[lit] Support %if ... %else syntax for RUN lines

This syntax allows to modify RUN lines based on features
available. For example:

    RUN: ... | FileCheck %s --check-prefix=%if windows %{CHECK-W%} %else %{CHECK-NON-W%}
    CHECK-W: ...
    CHECK-NON-W: ...

The whole command can be put under %if ... %else:

    RUN: %if tool_available %{ %tool %} %else %{ true %}

or:

    RUN: %if tool_available %{ %tool %}

If tool_available feature is missing, we'll have an empty command in
this RUN line.  LIT used to emit an error for empty commands, but now
it treats such commands as nop in all cases.

Multi-line expressions are also supported:

    RUN: %if tool_available %{ \
    RUN:   %tool               \
    RUN: %} %else %{           \
    RUN:   true                \
    RUN: %}

Background and motivation:
D121727 [NVPTX] Integrate ptxas to LIT tests
https://reviews.llvm.org/D121727

Differential Revision: https://reviews.llvm.org/D122569

Author: asavonic

llvm/docs/TestingGuide.rst

@@ -612,6 +612,13 @@ RUN lines:
 
    Example: ``Windows %errc_ENOENT: no such file or directory``
 
+``%if feature %{<if branch>%} %else %{<else branch>%}``
+
+ Conditional substitution: if ``feature`` is available it expands to
+ ``<if branch>``, otherwise it expands to ``<else branch>``.
+ ``%else %{<else branch>%}`` is optional and treated like ``%else %{%}``
+ if not present.
+
 **LLVM-specific substitutions:**
 
 ``%shlibext``

llvm/utils/lit/lit/TestRunner.py

@@ -48,7 +48,10 @@ def __init__(self, command, message):
 # This regex captures ARG.  ARG must not contain a right parenthesis, which
 # terminates %dbg.  ARG must not contain quotes, in which ARG might be enclosed
 # during expansion.
-kPdbgRegex = '%dbg\\(([^)\'"]*)\\)'
+#
+# COMMAND that follows %dbg(ARG) is also captured. COMMAND can be
+# empty as a result of conditinal substitution.
+kPdbgRegex = '%dbg\\(([^)\'"]*)\\)(.*)'
 
 class ShellEnvironment(object):
 
@@ -899,7 +902,11 @@ def _executeShCmd(cmd, shenv, results, timeoutHelper):
 def executeScriptInternal(test, litConfig, tmpBase, commands, cwd):
     cmds = []
     for i, ln in enumerate(commands):
-        ln = commands[i] = re.sub(kPdbgRegex, ": '\\1'; ", ln)
+        match = re.match(kPdbgRegex, ln)
+        if match:
+            command = match.group(2)
+            ln = commands[i] = \
+                match.expand(": '\\1'; \\2" if command else ": '\\1'")
         try:
             cmds.append(ShUtil.ShParser(ln, litConfig.isWindows,
                                         test.config.pipefail).parse())
@@ -987,15 +994,24 @@ def executeScript(test, litConfig, tmpBase, commands, cwd):
     f = open(script, mode, **open_kwargs)
     if isWin32CMDEXE:
         for i, ln in enumerate(commands):
-            commands[i] = re.sub(kPdbgRegex, "echo '\\1' > nul && ", ln)
+            match = re.match(kPdbgRegex, ln)
+            if match:
+                command = match.group(2)
+                commands[i] = \
+                    match.expand("echo '\\1' > nul && " if command
+                                 else "echo '\\1' > nul")
         if litConfig.echo_all_commands:
             f.write('@echo on\n')
         else:
             f.write('@echo off\n')
         f.write('\n@if %ERRORLEVEL% NEQ 0 EXIT\n'.join(commands))
     else:
         for i, ln in enumerate(commands):
-            commands[i] = re.sub(kPdbgRegex, ": '\\1'; ", ln)
+            match = re.match(kPdbgRegex, ln)
+            if match:
+                command = match.group(2)
+                commands[i] = match.expand(": '\\1'; \\2" if command
+                                           else ": '\\1'")
         if test.config.pipefail:
             f.write(b'set -o pipefail;' if mode == 'wb' else 'set -o pipefail;')
         if litConfig.echo_all_commands:
@@ -1179,7 +1195,8 @@ def memoized(x):
 def _caching_re_compile(r):
     return re.compile(r)
 
