summaryrefslogtreecommitdiff
path: root/userdiff.c
diff options
context:
space:
mode:
Diffstat (limited to 'userdiff.c')
-rw-r--r--userdiff.c209
1 files changed, 149 insertions, 60 deletions
diff --git a/userdiff.c b/userdiff.c
index 1df884e..3c3bbe3 100644
--- a/userdiff.c
+++ b/userdiff.c
@@ -23,6 +23,67 @@ IPATTERN("ada",
"[a-zA-Z][a-zA-Z0-9_]*"
"|[-+]?[0-9][0-9#_.aAbBcCdDeEfF]*([eE][+-]?[0-9_]+)?"
"|=>|\\.\\.|\\*\\*|:=|/=|>=|<=|<<|>>|<>"),
+PATTERNS("bash",
+ /* Optional leading indentation */
+ "^[ \t]*"
+ /* Start of captured text */
+ "("
+ "("
+ /* POSIX identifier with mandatory parentheses */
+ "[a-zA-Z_][a-zA-Z0-9_]*[ \t]*\\([ \t]*\\))"
+ "|"
+ /* Bashism identifier with optional parentheses */
+ "(function[ \t]+[a-zA-Z_][a-zA-Z0-9_]*(([ \t]*\\([ \t]*\\))|([ \t]+))"
+ ")"
+ /* Optional whitespace */
+ "[ \t]*"
+ /* Compound command starting with `{`, `(`, `((` or `[[` */
+ "(\\{|\\(\\(?|\\[\\[)"
+ /* End of captured text */
+ ")",
+ /* -- */
+ /* Characters not in the default $IFS value */
+ "[^ \t]+"),
+PATTERNS("bibtex",
+ "(@[a-zA-Z]{1,}[ \t]*\\{{0,1}[ \t]*[^ \t\"@',\\#}{~%]*).*$",
+ /* -- */
+ "[={}\"]|[^={}\" \t]+"),
+PATTERNS("cpp",
+ /* Jump targets or access declarations */
+ "!^[ \t]*[A-Za-z_][A-Za-z_0-9]*:[[:space:]]*($|/[/*])\n"
+ /* functions/methods, variables, and compounds at top level */
+ "^((::[[:space:]]*)?[A-Za-z_].*)$",
+ /* -- */
+ "[a-zA-Z_][a-zA-Z0-9_]*"
+ "|[-+0-9.e]+[fFlL]?|0[xXbB]?[0-9a-fA-F]+[lLuU]*"
+ "|[-+*/<>%&^|=!]=|--|\\+\\+|<<=?|>>=?|&&|\\|\\||::|->\\*?|\\.\\*"),
+PATTERNS("csharp",
+ /* Keywords */
+ "!^[ \t]*(do|while|for|if|else|instanceof|new|return|switch|case|throw|catch|using)\n"
+ /* Methods and constructors */
+ "^[ \t]*(((static|public|internal|private|protected|new|virtual|sealed|override|unsafe|async)[ \t]+)*[][<>@.~_[:alnum:]]+[ \t]+[<>@._[:alnum:]]+[ \t]*\\(.*\\))[ \t]*$\n"
+ /* Properties */
+ "^[ \t]*(((static|public|internal|private|protected|new|virtual|sealed|override|unsafe)[ \t]+)*[][<>@.~_[:alnum:]]+[ \t]+[@._[:alnum:]]+)[ \t]*$\n"
+ /* Type definitions */
+ "^[ \t]*(((static|public|internal|private|protected|new|unsafe|sealed|abstract|partial)[ \t]+)*(class|enum|interface|struct)[ \t]+.*)$\n"
+ /* Namespace */
+ "^[ \t]*(namespace[ \t]+.*)$",
+ /* -- */
+ "[a-zA-Z_][a-zA-Z0-9_]*"
+ "|[-+0-9.e]+[fFlL]?|0[xXbB]?[0-9a-fA-F]+[lL]?"
+ "|[-+*/<>%&^|=!]=|--|\\+\\+|<<=?|>>=?|&&|\\|\\||::|->"),
+IPATTERN("css",
+ "![:;][[:space:]]*$\n"
+ "^[:[@.#]?[_a-z0-9].*$",
+ /* -- */
+ /*
+ * This regex comes from W3C CSS specs. Should theoretically also
+ * allow ISO 10646 characters U+00A0 and higher,
+ * but they are not handled in this regex.
