Inital commit.

1 files changed, 171 insertions, 0 deletions

diff --git a/tests/unit/extraction.bats b/tests/unit/extraction.bats
new file mode 100644
index 0000000..21c6784
--- /dev/null
+++ b/tests/unit/extraction.bats
@@ -0,0 +1,171 @@
+#!/usr/bin/env bats
+# tests/unit/extraction.bats
+# Verifies that the AWK extraction programs correctly identify doc comment
+# boundaries and produce chunk files for each supported language.
+#
+# Tests operate directly on the AWK programs (via helpers/common.bash) without
+# running the full trbldoc.sh pipeline.
+
+load "../helpers/common.bash"
+
+FIXTURES="$BATS_TEST_DIRNAME/../fixtures"
+
+setup() {
+  setup_workspace
+  CACHE=".trblcache"
+  mkdir -p "$CACHE/chunks"
+}
+
+teardown() {
+  teardown_workspace
+}
+
+# ── C (/* ... */) ──────────────────────────────────────────────────────────
+
+@test "C: single doc comment produces one chunk" {
+  local prog
+  prog="$(awk_prog_c "$CACHE")"
+  run_extraction "$FIXTURES/c/simple.c" "$prog" "$CACHE"
+  assert_equal "$(chunk_count "$CACHE")" "1"
+}
+
+@test "C: two doc comments produce two chunks" {
+  local prog
+  prog="$(awk_prog_c "$CACHE")"
+  run_extraction "$FIXTURES/c/multi_chunk.c" "$prog" "$CACHE"
+  assert_equal "$(chunk_count "$CACHE")" "2"
+}
+
+@test "C: file with no doc comments produces no chunks" {
+  local prog
+  prog="$(awk_prog_c "$CACHE")"
+  run_extraction "$FIXTURES/c/no_comments.c" "$prog" "$CACHE"
+  assert_equal "$(chunk_count "$CACHE")" "0"
+}
+
+@test "C: chunk contains @exec directive for renderer" {
+  local prog
+  prog="$(awk_prog_c "$CACHE")"
+  run_extraction "$FIXTURES/c/simple.c" "$prog" "$CACHE"
+  chunk_contains "$CACHE" "@exec"
+}
+
+@test "C: chunk contains @file directive with source file name" {
+  local prog
+  prog="$(awk_prog_c "$CACHE")"
+  run_extraction "$FIXTURES/c/simple.c" "$prog" "$CACHE"
+  chunk_contains "$CACHE" "@file"
+}
+
+@test "C: chunk body lines are captured" {
+  local prog
+  prog="$(awk_prog_c "$CACHE")"
+  run_extraction "$FIXTURES/c/simple.c" "$prog" "$CACHE"
+  chunk_contains "$CACHE" "Hello from a C comment"
+}
+
+@test "C: non-comment source lines are not captured in chunk" {
+  local prog
+  prog="$(awk_prog_c "$CACHE")"
+  run_extraction "$FIXTURES/c/simple.c" "$prog" "$CACHE"
+  # 'int main' is code, not doc
+  if grep -rl "int main" "$CACHE/chunks" >/dev/null 2>&1; then
+    echo "FAILED: code line 'int main' was captured in a chunk" >&2
+    return 1
+  fi
+}
+
+@test "C: single-line /* */ comment produces no chunks" {
+  local prog
+  prog="$(awk_prog_c "$CACHE")"
+  # no_comments.c contains a single-line /* ... */ comment on the first line
+  run_extraction "$FIXTURES/c/no_comments.c" "$prog" "$CACHE"
+  assert_equal "$(chunk_count "$CACHE")" "0"
+}
+
+@test "C: two-chunk file produces chunks with distinct content" {
+  local prog
+  prog="$(awk_prog_c "$CACHE")"
+  run_extraction "$FIXTURES/c/multi_chunk.c" "$prog" "$CACHE"
+  chunk_contains "$CACHE" "First chunk content"
+  chunk_contains "$CACHE" "Second chunk content"
+}
+
+# ── Lua (--[[ ... ]]) ──────────────────────────────────────────────────────
+
+@test "Lua: single doc comment produces one chunk" {
+  local prog
+  prog="$(awk_prog_lua "$CACHE")"
+  run_extraction "$FIXTURES/lua/simple.lua" "$prog" "$CACHE"
+  assert_equal "$(chunk_count "$CACHE")" "1"
+}
+
+@test "Lua: chunk body lines are captured" {
+  local prog
+  prog="$(awk_prog_lua "$CACHE")"
+  run_extraction "$FIXTURES/lua/simple.lua" "$prog" "$CACHE"
+  chunk_contains "$CACHE" "Hello from a Lua comment"
+}
+
+@test "Lua: non-comment source lines are not captured" {
+  local prog
+  prog="$(awk_prog_lua "$CACHE")"
+  run_extraction "$FIXTURES/lua/simple.lua" "$prog" "$CACHE"
+  if grep -rl "local x" "$CACHE/chunks" >/dev/null 2>&1; then
+    echo "FAILED: code line 'local x' was captured in a chunk" >&2
+    return 1
+  fi
+}
+
+@test "Lua: single-line --[[ ]] comment produces no chunks" {
+  local prog
+  prog="$(awk_prog_lua "$CACHE")"
+  run_extraction "$FIXTURES/lua/single_line.lua" "$prog" "$CACHE"
+  assert_equal "$(chunk_count "$CACHE")" "0"
+}
+
+# ── Python ('''renderer ... ''') ───────────────────────────────────────────
+
+@test "Python: single doc comment produces one chunk" {
+  local prog
+  prog="$(awk_prog_py "$CACHE")"
+  run_extraction "$FIXTURES/py/simple.py" "$prog" "$CACHE"
+  assert_equal "$(chunk_count "$CACHE")" "1"
+}
+
+@test "Python: chunk body lines are captured" {
+  local prog
+  prog="$(awk_prog_py "$CACHE")"
+  run_extraction "$FIXTURES/py/simple.py" "$prog" "$CACHE"
+  chunk_contains "$CACHE" "Hello from a Python doc comment"
+}
+
+@test "Python: single-line '''content''' on one line produces no chunks" {
+  local prog
+  prog="$(awk_prog_py "$CACHE")"
+  run_extraction "$FIXTURES/py/single_line.py" "$prog" "$CACHE"
+  assert_equal "$(chunk_count "$CACHE")" "0"
+}
+
+# ── Markdown (whole file = one chunk) ──────────────────────────────────────
+
+@test "Markdown: whole file produces exactly one chunk" {
+  local prog
+  prog="$(awk_prog_md "$CACHE")"
+  run_extraction "$FIXTURES/md/simple.md" "$prog" "$CACHE"
+  assert_equal "$(chunk_count "$CACHE")" "1"
+}
+
+@test "Markdown: chunk contains @exec md directive" {
+  local prog
+  prog="$(awk_prog_md "$CACHE")"
+  run_extraction "$FIXTURES/md/simple.md" "$prog" "$CACHE"
+  chunk_contains "$CACHE" "@exec md"
+}
+
+@test "Markdown: chunk includes file body content" {
+  local prog
+  prog="$(awk_prog_md "$CACHE")"
+  run_extraction "$FIXTURES/md/simple.md" "$prog" "$CACHE"
+  chunk_contains "$CACHE" "Hello from a markdown file"
+}