unikernel/duniverse/dune_/doc/exts/cram_lexer.py

@@ -0,0 +1,24 @@
+from pygments.lexer import DelegatingLexer, RegexLexer, bygroups, default
+from pygments.lexers.shell import BashLexer
+from pygments.token import Generic, Other, Comment
+
+
+class CramBaseLexer(RegexLexer):
+    tokens = {
+        "root": [
+            (r"(  \$ )(.*\n)", bygroups(Generic.Prompt, Other.Code), "continuations"),
+            (r"^  .*\n", Generic.Output),
+            (r"^.*\n", Comment.Multiline),
+        ],
+        "continuations": [
+            (r"(  > )(.*\n)", bygroups(Generic.Prompt, Other.Code)),
+            default("#pop"),
+        ],
+    }
+
+
+class CramLexer(DelegatingLexer):
+    name = "cram"
+
+    def __init__(self, **options):
+        super().__init__(BashLexer, CramBaseLexer, Other.Code, **options)

unikernel/duniverse/dune_/doc/exts/dune_lexer.py

@@ -0,0 +1,36 @@
+from pygments.token import Comment, Punctuation, Text, Name, String, Generic
+from pygments.lexer import RegexLexer
+
+
+def after_paren(r):
+    return r"(?<=\()(%s)" % r
+
+
+class DuneLexer(RegexLexer):
+    name = "dune"
+
+    atom = r'[^\s()"]+'
+
+    tokens = {
+        "root": [
+            (r";.*$", Comment.Single),
+            (r"(\(|\))", Punctuation),
+            # pforms (%{var} and %{fun:arg}
+            (r"%{[^}]+}", String.Backtick),
+            (r":[-\w]+", String.Symbol),
+            # placeholders like <arg> and ... that appear in docs
+            (r"<[-\w ]+>", Generic.Emph),
+            (r"\.\.\.", Generic.Emph),
+            (r'"\\\|', String.Double, "string-multiline"),
+            (r'"', String, "string"),
+            # instead of hardcoding "builtin" names,
+            # highlight the first atom in a list differently
+            (after_paren(atom), Name.Function),
+            (atom, Name),
+            (r"\s+", Text),
+        ],
+        "string": [
+            (r'(\\\\|\\"|[^"])*"', String, "#pop"),
+        ],
+        "string-multiline": [(r"[^\n]*\n", String, "#pop")],
+    }

unikernel/duniverse/dune_/doc/exts/opam_lexer.py

@@ -0,0 +1,26 @@
+from pygments.lexer import RegexLexer
+from pygments.token import (
+    Keyword,
+    Number,
+    Punctuation,
+    String,
+    Text,
+    Whitespace,
+)
+
+
+ident = r"[-\w]+"
+
+
+class OpamLexer(RegexLexer):
+    name = "opam"
+    tokens = {
+        "root": [
+            (r"\d\.\d", Number),
+            (r"^" + ident + ":", Keyword),
+            (ident, Text),
+            (r"[\[\]{}>=]", Punctuation),
+            (r"\s+", Whitespace),
+            (r'"[^\"]*"', String),
+        ]
+    }