[Python-checkins] Add tests for the C tokenizer and expose it as a private module (GH-27924)
pablogsal
webhook-mailer at python.org
Tue Aug 24 12:50:10 EDT 2021
https://github.com/python/cpython/commit/a24676bedcd332dd7e6fa5521d0449206391d190
commit: a24676bedcd332dd7e6fa5521d0449206391d190
branch: main
author: Pablo Galindo Salgado <Pablogsal at gmail.com>
committer: pablogsal <Pablogsal at gmail.com>
date: 2021-08-24T17:50:05+01:00
summary:
Add tests for the C tokenizer and expose it as a private module (GH-27924)
files:
A Python/Python-tokenize.c
A Python/clinic/Python-tokenize.c.h
M Lib/test/test_tokenize.py
M Lib/tokenize.py
M Makefile.pre.in
M Modules/config.c.in
M PC/config.c
M PCbuild/pythoncore.vcxproj
M Python/stdlib_module_names.h
diff --git a/Lib/test/test_tokenize.py b/Lib/test/test_tokenize.py
index 4bce1ca9c76f7c..f8b16e52976451 100644
--- a/Lib/test/test_tokenize.py
+++ b/Lib/test/test_tokenize.py
@@ -3,7 +3,7 @@
from tokenize import (tokenize, _tokenize, untokenize, NUMBER, NAME, OP,
STRING, ENDMARKER, ENCODING, tok_name, detect_encoding,
open as tokenize_open, Untokenizer, generate_tokens,
- NEWLINE)
+ NEWLINE, _generate_tokens_from_c_tokenizer)
from io import BytesIO, StringIO
import unittest
from unittest import TestCase, mock
@@ -12,7 +12,6 @@
import os
import token
-
# Converts a source string into a list of textual representation
# of the tokens such as:
# ` NAME 'if' (1, 0) (1, 2)`
@@ -1654,5 +1653,865 @@ def test_indentation_semantics_retained(self):
self.check_roundtrip(code)
+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.
+ with self.subTest(source=s):
+ result = stringify_tokens_from_source(
+ _generate_tokens_from_c_tokenizer(s), s
+ )
+ self.assertEqual(result, expected.rstrip().splitlines())
+
+ def test_int(self):
+
+ self.check_tokenize('0xff <= 255', """\
+ NUMBER '0xff' (1, 0) (1, 4)
+ LESSEQUAL '<=' (1, 5) (1, 7)
+ NUMBER '255' (1, 8) (1, 11)
+ """)
+
+ self.check_tokenize('0b10 <= 255', """\
+ NUMBER '0b10' (1, 0) (1, 4)
+ LESSEQUAL '<=' (1, 5) (1, 7)
+ NUMBER '255' (1, 8) (1, 11)
+ """)
+
+ self.check_tokenize('0o123 <= 0O123', """\
+ NUMBER '0o123' (1, 0) (1, 5)
+ LESSEQUAL '<=' (1, 6) (1, 8)
+ NUMBER '0O123' (1, 9) (1, 14)
+ """)
+
+ self.check_tokenize('1234567 > ~0x15', """\
+ NUMBER '1234567' (1, 0) (1, 7)
+ GREATER '>' (1, 8) (1, 9)
+ TILDE '~' (1, 10) (1, 11)
+ NUMBER '0x15' (1, 11) (1, 15)
+ """)
+
+ self.check_tokenize('2134568 != 1231515', """\
+ NUMBER '2134568' (1, 0) (1, 7)
+ NOTEQUAL '!=' (1, 8) (1, 10)
+ NUMBER '1231515' (1, 11) (1, 18)
+ """)
+
+ self.check_tokenize('(-124561-1) & 200000000', """\
+ LPAR '(' (1, 0) (1, 1)
+ MINUS '-' (1, 1) (1, 2)
+ NUMBER '124561' (1, 2) (1, 8)
+ MINUS '-' (1, 8) (1, 9)
+ NUMBER '1' (1, 9) (1, 10)
+ RPAR ')' (1, 10) (1, 11)
+ AMPER '&' (1, 12) (1, 13)
+ NUMBER '200000000' (1, 14) (1, 23)
+ """)
+
+ self.check_tokenize('0xdeadbeef != -1', """\
+ NUMBER '0xdeadbeef' (1, 0) (1, 10)
+ NOTEQUAL '!=' (1, 11) (1, 13)
+ MINUS '-' (1, 14) (1, 15)
+ NUMBER '1' (1, 15) (1, 16)
+ """)
+
+ self.check_tokenize('0xdeadc0de & 12345', """\
+ NUMBER '0xdeadc0de' (1, 0) (1, 10)
+ AMPER '&' (1, 11) (1, 12)
+ NUMBER '12345' (1, 13) (1, 18)
+ """)
+
+ self.check_tokenize('0xFF & 0x15 | 1234', """\
+ NUMBER '0xFF' (1, 0) (1, 4)
+ AMPER '&' (1, 5) (1, 6)
+ NUMBER '0x15' (1, 7) (1, 11)
+ VBAR '|' (1, 12) (1, 13)
+ NUMBER '1234' (1, 14) (1, 18)
+ """)
+
+ def test_float(self):
+
+ self.check_tokenize('x = 3.14159', """\
+ NAME 'x' (1, 0) (1, 1)
+ EQUAL '=' (1, 2) (1, 3)
+ NUMBER '3.14159' (1, 4) (1, 11)
+ """)
+
+ self.check_tokenize('x = 314159.', """\
+ NAME 'x' (1, 0) (1, 1)
+ EQUAL '=' (1, 2) (1, 3)
+ NUMBER '314159.' (1, 4) (1, 11)
+ """)
+
+ self.check_tokenize('x = .314159', """\
+ NAME 'x' (1, 0) (1, 1)
+ EQUAL '=' (1, 2) (1, 3)
+ NUMBER '.314159' (1, 4) (1, 11)
+ """)
+
+ self.check_tokenize('x = 3e14159', """\
+ NAME 'x' (1, 0) (1, 1)
+ EQUAL '=' (1, 2) (1, 3)
+ NUMBER '3e14159' (1, 4) (1, 11)
+ """)
+
+ self.check_tokenize('x = 3E123', """\
+ NAME 'x' (1, 0) (1, 1)
+ EQUAL '=' (1, 2) (1, 3)
