Merge pull request #165 from pixlie/feature/email-list-ux-158

Email list ux improvements

package.json

@@ -1,6 +1,6 @@
 {
   "name": "dwata",
-  "version": "0.1.6",
+  "version": "0.2.0",
   "description": "AI assistants for everyone",
   "type": "module",
   "author": {

src-tauri/Cargo.toml

@@ -3,7 +3,7 @@ members = ["openai"]
 
 [package]
 name = "dwata"
-version = "0.1.6"
+version = "0.2.0"
 description = "AI assisted app for our private data"
 authors = ["Sumit Datta <[email protected]>"]
 license = "Apache-2.0 license"
@@ -56,6 +56,7 @@ slug = "0.1.5"
 openai = { version = "2.0.0", path = "openai" }
 tantivy = "0.22.0"
 tauri-plugin-shell = "2.0.0-rc.2"
+regex = "1.10.6"
 
 [features]
 # this feature is used for production builds or when `devPath` points to the filesystem

src-tauri/src/email/crud.rs

@@ -1,6 +1,8 @@
-use super::{EmailCreateUpdate, EmailFilters};
+use super::{Email, EmailCreateUpdate, EmailFilters};
 use crate::error::DwataError;
-use crate::workspace::crud::{CRUDCreateUpdate, CRUDReadFilter, InputValue, VecColumnNameValue};
+use crate::workspace::crud::{
+    CRUDCreateUpdate, CRUDRead, CRUDReadFilter, InputValue, VecColumnNameValue,
+};
 
 impl CRUDReadFilter for EmailFilters {
     fn get_column_names_values_to_filter(&self) -> VecColumnNameValue {
@@ -29,3 +31,9 @@ impl CRUDCreateUpdate for EmailCreateUpdate {
         Ok(names_values)
     }
 }
+
+impl CRUDRead for Email {
+    fn table_name() -> String {
+        "email".to_string()
+    }
+}

src-tauri/src/email/helpers.rs

@@ -5,6 +5,7 @@ use crate::workspace::crud::{CRUDRead, CRUDReadFilter, InputValue, VecColumnName
 use chrono::{DateTime, Utc};
 use log::{error, info};
 use mail_parser::MessageParser;
+use regex::Regex;
 use sqlx::{Execute, Pool, QueryBuilder, Sqlite};
 use std::{fs::create_dir_all, path::PathBuf};
 use tantivy::{
@@ -254,6 +255,41 @@ pub async fn search_emails_in_tantivy(
     Ok(emails)
 }
 
+pub fn clean_email_body_text(body_text: &String) -> String {
+    let mut body_text = body_text.clone().chars().take(400).collect::<String>();
+    // We remove consecutive new lines from the body text
+    match Regex::new(r"\n{2,}") {
+        Ok(re) => {
+            body_text = re.replace(&body_text, "\n").to_string();
+        }
+        Err(_) => {}
+    };
+    // We remove consecutive spaces from the body text
+    match Regex::new(r" {2,}") {
+        Ok(re) => {
+            body_text = re.replace(&body_text, " ").to_string();
+        }
+        Err(_) => {}
+    };
+    // We remove consecutive tabs from the body text
+    // body_text = body_text.map(|x| x.replace("\t", " "));
+    // We remove consecutive underscores (2 or more) from the body text
+    match Regex::new("_{2,}") {
+        Ok(re) => {
+            body_text = re.replace(&body_text, "").to_string();
+        }
+        Err(_) => {}
+    };
+    // We remove consecutive dashes (2 or more) from the body text
+    match Regex::new(r"\-{2,}") {
+        Ok(re) => {
+            body_text = re.replace(&body_text, "").to_string();
+        }
+        Err(_) => {}
+    };
+    body_text
+}
+
 pub async fn search_emails_in_tantity_and_dwata_db(
     filters: EmailFilters,
     limit: usize,
@@ -316,16 +352,7 @@ pub async fn search_emails_in_tantity_and_dwata_db(
             // We select first 200 characters of the body text for each email
             result.iter_mut().for_each(|x: &mut Email| {
                 if let Some(body) = &x.body_text {
-                    let mut body_text = Some(body.clone().chars().take(400).collect::<String>());
-                    // We remove consecutive new lines from the body text
-                    body_text = body_text.map(|x| x.replace("\n\n", "\n"));
-                    // We remove consecutive spaces from the body text
-                    body_text = body_text.map(|x| x.replace("  ", " "));
-                    // We remove consecutive tabs from the body text
-                    body_text = body_text.map(|x| x.replace("\t", " "));
-                    // We remove consecutive dashes (2 or more) from the body text using a regex
-                    body_text = body_text.map(|x| x.replace(r"-{2,}", "-"));
-                    x.body_text = body_text;
+                    x.body_text = Some(clean_email_body_text(body));
                 }
             });
             let count = match count_builder

src-tauri/src/email/mod.rs

@@ -6,6 +6,7 @@ use ts_rs::TS;
 pub mod commands;
 pub mod crud;
 pub mod helpers;
+pub mod tests;
 
 #[derive(Deserialize, Serialize, TS, Type, EnumString, Display)]
 #[sqlx(rename_all = "lowercase")]

src-tauri/src/email/tests.rs

@@ -0,0 +1,35 @@
+use super::helpers::clean_email_body_text;
+
+#[cfg(test)]
+mod tests {
+    use crate::email::helpers::clean_email_body_text;
+
+    // use super::*;
+    #[test]
+    fn check_consecutive_end_of_lines_removed() {
+        let body_text = "\n\n\n\n\n\n\n".to_string();
+        let cleaned = clean_email_body_text(&body_text);
+        assert_eq!(cleaned, "\n");
+    }
+
+    #[test]
+    fn check_consecutive_spaces_removed() {
+        let body_text = "             ".to_string();
+        let cleaned = clean_email_body_text(&body_text);
+        assert_eq!(cleaned, " ");
+    }
+
+    #[test]
+    fn check_consecutive_underscores_removed() {
+        let body_text = "_______________________________________".to_string();
+        let cleaned = clean_email_body_text(&body_text);
+        assert_eq!(cleaned, "");
+    }
+
+    #[test]
+    fn check_consecutive_dashes_removed() {
+        let body_text = "---------------------------------".to_string();
+        let cleaned = clean_email_body_text(&body_text);
+        assert_eq!(cleaned, "");
+    }
+}