interfaces: introduce and use a protocol class for the `bdiff` module This is allowed by PEP 544[1], and we basically follow the example there. The class here is copied from `mercurial.pure.bdiff`, and the implementation removed. There are several modules that have a few different implementations, and the implementation chosen is controlled by `HGMODULEPOLICY`. The module is loaded via `mercurial/policy.py`, and has been inferred by pytype as `Any` up to this point. Therefore it and PyCharm were blind to all functions on the module, and their signatures. Also, having multiple instances of the same module allows their signatures to get out of sync. Introducing a protocol class allows the loaded module that is stored in a variable to be given type info, which cascades through the various places it is used. This change alters 11 *.pyi files, for example. In theory, this would also allow us to ensure the various implementations of the same module are kept in alignment- simply import the module in a test module, attempt to pass it to a function that uses the corresponding protocol as an argument, and run pytype on it. In practice, this doesn't work (yet). PyCharm (erroneously) flags imported modules being passed where a protocol class is used[2]. Pytype has problems the other way- it fails to detect when a module that doesn't adhere to the protocol is passed to a protocol argument. The good news is that mypy properly detects this case. The bad news is that mypy spews a bunch of other errors when importing even simple modules, like the various `bdiff` modules. Therefore I'm punting on the tests for now because the type info around a loaded module in PyCharm is a clear win by itself. [1] https://peps.python.org/pep-0544/#modules-as-implementations-of-protocols [2] https://youtrack.jetbrains.com/issue/PY-58679/Support-modules-implementing-protocols

     1

#ifndef HG_BITMANIPULATION_H

     2

#define HG_BITMANIPULATION_H

     3

     4

#include <string.h>

     5

     6

#include "compat.h"

     7

     8

/* Reads a 64 bit integer from big-endian bytes. Assumes that the data is long

     9

 enough */

    10

static inline uint64_t getbe64(const char *c)

    11

{

    12

	const unsigned char *d = (const unsigned char *)c;

    13

    14

	return ((((uint64_t)d[0]) << 56) | (((uint64_t)d[1]) << 48) |

    15

	        (((uint64_t)d[2]) << 40) | (((uint64_t)d[3]) << 32) |

    16

	        (((uint64_t)d[4]) << 24) | (((uint64_t)d[5]) << 16) |

    17

	        (((uint64_t)d[6]) << 8) | (d[7]));

    18

}

    19

    20

static inline uint32_t getbe32(const char *c)

    21

{

    22

	const unsigned char *d = (const unsigned char *)c;

    23

    24

	return ((((uint32_t)d[0]) << 24) | (((uint32_t)d[1]) << 16) |

    25

	        (((uint32_t)d[2]) << 8) | (d[3]));

    26

}

    27

    28

static inline int16_t getbeint16(const char *c)

    29

{

    30

	const unsigned char *d = (const unsigned char *)c;

    31

    32

	return ((d[0] << 8) | (d[1]));

    33

}

    34

    35

static inline uint16_t getbeuint16(const char *c)

    36

{

    37

	const unsigned char *d = (const unsigned char *)c;

    38

    39

	return ((d[0] << 8) | (d[1]));

    40

}

    41

    42

/* Writes a 64 bit integer to bytes in a big-endian format.

    43

 Assumes that the buffer is long enough */

    44

static inline void putbe64(uint64_t x, char *c)

    45

{

    46

	c[0] = (x >> 56) & 0xff;

    47

	c[1] = (x >> 48) & 0xff;

    48

	c[2] = (x >> 40) & 0xff;

    49

	c[3] = (x >> 32) & 0xff;

    50

	c[4] = (x >> 24) & 0xff;

    51

	c[5] = (x >> 16) & 0xff;

    52

	c[6] = (x >> 8) & 0xff;

    53

	c[7] = (x)&0xff;

    54

}

    55

    56

static inline void putbe32(uint32_t x, char *c)

    57

{

    58

	c[0] = (x >> 24) & 0xff;

    59

	c[1] = (x >> 16) & 0xff;

    60

	c[2] = (x >> 8) & 0xff;

    61

	c[3] = (x)&0xff;

    62

}

    63

    64

static inline double getbefloat64(const char *c)

    65

{

    66

	const unsigned char *d = (const unsigned char *)c;

    67

	double ret;

    68

	int i;

    69

	uint64_t t = 0;

    70

	for (i = 0; i < 8; i++) {

    71

		t = (t << 8) + d[i];

    72

	}

    73

	memcpy(&ret, &t, sizeof(t));

    74

	return ret;

    75

}

    76

    77

#endif