Support named capture groups

.ocamlformat

@@ -1,4 +1,4 @@
-version=0.19.0
+#version=0.19.0
 profile = conventional
 break-separators = after
 space-around-lists = false

src/lib/sedlexing.ml

@@ -36,6 +36,7 @@ type lexbuf = {
   mutable marked_bol : int;
   mutable marked_line : int;
   mutable marked_val : int;
+  mutable marked_path : int list;
   mutable filename : string;
   mutable finished : bool;
 }
@@ -58,6 +59,7 @@ let empty_lexbuf =
     marked_bol = 0;
     marked_line = 0;
     marked_val = 0;
+    marked_path = [];
     filename = "";
     finished = false;
   }
@@ -154,23 +156,24 @@ let __private__next_int lexbuf : int =
     Uchar.to_int ret
   end
 
-let mark lexbuf i =
+let mark lexbuf i path =
   lexbuf.marked_pos <- lexbuf.pos;
   lexbuf.marked_bol <- lexbuf.curr_bol;
   lexbuf.marked_line <- lexbuf.curr_line;
-  lexbuf.marked_val <- i
+  lexbuf.marked_val <- i;
+  lexbuf.marked_path <- path
 
 let start lexbuf =
   lexbuf.start_pos <- lexbuf.pos;
   lexbuf.start_bol <- lexbuf.curr_bol;
   lexbuf.start_line <- lexbuf.curr_line;
-  mark lexbuf (-1)
+  mark lexbuf (-1) []
 
 let backtrack lexbuf =
   lexbuf.pos <- lexbuf.marked_pos;
   lexbuf.curr_bol <- lexbuf.marked_bol;
   lexbuf.curr_line <- lexbuf.marked_line;
-  lexbuf.marked_val
+  (lexbuf.marked_val, lexbuf.marked_path)
 
 let rollback lexbuf =
   lexbuf.pos <- lexbuf.start_pos;
@@ -189,6 +192,7 @@ let lexeme lexbuf =
   Array.sub lexbuf.buf lexbuf.start_pos (lexbuf.pos - lexbuf.start_pos)
 
 let lexeme_char lexbuf pos = lexbuf.buf.(lexbuf.start_pos + pos)
+let lexeme_code lexbuf pos = Uchar.to_int lexbuf.buf.(lexbuf.start_pos + pos)
 
 let lexing_positions lexbuf =
   let start_p =

src/lib/sedlexing.mli

@@ -114,6 +114,10 @@ val lexeme : lexbuf -> Uchar.t array
         the matched string. *)
 val lexeme_char : lexbuf -> int -> Uchar.t
 
+(** [Sedlexing.lexeme_code lexbuf pos] returns code point number [pos] in
+        the matched string. *)
+val lexeme_code : lexbuf -> int -> int
+
 (** [Sedlexing.sub_lexeme lexbuf pos len] returns a substring of the string
     matched by the regular expression as an array of Unicode code point. *)
 val sub_lexeme : lexbuf -> int -> int -> Uchar.t array
@@ -151,19 +155,19 @@ val next : lexbuf -> Uchar.t option
     lexer buffer and increments to current position. If the input stream
     is exhausted, the function returns -1.
     If a ['\n'] is encountered, the tracked line number is incremented.
-    
+
     This is a private API, it should not be used by code using this module's
     API and can be removed at any time. *)
 val __private__next_int : lexbuf -> int
 
-(** [mark lexbuf i] stores the integer [i] in the internal
-    slot. The backtrack position is set to the current position. *)
-val mark : lexbuf -> int -> unit
+(** [mark lexbuf i path] stores the integer [i] and the list [path] in the
+    internal slot. The backtrack position is set to the current position. *)
+val mark : lexbuf -> int -> int list -> unit
 
-(** [backtrack lexbuf] returns the value stored in the
+(** [backtrack lexbuf] returns the value and path stored in the
     internal slot of the buffer, and performs backtracking
     (the current position is set to the value of the backtrack position). *)
-val backtrack : lexbuf -> int
+val backtrack : lexbuf -> int * int list
 
 (** [with_tokenizer tokenizer lexbuf] given a lexer and a lexbuf,
     returns a generator of tokens annotated with positions.