grep: handle pre context lines on demand

Factor out pre context line handling into the new function
show_pre_context() and change the algorithm to rewind by looking for
newline characters and roll forward again, instead of maintaining an
array of line beginnings and ends.

This is slower for hits, but the cost for non-matching lines becomes
zero.  Normally, there are far more non-matching lines, so the time
spent in total decreases.

Before this patch (current Linux kernel repo, best of five runs):

$ time git grep --no-ext-grep -B1 memset >/dev/null

real	0m2.134s
user	0m1.932s
sys	0m0.196s

$ time git grep --no-ext-grep -B1000 memset >/dev/null

real	0m12.059s
user	0m11.837s
sys	0m0.224s

The same with this patch:

$ time git grep --no-ext-grep -B1 memset >/dev/null

real	0m2.117s
user	0m1.892s
sys	0m0.228s

$ time git grep --no-ext-grep -B1000 memset >/dev/null

real	0m2.986s
user	0m2.696s
sys	0m0.288s

Signed-off-by: Rene Scharfe <rene.scharfe@lsrfire.ath.cx>
Signed-off-by: Junio C Hamano <gitster@pobox.com>

diff --git a/grep.c b/grep.c
index 4bca759b67e2d386ae87975780b0272209cc2942..9b9d2e39f8ae71e6e9a394f2b0566d7a137082e2 100644 (file)
--- a/grep.c
+++ b/grep.c
@@ -531,16 +531,42 @@ static void show_line(struct grep_opt *opt, char *bol, char *eol,
        printf("%.*s\n", rest, bol);
 }
 
        printf("%.*s\n", rest, bol);
 }
 

+static void show_pre_context(struct grep_opt *opt, const char *name, char *buf,
+                            char *bol, unsigned lno)
+{
+       unsigned cur = lno, from = 1;
+
+       if (opt->pre_context < lno)
+               from = lno - opt->pre_context;
+       if (from <= opt->last_shown)
+               from = opt->last_shown + 1;
+
+       /* Rewind. */
+       while (bol > buf && cur > from) {
+               bol--;
+               while (bol > buf && bol[-1] != '\n')
+                       bol--;
+               cur--;
+       }
+
+       /* Back forward. */
+       while (cur < lno) {
+               char *eol = bol;
+
+               while (*eol != '\n')
+                       eol++;
+               show_line(opt, bol, eol, name, cur, '-');
+               bol = eol + 1;
+               cur++;
+       }
+}
+

 static int grep_buffer_1(struct grep_opt *opt, const char *name,
                         char *buf, unsigned long size, int collect_hits)
 {
        char *bol = buf;
        unsigned long left = size;
        unsigned lno = 1;
 static int grep_buffer_1(struct grep_opt *opt, const char *name,
                         char *buf, unsigned long size, int collect_hits)
 {
        char *bol = buf;
        unsigned long left = size;
        unsigned lno = 1;

-       struct pre_context_line {
-               char *bol;
-               char *eol;
-       } *prev = NULL, *pcl;

        unsigned last_hit = 0;
        int binary_match_only = 0;
        unsigned count = 0;
        unsigned last_hit = 0;
        int binary_match_only = 0;
        unsigned count = 0;


@@ -561,9 +587,6 @@ static int grep_buffer_1(struct grep_opt *opt, const char *name,
                }
        }
 
                }
        }
 

-       if (opt->pre_context)
-               prev = xcalloc(opt->pre_context, sizeof(*prev));
-

        while (left) {
                char *eol, ch;
                int hit;
        while (left) {
                char *eol, ch;
                int hit;


@@ -610,21 +633,8 @@ static int grep_buffer_1(struct grep_opt *opt, const char *name,
                         * the context which is nonsense, but the user
                         * deserves to get that ;-).
                         */
                         * the context which is nonsense, but the user
                         * deserves to get that ;-).
                         */

-                       if (opt->pre_context) {
-                               unsigned from;
-                               if (opt->pre_context < lno)
-                                       from = lno - opt->pre_context;
-                               else
-                                       from = 1;
-                               if (from <= opt->last_shown)
-                                       from = opt->last_shown + 1;
-                               while (from < lno) {
-                                       pcl = &prev[lno-from-1];
-                                       show_line(opt, pcl->bol, pcl->eol,
-                                                 name, from, '-');
-                                       from++;
-                               }
-                       }
+                       if (opt->pre_context)
+                               show_pre_context(opt, name, buf, bol, lno);

                        if (!opt->count)
                                show_line(opt, bol, eol, name, lno, ':');
                        last_hit = lno;
                        if (!opt->count)
                                show_line(opt, bol, eol, name, lno, ':');
                        last_hit = lno;


@@ -636,12 +646,6 @@ static int grep_buffer_1(struct grep_opt *opt, const char *name,
                         */
                        show_line(opt, bol, eol, name, lno, '-');
                }
                         */
                        show_line(opt, bol, eol, name, lno, '-');
                }

-               if (opt->pre_context) {
-                       memmove(prev+1, prev,
-                               (opt->pre_context-1) * sizeof(*prev));
-                       prev->bol = bol;
-                       prev->eol = eol;
-               }

 
        next_line:
                bol = eol + 1;
 
        next_line:
                bol = eol + 1;


@@ -651,7 +655,6 @@ static int grep_buffer_1(struct grep_opt *opt, const char *name,
                lno++;
        }
 
                lno++;
        }
 

-       free(prev);

        if (collect_hits)
                return 0;
 
        if (collect_hits)
                return 0;