refactor, mod rfc5322 to imf

README.md

@@ -3,6 +3,24 @@
 **⚠️ Work in progress, do not use in production**  
 **⚠️ This is currently only a decoder (parser), encoding is not yet implemented.**
 
+## Example
+
+```rust
+let input = br#"
+Date: 7 Mar 2023 08:00:00 +0200
+From: deuxfleurs@example.com
+To: someone_else@example.com
+Subject: An RFC 822 formatted message
+MIME-Version: 1.0
+Content-Type: text/plain; charset=us-ascii
+
+This is the plain text body of the message. Note the blank line
+between the header information and the body of the message.#;
+
+let email = eml_codec::email(input).unwrap();
+println!("{} just sent you an email with subject \"{}\", email.1.
+```
+
 ## About the name
 
 This library does not aim at implementing a specific RFC, but to be a swiss-army knife to decode and encode ("codec") what is generaly considered an email (generally abbreviated "eml"), hence the name: **eml-codec**.
@@ -18,8 +36,7 @@ This library does not aim at implementing a specific RFC, but to be a swiss-army
 
   - Parsing optimization that would make more complicated to understand the logic.
   - Optimization for a specific use case, to the detriment of other use cases.
-  - Pipelining/streaming/buffering as the parser can arbitrarily backtrack + our result contains reference to the whole buffer, imf-codec must keep the whole buffer in memory. Avoiding the sequential approach would certainly speed-up a little bit the parsing, but it's too much work to implement currently.
-  - Zerocopy. It might be implementable in the future, but to quickly bootstrap this project, I avoided it for now.
+  - Pipelining/streaming/buffering as the parser can arbitrarily backtrack + our result contains reference to the whole buffer, eml-codec must keep the whole buffer in memory. Avoiding the sequential approach would certainly speed-up a little bit the parsing, but it's too much work to implement currently.
 
 ## Missing / known bugs
 
@@ -37,7 +54,7 @@ Speak about parser combinators.
 
 ## Testing strategy
 
-imf-codec aims to be as much tested as possible against reald
+eml-codec aims to be as much tested as possible against real word data.
 
 ### Unit testing: parser combinator independently (done)
 

notes.md

@@ -1,8 +0,0 @@
-Test enron files:
-
-```
-cd resources/enron
-./restore.sh
-cd -
-(set -euo pipefail; find resources/enron/maildir/ -type f | while read f; do echo $f; ./target/debug/imf_parse < $f > /dev/null; done)
-```

rfc822.eml

@@ -1,7 +0,0 @@
-Date: 7 Mar 2023 08:00:00 +0200
-From: someone@example.com
-To: someone_else@example.com
-Subject: An RFC 822 formatted message
-
-This is the plain text body of the message. Note the blank line
-between the header information and the body of the message.

src/imf/address.rs

@@ -8,7 +8,7 @@ use nom::{
 };
 
 //use crate::error::IMFError;
-use crate::rfc5322::mailbox::{mailbox, MailboxRef};
+use crate::imf::mailbox::{mailbox, MailboxRef};
 use crate::text::misc_token::{phrase, Phrase};
 use crate::text::whitespace::cfws;
 
@@ -109,7 +109,7 @@ pub fn nullable_address_list(input: &[u8]) -> IResult<&[u8], Vec<AddressRef>> {
 #[cfg(test)]
 mod tests {
     use super::*;
-    use crate::rfc5322::mailbox::{AddrSpec, Domain, LocalPart, LocalPartToken};
+    use crate::imf::mailbox::{AddrSpec, Domain, LocalPart, LocalPartToken};
     use crate::text::misc_token::{Phrase, Word};
 
     #[test]

src/imf/field.rs

@@ -7,13 +7,13 @@ use nom::{
 };
 
 use crate::header::{field_name, header};
-use crate::rfc5322::address::{address_list, mailbox_list, nullable_address_list, AddressList};
-use crate::rfc5322::datetime::section as date;
-use crate::rfc5322::identification::{msg_id, msg_list, MessageID, MessageIDList};
-use crate::rfc5322::mailbox::{mailbox, AddrSpec, MailboxList, MailboxRef};
-use crate::rfc5322::message::Message;
-use crate::rfc5322::mime::{version, Version};
-use crate::rfc5322::trace::{received_log, return_path, ReceivedLog};
+use crate::imf::address::{address_list, mailbox_list, nullable_address_list, AddressList};
+use crate::imf::datetime::section as date;
+use crate::imf::identification::{msg_id, msg_list, MessageID, MessageIDList};
+use crate::imf::mailbox::{mailbox, AddrSpec, MailboxList, MailboxRef};
+use crate::imf::message::Message;
+use crate::imf::mime::{version, Version};
+use crate::imf::trace::{received_log, return_path, ReceivedLog};
 use crate::text::misc_token::{phrase_list, unstructured, PhraseList, Unstructured};
 use crate::text::whitespace::obs_crlf;
 
