rules: add include statements to rules files

The majority use-case for extending XKB on a machine is to override one or a
few keys with custom keycodes, not to define whole layouts.

Previously, we relied on the rules file to be a single file, making it hard to
extend. libxkbcommon parses $XDG_CONFIG_HOME/xkb/ but that only works as long
as there is a rule that matches the user-specified RMLVO. This works for MLV
but not for options which don't have a wildcard defined. Users have to copy
the whole rules file and then work from there - not something easy to extend
and maintain.

This patch adds a new ! include directive to rules files that allows including
another file. The file path must be without quotes and may not start with the
literal "include". Two directives are supported, %H to $HOME and %S for the
system-installed rules directory (usually /usr/share/X11/xkb/rules).

A user would typically use a custom rules file like this:

! option                =       symbols
  custom:foo            =       +custom(foo)
  custom:bar            =       +custom(baz)

! include %S/evdev

Where the above defines the two options and then includes the system-installed
evdev rule. Since most current implementations default to loading the "evdev"
ruleset, it's best to name this $XDG_CONFIG_HOME/xkb/rules/evdev, but any
valid name is allowed.

The include functionally replaces the line with the content of the included
file which means the behavior of rules files is maintained. Specifically,
custom options must be defined before including another file because the first
match usually wins. In other words, the following ruleset will not assign
my_model as one would expect:

! include %S/evdev

! model                 =  symbols
  my_model              =  +custom(foo)

The default evdev ruleset has wildcards for model and those match before the
my_model is hit.

The actual resolved components need only be in one of the XKB lookup
directories, e.g. for the example above:

$ cat $XDG_CONFIG_HOME/xkb/symbols/custom
partial alphanumeric_keys
xkb_symbols "foo" {
    key <TLDE> {        [      VoidSymbol ]       };
};

partial alphanumeric_keys
xkb_symbols "baz" {
    key <AB01> {        [      k, K ]       };
};

This can then be loaded with the XKB option "custom:foo,custom:bar".

The use of "custom" is just as an example, there are no naming requirements
beyond avoiding already-used ones. Also note the bar/baz above - the option
names don't have to match the component names.

Signed-off-by: Peter Hutterer <peter.hutterer@who-t.net>

1 files changed, 90 insertions, 2 deletions

diff --git a/src/xkbcomp/rules.c b/src/xkbcomp/rules.c
index 15b6012..a08e3c5 100644
--- a/src/xkbcomp/rules.c
+++ b/src/xkbcomp/rules.c
@@ -52,6 +52,8 @@
 #include "include.h"
 #include "scanner-utils.h"
 
+#define MAX_INCLUDE_DEPTH 5
+
 /* Scanner / Lexer */
 
 /* Values returned with some tokens, like yylval. */
@@ -67,6 +69,7 @@ enum rules_token {
     TOK_BANG,
     TOK_EQUALS,
     TOK_STAR,
+    TOK_INCLUDE,
     TOK_ERROR
 };
 
@@ -131,6 +134,10 @@ skip_more_whitespace_and_comments:
         return TOK_GROUP_NAME;
     }
 
+    /* Include statement. */
+    if (lit(s, "include"))
+        return TOK_INCLUDE;
+
     /* Identifier. */
     if (is_ident(peek(s))) {
         val->string.start = s->s + s->pos;
@@ -338,6 +345,74 @@ matcher_group_add_element(struct matcher *m, struct scanner *s,
                   element);
 }
 
