Update wordlist

README.adoc

@@ -1,5 +1,5 @@
 // echo README.adoc | entr sh -c "podman run --rm -it --network none -v "${PWD}:/documents/" asciidoctor/docker-asciidoctor asciidoctor -r asciidoctor-mathematical -a mathematical-format=svg README.adoc; printf 'Done ($(date -Isecond))\n'"
-:toc:
+// :toc:
 :nofooter:
 :!webfonts:
 :source-highlighter: rouge
@@ -7,3 +7,54 @@
 :sectlinks:
 
 = xpin
+
+== File Structure
+
+In order of dependency, the role of each of these directories in this repository is:
+
+[cols="m,,"]
+|===
+|Directory |Contents |Description
+
+|docs
+|Asciidoctor documentation
+|Design decisions and algorithm definition documentation
+
+|wordlist
+|Python/CSV
+|Wordlist sources and generator code
+
+|test-data
+|C++/CSV
+|Test data mapping random and hand-picked lat/lon transformed to CellIDs and xpin addresses.
+Also contains source code linking to the C++ S2 library to ensure CellIDs are translated properly.
+
+|words
+|Rust Crate
+|Crate to store the mapping of words and their associated numeric values.
+
+|src
+|Rust Crate
+|
+
+|tests
+|
+|
+
+|xpin-wasm
+|Rust Crate
+|WASM bindings for xpin
+
+|web-frontend
+|
+|
+
+|build
+|
+|
+
+|web
+|Rust Crate
+|
+
+|===

wordlist/03-exclude.csv

@@ -555,6 +555,7 @@ CASTILE
 CASTRO
 CATALOGING
 CATALOGUING
+CATARACT
 CATASTROPHE
 CATECHISM
 CATHARINE
@@ -1472,6 +1473,7 @@ HOSTAGE
 HOSTILITY
 HOT
 HOUGH
+HOUSEWIFE
 HOUSTON
 HOWARD
 HP
@@ -2141,7 +2143,6 @@ MYSORE
 NAD
 NAIROBI
 NAKED
-NAKED
 NAMIBIA
 NAN
 NANCY
@@ -2676,6 +2677,7 @@ RUSSIA
 RUSSIAN
 RUTH
 RUTHERFORD
+RUTHLESS
 RUTLAND
 RWANDA
 SABBATH

wordlist/04-deduplicated-words.py

@@ -114,7 +114,9 @@ pprint(list(enumerate(final_wordlist)))
 print(f"Ending index: {ending_word_index}")
 
 final_wordlist = [
-    (idx + 1, word)
+    # The idx here starts at 0, which is fine
+    # It indicates that a *word* component can map to 0 (not that the numeric component can)
+    (idx, word)
     for idx, words in enumerate(final_wordlist)
     for word in words
 ]

wordlist/99-wordlist.csv

@@ -0,0 +1 @@
+04-deduplicated-words.py

words/build.rs

@@ -11,7 +11,7 @@ use std::path::Path;
 fn main() {
     let path = Path::new(&env::var("OUT_DIR").unwrap()).join("codegen.rs");
     let mut file = BufWriter::new(File::create(path).unwrap());
-    let wordlist_path = "../data/wordlist-tmp.csv";
+    let wordlist_path = "../wordlist/99-wordlist.csv";
 
     println!("cargo:rerun-if-changed={}", wordlist_path);