[3.12] gh-105069: Add a readline-like callable to the tokenizer to consume input iteratively (GH-105070) (#105119)

gh-105069: Add a readline-like callable to the tokenizer to consume input iteratively (GH-105070)
(cherry picked from commit 9216e69)

Co-authored-by: Pablo Galindo Salgado <[email protected]>

Author: miss-islington

Lib/inspect.py

@@ -2203,7 +2203,7 @@ def _signature_strip_non_python_syntax(signature):
         add(string)
         if (string == ','):
             add(' ')
-    clean_signature = ''.join(text).strip()
+    clean_signature = ''.join(text).strip().replace("\n", "")
     return clean_signature, self_parameter
 
 

Lib/test/test_tokenize.py

@@ -1,6 +1,6 @@
 from test import support
 from test.support import os_helper
-from tokenize import (tokenize, _tokenize, untokenize, NUMBER, NAME, OP,
+from tokenize import (tokenize, untokenize, NUMBER, NAME, OP,
                      STRING, ENDMARKER, ENCODING, tok_name, detect_encoding,
                      open as tokenize_open, Untokenizer, generate_tokens,
                      NEWLINE, _generate_tokens_from_c_tokenizer, DEDENT, TokenInfo)
@@ -51,6 +51,25 @@ def check_tokenize(self, s, expected):
                          ["    ENCODING   'utf-8'       (0, 0) (0, 0)"] +
                          expected.rstrip().splitlines())
 
+    def test_invalid_readline(self):
+        def gen():
+            yield "sdfosdg"
+            yield "sdfosdg"
+        with self.assertRaises(TypeError):
+            list(tokenize(gen().__next__))
+
+        def gen():
+            yield b"sdfosdg"
+            yield b"sdfosdg"
+        with self.assertRaises(TypeError):
+            list(generate_tokens(gen().__next__))
+
+        def gen():
+            yield "sdfosdg"
+            1/0
+        with self.assertRaises(ZeroDivisionError):
+            list(generate_tokens(gen().__next__))
+
     def test_implicit_newline(self):
         # Make sure that the tokenizer puts in an implicit NEWLINE
         # when the input lacks a trailing new line.
@@ -1161,7 +1180,8 @@ class TestTokenizerAdheresToPep0263(TestCase):
 
     def _testFile(self, filename):
         path = os.path.join(os.path.dirname(__file__), filename)
-        TestRoundtrip.check_roundtrip(self, open(path, 'rb'))
+        with open(path, 'rb') as f:
+            TestRoundtrip.check_roundtrip(self, f)
 
     def test_utf8_coding_cookie_and_no_utf8_bom(self):
         f = 'tokenize_tests-utf8-coding-cookie-and-no-utf8-bom-sig.txt'
@@ -1206,7 +1226,8 @@ def readline():
                 yield b''
 
         # skip the initial encoding token and the end tokens
-        tokens = list(_tokenize(readline(), encoding='utf-8'))[:-2]
+        tokens = list(_generate_tokens_from_c_tokenizer(readline().__next__, encoding='utf-8',
+                      extra_tokens=True))[:-2]
         expected_tokens = [TokenInfo(3, '"ЉЊЈЁЂ"', (1, 0), (1, 7), '"ЉЊЈЁЂ"\n')]
         self.assertEqual(tokens, expected_tokens,
                          "bytes not decoded with encoding")
@@ -1475,13 +1496,13 @@ def test_tokenize(self):
         def mock_detect_encoding(readline):
             return encoding, [b'first', b'second']
 
-        def mock__tokenize(readline, encoding):
+        def mock__tokenize(readline, encoding, **kwargs):
             nonlocal encoding_used
             encoding_used = encoding
             out = []
             while True:
                 try:
-                    next_line = next(readline)
+                    next_line = readline()
                 except StopIteration:
                     return out
                 if next_line:
@@ -1498,16 +1519,16 @@ def mock_readline():
             return str(counter).encode()
 
         orig_detect_encoding = tokenize_module.detect_encoding
-        orig__tokenize = tokenize_module._tokenize
+        orig_c_token = tokenize_module._generate_tokens_from_c_tokenizer
         tokenize_module.detect_encoding = mock_detect_encoding
-        tokenize_module._tokenize = mock__tokenize
+        tokenize_module._generate_tokens_from_c_tokenizer = mock__tokenize
         try:
             results = tokenize(mock_readline)
             self.assertEqual(list(results)[1:],
                              [b'first', b'second', b'1', b'2', b'3', b'4'])
         finally:
             tokenize_module.detect_encoding = orig_detect_encoding
-            tokenize_module._tokenize = orig__tokenize
+            tokenize_module._generate_tokens_from_c_tokenizer = orig_c_token
 
         self.assertEqual(encoding_used, encoding)
 
