1
0
Fork 0
mirror of https://github.com/git/git.git synced 2024-05-19 22:16:21 +02:00
git/userdiff.c
Johannes Sixt 8a2e8da367 userdiff: have 'cpp' hunk header pattern catch more C++ anchor points
The hunk header pattern 'cpp' is intended for C and C++ source code, but
it is actually not particularly useful for the latter, and even misses
some use-cases for the former.

The parts of the pattern have the following flaws:

- The first part matches an identifier followed immediately by a colon
  and arbitrary text and is intended to reject goto labels and C++
  access specifiers (public, private, protected). But this pattern also
  rejects C++ constructs, which look like this:

    MyClass::MyClass()
    MyClass::~MyClass()
    MyClass::Item MyClass::Find(...

- The second part matches an identifier followed by a list of qualified
  names (i.e. identifiers separated by the C++ scope operator '::')
  separated by space or '*' followed by an opening parenthesis (with
  space between the tokens). It matches function declarations like

    struct item* get_head(...
    int Outer::Inner::Func(...

  Since the pattern requires at least two identifiers, GNU-style
  function definitions are ignored:

    void
    func(...

  Moreover, since the pattern does not allow punctuation other than '*',
  the following C++ constructs are not recognized:

  . template definitions:
      template<class T> int func(T arg)

  . functions returning references:
      const string& get_message()

  . functions returning templated types:
      vector<int> foo()

  . operator definitions:
      Value operator+(Value l, Value r)

- The third part of the pattern finally matches compound definitions.
  But it forgets about unions and namespaces, and also skips single-line
  definitions

    struct random_iterator_tag {};

  because no semicolon can occur on the line.

Change the first pattern to require a colon at the end of the line
(except for trailing space and comments), so that it does not reject
constructor or destructor definitions.

Notice that all interesting anchor points begin with an identifier or
keyword. But since there is a large variety of syntactical constructs
after the first "word", the simplest is to require only this word and
accept everything else. Therefore, this boils down to a line that begins
with a letter or underscore (optionally preceded by the C++ scope
operator '::' to accept functions returning a type anchored at the
global namespace). Replace the second and third part by a single pattern
that picks such a line.

This has the following desirable consequence:

- All constructs mentioned above are recognized.

and the following likely desirable consequences:

- Definitions of global variables and typedefs are recognized:

    int num_entries = 0;
    extern const char* help_text;
    typedef basic_string<wchar_t> wstring;

- Commonly used marco-ized boilerplate code is recognized:

    BEGIN_MESSAGE_MAP(CCanvas,CWnd)
    Q_DECLARE_METATYPE(MyStruct)
    PATTERNS("tex",...)

  (The last one is from this very patch.)

but also the following possibly undesirable consequence:

- When a label is not on a line by itself (except for a comment) it is
  no longer rejected, but can appear as a hunk header if it occurs at
  the beginning of a line:

    next:;

IMO, the benefits of the change outweigh the (possible) regressions by a
large margin.

Signed-off-by: Johannes Sixt <j6t@kdbg.org>
Signed-off-by: Junio C Hamano <gitster@pobox.com>
2014-03-21 15:03:32 -07:00