+ NUMBER '3E123' (1, 4) (1, 9)
+ """)
+
+ self.check_tokenize('x+y = 3e-1230', """\
+ NAME 'x' (1, 0) (1, 1)
+ PLUS '+' (1, 1) (1, 2)
+ NAME 'y' (1, 2) (1, 3)
+ EQUAL '=' (1, 4) (1, 5)
+ NUMBER '3e-1230' (1, 6) (1, 13)
+ """)
+
+ self.check_tokenize('x = 3.14e159', """\
+ NAME 'x' (1, 0) (1, 1)
+ EQUAL '=' (1, 2) (1, 3)
+ NUMBER '3.14e159' (1, 4) (1, 12)
+ """)
+
+ def test_string(self):
+
+ self.check_tokenize('x = \'\'; y = ""', """\
+ NAME 'x' (1, 0) (1, 1)
+ EQUAL '=' (1, 2) (1, 3)
+ STRING "''" (1, 4) (1, 6)
+ SEMI ';' (1, 6) (1, 7)
+ NAME 'y' (1, 8) (1, 9)
+ EQUAL '=' (1, 10) (1, 11)
+ STRING '""' (1, 12) (1, 14)
+ """)
+
+ self.check_tokenize('x = \'"\'; y = "\'"', """\
+ NAME 'x' (1, 0) (1, 1)
+ EQUAL '=' (1, 2) (1, 3)
+ STRING '\\'"\\'' (1, 4) (1, 7)
+ SEMI ';' (1, 7) (1, 8)
+ NAME 'y' (1, 9) (1, 10)
+ EQUAL '=' (1, 11) (1, 12)
+ STRING '"\\'"' (1, 13) (1, 16)
+ """)
+
+ self.check_tokenize('x = "doesn\'t "shrink", does it"', """\
+ NAME 'x' (1, 0) (1, 1)
+ EQUAL '=' (1, 2) (1, 3)
+ STRING '"doesn\\'t "' (1, 4) (1, 14)
+ NAME 'shrink' (1, 14) (1, 20)
+ STRING '", does it"' (1, 20) (1, 31)
+ """)
+
+ self.check_tokenize("x = 'abc' + 'ABC'", """\
+ NAME 'x' (1, 0) (1, 1)
+ EQUAL '=' (1, 2) (1, 3)
+ STRING "'abc'" (1, 4) (1, 9)
+ PLUS '+' (1, 10) (1, 11)
+ STRING "'ABC'" (1, 12) (1, 17)
+ """)
+
+ self.check_tokenize('y = "ABC" + "ABC"', """\
+ NAME 'y' (1, 0) (1, 1)
+ EQUAL '=' (1, 2) (1, 3)
+ STRING '"ABC"' (1, 4) (1, 9)
+ PLUS '+' (1, 10) (1, 11)
+ STRING '"ABC"' (1, 12) (1, 17)
+ """)
+
+ self.check_tokenize("x = r'abc' + r'ABC' + R'ABC' + R'ABC'", """\
+ NAME 'x' (1, 0) (1, 1)
+ EQUAL '=' (1, 2) (1, 3)
+ STRING "r'abc'" (1, 4) (1, 10)
+ PLUS '+' (1, 11) (1, 12)
+ STRING "r'ABC'" (1, 13) (1, 19)
+ PLUS '+' (1, 20) (1, 21)
+ STRING "R'ABC'" (1, 22) (1, 28)
+ PLUS '+' (1, 29) (1, 30)
+ STRING "R'ABC'" (1, 31) (1, 37)
+ """)
+
+ self.check_tokenize('y = r"abc" + r"ABC" + R"ABC" + R"ABC"', """\
+ NAME 'y' (1, 0) (1, 1)
+ EQUAL '=' (1, 2) (1, 3)
+ STRING 'r"abc"' (1, 4) (1, 10)
+ PLUS '+' (1, 11) (1, 12)
+ STRING 'r"ABC"' (1, 13) (1, 19)
+ PLUS '+' (1, 20) (1, 21)
+ STRING 'R"ABC"' (1, 22) (1, 28)
+ PLUS '+' (1, 29) (1, 30)
+ STRING 'R"ABC"' (1, 31) (1, 37)
+ """)
+
+ self.check_tokenize("u'abc' + U'abc'", """\
+ STRING "u'abc'" (1, 0) (1, 6)
+ PLUS '+' (1, 7) (1, 8)
+ STRING "U'abc'" (1, 9) (1, 15)
+ """)
+
+ self.check_tokenize('u"abc" + U"abc"', """\
+ STRING 'u"abc"' (1, 0) (1, 6)
+ PLUS '+' (1, 7) (1, 8)
+ STRING 'U"abc"' (1, 9) (1, 15)
+ """)
+
+ self.check_tokenize("b'abc' + B'abc'", """\
+ STRING "b'abc'" (1, 0) (1, 6)
+ PLUS '+' (1, 7) (1, 8)
+ STRING "B'abc'" (1, 9) (1, 15)
+ """)
+
+ self.check_tokenize('b"abc" + B"abc"', """\
+ STRING 'b"abc"' (1, 0) (1, 6)
+ PLUS '+' (1, 7) (1, 8)
+ STRING 'B"abc"' (1, 9) (1, 15)
+ """)
+
+ self.check_tokenize("br'abc' + bR'abc' + Br'abc' + BR'abc'", """\
+ STRING "br'abc'" (1, 0) (1, 7)
+ PLUS '+' (1, 8) (1, 9)
+ STRING "bR'abc'" (1, 10) (1, 17)
+ PLUS '+' (1, 18) (1, 19)
+ STRING "Br'abc'" (1, 20) (1, 27)
+ PLUS '+' (1, 28) (1, 29)
+ STRING "BR'abc'" (1, 30) (1, 37)
+ """)
+
+ self.check_tokenize('br"abc" + bR"abc" + Br"abc" + BR"abc"', """\
+ STRING 'br"abc"' (1, 0) (1, 7)
+ PLUS '+' (1, 8) (1, 9)
+ STRING 'bR"abc"' (1, 10) (1, 17)
+ PLUS '+' (1, 18) (1, 19)
+ STRING 'Br"abc"' (1, 20) (1, 27)
+ PLUS '+' (1, 28) (1, 29)
+ STRING 'BR"abc"' (1, 30) (1, 37)
+ """)
+
+ self.check_tokenize("rb'abc' + rB'abc' + Rb'abc' + RB'abc'", """\
+ STRING "rb'abc'" (1, 0) (1, 7)
+ PLUS '+' (1, 8) (1, 9)
+ STRING "rB'abc'" (1, 10) (1, 17)
+ PLUS '+' (1, 18) (1, 19)
+ STRING "Rb'abc'" (1, 20) (1, 27)
+ PLUS '+' (1, 28) (1, 29)
+ STRING "RB'abc'" (1, 30) (1, 37)
+ """)
+
+ self.check_tokenize('rb"abc" + rB"abc" + Rb"abc" + RB"abc"', """\
+ STRING 'rb"abc"' (1, 0) (1, 7)
+ PLUS '+' (1, 8) (1, 9)
+ STRING 'rB"abc"' (1, 10) (1, 17)
+ PLUS '+' (1, 18) (1, 19)
+ STRING 'Rb"abc"' (1, 20) (1, 27)
+ PLUS '+' (1, 28) (1, 29)
+ STRING 'RB"abc"' (1, 30) (1, 37)
+ """)
+
+ self.check_tokenize('"a\\\nde\\\nfg"', """\