@@ -1834,12 +1855,33 @@ class CTokenizeTest(TestCase):
     def check_tokenize(self, s, expected):
         # Format the tokens in s in a table format.
         # The ENDMARKER and final NEWLINE are omitted.
+        f = StringIO(s)
         with self.subTest(source=s):
             result = stringify_tokens_from_source(
-                _generate_tokens_from_c_tokenizer(s), s
+                _generate_tokens_from_c_tokenizer(f.readline), s
             )
             self.assertEqual(result, expected.rstrip().splitlines())
 
+    def test_encoding(self):
+        def readline(encoding):
+            yield "1+1".encode(encoding)
+
+        expected = [
+            TokenInfo(type=NUMBER, string='1', start=(1, 0), end=(1, 1), line='1+1\n'),
+            TokenInfo(type=OP, string='+', start=(1, 1), end=(1, 2), line='1+1\n'),
+            TokenInfo(type=NUMBER, string='1', start=(1, 2), end=(1, 3), line='1+1\n'),
+            TokenInfo(type=NEWLINE, string='\n', start=(1, 3), end=(1, 4), line='1+1\n'),
+            TokenInfo(type=ENDMARKER, string='', start=(2, 0), end=(2, 0), line='')
+        ]
+        for encoding in ["utf-8", "latin-1", "utf-16"]:
+            with self.subTest(encoding=encoding):
+                tokens = list(_generate_tokens_from_c_tokenizer(
+                    readline(encoding).__next__,
+                    extra_tokens=True,
+                    encoding=encoding,
+                ))
+                self.assertEqual(tokens, expected)
+
     def test_int(self):
 
         self.check_tokenize('0xff <= 255', """\
@@ -2675,43 +2717,44 @@ def test_unicode(self):
 
     def test_invalid_syntax(self):
         def get_tokens(string):
-            return list(_generate_tokens_from_c_tokenizer(string))
-
-        self.assertRaises(SyntaxError, get_tokens, "(1+2]")
-        self.assertRaises(SyntaxError, get_tokens, "(1+2}")
-        self.assertRaises(SyntaxError, get_tokens, "{1+2]")
-
-        self.assertRaises(SyntaxError, get_tokens, "1_")
-        self.assertRaises(SyntaxError, get_tokens, "1.2_")
-        self.assertRaises(SyntaxError, get_tokens, "1e2_")
-        self.assertRaises(SyntaxError, get_tokens, "1e+")
-
-        self.assertRaises(SyntaxError, get_tokens, "\xa0")
-        self.assertRaises(SyntaxError, get_tokens, "€")
-
-        self.assertRaises(SyntaxError, get_tokens, "0b12")
-        self.assertRaises(SyntaxError, get_tokens, "0b1_2")
-        self.assertRaises(SyntaxError, get_tokens, "0b2")
-        self.assertRaises(SyntaxError, get_tokens, "0b1_")
-        self.assertRaises(SyntaxError, get_tokens, "0b")
-        self.assertRaises(SyntaxError, get_tokens, "0o18")
-        self.assertRaises(SyntaxError, get_tokens, "0o1_8")
-        self.assertRaises(SyntaxError, get_tokens, "0o8")
-        self.assertRaises(SyntaxError, get_tokens, "0o1_")
-        self.assertRaises(SyntaxError, get_tokens, "0o")
-        self.assertRaises(SyntaxError, get_tokens, "0x1_")
-        self.assertRaises(SyntaxError, get_tokens, "0x")
-        self.assertRaises(SyntaxError, get_tokens, "1_")
-        self.assertRaises(SyntaxError, get_tokens, "012")
-        self.assertRaises(SyntaxError, get_tokens, "1.2_")
-        self.assertRaises(SyntaxError, get_tokens, "1e2_")
-        self.assertRaises(SyntaxError, get_tokens, "1e+")
-
-        self.assertRaises(SyntaxError, get_tokens, "'sdfsdf")
-        self.assertRaises(SyntaxError, get_tokens, "'''sdfsdf''")
-
-        self.assertRaises(SyntaxError, get_tokens, "("*1000+"a"+")"*1000)
-        self.assertRaises(SyntaxError, get_tokens, "]")
+            the_string = StringIO(string)
+            return list(_generate_tokens_from_c_tokenizer(the_string.readline))
+
+        for case in [
+            "(1+2]",
+            "(1+2}",
+            "{1+2]",
+            "1_",
+            "1.2_",
+            "1e2_",
+            "1e+",
+
+            "\xa0",
+            "€",
+            "0b12",
+            "0b1_2",
+            "0b2",
+            "0b1_",
+            "0b",
+            "0o18",
+            "0o1_8",
+            "0o8",
+            "0o1_",
+            "0o",
+            "0x1_",
+            "0x",
+            "1_",
+            "012",
+            "1.2_",
+            "1e2_",
+            "1e+",
+            "'sdfsdf",
+            "'''sdfsdf''",
+            "("*1000+"a"+")"*1000,
+            "]",
+        ]:
+            with self.subTest(case=case):
+                self.assertRaises(SyntaxError, get_tokens, case)
 
