feat: add html2text dependency and implement HTML to Markdown conversion in email body processing

Cargo.lock

@@ -305,6 +305,28 @@ version = "0.16.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "841d1cc9bed7f9236f321df977030373f4a4163ae1a7dbfe1a51a2c1a51d9100"
 
+[[package]]
+name = "html2text"
+version = "0.16.6"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "9ea4ba4c0f993633569337a4fadfbd4f27448c81adb1af0c2407065f52809662"
+dependencies = [
+ "html5ever",
+ "tendril",
+ "thiserror",
+ "unicode-width",
+]
+
+[[package]]
+name = "html5ever"
+version = "0.37.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "5935f02fdc02823ff15fec27c2b3d7ca19d629e996f7a0ae4d7d500e62e54c76"
+dependencies = [
+ "log",
+ "markup5ever",
+]
+
 [[package]]
 name = "http"
 version = "0.2.12"
@@ -596,6 +618,15 @@ version = "0.8.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "6373607a59f0be73a39b6fe456b8192fcc3585f602af20751600e974dd455e77"
 
+[[package]]
+name = "lock_api"
+version = "0.4.14"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "224399e74b87b5f3557511d98dff8b14089b3dadafcab6bb93eab67d3aace965"
+dependencies = [
+ "scopeguard",
+]
+
 [[package]]
 name = "log"
 version = "0.4.29"
@@ -613,6 +644,17 @@ dependencies = [
  "quoted_printable",
 ]
 
+[[package]]
+name = "markup5ever"
+version = "0.37.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "7cfb33ea12d5d83b1ba9a55ae7d05faec4f2189d47b79c04d4cea6bbe9f5b083"
+dependencies = [
+ "log",
+ "tendril",
+ "web_atoms",
+]
+
 [[package]]
 name = "memchr"
 version = "2.7.6"
@@ -653,14 +695,22 @@ dependencies = [
  "tempfile",
 ]
 
+[[package]]
+name = "new_debug_unreachable"
+version = "1.0.6"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "650eef8c711430f1a879fdd01d4745a7deea475becfb90269c06775983bbf086"
+
 [[package]]
 name = "newsletter"
 version = "0.1.0"
 dependencies = [
  "chrono",
+ "html2text",
  "imap",
  "mailparse",
  "native-tls",
+ "regex",
  "reqwest",
  "serde",
  "serde_json",
@@ -747,12 +797,74 @@ dependencies = [
  "vcpkg",
 ]
 
+[[package]]
+name = "parking_lot"
+version = "0.12.5"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "93857453250e3077bd71ff98b6a65ea6621a19bb0f559a85248955ac12c45a1a"
+dependencies = [
+ "lock_api",
+ "parking_lot_core",
+]
+
+[[package]]
+name = "parking_lot_core"
+version = "0.9.12"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "2621685985a2ebf1c516881c026032ac7deafcda1a2c9b7850dc81e3dfcb64c1"
+dependencies = [
+ "cfg-if",
+ "libc",
+ "redox_syscall",
+ "smallvec",
+ "windows-link",
+]
+
 [[package]]
 name = "percent-encoding"
 version = "2.3.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "9b4f627cb1b25917193a259e49bdad08f671f8d9708acfd5fe0a8c1455d87220"
 
+[[package]]
+name = "phf"
+version = "0.13.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "c1562dc717473dbaa4c1f85a36410e03c047b2e7df7f45ee938fbef64ae7fadf"
+dependencies = [
+ "phf_shared",
+ "serde",
+]
+
+[[package]]
+name = "phf_codegen"
+version = "0.13.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "49aa7f9d80421bca176ca8dbfebe668cc7a2684708594ec9f3c0db0805d5d6e1"
+dependencies = [
+ "phf_generator",
+ "phf_shared",
+]
+
+[[package]]
+name = "phf_generator"
+version = "0.13.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "135ace3a761e564ec88c03a77317a7c6b80bb7f7135ef2544dbe054243b89737"
+dependencies = [
+ "fastrand",
+ "phf_shared",
+]
+
+[[package]]
+name = "phf_shared"
+version = "0.13.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "e57fef6bc5981e38c2ce2d63bfa546861309f875b8a75f092d1d54ae2d64f266"
+dependencies = [
+ "siphasher",
+]
+
 [[package]]
 name = "pin-project-lite"
 version = "0.2.16"
@@ -780,6 +892,12 @@ dependencies = [
  "zerovec",
 ]
 
+[[package]]
+name = "precomputed-hash"
+version = "0.1.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "925383efa346730478fb4838dbe9137d2a47675ad789c546d150a6e1dd4ab31c"
+
 [[package]]
 name = "proc-macro2"
 version = "1.0.105"
@@ -810,6 +928,15 @@ version = "5.3.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "69cdb34c158ceb288df11e18b4bd39de994f6657d83847bdffdbd7f346754b0f"
 
+[[package]]
+name = "redox_syscall"
+version = "0.5.18"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "ed2bf2547551a7053d6fdfafda3f938979645c44812fbfcda098faae3f1a362d"
+dependencies = [
+ "bitflags 2.10.0",
+]
+
 [[package]]
 name = "regex"
 version = "1.12.2"
@@ -922,6 +1049,12 @@ dependencies = [
  "windows-sys 0.61.2",
 ]
 
+[[package]]
+name = "scopeguard"
+version = "1.2.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "94143f37725109f92c262ed2cf5e59bce7498c01bcc1502d7b9afe439a4e9f49"
+
 [[package]]
 name = "security-framework"
 version = "2.11.1"
@@ -1015,6 +1148,12 @@ version = "1.3.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "0fda2ff0d084019ba4d7c6f371c95d8fd75ce3524c3cb8fb653a3023f6323e64"
 
