scanner: don't fail over unknown escape sequence

This is too strict, and causes symbols/cz to fail parsing. Instead, just
emit a warning (not shown by default):
    xkbcommon: WARNING: cz:75:19: unknown escape sequence in string literal

https://bugs.freedesktop.org/show_bug.cgi?id=68056

Reported-By: Gatis Paeglis <gatis.paeglis@digia.com>
Signed-off-by: Ran Benita <ran234@gmail.com>

diff --git a/src/xkbcomp/parser-priv.h b/src/xkbcomp/parser-priv.h
index 465b19d..f0d1f22 100644 (file)
--- a/src/xkbcomp/parser-priv.h
+++ b/src/xkbcomp/parser-priv.h
@@ -35,6 +35,9 @@ struct parser_param;
 int
 scanner_error(YYLTYPE *yylloc, struct scanner *scanner, const char *msg);
 
+void
+scanner_warn(YYLTYPE *yylloc, struct scanner *s, const char *msg);
+
 int
 _xkbcommon_lex(YYSTYPE *yylval, YYLTYPE *yylloc, struct scanner *scanner);
 

diff --git a/src/xkbcomp/scanner.c b/src/xkbcomp/scanner.c
index 49df658..b37adec 100644 (file)
--- a/src/xkbcomp/scanner.c
+++ b/src/xkbcomp/scanner.c
@@ -25,14 +25,27 @@
 #include "parser-priv.h"
 #include "scanner-utils.h"
 
+static void
+scanner_log(enum xkb_log_level level, YYLTYPE *yylloc, struct scanner *s,
+            const char *msg)
+{
+    xkb_log_cond_level(s->ctx, level, "%s:%d:%d: %s\n", s->file_name,
+                       yylloc->first_line, yylloc->first_column, msg);
+}
+
 int
 scanner_error(YYLTYPE *yylloc, struct scanner *s, const char *msg)
 {
-    log_err(s->ctx, "%s:%d:%d: %s\n",
-            s->file_name, yylloc->first_line, yylloc->first_column, msg);
+    scanner_log(XKB_LOG_LEVEL_ERROR, yylloc, s, msg);
     return ERROR_TOK;
 }
 
+void
+scanner_warn(YYLTYPE *yylloc, struct scanner *s, const char *msg)
+{
+    scanner_log(XKB_LOG_LEVEL_WARNING, yylloc, s, msg);
+}
+
 static bool
 number(struct scanner *s, int64_t *out, enum yytokentype *out_tok)
 {
@@ -103,8 +116,11 @@ skip_more_whitespace_and_comments:
                 else if (chr(s, 'v'))  buf_append(s, '\v');
                 else if (chr(s, 'e'))  buf_append(s, '\033');
                 else if (oct(s, &o))   buf_append(s, (char) o);
-                else return scanner_error(yylloc, s,
-                                          "illegal escape sequence in string literal");
+                else {
+                    scanner_warn(yylloc, s,
+                                 "unknown escape sequence in string literal");
+                    /* Ignore. */
+                }
             } else {
                 buf_append(s, next(s));
             }

