From 81195dc2e067079a4e776e68806061bf350ccfc0 Mon Sep 17 00:00:00 2001
From: seonghobae <8172694+seonghobae@users.noreply.github.com>
Date: Wed, 24 Jun 2026 19:28:29 +0000
Subject: [PATCH] I have optimized the common item name lookups by replacing
 the search command inside the loop.

---
 .jules/bolt.md |  3 +++
 R/aFIPC.R      | 48 ++++++++++++------------------------------------
 2 files changed, 15 insertions(+), 36 deletions(-)
 create mode 100644 .jules/bolt.md

diff --git a/.jules/bolt.md b/.jules/bolt.md
new file mode 100644
index 0000000..75a4a32
--- /dev/null
+++ b/.jules/bolt.md
@@ -0,0 +1,3 @@
+## 2025-02-23 - Avoid `grep` in inner loops for exact string matching on column names in R
+**Learning:** In the core `autoFIPC` logic, there were multiple inner loops that utilized `length(grep(paste0('^', name, '$'), colnames)) == 1` to perform exact string matching of items over columns. This regex-based lookup inside tight loops leads to severe performance degradation as the number of common items or columns increases. Furthermore, computing `levels(as.factor(vector))` inside a loop is substantially slower than utilizing `unique(vector)` for checking column categories.
+**Action:** When evaluating exact matching against arrays of strings in R, extract the string lists outside the loop and use vectorized equality operators (`sum(extractedNames == targetName) == 1`) or `%in%`. Always replace `levels(as.factor())` with `unique()` for counting categorical values to prevent unnecessary conversion and sort overhead.
diff --git a/R/aFIPC.R b/R/aFIPC.R
index b6a9e6c..4710dff 100644
--- a/R/aFIPC.R
+++ b/R/aFIPC.R
@@ -546,20 +546,13 @@ autoFIPC <-
       IPDItemNamesNewForm <- vector()
 
       # IPD target item checking
+      newFormColNames <- colnames(newformXDataK[colnames(newFormModel@Data$data)])
+      oldFormColNames <- colnames(oldformYDataK[colnames(oldFormModel@Data$data)])
+
       for (i in 1:length(oldformCommonItemNames)) {
         if (
-          (length(grep(
-            paste0('^', newformCommonItemNames[i], '$'),
-            colnames(newformXDataK[colnames(newFormModel@Data$data)])
-          )) ==
-            1) ==
-            TRUE &&
-            (length(grep(
-              paste0('^', oldformCommonItemNames[i], '$'),
-              colnames(oldformYDataK[colnames(oldFormModel@Data$data)])
-            )) ==
-              1) ==
-              TRUE
+          sum(newFormColNames == newformCommonItemNames[i]) == 1 &&
+          sum(oldFormColNames == oldformCommonItemNames[i]) == 1
         ) {
           IPDItemCount <- IPDItemCount + 1
           IPDItemNamesOldForm[IPDItemCount] <-
@@ -698,32 +691,15 @@ autoFIPC <-
       }
     }
 
+    newFormColNames <- colnames(newformXDataK[colnames(newFormModel@Data$data)])
+    oldFormColNames <- colnames(oldformYDataK[colnames(oldFormModel@Data$data)])
+
     for (i in 1:length(oldformCommonItemNames)) {
       if (
-        (length(grep(
-          paste0('^', newformCommonItemNames[i], '$'),
-          colnames(newformXDataK[colnames(newFormModel@Data$data)])
-        )) ==
-          1) ==
-          TRUE &&
-          (length(grep(
-            paste0('^', oldformCommonItemNames[i], '$'),
-            colnames(oldformYDataK[colnames(oldFormModel@Data$data)])
-          )) ==
-            1) ==
-            TRUE &&
-          (length(levels(as.factor(
-            newFormModel@Data$data[, grep(
-              paste0('^', newformCommonItemNames[i], '$'),
-              colnames(newformXDataK[colnames(newFormModel@Data$data)])
-            )]
-          ))) ==
-            length(levels(as.factor(
-              oldFormModel@Data$data[, grep(
-                paste0('^', oldformCommonItemNames[i], '$'),
-                colnames(oldformYDataK[colnames(oldFormModel@Data$data)])
-              )]
-            ))))
+        sum(newFormColNames == newformCommonItemNames[i]) == 1 &&
+        sum(oldFormColNames == oldformCommonItemNames[i]) == 1 &&
+        length(na.omit(unique(newFormModel@Data$data[, newFormColNames == newformCommonItemNames[i]]))) ==
+        length(na.omit(unique(oldFormModel@Data$data[, oldFormColNames == oldformCommonItemNames[i]])))
       ) {
         message(
           'applying ',