implement date parsing

Cargo.lock

@@ -2,13 +2,118 @@
 # It is not intended for manual editing.
 version = 3
 
+[[package]]
+name = "android-tzdata"
+version = "0.1.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "e999941b234f3131b00bc13c22d06e8c5ff726d1b6318ac7eb276997bbb4fef0"
+
+[[package]]
+name = "android_system_properties"
+version = "0.1.5"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "819e7219dbd41043ac279b19830f2efc897156490d7fd6ea916720117ee66311"
+dependencies = [
+ "libc",
+]
+
+[[package]]
+name = "autocfg"
+version = "1.1.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "d468802bab17cbc0cc575e9b053f41e72aa36bfa6b7f55e3529ffa43161b97fa"
+
+[[package]]
+name = "bumpalo"
+version = "3.13.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "a3e2c3daef883ecc1b5d58c15adae93470a91d425f3532ba1695849656af3fc1"
+
+[[package]]
+name = "cc"
+version = "1.0.79"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "50d30906286121d95be3d479533b458f87493b30a4b5f79a607db8f5d11aa91f"
+
+[[package]]
+name = "cfg-if"
+version = "1.0.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "baf1de4339761588bc0619e3cbc0120ee582ebb74b53b4efbf79117bd2da40fd"
+
+[[package]]
+name = "chrono"
+version = "0.4.26"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "ec837a71355b28f6556dbd569b37b3f363091c0bd4b2e735674521b4c5fd9bc5"
+dependencies = [
+ "android-tzdata",
+ "iana-time-zone",
+ "js-sys",
+ "num-traits",
+ "time",
+ "wasm-bindgen",
+ "winapi",
+]
+
+[[package]]
+name = "core-foundation-sys"
+version = "0.8.4"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "e496a50fda8aacccc86d7529e2c1e0892dbd0f898a6b5645b5561b89c3210efa"
+
+[[package]]
+name = "iana-time-zone"
+version = "0.1.57"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "2fad5b825842d2b38bd206f3e81d6957625fd7f0a361e345c30e01a0ae2dd613"
+dependencies = [
+ "android_system_properties",
+ "core-foundation-sys",
+ "iana-time-zone-haiku",
+ "js-sys",
+ "wasm-bindgen",
+ "windows",
+]
+
+[[package]]
+name = "iana-time-zone-haiku"
+version = "0.1.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "f31827a206f56af32e590ba56d5d2d085f558508192593743f16b2306495269f"
+dependencies = [
+ "cc",
+]
+
 [[package]]
 name = "imf-codec"
 version = "0.1.0"
 dependencies = [
+ "chrono",
  "nom",
 ]
 
