Phoneme codec for cit names

bin/mw_datatool/src/cmd/gen_map.rs

@@ -1,6 +1,6 @@
 use std::io::BufWriter;
 
-use mw_common::{game::{MapGenTileData, TileKind}, grid::*};
+use mw_common::{game::{MapGenTileData, TileKind}, grid::*, phoneme::Ph};
 
 use crate::prelude::*;
 use crate::{CommonArgs, GenMapArgs};
@@ -28,7 +28,10 @@ pub fn main(common: &CommonArgs, args: &GenMapArgs) -> AnyResult<()> {
         .start_is()?;
     let is = b_is
         .with_map_lz4compressed(&map, true, &mut scratch)?
-        .with_cits([Pos(12, 17), Pos(7, 3)])?
+        .with_cits([
+            (Pos(12, 17), [Ph::A, Ph::B, Ph::E, Ph::Z].as_slice()),
+            (Pos(7, 3), [Ph::I, Ph::D, Ph::A].as_slice()),
+        ])?
         .with_named_players(["iyes", "georgie", "gr.NET"])?
         .finish()?;
     let b_file = b_file.with_is(is)?;

bin/mw_datatool/src/cmd/info.rs

@@ -1,3 +1,4 @@
+use mw_common::phoneme::{lang, render_str};
 use mw_dataformat::read::MwFileReader;
 
 use crate::prelude::*;
@@ -55,5 +56,13 @@ pub fn main(common: &CommonArgs, args: &InfoArgs) -> AnyResult<()> {
         eprintln!("{}: {:?}", i, name);
     }
 
+    eprintln!();
+    eprintln!("Cits:");
+    let cit_pos = isr.read_cits_pos()?.to_owned();
+    let iter_cit_names = isr.read_cits_names()?;
+    for (i, (pos, name)) in cit_pos.iter().cloned().zip(iter_cit_names).enumerate() {
+        eprintln!("{}: Y:{},X:{} {:?}", i, pos.y(), pos.x(), render_str::<lang::EN>(name));
+    }
+
     Ok(())
 }

bin/mw_datatool/src/cmd/map_ascii.rs

@@ -22,7 +22,7 @@ pub fn main(common: &CommonArgs, _args: &MapAsciiArgs) -> AnyResult<()> {
 
     let (_, mut isr) = mfr.read_is()?;
     let map: MapDataTopo<MapGenTileData> = isr.read_map_dyntopo(Some(&mut scratch), false)?;
-    let cits = isr.read_cits()?;
+    let cits = isr.read_cits_pos()?;
 
     fn f_tile_ascii(cits: &[Pos], pos: Pos, kind: TileKind) -> u8 {
         if cits.iter().position(|p| *p == pos).is_some() {

bin/mw_datatool/src/cmd/reencode.rs

@@ -89,8 +89,9 @@ fn reencode<R: Read + Seek, W: Write + Seek>(reader: R, writer: W, args: &Reenco
         }
     };
 
-    let cits = isr.read_cits()?;
-    let b_is = b_is.with_cits(cits.iter().cloned())?;
+    let cit_pos = isr.read_cits_pos()?.to_owned();
+    let iter_cit_names = isr.read_cits_names()?;
+    let b_is = b_is.with_cits(cit_pos.iter().cloned().zip(iter_cit_names))?;
 
     let b_is = if args.anonymize || isr.is_anonymized() {
         b_is.with_anonymous_players(isr.n_players())?

doc/src/tech/dataformat-player.md

@@ -46,9 +46,11 @@ It begins with a header:
  - `u8`: map size (radius)
  - `u8`: number of players
  - `u8`: number of cities/regions
- - `u16`: length of the whole Initialization Sequence / offset at which Messages will start
- - `u16`: length of player names data (0 for an anonymized stream)
  - `u32`: length of compressed map data in bytes
+ - `u16`: length of the Rules data
+ - `u16`: length of the Cits names data
+ - `u16`: length of the player names data (0 for an anonymized stream)
+ - `u16`: (reserved)
 
 The `flags` field is encoded as follows:
 
@@ -108,9 +110,17 @@ Hex example:
 After the map data, regions are encoded the same way: one byte per tile, in
 concentric ring order. The byte is the city/region ID for that tile.
 
-### City Locations
+### City Info
 
-Then follows the list of city coordinates.
+First, locations for each city on the map:
+ - `(u8, u8)`: (y, x) location
+
+Then, names for each city on the map:
+ - `u8`: length in bytes
+ - …: phonemes
+
+The name uses a special Phoneme encoding (undocumented, see source code),
+which can be rendered/localized based on client language.
 
 ### Player Names
 

lib/mw_common/src/lib.rs

@@ -52,4 +52,5 @@ pub mod algo;
 pub mod driver;
 pub mod grid;
 pub mod plid;
+pub mod phoneme;
 pub mod game;