Revert "[lit] Refactor out some more common lit configuration code."

This is breaking several bots.  I have enough information to
investigate, so I'm reverting to green until I get it figured
out.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@313922 91177308-0d34-0410-b5e6-96231b3b80d8

Author: Zachary Turner

test/lit.cfg.py

@@ -11,7 +11,6 @@
 import lit.util
 import lit.formats
 from lit.llvm import llvm_config
-from lit.llvm import ToolFilter
 
 # name: The name of this test suite.
 config.name = 'LLVM'
@@ -135,39 +134,108 @@ def get_asan_rtlib():
 # The regex is a pre-assertion to avoid matching a preceding
 # dot, hyphen, carat, or slash (.foo, -foo, etc.).  Some patterns
 # also have a post-assertion to not match a trailing hyphen (foo-).
-JUNKCHARS = r".-^/<"
-
-required_tools = [
-    'lli', 'llvm-ar', 'llvm-as', 'llvm-bcanalyzer', 'llvm-config', 'llvm-cov',
-    'llvm-cxxdump', 'llvm-cvtres', 'llvm-diff', 'llvm-dis', 'llvm-dsymutil',
-    'llvm-dwarfdump', 'llvm-extract', 'llvm-isel-fuzzer', 'llvm-lib',
-    'llvm-link', 'llvm-lto', 'llvm-lto2', 'llvm-mc', 'llvm-mcmarkup',
-    'llvm-modextract', 'llvm-nm', 'llvm-objcopy', 'llvm-objdump',
-    'llvm-pdbutil', 'llvm-profdata', 'llvm-ranlib', 'llvm-readobj',
-    'llvm-rtdyld', 'llvm-size', 'llvm-split', 'llvm-strings', 'llvm-tblgen',
-    'llvm-c-test', 'llvm-cxxfilt', 'llvm-xray', 'yaml2obj', 'obj2yaml',
-    'FileCheck', 'yaml-bench', 'verify-uselistorder',
-    ToolFilter('bugpoint', post='-'),
-    ToolFilter('llc', pre=JUNKCHARS),
-    ToolFilter('llvm-symbolizer', pre=JUNKCHARS),
-    ToolFilter('opt', JUNKCHARS),
-    ToolFilter('sancov', pre=JUNKCHARS),
-    ToolFilter('sanstats', pre=JUNKCHARS),
-    # Handle these specially as they are strings searched for during testing.
-    ToolFilter(r'\| \bcount\b', verbatim=True),
-    ToolFilter(r'\| \bnot\b', verbatim=True)]
-
-llvm_config.add_tool_substitutions(required_tools, config.llvm_tools_dir)
+NOJUNK = r"(?<!\.|-|\^|/|<)"
+
+
+def find_tool_substitution(pattern):
+    # Extract the tool name from the pattern.  This relies on the tool
+    # name being surrounded by \b word match operators.  If the
+    # pattern starts with "| ", include it in the string to be
+    # substituted.
+    tool_match = re.match(r"^(\\)?((\| )?)\W+b([0-9A-Za-z-_]+)\\b\W*$",
+                          pattern)
+    tool_pipe = tool_match.group(2)
+    tool_name = tool_match.group(4)
+    # Did the user specify the tool path + arguments? This allows things like
+    # llvm-lit "-Dllc=llc -enable-misched -verify-machineinstrs"
+    tool_path = lit_config.params.get(tool_name)
+    if tool_path is None:
+        tool_path = lit.util.which(tool_name, config.llvm_tools_dir)
+        if tool_path is None:
+            return tool_name, tool_path, tool_pipe
+    if (tool_name == "llc" and
+       'LLVM_ENABLE_MACHINE_VERIFIER' in os.environ and
+       os.environ['LLVM_ENABLE_MACHINE_VERIFIER'] == "1"):
+        tool_path += " -verify-machineinstrs"
+    if (tool_name == "llvm-go"):
+        tool_path += " go=" + config.go_executable
+    return tool_name, tool_path, tool_pipe
+
+
+for pattern in [r"\bbugpoint\b(?!-)",
+                NOJUNK + r"\bllc\b",
+                r"\blli\b",
+                r"\bllvm-ar\b",
+                r"\bllvm-as\b",
+                r"\bllvm-bcanalyzer\b",
+                r"\bllvm-config\b",
+                r"\bllvm-cov\b",
+                r"\bllvm-cxxdump\b",
+                r"\bllvm-cvtres\b",
+                r"\bllvm-diff\b",
+                r"\bllvm-dis\b",
+                r"\bllvm-dsymutil\b",
+                r"\bllvm-dwarfdump\b",
+                r"\bllvm-extract\b",
+                r"\bllvm-isel-fuzzer\b",
+                r"\bllvm-lib\b",
+                r"\bllvm-link\b",
+                r"\bllvm-lto\b",
+                r"\bllvm-lto2\b",
+                r"\bllvm-mc\b",
+                r"\bllvm-mcmarkup\b",
+                r"\bllvm-modextract\b",
+                r"\bllvm-nm\b",
+                r"\bllvm-objcopy\b",
+                r"\bllvm-objdump\b",
+                r"\bllvm-pdbutil\b",
+                r"\bllvm-profdata\b",
+                r"\bllvm-ranlib\b",
+                r"\bllvm-readobj\b",
+                r"\bllvm-rtdyld\b",
+                r"\bllvm-size\b",
+                r"\bllvm-split\b",
+                r"\bllvm-strings\b",
+                r"\bllvm-tblgen\b",
+                r"\bllvm-c-test\b",
+                r"\bllvm-cxxfilt\b",
+                r"\bllvm-xray\b",
+                NOJUNK + r"\bllvm-symbolizer\b",
+                NOJUNK + r"\bopt\b",
+                r"\bFileCheck\b",
+                r"\bobj2yaml\b",
+                NOJUNK + r"\bsancov\b",
+                NOJUNK + r"\bsanstats\b",
+                r"\byaml2obj\b",
+                r"\byaml-bench\b",
+                r"\bverify-uselistorder\b",
+                # Handle these specially as they are strings searched
+                # for during testing.
+                r"\| \bcount\b",
+                r"\| \bnot\b"]:
+    tool_name, tool_path, tool_pipe = find_tool_substitution(pattern)
+    if not tool_path:
+        # Warn, but still provide a substitution.
+        lit_config.note('Did not find ' + tool_name + ' in ' + config.llvm_tools_dir)
+        tool_path = config.llvm_tools_dir + '/' + tool_name
+    config.substitutions.append((pattern, tool_pipe + tool_path))
 
