[Utils] Add support for split-file to diff_test_updater (#157765)

2025-09-11 12:58:59 -07:00 · 2025-09-11 12:58:59 -07:00 · 9eb17cc034
commit 9eb17cc034
parent 4ae520bfb4
21 changed files with 260 additions and 14 deletions
--- a/llvm/utils/lit/lit/DiffUpdater.py
+++ b/llvm/utils/lit/lit/DiffUpdater.py
@ -1,37 +1,136 @@
 import shutil
+import os
+import shlex

 """
 This file provides the `diff_test_updater` function, which is invoked on failed RUN lines when lit is executed with --update-tests.
 It checks whether the failed command is `diff` and, if so, uses heuristics to determine which file is the checked-in reference file and which file is output from the test case.
 The heuristics are currently as follows:
+    - if exactly one file originates from the `split-file` command, that file is the reference file and the other is the output file
    - if exactly one file ends with ".expected" (common pattern in LLVM), that file is the reference file and the other is the output file
    - if exactly one file path contains ".tmp" (e.g. because it contains the expansion of "%t"), that file is the reference file and the other is the output file
 If the command matches one of these patterns the output file content is copied to the reference file to make the test pass.
+If the reference file originated in `split-file`, the output file content is instead copied to the corresponding slice of the test file.
 Otherwise the test is ignored.

 Possible improvements:
    - Support stdin patterns like "my_binary %s | diff expected.txt"
-    - Scan RUN lines to see if a file is the source of output from a previous command.
+    - Scan RUN lines to see if a file is the source of output from a previous command (other than `split-file`).
      If it is then it is not a reference file that can be copied to, regardless of name, since the test will overwrite it anyways.
    - Only update the parts that need updating (based on the diff output). Could help avoid noisy updates when e.g. whitespace changes are ignored.
 """


-def get_source_and_target(a, b):
+class NormalFileTarget:
+    def __init__(self, target):
+        self.target = target
+
+    def copyFrom(self, source):
+        shutil.copy(source, self.target)
+
+    def __str__(self):
+        return self.target
+
+
+class SplitFileTarget:
+    def __init__(self, slice_start_idx, test_path, lines):
+        self.slice_start_idx = slice_start_idx
+        self.test_path = test_path
+        self.lines = lines
+
+    def copyFrom(self, source):
+        lines_before = self.lines[: self.slice_start_idx + 1]
+        self.lines = self.lines[self.slice_start_idx + 1 :]
+        slice_end_idx = None
+        for i, l in enumerate(self.lines):
+            if SplitFileTarget._get_split_line_path(l) != None:
+                slice_end_idx = i
+                break
+        if slice_end_idx is not None:
+            lines_after = self.lines[slice_end_idx:]
+        else:
+            lines_after = []
+        with open(source, "r") as f:
+            new_lines = lines_before + f.readlines() + lines_after
+        with open(self.test_path, "w") as f:
+            for l in new_lines:
+                f.write(l)
+
+    def __str__(self):
+        return f"slice in {self.test_path}"
+
+    @staticmethod
+    def get_target_dir(commands, test_path):
+        for cmd in commands:
+            split = shlex.split(cmd)
+            if "split-file" not in split:
+                continue
+            start_idx = split.index("split-file")
+            split = split[start_idx:]
+            if len(split) < 3:
+                continue
+            if split[1].strip() != test_path:
+                continue
+            return split[2].strip()
+        return None
+
+    @staticmethod
+    def create(path, commands, test_path, target_dir):
+        filename = path.replace(target_dir, "")
+        if filename.startswith(os.sep):
+            filename = filename[len(os.sep) :]
+        with open(test_path, "r") as f:
+            lines = f.readlines()
+        for i, l in enumerate(lines):
+            p = SplitFileTarget._get_split_line_path(l)
+            if p == filename:
+                idx = i
+                break
+        else:
+            return None
+        return SplitFileTarget(idx, test_path, lines)
+
+    @staticmethod
+    def _get_split_line_path(l):
+        if len(l) < 6:
+            return None
+        if l.startswith("//"):
+            l = l[2:]
+        else:
+            l = l[1:]
+        if l.startswith("--- "):
+            l = l[4:]
+        else:
+            return None
+        return l.rstrip()
+
+
+def get_source_and_target(a, b, test_path, commands):
    """
    Try to figure out which file is the test output and which is the reference.
    """
+    split_target_dir = SplitFileTarget.get_target_dir(commands, test_path)
+    if split_target_dir:
+        a_target = SplitFileTarget.create(a, commands, test_path, split_target_dir)
+        b_target = SplitFileTarget.create(b, commands, test_path, split_target_dir)
+        if a_target and b_target:
+            return None
+        if a_target:
+            return b, a_target
+        if b_target:
+            return a, b_target
+
    expected_suffix = ".expected"
    if a.endswith(expected_suffix) and not b.endswith(expected_suffix):
-        return b, a
+        return b, NormalFileTarget(a)
    if b.endswith(expected_suffix) and not a.endswith(expected_suffix):
-        return a, b
+        return a, NormalFileTarget(b)