+[[package]]
+name = "js-sys"
+version = "0.3.63"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "2f37a4a5928311ac501dee68b3c7613a1037d0edb30c8e5427bd832d55d1b790"
+dependencies = [
+ "wasm-bindgen",
+]
+
+[[package]]
+name = "libc"
+version = "0.2.146"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "f92be4933c13fd498862a9e02a3055f8a8d9c039ce33db97306fd5a6caa7f29b"
+
+[[package]]
+name = "log"
+version = "0.4.19"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "b06a4cde4c0f271a446782e3eff8de789548ce57dbc8eca9292c27f4a42004b4"
+
 [[package]]
 name = "memchr"
 version = "2.5.0"
@@ -30,3 +135,212 @@ dependencies = [
  "memchr",
  "minimal-lexical",
 ]
+
+[[package]]
+name = "num-traits"
+version = "0.2.15"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "578ede34cf02f8924ab9447f50c28075b4d3e5b269972345e7e0372b38c6cdcd"
+dependencies = [
+ "autocfg",
+]
+
+[[package]]
+name = "once_cell"
+version = "1.18.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "dd8b5dd2ae5ed71462c540258bedcb51965123ad7e7ccf4b9a8cafaa4a63576d"
+
+[[package]]
+name = "proc-macro2"
+version = "1.0.60"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "dec2b086b7a862cf4de201096214fa870344cf922b2b30c167badb3af3195406"
+dependencies = [
+ "unicode-ident",
+]
+
+[[package]]
+name = "quote"
+version = "1.0.28"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "1b9ab9c7eadfd8df19006f1cf1a4aed13540ed5cbc047010ece5826e10825488"
+dependencies = [
+ "proc-macro2",
+]
+
+[[package]]
+name = "syn"
+version = "2.0.18"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "32d41677bcbe24c20c52e7c70b0d8db04134c5d1066bf98662e2871ad200ea3e"
+dependencies = [
+ "proc-macro2",
+ "quote",
+ "unicode-ident",
+]
+
+[[package]]
+name = "time"
+version = "0.1.45"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "1b797afad3f312d1c66a56d11d0316f916356d11bd158fbc6ca6389ff6bf805a"
+dependencies = [
+ "libc",
+ "wasi",
+ "winapi",
+]
+
+[[package]]
+name = "unicode-ident"
+version = "1.0.9"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "b15811caf2415fb889178633e7724bad2509101cde276048e013b9def5e51fa0"
+
+[[package]]
+name = "wasi"
+version = "0.10.0+wasi-snapshot-preview1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "1a143597ca7c7793eff794def352d41792a93c481eb1042423ff7ff72ba2c31f"
+
+[[package]]
+name = "wasm-bindgen"
+version = "0.2.86"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "5bba0e8cb82ba49ff4e229459ff22a191bbe9a1cb3a341610c9c33efc27ddf73"
+dependencies = [
+ "cfg-if",
+ "wasm-bindgen-macro",
+]
+
+[[package]]
+name = "wasm-bindgen-backend"
+version = "0.2.86"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "19b04bc93f9d6bdee709f6bd2118f57dd6679cf1176a1af464fca3ab0d66d8fb"
+dependencies = [
+ "bumpalo",
+ "log",
+ "once_cell",
+ "proc-macro2",
+ "quote",
+ "syn",
+ "wasm-bindgen-shared",
+]
+
+[[package]]
+name = "wasm-bindgen-macro"
+version = "0.2.86"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "14d6b024f1a526bb0234f52840389927257beb670610081360e5a03c5df9c258"
+dependencies = [
+ "quote",
+ "wasm-bindgen-macro-support",
+]
+
+[[package]]
+name = "wasm-bindgen-macro-support"
+version = "0.2.86"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "e128beba882dd1eb6200e1dc92ae6c5dbaa4311aa7bb211ca035779e5efc39f8"
+dependencies = [
+ "proc-macro2",
+ "quote",
+ "syn",
+ "wasm-bindgen-backend",
+ "wasm-bindgen-shared",
+]
+
+[[package]]
+name = "wasm-bindgen-shared"
+version = "0.2.86"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "ed9d5b4305409d1fc9482fee2d7f9bcbf24b3972bf59817ef757e23982242a93"
+
+[[package]]
+name = "winapi"
+version = "0.3.9"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "5c839a674fcd7a98952e593242ea400abe93992746761e38641405d28b00f419"
+dependencies = [
+ "winapi-i686-pc-windows-gnu",
+ "winapi-x86_64-pc-windows-gnu",
+]
+
+[[package]]
+name = "winapi-i686-pc-windows-gnu"
+version = "0.4.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "ac3b87c63620426dd9b991e5ce0329eff545bccbbb34f3be09ff6fb6ab51b7b6"
+
+[[package]]
+name = "winapi-x86_64-pc-windows-gnu"
+version = "0.4.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "712e227841d057c1ee1cd2fb22fa7e5a5461ae8e48fa2ca79ec42cfc1931183f"
+
+[[package]]
+name = "windows"
+version = "0.48.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "e686886bc078bc1b0b600cac0147aadb815089b6e4da64016cbd754b6342700f"
+dependencies = [
+ "windows-targets",
+]
+
+[[package]]
+name = "windows-targets"
+version = "0.48.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "7b1eb6f0cd7c80c79759c929114ef071b87354ce476d9d94271031c0497adfd5"
+dependencies = [
+ "windows_aarch64_gnullvm",
+ "windows_aarch64_msvc",
+ "windows_i686_gnu",
+ "windows_i686_msvc",
+ "windows_x86_64_gnu",
+ "windows_x86_64_gnullvm",
+ "windows_x86_64_msvc",
+]
+
+[[package]]
+name = "windows_aarch64_gnullvm"
+version = "0.48.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "91ae572e1b79dba883e0d315474df7305d12f569b400fcf90581b06062f7e1bc"
+
+[[package]]
+name = "windows_aarch64_msvc"
+version = "0.48.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "b2ef27e0d7bdfcfc7b868b317c1d32c641a6fe4629c171b8928c7b08d98d7cf3"
+
+[[package]]
+name = "windows_i686_gnu"
+version = "0.48.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "622a1962a7db830d6fd0a69683c80a18fda201879f0f447f065a3b7467daa241"
+
+[[package]]
+name = "windows_i686_msvc"
+version = "0.48.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "4542c6e364ce21bf45d69fdd2a8e455fa38d316158cfd43b3ac1c5b1b19f8e00"
+
+[[package]]
+name = "windows_x86_64_gnu"
+version = "0.48.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "ca2b8a661f7628cbd23440e50b05d705db3686f894fc9580820623656af974b1"
+
+[[package]]
+name = "windows_x86_64_gnullvm"
+version = "0.48.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "7896dbc1f41e08872e9d5e8f8baa8fdd2677f29468c4e156210174edc7f7b953"
+
+[[package]]
+name = "windows_x86_64_msvc"
+version = "0.48.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "1a515f5799fe4961cb532f983ce2b23082366b898e52ffbce459c86f67c8378a"

