Import spec tests for awk, jq and sed (#53)

Author: cramforce

src/awk-spec-tests/awk-spec.test.ts

@@ -0,0 +1,85 @@
+/**
+ * Vitest runner for onetrueawk spec tests
+ *
+ * This runs the imported spec tests from the onetrueawk project against just-bash's awk.
+ */
+
+import * as fs from "node:fs";
+import * as path from "node:path";
+import { describe, expect, it } from "vitest";
+import { parseAwkTestFile } from "./parser.js";
+import { formatError, runAwkTestCase } from "./runner.js";
+import { getSkipReason, isFileSkipped } from "./skips.js";
+
+const CASES_DIR = path.join(__dirname, "cases");
+
+// Get all T.* test files (the systematic test scripts)
+// Filter: starts with T., no file extension (no second dot)
+const ALL_TEST_FILES = fs
+  .readdirSync(CASES_DIR)
+  .filter((f) => f.startsWith("T.") && f.indexOf(".", 2) === -1)
+  .sort();
+
+// Filter out completely skipped files
+const TEST_FILES = ALL_TEST_FILES.filter((f) => !isFileSkipped(f));
+
+/**
+ * Truncate program for test name display
+ */
+function truncateProgram(program: string, maxLen = 50): string {
+  const normalized = program
+    .split("\n")
+    .map((l) => l.trim())
+    .filter((l) => l)
+    .join(" ");
+
+  if (normalized.length <= maxLen) {
+    return normalized;
+  }
+  return `${normalized.slice(0, maxLen - 3)}...`;
+}
+
+describe("OneTrue AWK Spec Tests", () => {
+  for (const fileName of TEST_FILES) {
+    const filePath = path.join(CASES_DIR, fileName);
+
+    describe(fileName, () => {
+      // Parse the test file
+      const content = fs.readFileSync(filePath, "utf-8");
+      const parsed = parseAwkTestFile(content, filePath);
+
+      // Skip files with no parseable tests
+      if (parsed.testCases.length === 0) {
+        it.skip("No parseable tests", () => {});
+        return;
+      }
+
+      for (const testCase of parsed.testCases) {
+        // Check for individual test skip (pass program for pattern matching)
+        const skipReason = getSkipReason(
+          fileName,
+          testCase.name,
+          testCase.program,
+        );
+        if (skipReason) {
+          testCase.skip = skipReason;
+        }
+
+        const programPreview = truncateProgram(testCase.program);
+        const testName = `[L${testCase.lineNumber}] ${testCase.name}: ${programPreview}`;
+
+        it(testName, async () => {
+          const result = await runAwkTestCase(testCase);
+
+          if (result.skipped) {
+            return;
+          }
+
+          if (!result.passed) {
+            expect.fail(formatError(result));
+          }
+        });
+      }
+    });
+  }
+});

src/awk-spec-tests/cases/Compare.T1

@@ -0,0 +1,10 @@
+
+oldawk=${oldawk-awk}
+awk=${awk-../a.out}
+
+echo oldawk=$oldawk, awk=$awk
+
+for i in T.*
+do 
+	$i
+done

src/awk-spec-tests/cases/Compare.drek

@@ -0,0 +1,35 @@
+# an arbitrary collection of input data
+
+cat td.1 td.1 >foo.td
+sed 's/^........................//' td.1 >>foo.td
+pr -m td.1 td.1 td.1 >>foo.td
+pr -2 td.1 >>foo.td
+wc foo.td
+
+td=foo.td
+>footot
+
+for i in $*
+do
+	echo $i >/dev/tty
+	echo $i '<<<'
+	cd ..
+	echo testdir/$i:
+	ind <testdir/$i
+	a.out -f testdir/$i >drek.c
+	cat drek.c
+	make drek || ( echo $i '	' bad compile; echo $i '	' bad compile >/dev/tty; continue )
+	cd testdir
+
+	time /usr/bin/awk -f $i $td >foo2 2>foo2t
+	cat foo2t
+	time ../drek $td >foo1 2>foo1t
+	cat foo1t
+	cmp foo1 foo2 || ( echo $i '	' bad; echo $i '	' bad >/dev/tty; diff foo1 foo2 | sed 20q )
+	echo '>>>' $i
+	echo
+	echo $i: >>footot
+	cat foo1t foo2t >>footot
+done
+
+ctimes footot

src/awk-spec-tests/cases/Compare.p

@@ -0,0 +1,17 @@
+
+oldawk=${oldawk-awk}
+awk=${awk-../a.out}
+
+echo oldawk=$oldawk, awk=$awk
+
+for i
+do
+	echo "$i:"
+	$oldawk -f $i test.countries test.countries >foo1 
+	$awk -f $i test.countries test.countries >foo2 
+	if cmp -s foo1 foo2
+	then true
+	else echo -n "$i:	BAD ..."
+	fi
+	diff -b foo1 foo2 | sed -e 's/^/	/' -e 10q
+done

src/awk-spec-tests/cases/Compare.t

@@ -0,0 +1,17 @@
+
+oldawk=${oldawk-myawk}
+awk=${awk-../a.out}
+
+echo oldawk=$oldawk, awk=$awk
+
+for i
+do
+	echo "$i:"
+	$oldawk -f $i test.data >foo1 
+	$awk -f $i test.data >foo2 
+	if cmp -s foo1 foo2
+	then true
+	else echo -n "$i:	BAD ..."
+	fi
+	diff -b foo1 foo2 | sed -e 's/^/	/' -e 10q
+done