 # For tools that are optional depending on the config, we won't warn
 # if they're missing.
+for pattern in [r"\bllvm-go\b",
+                r"\bllvm-mt\b",
+                r"\bKaleidoscope-Ch3\b",
+                r"\bKaleidoscope-Ch4\b",
+                r"\bKaleidoscope-Ch5\b",
+                r"\bKaleidoscope-Ch6\b",
+                r"\bKaleidoscope-Ch7\b",
+                r"\bKaleidoscope-Ch8\b"]:
+    tool_name, tool_path, tool_pipe = find_tool_substitution(pattern)
+    if not tool_path:
+        # Provide a substitution anyway, for the sake of consistent errors.
+        tool_path = config.llvm_tools_dir + '/' + tool_name
+    config.substitutions.append((pattern, tool_pipe + tool_path))
 
-optional_tools = [
-    'llvm-go', 'llvm-mt', 'Kaleidoscope-Ch3', 'Kaleidoscope-Ch4',
-    'Kaleidoscope-Ch5', 'Kaleidoscope-Ch6', 'Kaleidoscope-Ch7',
-    'Kaleidoscope-Ch8']
-llvm_config.add_tool_substitutions(optional_tools, config.llvm_tools_dir,
-                                   warn_missing=False)
 
 ### Targets
 

utils/lit/lit/llvm/__init__.py

@@ -1,51 +1,9 @@
+
 from lit.llvm import config
-import lit.util
-import re
 
 llvm_config = None
 
-class ToolFilter(object):
-    """
-        String-like class used to build regex substitution patterns for
-        llvm tools.  Handles things like adding word-boundary patterns,
-        and filtering characters from the beginning an end of a tool name
-    """
-
-    def __init__(self, name, pre=None, post=None, verbatim=False):
-        """
-            Construct a ToolFilter.
-
-            name: the literal name of the substitution to look for.
-
-            pre: If specified, the substitution will not find matches where
-            the character immediately preceding the word-boundary that begins
-            `name` is any of the characters in the string `pre`.
-
-            post: If specified, the substitution will not find matches where
-            the character immediately after the word-boundary that ends `name`
-            is any of the characters specified in the string `post`.
-
-            verbatim: If True, `name` is an exact regex that is passed to the
-            underlying substitution
-        """
-        if verbatim:
-            self.regex = name
-            return
-
-        def not_in(chars, where=''):
-            if not chars:
-                return ''
-            pattern_str = '|'.join(re.escape(x) for x in chars)
-            return r'(?{}!({}))'.format(where, pattern_str)
-
-        self.regex = not_in(pre, '<') + r'\b' + name + r'\b' + not_in(post)
-
-    def __str__(self):
-        return self.regex
-
-
 def initialize(lit_config, test_config):
     global llvm_config
-
     llvm_config = config.LLVMConfig(lit_config, test_config)
 

utils/lit/lit/llvm/config.py

@@ -136,24 +136,22 @@ def clear_environment(self, variables):
             if name in self.config.environment:
                 del self.config.environment[name]
 
-    def get_process_output(self, command):
-        try:
-            cmd = subprocess.Popen(
-                command, stdout=subprocess.PIPE,
-                stderr=subprocess.PIPE, env=self.config.environment)
-            stdout, stderr = cmd.communicate()
-            return (stdout, stderr)
-        except OSError:
-            self.lit_config.fatal("Could not run process %s" % command)
-
-    def feature_config(self, features):
+    def feature_config(self, features, encoding = 'ascii'):
         # Ask llvm-config about the specified feature.
         arguments = [x for (x, _) in features]
-        config_path = os.path.join(self.config.llvm_tools_dir, 'llvm-config')
+        try:
+            config_path = os.path.join(self.config.llvm_tools_dir, 'llvm-config')
 
