Merge branch 'cycache_directives'

Relevant options/directives must go into the cache fingerprint #2237.

Cython/Build/Dependencies.py

@@ -616,15 +616,28 @@ class DependencyTree(object):
     def newest_dependency(self, filename):
         return max([self.extract_timestamp(f) for f in self.all_dependencies(filename)])
 
-    def transitive_fingerprint(self, filename, extra=None):
+    def transitive_fingerprint(self, filename, module, compilation_options):
+        r"""
+        Return a fingerprint of a cython file that is about to be cythonized.
+
+        Fingerprints are looked up in future compilations. If the fingerprint
+        is found, the cythonization can be skipped. The fingerprint must
+        incorporate everything that has an influence on the generated code.
+        """
         try:
             m = hashlib.md5(__version__.encode('UTF-8'))
             m.update(file_hash(filename).encode('UTF-8'))
             for x in sorted(self.all_dependencies(filename)):
                 if os.path.splitext(x)[1] not in ('.c', '.cpp', '.h'):
                     m.update(file_hash(x).encode('UTF-8'))
-            if extra is not None:
-                m.update(str(extra).encode('UTF-8'))
+            # Include the module attributes that change the compilation result
+            # in the fingerprint. We do not iterate over module.__dict__ and
+            # include almost everything here as users might extend Extension
+            # with arbitrary (random) attributes that would lead to cache
+            # misses.
+            m.update(str((module.language, module.py_limited_api, module.np_pythran)).encode('UTF-8'))
+
+            m.update(compilation_options.get_fingerprint().encode('UTF-8'))
             return m.hexdigest()
         except IOError:
             return None
@@ -881,8 +894,6 @@ def cythonize(module_list, exclude=None, nthreads=0, aliases=None, quiet=False,
     if 'include_path' not in options:
         options['include_path'] = ['.']
     if 'common_utility_include_dir' in options:
-        if options.get('cache'):
-            raise NotImplementedError("common_utility_include_dir does not yet work with caching")
         safe_makedirs(options['common_utility_include_dir'])
 
     pythran_options = None
@@ -973,8 +984,7 @@ def cythonize(module_list, exclude=None, nthreads=0, aliases=None, quiet=False,
                         else:
                             print("Compiling %s because it depends on %s." % (source, dep))
                     if not force and options.cache:
-                        extra = m.language
-                        fingerprint = deps.transitive_fingerprint(source, extra)
+                        fingerprint = deps.transitive_fingerprint(source, m, options)
                     else:
                         fingerprint = None
                     to_compile.append((

Cython/Build/Tests/TestCyCache.py

@@ -84,3 +84,23 @@ class TestCyCache(CythonTest):
         self.fresh_cythonize(a_pyx, cache=self.cache_dir)
         for output in expected:
             self.assertTrue(os.path.exists(output), output)
+
+    def test_options_invalidation(self):
+        hash_pyx = os.path.join(self.src_dir, 'options.pyx')
+        hash_c = hash_pyx[:-len('.pyx')] + '.c'
+
+        open(hash_pyx, 'w').write('pass')
+        self.fresh_cythonize(hash_pyx, cache=self.cache_dir, cplus=False)
+        self.assertEqual(1, len(self.cache_files('options.c*')))
+
+        os.unlink(hash_c)
+        self.fresh_cythonize(hash_pyx, cache=self.cache_dir, cplus=True)
+        self.assertEqual(2, len(self.cache_files('options.c*')))
+
+        os.unlink(hash_c)
+        self.fresh_cythonize(hash_pyx, cache=self.cache_dir, cplus=False, show_version=False)
+        self.assertEqual(2, len(self.cache_files('options.c*')))
+
+        os.unlink(hash_c)
+        self.fresh_cythonize(hash_pyx, cache=self.cache_dir, cplus=False, show_version=True)
+        self.assertEqual(2, len(self.cache_files('options.c*')))

