jbcoe retitled this revision from "Incomplete support for Python 3 in libclang 
python bindings" to "Support for Python 3 in libclang python bindings".
jbcoe updated the summary for this revision.
jbcoe updated this revision to Diff 76338.
jbcoe added a comment.

Python bindings tests now pass in Python 3.


Repository:
  rL LLVM

https://reviews.llvm.org/D26082

Files:
  bindings/python/clang/cindex.py
  bindings/python/tests/cindex/test_comment.py
  bindings/python/tests/cindex/test_translation_unit.py

Index: bindings/python/tests/cindex/test_translation_unit.py
===================================================================
--- bindings/python/tests/cindex/test_translation_unit.py
+++ bindings/python/tests/cindex/test_translation_unit.py
@@ -59,9 +59,13 @@
     assert spellings[-1] == 'y'
 
 def test_unsaved_files_2():
-    import StringIO
+    try:
+        from StringIO import StringIO
+    except:
+        from io import StringIO
+
     tu = TranslationUnit.from_source('fake.c', unsaved_files = [
-            ('fake.c', StringIO.StringIO('int x;'))])
+            ('fake.c', StringIO('int x;'))])
     spellings = [c.spelling for c in tu.cursor.get_children()]
     assert spellings[-1] == 'x'
 
Index: bindings/python/tests/cindex/test_comment.py
===================================================================
--- bindings/python/tests/cindex/test_comment.py
+++ bindings/python/tests/cindex/test_comment.py
@@ -34,6 +34,12 @@
     f = get_cursor(tu, 'f')
     raw = f.raw_comment
     brief = f.brief_comment
+
+    print(raw)
+    print(type(raw))
+    print(brief)
+    print(type(brief))
+
     assert raw is None
     assert brief is None
 
Index: bindings/python/clang/cindex.py
===================================================================
--- bindings/python/clang/cindex.py
+++ bindings/python/clang/cindex.py
@@ -73,6 +73,30 @@
 # this by marshalling object arguments as void**.
 c_object_p = POINTER(c_void_p)
 
+# Python 3 strings are unicode, translate them to/from utf8 for C-interop
+if type(u"") == str:
+    class c_string_p(c_char_p):
+        def __init__(self, p=None):
+            if type(p) == str:
+                p = p.encode("utf8")
+            super(c_char_p, self).__init__(p)
+
+        def __str__(self):
+            return str(self.value)
+
+        @property
+        def value(self):
+            if super(c_char_p, self).value is None:
+                return None
+            return super(c_char_p, self).value.decode("utf8")
+
+        @classmethod
+        def from_param(cls, param):
+                return cls(param)
+else:
+    c_string_p = c_char_p
+
+
 callbacks = {}
 
 ### Exception Classes ###
@@ -147,7 +171,7 @@
 class _CXString(Structure):
     """Helper for transforming CXString results."""
 
-    _fields_ = [("spelling", c_char_p), ("free", c_int)]
+    _fields_ = [("spelling", c_string_p), ("free", c_int)]
 
     def __del__(self):
         conf.lib.clang_disposeString(self)
@@ -329,7 +353,7 @@
 
     @property
     def spelling(self):
-        return conf.lib.clang_getDiagnosticSpelling(self)
+        return str(conf.lib.clang_getDiagnosticSpelling(self))
 
     @property
     def ranges(self):
@@ -358,8 +382,8 @@
 
             def __getitem__(self, key):
                 range = SourceRange()
-                value = conf.lib.clang_getDiagnosticFixIt(self.diag, key,
-                        byref(range))
+                value = str(conf.lib.clang_getDiagnosticFixIt(self.diag, key,
+                        byref(range)))
                 if len(value) == 0:
                     raise IndexError
 
@@ -392,20 +416,20 @@
     @property
     def category_name(self):
         """The string name of the category for this diagnostic."""
-        return conf.lib.clang_getDiagnosticCategoryText(self)
+        return str(conf.lib.clang_getDiagnosticCategoryText(self))
 
     @property
     def option(self):
         """The command-line option that enables this diagnostic."""
-        return conf.lib.clang_getDiagnosticOption(self, None)
+        return str(conf.lib.clang_getDiagnosticOption(self, None))
 
     @property
     def disable_option(self):
         """The command-line option that disables this diagnostic."""
         disable = _CXString()
         conf.lib.clang_getDiagnosticOption(self, byref(disable))
 
-        return conf.lib.clang_getCString(disable)
+        return str(conf.lib.clang_getCString(disable))
 
     def format(self, options=None):
         """
@@ -491,7 +515,7 @@
 
         token_group = TokenGroup(tu, tokens_memory, tokens_count)
 