    tmp_substr = ".tmp"
    if tmp_substr in a and not tmp_substr in b:
-        return a, b
+        return a, NormalFileTarget(b)
    if tmp_substr in b and not tmp_substr in a:
-        return b, a
+        return b, NormalFileTarget(a)

    return None

@ -40,16 +139,16 @@ def filter_flags(args):
    return [arg for arg in args if not arg.startswith("-")]


-def diff_test_updater(result, test):
+def diff_test_updater(result, test, commands):
    args = filter_flags(result.command.args)
    if len(args) != 3:
        return None
    [cmd, a, b] = args
    if cmd != "diff":
        return None
-    res = get_source_and_target(a, b)
+    res = get_source_and_target(a, b, test.getFilePath(), commands)
    if not res:
        return f"update-diff-test: could not deduce source and target from {a} and {b}"
    source, target = res
-    shutil.copy(source, target)
+    target.copyFrom(source)
    return f"update-diff-test: copied {source} to {target}"
--- a/llvm/utils/lit/lit/TestRunner.py
+++ b/llvm/utils/lit/lit/TestRunner.py
@ -1241,7 +1241,7 @@ def executeScriptInternal(
        ):
            for test_updater in litConfig.test_updaters:
                try:
-                    update_output = test_updater(result, test)
+                    update_output = test_updater(result, test, commands)
                except Exception as e:
                    output = out
                    output += err
--- a/llvm/utils/lit/tests/Inputs/diff-test-update/.gitignore
+++ b/llvm/utils/lit/tests/Inputs/diff-test-update/.gitignore
@ -1,2 +1,10 @@
 ; diff-tmp-dir.test clobbers this file
 empty.txt
+; these test cases are clobbered when run, so they're recreated each time
+single-split-file.test
+single-split-file-populated.test
+multiple-split-file.test
+multiple-split-file-populated.test
+single-split-file-no-expected.test
+split-c-comments.test
+split whitespace.test
--- a/llvm/utils/lit/tests/Inputs/diff-test-update/multiple-split-file-populated.in
+++ b/llvm/utils/lit/tests/Inputs/diff-test-update/multiple-split-file-populated.in
@ -0,0 +1,17 @@
+# RUN: split-file %s %t
+# RUN: cp %S/1.in %t/out.txt
+# RUN: diff %t/test3.expected %t/out.txt
+
+#--- test1.expected
+unrelated
+#--- test2.expected
+#--- test3.expected
+BAR
+
+BAZ
+
+#--- test4.expected
+filler
+#--- test5.expected
+
+
--- a/llvm/utils/lit/tests/Inputs/diff-test-update/multiple-split-file.in
+++ b/llvm/utils/lit/tests/Inputs/diff-test-update/multiple-split-file.in
@ -0,0 +1,13 @@
+# RUN: split-file %s %t
+# RUN: cp %S/1.in %t/out.txt
+# RUN: diff %t/test3.expected %t/out.txt
+
+#--- test1.expected
+unrelated
+#--- test2.expected
+#--- test3.expected
+#--- test4.expected
+filler
+#--- test5.expected
+
+
--- a/llvm/utils/lit/tests/Inputs/diff-test-update/multiple-split-file.out
+++ b/llvm/utils/lit/tests/Inputs/diff-test-update/multiple-split-file.out
@ -0,0 +1,14 @@
+# RUN: split-file %s %t
+# RUN: cp %S/1.in %t/out.txt
+# RUN: diff %t/test3.expected %t/out.txt
+
+#--- test1.expected
+unrelated
+#--- test2.expected
+#--- test3.expected
+FOO
+#--- test4.expected
+filler
+#--- test5.expected
+
+
--- a/llvm/utils/lit/tests/Inputs/diff-test-update/single-split-file-no-expected.in
+++ b/llvm/utils/lit/tests/Inputs/diff-test-update/single-split-file-no-expected.in
@ -0,0 +1,6 @@
+# RUN: split-file %s %t
+# RUN: cp %S/1.in %t/out.txt
+# RUN: diff %t/test.txt %t/out.txt
+
+#--- test.txt
+
--- a/llvm/utils/lit/tests/Inputs/diff-test-update/single-split-file-no-expected.out
+++ b/llvm/utils/lit/tests/Inputs/diff-test-update/single-split-file-no-expected.out
@ -0,0 +1,6 @@
+# RUN: split-file %s %t
+# RUN: cp %S/1.in %t/out.txt
+# RUN: diff %t/test.txt %t/out.txt
+
+#--- test.txt
+FOO
--- a/llvm/utils/lit/tests/Inputs/diff-test-update/single-split-file-populated.in
+++ b/llvm/utils/lit/tests/Inputs/diff-test-update/single-split-file-populated.in
@ -0,0 +1,7 @@
+# RUN: split-file %s %t
+# RUN: cp %S/1.in %t/out.txt
