From 62c083b5e3a164d596b49132c8c53248aa2daf42 Mon Sep 17 00:00:00 2001
From: Teddy Wing
Date: Sun, 14 Mar 2021 17:24:18 +0100
Subject: Strip HTML tags from single-part HTML emails

When an HTML body is fed to 'whatlang', it recognises it as English.
This is likely due to the English HTML syntax. Remove all HTML tags with
a simple regex substitution to get the language recognition working more
properly.

This doesn't remove CSS, which could also confuse the language
recogniser. In a limited test, it seemed to work without having to
remove any CSS, so not bothering with that.

Still need to get this working for multipart emails.
---
 src/main.rs | 11 ++++++++++-
 1 file changed, 10 insertions(+), 1 deletion(-)

(limited to 'src')

diff --git a/src/main.rs b/src/main.rs
index fbb6976..656403a 100644
--- a/src/main.rs
+++ b/src/main.rs
@@ -15,6 +15,7 @@
 
 use exitcode;
 use mailparse;
+use regex::Regex;
 use thiserror::Error;
 use whatlang::{self, Lang};
 use xdg;
@@ -109,6 +110,7 @@ fn run() -> Result<(), OttolangyError> {
     let lang_info = whatlang::detect(&body)
         .ok_or(OttolangyError::DetectLanguage)?;
 
+    println!("lang: {:?}", lang_info);
     let attribution_config = if lang_info.lang() == Lang::Fra {
         ATTRIBUTION_FR
     } else {
@@ -131,7 +133,14 @@ fn get_email_body(email: &[u8]) -> Result<String, WrapError> {
     println!("ctype: {:?}", email.ctype);
 
     if email.subparts.is_empty() {
-        let body = email.get_body()?;
+        let mut body = email.get_body()?;
+
+        if email.ctype.mimetype == "text/html" {
+            let re = Regex::new("<[^>]*>").unwrap();
+            body = re.replace_all(&body, "").into_owned();
+        }
+
+        println!("body: {:?}", body);
 
         return Ok(body);
     }
-- 
cgit v1.2.3