TypedDevs · Chemaclass · Sep 9, 2026 · Sep 9, 2026
diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -3,11 +3,13 @@
 ## Unreleased
 
 ### Changed
+- Performance: startup is faster on suites of plain test files. Printing "Running N tests" sourced every file a second time and re-ran every data provider before the run began. A file whose functions the provider scan can already see is counted from that scan instead: over this repo's 241 files the counting pass went from 1.72s to 1.51s, and 124 of them no longer source or run a provider twice. Files with a data provider, a heredoc, a multi-line string, an `eval`, a nested `source` or a conditional definition keep the old path, so the count can never disagree with the run (#1347)
 - Performance: a sequential run is about 0.7ms faster per test — a 500-test file went from 2.75s to 2.40s on macOS arm64, bash 3.2. Every test forked a subshell to read its own definition line, for a `<file>:<line>` that only a failure message and a report row ever use. It is resolved on demand now (#1346)
 - A standalone `bashunit assert <fn> …` no longer reports a source location belonging to another process. Launched from inside a test, it inherited that test's exported location and printed it as its own (#1346)
 - Performance: a test in a file that defines `set_up` or `tear_down` is about 2.6x faster, which brings it level with a hookless test (14.1ms to 5.4ms per test on macOS arm64, bash 3.2). Each hook minted its output file with `mktemp` and removed it with `rm`, and the ownership marker that left behind made the runner `rm -rf` the test's temp files at exit — five forks per test, even for a test that created no temp file of its own (#1345)
 
 ### Fixed
+- A test function whose name another selected name starts with is no longer rejected as a duplicate. `test_a` alongside `test_ab` read as one name twice, which made the whole file select nothing. Only definition order reached it, so nothing hit it before (#1347)
 - Coverage counts every line of a multiline statement: array literals, quoted strings, heredocs, backslash continuations. An array written one element per line cost one uncovered line per element. Bash 3.x records the assignment on its closing `)`, so there the whole array read as uncovered. A parent statement's hits no longer mark commands inside command or process substitutions as covered, even within quotes or arrays (#1338)
 - `--exclude-filter` keeps a comma as part of the test function name. The value was split at the comma, so `--exclude-filter 'test_a,{b}'` also excluded `test_a`. Repeat the flag to exclude several names. `BASHUNIT_EXCLUDE_FILTER` stays comma-separated, so one of its filters cannot hold a literal comma (#1340)
 - A `--parallel` run no longer replays bash's `child setpgid` warning as the stderr of a file that wrote nothing. Job control puts each test in its own process group. The parent-side `setpgid` then loses a harmless race with a child that already exec'd. The child sets the group first, so only the message was ever wrong (#1344)

diff --git a/src/helper/discovery.sh b/src/helper/discovery.sh
@@ -147,7 +147,11 @@ function bashunit::helper::get_functions_to_run() {
     fi
     if [ "$_fn_match" = true ]; then
       local _dup=false
-      case "$filtered_functions" in *" $fn"*) _dup=true ;; esac
+      # Both delimiters, or a name is "already present" whenever an earlier one
+      # merely starts with it: `test_a` reads as a duplicate of `test_ab`. That
+      # stayed hidden while the only caller fed this `compgen` output, which is
+      # sorted, so a prefix always arrived first (#1347).
+      case "$filtered_functions " in *" $fn "*) _dup=true ;; esac
       if [ "$_dup" = true ]; then
         return 1
       fi
@@ -206,6 +210,62 @@ function bashunit::helper::find_files_recursive() {
 _BASHUNIT_HELPER_VARNAME_OUT=""
 
