GitLab

The GreenHills preprocessor produces #line directives without a file name,
which the regular expression used to distiguish between
"# <number> file..." (GCC and similar) and "#line <number> file..."
(Microsoft C and similar) does not match, aborting processing.

Besides, the regular expression was unnecessarily wide, matching lines
containing a "#", followed by any  number of 'l','i','n', and 'e'
characters.
Signed-off-by: Alex Riesen <alexander.riesen@cetitec.com>

This adds a new MODE_PYPROJECT, which gives basic support to allow
packaging a small subset of micropython-lib packages to PyPI.

This change allows a package in micropython-lib to:
- Add a "pypi" name to its metadata indicating that it's based on a PyPI
  package.
- Add "stdlib" to its metadata indicating that it's a micropython version
  of a stdlib package.
- Add a "pypi_publish" name to its metadata to indicate that it can be
  published to PyPI (this can be different to the package name, e.g. "foo"
  might want to be published as "micropython-foo").

When a package requires() another one, if it's in MODE_PYPROJECT then if
the package is from pypi then it will record that as a pypi dependency
instead (or no dependency at all if it's from stdlib).

Also allows require() to explicitly specify the pypi name.
Signed-off-by: Jim Mussared <jim.mussared@gmail.com>

Helps prevent the filesystem from getting formatted by mistake, among other
things.  For example, on a Pico board, entering Ctrl+D and Ctrl+C fast many
times will eventually wipe the filesystem (without warning or notice).

Further rationale: Ctrl+C is used a lot by automation scripts (eg mpremote)
and UI's (eg Mu, Thonny) to get the board into a known state.  If the board
is not responding for a short time then it's not possible to know if it's
just a slow start up (eg in _boot.py), or an infinite loop in the main
application.  The former should not be interrupted, but the latter should.
The only way to distinguish these two cases would be to wait "long enough",
and if there's nothing on the serial after "long enough" then assume it's
running the application and Ctrl+C should break out of it.  But defining
"long enough" is impossible for all the different boards and their possible
behaviour.  The solution in this commit is to make it so that frozen
start-up code cannot be interrupted by Ctrl+C.  That code then effectively
acts like normal C start-up code, which also cannot be interrupted.

Note: on the stm32 port this was never seen as an issue because all
start-up code is in C.  But now other ports start to put more things in
_boot.py and so this problem crops up.
Signed-off-by: David Grayson <davidegrayson@gmail.com>

The dispatch active flag is only set once and never reset, so it will
always call the dispatch handler (once enabled), and it's not really
needed because it doesn't make things more efficient.

Also remove unused included headers.

Like frame error, overrun, etc.  Fix is provided by @ricksorensen.

It was incomplete.

Changes in this commit:
- Move the pwm_seq array to the p_config data structure.  That prevents
  potential resource collisions between PWM devices.
- Rename the keyword argument 'id' to 'device'.  That's consistent with the
  SAMD port as the other port allowing to specify it.

This regression was introduced by 3d46fe67.

This enables the use of WLAN(0).status('rssi') to get current RSSI of the
AP that the STA is connected to.
Signed-off-by: Damien George <damien@micropython.org>

This bug is probably a typo. args[0] is the cyw43 object itself.
While the value of a kwargs is in e->value.

The NINA socket types have the same values as modnetwork, but that may
change in the future.  So check the socket types passed to socket() and
convert them (if needed) to their respective Nina socket types.

Also remove the unnecessary socket type check code from bind(), as pointed
out by @robert-hh.

ESP32 pins 34, 35, 36 and 39 are input only, and should not be configured
as output.

STM32H750 has only 1 flash bank so function get_bank should always return
FLASH_BANK_1.

This is a follow up to d263438a, which
solved one problem (reset on disconnect) but introduced a second one (hang
in bootloader).

To solve both probles, False/False is needed for DTR/RTS for ESPxx, but
that would then block stm32 and others.  Any unconditional combination of
DTR/RTS ends up blocking normal operation on some type of board or another.

A simple overview (for windows only):

  DTR          CTS            ESP8266/ESP32          STM32/SAMD51/RP2040
  unspecified  unspecified    Reset on disconnect    OK
  True         False          Hang in bootloader     OK
  False        False          OK                     No Repl
  True         True           Reset on disconnect    No Repl
  False        True           Reset on disconnect    No Repl

  serial.manufacturer:        wch.cn/Silicon Labs    Microsoft

  serial.description:         USB-SERIAL CH340 /     USB Serial Device
                              CP210x USB to UART
                              Bridge

The updated logic will only set the DTR/RTS signals for boards that do not
use standard Microsoft drivers (based on the manufacturer).  It would also
be possible to check against a list of known driver manufactures (like
wch.cn or Silicon Labs) but this would require a list of known drivers for
all ports.
Signed-off-by: Jos Verlinde <jos_verlinde@hotmail.com>

Signed-off-by: Damien George <damien@micropython.org>

Following other vfs_fat tests, so the test works on ports like stm32 that
only support 512-byte block size.
Signed-off-by: Damien George <damien@micropython.org>

Signed-off-by: David Lechner <david@pybricks.com>

This is a best-effort implementation of write polling.  It's difficult to
do correctly because if there are multiple output streams (eg UART and USB
CDC) then some may not be writeable while others are.  A full solution
should also have a return value from mp_hal_stdout_tx_strn(), returning the
number of bytes written to the stream(s).  That's also hard to define.

