1  from pygments.lexer import RegexLexer, bygroups, include
       2  from pygments.token import Comment, Generic, Keyword, Name, Operator, Punctuation, Text
       3  
       4  from sphinx.highlighting import lexers
       5  
       6  
       7  class ESC[4;38;5;81mPEGLexer(ESC[4;38;5;149mRegexLexer):
       8      """Pygments Lexer for PEG grammar (.gram) files
       9  
      10      This lexer strips the following elements from the grammar:
      11  
      12          - Meta-tags
      13          - Variable assignments
      14          - Actions
      15          - Lookaheads
      16          - Rule types
      17          - Rule options
      18          - Rules named `invalid_*` or `incorrect_*`
      19      """
      20  
      21      name = "PEG"
      22      aliases = ["peg"]
      23      filenames = ["*.gram"]
      24      _name = r"([^\W\d]\w*)"
      25      _text_ws = r"(\s*)"
      26  
      27      tokens = {
      28          "ws": [(r"\n", Text), (r"\s+", Text), (r"#.*$", Comment.Singleline),],
      29          "lookaheads": [
      30              # Forced tokens
      31              (r"(&&)(?=\w+\s?)", bygroups(None)),
      32              (r"(&&)(?='.+'\s?)", bygroups(None)),
      33              (r'(&&)(?=".+"\s?)', bygroups(None)),
      34              (r"(&&)(?=\(.+\)\s?)", bygroups(None)),
      35  
      36              (r"(?<=\|\s)(&\w+\s?)", bygroups(None)),
      37              (r"(?<=\|\s)(&'.+'\s?)", bygroups(None)),
      38              (r'(?<=\|\s)(&".+"\s?)', bygroups(None)),
      39              (r"(?<=\|\s)(&\(.+\)\s?)", bygroups(None)),
      40          ],
      41          "metas": [
      42              (r"(@\w+ '''(.|\n)+?''')", bygroups(None)),
      43              (r"^(@.*)$", bygroups(None)),
      44          ],
      45          "actions": [
      46              (r"{(.|\n)+?}", bygroups(None)),
      47          ],
      48          "strings": [
      49              (r"'\w+?'", Keyword),
      50              (r'"\w+?"', Keyword),
      51              (r"'\W+?'", Text),
      52              (r'"\W+?"', Text),
      53          ],
      54          "variables": [
      55              (_name + _text_ws + "(=)", bygroups(None, None, None),),
      56              (_name + _text_ws + r"(\[[\w\d_\*]+?\])" + _text_ws + "(=)", bygroups(None, None, None, None, None),),
      57          ],
      58          "invalids": [
      59              (r"^(\s+\|\s+.*invalid_\w+.*\n)", bygroups(None)),
      60              (r"^(\s+\|\s+.*incorrect_\w+.*\n)", bygroups(None)),
      61              (r"^(#.*invalid syntax.*(?:.|\n)*)", bygroups(None),),
      62          ],
      63          "root": [
      64              include("invalids"),
      65              include("ws"),
      66              include("lookaheads"),
      67              include("metas"),
      68              include("actions"),
      69              include("strings"),
      70              include("variables"),
      71              (r"\b(?!(NULL|EXTRA))([A-Z_]+)\b\s*(?!\()", Text,),
      72              (
      73                  r"^\s*" + _name + r"\s*" + r"(\[.*\])?" + r"\s*" + r"(\(.+\))?" + r"\s*(:)",
      74                  bygroups(Name.Function, None, None, Punctuation),
      75              ),
      76              (_name, Name.Function),
      77              (r"[\||\.|\+|\*|\?]", Operator),
      78              (r"{|}|\(|\)|\[|\]", Punctuation),
      79              (r".", Text),
      80          ],
      81      }
      82  
      83  
      84  def setup(app):
      85      lexers["peg"] = PEGLexer()
      86      return {"version": "1.0", "parallel_read_safe": True}