diff options
Diffstat (limited to 'userdiff.c')
| -rw-r--r-- | userdiff.c | 312 |
1 files changed, 234 insertions, 78 deletions
diff --git a/userdiff.c b/userdiff.c index fde02f225b..e399543823 100644 --- a/userdiff.c +++ b/userdiff.c @@ -1,18 +1,43 @@ -#include "cache.h" +#include "git-compat-util.h" #include "config.h" #include "userdiff.h" #include "attr.h" +#include "strbuf.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]+" } +#define PATTERNS(lang, rx, wrx) { \ + .name = lang, \ + .binary = -1, \ + .funcname = { \ + .pattern = rx, \ + .cflags = REG_EXTENDED, \ + }, \ + .word_regex = wrx "|[^[:space:]]|[\xc0-\xff][\x80-\xbf]+", \ + .word_regex_multi_byte = wrx "|[^[:space:]]", \ +} +#define IPATTERN(lang, rx, wrx) { \ + .name = lang, \ + .binary = -1, \ + .funcname = { \ + .pattern = rx, \ + .cflags = REG_EXTENDED | REG_ICASE, \ + }, \ + .word_regex = wrx "|[^[:space:]]|[\xc0-\xff][\x80-\xbf]+", \ + .word_regex_multi_byte = wrx "|[^[:space:]]", \ +} + +/* + * 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" @@ -23,6 +48,73 @@ 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:]]*($|/[/*])\n" + /* functions/methods, variables, and compounds at top level */ + "^((::[[:space:]]*)?[A-Za-z_].*)$", + /* -- */ + /* identifiers and keywords */ + "[a-zA-Z_][a-zA-Z0-9_]*" + /* 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" + /* 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|record)[ \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" @@ -62,7 +154,9 @@ 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 */ @@ -73,18 +167,37 @@ 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" - "^[ \t]*(([A-Za-z_][A-Za-z_0-9]*[ \t]+)+[A-Za-z_][A-Za-z_0-9]*[ \t]*\\([^;]*)$", + /* Class, enum, interface, and record declarations */ + "^[ \t]*(([a-z-]+[ \t]+)*(class|enum|interface|record)[ \t]+.*)$\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]*\\([^;]*)$", /* -- */ "[a-zA-Z_][a-zA-Z0-9_]*" "|[-+0-9.e]+[fFlL]?|0[xXbB]?[0-9a-fA-F]+[lL]?" "|[-+*/<>%&^|=!]=" "|--|\\+\\+|<<=?|>>>?=?|&&|\\|\\|"), +PATTERNS("kotlin", + "^[ \t]*(([a-z]+[ \t]+)*(fun|class|interface)[ \t]+.*)$", + /* -- */ + "[a-zA-Z_][a-zA-Z0-9_]*" + /* hexadecimal and binary numbers */ + "|0[xXbB][0-9a-fA-F_]+[lLuU]*" + /* integers and floats */ + "|[0-9][0-9_]*([.][0-9_]*)?([Ee][-+]?[0-9]+)?[fFlLuU]*" + /* floating point numbers beginning with decimal point */ + "|[.][0-9][0-9_]*([Ee][-+]?[0-9]+)?[fFlLuU]?" + /* unary and binary operators */ + "|[-+*/<>%&^|=!]==?|--|\\+\\+|<<=|>>=|&&|\\|\\||->|\\.\\*|!!|[?:.][.:]"), PATTERNS("markdown", "^ {0,3}#{1,6}[ \t].*", + /* -- */ "[^<>= \t]+"), PATTERNS("matlab", /* @@ -93,6 +206,7 @@ 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 */ @@ -108,9 +222,8 @@ 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).*)$", /* -- */ "[a-zA-Z_][a-zA-Z0-9_]*" @@ -147,102 +260,104 @@ PATTERNS("perl", "|=~|!~" "|<<|<>|<=>|>>"), PATTERNS("php", - "^[\t ]*(((public|protected|private|static)[\t ]+)*function.*)$\n" - "^[\t ]*((((final|abstract)[\t ]+)?class|interface|trait).*)$", + "^[\t ]*(((public|protected|private|static|abstract|final)[\t ]+)*function.*)$\n" + "^[\t ]*((((final|abstract)[\t ]+)?class|enum|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]).*)$", /* - * This regex comes from W3C CSS specs. Should theoretically also - * allow ISO 10646 characters U+00A0 and higher, - * but they are not handled in this regex. + * R7RS valid identifiers include any sequence enclosed + * within vertical lines having no backslashes */ - "-?[_a-zA-Z][-_a-zA-Z0-9]*" /* identifiers */ - "|-?[0-9]+|\\#[0-9a-fA-F]+" /* numbers */ -), -{ "default", NULL, -1, { NULL, 0 } }, + "\\|([^\\\\]*)\\|" + /* All other words should be delimited by spaces or parentheses */ + "|([^][)(}{[ \t])+"), +PATTERNS("tex", "^(\\\\((sub)*section|chapter|part)\\*{0,1}\\{.*)$", + "\\\\[a-zA-Z@]+|\\\\.|([a-zA-Z0-9]|[^\x01-\x7f])+"), +{ "default", NULL, NULL, -1, { NULL, 0 } }, }; #undef PATTERNS #undef IPATTERN static struct userdiff_driver driver_true = { - "diff=true", - NULL, - 0, - { NULL, 0 } + .name = "diff=true", + .binary = 0, }; static struct userdiff_driver driver_false = { - "!diff", - NULL, - 1, - { NULL, 0 } + .name = "!diff", + .binary = 1, +}; + +struct find_by_namelen_data { + const char *name; + size_t len; + struct userdiff_driver *driver; }; -static struct userdiff_driver *userdiff_find_by_namelen(const char *k, size_t len) +static int userdiff_find_by_namelen_cb(struct userdiff_driver *driver, + enum userdiff_driver_type type UNUSED, + 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 int regexec_supports_multi_byte_chars(void) +{ + static const char not_space[] = "[^[:space:]]"; + static const char utf8_multi_byte_char[] = "\xc2\xa3"; + regex_t re; + regmatch_t match; + static int result = -1; + + if (result != -1) + return result; + if (regcomp(&re, not_space, REG_EXTENDED)) + BUG("invalid regular expression: %s", not_space); + result = !regexec(&re, utf8_multi_byte_char, 1, &match, 0) && + match.rm_so == 0 && + match.rm_eo == strlen(utf8_multi_byte_char); + regfree(&re); + return result; +} + +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, @@ -301,6 +416,8 @@ int userdiff_config(const char *k, const char *v) return parse_bool(&drv->textconv_want_cache, k, v); if (!strcmp(type, "wordregex")) return git_config_string(&drv->word_regex, k, v); + if (!strcmp(type, "algorithm")) + return git_config_string(&drv->algorithm, k, v); return 0; } @@ -308,7 +425,13 @@ int userdiff_config(const char *k, const char *v) struct userdiff_driver *userdiff_find_by_name(const char *name) { int len = strlen(name); - return userdiff_find_by_namelen(name, len); + struct userdiff_driver *driver = userdiff_find_by_namelen(name, len); + if (driver && driver->word_regex_multi_byte) { + if (regexec_supports_multi_byte_chars()) + driver->word_regex = driver->word_regex_multi_byte; + driver->word_regex_multi_byte = NULL; + } + return driver; } struct userdiff_driver *userdiff_find_by_path(struct index_state *istate, @@ -349,3 +472,36 @@ 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; +} |