implement const of ignored special chars for citekey formatting

* the list contains 33 special chars at the moment
* it will only affect already existing special chars in biblatex fields
* delimiter specified for citekey formatting are not affected
* char count is also not affected, ignored chars are not counted

3 files changed, 27 insertions, 20 deletions

diff --git a/src/bibiman/citekeys.rs b/src/bibiman/citekeys.rs
index 5121741..7c06886 100644
--- a/src/bibiman/citekeys.rs
+++ b/src/bibiman/citekeys.rs
@@ -31,7 +31,10 @@ use owo_colors::{
 };
 use serde::{Deserialize, Serialize};
 
-use crate::{bibiman::sanitize::sanitize_single_string_fully, config::BibiConfig};
+use crate::{
+    bibiman::sanitize::sanitize_single_string_fully,
+    config::{BibiConfig, IGNORED_SPECIAL_CHARS},
+};
 
 #[derive(Debug, Clone, PartialEq, Serialize, Deserialize)]
 pub enum CitekeyCase {
@@ -354,26 +357,25 @@ fn preformat_field(field: &str, entry: &Entry) -> String {
 
 /// Cut of word at char count index if its set
 fn format_word(word: &str, count: Option<usize>) -> String {
-    if let Some(len) = count
-        && len < word.chars().count()
-    {
-        // Since chars can consist of multiple bytes, we need this more complex
-        // loop to collect a specified number of chars (e.g. ÄÖÜäöü¢æø etc...)
-        // instead of simple byte indexing
-        let mut word_slice = String::new();
-        let word_chars = word.chars();
-        let mut counter = 0;
-        for c in word_chars {
-            if counter == len {
-                break;
-            }
-            word_slice.push(c);
-            counter += 1;
+    // Since chars can consist of multiple bytes, we need this more complex
+    // loop to collect a specified number of chars (e.g. ÄÖÜäöü¢æø etc...)
+    // instead of simple byte indexing
+    let mut word_slice = String::new();
+    let word_chars = word.chars();
+    let mut counter = 0;
+    for c in word_chars {
+        if let Some(len) = count
+            && counter == len
+        {
+            break;
         }
-        word_slice
-    } else {
-        word.to_string()
+        if IGNORED_SPECIAL_CHARS.contains(&c) {
+            continue;
+        }
+        word_slice.push(c);
+        counter += 1;
     }
+    word_slice
 }
 
 /// Split a formatting pattern of kind
diff --git a/src/config.rs b/src/config.rs
index a5df61c..a4e89be 100644
--- a/src/config.rs
+++ b/src/config.rs
@@ -35,6 +35,11 @@ use crate::{
     cliargs::CLIArgs,
 };
 
+pub const IGNORED_SPECIAL_CHARS: [char; 33] = [
+    '?', '!', '\\', '\'', '.', '-', '–', ':', ',', '[', ']', '(', ')', '{', '}', '§', '$', '%',
+    '&', '/', '`', '´', '#', '+', '*', '=', '|', '<', '>', '^', '°', '_', '"',
+];
+
 const DEFAULT_CONFIG: &str = r##"
 # [general]
 ## Default files/dirs which are loaded on startup
diff --git a/tests/test-config.toml b/tests/test-config.toml
index b484b69..558d216 100644
--- a/tests/test-config.toml
+++ b/tests/test-config.toml
@@ -61,5 +61,5 @@ custom_column = "series"
 # year_color = "135"
 
 [citekey_formatter]
-fields = [ "author;2;;-;_", "title;3;3;_;_", "year" ]
+fields = [ "author;2;;-;_", "title;3;6;_;_", "year" ]
 case = "lowercase"