static int drivers_alloc;
#define PATTERNS(name, pattern, word_regex) \
- { name, NULL, -1, { pattern, REG_EXTENDED }, word_regex }
+ { name, NULL, -1, { pattern, REG_EXTENDED }, \
+ word_regex "|[^[:space:]]|[\xc0-\xff][\x80-\xbf]+" }
#define IPATTERN(name, pattern, word_regex) \
- { name, NULL, -1, { pattern, REG_EXTENDED | REG_ICASE }, word_regex }
+ { name, NULL, -1, { pattern, REG_EXTENDED | REG_ICASE }, \
+ word_regex "|[^[:space:]]|[\xc0-\xff][\x80-\xbf]+" }
static struct userdiff_driver builtin_drivers[] = {
IPATTERN("fortran",
"!^([C*]|[ \t]*!)\n"
* Don't worry about format statements without leading digits since
* they would have been matched above as a variable anyway. */
"|[-+]?[0-9.]+([AaIiDdEeFfLlTtXx][Ss]?[-+]?[0-9.]*)?(_[a-zA-Z0-9][a-zA-Z0-9_]*)?"
- "|//|\\*\\*|::|[/<>=]="
- "|[^[:space:]]|[\x80-\xff]+"),
+ "|//|\\*\\*|::|[/<>=]="),
PATTERNS("html", "^[ \t]*(<[Hh][1-6][ \t].*>.*)$",
- "[^<>= \t]+|[^[:space:]]|[\x80-\xff]+"),
+ "[^<>= \t]+"),
PATTERNS("java",
"!^[ \t]*(catch|do|for|if|instanceof|new|return|switch|throw|while)\n"
"^[ \t]*(([A-Za-z_][A-Za-z_0-9]*[ \t]+)+[A-Za-z_][A-Za-z_0-9]*[ \t]*\\([^;]*)$",
"[a-zA-Z_][a-zA-Z0-9_]*"
"|[-+0-9.e]+[fFlL]?|0[xXbB]?[0-9a-fA-F]+[lL]?"
"|[-+*/<>%&^|=!]="
- "|--|\\+\\+|<<=?|>>>?=?|&&|\\|\\|"
- "|[^[:space:]]|[\x80-\xff]+"),
+ "|--|\\+\\+|<<=?|>>>?=?|&&|\\|\\|"),
PATTERNS("objc",
/* Negate C statements that can look like functions */
"!^[ \t]*(do|for|if|else|return|switch|while)\n"
/* -- */
"[a-zA-Z_][a-zA-Z0-9_]*"
"|[-+0-9.e]+[fFlL]?|0[xXbB]?[0-9a-fA-F]+[lL]?"
- "|[-+*/<>%&^|=!]=|--|\\+\\+|<<=?|>>=?|&&|\\|\\||::|->"
- "|[^[:space:]]|[\x80-\xff]+"),
+ "|[-+*/<>%&^|=!]=|--|\\+\\+|<<=?|>>=?|&&|\\|\\||::|->"),
PATTERNS("pascal",
"^(((class[ \t]+)?(procedure|function)|constructor|destructor|interface|"
"implementation|initialization|finalization)[ \t]*.*)$"
/* -- */
"[a-zA-Z_][a-zA-Z0-9_]*"
"|[-+0-9.e]+|0[xXbB]?[0-9a-fA-F]+"
- "|<>|<=|>=|:=|\\.\\."
- "|[^[:space:]]|[\x80-\xff]+"),
+ "|<>|<=|>=|:=|\\.\\."),
+PATTERNS("perl",
+ "^[ \t]*package .*;\n"
+ "^[ \t]*sub .* \\{\n"
+ "^[A-Z]+ \\{\n" /* BEGIN, END, ... */
+ "^=head[0-9] ", /* POD */
+ /* -- */
+ "[[:alpha:]_'][[:alnum:]_']*"
+ "|0[xb]?[0-9a-fA-F_]*"
+ /* taking care not to interpret 3..5 as (3.)(.5) */
+ "|[0-9a-fA-F_]+(\\.[0-9a-fA-F_]+)?([eE][-+]?[0-9_]+)?"
