# -*- coding: utf-8 -*-
"""
    jinja2.ext
    ~~~~~~~~~~

    Jinja extensions allow to add custom tags similar to the way django custom
    tags work.  By default two example extensions exist: an i18n and a cache
    extension.

    :copyright: (c) 2017 by the Jinja Team.
    :license: BSD.
"""
import re

from jinja2 import nodes
from jinja2.defaults import BLOCK_START_STRING, \
     BLOCK_END_STRING, VARIABLE_START_STRING, VARIABLE_END_STRING, \
     COMMENT_START_STRING, COMMENT_END_STRING, LINE_STATEMENT_PREFIX, \
     LINE_COMMENT_PREFIX, TRIM_BLOCKS, NEWLINE_SEQUENCE, \
     KEEP_TRAILING_NEWLINE, LSTRIP_BLOCKS
from jinja2.environment import Environment
from jinja2.runtime import concat
from jinja2.exceptions import TemplateAssertionError, TemplateSyntaxError
from jinja2.utils import contextfunction, import_string, Markup
from jinja2._compat import with_metaclass, string_types, iteritems


# the only real useful gettext functions for a Jinja template.  Note
# that ugettext must be assigned to gettext as Jinja doesn't support
# non unicode strings.
GETTEXT_FUNCTIONS = ('_', 'gettext', 'ngettext')


class ExtensionRegistry(type):
    """Gives the extension an unique identifier."""

    def __new__(cls, name, bases, d):
        rv = type.__new__(cls, name, bases, d)
        rv.identifier = rv.__module__ + '.' + rv.__name__
        return rv


class Extension(with_metaclass(ExtensionRegistry, object)):
    """Extensions can be used to add extra functionality to the Jinja template
    system at the parser level.  Custom extensions are bound to an environment
    but may not store environment specific data on `self`.  The reason for
    this is that an extension can be bound to another environment (for
    overlays) by creating a copy and reassigning the `environment` attribute.

    As extensions are created by the environment they cannot accept any
    arguments for configuration.  One may want to work around that by using
    a factory function, but that is not possible as extensions are identified
    by their import name.  The correct way to configure the extension is
    storing the configuration values on the environment.  Because this way the
    environment ends up acting as central configuration storage the
    attributes may clash which is why extensions have to ensure that the names
    they choose for configuration are not too generic.  ``prefix`` for example
    is a terrible name, ``fragment_cache_prefix`` on the other hand is a good
    name as includes the name of the extension (fragment cache).
    """

    #: if this extension parses this is the list of tags it's listening to.
    tags = set()

    #: the priority of that extension.  This is especially useful for
    #: extensions that preprocess values.  A lower value means higher
    #: priority.
    #:
    #: .. versionadded:: 2.4
    priority = 100

    def __init__(self, environment):
        self.environment = environment

    def bind(self, environment):
        """Create a copy of this extension bound to another environment."""
        rv = object.__new__(self.__class__)
        rv.__dict__.update(self.__dict__)
        rv.environment = environment
        return rv

    def preprocess(self, source, name, filename=None):
        """This method is called before the actual lexing and can be used to
        preprocess the source.  The `filename` is optional.  The return value
        must be the preprocessed source.
        """
        return source

    def filter_stream(self, stream):
        """It's passed a :class:`~jinja2.lexer.TokenStream` that can be used
        to filter tokens returned.  This method has to return an iterable of
        :class:`~jinja2.lexer.Token`\\s, but it doesn't have to return a
        :class:`~jinja2.lexer.TokenStream`.

        In the `ext` folder of the Jinja2 source distribution there is a file
        called `inlinegettext.py` which implements a filter that utilizes this
        method.
        """
        return stream

    def parse(self, parser):
        """If any of the :attr:`tags` matched this method is called with the
        parser as first argument.  The token the parser stream is pointing at
        is the name token that matched.  This method has to return one or a
        list of multiple nodes.
        """
        raise NotImplementedError()

    def attr(self, name, lineno=None):
        """Return an attribute node for the current extension.  This is useful
        to pass constants on extensions to generated template code.

        ::

            self.attr('_my_attribute', lineno=lineno)
        """
        return nodes.ExtensionAttribute(self.identifier, name, lineno=lineno)

    def call_method(self, name, args=None, kwargs=None, dyn_args=None,
                    dyn_kwargs=None, lineno=None):
        """Call a method of the extension.  This is a shortcut for
        :meth:`attr` + :class:`jinja2.nodes.Call`.
        """
        if args is None:
            args = []
        if kwargs is None:
            kwargs = []
        return nodes.Call(self.attr(name, lineno=lineno), args, kwargs,
                          dyn_args, dyn_kwargs, lineno=lineno)


@contextfunction
def _gettext_alias(__context, *args, **kwargs):
    return __context.call(__context.resolve('gettext'), *args, **kwargs)


def _make_new_gettext(func):
    @contextfunction
    def gettext(__context, __string, **variables):
        rv = __context.call(func, __string)
        if __context.eval_ctx.autoescape:
            rv = Markup(rv)
        return rv % variables
    return gettext


def _make_new_ngettext(func):
    @contextfunction
    def ngettext(__context, __singular, __plural, __num, **variables):
        variables.setdefault('num', __num)
        rv = __context.call(func, __singular, __plural, __num)
        if __context.eval_ctx.autoescape:
            rv = Markup(rv)
        return rv % variables
    return ngettext


class InternationalizationExtension(Extension):
    """This extension adds gettext support to Jinja2."""
    tags = set(['trans'])

    # TODO: the i18n extension is currently reevaluating values in a few
    # situations.  Take this example:
    #   {% trans count=something() %}{{ count }} foo{% pluralize
    #     %}{{ count }} fooss{% endtrans %}
    # something is called twice here.  One time for the gettext value and
    # the other time for the n-parameter of the ngettext function.