+ STRING '"a\\\\\\nde\\\\\\nfg"\' (1, 0) (3, 3)
+ """)
+
+ self.check_tokenize('u"a\\\nde"', """\
+ STRING 'u"a\\\\\\nde"\' (1, 0) (2, 3)
+ """)
+
+ self.check_tokenize('rb"a\\\nd"', """\
+ STRING 'rb"a\\\\\\nd"\' (1, 0) (2, 2)
+ """)
+
+ self.check_tokenize(r'"""a\
+b"""', """\
+ STRING '\"\""a\\\\\\nb\"\""' (1, 0) (2, 4)
+ """)
+ self.check_tokenize(r'u"""a\
+b"""', """\
+ STRING 'u\"\""a\\\\\\nb\"\""' (1, 0) (2, 4)
+ """)
+ self.check_tokenize(r'rb"""a\
+b\
+c"""', """\
+ STRING 'rb"\""a\\\\\\nb\\\\\\nc"\""' (1, 0) (3, 4)
+ """)
+
+ self.check_tokenize('f"abc"', """\
+ STRING 'f"abc"' (1, 0) (1, 6)
+ """)
+
+ self.check_tokenize('fR"a{b}c"', """\
+ STRING 'fR"a{b}c"' (1, 0) (1, 9)
+ """)
+
+ self.check_tokenize('f"""abc"""', """\
+ STRING 'f\"\"\"abc\"\"\"' (1, 0) (1, 10)
+ """)
+
+ self.check_tokenize(r'f"abc\
+def"', """\
+ STRING 'f"abc\\\\\\ndef"' (1, 0) (2, 4)
+ """)
+
+ self.check_tokenize(r'Rf"abc\
+def"', """\
+ STRING 'Rf"abc\\\\\\ndef"' (1, 0) (2, 4)
+ """)
+
+ def test_function(self):
+
+ self.check_tokenize('def d22(a, b, c=2, d=2, *k): pass', """\
+ NAME 'def' (1, 0) (1, 3)
+ NAME 'd22' (1, 4) (1, 7)
+ LPAR '(' (1, 7) (1, 8)
+ NAME 'a' (1, 8) (1, 9)
+ COMMA ',' (1, 9) (1, 10)
+ NAME 'b' (1, 11) (1, 12)
+ COMMA ',' (1, 12) (1, 13)
+ NAME 'c' (1, 14) (1, 15)
+ EQUAL '=' (1, 15) (1, 16)
+ NUMBER '2' (1, 16) (1, 17)
+ COMMA ',' (1, 17) (1, 18)
+ NAME 'd' (1, 19) (1, 20)
+ EQUAL '=' (1, 20) (1, 21)
+ NUMBER '2' (1, 21) (1, 22)
+ COMMA ',' (1, 22) (1, 23)
+ STAR '*' (1, 24) (1, 25)
+ NAME 'k' (1, 25) (1, 26)
+ RPAR ')' (1, 26) (1, 27)
+ COLON ':' (1, 27) (1, 28)
+ NAME 'pass' (1, 29) (1, 33)
+ """)
+
+ self.check_tokenize('def d01v_(a=1, *k, **w): pass', """\
+ NAME 'def' (1, 0) (1, 3)
+ NAME 'd01v_' (1, 4) (1, 9)
+ LPAR '(' (1, 9) (1, 10)
+ NAME 'a' (1, 10) (1, 11)
+ EQUAL '=' (1, 11) (1, 12)
+ NUMBER '1' (1, 12) (1, 13)
+ COMMA ',' (1, 13) (1, 14)
+ STAR '*' (1, 15) (1, 16)
+ NAME 'k' (1, 16) (1, 17)
+ COMMA ',' (1, 17) (1, 18)
+ DOUBLESTAR '**' (1, 19) (1, 21)
+ NAME 'w' (1, 21) (1, 22)
+ RPAR ')' (1, 22) (1, 23)
+ COLON ':' (1, 23) (1, 24)
+ NAME 'pass' (1, 25) (1, 29)
+ """)
+
+ self.check_tokenize('def d23(a: str, b: int=3) -> int: pass', """\
+ NAME 'def' (1, 0) (1, 3)
+ NAME 'd23' (1, 4) (1, 7)
+ LPAR '(' (1, 7) (1, 8)
+ NAME 'a' (1, 8) (1, 9)
+ COLON ':' (1, 9) (1, 10)
+ NAME 'str' (1, 11) (1, 14)
+ COMMA ',' (1, 14) (1, 15)
+ NAME 'b' (1, 16) (1, 17)
+ COLON ':' (1, 17) (1, 18)
+ NAME 'int' (1, 19) (1, 22)
+ EQUAL '=' (1, 22) (1, 23)
+ NUMBER '3' (1, 23) (1, 24)
+ RPAR ')' (1, 24) (1, 25)
+ RARROW '->' (1, 26) (1, 28)
+ NAME 'int' (1, 29) (1, 32)
+ COLON ':' (1, 32) (1, 33)
+ NAME 'pass' (1, 34) (1, 38)
+ """)
+
+ def test_comparison(self):
+
+ self.check_tokenize("if 1 < 1 > 1 == 1 >= 5 <= 0x15 <= 0x12 != "
+ "1 and 5 in 1 not in 1 is 1 or 5 is not 1: pass", """\
+ NAME 'if' (1, 0) (1, 2)
+ NUMBER '1' (1, 3) (1, 4)
+ LESS '<' (1, 5) (1, 6)
+ NUMBER '1' (1, 7) (1, 8)
+ GREATER '>' (1, 9) (1, 10)
+ NUMBER '1' (1, 11) (1, 12)
+ EQEQUAL '==' (1, 13) (1, 15)
+ NUMBER '1' (1, 16) (1, 17)
+ GREATEREQUAL '>=' (1, 18) (1, 20)
+ NUMBER '5' (1, 21) (1, 22)
+ LESSEQUAL '<=' (1, 23) (1, 25)
+ NUMBER '0x15' (1, 26) (1, 30)
+ LESSEQUAL '<=' (1, 31) (1, 33)
+ NUMBER '0x12' (1, 34) (1, 38)
+ NOTEQUAL '!=' (1, 39) (1, 41)
+ NUMBER '1' (1, 42) (1, 43)
+ NAME 'and' (1, 44) (1, 47)
+ NUMBER '5' (1, 48) (1, 49)
+ NAME 'in' (1, 50) (1, 52)
+ NUMBER '1' (1, 53) (1, 54)
+ NAME 'not' (1, 55) (1, 58)
+ NAME 'in' (1, 59) (1, 61)
+ NUMBER '1' (1, 62) (1, 63)
+ NAME 'is' (1, 64) (1, 66)
+ NUMBER '1' (1, 67) (1, 68)
+ NAME 'or' (1, 69) (1, 71)
+ NUMBER '5' (1, 72) (1, 73)
+ NAME 'is' (1, 74) (1, 76)
+ NAME 'not' (1, 77) (1, 80)
+ NUMBER '1' (1, 81) (1, 82)
+ COLON ':' (1, 82) (1, 83)
+ NAME 'pass' (1, 84) (1, 88)
+ """)
+
+ def test_additive(self):
+
+ self.check_tokenize('x = 1 - y + 15 - 1 + 0x124 + z + a[5]', """\
+ NAME 'x' (1, 0) (1, 1)
+ EQUAL '=' (1, 2) (1, 3)
+ NUMBER '1' (1, 4) (1, 5)
+ MINUS '-' (1, 6) (1, 7)
+ NAME 'y' (1, 8) (1, 9)
+ PLUS '+' (1, 10) (1, 11)
+ NUMBER '15' (1, 12) (1, 14)