The renesas-ra and stm32 ports already implement a similar best-effort
mechanism for write polling.

Fixes issue #11026.
Signed-off-by: Damien George <damien@micropython.org>

Signed-off-by: Damien George <damien@micropython.org>

If a multitest calls `multitest.output_metric(...)` then that output will
be collected separately, not considered as part of the test verification
output, and instead be printed at the end.  This is useful for tests that
want to output performance/timing metrics that may change from one run to
the next.
Signed-off-by: Damien George <damien@micropython.org>

But leave these disabled.
Signed-off-by: Damien George <damien@micropython.org>

Signed-off-by: Damien George <damien@micropython.org>

Signed-off-by: Damien George <damien@micropython.org>

Prior to this change, setting of UART parameters like parity, stop bits or
data bits did not work correctly.  As suggested by @iabdalkader, adding
__DSB() fixes the problem, making sure that changes to the UART LCR_H
register are seen by the peripheral.

Note: the FIFO is already enabled in the call to uart_init(), so the call
to uart_set_fifo_enabled() is not required, but kept for visibility.

Fixes issue #10976.

This was broken by 5327cd10Signed-off-by: Damien George <damien@micropython.org>

This is intended to be used by the very outer caller of the VM/runtime.  It
allows setting a top-level NLR handler that can be jumped to directly, in
order to forcefully abort the VM/runtime.

Enable using:

    #define MICROPY_ENABLE_VM_ABORT (1)

Set up the handler at the top level using:

    nlr_buf_t nlr;
    nlr.ret_val = NULL;
    if (nlr_push(&nlr) == 0) {
        nlr_set_abort(&nlr);
        // call into the VM/runtime
        ...
        nlr_pop();
    } else {
        if (nlr.ret_val == NULL) {
            // handle abort
            ...
        } else {
            // handle other exception that propagated to the top level
            ...
        }
    }
    nlr_set_abort(NULL);

Schedule an abort, eg from an interrupt handler, using:

    mp_sched_vm_abort();
Signed-off-by: Damien George <damien@micropython.org>

Signed-off-by: Damien George <damien@micropython.org>

When iterating over os.ilistdir(), the special directories '.' and '..'
are filtered from the results.  But the code inadvertently also filtered
any file/directory which happened to match '..*'.  This change fixes the
filter.

Fixes issue #11032.
Signed-off-by: Jeremy Rand <jeremy@rand-family.com>

The following have been tested and are working:
- 550MHz CPU frequency
- UART REPL via ST-Link
- USB REPL and mass storage
- 3x LEDs and 1x user button
- Ethernet
Signed-off-by: Damien George <damien@micropython.org>

Signed-off-by: Damien George <damien@micropython.org>

Signed-off-by: Damien George <damien@micropython.org>

Signed-off-by: Damien George <damien@micropython.org>

Signed-off-by: Damien George <damien@micropython.org>

For builds with DEBUG=1 and MICROPY_HW_ENABLE_UART_REPL=1, calling
stdio_init_all() in main() detaches the UART input from REPL.  This change
suppresses calling stdio_init_all() then.

Previously, setting MICROPY_HW_ENABLE_USBDEV to 0 caused build errors.  The
change affects the nrf and samd ports as well, so MICROPY_HW_ENABLE_USBDEV
had to be explicitly enabled there.

The configuration options MICROPY_HW_ENABLE_USBDEV and
MICROPY_HW_ENABLE_UART_REPL are independent, and can be enabled or disabled
by a board.
Signed-off-by: Damien George <damien@micropython.org>

Mostly for compatibility.  Effective values are 100000, 250000 and 400000.
The supplied values are mapped to these.

Calling MICROPY_EVENT_POLL_HOOK.  That allows Ctrl-C to break loops with
idle().

Suggested by @ricksorensen after testing.  These match better the hardware
of the NRF52xx.

Changes in this commit:
- Add the timeout and timeout_char keyword options.
- Make uart.read() non-blocking.
- Add uart.any().
- Add ioctl MP_STREAM_POLL handling.
- Change uart.write() into non-busy waiting. uart.write() still waits until
  all data has been sent, but calls MICROPY_EVENT_POLL_HOOK while waiting.
  uart.write() uses DMA for transfer.  One option would be to add a small
  local buffer, such that transfers up to the size of the buffer could be
  done without waiting.
- As a side effect to the change of uart.write(), uart.txdone() and ioctl
  flush now report/wait correctly for the end of transmission.
- Change machine_hard_uart_buf_t in machine_hard_uart_obj_t to an instance
  of that struct, rather than a pointer to one.