17.12

2019-12-17 14:09:10 +01:00
parent 66e908fc8a
commit 4791d00a43
2122 changed files with 423791 additions and 0 deletions
@@ -0,0 +1,105 @@
+#------------------------------------------------------------------------------
+# pycparser: ast_transforms.py
+#
+# Some utilities used by the parser to create a friendlier AST.
+#
+# Eli Bendersky [https://eli.thegreenplace.net/]
+# License: BSD
+#------------------------------------------------------------------------------
+
+from . import c_ast
+
+
+def fix_switch_cases(switch_node):
+    """ The 'case' statements in a 'switch' come out of parsing with one
+        child node, so subsequent statements are just tucked to the parent
+        Compound. Additionally, consecutive (fall-through) case statements
+        come out messy. This is a peculiarity of the C grammar. The following:
+
+            switch (myvar) {
+                case 10:
+                    k = 10;
+                    p = k + 1;
+                    return 10;
+                case 20:
+                case 30:
+                    return 20;
+                default:
+                    break;
+            }
+
+        Creates this tree (pseudo-dump):
+
+            Switch
+                ID: myvar
+                Compound:
+                    Case 10:
+                        k = 10
+                    p = k + 1
+                    return 10
+                    Case 20:
+                        Case 30:
+                            return 20
+                    Default:
+                        break
+
+        The goal of this transform is to fix this mess, turning it into the
+        following:
+
+            Switch
+                ID: myvar
+                Compound:
+                    Case 10:
+                        k = 10
+                        p = k + 1
+                        return 10
+                    Case 20:
+                    Case 30:
+                        return 20
+                    Default:
+                        break
+
+        A fixed AST node is returned. The argument may be modified.
+    """
+    assert isinstance(switch_node, c_ast.Switch)
+    if not isinstance(switch_node.stmt, c_ast.Compound):
+        return switch_node
+
+    # The new Compound child for the Switch, which will collect children in the
+    # correct order
+    new_compound = c_ast.Compound([], switch_node.stmt.coord)
+
+    # The last Case/Default node
+    last_case = None
+
+    # Goes over the children of the Compound below the Switch, adding them
+    # either directly below new_compound or below the last Case as appropriate
+    for child in switch_node.stmt.block_items:
+        if isinstance(child, (c_ast.Case, c_ast.Default)):
+            # If it's a Case/Default:
+            # 1. Add it to the Compound and mark as "last case"
+            # 2. If its immediate child is also a Case or Default, promote it
+            #    to a sibling.
+            new_compound.block_items.append(child)
+            _extract_nested_case(child, new_compound.block_items)
+            last_case = new_compound.block_items[-1]
+        else:
+            # Other statements are added as children to the last case, if it
+            # exists.
+            if last_case is None:
+                new_compound.block_items.append(child)
+            else:
+                last_case.stmts.append(child)
+
+    switch_node.stmt = new_compound
+    return switch_node
+
+
+def _extract_nested_case(case_node, stmts_list):
+    """ Recursively extract consecutive Case statements that are made nested
+        by the parser and add them to the stmts_list.
+    """
+    if isinstance(case_node.stmts[0], (c_ast.Case, c_ast.Default)):
+        stmts_list.append(case_node.stmts.pop())
+        _extract_nested_case(stmts_list[-1], stmts_list)
+
@@ -0,0 +1,133 @@
+# ----------------------------------------------------------------------
+# ctokens.py
+#
+# Token specifications for symbols in ANSI C and C++.  This file is
+# meant to be used as a library in other tokenizers.