src/awk-spec-tests/cases/Compare.tt

@@ -0,0 +1,49 @@
+#!/bin/sh
+
+oldawk=${oldawk-awk}
+awk=${awk-../a.out}
+
+echo compiling time.c
+cc time.c -o time
+time=./time
+
+echo time command = $time
+
+#case `uname` in
+#SunOS)
+#	time=/usr/bin/time ;;
+#Linux)
+#	time=/usr/bin/time ;;
+#*)
+#	time=time ;;
+#esac
+
+echo oldawk = $oldawk, awk = $awk, time command = $time
+
+
+# an arbitrary collection of input data
+
+cat td.1 td.1 >foo.td
+sed 's/^........................//' td.1 >>foo.td
+pr -m td.1 td.1 td.1 >>foo.td
+pr -2 td.1 >>foo.td
+cat bib >>foo.td
+wc foo.td
+
+td=foo.td
+>footot
+
+for i in $*
+do
+	echo $i "($oldawk vs $awk)":
+	# ind <$i
+	$time $oldawk -f $i $td >foo2 2>foo2t
+	cat foo2t
+	$time $awk -f $i $td >foo1 2>foo1t
+	cat foo1t
+	cmp foo1 foo2
+	echo $i: >>footot
+	cat foo1t foo2t >>footot
+done
+
+ctimes footot

src/awk-spec-tests/cases/LICENSE

@@ -0,0 +1,23 @@
+/****************************************************************
+Copyright (C) Lucent Technologies 1997
+All Rights Reserved
+
+Permission to use, copy, modify, and distribute this software and
+its documentation for any purpose and without fee is hereby
+granted, provided that the above copyright notice appear in all
+copies and that both that the copyright notice and this
+permission notice and warranty disclaimer appear in supporting
+documentation, and that the name Lucent Technologies or any of
+its entities not be used in advertising or publicity pertaining
+to distribution of the software without specific, written prior
+permission.
+
+LUCENT DISCLAIMS ALL WARRANTIES WITH REGARD TO THIS SOFTWARE,
+INCLUDING ALL IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS.
+IN NO EVENT SHALL LUCENT OR ANY OF ITS ENTITIES BE LIABLE FOR ANY
+SPECIAL, INDIRECT OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES
+WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER
+IN AN ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION,
+ARISING OUT OF OR IN CONNECTION WITH THE USE OR PERFORMANCE OF
+THIS SOFTWARE.
+****************************************************************/

src/awk-spec-tests/cases/NOTES

@@ -0,0 +1,10 @@
+Need some tests for octal, hex, various string escapes.
+
+Need to complete the sub and gsub tests.
+
+more on printf, especially weird formats
+
+more on operators
+
+
+never throw away a test

src/awk-spec-tests/cases/README.TESTS

@@ -0,0 +1,44 @@
+The archive of test files contains 
+
+- A shell file called REGRESS that controls the testing process.
+
+- Several shell files called Compare* that control sub-parts
+of the testing.
+
+- About 160 small tests called t.* that constitute a random
+sampling of awk constructions collected over the years.
+Not organized, but they touch almost everything.
+
+- About 60 small tests called p.* that come from the first
+two chapters of The AWK Programming Language.  This is
+basic stuff -- they have to work.
+
+These two sets are intended as regression tests, to be sure
+that a new version produces the same results as a previous one.
+There are a couple of standard data files used with them,
+test.data and test.countries, but others would work too.
+
+- About 20 files called T.* that are self-contained and
+more systematic tests of specific language features.
+For example, T.clv tests command-line variable handling.
+These tests are not regressions -- they compute the right
+answer by separate means, then compare the awk output.
+A specific test for each new bug found shows up in at least
+one of these, most often T.misc.  There are about 220 tests
+total in these files.
+
+- Two of these files, T.re and T.sub, are systematic tests
+of the regular expression and substitution code.  They express
+tests in a small language, then generate awk programs that
+verify behavior.
+
+- About 20 files called tt.* that are used as timing tests;
+they use the most common awk constructions in straightforward
+ways, against a large input file constructed by Compare.tt.
+
+
+There is undoubtedly more stuff in the archive;  it's been
+collecting for years and may need pruning.  Suggestions for
+improvement, additional tests (especially systematic ones),
+and the like are all welcome.
+

src/awk-spec-tests/cases/REGRESS

@@ -0,0 +1,21 @@
+#!/bin/sh
+
+uname -a
+cc echo.c -o echo && echo echo compiled
+
+oldawk=${oldawk-awk}
+awk=${awk-../a.out}
+
+echo oldawk=$oldawk, awk=$awk 
+
+oldawk=$oldawk awk=$awk Compare.t t.*
+	echo `ls t.* | wc -l` tests; echo
+
+oldawk=$oldawk awk=$awk Compare.p p.? p.??*
+	echo `ls p.* | wc -l` tests; echo
+
+oldawk=$oldawk awk=$awk Compare.T1
+	echo `grep '\$awk' T.* | wc -l` tests; echo
+
+oldawk=$oldawk awk=$awk Compare.tt tt.*
+	echo `ls tt.* | wc -l` tests; echo