+ MINUS '-' (1, 15) (1, 16)
+ NUMBER '1' (1, 17) (1, 18)
+ PLUS '+' (1, 19) (1, 20)
+ NUMBER '0x124' (1, 21) (1, 26)
+ PLUS '+' (1, 27) (1, 28)
+ NAME 'z' (1, 29) (1, 30)
+ PLUS '+' (1, 31) (1, 32)
+ NAME 'a' (1, 33) (1, 34)
+ LSQB '[' (1, 34) (1, 35)
+ NUMBER '5' (1, 35) (1, 36)
+ RSQB ']' (1, 36) (1, 37)
+ """)
+
+ def test_multiplicative(self):
+
+ self.check_tokenize('x = 1//1*1/5*12%0x12 at 42', """\
+ NAME 'x' (1, 0) (1, 1)
+ EQUAL '=' (1, 2) (1, 3)
+ NUMBER '1' (1, 4) (1, 5)
+ DOUBLESLASH '//' (1, 5) (1, 7)
+ NUMBER '1' (1, 7) (1, 8)
+ STAR '*' (1, 8) (1, 9)
+ NUMBER '1' (1, 9) (1, 10)
+ SLASH '/' (1, 10) (1, 11)
+ NUMBER '5' (1, 11) (1, 12)
+ STAR '*' (1, 12) (1, 13)
+ NUMBER '12' (1, 13) (1, 15)
+ PERCENT '%' (1, 15) (1, 16)
+ NUMBER '0x12' (1, 16) (1, 20)
+ AT '@' (1, 20) (1, 21)
+ NUMBER '42' (1, 21) (1, 23)
+ """)
+
+ def test_unary(self):
+
+ self.check_tokenize('~1 ^ 1 & 1 |1 ^ -1', """\
+ TILDE '~' (1, 0) (1, 1)
+ NUMBER '1' (1, 1) (1, 2)
+ CIRCUMFLEX '^' (1, 3) (1, 4)
+ NUMBER '1' (1, 5) (1, 6)
+ AMPER '&' (1, 7) (1, 8)
+ NUMBER '1' (1, 9) (1, 10)
+ VBAR '|' (1, 11) (1, 12)
+ NUMBER '1' (1, 12) (1, 13)
+ CIRCUMFLEX '^' (1, 14) (1, 15)
+ MINUS '-' (1, 16) (1, 17)
+ NUMBER '1' (1, 17) (1, 18)
+ """)
+
+ self.check_tokenize('-1*1/1+1*1//1 - ---1**1', """\
+ MINUS '-' (1, 0) (1, 1)
+ NUMBER '1' (1, 1) (1, 2)
+ STAR '*' (1, 2) (1, 3)
+ NUMBER '1' (1, 3) (1, 4)
+ SLASH '/' (1, 4) (1, 5)
+ NUMBER '1' (1, 5) (1, 6)
+ PLUS '+' (1, 6) (1, 7)
+ NUMBER '1' (1, 7) (1, 8)
+ STAR '*' (1, 8) (1, 9)
+ NUMBER '1' (1, 9) (1, 10)
+ DOUBLESLASH '//' (1, 10) (1, 12)
+ NUMBER '1' (1, 12) (1, 13)
+ MINUS '-' (1, 14) (1, 15)
+ MINUS '-' (1, 16) (1, 17)
+ MINUS '-' (1, 17) (1, 18)
+ MINUS '-' (1, 18) (1, 19)
+ NUMBER '1' (1, 19) (1, 20)
+ DOUBLESTAR '**' (1, 20) (1, 22)
+ NUMBER '1' (1, 22) (1, 23)
+ """)
+
+ def test_selector(self):
+
+ self.check_tokenize("import sys, time\nx = sys.modules['time'].time()", """\
+ NAME 'import' (1, 0) (1, 6)
+ NAME 'sys' (1, 7) (1, 10)
+ COMMA ',' (1, 10) (1, 11)
+ NAME 'time' (1, 12) (1, 16)
+ NEWLINE '' (1, 16) (1, 16)
+ NAME 'x' (2, 0) (2, 1)
+ EQUAL '=' (2, 2) (2, 3)
+ NAME 'sys' (2, 4) (2, 7)
+ DOT '.' (2, 7) (2, 8)
+ NAME 'modules' (2, 8) (2, 15)
+ LSQB '[' (2, 15) (2, 16)
+ STRING "'time'" (2, 16) (2, 22)
+ RSQB ']' (2, 22) (2, 23)
+ DOT '.' (2, 23) (2, 24)
+ NAME 'time' (2, 24) (2, 28)
+ LPAR '(' (2, 28) (2, 29)
+ RPAR ')' (2, 29) (2, 30)
+ """)
+
+ def test_method(self):
+
+ self.check_tokenize('@staticmethod\ndef foo(x,y): pass', """\
+ AT '@' (1, 0) (1, 1)
+ NAME 'staticmethod' (1, 1) (1, 13)
+ NEWLINE '' (1, 13) (1, 13)
+ NAME 'def' (2, 0) (2, 3)
+ NAME 'foo' (2, 4) (2, 7)
+ LPAR '(' (2, 7) (2, 8)
+ NAME 'x' (2, 8) (2, 9)
+ COMMA ',' (2, 9) (2, 10)
+ NAME 'y' (2, 10) (2, 11)
+ RPAR ')' (2, 11) (2, 12)
+ COLON ':' (2, 12) (2, 13)
+ NAME 'pass' (2, 14) (2, 18)
+ """)
+
+ def test_tabs(self):
+
+ self.check_tokenize('@staticmethod\ndef foo(x,y): pass', """\
+ AT '@' (1, 0) (1, 1)
+ NAME 'staticmethod' (1, 1) (1, 13)
+ NEWLINE '' (1, 13) (1, 13)
+ NAME 'def' (2, 0) (2, 3)
+ NAME 'foo' (2, 4) (2, 7)
+ LPAR '(' (2, 7) (2, 8)
+ NAME 'x' (2, 8) (2, 9)
+ COMMA ',' (2, 9) (2, 10)
+ NAME 'y' (2, 10) (2, 11)
+ RPAR ')' (2, 11) (2, 12)
+ COLON ':' (2, 12) (2, 13)
+ NAME 'pass' (2, 14) (2, 18)
+ """)
+
+ def test_async(self):
+
+ self.check_tokenize('async = 1', """\
+ ASYNC 'async' (1, 0) (1, 5)
+ EQUAL '=' (1, 6) (1, 7)
+ NUMBER '1' (1, 8) (1, 9)
+ """)
+
+ self.check_tokenize('a = (async = 1)', """\
+ NAME 'a' (1, 0) (1, 1)
+ EQUAL '=' (1, 2) (1, 3)
+ LPAR '(' (1, 4) (1, 5)
+ ASYNC 'async' (1, 5) (1, 10)
+ EQUAL '=' (1, 11) (1, 12)
+ NUMBER '1' (1, 13) (1, 14)
+ RPAR ')' (1, 14) (1, 15)
+ """)
+
+ self.check_tokenize('async()', """\
+ ASYNC 'async' (1, 0) (1, 5)
+ LPAR '(' (1, 5) (1, 6)
+ RPAR ')' (1, 6) (1, 7)
+ """)
+
+ self.check_tokenize('class async(Bar):pass', """\
+ NAME 'class' (1, 0) (1, 5)
+ ASYNC 'async' (1, 6) (1, 11)
+ LPAR '(' (1, 11) (1, 12)
+ NAME 'Bar' (1, 12) (1, 15)
+ RPAR ')' (1, 15) (1, 16)
