ui-log: Fix filecount/linecount when path limit is in effect

When using ui-log with path limits, the listing of commits enables parent
rewriting in Git's internal log machinery. This did not work well together
with cgit_diff_commit() which is used to generate the filecount and
linecount numbers for each commit in the log view. cgit_diff_commit() would
operate without any path limits, and would therefore process the full diff
between the commits shown (which, because of parent rewriting, is not the
same as processing the diff for the commit itself). Additionally, the bottom
commit in the log view would (again, because of parent rewriting) have zero
parents, causing us to process the entire diff between the empty tree and
that commit. Since path limits were not in effect, this would (in large
projects) reports thousands of files and millions of lines changed in that
bottom commit.

This patch fixes the issue by applying the same path limit to
cgit_diff_commit() as is applied to the rest of the log view. The result is
that the filecount/linecount now only reflects the diff as it pertains to
the given path limit.

Signed-off-by: Johan Herland <johan@herland.net>
Signed-off-by: Lars Hjemli <hjemli@gmail.com>

3 files changed, 5 insertions, 4 deletions

diff --git a/cgit.h b/cgit.h
index a9896cf..f5f68ac 100644
--- a/cgit.h
+++ b/cgit.h
@@ -169,149 +169,150 @@ struct cgit_config {
         char *module_link;
         char *project_list;
         char *readme;
         char *robots;
         char *root_title;
         char *root_desc;
         char *root_readme;
         char *script_name;
         char *section;
         char *virtual_root;
         char *strict_export;
         int cache_size;
         int cache_dynamic_ttl;
         int cache_max_create_time;
         int cache_repo_ttl;
         int cache_root_ttl;
         int cache_scanrc_ttl;
         int cache_static_ttl;
         int embedded;
         int enable_filter_overrides;
         int enable_gitweb_owner;
         int enable_index_links;
         int enable_log_filecount;
         int enable_log_linecount;
         int enable_remote_branches;
         int enable_subject_links;
         int enable_tree_linenumbers;
         int local_time;
         int max_atom_items;
         int max_repo_count;
         int max_commit_count;
         int max_lock_attempts;
         int max_msg_len;
         int max_repodesc_len;
         int max_blob_size;
         int max_stats;
         int nocache;
         int noplainemail;
         int noheader;
         int renamelimit;
         int remove_suffix;
         int section_from_path;
         int snapshots;
         int summary_branches;
         int summary_log;
         int summary_tags;
         int ssdiff;
         struct string_list mimetypes;
         struct cgit_filter *about_filter;
         struct cgit_filter *commit_filter;
         struct cgit_filter *source_filter;
 };
 
 struct cgit_page {
         time_t modified;
         time_t expires;
         size_t size;
         char *mimetype;
         char *charset;
         char *filename;
         char *etag;
         char *title;
         int status;
         char *statusmsg;
 };
 
 struct cgit_environment {
         char *cgit_config;
         char *http_host;
         char *https;
         char *no_http;
         char *path_info;
         char *query_string;
         char *request_method;
         char *script_name;
         char *server_name;
         char *server_port;
 };
 
 struct cgit_context {
         struct cgit_environment env;
         struct cgit_query qry;
         struct cgit_config cfg;
         struct cgit_repo *repo;
         struct cgit_page page;
 };
 
 struct cgit_snapshot_format {
         const char *suffix;
         const char *mimetype;
         write_archive_fn_t write_func;
         int bit;
 };
 
 extern const char *cgit_version;
 
 extern struct cgit_repolist cgit_repolist;
 extern struct cgit_context ctx;
 extern const struct cgit_snapshot_format cgit_snapshot_formats[];
 
 extern struct cgit_repo *cgit_add_repo(const char *url);
 extern struct cgit_repo *cgit_get_repoinfo(const char *url);
 extern void cgit_repo_config_cb(const char *name, const char *value);
 
 extern int chk_zero(int result, char *msg);
 extern int chk_positive(int result, char *msg);
 extern int chk_non_negative(int result, char *msg);
 
 extern char *trim_end(const char *str, char c);
 extern char *strlpart(char *txt, int maxlen);
 extern char *strrpart(char *txt, int maxlen);
 
