Upgrade nom dependency to 7.1.3 (#41)

* upgrade nom to 6.2.2 * upgrade nom to 7.1.3 * cargo clippy * fix formatting and clippy lint * bump major version because of Display trait implementation
jedireza · Nov 27, 2024 · 31235a2 · 31235a2
1 parent b34caac
commit 31235a2
Show file tree

Hide file tree

Showing 12 changed files with 111 additions and 88 deletions.
diff --git a/Cargo.toml b/Cargo.toml
@@ -1,6 +1,6 @@
 [package]
 name = "warc"
-version = "0.3.3"
+version = "0.4.0"
 description = "A Rust library for reading and writing WARC files."
 readme = "README.md"
 repository = "https://github.com/jedireza/warc"
@@ -12,7 +12,7 @@ edition = "2018"
 
 [dependencies]
 chrono = "0.4.11"
-nom = "5.1.1"
+nom = "7.1.3"
 url = "2"
 uuid = { version = "0.8.1", features = ["v4"] }
 

diff --git a/examples/read_file.rs b/examples/read_file.rs
@@ -10,9 +10,9 @@ fn main() -> Result<(), std::io::Error> {
         match record {
             Err(err) => println!("ERROR: {}\r\n", err),
             Ok(record) => {
-                println!("{}: {}", WarcHeader::RecordID.to_string(), record.warc_id(),);
-                println!("{}: {}", WarcHeader::Date.to_string(), record.date(),);
-                println!("");
+                println!("{}: {}", WarcHeader::RecordID, record.warc_id(),);
+                println!("{}: {}", WarcHeader::Date, record.date(),);
+                println!();
             }
         }
     }

diff --git a/examples/read_filtered.rs b/examples/read_filtered.rs
@@ -16,7 +16,7 @@ fn main() -> std::io::Result<()> {
 
     let filtered_file_names: Vec<_> = args.map(|s| s.to_string_lossy().to_string()).collect();
     if filtered_file_names.is_empty() {
-        return Err(usage_err!("one or more filtered file names not supplied"))?;
+        Err(usage_err!("one or more filtered file names not supplied"))?;
     }
 
     let mut file = WarcReader::from_path_gzip(warc_name)?;

diff --git a/examples/read_gzip.rs b/examples/read_gzip.rs
@@ -10,9 +10,9 @@ fn main() -> Result<(), std::io::Error> {
         match record {
             Err(err) => println!("ERROR: {}\r\n", err),
             Ok(record) => {
-                println!("{}: {}", WarcHeader::RecordID.to_string(), record.warc_id());
-                println!("{}: {}", WarcHeader::Date.to_string(), record.date());
-                println!("");
+                println!("{}: {}", WarcHeader::RecordID, record.warc_id());
+                println!("{}: {}", WarcHeader::Date, record.date());
+                println!();
             }
         }
     }

diff --git a/examples/read_raw.rs b/examples/read_raw.rs
@@ -12,15 +12,15 @@ fn main() -> Result<(), std::io::Error> {
             Ok((headers, _)) => {
                 println!(
                     "{}: {}",
-                    WarcHeader::RecordID.to_string(),
+                    WarcHeader::RecordID,
                     String::from_utf8_lossy(headers.as_ref().get(&WarcHeader::RecordID).unwrap())
                 );
                 println!(
                     "{}: {}",
-                    WarcHeader::Date.to_string(),
+                    WarcHeader::Date,
                     String::from_utf8_lossy(headers.as_ref().get(&WarcHeader::Date).unwrap())
                 );
-                println!("");
+                println!();
             }
         }
     }

diff --git a/src/error.rs b/src/error.rs
@@ -26,9 +26,9 @@ impl fmt::Display for Error {
     fn fmt(&self, f: &mut fmt::Formatter) -> fmt::Result {
         match self {
             Error::ParseHeaders(_) => write!(f, "Error parsing headers."),
-            Error::MissingHeader(ref h) => write!(f, "Missing required header: {}", h.to_string()),
+            Error::MissingHeader(ref h) => write!(f, "Missing required header: {}", h),
             Error::MalformedHeader(ref h, ref r) => {
-                write!(f, "Malformed header: {}: {}", h.to_string(), r)
+                write!(f, "Malformed header: {}: {}", h, r)
             }
             Error::ReadData(_) => write!(f, "Error reading data source."),
             Error::ReadOverflow => write!(f, "Read further than expected."),

