Remove match_length lexer user code block for Rust

CHANGELOG.md

@@ -10,7 +10,7 @@
   `match_text` for every target language. It was previously named `match` for
   C, C++, and D, and `match_` for Rust. Any lexer user code block which
   references the matched text must be updated to use the new name. The
-  `match_length` argument (C, C++, and Rust) is unchanged.
+  `match_length` argument (C and C++) is unchanged.
 - Tree generation mode now stores all tree nodes in a compact arena owned by
   the parser context (a flat node array plus a shared child-link array).
   This replaces the previous design of one heap allocation per node with

assets/parser.rs.erb

@@ -484,8 +484,6 @@ static lexer_mode_table: [lexer_mode_t; <%= @lexer.mode_table.size %>] = [
  *   The ID of the user code block to execute.
  * @param match_text
  *   Matched text for this pattern.
- * @param match_length
- *   Matched text length.
  * @param out_token_info
  *   Lexer token info in progress.
  *
@@ -494,7 +492,7 @@ static lexer_mode_table: [lexer_mode_t; <%= @lexer.mode_table.size %>] = [
  */
 fn lexer_user_code(context: &mut <%= @grammar.prefix %>context_t,
     code_id: <%= get_type_for(user_code_id_count) %>, match_text: &[u8],
-    match_length: usize, out_token_info: &mut <%= @grammar.prefix %>token_info_t) -> <%= @grammar.prefix %>token_t {
+    out_token_info: &mut <%= @grammar.prefix %>token_info_t) -> <%= @grammar.prefix %>token_t {
     match code_id {
 <% @grammar.patterns.each do |pattern| %>
 <%   if pattern.code_id %>
@@ -668,7 +666,7 @@ fn attempt_lex_token(context: &mut <%= @grammar.prefix %>context_t, out_token_in
                 let match_start = context.input_index;
                 let match_slice = context.input[match_start..(match_start + match_info.length)].to_vec();
                 let user_code_token = lexer_user_code(context,
-                    lexer_state_table[match_info.accepting_state as usize].code_id, &match_slice, match_info.length, &mut token_info);
+                    lexer_state_table[match_info.accepting_state as usize].code_id, &match_slice, &mut token_info);
                 /* A TERMINATE_TOKEN_ID return code from lexer_user_code() means
                  * that the user code is requesting to terminate the lexer. */
                 if user_code_token == TERMINATE_TOKEN_ID {

doc/user_guide.md

@@ -249,7 +249,6 @@ token integer /\d+/ <<
 The lexer code block is passed the following arguments:
 
   * `match_text` (`&[u8]`) - a slice containing the text matched by the lexer pattern.
-  * `match_length` (`usize`) - length of the matched text.
 
 The matched text is a byte slice rather than a string; use
 `std::str::from_utf8()` or `String::from_utf8_lossy()` to view it as a string.

spec/propane_spec.rb

@@ -1124,7 +1124,7 @@ EOF
           write_grammar <<EOF
 ptype u64;
 token word /[a-z]+/ <<
-  $$ = match_length as u64;
+  $$ = match_text.len() as u64;
 >>
 Start -> word <<
   $$ = $1;