-        output, _ = self.get_process_output([config_path] + arguments)
-        lines = output.split('\n')
+            llvm_config_cmd = subprocess.Popen(
+                [config_path] + arguments,
+                stdout = subprocess.PIPE,
+                env=self.config.environment)
+        except OSError:
+            self.lit_config.fatal("Could not find llvm-config in " + self.config.llvm_tools_dir)
 
+        output, _ = llvm_config_cmd.communicate()
+        output = output.decode(encoding)
+        lines = output.split('\n')
         for (feature_line, (_, patterns)) in zip(lines, features):
             # We should have either a callable or a dictionary.  If it's a
             # dictionary, grep each key against the output and use the value if
@@ -165,85 +163,3 @@ def feature_config(self, features):
                 for (re_pattern, feature) in patterns.items():
                     if re.search(re_pattern, feature_line):
                         self.config.available_features.add(feature)
-
-
-    # Note that when substituting %clang_cc1 also fill in the include directory of
-    # the builtin headers. Those are part of even a freestanding environment, but
-    # Clang relies on the driver to locate them.
-    def get_clang_builtin_include_dir(self, clang):
-        # FIXME: Rather than just getting the version, we should have clang print
-        # out its resource dir here in an easy to scrape form.
-        clang_dir, _ = self.get_process_output([clang, '-print-file-name=include'])
-
-        if not clang_dir:
-          self.lit_config.fatal("Couldn't find the include dir for Clang ('%s')" % clang)
-
-        clang_dir = clang_dir.strip()
-        if sys.platform in ['win32'] and not self.use_lit_shell:
-            # Don't pass dosish path separator to msys bash.exe.
-            clang_dir = clang_dir.replace('\\', '/')
-        # Ensure the result is an ascii string, across Python2.5+ - Python3.
-        return clang_dir
-
-    def make_itanium_abi_triple(self, triple):
-        m = re.match(r'(\w+)-(\w+)-(\w+)', triple)
-        if not m:
-          self.lit_config.fatal("Could not turn '%s' into Itanium ABI triple" % triple)
-        if m.group(3).lower() != 'win32':
-          # All non-win32 triples use the Itanium ABI.
-          return triple
-        return m.group(1) + '-' + m.group(2) + '-mingw32'
-
-    def make_msabi_triple(self, triple):
-        m = re.match(r'(\w+)-(\w+)-(\w+)', triple)
-        if not m:
-          self.lit_config.fatal("Could not turn '%s' into MS ABI triple" % triple)
-        isa = m.group(1).lower()
-        vendor = m.group(2).lower()
-        os = m.group(3).lower()
-        if os == 'win32':
-          # If the OS is win32, we're done.
-          return triple
-        if isa.startswith('x86') or isa == 'amd64' or re.match(r'i\d86', isa):
-          # For x86 ISAs, adjust the OS.
-          return isa + '-' + vendor + '-win32'
-        # -win32 is not supported for non-x86 targets; use a default.
-        return 'i686-pc-win32'
-
-    def add_tool_substitutions(self, tools, search_dirs, warn_missing = True):
-        if lit.util.is_string(search_dirs):
-            search_dirs = [search_dirs]
-
-        search_dirs = os.pathsep.join(search_dirs)
-        for tool in tools:
-            # Extract the tool name from the pattern.  This relies on the tool
-            # name being surrounded by \b word match operators.  If the
-            # pattern starts with "| ", include it in the string to be
-            # substituted.
-            if lit.util.is_string(tool):
-                tool = lit.util.make_word_regex(tool)
-            else:
-                tool = str(tool)
-
-            tool_match = re.match(r"^(\\)?((\| )?)\W+b([0-9A-Za-z-_\.]+)\\b\W*$",
-                                  tool)
-            if not tool_match:
-                continue
-
-            tool_pipe = tool_match.group(2)
-            tool_name = tool_match.group(4)
-            tool_path = lit.util.which(tool_name, search_dirs)
-            if not tool_path:
-                if warn_missing:
-                    # Warn, but still provide a substitution.
-                    self.lit_config.note('Did not find ' + tool_name + ' in %s' % search_dirs)
-                tool_path = self.config.llvm_tools_dir + '/' + tool_name
-
-            if tool_name == 'llc' and os.environ.get('LLVM_ENABLE_MACHINE_VERIFIER') == '1':
-                tool_path += ' -verify-machineinstrs'
-            if tool_name == 'llvm-go':
-                exe = getattr(self.config, 'go_executable', None)
-                if exe:
-                    tool_path += " go=" + exe
-
-            self.config.substitutions.append((tool, tool_pipe + tool_path))

utils/lit/lit/util.py

@@ -36,8 +36,6 @@ def pythonize_bool(value):
             return False
     raise ValueError('"{}" is not a valid boolean'.format(value))
 
-def make_word_regex(word):
-    return r'\b' + word + r'\b'
 
 def to_bytes(s):
     """Return the parameter as type 'bytes', possibly encoding it.