-        for i in xrange(0, count):
+        for i in range(0, count):
             token = Token()
             token.int_data = tokens_array[i].int_data
             token.ptr_data = tokens_array[i].ptr_data
@@ -554,8 +578,8 @@
         if value >= len(self.__class__._kinds):
             self.__class__._kinds += [None] * (value - len(self.__class__._kinds) + 1)
         if self.__class__._kinds[value] is not None:
-            raise ValueError,'{0} value {1} already loaded'.format(
-                str(self.__class__), value)
+            raise ValueError('{0} value {1} already loaded'.format(
+                str(self.__class__), value))
         self.value = value
         self.__class__._kinds[value] = self
         self.__class__._name_map = None
@@ -572,12 +596,12 @@
             for key, value in self.__class__.__dict__.items():
                 if isinstance(value, self.__class__):
                     self._name_map[value] = key
-        return self._name_map[self]
+        return str(self._name_map[self])
 
     @classmethod
     def from_id(cls, id):
         if id >= len(cls._kinds) or cls._kinds[id] is None:
-            raise ValueError,'Unknown template argument kind %d' % id
+            raise ValueError('Unknown template argument kind %d' % id)
         return cls._kinds[id]
 
     def __repr__(self):
@@ -596,7 +620,7 @@
     @staticmethod
     def get_all_kinds():
         """Return all CursorKind enumeration instances."""
-        return filter(None, CursorKind._kinds)
+        return [x for x in CursorKind._kinds if x]
 
     def is_declaration(self):
         """Test if this is a declaration kind."""
@@ -1427,9 +1451,9 @@
     def spelling(self):
         """Return the spelling of the entity pointed at by the cursor."""
         if not hasattr(self, '_spelling'):
-            self._spelling = conf.lib.clang_getCursorSpelling(self)
+            self._spelling = str(conf.lib.clang_getCursorSpelling(self))
 
-        return self._spelling
+        return str(self._spelling)
 
     @property
     def displayname(self):
@@ -1441,15 +1465,15 @@
         arguments of a class template specialization.
         """
         if not hasattr(self, '_displayname'):
-            self._displayname = conf.lib.clang_getCursorDisplayName(self)
+            self._displayname = str(conf.lib.clang_getCursorDisplayName(self))
 
         return self._displayname
 
     @property
     def mangled_name(self):
         """Return the mangled name for the entity referenced by this cursor."""
         if not hasattr(self, '_mangled_name'):
-            self._mangled_name = conf.lib.clang_Cursor_getMangling(self)
+            self._mangled_name = str(conf.lib.clang_Cursor_getMangling(self))
 
         return self._mangled_name
 
@@ -1588,7 +1612,7 @@
             self._objc_type_encoding = \
               conf.lib.clang_getDeclObjCTypeEncoding(self)
 
-        return self._objc_type_encoding
+        return str(self._objc_type_encoding)
 
     @property
     def hash(self):
@@ -1635,12 +1659,18 @@
     @property
     def brief_comment(self):
         """Returns the brief comment text associated with that Cursor"""
-        return conf.lib.clang_Cursor_getBriefCommentText(self)
+        r = conf.lib.clang_Cursor_getBriefCommentText(self)
+        if not r:
+            return None    
+        return str(r)
 
     @property
     def raw_comment(self):
         """Returns the raw comment text associated with that Cursor"""
-        return conf.lib.clang_Cursor_getRawCommentText(self)
+        r = conf.lib.clang_Cursor_getRawCommentText(self)
+        if not r:
+            return None
+        return str(r)
 
     def get_arguments(self):
         """Return an iterator for accessing the arguments of this cursor."""
@@ -1775,7 +1805,7 @@
         if value >= len(StorageClass._kinds):
             StorageClass._kinds += [None] * (value - len(StorageClass._kinds) + 1)
         if StorageClass._kinds[value] is not None:
-            raise ValueError,'StorageClass already loaded'
+            raise ValueError('StorageClass already loaded')
         self.value = value
         StorageClass._kinds[value] = self
         StorageClass._name_map = None
@@ -1796,7 +1826,7 @@
     @staticmethod
     def from_id(id):
         if id >= len(StorageClass._kinds) or not StorageClass._kinds[id]:
-            raise ValueError,'Unknown storage class %d' % id
+            raise ValueError('Unknown storage class %d' % id)
         return StorageClass._kinds[id]
 
     def __repr__(self):
@@ -1849,7 +1879,7 @@
     @property
     def spelling(self):
         """Retrieve the spelling of this TypeKind."""
-        return conf.lib.clang_getTypeKindSpelling(self.value)
+        return str(conf.lib.clang_getTypeKindSpelling(self.value))
 