+ COLON ':' (1, 16) (1, 17)
+ NAME 'pass' (1, 17) (1, 21)
+ """)
+
+ self.check_tokenize('class async:pass', """\
+ NAME 'class' (1, 0) (1, 5)
+ ASYNC 'async' (1, 6) (1, 11)
+ COLON ':' (1, 11) (1, 12)
+ NAME 'pass' (1, 12) (1, 16)
+ """)
+
+ self.check_tokenize('await = 1', """\
+ AWAIT 'await' (1, 0) (1, 5)
+ EQUAL '=' (1, 6) (1, 7)
+ NUMBER '1' (1, 8) (1, 9)
+ """)
+
+ self.check_tokenize('foo.async', """\
+ NAME 'foo' (1, 0) (1, 3)
+ DOT '.' (1, 3) (1, 4)
+ ASYNC 'async' (1, 4) (1, 9)
+ """)
+
+ self.check_tokenize('async for a in b: pass', """\
+ ASYNC 'async' (1, 0) (1, 5)
+ NAME 'for' (1, 6) (1, 9)
+ NAME 'a' (1, 10) (1, 11)
+ NAME 'in' (1, 12) (1, 14)
+ NAME 'b' (1, 15) (1, 16)
+ COLON ':' (1, 16) (1, 17)
+ NAME 'pass' (1, 18) (1, 22)
+ """)
+
+ self.check_tokenize('async with a as b: pass', """\
+ ASYNC 'async' (1, 0) (1, 5)
+ NAME 'with' (1, 6) (1, 10)
+ NAME 'a' (1, 11) (1, 12)
+ NAME 'as' (1, 13) (1, 15)
+ NAME 'b' (1, 16) (1, 17)
+ COLON ':' (1, 17) (1, 18)
+ NAME 'pass' (1, 19) (1, 23)
+ """)
+
+ self.check_tokenize('async.foo', """\
+ ASYNC 'async' (1, 0) (1, 5)
+ DOT '.' (1, 5) (1, 6)
+ NAME 'foo' (1, 6) (1, 9)
+ """)
+
+ self.check_tokenize('async', """\
+ ASYNC 'async' (1, 0) (1, 5)
+ """)
+
+ self.check_tokenize('async\n#comment\nawait', """\
+ ASYNC 'async' (1, 0) (1, 5)
+ NEWLINE '' (1, 5) (1, 5)
+ AWAIT 'await' (3, 0) (3, 5)
+ """)
+
+ self.check_tokenize('async\n...\nawait', """\
+ ASYNC 'async' (1, 0) (1, 5)
+ NEWLINE '' (1, 5) (1, 5)
+ ELLIPSIS '...' (2, 0) (2, 3)
+ NEWLINE '' (2, 3) (2, 3)
+ AWAIT 'await' (3, 0) (3, 5)
+ """)
+
+ self.check_tokenize('async\nawait', """\
+ ASYNC 'async' (1, 0) (1, 5)
+ NEWLINE '' (1, 5) (1, 5)
+ AWAIT 'await' (2, 0) (2, 5)
+ """)
+
+ self.check_tokenize('foo.async + 1', """\
+ NAME 'foo' (1, 0) (1, 3)
+ DOT '.' (1, 3) (1, 4)
+ ASYNC 'async' (1, 4) (1, 9)
+ PLUS '+' (1, 10) (1, 11)
+ NUMBER '1' (1, 12) (1, 13)
+ """)
+
+ self.check_tokenize('async def foo(): pass', """\
+ ASYNC 'async' (1, 0) (1, 5)
+ NAME 'def' (1, 6) (1, 9)
+ NAME 'foo' (1, 10) (1, 13)
+ LPAR '(' (1, 13) (1, 14)
+ RPAR ')' (1, 14) (1, 15)
+ COLON ':' (1, 15) (1, 16)
+ NAME 'pass' (1, 17) (1, 21)
+ """)
+
+ self.check_tokenize('''\
+async def foo():
+ def foo(await):
+ await = 1
+ if 1:
+ await
+async += 1
+''', """\
+ ASYNC 'async' (1, 0) (1, 5)
+ NAME 'def' (1, 6) (1, 9)
+ NAME 'foo' (1, 10) (1, 13)
+ LPAR '(' (1, 13) (1, 14)
+ RPAR ')' (1, 14) (1, 15)
+ COLON ':' (1, 15) (1, 16)
+ NEWLINE '' (1, 16) (1, 16)
+ INDENT '' (2, -1) (2, -1)
+ NAME 'def' (2, 2) (2, 5)
+ NAME 'foo' (2, 6) (2, 9)
+ LPAR '(' (2, 9) (2, 10)
+ AWAIT 'await' (2, 10) (2, 15)
+ RPAR ')' (2, 15) (2, 16)
+ COLON ':' (2, 16) (2, 17)
+ NEWLINE '' (2, 17) (2, 17)
+ INDENT '' (3, -1) (3, -1)
+ AWAIT 'await' (3, 4) (3, 9)
+ EQUAL '=' (3, 10) (3, 11)
+ NUMBER '1' (3, 12) (3, 13)
+ NEWLINE '' (3, 13) (3, 13)
+ DEDENT '' (4, -1) (4, -1)
+ NAME 'if' (4, 2) (4, 4)
+ NUMBER '1' (4, 5) (4, 6)
+ COLON ':' (4, 6) (4, 7)
+ NEWLINE '' (4, 7) (4, 7)
+ INDENT '' (5, -1) (5, -1)
+ AWAIT 'await' (5, 4) (5, 9)
+ NEWLINE '' (5, 9) (5, 9)
+ DEDENT '' (6, -1) (6, -1)
+ DEDENT '' (6, -1) (6, -1)
+ ASYNC 'async' (6, 0) (6, 5)
+ PLUSEQUAL '+=' (6, 6) (6, 8)
+ NUMBER '1' (6, 9) (6, 10)
+ NEWLINE '' (6, 10) (6, 10)
+ """)
+
+ self.check_tokenize('async def foo():\n async for i in 1: pass', """\
+ ASYNC 'async' (1, 0) (1, 5)
+ NAME 'def' (1, 6) (1, 9)
+ NAME 'foo' (1, 10) (1, 13)
+ LPAR '(' (1, 13) (1, 14)
+ RPAR ')' (1, 14) (1, 15)
+ COLON ':' (1, 15) (1, 16)
+ NEWLINE '' (1, 16) (1, 16)
+ INDENT '' (2, -1) (2, -1)
+ ASYNC 'async' (2, 2) (2, 7)
+ NAME 'for' (2, 8) (2, 11)
+ NAME 'i' (2, 12) (2, 13)
+ NAME 'in' (2, 14) (2, 16)
+ NUMBER '1' (2, 17) (2, 18)
+ COLON ':' (2, 18) (2, 19)
+ NAME 'pass' (2, 20) (2, 24)
+ DEDENT '' (2, -1) (2, -1)
+ """)
+
+ self.check_tokenize('async def foo(async): await', """\
+ ASYNC 'async' (1, 0) (1, 5)
+ NAME 'def' (1, 6) (1, 9)
+ NAME 'foo' (1, 10) (1, 13)
+ LPAR '(' (1, 13) (1, 14)
+ ASYNC 'async' (1, 14) (1, 19)
+ RPAR ')' (1, 19) (1, 20)
+ COLON ':' (1, 20) (1, 21)