+# RUN: diff %t/test.expected %t/out.txt
+
+#--- test.expected
+BAR
+
--- a/llvm/utils/lit/tests/Inputs/diff-test-update/single-split-file.in
+++ b/llvm/utils/lit/tests/Inputs/diff-test-update/single-split-file.in
@ -0,0 +1,5 @@
+# RUN: split-file %s %t
+# RUN: cp %S/1.in %t/out.txt
+# RUN: diff %t/test.expected %t/out.txt
+
+#--- test.expected
--- a/llvm/utils/lit/tests/Inputs/diff-test-update/single-split-file.out
+++ b/llvm/utils/lit/tests/Inputs/diff-test-update/single-split-file.out
@ -0,0 +1,6 @@
+# RUN: split-file %s %t
+# RUN: cp %S/1.in %t/out.txt
+# RUN: diff %t/test.expected %t/out.txt
+
+#--- test.expected
+FOO
--- a/llvm/utils/lit/tests/Inputs/diff-test-update/split-both.test
+++ b/llvm/utils/lit/tests/Inputs/diff-test-update/split-both.test
@ -0,0 +1,11 @@
+# RUN: split-file %s %t
+# RUN: diff %t/split-both.expected %t/split-both.out
+
+# ignore the fact that it's called ".expected"
+# when comparing two files originating in split-file
+
+#--- split-both.expected
+FOO
+#--- split-both.out
+BAR
+
--- a/llvm/utils/lit/tests/Inputs/diff-test-update/split-c-comments.in
+++ b/llvm/utils/lit/tests/Inputs/diff-test-update/split-c-comments.in
@ -0,0 +1,6 @@
+// RUN: split-file %s %t
+// RUN: cp %S/1.in %t/out.txt
+// RUN: diff %t/test.txt %t/out.txt
+//
+//--- test.txt
+
--- a/llvm/utils/lit/tests/Inputs/diff-test-update/split-c-comments.out
+++ b/llvm/utils/lit/tests/Inputs/diff-test-update/split-c-comments.out
@ -0,0 +1,6 @@
+// RUN: split-file %s %t
+// RUN: cp %S/1.in %t/out.txt
+// RUN: diff %t/test.txt %t/out.txt
+//
+//--- test.txt
+FOO
--- a/llvm/utils/lit/tests/Inputs/diff-test-update/split-whitespace.in
+++ b/llvm/utils/lit/tests/Inputs/diff-test-update/split-whitespace.in
@ -0,0 +1,6 @@
+// RUN: split-file "%s" "%t"
+// RUN: cp %S/1.in "%t/out.txt"
+// RUN: diff "%t/test.txt" "%t/out.txt"
+//
+//--- test.txt
+
--- a/llvm/utils/lit/tests/Inputs/diff-test-update/split-whitespace.out
+++ b/llvm/utils/lit/tests/Inputs/diff-test-update/split-whitespace.out
@ -0,0 +1,6 @@
+// RUN: split-file "%s" "%t"
+// RUN: cp %S/1.in "%t/out.txt"
+// RUN: diff "%t/test.txt" "%t/out.txt"
+//
+//--- test.txt
+FOO
--- a/llvm/utils/lit/tests/Inputs/diff-test-update/unrelated-split.test
+++ b/llvm/utils/lit/tests/Inputs/diff-test-update/unrelated-split.test
@ -0,0 +1,11 @@
+# the fact that this test runs split-file is unrelated
+# to the diffed files
+
+# RUN: mkdir %t
+# RUN: split-file %s %t
+# RUN: cp %S/1.in %t/unrelated-split.expected
+# RUN: cp %S/2.in %t/unrelated-split.txt
+# RUN: diff %t/unrelated-split.expected %t/unrelated-split.txt
+
+#--- distraction.txt
+
--- a/llvm/utils/lit/tests/Inputs/pass-test-update/should_not_run.py
+++ b/llvm/utils/lit/tests/Inputs/pass-test-update/should_not_run.py
@ -1,2 +1,2 @@
-def should_not_run(foo, bar):
+def should_not_run(foo, bar, baz):
    raise Exception("this test updater should only run on failure")
--- a/llvm/utils/lit/tests/diff-test-update.py
+++ b/llvm/utils/lit/tests/diff-test-update.py
@ -1,10 +1,29 @@
+# RUN: cp %S/Inputs/diff-test-update/single-split-file.in %S/Inputs/diff-test-update/single-split-file.test
+# RUN: cp %S/Inputs/diff-test-update/single-split-file-populated.in %S/Inputs/diff-test-update/single-split-file-populated.test
+# RUN: cp %S/Inputs/diff-test-update/multiple-split-file.in %S/Inputs/diff-test-update/multiple-split-file.test
+# RUN: cp %S/Inputs/diff-test-update/multiple-split-file-populated.in %S/Inputs/diff-test-update/multiple-split-file-populated.test
+# RUN: cp %S/Inputs/diff-test-update/single-split-file-no-expected.in %S/Inputs/diff-test-update/single-split-file-no-expected.test
+# RUN: cp %S/Inputs/diff-test-update/split-c-comments.in %S/Inputs/diff-test-update/split-c-comments.test
+# RUN: cp %S/Inputs/diff-test-update/split-whitespace.in "%S/Inputs/diff-test-update/split whitespace.test"
+
 # RUN: not %{lit} --update-tests -v %S/Inputs/diff-test-update | FileCheck %s

