gh-112243: Don't include comments in f-string debug expressions (#112284)

diff --git a/Lib/test/test_fstring.py b/Lib/test/test_fstring.py
index dd8c2dd628ee13582802347da57fe1456e4e4ca8..da0160d2382cc6b028bfff3c8c79279b2c50e088 100644 (file)
--- a/Lib/test/test_fstring.py
+++ b/Lib/test/test_fstring.py
@@ -1627,6 +1627,9 @@ x = (
         self.assertEqual(f'X{x  =  }Y', 'Xx  =  '+repr(x)+'Y')
         self.assertEqual(f"sadsd {1 + 1 =  :{1 + 1:1d}f}", "sadsd 1 + 1 =  2.000000")
 
+        self.assertEqual(f"{1+2 = # my comment
+  }", '1+2 = \n  3')
+
         # These next lines contains tabs.  Backslash escapes don't
         # work in f-strings.
         # patchcheck doesn't like these tabs.  So the only way to test

diff --git a/Misc/NEWS.d/next/Core and Builtins/2023-11-20-14-13-02.gh-issue-112243.FKdQnr.rst b/Misc/NEWS.d/next/Core and Builtins/2023-11-20-14-13-02.gh-issue-112243.FKdQnr.rst
new file mode 100644 (file)
index 0000000..d69f29f
--- /dev/null
+++ b/Misc/NEWS.d/next/Core and Builtins/2023-11-20-14-13-02.gh-issue-112243.FKdQnr.rst
@@ -0,0 +1 @@
+Don't include comments in f-string debug expressions. Patch by Pablo Galindo

diff --git a/Parser/lexer/lexer.c b/Parser/lexer/lexer.c
index 2ba24a2c2405f222b242cb01cb09e16a4f44f947..ea4bdf7ce4a24c1eb99d08da016417cb99f9facd 100644 (file)
--- a/Parser/lexer/lexer.c
+++ b/Parser/lexer/lexer.c
@@ -116,13 +116,56 @@ set_fstring_expr(struct tok_state* tok, struct token *token, char c) {
     if (!tok_mode->f_string_debug || token->metadata) {
         return 0;
     }
+    PyObject *res = NULL;
 
-    PyObject *res = PyUnicode_DecodeUTF8(
-        tok_mode->last_expr_buffer,
-        tok_mode->last_expr_size - tok_mode->last_expr_end,
-        NULL
-    );
-    if (!res) {
+    // Check if there is a # character in the expression
+    int hash_detected = 0;
+    for (Py_ssize_t i = 0; i < tok_mode->last_expr_size - tok_mode->last_expr_end; i++) {
+        if (tok_mode->last_expr_buffer[i] == '#') {
+            hash_detected = 1;
+            break;
+        }
+    }
+
+    if (hash_detected) {
+        Py_ssize_t input_length = tok_mode->last_expr_size - tok_mode->last_expr_end;
+        char *result = (char *)PyObject_Malloc((input_length + 1) * sizeof(char));
+        if (!result) {
+            return -1;
+        }
+
+        Py_ssize_t i = 0;
+        Py_ssize_t j = 0;
+
+        for (i = 0, j = 0; i < input_length; i++) {
+            if (tok_mode->last_expr_buffer[i] == '#') {
+                // Skip characters until newline or end of string
+                while (tok_mode->last_expr_buffer[i] != '\0' && i < input_length) {
+                    if (tok_mode->last_expr_buffer[i] == '\n') {
+                        result[j++] = tok_mode->last_expr_buffer[i];
+                        break;
+                    }
+                    i++;
+                }
+            } else {
+                result[j++] = tok_mode->last_expr_buffer[i];
+            }
+        }
+
+        result[j] = '\0';  // Null-terminate the result string
+        res = PyUnicode_DecodeUTF8(result, j, NULL);
+        PyObject_Free(result);
+    } else {
+        res = PyUnicode_DecodeUTF8(
+            tok_mode->last_expr_buffer,
+            tok_mode->last_expr_size - tok_mode->last_expr_end,
+            NULL
+        );
+
+    }
+
+
+   if (!res) {
         return -1;
     }
     token->metadata = res;