+ AWAIT 'await' (1, 22) (1, 27)
+ """)
+
+ self.check_tokenize('''\
+def f():
+
+ def baz(): pass
+ async def bar(): pass
+
+ await = 2''', """\
+ NAME 'def' (1, 0) (1, 3)
+ NAME 'f' (1, 4) (1, 5)
+ LPAR '(' (1, 5) (1, 6)
+ RPAR ')' (1, 6) (1, 7)
+ COLON ':' (1, 7) (1, 8)
+ NEWLINE '' (1, 8) (1, 8)
+ INDENT '' (3, -1) (3, -1)
+ NAME 'def' (3, 2) (3, 5)
+ NAME 'baz' (3, 6) (3, 9)
+ LPAR '(' (3, 9) (3, 10)
+ RPAR ')' (3, 10) (3, 11)
+ COLON ':' (3, 11) (3, 12)
+ NAME 'pass' (3, 13) (3, 17)
+ NEWLINE '' (3, 17) (3, 17)
+ ASYNC 'async' (4, 2) (4, 7)
+ NAME 'def' (4, 8) (4, 11)
+ NAME 'bar' (4, 12) (4, 15)
+ LPAR '(' (4, 15) (4, 16)
+ RPAR ')' (4, 16) (4, 17)
+ COLON ':' (4, 17) (4, 18)
+ NAME 'pass' (4, 19) (4, 23)
+ NEWLINE '' (4, 23) (4, 23)
+ AWAIT 'await' (6, 2) (6, 7)
+ EQUAL '=' (6, 8) (6, 9)
+ NUMBER '2' (6, 10) (6, 11)
+ DEDENT '' (6, -1) (6, -1)
+ """)
+
+ self.check_tokenize('''\
+async def f():
+
+ def baz(): pass
+ async def bar(): pass
+
+ await = 2''', """\
+ ASYNC 'async' (1, 0) (1, 5)
+ NAME 'def' (1, 6) (1, 9)
+ NAME 'f' (1, 10) (1, 11)
+ LPAR '(' (1, 11) (1, 12)
+ RPAR ')' (1, 12) (1, 13)
+ COLON ':' (1, 13) (1, 14)
+ NEWLINE '' (1, 14) (1, 14)
+ INDENT '' (3, -1) (3, -1)
+ NAME 'def' (3, 2) (3, 5)
+ NAME 'baz' (3, 6) (3, 9)
+ LPAR '(' (3, 9) (3, 10)
+ RPAR ')' (3, 10) (3, 11)
+ COLON ':' (3, 11) (3, 12)
+ NAME 'pass' (3, 13) (3, 17)
+ NEWLINE '' (3, 17) (3, 17)
+ ASYNC 'async' (4, 2) (4, 7)
+ NAME 'def' (4, 8) (4, 11)
+ NAME 'bar' (4, 12) (4, 15)
+ LPAR '(' (4, 15) (4, 16)
+ RPAR ')' (4, 16) (4, 17)
+ COLON ':' (4, 17) (4, 18)
+ NAME 'pass' (4, 19) (4, 23)
+ NEWLINE '' (4, 23) (4, 23)
+ AWAIT 'await' (6, 2) (6, 7)
+ EQUAL '=' (6, 8) (6, 9)
+ NUMBER '2' (6, 10) (6, 11)
+ DEDENT '' (6, -1) (6, -1)
+ """)
+
+ def test_unicode(self):
+
+ self.check_tokenize("Örter = u'places'\ngrün = U'green'", """\
+ NAME 'Örter' (1, 0) (1, 6)
+ EQUAL '=' (1, 7) (1, 8)
+ STRING "u'places'" (1, 9) (1, 18)
+ NEWLINE '' (1, 18) (1, 18)
+ NAME 'grün' (2, 0) (2, 5)
+ EQUAL '=' (2, 6) (2, 7)
+ STRING "U'green'" (2, 8) (2, 16)
+ """)
+
+ 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, "]")
+
+
if __name__ == "__main__":
unittest.main()
diff --git a/Lib/tokenize.py b/Lib/tokenize.py
index 7d7736fe985981..0b9e238310049c 100644
--- a/Lib/tokenize.py
+++ b/Lib/tokenize.py
@@ -680,5 +680,13 @@ def error(message, filename=None, location=None):
perror("unexpected error: %s" % err)
raise
+def _generate_tokens_from_c_tokenizer(source):
+ """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):
+ tok, type, lineno, end_lineno, col_off, end_col_off, line = info
+ yield TokenInfo(type, tok, (lineno, col_off), (end_lineno, end_col_off), line)
+
+
if __name__ == "__main__":
main()
diff --git a/Makefile.pre.in b/Makefile.pre.in
index f503ac4d876726..1007f440759b1a 100644
--- a/Makefile.pre.in
+++ b/Makefile.pre.in
@@ -339,6 +339,7 @@ PARSER_HEADERS= \
PYTHON_OBJS= \
Python/_warnings.o \
Python/Python-ast.o \
+ Python/Python-tokenize.o \
Python/asdl.o \
Python/ast.o \
Python/ast_opt.o \
diff --git a/Modules/config.c.in b/Modules/config.c.in
index d69e8e88b0ca45..6081f95759538f 100644
--- a/Modules/config.c.in
+++ b/Modules/config.c.in
@@ -28,6 +28,7 @@ extern PyObject* PyMarshal_Init(void);
extern PyObject* PyInit__imp(void);
extern PyObject* PyInit_gc(void);
extern PyObject* PyInit__ast(void);
+extern PyObject* PyInit__tokenize(void);
extern PyObject* _PyWarnings_Init(void);
extern PyObject* PyInit__string(void);
@@ -44,6 +45,9 @@ struct _inittab _PyImport_Inittab[] = {
/* This lives in Python/Python-ast.c */
{"_ast", PyInit__ast},
+ /* This lives in Python/Python-tokenizer.c */
+ {"_tokenize", PyInit__tokenize},
+
/* These entries are here for sys.builtin_module_names */
{"builtins", NULL},
{"sys", NULL},
diff --git a/PC/config.c b/PC/config.c
index 11743ea45a969d..9d900c78e40d00 100644
--- a/PC/config.c
+++ b/PC/config.c
@@ -72,9 +72,8 @@ extern PyObject* _PyWarnings_Init(void);
extern PyObject* PyInit__string(void);
extern PyObject* PyInit__stat(void);
extern PyObject* PyInit__opcode(void);
