Plugins: String parser errors on invalid UTF-8

This will extend the example with error handling situation

application/apps/indexer/plugins/string_parser/Cargo.toml

@@ -5,7 +5,7 @@ name = "string_parser"
 version = "0.1.0"
 edition = "2021"
 authors = ["Ammar Abou Zor <ammar.abou.zor@accenture.com>"]
-description = "An example of a Chipmunk parser that parses the bytes into UTF-8 strings line by line, including invalid characters"
+description = "An example of a Chipmunk parser that parses the bytes into valid UTF-8 strings line by line"
 
 [dependencies]
 # TODO AAZ: Use lib from crates.io once the crate is published

application/apps/indexer/plugins/string_parser/README.md

@@ -1,5 +1,5 @@
 # String Tokenizer Parser
 
 This example demonstrates a simple plugin parser in Chipmunk.
-The parser converts the provided bytes into UTF-8 strings, processing them line by line, including any invalid characters.
+The parser converts the provided bytes into UTF-8 strings, processing them line by line, and it will error on encountering invalid UTF-8 characters.
 This example will guide you through creating and configuring a plugin using the provided configurations, as well as utilizing support functions from this library, such as logging.

application/apps/indexer/plugins/string_parser/src/lib.rs

@@ -1,3 +1,4 @@
+use core::str;
 use std::{iter, path::PathBuf};
 
 use memchr::memchr;
@@ -7,27 +8,20 @@ use plugins_api::{
     parser_export,
 };
 
-/// Simple struct that converts the given bytes into UTF-8 Strings - including
-/// invalid characters, line by line.
+/// Simple struct that converts the given bytes into valid UTF-8 Strings line by line.
 pub struct StringTokenizer;
 
 impl StringTokenizer {
     /// Converts a slice from the given data to UTF-8 String stopping when it hit the first
     /// break-line character to return one line at a time.
     fn parse_line(&self, data: &[u8]) -> Result<ParseReturn, ParseError> {
-        let res = if let Some(line_brk_idx) = memchr(b'\n', data) {
-            let line = String::from_utf8_lossy(&data[..line_brk_idx]);
-            let yld = ParseYield::Message(line.into());
+        let end_idx = memchr(b'\n', data).unwrap_or_else(|| data.len() - 1);
 
-            ParseReturn::new((line_brk_idx + 1) as u64, Some(yld))
-        } else {
-            let content = String::from_utf8_lossy(data);
-            let yld = ParseYield::Message(content.into());
+        let line = str::from_utf8(&data[..end_idx])
+            .map_err(|err| ParseError::Parse(format!("Convertion to UTF-8 failed. Error {err}")))?;
+        let yld = ParseYield::Message(line.into());
 
-            ParseReturn::new(data.len() as u64, Some(yld))
-        };
-
-        Ok(res)
+        Ok(ParseReturn::new((end_idx + 1) as u64, Some(yld)))
     }
 }