diff options
Diffstat (limited to 'userdiff.c')
| -rw-r--r-- | userdiff.c | 28 |
1 files changed, 24 insertions, 4 deletions
diff --git a/userdiff.c b/userdiff.c index d9b2ba752f..8578cb0d12 100644 --- a/userdiff.c +++ b/userdiff.c @@ -13,6 +13,16 @@ static int drivers_alloc; #define IPATTERN(name, pattern, word_regex) \ { name, NULL, -1, { pattern, REG_EXTENDED | REG_ICASE }, \ word_regex "|[^[:space:]]|[\xc0-\xff][\x80-\xbf]+" } + +/* + * Built-in drivers for various languages, sorted by their names + * (except that the "default" is left at the end). + * + * When writing or updating patterns, assume that the contents these + * patterns are applied to are syntactically correct. The patterns + * can be simple without implementing all syntactical corner cases, as + * long as they are sufficiently permissive. + */ static struct userdiff_driver builtin_drivers[] = { IPATTERN("ada", "!^(.*[ \t])?(is[ \t]+new|renames|is[ \t]+separate)([ \t].*)?$\n" @@ -54,9 +64,15 @@ PATTERNS("cpp", /* functions/methods, variables, and compounds at top level */ "^((::[[:space:]]*)?[A-Za-z_].*)$", /* -- */ + /* identifiers and keywords */ "[a-zA-Z_][a-zA-Z0-9_]*" - "|[-+0-9.e]+[fFlL]?|0[xXbB]?[0-9a-fA-F]+[lLuU]*" - "|[-+*/<>%&^|=!]=|--|\\+\\+|<<=?|>>=?|&&|\\|\\||::|->\\*?|\\.\\*"), + /* decimal and octal integers as well as floatingpoint numbers */ + "|[0-9][0-9.]*([Ee][-+]?[0-9]+)?[fFlLuU]*" + /* hexadecimal and binary integers */ + "|0[xXbB][0-9a-fA-F]+[lLuU]*" + /* floatingpoint numbers that begin with a decimal point */ + "|\\.[0-9][0-9]*([Ee][-+]?[0-9]+)?[fFlL]?" + "|[-+*/<>%&^|=!]=|--|\\+\\+|<<=?|>>=?|&&|\\|\\||::|->\\*?|\\.\\*|<=>"), PATTERNS("csharp", /* Keywords */ "!^[ \t]*(do|while|for|if|else|instanceof|new|return|switch|case|throw|catch|using)\n" @@ -142,7 +158,11 @@ PATTERNS("html", "[^<>= \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]*\\([^;]*)$", + /* Class, enum, and interface declarations */ + "^[ \t]*(([a-z]+[ \t]+)*(class|enum|interface)[ \t]+[A-Za-z][A-Za-z0-9_$]*[ \t]+.*)$\n" + /* Method definitions; note that constructor signatures are not */ + /* matched because they are indistinguishable from method calls. */ + "^[ \t]*(([A-Za-z_<>&][][?&<>.,A-Za-z_0-9]*[ \t]+)+[A-Za-z_][A-Za-z_0-9]*[ \t]*\\([^;]*)$", /* -- */ "[a-zA-Z_][a-zA-Z0-9_]*" "|[-+0-9.e]+[fFlL]?|0[xXbB]?[0-9a-fA-F]+[lL]?" @@ -214,7 +234,7 @@ PATTERNS("perl", "|<<|<>|<=>|>>"), PATTERNS("php", "^[\t ]*(((public|protected|private|static|abstract|final)[\t ]+)*function.*)$\n" - "^[\t ]*((((final|abstract)[\t ]+)?class|interface|trait).*)$", + "^[\t ]*((((final|abstract)[\t ]+)?class|enum|interface|trait).*)$", /* -- */ "[a-zA-Z_][a-zA-Z0-9_]*" "|[-+0-9.e]+|0[xXbB]?[0-9a-fA-F]+" |