Merge branch 'master' into remove-atan2-helpers-122681

Doc/library/inspect.rst

@@ -153,6 +153,19 @@ attributes (see :ref:`import-mod-attrs` for module attributes):
 |                 | f_trace           | tracing function for this |
 |                 |                   | frame, or ``None``        |
 +-----------------+-------------------+---------------------------+
+|                 | f_trace_lines     | indicate whether a        |
+|                 |                   | tracing event is          |
+|                 |                   | triggered for each source |
+|                 |                   | source line               |
++-----------------+-------------------+---------------------------+
+|                 | f_trace_opcodes   | indicate whether          |
+|                 |                   | per-opcode events are     |
+|                 |                   | requested                 |
++-----------------+-------------------+---------------------------+
+|                 | clear()           | used to clear all         |
+|                 |                   | references to local       |
+|                 |                   | variables                 |
++-----------------+-------------------+---------------------------+
 | code            | co_argcount       | number of arguments (not  |
 |                 |                   | including keyword only    |
 |                 |                   | arguments, \* or \*\*     |
@@ -214,6 +227,18 @@ attributes (see :ref:`import-mod-attrs` for module attributes):
 |                 |                   | arguments and local       |
 |                 |                   | variables                 |
 +-----------------+-------------------+---------------------------+
+|                 | co_lines()        | returns an iterator that  |
+|                 |                   | yields successive         |
+|                 |                   | bytecode ranges           |
++-----------------+-------------------+---------------------------+
+|                 | co_positions()    | returns an iterator of    |
+|                 |                   | source code positions for |
+|                 |                   | each bytecode instruction |
++-----------------+-------------------+---------------------------+
+|                 | replace()         | returns a copy of the     |
+|                 |                   | code object with new      |
+|                 |                   | values                    |
++-----------------+-------------------+---------------------------+
 | generator       | __name__          | name                      |
 +-----------------+-------------------+---------------------------+
 |                 | __qualname__      | qualified name            |

Include/internal/pycore_parser.h

@@ -21,15 +21,20 @@ extern "C" {
 struct _parser_runtime_state {
 #ifdef Py_DEBUG
     long memo_statistics[_PYPEGEN_NSTATISTICS];
+#ifdef Py_GIL_DISABLED
+    PyMutex mutex;
+#endif
 #else
     int _not_used;
 #endif
     struct _expr dummy_name;
 };
 
 _Py_DECLARE_STR(empty, "")
+#if defined(Py_DEBUG) && defined(Py_GIL_DISABLED)
 #define _parser_runtime_state_INIT \
     { \
+        .mutex = {0}, \
         .dummy_name = { \
             .kind = Name_kind, \
             .v.Name.id = &_Py_STR(empty), \
@@ -40,6 +45,20 @@ _Py_DECLARE_STR(empty, "")
             .end_col_offset = 0, \
         }, \
     }
+#else
+#define _parser_runtime_state_INIT \
+    { \
+        .dummy_name = { \
+            .kind = Name_kind, \
+            .v.Name.id = &_Py_STR(empty), \
+            .v.Name.ctx = Load, \
+            .lineno = 1, \
+            .col_offset = 0, \
+            .end_lineno = 1, \
+            .end_col_offset = 0, \
+        }, \
+    }
+#endif
 
 extern struct _mod* _PyParser_ASTFromString(
     const char *str,

Lib/_android_support.py

@@ -1,19 +1,20 @@
 import io
 import sys
-
+from threading import RLock
+from time import sleep, time
 
 # The maximum length of a log message in bytes, including the level marker and
-# tag, is defined as LOGGER_ENTRY_MAX_PAYLOAD in
-# platform/system/logging/liblog/include/log/log.h. As of API level 30, messages
-# longer than this will be be truncated by logcat. This limit has already been
-# reduced at least once in the history of Android (from 4076 to 4068 between API
-# level 23 and 26), so leave some headroom.
+# tag, is defined as LOGGER_ENTRY_MAX_PAYLOAD at
+# https://cs.android.com/android/platform/superproject/+/android-14.0.0_r1:system/logging/liblog/include/log/log.h;l=71.
+# Messages longer than this will be be truncated by logcat. This limit has already
+# been reduced at least once in the history of Android (from 4076 to 4068 between
+# API level 23 and 26), so leave some headroom.
 MAX_BYTES_PER_WRITE = 4000
 
 # UTF-8 uses a maximum of 4 bytes per character, so limiting text writes to this
-# size ensures that TextIOWrapper can always avoid exceeding MAX_BYTES_PER_WRITE.
+# size ensures that we can always avoid exceeding MAX_BYTES_PER_WRITE.
 # However, if the actual number of bytes per character is smaller than that,
-# then TextIOWrapper may still join multiple consecutive text writes into binary
+# then we may still join multiple consecutive text writes into binary
 # writes containing a larger number of characters.
 MAX_CHARS_PER_WRITE = MAX_BYTES_PER_WRITE // 4
 
@@ -26,18 +27,22 @@ def init_streams(android_log_write, stdout_prio, stderr_prio):
     if sys.executable:
         return  # Not embedded in an app.
 