+ "|=>|-[rwxoRWXOezsfdlpSugkbctTBMAC>]|~~|::"
+ "|&&=|\\|\\|=|//=|\\*\\*="
+ "|&&|\\|\\||//|\\+\\+|--|\\*\\*|\\.\\.\\.?"
+ "|[-+*/%.^&<>=!|]="
+ "|=~|!~"
+ "|<<|<>|<=>|>>"),
PATTERNS("php",
"^[\t ]*(((public|protected|private|static)[\t ]+)*function.*)$\n"
"^[\t ]*(class.*)$",
/* -- */
"[a-zA-Z_][a-zA-Z0-9_]*"
"|[-+0-9.e]+|0[xXbB]?[0-9a-fA-F]+"
- "|[-+*/<>%&^|=!.]=|--|\\+\\+|<<=?|>>=?|===|&&|\\|\\||::|->"
- "|[^[:space:]]|[\x80-\xff]+"),
+ "|[-+*/<>%&^|=!.]=|--|\\+\\+|<<=?|>>=?|===|&&|\\|\\||::|->"),
PATTERNS("python", "^[ \t]*((class|def)[ \t].*)$",
/* -- */
"[a-zA-Z_][a-zA-Z0-9_]*"
"|[-+0-9.e]+[jJlL]?|0[xX]?[0-9a-fA-F]+[lL]?"
- "|[-+*/<>%&^|=!]=|//=?|<<=?|>>=?|\\*\\*=?"
- "|[^[:space:]]|[\x80-\xff]+"),
+ "|[-+*/<>%&^|=!]=|//=?|<<=?|>>=?|\\*\\*=?"),
/* -- */
PATTERNS("ruby", "^[ \t]*((class|module|def)[ \t].*)$",
/* -- */
"(@|@@|\\$)?[a-zA-Z_][a-zA-Z0-9_]*"
"|[-+0-9.e]+|0[xXbB]?[0-9a-fA-F]+|\\?(\\\\C-)?(\\\\M-)?."
- "|//=?|[-+*/<>%&^|=!]=|<<=?|>>=?|===|\\.{1,3}|::|[!=]~"
- "|[^[:space:]]|[\x80-\xff]+"),
+ "|//=?|[-+*/<>%&^|=!]=|<<=?|>>=?|===|\\.{1,3}|::|[!=]~"),
PATTERNS("bibtex", "(@[a-zA-Z]{1,}[ \t]*\\{{0,1}[ \t]*[^ \t\"@',\\#}{~%]*).*$",
"[={}\"]|[^={}\" \t]+"),
PATTERNS("tex", "^(\\\\((sub)*section|chapter|part)\\*{0,1}\\{.*)$",
- "\\\\[a-zA-Z@]+|\\\\.|[a-zA-Z0-9\x80-\xff]+|[^[:space:]]"),
+ "\\\\[a-zA-Z@]+|\\\\.|[a-zA-Z0-9\x80-\xff]+"),
PATTERNS("cpp",
/* Jump targets or access declarations */
"!^[ \t]*[A-Za-z_][A-Za-z_0-9]*:.*$\n"
/* -- */
"[a-zA-Z_][a-zA-Z0-9_]*"
"|[-+0-9.e]+[fFlL]?|0[xXbB]?[0-9a-fA-F]+[lL]?"
- "|[-+*/<>%&^|=!]=|--|\\+\\+|<<=?|>>=?|&&|\\|\\||::|->"
- "|[^[:space:]]|[\x80-\xff]+"),
+ "|[-+*/<>%&^|=!]=|--|\\+\\+|<<=?|>>=?|&&|\\|\\||::|->"),
PATTERNS("csharp",
/* Keywords */
"!^[ \t]*(do|while|for|if|else|instanceof|new|return|switch|case|throw|catch|using)\n"
/* -- */
"[a-zA-Z_][a-zA-Z0-9_]*"
"|[-+0-9.e]+[fFlL]?|0[xXbB]?[0-9a-fA-F]+[lL]?"
- "|[-+*/<>%&^|=!]=|--|\\+\\+|<<=?|>>=?|&&|\\|\\||::|->"
- "|[^[:space:]]|[\x80-\xff]+"),
+ "|[-+*/<>%&^|=!]=|--|\\+\\+|<<=?|>>=?|&&|\\|\\||::|->"),
{ "default", NULL, -1, { NULL, 0 } },
};
#undef PATTERNS