diff --git a/src/parser.rs b/src/parser.rs
@@ -14,7 +14,10 @@ fn version(input: &[u8]) -> IResult<&[u8], &str> {
 
     let version_str = match str::from_utf8(version) {
         Err(_) => {
-            return Err(nom::Err::Error((input, ErrorKind::Verify)));
+            return Err(nom::Err::Error(nom::error::Error::new(
+                input,
+                ErrorKind::Verify,
+            )));
         }
         Ok(version) => version,
     };
@@ -23,8 +26,7 @@ fn version(input: &[u8]) -> IResult<&[u8], &str> {
 }
 
 fn is_header_token_char(chr: u8) -> bool {
-    match chr {
-        0..=31
+    !matches!(chr, 0..=31
         | 128..=255
         | b'('
         | b')'
@@ -43,9 +45,7 @@ fn is_header_token_char(chr: u8) -> bool {
         | b'{'
         | b'}'
         | b' '
-        | b'\\' => false,
-        _ => true,
-    }
+        | b'\\')
 }
 
 fn header(input: &[u8]) -> IResult<&[u8], (&[u8], &[u8])> {
@@ -63,6 +63,7 @@ fn header(input: &[u8]) -> IResult<&[u8], (&[u8], &[u8])> {
 
 /// Parse a WARC header block.
 // TODO: evaluate the use of `ErrorKind::Verify` here.
+#[allow(clippy::type_complexity)]
 pub fn headers(input: &[u8]) -> IResult<&[u8], (&str, Vec<(&str, &[u8])>, usize)> {
     let (input, version) = version(input)?;
     let (input, headers) = many1(header)(input)?;
@@ -73,22 +74,31 @@ pub fn headers(input: &[u8]) -> IResult<&[u8], (&str, Vec<(&str, &[u8])>, usize)
     for header in headers {
         let token_str = match str::from_utf8(header.0) {
             Err(_) => {
-                return Err(nom::Err::Error((input, ErrorKind::Verify)));
+                return Err(nom::Err::Error(nom::error::Error::new(
+                    input,
+                    ErrorKind::Verify,
+                )));
             }
             Ok(token) => token,
         };
 
-        if content_length == None && token_str.to_lowercase() == "content-length" {
+        if content_length.is_none() && token_str.to_lowercase() == "content-length" {
             let value_str = match str::from_utf8(header.1) {
                 Err(_) => {
-                    return Err(nom::Err::Error((input, ErrorKind::Verify)));
+                    return Err(nom::Err::Error(nom::error::Error::new(
+                        input,
+                        ErrorKind::Verify,
+                    )));
                 }
                 Ok(value) => value,
             };
 
             match value_str.parse::<usize>() {
                 Err(_) => {
-                    return Err(nom::Err::Error((input, ErrorKind::Verify)));
+                    return Err(nom::Err::Error(nom::error::Error::new(
+                        input,
+                        ErrorKind::Verify,
+                    )));
                 }
                 Ok(len) => {
                     content_length = Some(len);
@@ -101,14 +111,15 @@ pub fn headers(input: &[u8]) -> IResult<&[u8], (&str, Vec<(&str, &[u8])>, usize)
 
     // TODO: Technically if we didn't find a `content-length` header, the record is invalid. Should
     // we be returning an error here instead?
-    if content_length == None {
+    if content_length.is_none() {
         content_length = Some(0);
     }
 
     Ok((input, (version, warc_headers, content_length.unwrap())))
 }
 
 /// Parse an entire WARC record.
+#[allow(clippy::type_complexity)]
 pub fn record(input: &[u8]) -> IResult<&[u8], (&str, Vec<(&str, &[u8])>, &[u8])> {
     let (input, (headers, _)) = tuple((headers, line_ending))(input)?;
     let (input, (body, _, _)) = tuple((take(headers.2), line_ending, line_ending))(input)?;
@@ -125,13 +136,13 @@ mod tests {
 
     #[test]
     fn version_parsing() {
-        assert_eq!(version(&b"WARC/0.0\r\n"[..]), Ok((&b""[..], &"0.0"[..])));
+        assert_eq!(version(&b"WARC/0.0\r\n"[..]), Ok((&b""[..], "0.0")));
 
