feat: trim_whitespace option for grep (#356)

* feat: trim_whitespace optin for grep

closes #307

* chore: Update docs for - feat: trim_whitespace optin for grep

Author: dmtrKovalenko

README.md

@@ -289,6 +289,7 @@ require('fff').setup({
       smart_case = true, -- Case-insensitive unless query has uppercase
       time_budget_ms = 150, -- Max search time in ms per call (prevents UI freeze, 0 = no limit)
       modes = { 'plain', 'regex', 'fuzzy' }, -- Available grep modes and their cycling order
+      trim_whitespace = false, -- Strip leading whitespace from matched lines
     },
   })
 ```

crates/fff-c/src/lib.rs

@@ -390,6 +390,7 @@ pub unsafe extern "C" fn fff_live_grep(
         before_context: before_context as usize,
         after_context: after_context as usize,
         classify_definitions,
+        trim_whitespace: false,
     };
 
     let result = picker.grep(&parsed, &options);
@@ -491,6 +492,7 @@ pub unsafe extern "C" fn fff_multi_grep(
         before_context: before_context as usize,
         after_context: after_context as usize,
         classify_definitions,
+        trim_whitespace: false,
     };
 
     let result = fff::multi_grep_search(

crates/fff-core/src/grep.rs

@@ -279,6 +279,35 @@ pub struct GrepMatch {
     pub context_after: Vec<String>,
 }
 
+impl GrepMatch {
+    /// Strip leading whitespace from `line_content` and all context lines,
+    /// adjusting `col` and `match_byte_offsets` so highlights remain correct.
+    pub fn trim_leading_whitespace(&mut self) {
+        let strip_len = self.line_content.len() - self.line_content.trim_start().len();
+        if strip_len > 0 {
+            self.line_content.drain(..strip_len);
+            let off = strip_len as u32;
+            self.col = self.col.saturating_sub(strip_len);
+            for range in &mut self.match_byte_offsets {
+                range.0 = range.0.saturating_sub(off);
+                range.1 = range.1.saturating_sub(off);
+            }
+        }
+        for line in &mut self.context_before {
+            let n = line.len() - line.trim_start().len();
+            if n > 0 {
+                line.drain(..n);
+            }
+        }
+        for line in &mut self.context_after {
+            let n = line.len() - line.trim_start().len();
+            if n > 0 {
+                line.drain(..n);
+            }
+        }
+    }
+}
+
 /// Result of a grep search.
 #[derive(Debug, Clone, Default)]
 pub struct GrepResult<'a> {
@@ -326,6 +355,28 @@ pub struct GrepSearchOptions {
     /// Whether to classify each match as a definition line. Adds ~2% overhead
     /// on large repos; disable for interactive grep where it is not needed.
     pub classify_definitions: bool,
+    /// Strip leading whitespace from matched lines and context lines, adjusting
+    /// highlight byte offsets accordingly. Useful for AI/MCP consumers and UIs
+    /// that don't need indentation. Default: false.
+    pub trim_whitespace: bool,
+}
+
+impl Default for GrepSearchOptions {
+    fn default() -> Self {
+        Self {
+            max_file_size: 10 * 1024 * 1024,
+            max_matches_per_file: 200,
+            smart_case: true,
+            file_offset: 0,
+            page_limit: 50,
+            mode: GrepMode::default(),
+            time_budget_ms: 0,
+            before_context: 0,
+            after_context: 0,
+            classify_definitions: false,
+            trim_whitespace: false,
+        }
+    }
 }
 
 #[derive(Clone, Copy)]
@@ -1157,6 +1208,9 @@ where
 
             for mut m in file_matches {
                 m.file_index = file_result_idx;
+                if options.trim_whitespace {
+                    m.trim_leading_whitespace();
+                }
                 all_matches.push(m);
             }
 
@@ -1237,6 +1291,9 @@ fn collect_grep_results<'a>(
 
         for mut m in file_matches {
             m.file_index = file_result_idx;
+            if options.trim_whitespace {
+                m.trim_leading_whitespace();
+            }
             all_matches.push(m);
         }
 
@@ -2158,6 +2215,7 @@ mod tests {
             before_context: 0,
             after_context: 0,
             classify_definitions: false,
+            trim_whitespace: false,
         };
 
         // Test with 3 patterns

crates/fff-core/tests/bigram_overlay_coherence_test.rs

@@ -1373,6 +1373,7 @@ fn grep_opts() -> GrepSearchOptions {
         before_context: 0,
         after_context: 0,
         classify_definitions: false,
+        trim_whitespace: false,
     }
 }
 

crates/fff-core/tests/bigram_overlay_integration.rs

@@ -302,6 +302,7 @@ fn grep_opts() -> GrepSearchOptions {
         before_context: 0,
         after_context: 0,
         classify_definitions: false,
