def get_tokens_unprocessed(self, text):
     for index, token, value in RubyLexer.get_tokens_unprocessed(
             self, text):
         if token is Name and value in self.EXTRA_KEYWORDS:
             yield index, Keyword, value
         else:
             yield index, token, value
Exemple #2
0
class ErbLexer(Lexer):
    """
    Generic `ERB <http://ruby-doc.org/core/classes/ERB.html>`_ (Ruby Templating)
    lexer.

    Just highlights ruby code between the preprocessor directives, other data
    is left untouched by the lexer.

    All options are also forwarded to the `RubyLexer`.
    """

    name = 'ERB'
    aliases = ['erb']
    mimetypes = ['application/x-ruby-templating']

    _block_re = re.compile(r'(<%%|%%>|<%=|<%#|<%-|<%|-%>|%>|^%[^%].*?$)', re.M)

    def __init__(self, **options):
        from pygments.lexers.agile import RubyLexer
        self.ruby_lexer = RubyLexer(**options)
        Lexer.__init__(self, **options)

    def get_tokens_unprocessed(self, text):
        """
        Since ERB doesn't allow "<%" and other tags inside of ruby
        blocks we have to use a split approach here that fails for
        that too.
        """
        tokens = self._block_re.split(text)
        tokens.reverse()
        state = idx = 0
        try:
            while True:
                # text
                if state == 0:
                    val = tokens.pop()
                    yield idx, Other, val
                    idx += len(val)
                    state = 1
                # block starts
                elif state == 1:
                    tag = tokens.pop()
                    # literals
                    if tag in ('<%%', '%%>'):
                        yield idx, Other, tag
                        idx += 3
                        state = 0
                    # comment
                    elif tag == '<%#':
                        yield idx, Comment.Preproc, tag
                        val = tokens.pop()
                        yield idx + 3, Comment, val
                        idx += 3 + len(val)
                        state = 2
                    # blocks or output
                    elif tag in ('<%', '<%=', '<%-'):
                        yield idx, Comment.Preproc, tag
                        idx += len(tag)
                        data = tokens.pop()
                        r_idx = 0
                        for r_idx, r_token, r_value in \
                            self.ruby_lexer.get_tokens_unprocessed(data):
                            yield r_idx + idx, r_token, r_value
                        idx += len(data)
                        state = 2
                    elif tag in ('%>', '-%>'):
                        yield idx, Error, tag
                        idx += len(tag)
                        state = 0
                    # % raw ruby statements
                    else:
                        yield idx, Comment.Preproc, tag[0]
                        r_idx = 0
                        for r_idx, r_token, r_value in \
                            self.ruby_lexer.get_tokens_unprocessed(tag[1:]):
                            yield idx + 1 + r_idx, r_token, r_value
                        idx += len(tag)
                        state = 0
                # block ends
                elif state == 2:
                    tag = tokens.pop()
                    if tag not in ('%>', '-%>'):
                        yield idx, Other, tag
                    else:
                        yield idx, Comment.Preproc, tag
                    idx += len(tag)
                    state = 0
        except IndexError:
            return

    def analyse_text(text):
        if '<%' in text and '%>' in text:
            return 0.4
 def get_tokens_unprocessed(self, text):
     for index, token, value in RubyLexer.get_tokens_unprocessed(self, text):
         if token is Name and value in self.EXTRA_KEYWORDS:
             yield index, Keyword, value
         else:
             yield index, token, value
Exemple #4
0
class ErbLexer(Lexer):
    """
    Generic `ERB <http://ruby-doc.org/core/classes/ERB.html>`_ (Ruby Templating)
    lexer.

    Just highlights ruby code between the preprocessor directives, other data
    is left untouched by the lexer.

    All options are also forwarded to the `RubyLexer`.
    """

    name = 'ERB'
    aliases = ['erb']
    mimetypes = ['application/x-ruby-templating']

    _block_re = re.compile(r'(<%%|%%>|<%=|<%#|<%-|<%|-%>|%>|^%[^%].*?$)', re.M)

    def __init__(self, **options):
        from pygments.lexers.agile import RubyLexer
        self.ruby_lexer = RubyLexer(**options)
        Lexer.__init__(self, **options)

    def get_tokens_unprocessed(self, text):
        """
        Since ERB doesn't allow "<%" and other tags inside of ruby
        blocks we have to use a split approach here that fails for
        that too.
        """
        tokens = self._block_re.split(text)
        tokens.reverse()
        state = idx = 0
        try:
            while True:
                # text
                if state == 0:
                    val = tokens.pop()
                    yield idx, Other, val
                    idx += len(val)
                    state = 1
                # block starts
                elif state == 1:
                    tag = tokens.pop()
                    # literals
                    if tag in ('<%%', '%%>'):
                        yield idx, Other, tag
                        idx += 3
                        state = 0
                    # comment
                    elif tag == '<%#':
                        yield idx, Comment.Preproc, tag
                        val = tokens.pop()
                        yield idx + 3, Comment, val
                        idx += 3 + len(val)
                        state = 2
                    # blocks or output
                    elif tag in ('<%', '<%=', '<%-'):
                        yield idx, Comment.Preproc, tag
                        idx += len(tag)
                        data = tokens.pop()
                        r_idx = 0
                        for r_idx, r_token, r_value in \
                            self.ruby_lexer.get_tokens_unprocessed(data):
                            yield r_idx + idx, r_token, r_value
                        idx += len(data)
                        state = 2
                    elif tag in ('%>', '-%>'):
                        yield idx, Error, tag
                        idx += len(tag)
                        state = 0
                    # % raw ruby statements
                    else:
                        yield idx, Comment.Preproc, tag[0]
                        r_idx = 0
                        for r_idx, r_token, r_value in \
                            self.ruby_lexer.get_tokens_unprocessed(tag[1:]):
                            yield idx + 1 + r_idx, r_token, r_value
                        idx += len(tag)
                        state = 0
                # block ends
                elif state == 2:
                    tag = tokens.pop()
                    if tag not in ('%>', '-%>'):
                        yield idx, Other, tag
                    else:
                        yield idx, Comment.Preproc, tag
                    idx += len(tag)
                    state = 0
        except IndexError:
            return

    def analyse_text(text):
        if '<%' in text and '%>' in text:
            return 0.4