+ */
+ "-?[_a-zA-Z][-_a-zA-Z0-9]*" /* identifiers */
+ "|-?[0-9]+|\\#[0-9a-fA-F]+" /* numbers */
+),
PATTERNS("dts",
"!;\n"
"!=\n"
@@ -46,10 +107,14 @@ PATTERNS("elixir",
/* Not real operators, but should be grouped */
"|:?%[A-Za-z0-9_.]\\{\\}?"),
IPATTERN("fortran",
+ /* Don't match comment lines */
"!^([C*]|[ \t]*!)\n"
+ /* Don't match 'module procedure' lines */
"!^[ \t]*MODULE[ \t]+PROCEDURE[ \t]\n"
+ /* Program, module, block data */
"^[ \t]*((END[ \t]+)?(PROGRAM|MODULE|BLOCK[ \t]+DATA"
- "|([^'\" \t]+[ \t]+)*(SUBROUTINE|FUNCTION))[ \t]+[A-Z].*)$",
+ /* Subroutines and functions */
+ "|([^!'\" \t]+[ \t]+)*(SUBROUTINE|FUNCTION))[ \t]+[A-Z].*)$",
/* -- */
"[a-zA-Z][a-zA-Z0-9_]*"
"|\\.([Ee][Qq]|[Nn][Ee]|[Gg][TtEe]|[Ll][TtEe]|[Tt][Rr][Uu][Ee]|[Ff][Aa][Ll][Ss][Ee]|[Aa][Nn][Dd]|[Oo][Rr]|[Nn]?[Ee][Qq][Vv]|[Nn][Oo][Tt])\\."
@@ -58,7 +123,9 @@ IPATTERN("fortran",
* they would have been matched above as a variable anyway. */
"|[-+]?[0-9.]+([AaIiDdEeFfLlTtXx][Ss]?[-+]?[0-9.]*)?(_[a-zA-Z0-9][a-zA-Z0-9_]*)?"
"|//|\\*\\*|::|[/<>=]="),
-IPATTERN("fountain", "^((\\.[^.]|(int|ext|est|int\\.?/ext|i/e)[. ]).*)$",
+IPATTERN("fountain",
+ "^((\\.[^.]|(int|ext|est|int\\.?/ext|i/e)[. ]).*)$",
+ /* -- */
"[^ \t-]+"),
PATTERNS("golang",
/* Functions */
@@ -69,7 +136,9 @@ PATTERNS("golang",
"[a-zA-Z_][a-zA-Z0-9_]*"
"|[-+0-9.eE]+i?|0[xX]?[0-9a-fA-F]+i?"
"|[-+*/<>%&^|=!:]=|--|\\+\\+|<<=?|>>=?|&\\^=?|&&|\\|\\||<-|\\.{3}"),
-PATTERNS("html", "^[ \t]*(<[Hh][1-6]([ \t].*)?>.*)$",
+PATTERNS("html",
+ "^[ \t]*(<[Hh][1-6]([ \t].*)?>.*)$",
+ /* -- */
"[^<>= \t]+"),
PATTERNS("java",
"!^[ \t]*(catch|do|for|if|instanceof|new|return|switch|throw|while)\n"
@@ -81,6 +150,7 @@ PATTERNS("java",
"|--|\\+\\+|<<=?|>>>?=?|&&|\\|\\|"),
PATTERNS("markdown",
"^ {0,3}#{1,6}[ \t].*",
+ /* -- */
"[^<>= \t]+"),
PATTERNS("matlab",
/*
@@ -89,6 +159,7 @@ PATTERNS("matlab",
* that is understood by both.
*/
"^[[:space:]]*((classdef|function)[[:space:]].*)$|^(%%%?|##)[[:space:]].*$",
+ /* -- */
"[a-zA-Z_][a-zA-Z0-9_]*|[-+0-9.e]+|[=~<>]=|\\.[*/\\^']|\\|\\||&&"),
PATTERNS("objc",
/* Negate C statements that can look like functions */
@@ -104,9 +175,8 @@ PATTERNS("objc",
"|[-+0-9.e]+[fFlL]?|0[xXbB]?[0-9a-fA-F]+[lL]?"