+    global logcat
+    logcat = Logcat(android_log_write)
+
     sys.stdout = TextLogStream(
-        android_log_write, stdout_prio, "python.stdout", errors=sys.stdout.errors)
+        stdout_prio, "python.stdout", errors=sys.stdout.errors)
     sys.stderr = TextLogStream(
-        android_log_write, stderr_prio, "python.stderr", errors=sys.stderr.errors)
+        stderr_prio, "python.stderr", errors=sys.stderr.errors)
 
 
 class TextLogStream(io.TextIOWrapper):
-    def __init__(self, android_log_write, prio, tag, **kwargs):
+    def __init__(self, prio, tag, **kwargs):
         kwargs.setdefault("encoding", "UTF-8")
-        kwargs.setdefault("line_buffering", True)
-        super().__init__(BinaryLogStream(android_log_write, prio, tag), **kwargs)
-        self._CHUNK_SIZE = MAX_BYTES_PER_WRITE
+        super().__init__(BinaryLogStream(prio, tag), **kwargs)
+        self._lock = RLock()
+        self._pending_bytes = []
+        self._pending_bytes_count = 0
 
     def __repr__(self):
         return f"<TextLogStream {self.buffer.tag!r}>"
@@ -52,19 +57,48 @@ def write(self, s):
         s = str.__str__(s)
 
         # We want to emit one log message per line wherever possible, so split
-        # the string before sending it to the superclass. Note that
-        # "".splitlines() == [], so nothing will be logged for an empty string.
-        for line in s.splitlines(keepends=True):
-            while line:
-                super().write(line[:MAX_CHARS_PER_WRITE])
-                line = line[MAX_CHARS_PER_WRITE:]
+        # the string into lines first. Note that "".splitlines() == [], so
+        # nothing will be logged for an empty string.
+        with self._lock:
+            for line in s.splitlines(keepends=True):
+                while line:
+                    chunk = line[:MAX_CHARS_PER_WRITE]
+                    line = line[MAX_CHARS_PER_WRITE:]
+                    self._write_chunk(chunk)
 
         return len(s)
 
+    # The size and behavior of TextIOWrapper's buffer is not part of its public
+    # API, so we handle buffering ourselves to avoid truncation.
+    def _write_chunk(self, s):
+        b = s.encode(self.encoding, self.errors)
+        if self._pending_bytes_count + len(b) > MAX_BYTES_PER_WRITE:
+            self.flush()
+
+        self._pending_bytes.append(b)
+        self._pending_bytes_count += len(b)
+        if (
+            self.write_through
+            or b.endswith(b"\n")
+            or self._pending_bytes_count > MAX_BYTES_PER_WRITE
+        ):
+            self.flush()
+
+    def flush(self):
+        with self._lock:
+            self.buffer.write(b"".join(self._pending_bytes))
+            self._pending_bytes.clear()
+            self._pending_bytes_count = 0
+
+    # Since this is a line-based logging system, line buffering cannot be turned
+    # off, i.e. a newline always causes a flush.
+    @property
+    def line_buffering(self):
+        return True
+
 
 class BinaryLogStream(io.RawIOBase):
-    def __init__(self, android_log_write, prio, tag):
-        self.android_log_write = android_log_write
+    def __init__(self, prio, tag):
         self.prio = prio
         self.tag = tag
 
@@ -85,10 +119,48 @@ def write(self, b):
 
