perf(runner): build the provider map once per file, not twice (#817)

Author: Chemaclass

CHANGELOG.md

@@ -15,6 +15,7 @@
 - `--jobs auto` / `-j auto` caps parallel concurrency at the CPU core count (portable across Linux/macOS/BSD); the default stays unlimited (#766)
 
 ### Changed
+- Faster test runs: the data-provider map is built once per file in the main shell (the header's test count reads a return slot instead of a `$(...)` capture, so the cache survives for the runner) — one awk scan per file instead of two
 - Faster test runs: stripping ANSI codes from short colored strings is pure bash now, so aligning the per-test execution time (shown on systems with a fork-free clock, e.g. Linux) no longer forks `sed` once per passing test
 - Faster parallel runs: publishing each test's result file no longer forks `basename`, `mkdir` and an `echo | tr | sed` pipeline per test — the suite dir name is parameter expansion, the dir is pre-created once per file before workers spawn, and arg sanitizing is skipped without provider args (a 10-test parallel run dropped from 61 to 21 forks). No behaviour change
 - Faster test runs: listing all defined functions uses the `compgen -A function` builtin instead of forking `declare -F | awk` (three call sites; 5 -> 3 `awk` forks per test file). No behaviour change

src/console_header.sh

@@ -39,7 +39,11 @@ function bashunit::console_header::print_version() {
     # Skip counting in parallel+simple mode for faster startup
     total_tests=0
   else
-    total_tests=$(bashunit::helper::find_total_tests "$filter" "$@")
+    # Read via the return slot, not $(...): the capture subshell would discard
+    # the provider-map cache find_total_tests builds per file, forcing the
+    # runner to re-scan each file with a second awk fork.
+    bashunit::helper::find_total_tests "$filter" "$@" >/dev/null
+    total_tests=$_BASHUNIT_HELPER_TOTAL_TESTS_OUT
   fi
 
   if bashunit::env::is_header_ascii_art_enabled; then

src/helpers.sh

@@ -526,10 +526,15 @@ function bashunit::helper::get_latest_tag() {
     head -n 1
 }
 
+# Also written by find_total_tests so a main-shell caller can read the count
+# without a $() capture (which would discard the provider-map cache built here).
+_BASHUNIT_HELPER_TOTAL_TESTS_OUT=0
+
 function bashunit::helper::find_total_tests() {
   local filter=${1:-}
   shift || true
 
+  _BASHUNIT_HELPER_TOTAL_TESTS_OUT=0
   if [ $# -eq 0 ]; then
     echo 0
     return
@@ -543,6 +548,12 @@ function bashunit::helper::find_total_tests() {
       continue
     fi
 
+    # Build the provider map in THIS shell before the counting subshell: the
+    # subshell inherits it (its own build call becomes a cache hit), and when
+    # the caller runs in the main shell the runner's later build for the same
+    # file is a cache hit too — one awk scan per file instead of two.
+    bashunit::helper::build_provider_map "$file"
+
     local file_count
     file_count=$( (
       # shellcheck source=/dev/null
@@ -590,6 +601,7 @@ function bashunit::helper::find_total_tests() {
     total_count=$((total_count + file_count))
   done
 
+  _BASHUNIT_HELPER_TOTAL_TESTS_OUT=$total_count
   echo "$total_count"
 }
 

tests/acceptance/bashunit_run_forks_test.sh

@@ -126,8 +126,9 @@ function test_running_a_test_file_does_not_fork_sort() {
 
 # Regression guard: listing all defined functions must use the `compgen -A
 # function` builtin, not a `declare -F | awk` fork. The remaining awk budget of
-# a plain run is the per-file file scans (data-provider map, which runs in both
-# the counting subshell and the runner, plus the duplicate-name check).
+# a single-file run is one data-provider scan (built once in the main shell so
+# the header-count subshell and the runner both hit the cache) plus the
+# duplicate-name check.
 function test_running_a_test_file_stays_within_the_awk_fork_budget() {
   if bashunit::check_os::is_windows; then
     bashunit::skip "PATH shims are unreliable under Git Bash" && return
@@ -155,7 +156,7 @@ function test_running_a_test_file_stays_within_the_awk_fork_budget() {
     awk_forks="$(grep -c . "$count_file" || true)"
   fi
 
-  assert_less_or_equal_than 3 "$awk_forks"
+  assert_less_or_equal_than 2 "$awk_forks"
 }
 
 # Regression guard: a run must remove its run-output scratch directory on exit.