"|[-+*/<>%&^|=!]=|--|\\+\\+|<<=?|>>=?|&&|\\|\\||::|->"),
PATTERNS("pascal",
- "^(((class[ \t]+)?(procedure|function)|constructor|destructor|interface|"
- "implementation|initialization|finalization)[ \t]*.*)$"
- "\n"
+ "^(((class[ \t]+)?(procedure|function)|constructor|destructor|interface"
+ "|implementation|initialization|finalization)[ \t]*.*)$\n"
"^(.*=[ \t]*(class|record).*)$",
/* -- */
"[a-zA-Z_][a-zA-Z0-9_]*"
@@ -143,69 +213,42 @@ PATTERNS("perl",
"|=~|!~"
"|<<|<>|<=>|>>"),
PATTERNS("php",
- "^[\t ]*(((public|protected|private|static)[\t ]+)*function.*)$\n"
+ "^[\t ]*(((public|protected|private|static|abstract|final)[\t ]+)*function.*)$\n"
"^[\t ]*((((final|abstract)[\t ]+)?class|interface|trait).*)$",
/* -- */
"[a-zA-Z_][a-zA-Z0-9_]*"
"|[-+0-9.e]+|0[xXbB]?[0-9a-fA-F]+"
"|[-+*/<>%&^|=!.]=|--|\\+\\+|<<=?|>>=?|===|&&|\\|\\||::|->"),
-PATTERNS("python", "^[ \t]*((class|(async[ \t]+)?def)[ \t].*)$",
+PATTERNS("python",
+ "^[ \t]*((class|(async[ \t]+)?def)[ \t].*)$",
/* -- */
"[a-zA-Z_][a-zA-Z0-9_]*"
"|[-+0-9.e]+[jJlL]?|0[xX]?[0-9a-fA-F]+[lL]?"
"|[-+*/<>%&^|=!]=|//=?|<<=?|>>=?|\\*\\*=?"),
/* -- */
-PATTERNS("ruby", "^[ \t]*((class|module|def)[ \t].*)$",
+PATTERNS("ruby",
+ "^[ \t]*((class|module|def)[ \t].*)$",
/* -- */
"(@|@@|\\$)?[a-zA-Z_][a-zA-Z0-9_]*"
"|[-+0-9.e]+|0[xXbB]?[0-9a-fA-F]+|\\?(\\\\C-)?(\\\\M-)?."
"|//=?|[-+*/<>%&^|=!]=|<<=?|>>=?|===|\\.{1,3}|::|[!=]~"),
PATTERNS("rust",
- "^[\t ]*((pub(\\([^\\)]+\\))?[\t ]+)?((async|const|unsafe|extern([\t ]+\"[^\"]+\"))[\t ]+)?(struct|enum|union|mod|trait|fn|impl)[< \t]+[^;]*)$",
+ "^[\t ]*((pub(\\([^\\)]+\\))?[\t ]+)?((async|const|unsafe|extern([\t ]+\"[^\"]+\"))[\t ]+)?(struct|enum|union|mod|trait|fn|impl|macro_rules!)[< \t]+[^;]*)$",
/* -- */
"[a-zA-Z_][a-zA-Z0-9_]*"
"|[0-9][0-9_a-fA-Fiosuxz]*(\\.([0-9]*[eE][+-]?)?[0-9_fF]*)?"
"|[-+*\\/<>%&^|=!:]=|<<=?|>>=?|&&|\\|\\||->|=>|\\.{2}=|\\.{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]+"),
-PATTERNS("cpp",
- /* Jump targets or access declarations */
- "!^[ \t]*[A-Za-z_][A-Za-z_0-9]*:[[:space:]]*($|/[/*])\n"
- /* functions/methods, variables, and compounds at top level */
- "^((::[[:space:]]*)?[A-Za-z_].*)$",
- /* -- */
- "[a-zA-Z_][a-zA-Z0-9_]*"
- "|[-+0-9.e]+[fFlL]?|0[xXbB]?[0-9a-fA-F]+[lLuU]*"
- "|[-+*/<>%&^|=!]=|--|\\+\\+|<<=?|>>=?|&&|\\|\\||::|->\\*?|\\.\\*"),
-PATTERNS("csharp",
- /* Keywords */
- "!^[ \t]*(do|while|for|if|else|instanceof|new|return|switch|case|throw|catch|using)\n"
- /* Methods and constructors */
- "^[ \t]*(((static|public|internal|private|protected|new|virtual|sealed|override|unsafe|async)[ \t]+)*[][<>@.~_[:alnum:]]+[ \t]+[<>@._[:alnum:]]+[ \t]*\\(.*\\))[ \t]*$\n"
- /* Properties */
- "^[ \t]*(((static|public|internal|private|protected|new|virtual|sealed|override|unsafe)[ \t]+)*[][<>@.~_[:alnum:]]+[ \t]+[@._[:alnum:]]+)[ \t]*$\n"
- /* Type definitions */
- "^[ \t]*(((static|public|internal|private|protected|new|unsafe|sealed|abstract|partial)[ \t]+)*(class|enum|interface|struct)[ \t]+.*)$\n"
- /* Namespace */
- "^[ \t]*(namespace[ \t]+.*)$",
- /* -- */
- "[a-zA-Z_][a-zA-Z0-9_]*"
- "|[-+0-9.e]+[fFlL]?|0[xXbB]?[0-9a-fA-F]+[lL]?"