         # Writing an empty string to the stream should have no effect.
         if b:
-            # Encode null bytes using "modified UTF-8" to avoid truncating the
-            # message. This should not affect the return value, as the caller
-            # may be expecting it to match the length of the input.
-            self.android_log_write(self.prio, self.tag,
-                                   b.replace(b"\x00", b"\xc0\x80"))
-
+            logcat.write(self.prio, self.tag, b)
         return len(b)
+
+
+# When a large volume of data is written to logcat at once, e.g. when a test
+# module fails in --verbose3 mode, there's a risk of overflowing logcat's own
+# buffer and losing messages. We avoid this by imposing a rate limit using the
+# token bucket algorithm, based on a conservative estimate of how fast `adb
+# logcat` can consume data.
+MAX_BYTES_PER_SECOND = 1024 * 1024
+
+# The logcat buffer size of a device can be determined by running `logcat -g`.
+# We set the token bucket size to half of the buffer size of our current minimum
+# API level, because other things on the system will be producing messages as
+# well.
+BUCKET_SIZE = 128 * 1024
+
+# https://cs.android.com/android/platform/superproject/+/android-14.0.0_r1:system/logging/liblog/include/log/log_read.h;l=39
+PER_MESSAGE_OVERHEAD = 28
+
+
+class Logcat:
+    def __init__(self, android_log_write):
+        self.android_log_write = android_log_write
+        self._lock = RLock()
+        self._bucket_level = 0
+        self._prev_write_time = time()
+
+    def write(self, prio, tag, message):
+        # Encode null bytes using "modified UTF-8" to avoid them truncating the
+        # message.
+        message = message.replace(b"\x00", b"\xc0\x80")
+
+        with self._lock:
+            now = time()
+            self._bucket_level += (
+                (now - self._prev_write_time) * MAX_BYTES_PER_SECOND)
+            self._bucket_level = min(self._bucket_level, BUCKET_SIZE)
+            self._prev_write_time = now
+
+            self._bucket_level -= PER_MESSAGE_OVERHEAD + len(tag) + len(message)
+            if self._bucket_level < 0:
+                sleep(-self._bucket_level / MAX_BYTES_PER_SECOND)
+
+            self.android_log_write(prio, tag, message)

Lib/inspect.py

@@ -264,11 +264,16 @@ def isfunction(object):
     Function objects provide these attributes:
         __doc__         documentation string
         __name__        name with which this function was defined
+        __qualname__    qualified name of this function
+        __module__      name of the module the function was defined in or None
         __code__        code object containing compiled function bytecode
         __defaults__    tuple of any default values for arguments
         __globals__     global namespace in which this function was defined
         __annotations__ dict of parameter annotations
-        __kwdefaults__  dict of keyword only parameters with defaults"""
+        __kwdefaults__  dict of keyword only parameters with defaults
+        __dict__        namespace which is supporting arbitrary function attributes
+        __closure__     a tuple of cells or None
+        __type_params__ tuple of type parameters"""
     return isinstance(object, types.FunctionType)
 
 def _has_code_flag(f, flag):
@@ -333,17 +338,18 @@ def isgenerator(object):
     """Return true if the object is a generator.
 
     Generator objects provide these attributes:
-        __iter__        defined to support iteration over container
-        close           raises a new GeneratorExit exception inside the
-                        generator to terminate the iteration
         gi_code         code object
         gi_frame        frame object or possibly None once the generator has
                         been exhausted
         gi_running      set to 1 when generator is executing, 0 otherwise
-        next            return the next item from the container
-        send            resumes the generator and "sends" a value that becomes
+        gi_yieldfrom    object being iterated by yield from or None
+
+        __iter__()      defined to support iteration over container
+        close()         raises a new GeneratorExit exception inside the
+                        generator to terminate the iteration
+        send()          resumes the generator and "sends" a value that becomes
                         the result of the current yield-expression
-        throw           used to raise an exception inside the generator"""
+        throw()         used to raise an exception inside the generator"""
     return isinstance(object, types.GeneratorType)
 
 def iscoroutine(object):
@@ -378,7 +384,11 @@ def isframe(object):
         f_lasti         index of last attempted instruction in bytecode
         f_lineno        current line number in Python source code
         f_locals        local namespace seen by this frame
-        f_trace         tracing function for this frame, or None"""
+        f_trace         tracing function for this frame, or None
+        f_trace_lines   is a tracing event triggered for each source line?
+        f_trace_opcodes are per-opcode events being requested?
+
+        clear()          used to clear all references to local variables"""
     return isinstance(object, types.FrameType)
 
 def iscode(object):
@@ -403,7 +413,12 @@ def iscode(object):
         co_names            tuple of names other than arguments and function locals
         co_nlocals          number of local variables
         co_stacksize        virtual machine stack space required
-        co_varnames         tuple of names of arguments and local variables"""
+        co_varnames         tuple of names of arguments and local variables
+        co_qualname         fully qualified function name
+
+        co_lines()          returns an iterator that yields successive bytecode ranges
+        co_positions()      returns an iterator of source code positions for each bytecode instruction
+        replace()           returns a copy of the code object with a new values"""
     return isinstance(object, types.CodeType)
 
 def isbuiltin(object):

Lib/re/_casefix.py

@@ -1,4 +1,4 @@
-# Auto-generated by Tools/scripts/generate_re_casefix.py.
+# Auto-generated by Tools/build/generate_re_casefix.py.
 
 # Maps the code of lowercased character to codes of different lowercased
 # characters which have the same uppercase.