+# ----------------------------------------------------------------------
+
+# Reserved words
+
+tokens = [
+    # Literals (identifier, integer constant, float constant, string constant, char const)
+    'ID', 'TYPEID', 'INTEGER', 'FLOAT', 'STRING', 'CHARACTER',
+
+    # Operators (+,-,*,/,%,|,&,~,^,<<,>>, ||, &&, !, <, <=, >, >=, ==, !=)
+    'PLUS', 'MINUS', 'TIMES', 'DIVIDE', 'MODULO',
+    'OR', 'AND', 'NOT', 'XOR', 'LSHIFT', 'RSHIFT',
+    'LOR', 'LAND', 'LNOT',
+    'LT', 'LE', 'GT', 'GE', 'EQ', 'NE',
+    
+    # Assignment (=, *=, /=, %=, +=, -=, <<=, >>=, &=, ^=, |=)
+    'EQUALS', 'TIMESEQUAL', 'DIVEQUAL', 'MODEQUAL', 'PLUSEQUAL', 'MINUSEQUAL',
+    'LSHIFTEQUAL','RSHIFTEQUAL', 'ANDEQUAL', 'XOREQUAL', 'OREQUAL',
+
+    # Increment/decrement (++,--)
+    'INCREMENT', 'DECREMENT',
+
+    # Structure dereference (->)
+    'ARROW',
+
+    # Ternary operator (?)
+    'TERNARY',
+    
+    # Delimeters ( ) [ ] { } , . ; :
+    'LPAREN', 'RPAREN',
+    'LBRACKET', 'RBRACKET',
+    'LBRACE', 'RBRACE',
+    'COMMA', 'PERIOD', 'SEMI', 'COLON',
+
+    # Ellipsis (...)
+    'ELLIPSIS',
+]
+    
+# Operators
+t_PLUS             = r'\+'
+t_MINUS            = r'-'
+t_TIMES            = r'\*'
+t_DIVIDE           = r'/'
+t_MODULO           = r'%'
+t_OR               = r'\|'
+t_AND              = r'&'
+t_NOT              = r'~'
+t_XOR              = r'\^'
+t_LSHIFT           = r'<<'
+t_RSHIFT           = r'>>'
+t_LOR              = r'\|\|'
+t_LAND             = r'&&'
+t_LNOT             = r'!'
+t_LT               = r'<'
+t_GT               = r'>'
+t_LE               = r'<='
+t_GE               = r'>='
+t_EQ               = r'=='
+t_NE               = r'!='
+
+# Assignment operators
+
+t_EQUALS           = r'='
+t_TIMESEQUAL       = r'\*='
+t_DIVEQUAL         = r'/='
+t_MODEQUAL         = r'%='
+t_PLUSEQUAL        = r'\+='
+t_MINUSEQUAL       = r'-='
+t_LSHIFTEQUAL      = r'<<='
+t_RSHIFTEQUAL      = r'>>='
+t_ANDEQUAL         = r'&='
+t_OREQUAL          = r'\|='
+t_XOREQUAL         = r'\^='
+
+# Increment/decrement
+t_INCREMENT        = r'\+\+'
+t_DECREMENT        = r'--'
+
+# ->
+t_ARROW            = r'->'
+
+# ?
+t_TERNARY          = r'\?'
+
+# Delimeters
+t_LPAREN           = r'\('
+t_RPAREN           = r'\)'
+t_LBRACKET         = r'\['
+t_RBRACKET         = r'\]'
+t_LBRACE           = r'\{'
+t_RBRACE           = r'\}'
+t_COMMA            = r','
+t_PERIOD           = r'\.'
+t_SEMI             = r';'
+t_COLON            = r':'
+t_ELLIPSIS         = r'\.\.\.'
+
+# Identifiers
+t_ID = r'[A-Za-z_][A-Za-z0-9_]*'
+
+# Integer literal
+t_INTEGER = r'\d+([uU]|[lL]|[uU][lL]|[lL][uU])?'
+
+# Floating literal
+t_FLOAT = r'((\d+)(\.\d+)(e(\+|-)?(\d+))? | (\d+)e(\+|-)?(\d+))([lL]|[fF])?'
+
+# String literal
+t_STRING = r'\"([^\\\n]|(\\.))*?\"'
+
+# Character constant 'c' or L'c'
+t_CHARACTER = r'(L)?\'([^\\\n]|(\\.))*?\''
+
+# Comment (C-Style)
+def t_COMMENT(t):
+    r'/\*(.|\n)*?\*/'
+    t.lexer.lineno += t.value.count('\n')
+    return t
+
+# Comment (C++-Style)
+def t_CPPCOMMENT(t):
+    r'//.*\n'
+    t.lexer.lineno += 1
+    return t
+
+
+    
+
+
+