 extern void cgit_add_ref(struct reflist *list, struct refinfo *ref);
 extern int cgit_refs_cb(const char *refname, const unsigned char *sha1,
                         int flags, void *cb_data);
 
 extern void *cgit_free_commitinfo(struct commitinfo *info);
 
 extern int cgit_diff_files(const unsigned char *old_sha1,
                            const unsigned char *new_sha1,
                            unsigned long *old_size, unsigned long *new_size,
                            int *binary, int context, int ignorews,
                            linediff_fn fn);
 
 extern void cgit_diff_tree(const unsigned char *old_sha1,
                            const unsigned char *new_sha1,
                            filepair_fn fn, const char *prefix, int ignorews);
 
-extern void cgit_diff_commit(struct commit *commit, filepair_fn fn);
+extern void cgit_diff_commit(struct commit *commit, filepair_fn fn,
+                             const char *prefix);
 
 __attribute__((format (printf,1,2)))
 extern char *fmt(const char *format,...);
 
 extern struct commitinfo *cgit_parse_commit(struct commit *commit);
 extern struct taginfo *cgit_parse_tag(struct tag *tag);
 extern void cgit_parse_url(const char *url);
 
 extern const char *cgit_repobasename(const char *reponame);
 
 extern int cgit_parse_snapshots_mask(const char *str);
 
 extern int cgit_open_filter(struct cgit_filter *filter);
 extern int cgit_close_filter(struct cgit_filter *filter);
 
 extern int readfile(const char *path, char **buf, size_t *size);
 
 extern char *expand_macros(const char *txt);
 
 #endif /* CGIT_H */
diff --git a/shared.c b/shared.c
index 72ac140..765cd27 100644
--- a/shared.c
+++ b/shared.c
@@ -213,263 +213,263 @@ static int load_mmfile(mmfile_t *file, const unsigned char *sha1)
                 file->ptr = read_sha1_file(sha1, &type, 
                                            (unsigned long *)&file->size);
         }
         return 1;
 }
 
 /*
  * Receive diff-buffers from xdiff and concatenate them as
  * needed across multiple callbacks.
  *
  * This is basically a copy of xdiff-interface.c/xdiff_outf(),
  * ripped from git and modified to use globals instead of
  * a special callback-struct.
  */
 char *diffbuf = NULL;
 int buflen = 0;
 
 int filediff_cb(void *priv, mmbuffer_t *mb, int nbuf)
 {
         int i;
 
         for (i = 0; i < nbuf; i++) {
                 if (mb[i].ptr[mb[i].size-1] != '\n') {
                         /* Incomplete line */
                         diffbuf = xrealloc(diffbuf, buflen + mb[i].size);
                         memcpy(diffbuf + buflen, mb[i].ptr, mb[i].size);
                         buflen += mb[i].size;
                         continue;
                 }
 
                 /* we have a complete line */
                 if (!diffbuf) {
                         ((linediff_fn)priv)(mb[i].ptr, mb[i].size);
                         continue;
                 }
                 diffbuf = xrealloc(diffbuf, buflen + mb[i].size);
                 memcpy(diffbuf + buflen, mb[i].ptr, mb[i].size);
                 ((linediff_fn)priv)(diffbuf, buflen + mb[i].size);
                 free(diffbuf);
                 diffbuf = NULL;
                 buflen = 0;
         }
         if (diffbuf) {
                 ((linediff_fn)priv)(diffbuf, buflen);
                 free(diffbuf);
                 diffbuf = NULL;
                 buflen = 0;
         }
         return 0;
 }
 
 int cgit_diff_files(const unsigned char *old_sha1,
                     const unsigned char *new_sha1, unsigned long *old_size,
                     unsigned long *new_size, int *binary, int context,
                     int ignorews, linediff_fn fn)
 {
         mmfile_t file1, file2;
         xpparam_t diff_params;
         xdemitconf_t emit_params;
         xdemitcb_t emit_cb;
 
         if (!load_mmfile(&file1, old_sha1) || !load_mmfile(&file2, new_sha1))
                 return 1;
 