-def applySubstitutions(script, substitutions, recursion_limit=None):
+def applySubstitutions(script, substitutions, conditions={},
+                       recursion_limit=None):
     """
     Apply substitutions to the script.  Allow full regular expression syntax.
     Replace each matching occurrence of regular expression pattern a with
@@ -1193,14 +1210,103 @@ def applySubstitutions(script, substitutions, recursion_limit=None):
     """
 
     # We use #_MARKER_# to hide %% while we do the other substitutions.
-    def escape(ln):
+    def escapePercents(ln):
         return _caching_re_compile('%%').sub('#_MARKER_#', ln)
 
-    def unescape(ln):
+    def unescapePercents(ln):
         return _caching_re_compile('#_MARKER_#').sub('%', ln)
 
+    def substituteIfElse(ln):
+        # early exit to avoid wasting time on lines without
+        # conditional substitutions
+        if ln.find('%if ') == -1:
+            return ln
+
+        def tryParseIfCond(ln):
+            # space is important to not conflict with other (possible)
+            # substitutions
+            if not ln.startswith('%if '):
+                return None, ln
+            ln = ln[4:]
+
+            # stop at '%{'
+            match = _caching_re_compile('%{').search(ln)
+            if not match:
+                raise ValueError("'%{' is missing for %if substitution")
+            cond = ln[:match.start()]
+
+            # eat '%{' as well
+            ln = ln[match.end():]
+            return cond, ln
+
+        def tryParseElse(ln):
+            match = _caching_re_compile('^\s*%else\s*(%{)?').search(ln)
+            if not match:
+                return False, ln
+            if not match.group(1):
+                raise ValueError("'%{' is missing for %else substitution")
+            return True, ln[match.end():]
+
+        def tryParseEnd(ln):
+            if ln.startswith('%}'):
+                return True, ln[2:]
+            return False, ln
+
+        def parseText(ln, isNested):
+            # parse everything until %if, or %} if we're parsing a
+            # nested expression.
+            match = _caching_re_compile(
+                '(.*?)(?:%if|%})' if isNested else '(.*?)(?:%if)').search(ln)
+            if not match:
+                # there is no terminating pattern, so treat the whole
+                # line as text
+                return ln, ''
+            text_end = match.end(1)
+            return ln[:text_end], ln[text_end:]
+
+        def parseRecursive(ln, isNested):
+            result = ''
+            while len(ln):
+                if isNested:
+                    found_end, _ = tryParseEnd(ln)
+                    if found_end:
+                        break
+
+                # %if cond %{ branch_if %} %else %{ branch_else %}
+                cond, ln = tryParseIfCond(ln)
+                if cond:
+                    branch_if, ln = parseRecursive(ln, isNested=True)
+                    found_end, ln = tryParseEnd(ln)
+                    if not found_end:
+                        raise ValueError("'%}' is missing for %if substitution")
+
+                    branch_else = ''
+                    found_else, ln = tryParseElse(ln)
+                    if found_else:
+                        branch_else, ln = parseRecursive(ln, isNested=True)
+                        found_end, ln = tryParseEnd(ln)
+                        if not found_end:
+                            raise ValueError("'%}' is missing for %else substitution")
+
+                    if BooleanExpression.evaluate(cond, conditions):
+                        result += branch_if
+                    else:
+                        result += branch_else
+                    continue
+
+                # The rest is handled as plain text.
+                text, ln = parseText(ln, isNested)
+                result += text
+
+            return result, ln
+
+        result, ln = parseRecursive(ln, isNested=False)
+        assert len(ln) == 0
+        return result
+
     def processLine(ln):
         # Apply substitutions
+        ln = substituteIfElse(escapePercents(ln))
         for a,b in substitutions:
             if kIsWindows:
                 b = b.replace("\\","\\\\")
@@ -1211,7 +1317,7 @@ def processLine(ln):
             # short-lived, since the set of substitutions is fairly small, and
             # since thrashing has such bad consequences, not bounding the cache
             # seems reasonable.
-            ln = _caching_re_compile(a).sub(str(b), escape(ln))
+            ln = _caching_re_compile(a).sub(str(b), escapePercents(ln))
 