Cython/Compiler/Main.py

@@ -519,29 +519,11 @@ class CompilationSource(object):
 
 
 class CompilationOptions(object):
+    r"""
+    See default_options at the end of this module for a list of all possible
+    options and CmdLine.usage and CmdLine.parse_command_line() for their
+    meaning.
     """
-    Options to the Cython compiler:
-
-    show_version      boolean   Display version number
-    use_listing_file  boolean   Generate a .lis file
-    errors_to_stderr  boolean   Echo errors to stderr when using .lis
-    include_path      [string]  Directories to search for include files
-    output_file       string    Name of generated .c file
-    generate_pxi      boolean   Generate .pxi file for public declarations
-    capi_reexport_cincludes
-                      boolean   Add cincluded headers to any auto-generated
-                                header files.
-    timestamps        boolean   Only compile changed source files.
-    verbose           boolean   Always print source names being compiled
-    compiler_directives  dict   Overrides for pragma options (see Options.py)
-    embedded_metadata    dict   Metadata to embed in the C file as json.
-    evaluate_tree_assertions boolean  Test support: evaluate parse tree assertions
-    language_level    integer   The Python language level: 2 or 3
-    formal_grammar    boolean  Parse the file with the formal grammar
-
-    cplus             boolean   Compile as c++ code
-    """
-
     def __init__(self, defaults=None, **kw):
         self.include_path = []
         if defaults:
@@ -595,6 +577,83 @@ class CompilationOptions(object):
         return Context(self.include_path, self.compiler_directives,
                        self.cplus, self.language_level, options=self)
 
+    def get_fingerprint(self):
+        r"""
+        Return a string that contains all the options that are relevant for cache invalidation.
+        """
+        # Collect only the data that can affect the generated file(s).
+        data = {}
+
+        for key, value in self.__dict__.items():
+            if key in ['show_version', 'errors_to_stderr', 'verbose', 'quiet']:
+                # verbosity flags have no influence on the compilation result
+                continue
+            elif key in ['output_file', 'output_dir']:
+                # ignore the exact name of the output file
+                continue
+            elif key in ['timestamps']:
+                # the cache cares about the content of files, not about the timestamps of sources
+                continue
+            elif key in ['cache']:
+                # hopefully caching has no influence on the compilation result
+                continue
+            elif key in ['compiler_directives']:
+                # directives passed on to the C compiler do not influence the generated C code
+                continue
+            elif key in ['include_path']:
+                # this path changes which headers are tracked as dependencies,
+                # it has no influence on the generated C code
+                continue
+            elif key in ['working_path']:
+                # this path changes where modules and pxd files are found;
+                # their content is part of the fingerprint anyway, their
+                # absolute path does not matter
+                continue
+            elif key in ['create_extension']:
+                # create_extension() has already mangled the options, e.g.,
+                # embedded_metadata, when the fingerprint is computed so we
+                # ignore it here.
+                continue
+            elif key in ['build_dir']:
+                # the (temporary) directory where we collect dependencies
+                # has no influence on the C output
+                continue
+            elif key in ['use_listing_file', 'generate_pxi', 'annotate', 'annotate_coverage_xml']:
+                # all output files are contained in the cache so the types of
+                # files generated must be part of the fingerprint
+                data[key] = value
+            elif key in ['formal_grammar', 'evaluate_tree_assertions']:
+                # these bits can change whether compilation to C passes/fails
+                data[key] = value
+            elif key in ['embedded_metadata', 'emit_linenums', 'c_line_in_traceback', 'gdb_debug', 'relative_path_in_code_position_comments']:
+                # the generated code contains additional bits when these are set
+                data[key] = value
+            elif key in ['cplus', 'language_level', 'compile_time_env', 'np_pythran']:
+                # assorted bits that, e.g., influence the parser
+                data[key] = value
+            elif key == ['capi_reexport_cincludes']:
+                if self.capi_reexport_cincludes:
+                    # our caching implementation does not yet include fingerprints of all the header files
+                    raise NotImplementedError('capi_reexport_cincludes is not compatible with Cython caching')
+            elif key == ['common_utility_include_dir']:
+                if self.common_utility_include_dir:
+                    raise NotImplementedError('common_utility_include_dir is not compatible with Cython caching yet')
+            else:
+                # any unexpected option should go into the fingerprint; it's better
+                # to recompile than to return incorrect results from the cache.
+                data[key] = value
+
+        def to_fingerprint(item):
+            r"""
+            Recursively turn item into a string, turning dicts into lists with
+            deterministic ordering.
+            """
+            if isinstance(item, dict):
+                item = sorted([(repr(key), to_fingerprint(value)) for key, value in item.items()])
+            return repr(item)
+
+        return to_fingerprint(data)
+
 
 class CompilationResult(object):
     """