+# RUN: diff %S/Inputs/diff-test-update/single-split-file.out %S/Inputs/diff-test-update/single-split-file.test
+# RUN: diff %S/Inputs/diff-test-update/single-split-file.out %S/Inputs/diff-test-update/single-split-file-populated.test
+# RUN: diff %S/Inputs/diff-test-update/multiple-split-file.out %S/Inputs/diff-test-update/multiple-split-file.test
+# RUN: diff %S/Inputs/diff-test-update/multiple-split-file.out %S/Inputs/diff-test-update/multiple-split-file-populated.test
+# RUN: diff %S/Inputs/diff-test-update/single-split-file-no-expected.out %S/Inputs/diff-test-update/single-split-file-no-expected.test
+# RUN: diff %S/Inputs/diff-test-update/split-c-comments.out %S/Inputs/diff-test-update/split-c-comments.test
+# RUN: diff %S/Inputs/diff-test-update/split-whitespace.out "%S/Inputs/diff-test-update/split whitespace.test"
+
+
 # CHECK: # update-diff-test: could not deduce source and target from {{.*}}1.in and {{.*}}2.in
 # CHECK: # update-diff-test: could not deduce source and target from {{.*}}1.txt and {{.*}}2.txt
 # CHECK: # update-diff-test: copied {{.*}}my-file.txt to {{.*}}my-file.expected
 # CHECK: # update-diff-test: copied {{.*}}1.txt to {{.*}}empty.txt
 # CHECK: # update-diff-test: copied {{.*}}diff-tmp.test.tmp.txt to {{.*}}diff-t-out.txt
+# CHECK: # update-diff-test: could not deduce source and target from {{.*}}split-both.expected and {{.*}}split-both.out
+# CHECK: # update-diff-test: copied {{.*}}unrelated-split.txt to {{.*}}unrelated-split.expected


-# CHECK: Failed: 5 (100.00%)
+# CHECK: Failed: 14 (100.00%)
--- a/llvm/utils/lit/tests/pass-test-update.py
+++ b/llvm/utils/lit/tests/pass-test-update.py
@ -12,7 +12,7 @@
 # CHECK: Exception occurred in test updater:
 # CHECK: Traceback (most recent call last):
 # CHECK:   File {{.*}}, line {{.*}}, in {{.*}}
-# CHECK:     update_output = test_updater(result, test)
+# CHECK:     update_output = test_updater(result, test, commands)
 # CHECK:   File "{{.*}}{{/|\\}}should_not_run.py", line {{.*}}, in should_not_run
 # CHECK:     raise Exception("this test updater should only run on failure")
 # CHECK: Exception: this test updater should only run on failure
--- a/llvm/utils/update_any_test_checks.py
+++ b/llvm/utils/update_any_test_checks.py
@ -63,7 +63,7 @@ def expand_listfile_args(arg_list):
    return exp_arg_list


-def utc_lit_plugin(result, test):
+def utc_lit_plugin(result, test, commands):
    testname = test.getFilePath()
    if not testname:
        return None