From 9f03f43abfd7f56aadadb8aced31fb782390f657 Mon Sep 17 00:00:00 2001
From: Austen Adler <agadler@austenadler.com>
Date: Tue, 18 Apr 2023 14:55:02 -0400
Subject: [PATCH] Start working on wide addresses

---
 Cargo.lock       |   1 +
 Cargo.toml       |   1 +
 src/lib.rs       |   1 +
 src/wide.rs      | 148 +++++++++++++++++++++++++++++++++++++++++++++++
 words/src/lib.rs |   2 +-
 5 files changed, 152 insertions(+), 1 deletion(-)
 create mode 100644 src/wide.rs

diff --git a/Cargo.lock b/Cargo.lock
index cd80b03..aeac209 100644
--- a/Cargo.lock
+++ b/Cargo.lock
@@ -2081,6 +2081,7 @@ version = "0.1.0"
 dependencies = [
  "csv",
  "geoutils",
+ "nom",
  "s2",
  "serde",
  "thiserror",
diff --git a/Cargo.toml b/Cargo.toml
index 29734f0..ba25035 100644
--- a/Cargo.toml
+++ b/Cargo.toml
@@ -21,6 +21,7 @@ default = []
 s2 = {version="0.0.12", default-features=false}
 thiserror = "1.0.38"
 words = {path="./words"}
+nom = "*"
 
 [dev-dependencies]
 csv = "1.1"
diff --git a/src/lib.rs b/src/lib.rs
index ad242c5..0ce58f7 100644
--- a/src/lib.rs
+++ b/src/lib.rs
@@ -4,6 +4,7 @@
 #![allow(clippy::module_name_repetitions)]
 
 pub mod v0;
+pub mod wide;
 use conversions::lat_lon_to_cellid;
 pub use s2::s1::angle::Angle;
 use std::{
diff --git a/src/wide.rs b/src/wide.rs
new file mode 100644
index 0000000..4992a5b
--- /dev/null
+++ b/src/wide.rs
@@ -0,0 +1,148 @@
+use std::{fmt::Display, str::FromStr};
+
+use nom::{
+    branch::alt,
+    bytes::complete::tag_no_case,
+    character::complete::{self, alpha1, space0},
+    combinator::{eof, map, map_opt},
+    complete::tag,
+    multi::many1,
+    sequence::{pair, tuple},
+    IResult,
+};
+use words::Word;
+
+use crate::{Address, Error, Number};
+
+// TODO: Remove the english pronounciations of this separator from the wordlist
+pub const SEPARATOR: &str = "AND";
+pub const SEPARATOR_CHAR: &str = "&";
+
+pub struct Addresses<'a> {
+    addresses: Vec<Address<'a>>,
+}
+
+impl<'a> Addresses<'a> {
+    // fn to_compact_tokens(&self) -> impl Iterator<Item=Token<'a>> {
+
+    // }
+}
+
+impl<'a> From<Vec<Address<'a>>> for Addresses<'a> {
+    fn from(addresses: Vec<Address<'a>>) -> Self {
+        Self { addresses }
+    }
+}
+
+impl Display for Addresses<'_> {
+    fn fmt(&self, f: &mut std::fmt::Formatter<'_>) -> std::fmt::Result {
+        todo!()
+    }
+}
+
+impl FromStr for Addresses<'static> {
+    type Err = Error;
+
+    fn from_str(s: &str) -> Result<Self, Self::Err> {
+        todo!()
+    }
+}
+
+#[derive(Debug, Eq, PartialEq, PartialOrd, Ord)]
+enum Token<'a> {
+    Number(Number),
+    Word(&'a Word<'a>),
+    WideSeparator,
+}
+
+impl Token<'static> {
+    fn parse_stream(i: &str) -> IResult<&str, Vec<Self>> {
+        tuple((
+            space0,
+            many1(map(pair(Self::parse, space0), |(t, _)| t)),
+            eof,
+        ))(i)
+        .map(|(_i, (_space, tokens, _eof))| ("", tokens))
+    }
+
+    fn parse(i: &str) -> IResult<&str, Self> {
+        alt((
+            map_opt(alpha1, |maybe_word| {
+                words::get_word(maybe_word).map(Self::Word)
+            }),
+            map(complete::u32, Self::Number),
+            map(
+                alt((tag_no_case(SEPARATOR), tag_no_case(SEPARATOR_CHAR))),
+                |_| Self::WideSeparator,
+            ),
+        ))(i)
+    }
+}
+
+#[cfg(test)]
+mod tests {
+    use super::*;
+
+    #[test]
+    fn test_parse_token() {
+        assert_eq!(Token::parse("&"), Ok(("", Token::WideSeparator)));
+        assert_eq!(Token::parse("AnD"), Ok(("", Token::WideSeparator)));
+        assert_eq!(Token::parse("AnD  "), Ok(("  ", Token::WideSeparator)));
+        assert_eq!(Token::parse("AnD&&  "), Ok(("&&  ", Token::WideSeparator)));
+
+        assert_eq!(Token::parse("1234&&"), Ok(("&&", Token::Number(1234))));
+
+        assert_eq!(
+            Token::parse("clarify"),
+            Ok(("", Token::Word(words::get_word("clarify").unwrap())))
+        );
+
+        assert!(Token::parse("").is_err());
+    }
+
+    #[test]
+    fn test_parse_token_stream() {
+        assert_eq!(
+            Token::parse_stream(" & "),
+            Ok(("", vec![Token::WideSeparator]))
+        );
+        assert_eq!(
+            Token::parse_stream("AnD"),
+            Ok(("", vec![Token::WideSeparator,]))
+        );
+        assert_eq!(
+            Token::parse_stream("AnD  "),
+            Ok(("", vec![Token::WideSeparator]))
+        );
+        assert_eq!(
+            Token::parse_stream("AnD&&  "),
+            Ok((
+                "",
+                vec![
+                    Token::WideSeparator,
+                    Token::WideSeparator,
+                    Token::WideSeparator,
+                ]
+            ))
+        );
+
+        assert_eq!(
+            Token::parse_stream("1234&&"),
+            Ok((
+                "",
+                vec![
+                    Token::Number(1234),
+                    Token::WideSeparator,
+                    Token::WideSeparator,
+                ]
+            ))
+        );
+
+        assert_eq!(
+            Token::parse_stream("clarify"),
+            Ok(("", vec![Token::Word(words::get_word("clarify").unwrap())]))
+        );
+
+        assert!(Token::parse_stream("clarify _").is_err());
+    }
+}
diff --git a/words/src/lib.rs b/words/src/lib.rs
index 3f2dcd3..97e2992 100644
--- a/words/src/lib.rs
+++ b/words/src/lib.rs
@@ -2,7 +2,7 @@ use std::fmt::Display;
 
 include!(concat!(env!("OUT_DIR"), "/codegen.rs"));
 
-#[derive(Debug, Clone, Eq, PartialEq)]
+#[derive(Debug, Clone, Eq, PartialEq, Ord, PartialOrd)]
 /// A word struct
 pub struct Word<'a> {
     /// The word itself