-        assert_eq!(version(&b"WARC/1.0\r\n"[..]), Ok((&b""[..], &"1.0"[..])));
+        assert_eq!(version(&b"WARC/1.0\r\n"[..]), Ok((&b""[..], "1.0")));
 
         assert_eq!(
             version(&b"WARC/2.0-alpha\r\n"[..]),
-            Ok((&b""[..], &"2.0-alpha"[..]))
+            Ok((&b""[..], "2.0-alpha"))
         );
     }
 
@@ -168,7 +179,10 @@ mod tests {
 
         assert_eq!(
             headers(&raw_invalid[..]),
-            Err(Err::Error((&b"\r\n"[..], ErrorKind::Verify)))
+            Err(Err::Error(nom::error::Error::new(
+                &b"\r\n"[..],
+                ErrorKind::Verify
+            )))
         );
 
         let raw = b"\

diff --git a/src/record.rs b/src/record.rs
@@ -51,9 +51,8 @@ mod streaming_trait {
     impl<'t, T: Read + 't> Read for StreamingBody<'t, T> {
         fn read(&mut self, data: &mut [u8]) -> std::io::Result<usize> {
             let max_read = std::cmp::min(data.len(), *self.1 as usize);
-            self.0.read(&mut data[..max_read as usize]).map(|n| {
+            self.0.read(&mut data[..max_read]).inspect(|&n| {
                 *self.1 -= n as u64;
-                n
             })
         }
     }
@@ -156,7 +155,7 @@ impl std::fmt::Display for RawRecordHeader {
     fn fmt(&self, w: &mut std::fmt::Formatter<'_>) -> Result<(), std::fmt::Error> {
         writeln!(w, "WARC/{}", self.version)?;
         for (key, value) in self.as_ref().iter() {
-            writeln!(w, "{}: {}", key.to_string(), String::from_utf8_lossy(value))?;
+            writeln!(w, "{}: {}", key, String::from_utf8_lossy(value))?;
         }
         writeln!(w)?;
 
@@ -263,7 +262,7 @@ impl<T: BodyKind> Record<T> {
     /// The current implementation generates random values based on UUID version 4.
     ///
     pub fn generate_record_id() -> String {
-        format!("<{}>", Uuid::new_v4().to_urn().to_string())
+        format!("<{}>", Uuid::new_v4().to_urn())
     }
 
     fn parse_content_length(len: &str) -> Result<u64, WarcError> {
@@ -1058,7 +1057,7 @@ mod raw_tests {
 
         let output = headers.to_string();
 
-        let expected_lines = vec![
+        let expected_lines = [
             "WARC/1.0",
             "warc-type: dunno",
             "warc-date: 2024-01-01T00:00:00Z",

diff --git a/src/record_type.rs b/src/record_type.rs
@@ -1,4 +1,6 @@
 #![allow(missing_docs)]
+
+use std::fmt::Display;
 #[derive(Clone, Debug, PartialEq)]
 pub enum RecordType {
     WarcInfo,
@@ -12,8 +14,8 @@ pub enum RecordType {
     Unknown(String),
 }
 
-impl ToString for RecordType {
-    fn to_string(&self) -> String {
+impl Display for RecordType {
+    fn fmt(&self, f: &mut std::fmt::Formatter<'_>) -> std::fmt::Result {
         let stringified = match *self {
             RecordType::WarcInfo => "warcinfo",
             RecordType::Response => "response",
@@ -25,7 +27,7 @@ impl ToString for RecordType {
             RecordType::Continuation => "continuation",
             RecordType::Unknown(ref val) => val.as_ref(),
         };
-        stringified.to_string()
+        f.write_str(stringified)
     }
 }
 

diff --git a/src/truncated_type.rs b/src/truncated_type.rs
@@ -1,4 +1,6 @@
 #![allow(missing_docs)]
+
+use std::fmt::Display;
 #[derive(Clone, Debug, PartialEq)]
 pub enum TruncatedType {
     Length,
@@ -8,16 +10,16 @@ pub enum TruncatedType {
     Unknown(String),
 }
 
-impl ToString for TruncatedType {
-    fn to_string(&self) -> String {
+impl Display for TruncatedType {
+    fn fmt(&self, f: &mut std::fmt::Formatter<'_>) -> std::fmt::Result {
         let stringified = match *self {
             TruncatedType::Length => "length",
             TruncatedType::Time => "time",
             TruncatedType::Disconnect => "disconnect",
             TruncatedType::Unspecified => "unspecified",
             TruncatedType::Unknown(ref val) => val.as_ref(),
         };
-        stringified.to_string()
+        f.write_str(stringified)
     }
 }