makekeys

Branch :

Show log
Commit
Author : Pierre Le Marre
Date : 2024-03-05 10:28:11
Hash : 53d9881e
Message : keysyms: Fix inconsistent case-insensitive name lookup `xkb_keysym_from_name` has inconsistent behavior when used with the flag `XKB_KEYSYM_CASE_INSENSITIVE`: ```c xkb_keysym_from_name("a", XKB_KEYSYM_CASE_INSENSITIVE) == XKB_KEY_a; xkb_keysym_from_name("A", XKB_KEYSYM_CASE_INSENSITIVE) == XKB_KEY_a; xkb_keysym_from_name("dead_a", XKB_KEYSYM_CASE_INSENSITIVE) == XKB_KEY_dead_A; xkb_keysym_from_name("dead_A", XKB_KEYSYM_CASE_INSENSITIVE) == XKB_KEY_dead_A; xkb_keysym_from_name("dead_o", XKB_KEYSYM_CASE_INSENSITIVE) == XKB_KEY_dead_o; xkb_keysym_from_name("dead_O", XKB_KEYSYM_CASE_INSENSITIVE) == XKB_KEY_dead_o; xkb_keysym_from_name("KANA_tsu", XKB_KEYSYM_CASE_INSENSITIVE) == XKB_KEY_kana_tsu; xkb_keysym_from_name("KANA_TSU", XKB_KEYSYM_CASE_INSENSITIVE) == XKB_KEY_kana_tsu; xkb_keysym_from_name("KANA_ya", XKB_KEYSYM_CASE_INSENSITIVE) == XKB_KEY_kana_YA; xkb_keysym_from_name("KANA_YA", XKB_KEYSYM_CASE_INSENSITIVE) == XKB_KEY_kana_YA; xkb_keysym_from_name("XF86Screensaver", XKB_KEYSYM_CASE_INSENSITIVE) == XKB_KEY_XF86ScreenSaver; xkb_keysym_from_name("XF86ScreenSaver", XKB_KEYSYM_CASE_INSENSITIVE) == XKB_KEY_XF86ScreenSaver; ``` So currently, if two keysym names differ only by case, then the lower-case *keysym* is returned, not the keysym corresponding to the lower-case keysym *name*. Indeed, `xkb_keysym_from_name` uses `xkb_keysym_is_lower` to test if a keysym is a lower-case keysym. Let’s look at the example for keysyms `a` and `A`: we get the keysym `a` not because its name is lower case, but because `xkb_keysym_is_lower(XKB_KEY_a)` returns true and `xkb_keysym_is_lower(XKB_KEY_A)` returns false. So the results are correct according to the doc: - Katakana is not a bicameral script, so e.g. `kana_ya` is *not* the lower case of `kana_YA`. - As for the `dead_*` keysyms, they are not cased either because they do not correspond to characters. - `XF86ScreenSaver` and `XF86Screensaver` are two different keysyms. But this is also very counter-intuitive: `xkb_keysym_is_lower` is not the right function to use in this case, because one would expect to check only the name, not the corresponding character case: ```c xkb_keysym_from_name("KANA_YA", XKB_KEYSYM_CASE_INSENSITIVE) == XKB_KEY_kana_ya; xkb_keysym_from_name("XF86ScreenSaver", XKB_KEYSYM_CASE_INSENSITIVE) == XKB_KEY_XF86Screensaver; ``` Fixed by making the order of the keysyms names consistent in `src/ks_tables.h`: 1. Sort by the casefolded name: e.g. `kana_ya` < `kana_YO`. 2. If same casefolded name, then sort by cased name, i.e for ASCII: upper before lower: e.g `kana_YA` < `kana_ya`. Thus we now have e.g. `kana_YA` < `kana_ya` < `kana_YO` < `kana_yo`. The lookup logic has also been simplified. Added exhaustive test for ambiguous case-insensitive names.

scripts/makekeys

#!/usr/bin/env python

import re
import sys
import itertools

import perfect_hash

pattern = re.compile(r"^#define\s+XKB_KEY_(?P<name>\w+)\s+(?P<value>0x[0-9a-fA-F]+)\s")
matches = [pattern.match(line) for line in open(sys.argv[1])]
entries = [(m.group("name"), int(m.group("value"), 16)) for m in matches if m]

# Sort based on the keysym name:
#   1. Sort by the casefolded name: e.g. kana_ya < kana_YO.
#   2. If same casefolded name, then sort by cased name, i.e for
#      ASCII: upper before lower: e.g kana_YA < kana_ya.
# E.g. kana_YA < kana_ya < kana_YO < kana_yo
# WARNING: this sort must not be changed, as some functions e.g.
# xkb_keysym_from_name rely on upper case variant occuring first.
entries_isorted = sorted(entries, key=lambda e: (e[0].casefold(), e[0]))
# Sort based on keysym value. Sort is stable so in case of duplicate, the first
# keysym occurence stays first.
entries_kssorted = sorted(entries, key=lambda e: e[1])

print(
    """
/**
 * This file comes from libxkbcommon and was generated by makekeys.py
 * You can always fetch the latest version from:
 * https://raw.github.com/xkbcommon/libxkbcommon/master/src/ks_tables.h
 */
"""
)

entry_offsets = {}

print(
    """
#ifdef __GNUC__
#pragma GCC diagnostic push
#pragma GCC diagnostic ignored "-Woverlength-strings"
#endif
static const char *keysym_names =
""".strip()
)
offs = 0
for name, _ in entries_isorted:
    entry_offsets[name] = offs
    print('    "{name}\\0"'.format(name=name))
    offs += len(name) + 1
print(
    """
;
#ifdef __GNUC__
#pragma GCC diagnostic pop
#endif
""".strip()
)


template = r"""
static const uint16_t keysym_name_G[] = {
    $G
};

static size_t
keysym_name_hash_f(const char *key, const char *T)
{
    size_t sum = 0;
    for (size_t i = 0; key[i] != '\0'; i++)
        sum += T[i % $NS] * key[i];
    return sum % $NG;
}

static size_t
keysym_name_perfect_hash(const char *key)
{
    return (
        keysym_name_G[keysym_name_hash_f(key, "$S1")] +
        keysym_name_G[keysym_name_hash_f(key, "$S2")]
    ) % $NG;
}
"""
print(
    perfect_hash.generate_code(
        keys=[name for name, value in entries_isorted],
        template=template,
    )
)

print(
    """
struct name_keysym {
    xkb_keysym_t keysym;
    uint32_t offset;
};\n"""
)


def print_entries(x):
    for name, value in x:
        print(
            "    {{ 0x{value:08x}, {offs} }}, /* {name} */".format(
                offs=entry_offsets[name], value=value, name=name
            )
        )


print("static const struct name_keysym name_to_keysym[] = {")
print_entries(entries_isorted)
print("};\n")

# *.sort() is stable so we always get the first keysym for duplicate
print("static const struct name_keysym keysym_to_name[] = {")
print_entries(
    next(g[1]) for g in itertools.groupby(entries_kssorted, key=lambda e: e[1])
)
print("};")

kc3-lang/libxkbcommon/scripts/makekeys

Commit

kc3-lang/libxkbcommon /scripts/makekeys