         # Strip the trailing newline and any extra whitespace.
         return ln.strip()
@@ -1235,7 +1341,7 @@ def processLineToFixedPoint(ln):
 
     process = processLine if recursion_limit is None else processLineToFixedPoint
 
-    return [unescape(process(ln)) for ln in script]
+    return [unescapePercents(process(ln)) for ln in script]
 
 
 class ParserKind(object):
@@ -1610,7 +1716,8 @@ def executeShTest(test, litConfig, useExternalSh,
     substitutions = list(extra_substitutions)
     substitutions += getDefaultSubstitutions(test, tmpDir, tmpBase,
                                              normalize_slashes=useExternalSh)
-    script = applySubstitutions(script, substitutions,
+    conditions = { feature: True for feature in test.config.available_features }
+    script = applySubstitutions(script, substitutions, conditions,
                                 recursion_limit=test.config.recursiveExpansionLimit)
 
     return _runShTest(test, litConfig, useExternalSh, script, tmpBase)

llvm/utils/lit/tests/Inputs/shtest-if-else/lit.cfg

@@ -0,0 +1,8 @@
+import lit.formats
+config.name = 'shtest-if-else'
+config.test_format = lit.formats.ShTest()
+config.test_source_root = None
+config.test_exec_root = None
+config.suffixes = ['.txt']
+config.available_features.add('feature')
+config.substitutions.append(('%{sub}', 'ok'))

llvm/utils/lit/tests/Inputs/shtest-if-else/test-neg1.txt

@@ -0,0 +1,3 @@
+# CHECK: ValueError: '%{' is missing for %if substitution
+#
+# RUN: %if feature echo "test-1"

llvm/utils/lit/tests/Inputs/shtest-if-else/test-neg2.txt

@@ -0,0 +1,3 @@
+# CHECK: ValueError: '%}' is missing for %if substitution
+#
+# RUN: %if feature %{ echo

llvm/utils/lit/tests/Inputs/shtest-if-else/test-neg3.txt

@@ -0,0 +1,3 @@
+# CHECK: ValueError: '%{' is missing for %else substitution
+#
+# RUN: %if feature %{ echo %} %else fail

llvm/utils/lit/tests/Inputs/shtest-if-else/test-neg4.txt

@@ -0,0 +1,3 @@
+# CHECK: ValueError: '%}' is missing for %else substitution
+#
+# RUN: %if feature %{ echo %} %else %{ fail