+static bool
+read_rules_file(struct xkb_context *ctx,
+                struct matcher *matcher,
+                unsigned include_depth,
+                const char *path);
+
+static void
+matcher_include(struct matcher *m, struct scanner *parent_scanner,
+                unsigned include_depth,
+                struct sval inc)
+{
+    bool ret;
+    struct scanner s; /* parses the !include value */
+
+    scanner_init(&s, m->ctx, inc.start, inc.len,
+                 parent_scanner->file_name, NULL);
+    s.token_line = parent_scanner->token_line;
+    s.token_column = parent_scanner->token_column;
+    s.buf_pos = 0;
+
+    if (include_depth >= MAX_INCLUDE_DEPTH) {
+        scanner_err(&s, "maximum include depth (%d) exceeded; maybe there is an include loop?",
+                    MAX_INCLUDE_DEPTH);
+        return;
+    }
+
+    while (!eof(&s) && !eol(&s)) {
+        if (chr(&s, '%')) {
+            if (chr(&s, '%')) {
+                buf_append(&s, '%');
+            }
+            else if (chr(&s, 'H')) {
+                const char *home = secure_getenv("HOME");
+                if (!home) {
+                    scanner_err(&s, "%%H was used in an include statement, but the HOME environment variable is not set");
+                    return;
+                }
+                if (!buf_appends(&s, home)) {
+                    scanner_err(&s, "include path after expanding %%H is too long");
+                    return;
+                }
+            }
+            else if (chr(&s, 'S')) {
+                const char *default_root = xkb_context_include_path_get_system_path(m->ctx);
+                if (!buf_appends(&s, default_root) || !buf_appends(&s, "/rules")) {
+                    scanner_err(&s, "include path after expanding %%S is too long");
+                    return;
+                }
+            }
+            else {
+                scanner_err(&s, "unknown %% format (%c) in include statement", peek(&s));
+                return;
+            }
+        }
+        else {
+            buf_append(&s, next(&s));
+        }
+    }
+    if (!buf_append(&s, '\0')) {
+        scanner_err(&s, "include path is too long");
+        return;
+    }
+
+    ret = read_rules_file(m->ctx, m, include_depth + 1, s.buf);
+    if (!ret)
+        log_err(m->ctx, "No components returned from included XKB rules \"%s\"\n", s.buf);
+}
+
 static void
 matcher_mapping_start_new(struct matcher *m)
 {
@@ -822,6 +897,7 @@ gettok(struct matcher *m, struct scanner *s)
 
 static bool
 matcher_match(struct matcher *m, struct scanner *s,
+              unsigned include_depth,
               const char *string, size_t len,
               const char *file_name)
 {
@@ -847,6 +923,8 @@ bang:
     case TOK_GROUP_NAME:
         matcher_group_start_new(m, m->val.string);
         goto group_name;
+    case TOK_INCLUDE:
+        goto include_statement;
     case TOK_IDENTIFIER:
         matcher_mapping_start_new(m);
         matcher_mapping_set_mlvo(m, s, m->val.string);
@@ -874,6 +952,15 @@ group_element:
         goto unexpected;
     }
 
+include_statement:
+    switch (tok = gettok(m, s)) {
+    case TOK_IDENTIFIER:
+        matcher_include(m, s, include_depth, m->val.string);
+        goto initial;
+    default:
+        goto unexpected;
+    }
+
 mapping_mlvo:
     switch (tok = gettok(m, s)) {
     case TOK_IDENTIFIER:
@@ -971,6 +1058,7 @@ error:
 static bool
 read_rules_file(struct xkb_context *ctx,
                 struct matcher *matcher,
+                unsigned include_depth,
                 const char *path)
 {
     bool ret = false;
@@ -992,7 +1080,7 @@ read_rules_file(struct xkb_context *ctx,
 
     scanner_init(&scanner, matcher->ctx, string, size, path, NULL);
 
-    ret = matcher_match(matcher, &scanner, string, size, path);
+    ret = matcher_match(matcher, &scanner, include_depth, string, size, path);
 
     unmap_file(string, size);
 out:
@@ -1021,7 +1109,7 @@ xkb_components_from_rules(struct xkb_context *ctx,
 
     matcher = matcher_new(ctx, rmlvo);
 
-    ret = read_rules_file(ctx, matcher, path);
+    ret = read_rules_file(ctx, matcher, 0, path);
     if (!ret ||
         darray_empty(matcher->kccgst[KCCGST_KEYCODES]) ||
         darray_empty(matcher->kccgst[KCCGST_TYPES]) ||