- "|[-+*/<>%&^|=!]=|--|\\+\\+|<<=?|>>=?|&&|\\|\\||::|->"),
-IPATTERN("css",
- "![:;][[:space:]]*$\n"
- "^[_a-z0-9].*$",
- /* -- */
+PATTERNS("scheme",
+ "^[\t ]*(\\(((define|def(struct|syntax|class|method|rules|record|proto|alias)?)[-*/ \t]|(library|module|struct|class)[*+ \t]).*)$",
/*
- * This regex comes from W3C CSS specs. Should theoretically also
- * allow ISO 10646 characters U+00A0 and higher,
- * but they are not handled in this regex.
+ * R7RS valid identifiers include any sequence enclosed
+ * within vertical lines having no backslashes
*/
- "-?[_a-zA-Z][-_a-zA-Z0-9]*" /* identifiers */
- "|-?[0-9]+|\\#[0-9a-fA-F]+" /* numbers */
-),
+ "\\|([^\\\\]*)\\|"
+ /* All other words should be delimited by spaces or parentheses */
+ "|([^][)(}{[ \t])+"),
+PATTERNS("tex", "^(\\\\((sub)*section|chapter|part)\\*{0,1}\\{.*)$",
+ "\\\\[a-zA-Z@]+|\\\\.|[a-zA-Z0-9\x80-\xff]+"),
{ "default", NULL, -1, { NULL, 0 } },
};
#undef PATTERNS
@@ -225,20 +268,33 @@ static struct userdiff_driver driver_false = {
{ NULL, 0 }
};
-static struct userdiff_driver *userdiff_find_by_namelen(const char *k, size_t len)
+struct find_by_namelen_data {
+ const char *name;
+ size_t len;
+ struct userdiff_driver *driver;
+};
+
+static int userdiff_find_by_namelen_cb(struct userdiff_driver *driver,
+ enum userdiff_driver_type type, void *priv)
{
- int i;
- for (i = 0; i < ndrivers; i++) {
- struct userdiff_driver *drv = drivers + i;
- if (!strncmp(drv->name, k, len) && !drv->name[len])
- return drv;
- }
- for (i = 0; i < ARRAY_SIZE(builtin_drivers); i++) {
- struct userdiff_driver *drv = builtin_drivers + i;
- if (!strncmp(drv->name, k, len) && !drv->name[len])
- return drv;
+ struct find_by_namelen_data *cb_data = priv;
+
+ if (!strncmp(driver->name, cb_data->name, cb_data->len) &&
+ !driver->name[cb_data->len]) {
+ cb_data->driver = driver;
+ return 1; /* tell the caller to stop iterating */
}
- return NULL;
+ return 0;
+}
+
+static struct userdiff_driver *userdiff_find_by_namelen(const char *name, size_t len)
+{
+ struct find_by_namelen_data udcbdata = {
+ .name = name,
+ .len = len,
+ };
+ for_each_userdiff_driver(userdiff_find_by_namelen_cb, &udcbdata);
+ return udcbdata.driver;
}
static int parse_funcname(struct userdiff_funcname *f, const char *k,
@@ -345,3 +401,36 @@ struct userdiff_driver *userdiff_get_textconv(struct repository *r,
return driver;
}
+
+static int for_each_userdiff_driver_list(each_userdiff_driver_fn fn,
+ enum userdiff_driver_type type, void *cb_data,
+ struct userdiff_driver *drv,
+ int drv_size)
+{
+ int i;
+ int ret;
+ for (i = 0; i < drv_size; i++) {
+ struct userdiff_driver *item = drv + i;
+ if ((ret = fn(item, type, cb_data)))
+ return ret;
+ }
+ return 0;
+}
+
+int for_each_userdiff_driver(each_userdiff_driver_fn fn, void *cb_data)
+{
+ int ret;
+
+ ret = for_each_userdiff_driver_list(fn, USERDIFF_DRIVER_TYPE_CUSTOM,
+ cb_data, drivers, ndrivers);
+ if (ret)
+ return ret;
+
+ ret = for_each_userdiff_driver_list(fn, USERDIFF_DRIVER_TYPE_BUILTIN,
+ cb_data, builtin_drivers,
+ ARRAY_SIZE(builtin_drivers));
+ if (ret)
+ return ret;
+
+ return 0;
+}
generated by cgit v0.10.2-6-g49f6 at 2024-04-24 07:17:12 (GMT)