summaryrefslogtreecommitdiff
path: root/userdiff.c
diff options
context:
space:
mode:
Diffstat (limited to 'userdiff.c')
-rw-r--r--userdiff.c79
1 files changed, 51 insertions, 28 deletions
diff --git a/userdiff.c b/userdiff.c
index 9ebf231ea5..01d3a8b81e 100644
--- a/userdiff.c
+++ b/userdiff.c
@@ -8,9 +8,11 @@ static int ndrivers;
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"
@@ -24,10 +26,9 @@ IPATTERN("fortran",
* 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].*>.*)$",
- "[^<>= \t]+|[^[:space:]]|[\x80-\xff]+"),
+ "[^<>= \t]+"),
PATTERNS("java",
"!^[ \t]*(catch|do|for|if|instanceof|new|return|switch|throw|while)\n"
"^[ \t]*(([A-Za-z_][A-Za-z_0-9]*[ \t]+)+[A-Za-z_][A-Za-z_0-9]*[ \t]*\\([^;]*)$",
@@ -35,8 +36,7 @@ PATTERNS("java",
"[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"
@@ -49,8 +49,7 @@ PATTERNS("objc",
/* -- */
"[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]*.*)$"
@@ -59,13 +58,26 @@ PATTERNS("pascal",
/* -- */
"[a-zA-Z_][a-zA-Z0-9_]*"
"|[-+0-9.e]+|0[xXbB]?[0-9a-fA-F]+"
- "|<>|<=|>=|:=|\\.\\."
- "|[^[:space:]]|[\x80-\xff]+"),
+ "|<>|<=|>=|:=|\\.\\."),
PATTERNS("perl",
- "^[ \t]*package .*;\n"
- "^[ \t]*sub .* \\{\n"
- "^[A-Z]+ \\{\n" /* BEGIN, END, ... */
- "^=head[0-9] ", /* POD */
+ "^package .*\n"
+ "^sub [[:alnum:]_':]+[ \t]*"
+ "(\\([^)]*\\)[ \t]*)?" /* prototype */
+ /*
+ * Attributes. A regex can't count nested parentheses,
+ * so just slurp up whatever we see, taking care not
+ * to accept lines like "sub foo; # defined elsewhere".
+ *
+ * An attribute could contain a semicolon, but at that
+ * point it seems reasonable enough to give up.
+ */
+ "(:[^;#]*)?"
+ "(\\{[ \t]*)?" /* brace can come here or on the next line */
+ "(#.*)?$\n" /* comment */
+ "^(BEGIN|END|INIT|CHECK|UNITCHECK|AUTOLOAD|DESTROY)[ \t]*"
+ "(\\{[ \t]*)?" /* brace can come here or on the next line */
+ "(#.*)?$\n"
+ "^=head[0-9] .*", /* POD */
/* -- */
"[[:alpha:]_'][[:alnum:]_']*"
"|0[xb]?[0-9a-fA-F_]*"
@@ -76,33 +88,29 @@ PATTERNS("perl",
"|&&|\\|\\||//|\\+\\+|--|\\*\\*|\\.\\.\\.?"
"|[-+*/%.^&<>=!|]="
"|=~|!~"
- "|<<|<>|<=>|>>"
- "|[^[:space:]]"),
+ "|<<|<>|<=>|>>"),
PATTERNS("php",
"^[\t ]*(((public|protected|private|static)[\t ]+)*function.*)$\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"
@@ -113,8 +121,7 @@ PATTERNS("cpp",
/* -- */
"[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"
@@ -129,8 +136,7 @@ PATTERNS("csharp",
/* -- */
"[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
@@ -275,3 +281,20 @@ struct userdiff_driver *userdiff_find_by_path(const char *path)
return NULL;
return userdiff_find_by_name(check.value);
}
+
+struct userdiff_driver *userdiff_get_textconv(struct userdiff_driver *driver)
+{
+ if (!driver->textconv)
+ return NULL;
+
+ if (driver->textconv_want_cache && !driver->textconv_cache) {
+ struct notes_cache *c = xmalloc(sizeof(*c));
+ struct strbuf name = STRBUF_INIT;
+
+ strbuf_addf(&name, "textconv/%s", driver->name);
+ notes_cache_init(c, name.buf, driver->textconv);
+ driver->textconv_cache = c;
+ }
+
+ return driver;
+}
generated by cgit v1.2.3 (git 2.25.1) at 2024-11-02 10:19:23 +0000