     def __repr__(self):
         return 'TypeKind.%s' % (self.name,)
@@ -2125,7 +2155,7 @@
         """
         Retrieve the offset of a field in the record.
         """
-        return conf.lib.clang_Type_getOffsetOf(self, c_char_p(fieldname))
+        return conf.lib.clang_Type_getOffsetOf(self, fieldname)
 
     def get_ref_qualifier(self):
         """
@@ -2152,7 +2182,7 @@
     @property
     def spelling(self):
         """Retrieve the spelling of this Type."""
-        return conf.lib.clang_getTypeSpelling(self)
+        return str(conf.lib.clang_getTypeSpelling(self))
 
     def __eq__(self, other):
         if type(other) != type(self):
@@ -2184,7 +2214,7 @@
 
 class _CXUnsavedFile(Structure):
     """Helper for passing unsaved file arguments."""
-    _fields_ = [("name", c_char_p), ("contents", c_char_p), ('length', c_ulong)]
+    _fields_ = [("name", c_string_p), ("contents", c_string_p), ('length', c_ulong)]
 
 # Functions calls through the python interface are rather slow. Fortunately,
 # for most symboles, we do not need to perform a function call. Their spelling
@@ -2230,7 +2260,7 @@
         self.__kindNumberCache = -1
 
     def __repr__(self):
-        return "{'" + self.spelling + "', " + str(self.kind) + "}"
+        return "{'" + str(self.spelling) + "', " + str(self.kind) + "}"
 
     @CachedProperty
     def spelling(self):
@@ -2338,6 +2368,7 @@
             return conf.lib.clang_getCompletionBriefComment(self.obj)
         return _CXString()
 
+
     def __repr__(self):
         return " | ".join([str(a) for a in self]) \
                + " || Priority: " + str(self.priority) \
@@ -2539,17 +2570,19 @@
 
         args_array = None
         if len(args) > 0:
-            args_array = (c_char_p * len(args))(* args)
+            args_array = (c_string_p * len(args))()
+            for i,a in enumerate(args):
+                args_array[i] = c_string_p(a)
 
         unsaved_array = None
         if len(unsaved_files) > 0:
             unsaved_array = (_CXUnsavedFile * len(unsaved_files))()
             for i, (name, contents) in enumerate(unsaved_files):
                 if hasattr(contents, "read"):
                     contents = contents.read()
 
-                unsaved_array[i].name = name
-                unsaved_array[i].contents = contents
+                unsaved_array[i].name = c_string_p(name)
+                unsaved_array[i].contents = c_string_p(contents)
                 unsaved_array[i].length = len(contents)
 
         ptr = conf.lib.clang_parseTranslationUnit(index, filename, args_array,
@@ -2604,7 +2637,7 @@
     @property
     def spelling(self):
         """Get the original translation unit source file name."""
-        return conf.lib.clang_getTranslationUnitSpelling(self)
+        return str(conf.lib.clang_getTranslationUnitSpelling(self))
 
     def get_includes(self):
         """
@@ -2727,9 +2760,9 @@
                     # FIXME: It would be great to support an efficient version
                     # of this, one day.
                     value = value.read()
-                    print value
+                    print(value)
                 if not isinstance(value, str):
-                    raise TypeError,'Unexpected unsaved file contents.'
+                    raise TypeError('Unexpected unsaved file contents.')
                 unsaved_files_array[i].name = name
                 unsaved_files_array[i].contents = value
                 unsaved_files_array[i].length = len(value)
@@ -2791,11 +2824,11 @@
                     # FIXME: It would be great to support an efficient version
                     # of this, one day.
                     value = value.read()
-                    print value
+                    print(value)
                 if not isinstance(value, str):
-                    raise TypeError,'Unexpected unsaved file contents.'
-                unsaved_files_array[i].name = name
-                unsaved_files_array[i].contents = value
+                    raise TypeError('Unexpected unsaved file contents.')
+                unsaved_files_array[i].name = c_string_p(name)
+                unsaved_files_array[i].contents = c_string_p(value)
                 unsaved_files_array[i].length = len(value)
         ptr = conf.lib.clang_codeCompleteAt(self, path, line, column,
                 unsaved_files_array, len(unsaved_files), options)
@@ -2830,15 +2863,15 @@
     @property
     def name(self):
         """Return the complete file and path name of the file."""
-        return conf.lib.clang_getCString(conf.lib.clang_getFileName(self))
+        return str(conf.lib.clang_getCString(conf.lib.clang_getFileName(self)))
 
