fix: keyword search - add text_content field and CJK support

- Added text_content field to SearchResult and SemanticSearchResult
- Added get_chunk_by_id_no_embedding for keyword results without embedding requirement
- Fixed search_bm25 to use position-based ranking for CJK/Korean content
- Fixed sqlx column mapping with explicit alias
- Skip text_match filter for keyword-only results
- Use text_content as fallback when summary is empty

src/api/search.rs

@@ -34,6 +34,7 @@ pub struct SearchResult {
     pub end_time: f64,
     pub raw_text: Option<String>,
     pub summary: Option<String>,
+    pub text_content: Option<String>,
     pub metadata: Option<serde_json::Value>,
     pub similarity: Option<f64>,
     pub file_name: Option<String>,
@@ -82,6 +83,7 @@ async fn enrich_from_pg(
             end_time: p.end_time,
             raw_text: None,
             summary: Some(p.summary),
+            text_content: p.text_content.clone(),
             metadata: p.metadata.clone(),
             similarity: Some(qdrant_score as f64),
             file_name: None,
@@ -109,6 +111,7 @@ fn pg_result_to_search(p: &SemanticSearchResult) -> SearchResult {
         end_time: p.end_time,
         raw_text: None,
         summary: Some(p.summary.clone()),
+        text_content: p.text_content.clone(),
         metadata: p.metadata.clone(),
         similarity: p.similarity,
         file_name: None,
@@ -381,43 +384,55 @@ pub async fn smart_search(
     let mut final_results = Vec::new();
     for mr in ranked.iter().take(limit * 3) {
         // 取更多結果以便過濾
-        if let Some(pg) = db
-            .get_chunk_by_file_and_chunk_id(&mr.file_uuid, &mr.chunk_id)
-            .await
-            .ok()
-            .flatten()
-        {
-            // 關鍵字過濾: CJK 用子字串匹配，英文用單詞邊界匹配
-            let summary_lower = pg.summary.to_lowercase();
-            let query_words: Vec<String> = query_lower
-                .split_whitespace()
-                .map(|s| s.to_string())
-                .collect();
+        // Use no_embedding version for keyword results, regular for semantic
+        let pg_opt = if mr.keyword_score.is_some() && mr.semantic_score.is_none() {
+            db.get_chunk_by_id_no_embedding(&mr.file_uuid, &mr.chunk_id).await
+        } else {
+            db.get_chunk_by_file_and_chunk_id(&mr.file_uuid, &mr.chunk_id).await
+        };
+        if let Some(pg) = pg_opt.ok().flatten() {
+            // 關鍵字結果跳過 text_match 過濾（search_bm25 已經匹配過）
+            let is_keyword_only = mr.keyword_score.is_some() && mr.semantic_score.is_none();
+            if !is_keyword_only {
+                // 關鍵字過濾: CJK 用子字串匹配，英文用單詞邊界匹配
+                let summary_lower = pg.summary.to_lowercase();
+                let query_words: Vec<String> = query_lower
+                    .split_whitespace()
+                    .map(|s| s.to_string())
+                    .collect();
 
-            let text_match = !pg.summary.is_empty() && {
-                let has_cjk = |s: &str| -> bool {
-                    s.chars().any(|c| {
-                        ('\u{4E00}'..='\u{9FFF}').contains(&c)
-                            || ('\u{3040}'..='\u{309F}').contains(&c)
-                            || ('\u{30A0}'..='\u{30FF}').contains(&c)
-                            || ('\u{AC00}'..='\u{D7AF}').contains(&c)
-                    })
+                let text_match = !pg.summary.is_empty() && {
+                    let has_cjk = |s: &str| -> bool {
+                        s.chars().any(|c| {
+                            ('\u{4E00}'..='\u{9FFF}').contains(&c)
+                                || ('\u{3040}'..='\u{309F}').contains(&c)
+                                || ('\u{30A0}'..='\u{30FF}').contains(&c)
+                                || ('\u{AC00}'..='\u{D7AF}').contains(&c)
+                        })
+                    };
+
+                    if has_cjk(&query_lower) || has_cjk(&summary_lower) {
+                        query_words.iter().all(|w| summary_lower.contains(w))
+                    } else {
+                        let bordered = format!(" {} ", summary_lower);
+                        query_words
+                            .iter()
+                            .all(|w| bordered.contains(&format!(" {} ", w)))
+                    }
                 };
 
-                if has_cjk(&query_lower) || has_cjk(&summary_lower) {
-                    query_words.iter().all(|w| summary_lower.contains(w))
-                } else {
-                    let bordered = format!(" {} ", summary_lower);
-                    query_words
-                        .iter()
-                        .all(|w| bordered.contains(&format!(" {} ", w)))
+                if !text_match {
+                    continue;
                 }
-            };
-
-            if !text_match && mr.semantic_score.is_none() {
-                continue;
             }
 
+            // 使用 text_content 如果 summary 為空
+            let display_text = if pg.summary.is_empty() {
+                pg.text_content.clone().unwrap_or_default()
+            } else {
+                pg.summary.clone()
+            };
+
             final_results.push(SearchResult {
                 id: 0,
                 file_uuid: pg.file_uuid.clone(),
@@ -430,6 +445,7 @@ pub async fn smart_search(
                 end_time: pg.end_time,
                 raw_text: None,
                 summary: Some(pg.summary),
+                text_content: pg.text_content.clone(),
                 metadata: pg.metadata.clone(),
                 similarity: Some(mr.score),
                 file_name: None,