diff --git a/test/data/symbols/cz b/test/data/symbols/cz
new file mode 100644 (file)
index 0000000..336050c
--- /dev/null
+++ b/test/data/symbols/cz
@@ -0,0 +1,184 @@
+partial default alphanumeric_keys 
+xkb_symbols "basic" {
+     
+     // This layout conforms to a new cz compromise standard designed 
+     // to satisfy most unix, windows and mac users.
+     // 2001 by Kamil Toman <ktoman@email.cz>
+
+    include "latin"
+
+    name[Group1]= "Czech";
+
+    key <TLDE> { [ semicolon, dead_abovering,    grave,   asciitilde ] };
+    key <AE01> { [      plus,          1,       exclam,   dead_tilde ] };
+    key <AE02> { [    ecaron,          2,           at,   dead_caron ] };
+    key <AE03> { [    scaron,          3,   numbersign, dead_circumflex ] };
+    key <AE04> { [    ccaron,          4,       dollar,   dead_breve ] };
+    key <AE05> { [    rcaron,          5,      percent, dead_abovering ] };
+    key <AE06> { [    zcaron,          6,  asciicircum,  dead_ogonek ] };
+    key <AE07> { [    yacute,          7,    ampersand,   dead_grave ] };
+    key <AE08> { [    aacute,          8,     asterisk, dead_abovedot] };
+    key <AE09> { [    iacute,          9,    braceleft,   dead_acute ] };
+    key <AE10> { [    eacute,          0,   braceright, dead_doubleacute ] };
+    key <AE11> { [     equal,    percent,     NoSymbol, dead_diaeresis ] };
+    key <AE12> { [dead_acute, dead_caron,  dead_macron, dead_cedilla ] };
+
+    key <AD01> { [         q,          Q,    backslash,     NoSymbol ] };
+    key <AD02> { [         w,          W,          bar,     Nosymbol ] };
+    key <AD03> { [         e,          E,     EuroSign,     NoSymbol ] };
+    key <AD04> { [         r,          R,     NoSymbol,     NoSymbol ] };
+    key <AD05> { [         t,          T,     NoSymbol,     NoSymbol ] };
+    key <AD06> { [         z,          Z,     NoSymbol,     NoSymbol ] };
+    key <AD07> { [         u,          U,     NoSymbol,     NoSymbol ] };
+    key <AD08> { [         i,          I,     NoSymbol,     NoSymbol ] };
+    key <AD09> { [         o,          O,     NoSymbol,     NoSymbol ] };
+    key <AD10> { [         p,          P,     NoSymbol,     NoSymbol ] };
+
+    key <AD11> { [    uacute,      slash,  bracketleft,     division ] };
+    key <AD12> { [parenright,  parenleft, bracketright,     multiply ] };
+
+    key <AC01> { [         a,          A,   asciitilde,     NoSymbol ] };
+    key <AC02> { [         s,          S,      dstroke,     NoSymbol ] };
+    key <AC03> { [         d,          D,      Dstroke,     NoSymbol ] };
+    key <AC04> { [         f,          F,  bracketleft,     NoSymbol ] };
+    key <AC05> { [         g,          G, bracketright,     NoSymbol ] };
+    key <AC06> { [         h,          H,        grave,     NoSymbol ] };
+    key <AC07> { [         j,          J,   apostrophe,     NoSymbol ] };
+    key <AC08> { [         k,          K,      lstroke,     NoSymbol ] };
+    key <AC09> { [         l,          L,      Lstroke,     NoSymbol ] };
+                  
+    key <AC10> { [     uring,   quotedbl,       dollar,     NoSymbol ] };
+    key <AC11> { [   section,     exclam,   apostrophe,       ssharp ] };
+    key <AC12> { [  EuroSign, dead_diaeresis, NoSymbol,     NoSymbol ] };
+    key <BKSL> { [dead_diaeresis, apostrophe, backslash,         bar ] };
+
+    key <LSGT> { [ backslash,        bar,        slash,     NoSymbol ] };
+    key <AB01> { [         y,          Y,       degree,     NoSymbol ] };
+    key <AB02> { [         x,          X,   numbersign,     Nosymbol ] };
+    key <AB03> { [         c,          C,    ampersand,     NoSymbol ] };
+    key <AB04> { [         v,          V,           at,     NoSymbol ] };
+    key <AB05> { [         b,          B,    braceleft,     NoSymbol ] };
+    key <AB06> { [         n,          N,   braceright,     NoSymbol ] };
+    key <AB07> { [         m,          M,  asciicircum,     NoSymbol ] };
+    key <AB08> { [     comma,   question,         less,     NoSymbol ] };
+    key <AB09> { [    period,      colon,      greater,     NoSymbol ] };
+    key <AB10> { [     minus, underscore,     asterisk,     NoSymbol ] };
+
+    key <SPCE> { [     space,      space,        space,       space ]  };
+
+    include "level3(ralt_switch)"
+};
+
+// Use <BKSL> instead of <LSGT> (useful for keyboard without <LSGT> key)
+xkb_symbols "bksl" {
+    include "cz(basic)"
+    name[Group1]= "Czech (with <\|> key)";
+
+    key <BKSL> { [ backslash,        bar,        slash,     NoSymbol ] };
+};
+
+partial alphanumeric_keys 
+xkb_symbols "qwerty" {
+ 
+    // This layout represent actual keyboard layout. It complies with symbols
+    // printed on keys.