289 lines
9.2 KiB
C

#include "cache.h"
#include "userdiff.h"
#include "cache.h"
#include "attr.h"
static struct userdiff_driver *drivers;
static int ndrivers;
static int drivers_alloc;
#define PATTERNS(name, pattern, 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 "|[^[:space:]]|[\xc0-\xff][\x80-\xbf]+" }
static struct userdiff_driver builtin_drivers[] = {
IPATTERN("ada",
"!^(.*[ \t])?(is[ \t]+new|renames|is[ \t]+separate)([ \t].*)?$\n"
"!^[ \t]*with[ \t].*$\n"
"^[ \t]*((procedure|function)[ \t]+.*)$\n"
"^[ \t]*((package|protected|task)[ \t]+.*)$",
/* -- */
"[a-zA-Z][a-zA-Z0-9_]*"
"|[-+]?[0-9][0-9#_.aAbBcCdDeEfF]*([eE][+-]?[0-9_]+)?"
"|=>|\\.\\.|\\*\\*|:=|/=|>=|<=|<<|>>|<>"),
IPATTERN("fortran",
"!^([C*]|[ \t]*!)\n"
"!^[ \t]*MODULE[ \t]+PROCEDURE[ \t]\n"
"^[ \t]*((END[ \t]+)?(PROGRAM|MODULE|BLOCK[ \t]+DATA"
"|([^'\" \t]+[ \t]+)*(SUBROUTINE|FUNCTION))[ \t]+[A-Z].*)$",
/* -- */
"[a-zA-Z][a-zA-Z0-9_]*"
"|\\.([Ee][Qq]|[Nn][Ee]|[Gg][TtEe]|[Ll][TtEe]|[Tt][Rr][Uu][Ee]|[Ff][Aa][Ll][Ss][Ee]|[Aa][Nn][Dd]|[Oo][Rr]|[Nn]?[Ee][Qq][Vv]|[Nn][Oo][Tt])\\."
/* numbers and format statements like 2E14.4, or ES12.6, 9X.
* Don't worry about format statements without leading digits since
* they would have been matched above as a variable anyway. */
"|[-+]?[0-9.]+([AaIiDdEeFfLlTtXx][Ss]?[-+]?[0-9.]*)?(_[a-zA-Z0-9][a-zA-Z0-9_]*)?"
"|//|\\*\\*|::|[/<>=]="),
PATTERNS("html", "^[ \t]*(<[Hh][1-6][ \t].*>.*)$",
"[^<>= \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]*\\([^;]*)$",
/* -- */
"[a-zA-Z_][a-zA-Z0-9_]*"
"|[-+0-9.e]+[fFlL]?|0[xXbB]?[0-9a-fA-F]+[lL]?"
"|[-+*/<>%&^|=!]="
"|--|\\+\\+|<<=?|>>>?=?|&&|\\|\\|"),
PATTERNS("matlab",
"^[[:space:]]*((classdef|function)[[:space:]].*)$|^%%[[:space:]].*$",
"[a-zA-Z_][a-zA-Z0-9_]*|[-+0-9.e]+|[=~<>]=|\\.[*/\\^']|\\|\\||&&"),
PATTERNS("objc",
/* Negate C statements that can look like functions */
"!^[ \t]*(do|for|if|else|return|switch|while)\n"
/* Objective-C methods */
"^[ \t]*([-+][ \t]*\\([ \t]*[A-Za-z_][A-Za-z_0-9* \t]*\\)[ \t]*[A-Za-z_].*)$\n"
/* C functions */
"^[ \t]*(([A-Za-z_][A-Za-z_0-9]*[ \t]+)+[A-Za-z_][A-Za-z_0-9]*[ \t]*\\([^;]*)$\n"
/* Objective-C class/protocol definitions */
"^(@(implementation|interface|protocol)[ \t].*)$",
/* -- */
"[a-zA-Z_][a-zA-Z0-9_]*"
"|[-+0-9.e]+[fFlL]?|0[xXbB]?[0-9a-fA-F]+[lL]?"
"|[-+*/<>%&^|=!]=|--|\\+\\+|<<=?|>>=?|&&|\\|\\||::|->"),
PATTERNS("pascal",
"^(((class[ \t]+)?(procedure|function)|constructor|destructor|interface|"
"implementation|initialization|finalization)[ \t]*.*)$"
"\n"
"^(.*=[ \t]*(class|record).*)$",
/* -- */
"[a-zA-Z_][a-zA-Z0-9_]*"
"|[-+0-9.e]+|0[xXbB]?[0-9a-fA-F]+"
"|<>|<=|>=|:=|\\.\\."),
PATTERNS("perl",
"^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_]*"
/* 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]+"
"|[-+*/<>%&^|=!.]=|--|\\+\\+|<<=?|>>=?|===|&&|\\|\\||::|->"),
PATTERNS("python", "^[ \t]*((class|def)[ \t].*)$",
/* -- */
"[a-zA-Z_][a-zA-Z0-9_]*"