     @property
     def time(self):
         """Return the last modification time of the file."""
         return conf.lib.clang_getFileTime(self)
 
     def __str__(self):
-        return self.name
+        return str(self.name)
 
     def __repr__(self):
         return "<File: %s>" % (self.name)
@@ -2907,12 +2940,12 @@
     @property
     def directory(self):
         """Get the working directory for this CompileCommand"""
-        return conf.lib.clang_CompileCommand_getDirectory(self.cmd)
+        return str(conf.lib.clang_CompileCommand_getDirectory(self.cmd))
 
     @property
     def filename(self):
         """Get the working filename for this CompileCommand"""
-        return conf.lib.clang_CompileCommand_getFilename(self.cmd)
+        return str(conf.lib.clang_CompileCommand_getFilename(self.cmd))
 
     @property
     def arguments(self):
@@ -2923,8 +2956,8 @@
         Invariant : the first argument is the compiler executable
         """
         length = conf.lib.clang_CompileCommand_getNumArgs(self.cmd)
-        for i in xrange(length):
-            yield conf.lib.clang_CompileCommand_getArg(self.cmd, i)
+        for i in range(length):
+            yield str(conf.lib.clang_CompileCommand_getArg(self.cmd, i))
 
 class CompileCommands(object):
     """
@@ -3018,7 +3051,7 @@
 
         This is the textual representation of the token in source.
         """
-        return conf.lib.clang_getTokenSpelling(self._tu, self)
+        return str(conf.lib.clang_getTokenSpelling(self._tu, self))
 
     @property
     def kind(self):
@@ -3061,7 +3094,7 @@
    [c_object_p]),
 
   ("clang_CompilationDatabase_fromDirectory",
-   [c_char_p, POINTER(c_uint)],
+   [c_string_p, POINTER(c_uint)],
    c_object_p,
    CompilationDatabase.from_result),
 
@@ -3071,7 +3104,7 @@
    CompileCommands.from_result),
 
   ("clang_CompilationDatabase_getCompileCommands",
-   [c_object_p, c_char_p],
+   [c_object_p, c_string_p],
    c_object_p,
    CompileCommands.from_result),
 
@@ -3106,7 +3139,7 @@
    c_uint),
 
   ("clang_codeCompleteAt",
-   [TranslationUnit, c_char_p, c_int, c_int, c_void_p, c_int, c_int],
+   [TranslationUnit, c_string_p, c_int, c_int, c_void_p, c_int, c_int],
    POINTER(CCRStructure)),
 
   ("clang_codeCompleteGetDiagnostic",
@@ -3122,7 +3155,7 @@
    c_object_p),
 
   ("clang_createTranslationUnit",
-   [Index, c_char_p],
+   [Index, c_string_p],
    c_object_p),
 
   ("clang_CXXConstructor_isConvertingConstructor",
@@ -3272,7 +3305,7 @@
 
   ("clang_getCString",
    [_CXString],
-   c_char_p),
+   c_string_p),
 
   ("clang_getCursor",
    [TranslationUnit, SourceLocation],
@@ -3419,7 +3452,7 @@
    Type.from_result),
 
   ("clang_getFile",
-   [TranslationUnit, c_char_p],
+   [TranslationUnit, c_string_p],
    c_object_p),
 
   ("clang_getFileName",
@@ -3548,7 +3581,7 @@
 
   ("clang_getTUResourceUsageName",
    [c_uint],
-   c_char_p),
+   c_string_p),
 
   ("clang_getTypeDeclaration",
    [Type],
@@ -3643,15 +3676,15 @@
    bool),
 
   ("clang_parseTranslationUnit",
-   [Index, c_char_p, c_void_p, c_int, c_void_p, c_int, c_int],
+   [Index, c_string_p, c_void_p, c_int, c_void_p, c_int, c_int],
    c_object_p),
 
   ("clang_reparseTranslationUnit",
    [TranslationUnit, c_int, c_void_p, c_int],
    c_int),
 
   ("clang_saveTranslationUnit",
-   [TranslationUnit, c_char_p, c_uint],
+   [TranslationUnit, c_string_p, c_uint],
    c_int),
 
   ("clang_tokenize",
@@ -3723,7 +3756,7 @@
    Type.from_result),
 
   ("clang_Type_getOffsetOf",
-   [Type, c_char_p],
+   [Type, c_string_p],
    c_longlong),
 
   ("clang_Type_getSizeOf",
@@ -3782,7 +3815,8 @@
     def register(item):
         return register_function(lib, item, ignore_errors)
 
-    map(register, functionList)
+    for f in functionList:
+        register(f)
 
 class Config:
     library_path = None
_______________________________________________
cfe-commits mailing list
cfe-commits@lists.llvm.org
http://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits

Reply via email to