blocked word lists

cruciverb-core/src/dict/blocklist.rs

@@ -0,0 +1,82 @@
+use std::collections::HashSet;
+use std::path::Path;
+
+use crate::error::Result;
+
+// embedded at compile time - cannot be removed without recompiling
+const BUILTIN_LIST: &str = include_str!("../../../data/banned_words.txt");
+
+pub struct Blocklist {
+    words: HashSet<String>,
+}
+
+fn normalize_leet(s: &str) -> String {
+    s.chars().map(|c| match c {
+        '0' | 'O' => 'O',
+        '1' | 'l' | '!' | '|' => 'I',
+        '3' => 'E',
+        '4' | '@' => 'A',
+        '5' | '$' => 'S',
+        '7' => 'T',
+        '8' => 'B',
+        '9' => 'G',
+        _ => c.to_ascii_uppercase(),
+    }).collect()
+}
+
+fn parse_lines(content: &str) -> impl Iterator<Item = String> + '_ {
+    content.lines()
+        .map(|l| l.trim().to_uppercase())
+        .filter(|l| !l.is_empty() && !l.starts_with('#'))
+}
+
+impl Blocklist {
+    pub fn empty() -> Self {
+        // "empty" still includes the built-in list
+        let words = parse_lines(BUILTIN_LIST).collect();
+        Self { words }
+    }
+
+    pub fn load(path: &Path) -> Result<Self> {
+        // start with built-in, then add from file (additive only)
+        let mut words: HashSet<String> = parse_lines(BUILTIN_LIST).collect();
+        if let Ok(content) = std::fs::read_to_string(path) {
+            for w in parse_lines(&content) {
+                words.insert(w);
+            }
+        }
+        Ok(Self { words })
+    }
+
+    pub fn is_blocked(&self, word: &str) -> bool {
+        self.words.contains(word)
+    }
+
+    pub fn add_word(&mut self, word: &str) {
+        let w = word.trim().to_uppercase();
+        if !w.is_empty() {
+            self.words.insert(w);
+        }
+    }
+
+    pub fn extra_count(&self) -> usize {
+        let builtin: HashSet<String> = parse_lines(BUILTIN_LIST).collect();
+        self.words.len().saturating_sub(builtin.len())
+    }
+
+    pub fn contains_blocked(&self, text: &str) -> bool {
+        let upper = text.to_uppercase();
+        let normalized = normalize_leet(text);
+        let stripped: String = upper.chars().filter(|c| c.is_alphabetic()).collect();
+        let stripped_leet: String = normalized.chars().filter(|c| c.is_alphabetic()).collect();
+
+        for word in &self.words {
+            if word.len() < 3 { continue; }
+            if upper.contains(word.as_str()) { return true; }
+            if normalized.contains(word.as_str()) { return true; }
+            if stripped.contains(word.as_str()) { return true; }
+            if stripped_leet.contains(word.as_str()) { return true; }
+        }
+        false
+    }
+}