@@ -95,8 +95,8 @@ pub fn message(input: &[u8]) -> IResult<&[u8], Message> {
 #[cfg(test)]
 mod tests {
     use super::*;
-    use crate::rfc5322::address::*;
-    use crate::rfc5322::mailbox::*;
+    use crate::imf::address::*;
+    use crate::imf::mailbox::*;
     use crate::text::misc_token::*;
     use chrono::{FixedOffset, TimeZone};
 

src/imf/identification.rs

@@ -8,7 +8,7 @@ use nom::{
     IResult,
 };
 
-use crate::rfc5322::mailbox::is_dtext;
+use crate::imf::mailbox::is_dtext;
 use crate::text::whitespace::cfws;
 use crate::text::words::dot_atom_text;
 

src/imf/message.rs

@@ -1,9 +1,9 @@
-use crate::rfc5322::address::AddressRef;
-use crate::rfc5322::field::Field;
-use crate::rfc5322::identification::MessageID;
-use crate::rfc5322::mailbox::{AddrSpec, MailboxRef};
-use crate::rfc5322::mime::Version;
-use crate::rfc5322::trace::ReceivedLog;
+use crate::imf::address::AddressRef;
+use crate::imf::field::Field;
+use crate::imf::identification::MessageID;
+use crate::imf::mailbox::{AddrSpec, MailboxRef};
+use crate::imf::mime::Version;
+use crate::imf::trace::ReceivedLog;
 use crate::text::misc_token::{PhraseList, Unstructured};
 use chrono::{DateTime, FixedOffset};
 

src/imf/trace.rs

@@ -8,7 +8,7 @@ use nom::{
     IResult,
 };
 
-use crate::rfc5322::{datetime, mailbox};
+use crate::imf::{datetime, mailbox};
 use crate::text::{ascii, misc_token, whitespace};
 
 #[derive(Debug, PartialEq)]
@@ -75,7 +75,7 @@ fn received_tokens(input: &[u8]) -> IResult<&[u8], ReceivedLogToken> {
 #[cfg(test)]
 mod tests {
     use super::*;
-    use crate::rfc5322::trace::misc_token::Word;
+    use crate::imf::trace::misc_token::Word;
     use chrono::TimeZone;
 
     #[test]

src/lib.rs

@@ -2,7 +2,7 @@ mod error;
 mod header;
 mod mime;
 mod part;
-mod rfc5322;
+mod imf;
 mod text;
 
 pub fn email(input: &[u8]) -> Result<part::part::Message, error::EMLError> {
@@ -11,8 +11,8 @@ pub fn email(input: &[u8]) -> Result<part::part::Message, error::EMLError> {
         .map_err(error::EMLError::ParseError)
 }
 
-pub fn imf(input: &[u8]) -> Result<rfc5322::message::Message, error::EMLError> {
-    rfc5322::field::message(input)
+pub fn imf(input: &[u8]) -> Result<imf::message::Message, error::EMLError> {
+    imf::field::message(input)
         .map(|(_, v)| v)
         .map_err(error::EMLError::ParseError)
 }

src/mime/field.rs

@@ -9,7 +9,7 @@ use crate::header::{field_name, CompFieldList};
 use crate::mime::mechanism::{mechanism, Mechanism};
 use crate::mime::mime::AnyMIME;
 use crate::mime::r#type::{naive_type, NaiveType};
-use crate::rfc5322::identification::{msg_id, MessageID};
+use crate::imf::identification::{msg_id, MessageID};
 use crate::text::misc_token::{unstructured, Unstructured};
 use crate::text::whitespace::obs_crlf;
 

src/mime/mime.rs

@@ -1,7 +1,7 @@
 use crate::mime::field::Content;
 use crate::mime::mechanism::Mechanism;
 use crate::mime::r#type::{self as ctype, AnyType};
-use crate::rfc5322::identification::MessageID;
+use crate::imf::identification::MessageID;
 use crate::text::misc_token::Unstructured; //Multipart, Message, Text, Binary};
 
 #[derive(Debug, PartialEq, Clone)]

src/part/part.rs

@@ -11,7 +11,7 @@ use nom::{
 use crate::header::{header, CompFieldList};
 use crate::mime;
 use crate::mime::mime::AnyMIME;
-use crate::rfc5322::{self as imf};
+use crate::imf::{self as imf};
 use crate::text::ascii::CRLF;
 use crate::text::boundary::{boundary, Delimiter};
 use crate::text::whitespace::obs_crlf;