"|[-+0-9.e]+[jJlL]?|0[xX]?[0-9a-fA-F]+[lL]?"
"|[-+*/<>%&^|=!]=|//=?|<<=?|>>=?|\\*\\*=?"),
/* -- */
PATTERNS("ruby", "^[ \t]*((class|module|def)[ \t].*)$",
/* -- */
"(@|@@|\\$)?[a-zA-Z_][a-zA-Z0-9_]*"
"|[-+0-9.e]+|0[xXbB]?[0-9a-fA-F]+|\\?(\\\\C-)?(\\\\M-)?."
"|//=?|[-+*/<>%&^|=!]=|<<=?|>>=?|===|\\.{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]+"),
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)[ \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]?"
"|[-+*/<>%&^|=!]=|--|\\+\\+|<<=?|>>=?|&&|\\|\\||::|->"),
{ "default", NULL, -1, { NULL, 0 } },
};
#undef PATTERNS
#undef IPATTERN
static struct userdiff_driver driver_true = {
"diff=true",
NULL,
0,
{ NULL, 0 }
};
static struct userdiff_driver driver_false = {
"!diff",
NULL,
1,
{ NULL, 0 }
};
static struct userdiff_driver *userdiff_find_by_namelen(const char *k, int len)
{
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;
}
return NULL;
}
static int parse_funcname(struct userdiff_funcname *f, const char *k,
const char *v, int cflags)
{
if (git_config_string(&f->pattern, k, v) < 0)
return -1;
f->cflags = cflags;
return 0;
}
static int parse_tristate(int *b, const char *k, const char *v)
{
if (v && !strcasecmp(v, "auto"))
*b = -1;
else
*b = git_config_bool(k, v);
return 0;
}
static int parse_bool(int *b, const char *k, const char *v)
{
*b = git_config_bool(k, v);
return 0;
}
int userdiff_config(const char *k, const char *v)
{
struct userdiff_driver *drv;
const char *name, *type;
int namelen;
if (parse_config_key(k, "diff", &name, &namelen, &type) || !name)
return 0;
drv = userdiff_find_by_namelen(name, namelen);
if (!drv) {
ALLOC_GROW(drivers, ndrivers+1, drivers_alloc);
drv = &drivers[ndrivers++];
memset(drv, 0, sizeof(*drv));
drv->name = xmemdupz(name, namelen);
drv->binary = -1;
}
if (!strcmp(type, "funcname"))
return parse_funcname(&drv->funcname, k, v, 0);
if (!strcmp(type, "xfuncname"))
return parse_funcname(&drv->funcname, k, v, REG_EXTENDED);
if (!strcmp(type, "binary"))
return parse_tristate(&drv->binary, k, v);
if (!strcmp(type, "command"))
return git_config_string(&drv->external, k, v);
if (!strcmp(type, "textconv"))
return git_config_string(&drv->textconv, k, v);
if (!strcmp(type, "cachetextconv"))
return parse_bool(&drv->textconv_want_cache, k, v);
if (!strcmp(type, "wordregex"))
return git_config_string(&drv->word_regex, k, v);
return 0;
}
struct userdiff_driver *userdiff_find_by_name(const char *name) {
int len = strlen(name);
return userdiff_find_by_namelen(name, len);
}
struct userdiff_driver *userdiff_find_by_path(const char *path)
{
static struct git_attr *attr;
struct git_attr_check check;
if (!attr)
attr = git_attr("diff");
check.attr = attr;
if (!path)
return NULL;
if (git_check_attr(path, 1, &check))
return NULL;
if (ATTR_TRUE(check.value))
return &driver_true;
if (ATTR_FALSE(check.value))
return &driver_false;
if (ATTR_UNSET(check.value))
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;
}