compile subset

README.md

@@ -103,7 +103,7 @@ Todo:
 | 🔴 |2049	| ↳ Multipurpose Internet Mail Extensions (MIME) Part Five: Conformance Criteria and Examples |
 |    |      | **Headers extensions** |
 | 🔴 |2183  | ↳ Communicating Presentation Information in Internet Messages: The Content-Disposition Header Field |
-| 🟩 |6532	| ↳ Internationalized Email Headers |
+| 🔴 |6532	| ↳ Internationalized Email Headers |
 | 🔴 |9228  | ↳ Delivered-To Email Header Field |
 |    |      | **MIME extensions** |
 | 🔴 |1847  | ↳ Security Multiparts for MIME: Multipart/Signed and Multipart/Encrypted |

src/text/buffer.rs

@@ -1,12 +1,10 @@
-use encoding_rs::Encoding;
-
 #[derive(Debug, PartialEq, Default)]
 pub struct Text<'a> {
     parts: Vec<&'a [u8]>,
 }
 
 impl<'a> Text<'a> {
-    pub fn push(&mut self, e: &[u8]) {
+    pub fn push(&mut self, e: &'a [u8]) {
         self.parts.push(e)
     }
 

src/text/encoding.rs

@@ -48,6 +48,14 @@ pub enum EncodedWord<'a> {
     Quoted(QuotedWord<'a>),
     Base64(Base64Word<'a>),
 }
+impl<'a> EncodedWord<'a> {
+    pub fn to_string(&self) -> String  {
+        match self {
+            EncodedWord::Quoted(v) => v.to_string(),
+            EncodedWord::Base64(v) => v.to_string(),
+        }
+    }
+}
 
 #[derive(PartialEq,Debug)]
 pub struct Base64Word<'a> {

src/text/misc_token.rs

@@ -2,12 +2,11 @@ use nom::{
     branch::alt,
     bytes::complete::take_while1,
     character::complete::space0,
-    combinator::{into, map, opt},
+    combinator::{map, opt},
     multi::{many0, many1},
-    sequence::{preceded, tuple},
+    sequence::{preceded},
     IResult,
 };
-use std::borrow::Cow;
 
 use crate::text::{
     quoted::quoted_string,
@@ -52,7 +51,7 @@ impl<'a> Word<'a> {
         match self {
             Word::Quoted(v) => v.to_string(),
             Word::Encoded(v) => v.to_string(),
-            Word::Atom(v) => v.to_string(),
+            Word::Atom(v) => encoding_rs::UTF_8.decode_without_bom_handling(v).0.to_string(),
         }
     }
 }
@@ -73,7 +72,7 @@ pub fn word(input: &[u8]) -> IResult<&[u8], Word> {
 pub struct Phrase<'a>(pub Vec<Word<'a>>);
 impl<'a> Phrase<'a> {
     pub fn to_string(&self) -> String {
-        self.0.join(" ")
+        self.0.iter().map(|v| v.to_string()).collect::<Vec<String>>().join(" ")
     }
 }
 
@@ -96,7 +95,7 @@ fn is_unstructured(c: u8) -> bool {
     is_vchar(c) || is_obs_no_ws_ctl(c) || c == ascii::NULL
 }
 
-enum UnstrToken<'a> {
+pub enum UnstrToken<'a> {
     Init,
     Encoded(encoding::EncodedWord<'a>),
     Plain(&'a [u8]),
@@ -106,7 +105,7 @@ impl<'a> UnstrToken<'a> {
         match self {
             UnstrToken::Init => "".into(),
             UnstrToken::Encoded(e) => e.to_string(),
-            UnstrToken::Plain(e) => encoding_rs::UTF_8.decode_without_bom_handling(e).into_owned(),
+            UnstrToken::Plain(e) => encoding_rs::UTF_8.decode_without_bom_handling(e).0.into_owned(),
         }
     }
 }
@@ -116,19 +115,19 @@ impl<'a> Unstructured<'a> {
     pub fn to_string(&self) -> String {
         self.0.iter().fold(
             (&UnstrToken::Init, String::new()),
-            |(prev_token, result), current_token| {
+            |(prev_token, mut result), current_token| {
                 match (prev_token, current_token) {
                     (UnstrToken::Init, v) => result.push_str(v.to_string().as_ref()),
-                    (UnstrToken::EncodedWord(_), UnstrToken::EncodedWord(v)) => result.push_str(v.to_string()).as_ref(),
+                    (UnstrToken::Encoded(_), UnstrToken::Encoded(v)) => result.push_str(v.to_string().as_ref()),
                     (_, v) => {
                         result.push(' ');
                         result.push_str(v.to_string().as_ref())
                     },
                 };
 
-                result
+                (current_token, result)
             }
-        )
+        ).1
     }
 }
 

src/text/quoted.rs

@@ -1,8 +1,7 @@
 use nom::{
     branch::alt,
-    bytes::complete::{take_while1, tag},
-    character::complete::anychar,
-    combinator::{recognize, opt},
+    bytes::complete::{take_while1, take, tag},
+    combinator::{opt},
     multi::many0,
     sequence::{pair, preceded},
     IResult,
@@ -18,10 +17,12 @@ use crate::text::buffer;
 ///    quoted-pair     =   ("\" (VCHAR / WSP)) / obs-qp
 ///    obs-qp          =   "\" (%d0 / obs-NO-WS-CTL / LF / CR)
 /// ```
-pub fn quoted_pair(input: &[u8]) -> IResult<&[u8], u8> {
-    preceded(tag(&[ascii::SLASH]), anychar)(input)
+pub fn quoted_pair(input: &[u8]) -> IResult<&[u8], &[u8]> {
+    preceded(tag(&[ascii::SLASH]), take(1usize))(input)
 }
 
+
+
 /// Allowed characters in quote
 ///
 /// ```abnf
@@ -43,8 +44,8 @@ fn is_qtext(c: u8) -> bool {
 /// ```abnf
 ///   qcontent        =   qtext / quoted-pair
 /// ```
-fn qcontent(input: &u8) -> IResult<&[u8], &[u8]> {
-    alt((take_while1(is_qtext), recognize(quoted_pair)))(input)
+fn qcontent(input: &[u8]) -> IResult<&[u8], &[u8]> {
+    alt((take_while1(is_qtext), quoted_pair))(input)
 }
 
 /// Quoted string
@@ -63,7 +64,7 @@ pub fn quoted_string(input: &[u8]) -> IResult<&[u8], buffer::Text> {
     let mut qstring = content
         .iter()
         .fold(buffer::Text::default(), |mut acc, (maybe_wsp, c)| {
-            if let Some(wsp) = maybe_wsp {
+            if let Some(_) = maybe_wsp {
                 acc.push(&[ascii::SP]);
             }
             acc.push(c);
@@ -71,8 +72,8 @@ pub fn quoted_string(input: &[u8]) -> IResult<&[u8], buffer::Text> {
         });
 
     let (input, maybe_wsp) = opt(fws)(input)?;
-    if let Some(wsp) = maybe_wsp {
-        qstring.push(wsp);
+    if let Some(_) = maybe_wsp {
+        qstring.push(&[ascii::SP]);
     }
 
     let (input, _) = tag("\"")(input)?;