    def __init__(self, environment):
        Extension.__init__(self, environment)
        environment.globals['_'] = _gettext_alias
        environment.extend(
            install_gettext_translations=self._install,
            install_null_translations=self._install_null,
            install_gettext_callables=self._install_callables,
            uninstall_gettext_translations=self._uninstall,
            extract_translations=self._extract,
            newstyle_gettext=False
        )

    def _install(self, translations, newstyle=None):
        gettext = getattr(translations, 'ugettext', None)
        if gettext is None:
            gettext = translations.gettext
        ngettext = getattr(translations, 'ungettext', None)
        if ngettext is None:
            ngettext = translations.ngettext
        self._install_callables(gettext, ngettext, newstyle)

    def _install_null(self, newstyle=None):
        self._install_callables(
            lambda x: x,
            lambda s, p, n: (n != 1 and (p,) or (s,))[0],
            newstyle
        )

    def _install_callables(self, gettext, ngettext, newstyle=None):
        if newstyle is not None:
            self.environment.newstyle_gettext = newstyle
        if self.environment.newstyle_gettext:
            gettext = _make_new_gettext(gettext)
            ngettext = _make_new_ngettext(ngettext)
        self.environment.globals.update(
            gettext=gettext,
            ngettext=ngettext
        )

    def _uninstall(self, translations):
        for key in 'gettext', 'ngettext':
            self.environment.globals.pop(key, None)

    def _extract(self, source, gettext_functions=GETTEXT_FUNCTIONS):
        if isinstance(source, string_types):
            source = self.environment.parse(source)
        return extract_from_ast(source, gettext_functions)

    def parse(self, parser):
        """Parse a translatable tag."""
        lineno = next(parser.stream).lineno
        num_called_num = False

        # find all the variables referenced.  Additionally a variable can be
        # defined in the body of the trans block too, but this is checked at
        # a later state.
        plural_expr = None
        plural_expr_assignment = None
        variables = {}
        trimmed = None
        while parser.stream.current.type != 'block_end':
            if variables:
                parser.stream.expect('comma')

            # skip colon for python compatibility
            if parser.stream.skip_if('colon'):
                break

            name = parser.stream.expect('name')
            if name.value in variables:
                parser.fail('translatable variable %r defined twice.' %
                            name.value, name.lineno,
                            exc=TemplateAssertionError)

            # expressions
            if parser.stream.current.type == 'assign':
                next(parser.stream)
                variables[name.value] = var = parser.parse_expression()
            elif trimmed is None and name.value in ('trimmed', 'notrimmed'):
                trimmed = name.value == 'trimmed'
                continue
            else:
                variables[name.value] = var = nodes.Name(name.value, 'load')

            if plural_expr is None:
                if isinstance(var, nodes.Call):
                    plural_expr = nodes.Name('_trans', 'load')
                    variables[name.value] = plural_expr
                    plural_expr_assignment = nodes.Assign(
                        nodes.Name('_trans', 'store'), var)
                else:
                    plural_expr = var
                num_called_num = name.value == 'num'

        parser.stream.expect('block_end')

        plural = None
        have_plural = False
        referenced = set()

        # now parse until endtrans or pluralize
        singular_names, singular = self._parse_block(parser, True)
        if singular_names:
            referenced.update(singular_names)
            if plural_expr is None:
                plural_expr = nodes.Name(singular_names[0], 'load')
                num_called_num = singular_names[0] == 'num'

        # if we have a pluralize block, we parse that too
        if parser.stream.current.test('name:pluralize'):
            have_plural = True
            next(parser.stream)
            if parser.stream.current.type != 'block_end':
                name = parser.stream.expect('name')
                if name.value not in variables:
                    parser.fail('unknown variable %r for pluralization' %
                                name.value, name.lineno,
                                exc=TemplateAssertionError)
                plural_expr = variables[name.value]
                num_called_num = name.value == 'num'
            parser.stream.expect('block_end')
            plural_names, plural = self._parse_block(parser, False)
            next(parser.stream)
            referenced.update(plural_names)
        else:
            next(parser.stream)

        # register free names as simple name expressions
        for var in referenced:
            if var not in variables:
                variables[var] = nodes.Name(var, 'load')

        if not have_plural:
            plural_expr = None
        elif plural_expr is None:
            parser.fail('pluralize without variables', lineno)

        if trimmed is None:
            trimmed = self.environment.policies['ext.i18n.trimmed']
        if trimmed:
            singular = self._trim_whitespace(singular)
            if plural:
                plural = self._trim_whitespace(plural)

        node = self._make_node(singular, plural, variables, plural_expr,
                               bool(referenced),
                               num_called_num and have_plural)
        node.set_lineno(lineno)
        if plural_expr_assignment is not None:
            return [plural_expr_assignment, node]
        else:
            return node

    def _trim_whitespace(self, string, _ws_re=re.compile(r'\s*\n\s*')):
        return _ws_re.sub(' ', string.strip())

    def _parse_block(self, parser, allow_pluralize):
        """Parse until the next block tag with a given name."""
        referenced = []
        buf = []
        while 1:
            if parser.stream.current.type == 'data':
                buf.append(parser.stream.current.value.replace('%', '%%'))
                next(parser.stream)
            elif parser.stream.current.type == 'variable_begin':
                next(parser.stream)
                name = parser.stream.expect('name').value
                referenced.append(name)
                buf.append('%%(%s)s' % name)
                parser.stream.expect('variable_end')
            elif parser.stream.current.type == 'block_begin':
                next(parser.stream)
                if parser.stream.current.test('name:endtrans'):
                    break
                elif parser.stream.current.test('name:pluralize'):
                    if allow_pluralize:
                        break