Hash :
70d11abd
        
        Author :
  
        
        Date :
2025-03-26T07:38:05
        
      
messages: Add file encoding and invalid syntax entries Added: - `XKB_ERROR_INVALID_FILE_ENCODING` - `XKB_ERROR_INVALID_RULES_SYNTAX` - `XKB_ERROR_INVALID_COMPOSE_SYNTAX` Changed: - `XKB_ERROR_INVALID_SYNTAX` renamed to `XKB_ERROR_INVALID_XKB_SYNTAX`.
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244
/*
 * Copyright © 2012 Ran Benita <ran234@gmail.com>
 * SPDX-License-Identifier: MIT
 */
#pragma once
#include "config.h"
#include <stdbool.h>
#include <stddef.h>
#include <string.h>
#include "context.h"
#include "darray.h"
#include "messages-codes.h"
#include "utils.h"
/* Point to some substring in the file; used to avoid copying. */
struct sval {
    const char *start;
    unsigned int len;
};
typedef darray(struct sval) darray_sval;
static inline bool
svaleq(struct sval s1, struct sval s2)
{
    return s1.len == s2.len && memcmp(s1.start, s2.start, s1.len) == 0;
}
static inline bool
isvaleq(struct sval s1, struct sval s2)
{
    return s1.len == s2.len && istrncmp(s1.start, s2.start, s1.len) == 0;
}
static inline bool
svaleq_prefix(struct sval s1, struct sval s2)
{
    return s1.len <= s2.len && memcmp(s1.start, s2.start, s1.len) == 0;
}
#define SVAL(start, len) (struct sval){(start), len}
#define SVAL_LIT(literal) SVAL(literal, sizeof(literal) - 1)
#define SVAL_INIT(literal) { literal, sizeof(literal) - 1 }
/* A line:column location in the input string (1-based). */
struct scanner_loc {
    size_t line, column;
};
struct scanner {
    const char *s;
    size_t pos;
    size_t len;
    char buf[1024];
    size_t buf_pos;
    /* The position of the start of the current token. */
    size_t token_pos;
    /* Cached values used by scanner_token_location. */
    size_t cached_pos;
    struct scanner_loc cached_loc;
    const char *file_name;
    struct xkb_context *ctx;
    void *priv;
};
/* Compute the line:column location for the current token (slow). */
struct scanner_loc
scanner_token_location(struct scanner *s);
#define scanner_log_with_code(scanner, level, verbosity, log_msg_id, fmt, ...) do { \
    struct scanner_loc loc = scanner_token_location((scanner));                     \
    xkb_log_with_code((scanner)->ctx, (level), verbosity, log_msg_id,               \
                      "%s:%zu:%zu: " fmt "\n",                                      \
                      (scanner)->file_name,                                         \
                      loc.line,                                                     \
                      loc.column, ##__VA_ARGS__);                                   \
} while(0)
#define scanner_err(scanner, id, fmt, ...)                     \
    scanner_log_with_code(scanner, XKB_LOG_LEVEL_ERROR, 0, id, \
                          fmt, ##__VA_ARGS__)
#define scanner_warn(scanner, id, fmt, ...)                      \
    scanner_log_with_code(scanner, XKB_LOG_LEVEL_WARNING, 0, id, \
                          fmt, ##__VA_ARGS__)
#define scanner_vrb(scanner, verbosity, id, fmt, ...)                    \
    scanner_log_with_code(scanner, XKB_LOG_LEVEL_WARNING, verbosity, id, \
                          fmt, ##__VA_ARGS__)
static inline void
scanner_init(struct scanner *s, struct xkb_context *ctx,
             const char *string, size_t len, const char *file_name,
             void *priv)
{
    s->s = string;
    s->len = len;
    s->pos = 0;
    s->token_pos = 0;
    s->cached_pos = 0;
    s->cached_loc.line = s->cached_loc.column = 1;
    s->file_name = file_name;
    s->ctx = ctx;
    s->priv = priv;
