feat(grammar): add keyword extension

6cdh · Aug 2, 2023 · 43044ab · 43044ab
1 parent db5c4eb
commit 43044ab
Show file tree

Hide file tree

Showing 7 changed files with 2,495 additions and 2,203 deletions.
diff --git a/README.md b/README.md
@@ -23,7 +23,7 @@ current status:
 * [ ] Extensions
   * [x] `{}` as replacement for `()` or `[]`
   * [x] extend symbols which can start with digits, period, ... etc as long as it's not a number
-  * [ ] keyword `#:symbol`
+  * [x] keyword `#:symbol`
   * [ ] escape sequence in string `\` + any character
   * [ ] characters `#\bel`, `#\ls`, `#\nel`, `#\rubout`, `#\vt`
 

diff --git a/corpus/ext.scm b/corpus/ext.scm
@@ -0,0 +1,24 @@
+===
+list
+===
+
+{define x 1}
+
+---
+(program
+  (list
+    (symbol)
+    (symbol)
+    (number)))
+
+===
+keyword
+===
+
+#:abc
+#:1abc
+
+---
+(program
+  (keyword)
+  (keyword))
diff --git a/grammar.js b/grammar.js
@@ -115,6 +115,14 @@ const r7rs = {
       "|")
 };
 
+const hidden_node = {
+  symbol:
+    token(
+      choice(
+        repeat1(common.symbol_element),
+        r7rs.symbol)),
+};
+
 module.exports = grammar({
   name: "scheme",
 
@@ -170,7 +178,9 @@ module.exports = grammar({
       $.syntax,
       $.quasisyntax,
       $.unsyntax,
-      $.unsyntax_splicing),
+      $.unsyntax_splicing,
+
+      $.keyword),
 
     // simple datum {{{
 
@@ -212,12 +222,13 @@ module.exports = grammar({
           r6rs.escape_sequence,
           r7rs.escape_sequence)),
 
-    symbol: _ =>
-      PREC.symbol(
-        token(
-          choice(
-            repeat1(common.symbol_element),
-            r7rs.symbol))),
+    symbol: _ => PREC.symbol(hidden_node.symbol),
+
+    keyword: _ =>
+      token(
+        seq(
+          "#:",
+          hidden_node.symbol)),
 
     // simple datum }}}
 

diff --git a/nodes.md b/nodes.md
@@ -12,6 +12,8 @@ This page contains all visible nodes in yaml format.
 - escape_sequence # escape sequence in string, for example, \n in "abc\n"
 - number
 - symbol # identifier
+- keyword # #:identifier
+
 - list # things surrounded by () or [] or {}
 - quote # '
 - quasiquote # `
@@ -21,6 +23,7 @@ This page contains all visible nodes in yaml format.
 - unquote_splicing # ,@
 - unsyntax # #,
 - unsyntax_splicing # #,@
+
 - vector
 - byte_vector
 ```

diff --git a/src/grammar.json b/src/grammar.json
@@ -200,6 +200,10 @@
         {
           "type": "SYMBOL",
           "name": "unsyntax_splicing"
+        },
+        {
+          "type": "SYMBOL",
+          "name": "keyword"
         }
       ]
     },
@@ -12205,6 +12209,70 @@
         }
       }
     },
+    "keyword": {
+      "type": "TOKEN",
+      "content": {
+        "type": "SEQ",
+        "members": [
+          {
+            "type": "STRING",
+            "value": "#:"
+          },
+          {
+            "type": "TOKEN",
+            "content": {
+              "type": "CHOICE",
+              "members": [
+                {
+                  "type": "REPEAT1",
+                  "content": {
+                    "type": "PATTERN",
+                    "value": "[^ \\r\\n\\t\\f\\v\\p{Zs}\\p{Zl}\\p{Zp}#;\"'`,(){}\\[\\]\\\\|]"
+                  }
+                },
+                {
+                  "type": "SEQ",
+                  "members": [
+                    {
+                      "type": "STRING",
+                      "value": "|"
+                    },
+                    {
+                      "type": "REPEAT",
+                      "content": {
+                        "type": "CHOICE",
+                        "members": [
+                          {
+                            "type": "PATTERN",
+                            "value": "[^|\\\\]+"
+                          },
+                          {
+                            "type": "PATTERN",
+                            "value": "\\\\[xX][0-9a-fA-F]+;"
+                          },
+                          {
+                            "type": "PATTERN",
+                            "value": "\\\\[abtnr]"
+                          },
+                          {
+                            "type": "STRING",
+                            "value": "\\|"
+                          }
+                        ]
+                      }
+                    },
+                    {
+                      "type": "STRING",
+                      "value": "|"
+                    }
+                  ]
+                }
+              ]
+            }
+          }
+        ]
+      }
+    },
     "list": {
       "type": "CHOICE",
       "members": [

diff --git a/src/node-types.json b/src/node-types.json
@@ -46,6 +46,10 @@
           "type": "directive",
           "named": true
         },
+        {
+          "type": "keyword",
+          "named": true
+        },
         {
           "type": "list",
           "named": true
@@ -133,6 +137,10 @@
           "type": "directive",
           "named": true
         },
+        {
+          "type": "keyword",
+          "named": true
+        },
         {
           "type": "list",
           "named": true
@@ -247,6 +255,10 @@
           "type": "directive",
           "named": true
         },
+        {
+          "type": "keyword",
+          "named": true
+        },
         {
           "type": "list",
           "named": true
@@ -339,6 +351,10 @@
           "type": "directive",
           "named": true
         },
+        {
+          "type": "keyword",
+          "named": true
+        },
         {
           "type": "list",
           "named": true
@@ -426,6 +442,10 @@
           "type": "directive",
           "named": true
         },
+        {
+          "type": "keyword",
+          "named": true
+        },
         {
           "type": "list",
           "named": true
@@ -513,6 +533,10 @@
           "type": "directive",
           "named": true
         },
+        {
+          "type": "keyword",
+          "named": true
+        },
         {
           "type": "list",
           "named": true
@@ -600,6 +624,10 @@
           "type": "directive",
           "named": true
         },
+        {
+          "type": "keyword",
+          "named": true
+        },
         {
           "type": "list",
           "named": true
@@ -707,6 +735,10 @@
           "type": "directive",
           "named": true
         },
+        {
+          "type": "keyword",
+          "named": true
+        },
         {
           "type": "list",
           "named": true
@@ -794,6 +826,10 @@
           "type": "directive",
           "named": true
         },
+        {
+          "type": "keyword",
+          "named": true
+        },
         {
           "type": "list",
           "named": true
@@ -881,6 +917,10 @@
           "type": "directive",
           "named": true
         },
+        {
+          "type": "keyword",
+          "named": true
+        },
         {
           "type": "list",
           "named": true
@@ -968,6 +1008,10 @@
           "type": "directive",
           "named": true
         },
+        {
+          "type": "keyword",
+          "named": true
+        },
         {
           "type": "list",
           "named": true
@@ -1055,6 +1099,10 @@
           "type": "directive",
           "named": true
         },
+        {
+          "type": "keyword",
+          "named": true
+        },
         {
           "type": "list",
           "named": true
@@ -1142,6 +1190,10 @@
           "type": "directive",
           "named": true
         },
+        {
+          "type": "keyword",
+          "named": true
+        },
         {
           "type": "list",
           "named": true
@@ -1281,6 +1333,10 @@
     "type": "escape_sequence",
     "named": true
   },
+  {
+    "type": "keyword",
+    "named": true
+  },
   {
     "type": "{",
     "named": false