-
extern PyObject* PyInit__contextvars(void);
-
+extern PyObject* PyInit__tokenize(void);
/* tools/freeze/makeconfig.py marker for additional "extern" */
/* -- ADDMODULE MARKER 1 -- */
@@ -83,7 +82,6 @@ extern PyObject* PyMarshal_Init(void);
extern PyObject* PyInit__imp(void);
struct _inittab _PyImport_Inittab[] = {
-
{"_abc", PyInit__abc},
{"array", PyInit_array},
{"_ast", PyInit__ast},
@@ -105,6 +103,7 @@ struct _inittab _PyImport_Inittab[] = {
{"_blake2", PyInit__blake2},
{"time", PyInit_time},
{"_thread", PyInit__thread},
+ {"_tokenize", PyInit__tokenize},
{"_typing", PyInit__typing},
{"_statistics", PyInit__statistics},
#ifdef WIN32
diff --git a/PCbuild/pythoncore.vcxproj b/PCbuild/pythoncore.vcxproj
index ebc0f2879f9595..b8cadf469355f4 100644
--- a/PCbuild/pythoncore.vcxproj
+++ b/PCbuild/pythoncore.vcxproj
@@ -488,6 +488,7 @@
<ClCompile Include="..\Python\pystrtod.c" />
<ClCompile Include="..\Python\dtoa.c" />
<ClCompile Include="..\Python\Python-ast.c" />
+ <ClCompile Include="..\Python\Python-tokenize.c" />
<ClCompile Include="..\Python\pythonrun.c" />
<ClCompile Include="..\Python\specialize.c" />
<ClCompile Include="..\Python\suggestions.c" />
diff --git a/Python/Python-tokenize.c b/Python/Python-tokenize.c
new file mode 100644
index 00000000000000..b9fb1693ce117e
--- /dev/null
+++ b/Python/Python-tokenize.c
@@ -0,0 +1,195 @@
+#include "Python.h"
+#include "../Parser/tokenizer.h"
+
+static struct PyModuleDef _tokenizemodule;
+
+typedef struct {
+ PyTypeObject* TokenizerIter;
+} tokenize_state;
+
+static tokenize_state*
+get_tokenize_state(PyObject* module)
+{
+ return (tokenize_state*)PyModule_GetState(module);
+}
+
+#define _tokenize_get_state_by_type(type) \
+ get_tokenize_state(_PyType_GetModuleByDef(type, &_tokenizemodule))
+
+#include "clinic/Python-tokenize.c.h"
+
+/*[clinic input]
+module _tokenizer
+class _tokenizer.tokenizeriter "tokenizeriterobject *" "_tokenize_get_state_by_type(type)->TokenizerIter"
+[clinic start generated code]*/
+/*[clinic end generated code: output=da39a3ee5e6b4b0d input=96d98ee2fef7a8bc]*/
+
+typedef struct {
+ PyObject_HEAD
+ struct tok_state* tok;
+} tokenizeriterobject;
+
+/*[clinic input]
+ at classmethod
+_tokenizer.tokenizeriter.__new__ as tokenizeriter_new
+
+ source: str
+[clinic start generated code]*/
+
+static PyObject *
+tokenizeriter_new_impl(PyTypeObject *type, const char *source)
+/*[clinic end generated code: output=7fd9f46cf9263cbb input=4384b368407375c6]*/
+{
+ tokenizeriterobject* self = (tokenizeriterobject*)type->tp_alloc(type, 0);
+ if (self == NULL) {
+ return NULL;
+ }
+ PyObject* filename = PyUnicode_FromString("<string>");
+ if (filename == NULL) {
+ return NULL;
+ }
+ self->tok = PyTokenizer_FromUTF8(source, 1);
+ if (self->tok == NULL) {
+ return NULL;
+ }
+ self->tok->filename = filename;
+ return (PyObject*)self;
+}
+
+static PyObject*
+tokenizeriter_next(tokenizeriterobject* it)
+{
+ const char* start;
+ const char* end;
+ int type = PyTokenizer_Get(it->tok, &start, &end);
+ if (type == ERRORTOKEN && PyErr_Occurred()) {
+ return NULL;
+ }
+ if (type == ERRORTOKEN || type == ENDMARKER) {
+ PyErr_SetString(PyExc_StopIteration, "EOF");
+ return NULL;
+ }
+ PyObject* str = NULL;
+ if (start == NULL || end == NULL) {
+ str = PyUnicode_FromString("");
+ } else {
+ str = PyUnicode_FromStringAndSize(start, end - start);
+ }
+ if (str == NULL) {
+ return NULL;
+ }
+
+ Py_ssize_t size = it->tok->inp - it->tok->buf;
+ PyObject* line = PyUnicode_DecodeUTF8(it->tok->buf, size, "replace");
+ if (line == NULL) {
+ Py_DECREF(str);
+ return NULL;
+ }
+ const char* line_start = type == STRING ? it->tok->multi_line_start : it->tok->line_start;
+ int lineno = type == STRING ? it->tok->first_lineno : it->tok->lineno;
+ int end_lineno = it->tok->lineno;
+ int col_offset = -1;
+ int end_col_offset = -1;
+ if (start != NULL && start >= line_start) {
+ col_offset = (int)(start - line_start);
+ }
+ if (end != NULL && end >= it->tok->line_start) {
+ end_col_offset = (int)(end - it->tok->line_start);
+ }
+
