bpo-12486: Document tokenize.generate_tokens() as public API (#6957)
* Document tokenize.generate_tokens()
* Add news file
* Add test for generate_tokens
* Document behaviour around ENCODING token
* Add generate_tokens to __all__
diff --git a/Lib/test/test_tokenize.py b/Lib/test/test_tokenize.py
index 3520a67..93e40de 100644
--- a/Lib/test/test_tokenize.py
+++ b/Lib/test/test_tokenize.py
@@ -1,8 +1,8 @@
from test import support
from tokenize import (tokenize, _tokenize, untokenize, NUMBER, NAME, OP,
STRING, ENDMARKER, ENCODING, tok_name, detect_encoding,
- open as tokenize_open, Untokenizer)
-from io import BytesIO
+ open as tokenize_open, Untokenizer, generate_tokens)
+from io import BytesIO, StringIO
import unittest
from unittest import TestCase, mock
from test.test_grammar import (VALID_UNDERSCORE_LITERALS,
@@ -919,6 +919,19 @@
DEDENT '' (7, 0) (7, 0)
""")
+class GenerateTokensTest(TokenizeTest):
+ def check_tokenize(self, s, expected):
+ # Format the tokens in s in a table format.
+ # The ENDMARKER is omitted.
+ result = []
+ f = StringIO(s)
+ for type, token, start, end, line in generate_tokens(f.readline):
+ if type == ENDMARKER:
+ break
+ type = tok_name[type]
+ result.append(f" {type:10} {token!r:13} {start} {end}")
+ self.assertEqual(result, expected.rstrip().splitlines())
+
def decistmt(s):
result = []
diff --git a/Lib/tokenize.py b/Lib/tokenize.py
index 40e6a8b..c78d9f7 100644
--- a/Lib/tokenize.py
+++ b/Lib/tokenize.py
@@ -37,7 +37,7 @@
blank_re = re.compile(br'^[ \t\f]*(?:[#\r\n]|$)', re.ASCII)
import token
-__all__ = token.__all__ + ["tokenize", "detect_encoding",
+__all__ = token.__all__ + ["tokenize", "generate_tokens", "detect_encoding",
"untokenize", "TokenInfo"]
del token
@@ -653,9 +653,12 @@
yield TokenInfo(ENDMARKER, '', (lnum, 0), (lnum, 0), '')
-# An undocumented, backwards compatible, API for all the places in the standard
-# library that expect to be able to use tokenize with strings
def generate_tokens(readline):
+ """Tokenize a source reading Python code as unicode strings.
+
+ This has the same API as tokenize(), except that it expects the *readline*
+ callable to return str objects instead of bytes.
+ """
return _tokenize(readline, None)
def main():