 
+
+_BASHUNIT_HELPER_FILE_COUNT_OUT=0
+
+##
+# True when the provider map just built for a file is enough to count its
+# tests without sourcing it.
+#
+# Sourcing every file a second time, only to run `compgen -A function` in a
+# subshell, cost 671ms over this repo's 240 files before a single test ran, and
+# re-ran every data provider on the way (#1347). Two shapes still need it: a
+# provider's row count is only knowable by running it, and a file that could
+# define a test out of the scan's sight (eval, a nested source, a conditional
+# definition) would otherwise be undercounted -- a header that disagrees with
+# the run is worse than a slow one.
+##
+function bashunit::helper::_can_count_statically() {
+  if [ "$_BASHUNIT_PROVIDER_MAP_DYNAMIC" = true ]; then
+    return 1
+  fi
+
+  if [ "${#_BASHUNIT_PROVIDER_MAP_FNS[@]}" -ne 0 ]; then
+    return 1
+  fi
+
+  return 0
+}
+
+##
+# Counts the current provider map's test functions into
+# _BASHUNIT_HELPER_FILE_COUNT_OUT, applying the same selection the runner does.
+#
+# Every function without a provider is one test, which is what the sourcing
+# path counts too; only the names come from the scan rather than from
+# `compgen`. `get_functions_to_run` returns 1 on a duplicate name, exactly as
+# it does for the sourcing path, where `|| true` swallows it.
+#
+# Arguments: $1 - the --filter value
+##
+function bashunit::helper::_count_tests_statically() {
+  local filter=$1
+  # Set before the call, not after: get_functions_to_run word-splits its third
+  # argument with whatever IFS is current.
+  local IFS=$' \t\n'
+  local filtered_functions
+  filtered_functions=$(bashunit::helper::get_functions_to_run \
+    "test" "$filter" "$_BASHUNIT_PROVIDER_MAP_TEST_FNS") || true
+
+  local count=0
+  local fn
+  for fn in $filtered_functions; do
+    count=$((count + 1))
+  done
+
+  _BASHUNIT_HELPER_FILE_COUNT_OUT=$count
+}
+
 function bashunit::helper::find_total_tests() {
   local filter=${1:-}
   shift || true
@@ -230,8 +290,35 @@ function bashunit::helper::find_total_tests() {
     # 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=$( (
+    if bashunit::helper::_can_count_statically; then
+      bashunit::helper::_count_tests_statically "$filter"
+    else
+      bashunit::helper::_count_tests_by_sourcing "$file" "$filter"
+    fi
+    total_count=$((total_count + _BASHUNIT_HELPER_FILE_COUNT_OUT))
+  done
+
+  _BASHUNIT_HELPER_TOTAL_TESTS_OUT=$total_count
+  echo "$total_count"
+}
+
+##
+# Counts a file's tests into _BASHUNIT_HELPER_FILE_COUNT_OUT by sourcing it in
+# a subshell and asking `compgen`, then running each data provider to learn how
+# many rows it yields.
+#
+# The only way to count a provider, and the only way to see a function this
+# file defines through eval, a nested source or a condition. Everything else
+# takes the static path, because this one costs a double subshell, a re-source
+# and a second run of every provider in the suite (#1347).
+#
+# Arguments: $1 - the test file, $2 - the --filter value
+##
+function bashunit::helper::_count_tests_by_sourcing() {
+  local file=$1
+  local filter=$2
+
+  _BASHUNIT_HELPER_FILE_COUNT_OUT=$( (
       # shellcheck source=/dev/null
       source "$file"
       local all_fn_names
@@ -271,12 +358,6 @@ function bashunit::helper::find_total_tests() {
 
       echo "$count"
     ))
-
-    total_count=$((total_count + file_count))
-  done
-
-  _BASHUNIT_HELPER_TOTAL_TESTS_OUT=$total_count
-  echo "$total_count"
 }
 
 

diff --git a/src/helper/naming.sh b/src/helper/naming.sh
@@ -206,4 +206,10 @@ _BASHUNIT_PROVIDER_FN_OUT=""
 # Set true when the scanned file carries the "# bashunit: no-parallel-tests"
 # opt-out; detected in the same awk pass to avoid a per-file grep fork (#774).
 _BASHUNIT_PROVIDER_MAP_NO_PARALLEL=false
+# Every function the scanned file defines at column 0, space-separated, and
+# whether the file could also define one out of the scan's sight. The header
+# counts a file's tests from these instead of sourcing it a second time and
+# re-running its providers (#1347).
+_BASHUNIT_PROVIDER_MAP_TEST_FNS=""
+_BASHUNIT_PROVIDER_MAP_DYNAMIC=false
 