+    // -----------------------------------------------------------------------
+    // This layout was created in 2011 by Lukáš Mojžíš <lmojzis@grenames.cz>
+    
+    include "cz(basic)"
+    name[Group1]= "Czech (qwerty)";
+
+    key <AB01> { [         z,          Z,       degree,         NoSymbol ] };
+    key <AC10> { [     uring,   quotedbl,    semicolon,            colon ] };
+    key <AC11> { [   section,     exclam,   apostrophe,           ssharp ] };
+    key <AD06> { [         y,          Y,     NoSymbol,         NoSymbol ] };
+    key <AD11> { [    uacute,      slash,  bracketleft,        braceleft ] };
+    key <AD12> { [parenright,  parenleft, bracketright,       braceright ] };
+    key <AE09> { [    iacute,          9,    parenleft,       dead_acute ] };
+    key <AE10> { [    eacute,          0,   parenright, dead_doubleacute ] };
+};
+
+// Use <BKSL> instead of <LSGT> (useful for keyboard without <LSGT> key)
+xkb_symbols "qwerty_bksl" {
+    include "cz(qwerty)"
+
+    name[Group1]= "Czech (qwerty, extended Backslash)";
+
+    key <BKSL> { [ backslash,        bar,        slash,     NoSymbol ] };
+};
+
+partial alphanumeric_keys alternate_group
+xkb_symbols "ucw" {
+
+    // This layout is usually used as the second group, it contains
+    // accented characters only, no 'latin' set.
+    // 2008 by Milan Vancura <mvancura@suse.cz>
+
+    name[Group1]= "Czech (UCW layout, accented letters only)";
+
+    key <AB01> { [zcaron,      Zcaron      ] };
+    key <AB02> { [ssharp                   ] };
+    key <AB03> { [ccaron,      Ccaron      ] };
+    key <AB04> { [ccedilla,    Ccedilla    ] };
+    key <AB05> { [ntilde,      Ntilde      ] };
+    key <AB06> { [ncaron,      Ncaron      ] };
+    key <AB07> { [lacute,      Lacute      ] };
+
+    key <AC01> { [aacute,      Aacute      ] };
+    key <AC02> { [scaron,      Scaron      ] };
+    key <AC03> { [dcaron,      Dcaron      ] };
+    key <AC04> { [ediaeresis,  Ediaeresis  ] };
+    key <AC05> { [racute,      Racute      ] };
+    key <AC06> { [uacute,      Uacute      ] };
+    key <AC07> { [udiaeresis,  Udiaeresis  ] };
+    key <AC08> { [ocircumflex, Ocircumflex ] };
+    key <AC09> { [lcaron,      Lcaron      ] };
+
+    key <AD01> { [adiaeresis,  Adiaeresis  ] };
+    key <AD02> { [ecaron,      Ecaron      ] };
+    key <AD03> { [eacute,      Eacute      ] };
+    key <AD04> { [rcaron,      Rcaron      ] };
+    key <AD05> { [tcaron,      Tcaron      ] };
+    key <AD06> { [yacute,      Yacute      ] };
+    key <AD07> { [uring,       Uring       ] };
+    key <AD08> { [iacute,      Iacute      ] };
+    key <AD09> { [oacute,      Oacute      ] };
+    key <AD10> { [odiaeresis,  Odiaeresis  ] };
+};
+
+partial alphanumeric_keys
+xkb_symbols "dvorak-ucw" {
+
+    // US Dvorak layout extend with UCW - AltGr produces accented characters
+
+    include "us(dvorak)"
+
+    name[Group1]= "Czech (US Dvorak with CZ UCW support)";
+
+    key <AB03> { [ j, J, eacute, Eacute ] };
+    key <AB04> { [ k, K, uacute, Uacute ] };
+    key <AB10> { [ z, Z, zcaron, Zcaron ] };
+
+    key <AC01> { [ a, A, aacute, Aacute ] };
+    key <AC02> { [ o, O, oacute, Oacute ] };
+    key <AC03> { [ e, E, ecaron, Ecaron ] };
+    key <AC04> { [ u, U, uring,  Uring  ] };
+    key <AC05> { [ i, I, iacute, Iacute ] };
+    key <AC06> { [ d, D, dcaron, Dcaron ] };
+    key <AC08> { [ t, T, tcaron, Tcaron ] };
+    key <AC09> { [ n, N, ncaron, Ncaron ] };
+    key <AC10> { [ s, S, scaron, Scaron ] };
+
+    key <AD05> { [ y, Y, yacute, Yacute ] };
+    key <AD08> { [ c, C, ccaron, Ccaron ] };
+    key <AD09> { [ r, R, rcaron, Rcaron ] };
+
+    include "level3(ralt_switch)"
+};
+
+// EXTRAS:
+
+partial alphanumeric_keys
+       xkb_symbols "sun_type6" {
+       include "sun_vndr/cz(sun_type6)"
+};

diff --git a/test/data/sync.sh b/test/data/sync.sh
index 12ed434..206231a 100755 (executable)
--- a/test/data/sync.sh
+++ b/test/data/sync.sh
@@ -18,6 +18,7 @@ for file in \
     symbols/shift \
     symbols/pc \
     symbols/ca \
+    symbols/cz \
     symbols/srvr_ctrl \
     symbols/capslock \
     symbols/latin \

diff --git a/test/rulescomp.c b/test/rulescomp.c
index 60e7a4c..513607d 100644 (file)
--- a/test/rulescomp.c
+++ b/test/rulescomp.c
@@ -235,6 +235,10 @@ main(int argc, char *argv[])
     assert(test_rmlvo_env(ctx, "base", "empty", "empty", "", "",
                           KEY_A,          BOTH, XKB_KEY_NoSymbol,         FINISH));
 
+    /* Has an illegal escape sequence, but shouldn't fail. */
+    assert(test_rmlvo_env(ctx, "evdev", "", "cz", "bksl", "",
+                          KEY_A,          BOTH, XKB_KEY_a,                FINISH));
+
     xkb_context_unref(ctx);
 
     ctx = test_get_context(0);