gh-102856: Python tokenizer implementation for PEP 701 (#104323)

This commit replaces the Python implementation of the tokenize module with an implementation
that reuses the real C tokenizer via a private extension module. The tokenize module now implements
a compatibility layer that transforms tokens from the C tokenizer into Python tokenize tokens for backward
compatibility.

As the C tokenizer does not emit some tokens that the Python tokenizer provides (such as comments and non-semantic newlines), a new special mode has been added to the C tokenizer mode that currently is only used via
the extension module that exposes it to the Python layer. This new mode forces the C tokenizer to emit these new extra tokens and add the appropriate metadata that is needed to match the old Python implementation.

Co-authored-by: Pablo Galindo <pablogsal@gmail.com>

1 files changed, 10 insertions, 0 deletions

diff --git a/Lib/tabnanny.py b/Lib/tabnanny.py
index 9d2df59..e2ac683 100755
--- a/Lib/tabnanny.py
+++ b/Lib/tabnanny.py
@@ -107,6 +107,10 @@ def check(file):
         errprint("%r: Token Error: %s" % (file, msg))
         return
 
+    except SyntaxError as msg:
+        errprint("%r: Token Error: %s" % (file, msg))
+        return
+
     except IndentationError as msg:
         errprint("%r: Indentation Error: %s" % (file, msg))
         return
@@ -272,6 +276,12 @@ def format_witnesses(w):
     return prefix + " " + ', '.join(firsts)
 
 def process_tokens(tokens):
+    try:
+        _process_tokens(tokens)
+    except TabError as e:
+        raise NannyNag(e.lineno, e.msg, e.text)
+
+def _process_tokens(tokens):
     INDENT = tokenize.INDENT
     DEDENT = tokenize.DEDENT
     NEWLINE = tokenize.NEWLINE