diff --git a/src/helper/provider.sh b/src/helper/provider.sh
@@ -49,6 +49,8 @@ function bashunit::helper::build_provider_map() {
   _BASHUNIT_PROVIDER_MAP_FNS=()
   _BASHUNIT_PROVIDER_MAP_PROVIDERS=()
   _BASHUNIT_PROVIDER_MAP_NO_PARALLEL=false
+  _BASHUNIT_PROVIDER_MAP_TEST_FNS=""
+  _BASHUNIT_PROVIDER_MAP_DYNAMIC=false
 
   bashunit::helper::annotations_reset
 
@@ -80,6 +82,14 @@ function bashunit::helper::build_provider_map() {
       [ "$provider" = "1" ] && _BASHUNIT_PROVIDER_MAP_NO_PARALLEL=true
       continue
     fi
+    if [ "$fn" = "@@testfns@@" ]; then
+      _BASHUNIT_PROVIDER_MAP_TEST_FNS="$provider"
+      continue
+    fi
+    if [ "$fn" = "@@dynamic@@" ]; then
+      _BASHUNIT_PROVIDER_MAP_DYNAMIC=true
+      continue
+    fi
     if [ "$fn" = "@@annot@@" ]; then
       [ "$annot_timeout" = "@@none@@" ] && annot_timeout=""
       [ "$annot_retry" = "@@none@@" ] && annot_retry=""
@@ -132,6 +142,49 @@ function bashunit::helper::build_provider_map() {
         sub(/[[:space:]]*\(\).*/, "", fn)
       }
 
+      # A definition at column 0 is one this scan can be sure the file defines
+      # unconditionally, which is what lets the header count without sourcing.
+      # Anything that could define a function this scan cannot see -- eval,
+      # a nested source, an indented (so conditional or nested) definition --
+      # marks the file dynamic and sends the count back to sourcing.
+      if (match($0, /^(function[[:space:]]+)?[A-Za-z_][A-Za-z0-9_:]*[[:space:]]*\(\)/)) {
+        # Accumulated, not emitted per definition: the read loop below runs
+        # once per row, and a row per function cost about as much as counting
+        # statically saved.
+        top_level_fns = top_level_fns " " fn
+      } else if (is_fn) {
+        dynamic = 1
+      }
+      # A heredoc marks the file dynamic too, for the opposite reason: an
+      # acceptance test writes its fixtures with one, and a `function test_x()`
+      # in that body is text, not a definition -- counted statically it would
+      # inflate the header. So does a line whose quotes do not balance, which
+      # is how the rest of them write a fixture: a multi-line string whose
+      # continuation lines start at column 0 and look exactly like definitions.
+      # Escapes and balanced spans come out first, so an apostrophe inside a
+      # double-quoted string is not mistaken for one -- that alone was flagging
+      # a fifth of the suite.
+      #
+      # Both are flagged rather than parsed. This pass also builds the provider
+      # map, so a line-skipping bug here would mis-wire real tests; and a rule
+      # that guesses wrong about where a string ends can hide a real function,
+      # which is the one error a count must never make. Over-flagging only
+      # costs the file its fast path.
+      if (index($0, "<<") > 0) {
+        dynamic = 1
+      }
+      _t = $0
+      gsub(/\\./, "", _t)
+      gsub(/"[^"]*"/, "", _t)
+      gsub(/\047[^\047]*\047/, "", _t)
+      if (index(_t, "\047") > 0 || index(_t, "\"") > 0) {
+        dynamic = 1
+      }
+      if (match($0, /(^|[^[:alnum:]_])eval([^[:alnum:]_]|$)/) ||
+          match($0, /^[[:space:]]*(\.|source)[[:space:]]/)) {
+        dynamic = 1
+      }
+
       if (pending != "" && NR - pending_line <= 2) {
         if (is_fn) {
           printf "%s\t%s\n", fn, pending
@@ -158,7 +211,11 @@ function bashunit::helper::build_provider_map() {
       a_skip = ""
       a_reason = ""
     }
-    END { printf "@@no_parallel@@\t%d\n", no_parallel }
+    END {
+      printf "@@no_parallel@@\t%d\n", no_parallel
+      if (dynamic) { printf "@@dynamic@@\t1\n" }
+      else { printf "@@testfns@@\t%s\n", top_level_fns }
+    }
   ' "$script" 2>/dev/null)"
 }
 