+        trim_whitespace: false,
     }
 }
 

crates/fff-core/tests/grep_integration.rs

@@ -29,6 +29,7 @@ fn plain_opts() -> GrepSearchOptions {
         before_context: 0,
         after_context: 0,
         classify_definitions: false,
+        trim_whitespace: false,
     }
 }
 
@@ -45,6 +46,7 @@ fn regex_opts() -> GrepSearchOptions {
         before_context: 0,
         after_context: 0,
         classify_definitions: false,
+        trim_whitespace: false,
     }
 }
 
@@ -61,6 +63,7 @@ fn fuzzy_opts() -> GrepSearchOptions {
         before_context: 0,
         after_context: 0,
         classify_definitions: false,
+        trim_whitespace: false,
     }
 }
 

crates/fff-mcp/src/output.rs

@@ -81,34 +81,19 @@ fn trauncate_line_for_ai(
     match_ranges: Option<&[(u32, u32)]>,
     max_len: usize,
 ) -> String {
-    // Strip leading/trailing whitespace to save tokens — the LLM has file:line for location.
-    let trimmed = line.trim();
+    // Leading whitespace is already stripped by core (trim_whitespace option).
+    // Only strip trailing whitespace here.
+    let trimmed = line.trim_end();
     if trimmed.is_empty() {
         return String::new();
     }
 
-    let strip_offset = line.len() - line.trim_start().len();
-
     if trimmed.len() <= max_len {
         return trimmed.to_string();
     }
 
-    // Adjust match ranges for the stripped leading whitespace
-    let adjusted: Vec<(u32, u32)>;
-    let ranges = match match_ranges {
-        Some(r) if strip_offset > 0 => {
-            let off = strip_offset as u32;
-            adjusted = r
-                .iter()
-                .map(|&(s, e)| (s.saturating_sub(off), e.saturating_sub(off)))
-                .collect();
-            Some(adjusted.as_slice())
-        }
-        other => other,
-    };
-
     // Use first match range to center the window
-    if let Some(ranges) = ranges
+    if let Some(ranges) = match_ranges
         && let Some(&(match_start, match_end)) = ranges.first()
     {
         let match_start = match_start as usize;
@@ -569,26 +554,29 @@ mod tests {
     use super::*;
 
     #[test]
-    fn trunc_strips_whitespace() {
-        assert_eq!(trauncate_line_for_ai("    foo()", None, 180), "foo()");
-        assert_eq!(trauncate_line_for_ai("  bar  ", None, 180), "bar");
+    fn trunc_strips_trailing_whitespace() {
+        // Leading whitespace is now stripped by core's trim_whitespace option.
+        // This function only strips trailing whitespace.
+        assert_eq!(trauncate_line_for_ai("foo()", None, 180), "foo()");
+        assert_eq!(trauncate_line_for_ai("bar  ", None, 180), "bar");
         assert_eq!(trauncate_line_for_ai("   ", None, 180), "");
     }
 
     #[test]
-    fn trunc_adjusts_match_ranges_after_strip() {
-        // "    hello" — match on "hello" at bytes 4..9
-        let line = "    hello";
-        let ranges = [(4, 9)];
+    fn trunc_preserves_pre_trimmed_match_ranges() {
+        // Core already stripped leading whitespace and adjusted offsets,
+        // so "hello" arrives with match at bytes 0..5.
+        let line = "hello";
+        let ranges = [(0, 5)];
         let result = trauncate_line_for_ai(line, Some(&ranges), 180);
-        // After stripping 4 leading spaces, the trimmed line is "hello"
         assert_eq!(result, "hello");
     }
 
     #[test]
     fn trunc_long_line_centered() {
-        let line = format!("{}match_here{}", " ".repeat(8), "x".repeat(200));
-        let ranges = [(8u32, 18u32)];
+        // Core already stripped leading whitespace; offsets are pre-adjusted.
+        let line = format!("match_here{}", "x".repeat(200));
+        let ranges = [(0u32, 10u32)];
         let result = trauncate_line_for_ai(&line, Some(&ranges), 50);
         assert!(result.contains("match_here"));
         assert!(result.len() <= 55); // budget + ellipsis chars

crates/fff-mcp/src/server.rs

@@ -64,6 +64,7 @@ fn make_grep_options(
             before_context: ctx_lines,
             after_context: after_ctx,
             classify_definitions: true,
+            trim_whitespace: true,
         },
         auto_expand,
     )

crates/fff-nvim/benches/indexing_and_search.rs

@@ -707,6 +707,7 @@ fn bench_grep_search(c: &mut Criterion) {
         before_context: 0,
         after_context: 0,
         classify_definitions: false,
+        trim_whitespace: false,
     };
 
     let test_queries = vec![

crates/fff-nvim/src/bin/bench_grep_query.rs

@@ -30,6 +30,7 @@ fn run_grep(files: &[fff::FileItem], index: Option<&fff::BigramFilter>, query: &
         before_context: 0,
         after_context: 0,
         classify_definitions: false,
+        trim_whitespace: false,
     };
 
     let parsed = parse_grep_query(query);