added even more type hints

Author: manfred-kaiser

sifter/grammar/lexer.py

@@ -1,13 +1,22 @@
 # Parser based on RFC 5228, especially the grammar as defined in section 8. All
 # references are to sections in RFC 5228 unless stated otherwise.
 
+from typing import (
+    TYPE_CHECKING,
+    Any,
+    Optional
+)
+
 import math
 import ply.lex  # type: ignore
 
+if TYPE_CHECKING:
+    from ply.lex import Lexer, LexToken
+
 __all__ = ('lexer', 'tokens',)
 
 
-def lexer(**kwargs):
+def lexer(**kwargs: Any) -> 'Lexer':
     return ply.lex.lex(**kwargs)
 
 
@@ -22,22 +31,23 @@ def lexer(**kwargs):
 
 
 # section 2.3
-def t_HASH_COMMENT(t):
+def t_HASH_COMMENT(t: 'LexToken') -> Optional['LexToken']:
     r'\#.*\r\n'
     t.lexer.lineno += 1
+    return None
 
 
 # section 2.3
-def t_BRACKET_COMMENT(t):
+def t_BRACKET_COMMENT(t: 'LexToken') -> Optional['LexToken']:
     r'/\*.*\*/'
     # TODO: Bracketed comments begin with the token "/*" and end with "*/"
     # outside of a string.  Bracketed comments may span multiple lines.
     # Bracketed comments do not nest.
-    pass
+    return None
 
 
 # section 2.4.2
-def t_MULTILINE_STRING(t):
+def t_MULTILINE_STRING(t: 'LexToken') -> Optional['LexToken']:
     r'"@@@@@@@@@@@@@@@"'
     # TODO: For entering larger amounts of text, such as an email message,
     # a multi-line form is allowed.  It starts with the keyword "text:",
@@ -52,11 +62,11 @@ def t_MULTILINE_STRING(t):
     # that is, ".foo" is interpreted as ".foo".  However, because this is
     # potentially ambiguous, scripts SHOULD be properly dot-stuffed so such
     # lines do not appear.
-    pass
+    return None
 
 
 # section 2.4.2
-def t_QUOTED_STRING(t):
+def t_QUOTED_STRING(t: 'LexToken') -> Optional['LexToken']:
     r'"([^"\\]|\\["\\])*"'
     # TODO: Add support for:
     # - An undefined escape sequence (such as "\a" in a context where "a"
@@ -70,20 +80,20 @@ def t_QUOTED_STRING(t):
     return t
 
 
-def t_TAG(t):
+def t_TAG(t: 'LexToken') -> Optional['LexToken']:
     r':[a-zA-Z_][a-zA-Z0-9_]*'
     t.value = t.value[1:].upper()
     return t
 
 
-def t_IDENTIFIER(t):
+def t_IDENTIFIER(t: 'LexToken') -> Optional['LexToken']:
     r'[a-zA-Z_][a-zA-Z0-9_]*'
     t.value = t.value.upper()
     return t
 
 
 # section 2.4.1
-def t_NUMBER(t):
+def t_NUMBER(t: 'LexToken') -> Optional['LexToken']:
     r'[0-9]+[KkMmGg]?'
     exponents = {
         'G': 30, 'g': 30,
@@ -97,13 +107,15 @@ def t_NUMBER(t):
     return t
 
 
-def t_newline(t):
+def t_newline(t: 'LexToken') -> Optional['LexToken']:
     r'(\r\n)+'
     t.lexer.lineno += t.value.count('\n')
+    return None
 
 
-def t_error(t):
+def t_error(t: 'LexToken') -> Optional['LexToken']:
     t.lexer.skip(1)
+    return None
 
 
 if __name__ == '__main__':

sifter/parser.py

@@ -1,10 +1,16 @@
+from typing import (
+    cast,
+    TextIO
+)
+
 import sifter.extensions.builtin  # needed by the lexer
 import sifter.extensions.regex  # needed by the lexer
 from sifter.grammar import grammar
 from sifter.grammar import lexer
+from sifter.grammar.command_list import CommandList
 
 __all__ = ('parse_file',)
 
 
-def parse_file(filehandle):
-    return grammar.parser().parse(filehandle.read(), lexer=lexer.lexer())
+def parse_file(filehandle: TextIO) -> CommandList:
+    return cast(CommandList, grammar.parser().parse(filehandle.read(), lexer=lexer.lexer()))