llvm/utils/lit/tests/Inputs/shtest-if-else/test.txt

@@ -0,0 +1,92 @@
+# CHECK: -- Testing:{{.*}}
+# CHECK-NEXT: PASS: shtest-if-else :: test.txt (1 of 1)
+# CHECK-NEXT: Script:
+# CHECK-NEXT: --
+
+# RUN: %if feature %{ echo "test-1" %}
+# CHECK-NEXT: {{^.*'RUN}}: at line [[#@LINE-1]]'; echo "test-1"
+
+# If %else is not present it is treated like %else %{%}. Empty commands
+# are ignored.
+#
+# RUN: %if nofeature %{ echo "fail" %}
+# CHECK-NEXT: {{^.*'RUN}}: at line [[#@LINE-1]]'
+# CHECK-NOT: fail
+
+# RUN: %if nofeature %{ echo "fail" %} %else %{ echo "test-2" %}
+# CHECK-NEXT: {{^.*'RUN}}: at line [[#@LINE-1]]'; echo "test-2"
+
+# Spaces inside curly braces are not ignored
+#
+# RUN: echo test-%if feature %{ 3 %} %else %{ fail %}-test
+# RUN: echo test-%if feature %{ 4 4 %} %else %{ fail %}-test
+# RUN: echo test-%if nofeature %{ fail %} %else %{ 5 5 %}-test
+# CHECK-NEXT: {{^.*'RUN}}: at line [[#@LINE-3]]'; echo test- 3 -test
+# CHECK-NEXT: {{^.*'RUN}}: at line [[#@LINE-3]]'; echo test- 4 4 -test
+# CHECK-NEXT: {{^.*'RUN}}: at line [[#@LINE-3]]'; echo test- 5 5 -test
+
+# Escape line breaks for multi-line expressions
+#
+# RUN: %if feature  \
+# RUN:   %{ echo     \
+# RUN:     "test-5" \
+# RUN:   %}
+# CHECK-NEXT: {{^.*'RUN}}: at line [[#@LINE-4]]'; echo "test-5"
+
+# RUN: %if nofeature       \
+# RUN:   %{ echo "fail" %}   \
+# RUN: %else               \
+# RUN:   %{ echo "test-6" %}
+# CHECK-NEXT: {{^.*'RUN}}: at line [[#@LINE-4]]'; echo "test-6"
+
+# RUN: echo "test%if feature %{%} %else %{%}-7"
+# CHECK-NEXT: {{^.*'RUN}}: at line [[#@LINE-1]]'; echo "test-7"
+
+# Escape %if. Without %if..%else context '%{' and '%}' are treated
+# literally.
+#
+# RUN: echo %%if feature %{ echo "test-8" %}
+# CHECK-NEXT: {{^.*'RUN}}: at line [[#@LINE-1]]'; echo %if feature %{ echo "test-8" %}
+
+# Nested expressions are supported:
+#
+# RUN: echo %if feature %{ %if feature %{ %if nofeature %{"fail"%} %else %{"test-9"%} %} %}
+# CHECK-NEXT: {{^.*'RUN}}: at line [[#@LINE-1]]'; echo "test-9"
+
+# Binary expression evaluation and regex match can be used as
+# conditions.
+#
+# RUN: echo %if feature && !nofeature %{ "test-10" %}
+# RUN: echo %if feature && nofeature %{ "fail" %} %else %{ "test-11" %}
+# RUN: echo %if {{fea.+}} %{ "test-12" %} %else %{ "fail" %}
+# CHECK-NEXT: {{^.*'RUN}}: at line [[#@LINE-3]]'; echo "test-10"
+# CHECK-NEXT: {{^.*'RUN}}: at line [[#@LINE-3]]'; echo "test-11"
+# CHECK-NEXT: {{^.*'RUN}}: at line [[#@LINE-3]]'; echo "test-12"
+
+# Spaces between %if and %else are ignored. If there is no %else -
+# space after %if %{...%} is not ignored.
+#
+# RUN: echo XX %if feature %{YY%} ZZ
+# RUN: echo AA %if feature %{BB%} %else %{CC%} DD
+# RUN: echo AA %if nofeature %{BB%} %else %{CC%} DD
+# CHECK-NEXT: {{^.*'RUN}}: at line [[#@LINE-3]]'; echo XX YY ZZ
+# CHECK-NEXT: {{^.*'RUN}}: at line [[#@LINE-3]]'; echo AA BB DD
+# CHECK-NEXT: {{^.*'RUN}}: at line [[#@LINE-3]]'; echo AA CC DD
+
+# '{' and '}' can be used without escaping
+#
+# RUN: %if feature %{echo {}%}
+# CHECK-NEXT: {{^.*'RUN}}: at line [[#@LINE-1]]'; echo {}
+
+# Spaces are not required
+#
+# RUN: echo %if feature%{"ok"%}%else%{"fail"%}
+# CHECK-NEXT: {{^.*'RUN}}: at line [[#@LINE-1]]'; echo "ok"
+
+# Substitutions with braces are handled correctly
+#
+# RUN: echo %{sub} %if feature%{test-%{sub}%}%else%{"fail"%}
+# CHECK-NEXT: {{^.*'RUN}}: at line [[#@LINE-1]]'; echo ok test-ok
+
+# CHECK-NEXT: --
+# CHECK-NEXT: Exit Code: 0

llvm/utils/lit/tests/shtest-if-else.py

@@ -0,0 +1,14 @@
+# RUN: %{lit} -v --show-all %{inputs}/shtest-if-else/test.txt \
+# RUN:    | FileCheck %{inputs}/shtest-if-else/test.txt --match-full-lines
+
+# RUN: not %{lit} -v --show-all %{inputs}/shtest-if-else/test-neg1.txt 2>&1 \
+# RUN:    | FileCheck %{inputs}/shtest-if-else/test-neg1.txt
+
+# RUN: not %{lit} -v --show-all %{inputs}/shtest-if-else/test-neg2.txt 2>&1 \
+# RUN:    | FileCheck %{inputs}/shtest-if-else/test-neg2.txt
+
+# RUN: not %{lit} -v --show-all %{inputs}/shtest-if-else/test-neg3.txt 2>&1 \
+# RUN:    | FileCheck %{inputs}/shtest-if-else/test-neg3.txt
+
+# RUN: not %{lit} -v --show-all %{inputs}/shtest-if-else/test-neg4.txt 2>&1 \
+# RUN:    | FileCheck %{inputs}/shtest-if-else/test-neg4.txt