+ return Py_BuildValue("(NiiiiiN)", str, type, lineno, end_lineno, col_offset, end_col_offset, line);
+}
+
+static void
+tokenizeriter_dealloc(tokenizeriterobject* it)
+{
+ PyTypeObject* tp = Py_TYPE(it);
+ PyTokenizer_Free(it->tok);
+ tp->tp_free(it);
+ Py_DECREF(tp);
+}
+
+static PyType_Slot tokenizeriter_slots[] = {
+ {Py_tp_new, tokenizeriter_new},
+ {Py_tp_dealloc, tokenizeriter_dealloc},
+ {Py_tp_getattro, PyObject_GenericGetAttr},
+ {Py_tp_iter, PyObject_SelfIter},
+ {Py_tp_iternext, tokenizeriter_next},
+ {0, NULL},
+};
+
+static PyType_Spec tokenizeriter_spec = {
+ .name = "_tokenize.TokenizerIter",
+ .basicsize = sizeof(tokenizeriterobject),
+ .flags = (Py_TPFLAGS_DEFAULT | Py_TPFLAGS_IMMUTABLETYPE),
+ .slots = tokenizeriter_slots,
+};
+
+
+static int
+tokenizemodule_exec(PyObject* m)
+{
+ tokenize_state* state = get_tokenize_state(m);
+ if (state == NULL) {
+ return -1;
+ }
+
+ state->TokenizerIter = (PyTypeObject *)PyType_FromModuleAndSpec(
+ m, &tokenizeriter_spec, NULL);
+ if (state->TokenizerIter == NULL) {
+ return -1;
+ }
+ if (PyModule_AddType(m, state->TokenizerIter) < 0) {
+ return -1;
+ }
+
+ return 0;
+}
+
+static PyMethodDef tokenize_methods[] = {
+ {NULL, NULL, 0, NULL} /* Sentinel */
+};
+
+static PyModuleDef_Slot tokenizemodule_slots[] = {
+ {Py_mod_exec, tokenizemodule_exec},
+ {0, NULL}
+};
+
+static int
+tokenizemodule_traverse(PyObject *m, visitproc visit, void *arg)
+{
+ tokenize_state *state = get_tokenize_state(m);
+ Py_VISIT(state->TokenizerIter);
+ return 0;
+}
+
+static int
+tokenizemodule_clear(PyObject *m)
+{
+ tokenize_state *state = get_tokenize_state(m);
+ Py_CLEAR(state->TokenizerIter);
+ return 0;
+}
+
+static void
+tokenizemodule_free(void *m)
+{
+ tokenizemodule_clear((PyObject *)m);
+}
+
+static struct PyModuleDef _tokenizemodule = {
+ PyModuleDef_HEAD_INIT,
+ .m_name = "_tokenize",
+ .m_size = sizeof(tokenize_state),
+ .m_slots = tokenizemodule_slots,
+ .m_methods = tokenize_methods,
+ .m_traverse = tokenizemodule_traverse,
+ .m_clear = tokenizemodule_clear,
+ .m_free = tokenizemodule_free,
+};
+
+PyMODINIT_FUNC
+PyInit__tokenize(void)
+{
+ return PyModuleDef_Init(&_tokenizemodule);
+}
diff --git a/Python/clinic/Python-tokenize.c.h b/Python/clinic/Python-tokenize.c.h
new file mode 100644
index 00000000000000..050b4d49448c36
--- /dev/null
+++ b/Python/clinic/Python-tokenize.c.h
@@ -0,0 +1,41 @@
+/*[clinic input]
+preserve
+[clinic start generated code]*/
+
+static PyObject *
+tokenizeriter_new_impl(PyTypeObject *type, const char *source);
+
+static PyObject *
+tokenizeriter_new(PyTypeObject *type, PyObject *args, PyObject *kwargs)
+{
+ PyObject *return_value = NULL;
+ static const char * const _keywords[] = {"source", NULL};
+ static _PyArg_Parser _parser = {NULL, _keywords, "tokenizeriter", 0};
+ PyObject *argsbuf[1];
+ PyObject * const *fastargs;
+ Py_ssize_t nargs = PyTuple_GET_SIZE(args);
+ const char *source;
+
+ fastargs = _PyArg_UnpackKeywords(_PyTuple_CAST(args)->ob_item, nargs, kwargs, NULL, &_parser, 1, 1, 0, argsbuf);
+ if (!fastargs) {
+ goto exit;
+ }
+ if (!PyUnicode_Check(fastargs[0])) {
+ _PyArg_BadArgument("tokenizeriter", "argument 'source'", "str", fastargs[0]);
+ goto exit;
+ }
+ Py_ssize_t source_length;
+ source = PyUnicode_AsUTF8AndSize(fastargs[0], &source_length);
+ if (source == NULL) {
+ goto exit;
+ }
+ if (strlen(source) != (size_t)source_length) {
+ PyErr_SetString(PyExc_ValueError, "embedded null character");
+ goto exit;
+ }
+ return_value = tokenizeriter_new_impl(type, source);
+
+exit:
+ return return_value;
+}
+/*[clinic end generated code: output=dfcd64774e01bfe6 input=a9049054013a1b77]*/
diff --git a/Python/stdlib_module_names.h b/Python/stdlib_module_names.h
index 3c5f1768305cb0..2f75c2e54cd5e9 100644
--- a/Python/stdlib_module_names.h
+++ b/Python/stdlib_module_names.h
@@ -80,6 +80,7 @@ static const char* _Py_stdlib_module_names[] = {
"_thread",
"_threading_local",
"_tkinter",
+"_tokenize",
"_tracemalloc",
"_typing",
"_uuid",
More information about the Python-checkins
mailing list