}
static inline char
scanner_peek(struct scanner *s)
{
    if (unlikely(s->pos >= s->len))
        return '\0';
    return s->s[s->pos];
}
static inline bool
scanner_eof(struct scanner *s)
{
    return s->pos >= s->len;
}
static inline bool
scanner_eol(struct scanner *s)
{
    return scanner_peek(s) == '\n';
}
static inline void
scanner_skip_to_eol(struct scanner *s)
{
    const char *nl = memchr(s->s + s->pos, '\n', s->len - s->pos);
    const size_t new_pos = nl ? (size_t) (nl - s->s) : s->len;
    s->pos = new_pos;
}
static inline char
scanner_next(struct scanner *s)
{
    if (unlikely(scanner_eof(s)))
        return '\0';
    return s->s[s->pos++];
}
static inline bool
scanner_chr(struct scanner *s, char ch)
{
    if (likely(scanner_peek(s) != ch))
        return false;
    s->pos++;
    return true;
}
static inline bool
scanner_str(struct scanner *s, const char *string, size_t len)
{
    if (s->len - s->pos < len)
        return false;
    if (memcmp(s->s + s->pos, string, len) != 0)
        return false;
    s->pos += len;
    return true;
}
#define scanner_lit(s, literal) scanner_str(s, literal, sizeof(literal) - 1)
static inline bool
scanner_buf_append(struct scanner *s, char ch)
{
    if (s->buf_pos + 1 >= sizeof(s->buf))
        return false;
    s->buf[s->buf_pos++] = ch;
    return true;
}
static inline bool
scanner_buf_appends(struct scanner *s, const char *str)
{
    int ret;
    ret = snprintf(s->buf + s->buf_pos, sizeof(s->buf) - s->buf_pos, "%s", str);
    if (ret < 0 || (size_t) ret >= sizeof(s->buf) - s->buf_pos)
        return false;
    s->buf_pos += ret;
    return true;
}
static inline bool
scanner_oct(struct scanner *s, uint8_t *out)
{
    int i;
    for (i = 0, *out = 0; scanner_peek(s) >= '0' && scanner_peek(s) <= '7' && i < 3; i++)
        /* Test overflow */
        if (*out < 040) {
            *out = *out * 8 + scanner_next(s) - '0';
        } else {
            /* Consume valid digit, but mark result as invalid */
            scanner_next(s);
            return false;
        }
    return i > 0;
}
static inline bool
scanner_hex(struct scanner *s, uint8_t *out)
{
    int i;
    for (i = 0, *out = 0; is_xdigit(scanner_peek(s)) && i < 2; i++) {
        const char c = scanner_next(s);
        const char offset = (char) (c >= '0' && c <= '9' ? '0' :
                                    c >= 'a' && c <= 'f' ? 'a' - 10
                                                         : 'A' - 10);
        *out = *out * 16 + c - offset;
    }
    return i > 0;
}
/* Basic detection of wrong character encoding based on the first bytes */
static inline bool
scanner_check_supported_char_encoding(struct scanner *scanner)
{
    /* Skip UTF-8 encoded BOM (U+FEFF)
     * See: https://www.unicode.org/faq/utf_bom.html#bom5 */
    if (scanner_str(scanner, "\xef\xbb\xbf", 3) || scanner->len < 2) {
        /* Assume UTF-8 encoding or trivial short input */
        return true;
    }
    /* Early detection of wrong file encoding, e.g. UTF-16 or UTF-32 */
    if (scanner->s[0] == '\0' || scanner->s[1] == '\0') {
        scanner_err(scanner, XKB_ERROR_INVALID_FILE_ENCODING,
                    "unexpected NULL character.");
        return false;
    }
    /* Enforce the first character to be ASCII.
       See the note before the use of this function, that explains the relevant
       parts of the grammars of rules, keymap components and Compose. */
    if (!is_ascii(scanner->s[0])) {
        scanner_err(scanner, XKB_ERROR_INVALID_FILE_ENCODING,
                    "unexpected non-ASCII character.");
        return false;
    }
    return true;
}