit2 = mailmapping(email=commit.email)

        proper = mailmap.get(commit2, mailmapping(None, None))

    # Return the author field with proper values filled in

    return '%s <%s>' % (

        proper.name if proper.name else commit.name,

        proper.email if proper.email else commit.email,

    )

_correctauthorformat = remod.compile(br'^[^<]+\s\<[^<>]+@[^<>]+\>$')

def isauthorwellformed(author):

    '''Return True if the author field is well formed

    (ie "Contributor Name <contrib@email.dom>")

    >>> isauthorwellformed(b'Good Author <good@author.com>')

    True

    >>> isauthorwellformed(b'Author <good@author.com>')

    True

    >>> isauthorwellformed(b'Bad Author')

    False

    >>> isauthorwellformed(b'Bad Author <author@author.com')

    False

    >>> isauthorwellformed(b'Bad Author author@author.com')

    False

    >>> isauthorwellformed(b'<author@author.com>')

    False

    >>> isauthorwellformed(b'Bad Author <author>')

    False

    '''

    return _correctauthorformat.match(author) is not None

def ellipsis(text, maxlength=400):

    """Trim string to at most maxlength (default: 400) columns in display."""

    return encoding.trim(text, maxlength, ellipsis='...')

def escapestr(s):

    # call underlying function of s.encode('string_escape') directly for

    # Python 3 compatibility

    return codecs.escape_encode(s)[0]

def unescapestr(s):

    return codecs.escape_decode(s)[0]

def forcebytestr(obj):

    """Portably format an arbitrary object (e.g. exception) into a byte

    string."""

    try:

        return pycompat.bytestr(obj)

    except UnicodeEncodeError:

        # non-ascii string, may be lossy

        return pycompat.bytestr(encoding.strtolocal(str(obj)))

def uirepr(s):

    # Avoid double backslash in Windows path repr()

    return pycompat.byterepr(pycompat.bytestr(s)).replace(b'\\\\', b'\\')

# delay import of textwrap

def _MBTextWrapper(**kwargs):

    class tw(textwrap.TextWrapper):

        """

        Extend TextWrapper for width-awareness.

        Neither number of 'bytes' in any encoding nor 'characters' is

        appropriate to calculate terminal columns for specified string.

        Original TextWrapper implementation uses built-in 'len()' directly,

        so overriding is needed to use width information of each characters.

        In addition, characters classified into 'ambiguous' width are

        treated as wide in East Asian area, but as narrow in other.

        This requires use decision to determine width of such characters.

        """

        def _cutdown(self, ucstr, space_left):

            l = 0

            colwidth = encoding.ucolwidth

            for i in xrange(len(ucstr)):

                l += colwidth(ucstr[i])

                if space_left < l:

                    return (ucstr[:i], ucstr[i:])

            return ucstr, ''

        # overriding of base class

        def _handle_long_word(self, reversed_chunks, cur_line, cur_len, width):

            space_left = max(width - cur_len, 1)

            if self.break_long_words:

                cut, res = self._cutdown(reversed_chunks[-1], space_left)

                cur_line.append(cut)

                reversed_chunks[-1] = res

            elif not cur_line:

                cur_line.append(reversed_chunks.pop())

        # this overriding code is imported from TextWrapper of Python 2.6

        # to calculate columns of string by 'encoding.ucolwidth()'