Add a grammar for an amendment

and remove the amendment-specific token from the plan grammar

README.md

@@ -6,11 +6,11 @@
 nix develop
 
 # Inspect lexer
-antlr4-parse takentaal.g4 takentaal example -tokens
+antlr4-parse takentaal.g4 takentaal plan_example -tokens
 
 # Inspect parser
-antlr4-parse takentaal.g4 takentaal example -tree
+antlr4-parse takentaal.g4 takentaal plan_example -tree
-antlr4-parse takentaal.g4 takentaal example -gui
+antlr4-parse takentaal.g4 takentaal plan_example -gui
 
 # Generate TypeScript parser
 antlr4 -Dlanguage=TypeScript -o takentaal takentaal.g4

amendment_example

@@ -1,4 +1,4 @@
-takentaal v0.1.0
+takentaal-amendment v1.0
 #  {5000} Full work plan
 
 This is the (draft) description of the entire work plan.

plan_example

@@ -0,0 +1,20 @@
+takentaal v1.0
+#  {5000} Full work plan
+
+This is the (draft) description of the entire work plan.
+
+## {1000} First task
+
+This is the description of the first task.
+
+This description has # ' " [] symbols and ü © Ð Latin-1 chars.
+
+-   {500} First subtask
+-   {500} Second subtask
+
+## {1000} Second task
+
+This is the description of the {} second task for project 10.
+
+-   {500} First subtask
+- {500} 2nd subtask

takentaal.g4

@@ -14,14 +14,59 @@
 
 grammar takentaal;
 
-takentaal
+takentaal : (takentaal_v1_0 | amendment_v1_0) EOF ;
-    : header
+
-      plan
+takentaal_v1_0
+    : 'takentaal v1.0'
+      t1_0_plan
       EOL*
     ;
 
-header
+t1_0_plan
-    : 'takentaal v0.1.0'
+    : PLAN_TOKEN S* amount text
+      description
+      t1_0_task+
+    ;
+
+t1_0_task
+    : TASK_TOKEN S* amount text
+      description
+      t1_0_subtask*
+    ;
+
+t1_0_subtask
+    : SUBTASK_NEW_TOKEN S* amount text
+      description
+    ;
+
+amendment_v1_0
+    : 'takentaal-amendment v1.0'
+      a1_0_plan
+      EOL*
+    ;
+
+a1_0_plan
+    : PLAN_TOKEN S* amount text
+      description
+      a1_0_task+
+    ;
+
+a1_0_task
+    : TASK_TOKEN S* amount text
+      description
+      a1_0_subtask*
+    ;
+
+a1_0_subtask
+    : a1_0_subtask_token S* amount text
+      description
+    ;
+
+a1_0_subtask_token
+    : SUBTASK_NEW_TOKEN
+    | SUBTASK_PARTIAL_TOKEN
+    | SUBTASK_COMPLETE_TOKEN
+    | SUBTASK_OBSOLETE_TOKEN
     ;
 
 // Any implicit and explity lexer token that may appear in a text should be listed
@@ -30,87 +75,37 @@ text
     : (INT | '{' | '}' | S | CHAR | WORD)+
     ;
 
-plan
+description : (EOL text)* ;
-    : PLAN_TOKEN S* amount text
-      description
-      task+
-    ;
 
-description
+// An amount in curly brackes or nothing
-    : (EOL text)*
+amount : '{' S* INT S* '}' | ;
-    ;
 
-task
+// Lexer rules
-    : TASK_TOKEN S* amount text
-      description
-      subtask*
-    ;
 
-subtask
+PLAN_TOKEN : EOL+ '#' ;
-    : SUBTASK_TOKEN S* amount text
-      description
-    ;
 
-amount
+TASK_TOKEN : EOL+ '##' ;
-    : '{' S* INT S* '}'
-    |
-    ;
 
-PLAN_TOKEN
+// These lexer tokens are combined with EOL so that they only match at the
-    : EOL+ '#'
+// start of a line.
-    ;
+SUBTASK_NEW_TOKEN      : EOL+ '-' ;
+SUBTASK_PARTIAL_TOKEN  : EOL+ '/' ;
+SUBTASK_COMPLETE_TOKEN : EOL+ '*' ;
+SUBTASK_OBSOLETE_TOKEN : EOL+ '!' ;
 
-TASK_TOKEN
+S : ' ' ;
-    : EOL+ '##'
-    ;
 
-SUBTASK_TOKEN
+// No implicit whitespace handling
-    : (SUBTASK_NEW_TOKEN | SUBTASK_PARTIAL_TOKEN | SUBTASK_COMPLETE_TOKEN | SUBTASK_OBSOLETE_TOKEN)
+WS : [ ] -> skip ;
-    ;
 
-SUBTASK_NEW_TOKEN
+EOL : ' '* '\n'+ ;
-    : EOL+ '-'
-    ;
 
-SUBTASK_PARTIAL_TOKEN
+INT : DIGIT+ ;
-    : EOL+ '/'
-    ;
 
-SUBTASK_COMPLETE_TOKEN
+fragment DIGIT : [0-9] ;
-    : EOL+ '*'
-    ;
-
-SUBTASK_OBSOLETE_TOKEN
-    : EOL+ '!'
-    ;
-
-S
-    : ' '
-    ;
-    
-
-WS
-    : [ ] -> skip
-    ;
-
-EOL
-    : ' '* '\n'+
-    ;
-
-INT
-    : DIGIT+
-    ;
-
-fragment DIGIT
-    : [0-9]
-    ;
 
 // Match printable characters, except space which is covered by S
-CHAR
+CHAR : [!-~\u00A0-\u33FF] ; // ASCII and UNICODE
-    : [!-~\u00A0-\u33FF] // ASCII and UNICODE
-    ;
 
 // This is a performance improvement that groups chars that do not have a special meaning
-WORD
+WORD : [A-Za-z\u00A0-\u33FF]+ ;
-    : [A-Za-z\u00A0-\u33FF]+
-    ;