1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290
|
#include "git-compat-util.h"
#include "line-range.h"
#include "xdiff-interface.h"
#include "strbuf.h"
#include "userdiff.h"
/*
* Parse one item in the -L option
*
* 'begin' is applicable only to relative range anchors. Absolute anchors
* ignore this value.
*
* When parsing "-L A,B", parse_loc() is called once for A and once for B.
*
* When parsing A, 'begin' must be a negative number, the absolute value of
* which is the line at which relative start-of-range anchors should be
* based. Beginning of file is represented by -1.
*
* When parsing B, 'begin' must be the positive line number immediately
* following the line computed for 'A'.
*/
static const char *parse_loc(const char *spec, nth_line_fn_t nth_line,
void *data, long lines, long begin, long *ret)
{
char *term;
const char *line;
long num;
int reg_error;
regex_t regexp;
regmatch_t match[1];
/* Allow "-L <something>,+20" to mean starting at <something>
* for 20 lines, or "-L <something>,-5" for 5 lines ending at
* <something>.
*/
if (1 <= begin && (spec[0] == '+' || spec[0] == '-')) {
num = strtol(spec + 1, &term, 10);
if (term != spec + 1) {
if (!ret)
return term;
if (num == 0)
die("-L invalid empty range");
if (spec[0] == '-')
num = 0 - num;
if (0 < num)
*ret = begin + num - 2;
else if (!num)
*ret = begin;
else
*ret = begin + num;
return term;
}
return spec;
}
num = strtol(spec, &term, 10);
if (term != spec) {
if (ret) {
if (num <= 0)
die("-L invalid line number: %ld", num);
*ret = num;
}
return term;
}
if (begin < 0) {
if (spec[0] != '^')
begin = -begin;
else {
begin = 1;
spec++;
}
}
if (spec[0] != '/')
return spec;
/* it could be a regexp of form /.../ */
for (term = (char *) spec + 1; *term && *term != '/'; term++) {
if (*term == '\\')
term++;
}
if (*term != '/')
return spec;
/* in the scan-only case we are not interested in the regex */
if (!ret)
return term+1;
/* try [spec+1 .. term-1] as regexp */
*term = 0;
begin--; /* input is in human terms */
line = nth_line(data, begin);
if (!(reg_error = regcomp(®exp, spec + 1, REG_NEWLINE)) &&
!(reg_error = regexec(®exp, line, 1, match, 0))) {
const char *cp = line + match[0].rm_so;
const char *nline;
while (begin++ < lines) {
nline = nth_line(data, begin);
if (line <= cp && cp < nline)
break;
line = nline;
}
*ret = begin;
regfree(®exp);
*term++ = '/';
return term;
}
else {
char errbuf[1024];
regerror(reg_error, ®exp, errbuf, 1024);
die("-L parameter '%s' starting at line %ld: %s",
spec + 1, begin + 1, errbuf);
}
}
static int match_funcname(xdemitconf_t *xecfg, const char *bol, const char *eol)
{
if (xecfg) {
char buf[1];
return xecfg->find_func(bol, eol - bol, buf, 1,
xecfg->find_func_priv) >= 0;
}
if (bol == eol)
return 0;
if (isalpha(*bol) || *bol == '_' || *bol == '$')
return 1;
return 0;
}
static const char *find_funcname_matching_regexp(xdemitconf_t *xecfg, const char *start,
regex_t *regexp)
{
int reg_error;
regmatch_t match[1];
while (1) {
const char *bol, *eol;
reg_error = regexec(regexp, start, 1, match, 0);
if (reg_error == REG_NOMATCH)
return NULL;
else if (reg_error) {
char errbuf[1024];
regerror(reg_error, regexp, errbuf, 1024);
die("-L parameter: regexec() failed: %s", errbuf);
}
/* determine extent of line matched */
bol = start+match[0].rm_so;
eol = start+match[0].rm_eo;
while (bol > start && *bol != '\n')
bol--;
if (*bol == '\n')
bol++;
while (*eol && *eol != '\n')
eol++;
if (*eol == '\n')
eol++;
/* is it a funcname line? */
if (match_funcname(xecfg, (char*) bol, (char*) eol))
return bol;
start = eol;
}
}
static const char *parse_range_funcname(const char *arg, nth_line_fn_t nth_line_cb,
void *cb_data, long lines, long anchor, long *begin, long *end,
const char *path)
{
char *pattern;
const char *term;
struct userdiff_driver *drv;
xdemitconf_t *xecfg = NULL;
const char *start;
const char *p;
int reg_error;
regex_t regexp;
if (*arg == '^') {
anchor = 1;
arg++;
}
assert(*arg == ':');
term = arg+1;
while (*term && *term != ':') {
if (*term == '\\' && *(term+1))
term++;
term++;
}
if (term == arg+1)
return NULL;
if (!begin) /* skip_range_arg case */
return term;
pattern = xstrndup(arg+1, term-(arg+1));
anchor--; /* input is in human terms */
start = nth_line_cb(cb_data, anchor);
drv = userdiff_find_by_path(path);
if (drv && drv->funcname.pattern) {
const struct userdiff_funcname *pe = &drv->funcname;
xecfg = xcalloc(1, sizeof(*xecfg));
xdiff_set_find_func(xecfg, pe->pattern, pe->cflags);
}
reg_error = regcomp(®exp, pattern, REG_NEWLINE);
if (reg_error) {
char errbuf[1024];
regerror(reg_error, ®exp, errbuf, 1024);
die("-L parameter '%s': %s", pattern, errbuf);
}
p = find_funcname_matching_regexp(xecfg, (char*) start, ®exp);
if (!p)
die("-L parameter '%s' starting at line %ld: no match",
pattern, anchor + 1);
*begin = 0;
while (p > nth_line_cb(cb_data, *begin))
(*begin)++;
if (*begin >= lines)
die("-L parameter '%s' matches at EOF", pattern);
*end = *begin+1;
while (*end < lines) {
const char *bol = nth_line_cb(cb_data, *end);
const char *eol = nth_line_cb(cb_data, *end+1);
if (match_funcname(xecfg, bol, eol))
break;
(*end)++;
}
regfree(®exp);
free(xecfg);
free(pattern);
/* compensate for 1-based numbering */
(*begin)++;
return term;
}
int parse_range_arg(const char *arg, nth_line_fn_t nth_line_cb,
void *cb_data, long lines, long anchor,
long *begin, long *end, const char *path)
{
*begin = *end = 0;
if (anchor < 1)
anchor = 1;
if (anchor > lines)
anchor = lines + 1;
if (*arg == ':' || (*arg == '^' && *(arg + 1) == ':')) {
arg = parse_range_funcname(arg, nth_line_cb, cb_data, lines, anchor, begin, end, path);
if (!arg || *arg)
return -1;
return 0;
}
arg = parse_loc(arg, nth_line_cb, cb_data, lines, -anchor, begin);
if (*arg == ',')
arg = parse_loc(arg + 1, nth_line_cb, cb_data, lines, *begin + 1, end);
if (*arg)
return -1;
if (*begin && *end && *end < *begin) {
long tmp;
tmp = *end; *end = *begin; *begin = tmp;
}
return 0;
}
const char *skip_range_arg(const char *arg)
{
if (*arg == ':' || (*arg == '^' && *(arg + 1) == ':'))
return parse_range_funcname(arg, NULL, NULL, 0, 0, NULL, NULL, NULL);
arg = parse_loc(arg, NULL, NULL, 0, -1, NULL);
if (*arg == ',')
arg = parse_loc(arg+1, NULL, NULL, 0, 0, NULL);
return arg;
}
|