diff --git a/tests/unit/helper/helper_test.sh b/tests/unit/helper/helper_test.sh
@@ -502,6 +502,90 @@ function test_find_total_tests_with_filter() {
   assert_same "3" "$(helpers_test::find_total_in_subshell "with_provider" "$file1" "$file2")"
 }
 
+# Counting used to source every file a second time, just to run `compgen -A
+# function` in a subshell -- 671ms over this repo's 240 files, before a single
+# test ran, and it re-ran every data provider on the way (#1347). A file whose
+# functions the provider scan can already see is counted from that scan.
+# The duplicate guard used to be a substring match, so a name that another
+# already-selected name starts with read as a duplicate and the whole file
+# selected nothing. Only definition order exposes it: `compgen` is sorted, so a
+# prefix always came first there (#1347).
+function test_get_functions_to_run_does_not_call_a_prefix_a_duplicate() {
+  local actual
+  actual="$(bashunit::helper::get_functions_to_run "test" "" \
+    "test_alpha_extended test_alpha")"
+
+  assert_same "test_alpha_extended test_alpha" "$actual"
+}
+
+function test_get_functions_to_run_still_rejects_a_real_duplicate() {
+  local status=0
+  bashunit::helper::get_functions_to_run "test" "" \
+    "test_alpha test_alpha" >/dev/null || status=$?
+
+  assert_same "1" "$status"
+}
+
+function test_find_total_tests_does_not_source_a_static_file() {
+  local dir
+  dir="$(bashunit::temp_dir)"
+  local marker="$dir/was_sourced"
+  local fixture="$dir/static_count_fixture.sh"
+  {
+    echo "echo x >>\"$marker\""
+    echo 'function test_a() { :; }'
+    echo 'function test_b() { :; }'
+  } >"$fixture"
+
+  local total
+  total="$(helpers_test::find_total_in_subshell "" "$fixture")"
+
+  assert_same "2" "$total"
+  assert_file_not_exists "$marker"
+}
+
+# A provider's row count is only knowable by running it, so those files keep
+# the sourcing path.
+function test_find_total_tests_sources_a_file_with_a_provider() {
+  local dir
+  dir="$(bashunit::temp_dir)"
+  local marker="$dir/was_sourced"
+  local fixture="$dir/provider_count_fixture.sh"
+  {
+    echo "echo x >>\"$marker\""
+    echo 'function provider_rows() { echo 1; echo 2; echo 3; }'
+    echo '# @data_provider provider_rows'
+    echo 'function test_rows() { :; }'
+  } >"$fixture"
+
+  local total
+  total="$(helpers_test::find_total_in_subshell "" "$fixture")"
+
+  assert_same "3" "$total"
+  assert_file_exists "$marker"
+}
+
+# A static scan cannot see a function `eval`, a nested `source` or a
+# conditional definition creates, and a header that disagrees with the run is
+# worse than a slow one. Those files fall back to sourcing.
+function test_find_total_tests_sources_a_file_that_defines_functions_dynamically() {
+  local dir
+  dir="$(bashunit::temp_dir)"
+  local marker="$dir/was_sourced"
+  local fixture="$dir/dynamic_count_fixture.sh"
+  {
+    echo "echo x >>\"$marker\""
+    echo 'eval "function test_evaled() { :; }"'
+    echo 'function test_plain() { :; }'
+  } >"$fixture"
+
+  local total
+  total="$(helpers_test::find_total_in_subshell "" "$fixture")"
+
+  assert_same "2" "$total"
+  assert_file_exists "$marker"
+}
+
 function test_parse_file_path_filter_plain_path() {
   local result
   result=$(bashunit::helper::parse_file_path_filter "tests/unit/example_test.sh") || true