From 63fdc55828ec55bf7545c37bd56a4d537aa0cf71 Mon Sep 17 00:00:00 2001
From: Joel Natividad <1980690+jqnatividad@users.noreply.github.com>
Date: Fri, 10 May 2024 04:42:43 -0600
Subject: [PATCH] `stats`: added additional mode to `--cache-threshold`

Added addl logic to remove auto-created index if the `--cache-threshold` arg ends with a 5.
---
 src/cmd/stats.rs | 27 +++++++++++++++++++++++----
 1 file changed, 23 insertions(+), 4 deletions(-)

diff --git a/src/cmd/stats.rs b/src/cmd/stats.rs
index 0d825f854..c3211f13a 100644
--- a/src/cmd/stats.rs
+++ b/src/cmd/stats.rs
@@ -145,8 +145,10 @@ stats options:
                               Set to 0 to suppress caching. 
                               Set to 1 to force caching.
                               Set to a negative number to automatically create an index
-                              when the input file size is greater than abs(arg) in bytes
-                              AND to force caching.
+                              when the input file size is greater than abs(arg) in bytes.
+                              If the negative number ends with 5, it will delete the index
+                              file and the stats cache file after the stats run. Otherwise,
+                              the index file and the cache files are kept.
                               [default: 5000]
 
 Common options:
@@ -379,6 +381,7 @@ pub fn run(argv: &[&str]) -> CliResult<()> {
 
     let mut compute_stats = true;
     let mut create_cache = args.flag_cache_threshold > 0 || args.flag_stats_binout;
+    let mut autoindex_set = false;
 
     let write_stats_binout = args.flag_stats_binout;
 
@@ -484,8 +487,9 @@ pub fn run(argv: &[&str]) -> CliResult<()> {
 
             // check if flag_cache_threshold is a negative number,
             // if so, set the autoindex_size to absolute of the number
-            if args.flag_cache_threshold < 0 {
+            if args.flag_cache_threshold.is_negative() {
                 fconfig.autoindex_size = args.flag_cache_threshold.unsigned_abs() as u64;
+                autoindex_set = true;
             }
 
             // we need to count the number of records in the file to calculate sparsity
@@ -544,7 +548,8 @@ pub fn run(argv: &[&str]) -> CliResult<()> {
     }
 
     // ensure create_cache is also true if the user specified --cache-threshold 1
-    create_cache = create_cache || args.flag_cache_threshold == 1 || args.flag_cache_threshold < 0;
+    create_cache =
+        create_cache || args.flag_cache_threshold == 1 || args.flag_cache_threshold.is_negative();
 
     wtr.flush()?;
 
@@ -584,6 +589,20 @@ pub fn run(argv: &[&str]) -> CliResult<()> {
             fs::copy(currstats_filename.clone(), stats_pathbuf.clone())?;
         }
 
+        if args.flag_cache_threshold.is_negative() && args.flag_cache_threshold % 10 == -5 {
+            // if the cache threshold is a negative number ending in 5,
+            // delete both the index file and the stats cache file
+            if autoindex_set {
+                let index_file = path.with_extension("csv.idx");
+                log::debug!("deleting index file: {}", index_file.display());
+                if std::fs::remove_file(index_file.clone()).is_err() {
+                    // fails silently if it can't remove the index file
+                    log::warn!("Could not remove index file: {}", index_file.display());
+                }
+            }
+            create_cache = false;
+        }
+
         if !create_cache {
             // remove the stats cache file
             if fs::remove_file(stats_pathbuf.clone()).is_err() {