WIP

pablogsal · pablogsal · commit b3bae11717d4 · 2023-05-29T15:24:36.000+01:00
diff --git a/Lib/test/test_tokenize.py b/Lib/test/test_tokenize.py
@@ -1827,9 +1827,10 @@ 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())
 
diff --git a/Lib/tokenize.py b/Lib/tokenize.py
@@ -446,8 +446,14 @@ def tokenize(readline):
     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):
+    def gen(rl_gen):
+        while True:
+            try:
+                yield next(rl_gen).decode(encoding)
+            except StopIteration:
+                return
+    g = gen(rl_gen)
+    for token in _generate_tokens_from_c_tokenizer(g.__next__, extra_tokens=True):
         yield token
 
 def generate_tokens(readline):
diff --git a/Parser/tokenizer.c b/Parser/tokenizer.c
@@ -542,7 +542,13 @@ tok_readline_recode(struct tok_state *tok) {
     if (line == NULL) {
         line = PyObject_CallNoArgs(tok->decoding_readline);
         if (line == NULL) {
-            error_ret(tok);
+            if (!PyErr_ExceptionMatches(PyExc_StopIteration)) {
+                error_ret(tok);
+            } else {
+                PyErr_Clear();
+                tok->inp = tok->cur;
+                tok->done = E_EOF;
+            }
             goto error;
         }
     }
@@ -569,6 +575,7 @@ tok_readline_recode(struct tok_state *tok) {
         goto error;
     }
     Py_DECREF(line);
+exit:
     return 1;
 error:
     Py_XDECREF(line);
@@ -900,6 +907,30 @@ _PyTokenizer_FromString(const char *str, int exec_input, int preserve_crlf)
     return tok;
 }
 
+struct tok_state *
+_PyTokenizer_FromUTF8Readline(PyObject* readline, int exec_input, int preserve_crlf)
+{
+    struct tok_state *tok = tok_new();
+    if (tok == NULL)
+        return NULL;
+    if ((tok->buf = (char *)PyMem_Malloc(BUFSIZ)) == NULL) {
+        _PyTokenizer_Free(tok);
+        return NULL;
+    }
+    tok->cur = tok->inp = tok->buf;
+    tok->end = tok->buf + BUFSIZ;
+    tok->fp = NULL;
+
+    tok->enc = NULL;
+    tok->encoding = new_string("utf-8", 5, tok);
+    Py_INCREF(readline);
+    tok->decoding_readline = readline;
+    tok->decoding_state = STATE_NORMAL;
+    return tok;
+}
+
+
+
 /* Set up tokenizer for UTF-8 string */
 
 struct tok_state *
@@ -1238,7 +1269,10 @@ tok_nextc(struct tok_state *tok)
         if (tok->done != E_OK) {
             return EOF;
         }
-        if (tok->fp == NULL) {
+        if (tok->decoding_readline != NULL) {
+            rc = tok_underflow_file(tok);
+        }
+        else if (tok->fp == NULL) {
             rc = tok_underflow_string(tok);
         }
         else if (tok->prompt != NULL) {
diff --git a/Parser/tokenizer.h b/Parser/tokenizer.h
@@ -137,6 +137,7 @@ struct tok_state {
 
 extern struct tok_state *_PyTokenizer_FromString(const char *, int, int);
 extern struct tok_state *_PyTokenizer_FromUTF8(const char *, int, int);
+extern struct tok_state *_PyTokenizer_FromUTF8Readline(PyObject*, int, int);
 extern struct tok_state *_PyTokenizer_FromFile(FILE *, const char*,
                                               const char *, const char *);
 extern void _PyTokenizer_Free(struct tok_state *);
diff --git a/Python/Python-tokenize.c b/Python/Python-tokenize.c
@@ -37,15 +37,15 @@ typedef struct
 @classmethod
 _tokenizer.tokenizeriter.__new__ as tokenizeriter_new
 
-    source: str
+    source: object
     *
     extra_tokens: bool
 [clinic start generated code]*/
 
 static PyObject *
-tokenizeriter_new_impl(PyTypeObject *type, const char *source,
+tokenizeriter_new_impl(PyTypeObject *type, PyObject *source,
                        int extra_tokens)
-/*[clinic end generated code: output=f6f9d8b4beec8106 input=90dc5b6a5df180c2]*/
+/*[clinic end generated code: output=f174f61e34b2c306 input=32ddfe6d52575938]*/
 {
     tokenizeriterobject *self = (tokenizeriterobject *)type->tp_alloc(type, 0);
     if (self == NULL) {
@@ -55,7 +55,7 @@ tokenizeriter_new_impl(PyTypeObject *type, const char *source,
     if (filename == NULL) {
         return NULL;
     }
-    self->tok = _PyTokenizer_FromUTF8(source, 1, 1);
+    self->tok = _PyTokenizer_FromUTF8Readline(source, 1, 1);
     if (self->tok == NULL) {
         Py_DECREF(filename);
         return NULL;
diff --git a/Python/clinic/Python-tokenize.c.h b/Python/clinic/Python-tokenize.c.h