Cargo.toml

@@ -17,3 +17,4 @@ path = "src/parse.rs"
 
 [dependencies]
 nom = "7"
+chrono = "0.4"

src/headers.rs

@@ -1,3 +1,4 @@
+use chrono::DateTime;
 use nom::{
     IResult,
     bytes::complete::take_while1,
@@ -11,7 +12,7 @@ use nom::{
 };
 
 use crate::abnf::{fws, vchar_seq, perm_crlf};
-use crate::model::HeaderSection;
+use crate::model::{HeaderSection, HeaderDate};
 
 /// HEADERS
 
@@ -24,6 +25,11 @@ pub fn header_section(input: &str) -> IResult<&str, HeaderSection> {
         HeaderSection::default,
         |mut section, head| {
             match head {
+                HeaderField::Date(d) => {
+                    //@FIXME only one date is allowed, what are we doing if multiple dates are
+                    //encountered? Currently, we override...
+                    section.date = d;
+                }
                 HeaderField::Subject(title) => {
                     section.subject = Some(title);
                 }
@@ -42,7 +48,7 @@ pub fn header_section(input: &str) -> IResult<&str, HeaderSection> {
 
 enum HeaderField<'a> {
     // 3.6.1.  The Origination Date Field
-    Date,
+    Date(HeaderDate),
 
     // 3.6.2.  Originator Fields
     From,
@@ -97,21 +103,31 @@ fn header_field(input: &str) -> IResult<&str, HeaderField> {
     let (input, _) = tuple((tag(":"), space0))(input)?;
 
     // Extract field body
-    match field_name {
+    let (input, hfield) = match field_name {
-        "Date" => unimplemented!(),
+        "Date" => {
+            // @FIXME want to extract datetime our way in the future
+            // to better handle obsolete/bad cases instead of crashing.
+            let (input, raw_date) = unstructured(input)?;
+            let date = match DateTime::parse_from_rfc2822(&raw_date) {
+                Ok(chronodt) => HeaderDate::Parsed(chronodt),
+                Err(e) => HeaderDate::Unknown(raw_date, e),
+            };
+            (input, HeaderField::Date(date))
+        },
         //"From" => unimplemented!(),
         "Sender" => unimplemented!(),
         "Subject" => {
             let (input, body) = unstructured(input)?;
-            let (input, _) = crlf(input)?;
+            (input, HeaderField::Subject(body))
-            Ok((input, HeaderField::Subject(body)))
         },
         _ => {
             let (input, body) = unstructured(input)?;
+            (input, HeaderField::Optional(field_name, body))
+        }
+    };
+
     let (input, _) = crlf(input)?;
-            Ok((input, HeaderField::Optional(field_name, body)))
+    return Ok((input, hfield));
-        }
-    }
 }
 
 /// Unstructured header field body

src/model.rs

@@ -1,8 +1,33 @@
 use std::collections::HashMap;
+use chrono::{DateTime,FixedOffset,ParseError};
+
+#[derive(Debug, Default)]
+pub enum HeaderDate {
+    Parsed(DateTime<FixedOffset>),
+    Unknown(String, ParseError),
+    #[default]
+    None,
+}
 
 #[derive(Debug, Default)]
 pub struct HeaderSection<'a> {
     pub subject: Option<String>,
     pub from: Vec<String>,
+    pub date: HeaderDate,
     pub optional: HashMap<&'a str, String>,
 }
+
+enum InvalidEmailErr {
+    NoUsableDate,
+}
+
+impl<'a> HeaderSection<'a> {
+    fn is_valid(&self) -> Result<(), InvalidEmailErr> {
+        match self.date {
+            HeaderDate::Parsed(_) => (),
+            _ => return Err(InvalidEmailErr::NoUsableDate),
+        };
+
+        Ok(())
+    }
+}

src/parse.rs

@@ -1,6 +1,6 @@
 use imf_codec::headers;
 
 fn main() {
-    let header = "Subject: Hello\r\n World\r\nFrom: <quentin@deuxfleurs.fr>\r\n\r\nHello world";
+    let header = "Date: Fri, 21 Nov 1997 09:55:06 -0600\r\nSubject: Hello\r\n World\r\nFrom: <quentin@deuxfleurs.fr>\r\n\r\nHello world";
     println!("{:?}", headers::header_section(header));
 }