+[[package]]
+name = "siphasher"
+version = "1.0.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "56199f7ddabf13fe5074ce809e7d3f42b42ae711800501b5b16ea82ad029c39d"
+
 [[package]]
 name = "slab"
 version = "0.4.11"
@@ -1059,6 +1198,30 @@ version = "1.1.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "a2eb9349b6444b326872e140eb1cf5e7c522154d69e7a0ffb0fb81c06b37543f"
 
+[[package]]
+name = "string_cache"
+version = "0.9.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "a18596f8c785a729f2819c0f6a7eae6ebeebdfffbfe4214ae6b087f690e31901"
+dependencies = [
+ "new_debug_unreachable",
+ "parking_lot",
+ "phf_shared",
+ "precomputed-hash",
+]
+
+[[package]]
+name = "string_cache_codegen"
+version = "0.6.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "585635e46db231059f76c5849798146164652513eb9e8ab2685939dd90f29b69"
+dependencies = [
+ "phf_generator",
+ "phf_shared",
+ "proc-macro2",
+ "quote",
+]
+
 [[package]]
 name = "syn"
 version = "2.0.114"
@@ -1121,6 +1284,36 @@ dependencies = [
  "windows-sys 0.61.2",
 ]
 
+[[package]]
+name = "tendril"
+version = "0.5.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "c4790fc369d5a530f4b544b094e31388b9b3a37c0f4652ade4505945f5660d24"
+dependencies = [
+ "new_debug_unreachable",
+ "utf-8",
+]
+
+[[package]]
+name = "thiserror"
+version = "2.0.18"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "4288b5bcbc7920c07a1149a35cf9590a2aa808e0bc1eafaade0b80947865fbc4"
+dependencies = [
+ "thiserror-impl",
+]
+
+[[package]]
+name = "thiserror-impl"
+version = "2.0.18"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "ebc4ee7f67670e9b64d05fa4253e753e016c6c95ff35b89b7941d6b856dec1d5"
+dependencies = [
+ "proc-macro2",
+ "quote",
+ "syn",
+]
+
 [[package]]
 name = "tinystr"
 version = "0.8.2"
@@ -1246,6 +1439,12 @@ version = "1.0.22"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "9312f7c4f6ff9069b165498234ce8be658059c6728633667c526e27dc2cf1df5"
 
+[[package]]
+name = "unicode-width"
+version = "0.2.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "b4ac048d71ede7ee76d585517add45da530660ef4390e49b098733c6e897f254"
+
 [[package]]
 name = "url"
 version = "2.5.8"
@@ -1258,6 +1457,12 @@ dependencies = [
  "serde",
 ]
 
+[[package]]
+name = "utf-8"
+version = "0.7.6"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "09cc8ee72d2a9becf2f2febe0205bbed8fc6615b7cb429ad062dc7b7ddd036a9"
+
 [[package]]
 name = "utf8_iter"
 version = "1.0.4"
@@ -1369,6 +1574,18 @@ dependencies = [
  "wasm-bindgen",
 ]
 
+[[package]]
+name = "web_atoms"
+version = "0.2.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "30e588f10c7bc3465f5fc1ab087fc97877ec1064a7ec89fb685ac4ee998dac4a"
+dependencies = [
+ "phf",
+ "phf_codegen",
+ "string_cache",
+ "string_cache_codegen",
+]
+
 [[package]]
 name = "windows-core"
 version = "0.62.2"

Cargo.toml

@@ -12,6 +12,8 @@ serde = { version = "1.0", features = ["derive"] }
 serde_json = "1.0"
 toml = "0.8"
 chrono = { version = "0.4", features = ["serde"] }
+html2text = "0.16.6"
+regex = "1.12.2"
 
 
 

src/main.rs

@@ -1,5 +1,6 @@
 use mailparse::MailHeaderMap;
 use native_tls::TlsConnector;
+use regex::Regex;
 use serde::Deserialize;
 use std::fs;
 use std::thread;
@@ -139,9 +140,21 @@ fn run_monitor(config: &Config) -> Result<(), Box<dyn std::error::Error>> {
     }
 }
 
+fn clean_body(body: &str) -> String {
+    // Replace multiple newlines with double newline (max)
+    let re_newlines = Regex::new(r"\n{3,}").unwrap();
+    let body = re_newlines.replace_all(body, "\n\n");
+    
+    // Trim trailing spaces from each line
+    let re_trailing_spaces = Regex::new(r"(?m)[ \t]+$").unwrap();
+    let body = re_trailing_spaces.replace_all(&body, "");
+
+    body.trim().to_string()
+}
+
 fn extract_body(parsed: &mailparse::ParsedMail) -> Option<String> {
     if parsed.ctype.mimetype == "text/plain" {
-        return parsed.get_body().ok();
+        return parsed.get_body().ok().map(|s| clean_body(&s));
     }
     
     // If multipart, search for text/plain
@@ -153,8 +166,11 @@ fn extract_body(parsed: &mailparse::ParsedMail) -> Option<String> {
 
     // Fallback to text/html if no plain text found (or first part if nothing else)
     if parsed.ctype.mimetype == "text/html" {
-         // Naive stripping of HTML tags could be done here, or just return as is.
+         if let Ok(html_content) = parsed.get_body() {
-         return parsed.get_body().ok(); 
+             if let Ok(md) = html2text::from_read(html_content.as_bytes(), 80) {
+                 return Some(clean_body(&md));
+             }
+         }
     }
 
     None