     def test_max_indent(self):
         MAXINDENT = 100
@@ -2722,20 +2765,24 @@ def generate_source(indents):
             return source
 
         valid = generate_source(MAXINDENT - 1)
-        tokens = list(_generate_tokens_from_c_tokenizer(valid))
+        the_input = StringIO(valid)
+        tokens = list(_generate_tokens_from_c_tokenizer(the_input.readline))
         self.assertEqual(tokens[-2].type, DEDENT)
         self.assertEqual(tokens[-1].type, ENDMARKER)
         compile(valid, "<string>", "exec")
 
         invalid = generate_source(MAXINDENT)
-        self.assertRaises(SyntaxError, lambda: list(_generate_tokens_from_c_tokenizer(invalid)))
+        the_input = StringIO(invalid)
+        self.assertRaises(SyntaxError, lambda: list(_generate_tokens_from_c_tokenizer(the_input.readline)))
         self.assertRaises(
             IndentationError, compile, invalid, "<string>", "exec"
         )
 
     def test_continuation_lines_indentation(self):
         def get_tokens(string):
-            return [(kind, string) for (kind, string, *_) in _generate_tokens_from_c_tokenizer(string)]
+            the_string = StringIO(string)
+            return [(kind, string) for (kind, string, *_)
+                    in _generate_tokens_from_c_tokenizer(the_string.readline)]
 
         code = dedent("""
             def fib(n):

Lib/tokenize.py

@@ -34,6 +34,7 @@
 import sys
 from token import *
 from token import EXACT_TOKEN_TYPES
+import _tokenize
 
 cookie_re = re.compile(r'^[ \t\f]*#.*?coding[:=][ \t]*([-\w.]+)', re.ASCII)
 blank_re = re.compile(br'^[ \t\f]*(?:[#\r\n]|$)', re.ASCII)
@@ -443,29 +444,15 @@ def tokenize(readline):
             # BOM will already have been stripped.
             encoding = "utf-8"
         yield TokenInfo(ENCODING, encoding, (0, 0), (0, 0), '')
-    yield from _tokenize(rl_gen, encoding)
-
-def _tokenize(rl_gen, encoding):
-    source = b"".join(rl_gen).decode(encoding)
-    for token in _generate_tokens_from_c_tokenizer(source, extra_tokens=True):
-        yield token
+    yield from _generate_tokens_from_c_tokenizer(rl_gen.__next__, encoding, extra_tokens=True)
 
 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.
     """
-    def _gen():
-        while True:
-            try:
-                line = readline()
-            except StopIteration:
-                return
-            if not line:
-                return
-            yield line.encode()
-    return _tokenize(_gen(), 'utf-8')
+    return _generate_tokens_from_c_tokenizer(readline, extra_tokens=True)
 
 def main():
     import argparse
@@ -502,9 +489,9 @@ def error(message, filename=None, location=None):
                 tokens = list(tokenize(f.readline))
         else:
             filename = "<stdin>"
-            tokens = _tokenize(
+            tokens = _generate_tokens_from_c_tokenizer(
                 (x.encode('utf-8') for x in iter(sys.stdin.readline, "")
-            ), "utf-8")
+            ), "utf-8", extra_tokens=True)
 
 
         # Output the tokenization
@@ -531,10 +518,13 @@ def error(message, filename=None, location=None):
         perror("unexpected error: %s" % err)
         raise
 
-def _generate_tokens_from_c_tokenizer(source, extra_tokens=False):
+def _generate_tokens_from_c_tokenizer(source, encoding=None, extra_tokens=False):
     """Tokenize a source reading Python code as unicode strings using the internal C tokenizer"""
-    import _tokenize as c_tokenizer
-    for info in c_tokenizer.TokenizerIter(source, extra_tokens=extra_tokens):
+    if encoding is None:
+        it = _tokenize.TokenizerIter(source, extra_tokens=extra_tokens)
+    else:
+        it = _tokenize.TokenizerIter(source, encoding=encoding, extra_tokens=extra_tokens)
+    for info in it:
         yield TokenInfo._make(info)