         *old_size = file1.size;
         *new_size = file2.size;
 
         if ((file1.ptr && buffer_is_binary(file1.ptr, file1.size)) ||
             (file2.ptr && buffer_is_binary(file2.ptr, file2.size))) {
                 *binary = 1;
                 if (file1.size)
                         free(file1.ptr);
                 if (file2.size)
                         free(file2.ptr);
                 return 0;
         }
 
         memset(&diff_params, 0, sizeof(diff_params));
         memset(&emit_params, 0, sizeof(emit_params));
         memset(&emit_cb, 0, sizeof(emit_cb));
         diff_params.flags = XDF_NEED_MINIMAL;
         if (ignorews)
                 diff_params.flags |= XDF_IGNORE_WHITESPACE;
         emit_params.ctxlen = context > 0 ? context : 3;
         emit_params.flags = XDL_EMIT_FUNCNAMES;
         emit_cb.outf = filediff_cb;
         emit_cb.priv = fn;
         xdl_diff(&file1, &file2, &diff_params, &emit_params, &emit_cb);
         if (file1.size)
                 free(file1.ptr);
         if (file2.size)
                 free(file2.ptr);
         return 0;
 }
 
 void cgit_diff_tree(const unsigned char *old_sha1,
                     const unsigned char *new_sha1,
                     filepair_fn fn, const char *prefix, int ignorews)
 {
         struct diff_options opt;
         int ret;
         int prefixlen;
 
         diff_setup(&opt);
         opt.output_format = DIFF_FORMAT_CALLBACK;
         opt.detect_rename = 1;
         opt.rename_limit = ctx.cfg.renamelimit;
         DIFF_OPT_SET(&opt, RECURSIVE);
         if (ignorews)
                 DIFF_XDL_SET(&opt, IGNORE_WHITESPACE);
         opt.format_callback = cgit_diff_tree_cb;
         opt.format_callback_data = fn;
         if (prefix) {
                 opt.nr_paths = 1;
                 opt.paths = &prefix;
                 prefixlen = strlen(prefix);
                 opt.pathlens = &prefixlen;
         }
         diff_setup_done(&opt);
 
         if (old_sha1 && !is_null_sha1(old_sha1))
                 ret = diff_tree_sha1(old_sha1, new_sha1, "", &opt);
         else
                 ret = diff_root_tree_sha1(new_sha1, "", &opt);
         diffcore_std(&opt);
         diff_flush(&opt);
 }
 
-void cgit_diff_commit(struct commit *commit, filepair_fn fn)
+void cgit_diff_commit(struct commit *commit, filepair_fn fn, const char *prefix)
 {
         unsigned char *old_sha1 = NULL;
 
         if (commit->parents)
                 old_sha1 = commit->parents->item->object.sha1;
-        cgit_diff_tree(old_sha1, commit->object.sha1, fn, NULL,
+        cgit_diff_tree(old_sha1, commit->object.sha1, fn, prefix,
                        ctx.qry.ignorews);
 }
 
 int cgit_parse_snapshots_mask(const char *str)
 {
         const struct cgit_snapshot_format *f;
         static const char *delim = " \t,:/|;";
         int tl, sl, rv = 0;
 
         /* favor legacy setting */
         if(atoi(str))
                 return 1;
         for(;;) {
                 str += strspn(str,delim);
                 tl = strcspn(str,delim);
                 if (!tl)
                         break;
                 for (f = cgit_snapshot_formats; f->suffix; f++) {
                         sl = strlen(f->suffix);
                         if((tl == sl && !strncmp(f->suffix, str, tl)) ||
                            (tl == sl-1 && !strncmp(f->suffix+1, str, tl-1))) {
                                 rv |= f->bit;
                                 break;
                         }
                 }
                 str += tl;
         }
         return rv;
 }
 
 int cgit_open_filter(struct cgit_filter *filter)
 {
 
         filter->old_stdout = chk_positive(dup(STDOUT_FILENO),
                 "Unable to duplicate STDOUT");
         chk_zero(pipe(filter->pipe_fh), "Unable to create pipe to subprocess");
         filter->pid = chk_non_negative(fork(), "Unable to create subprocess");
         if (filter->pid == 0) {
                 close(filter->pipe_fh[1]);
                 chk_non_negative(dup2(filter->pipe_fh[0], STDIN_FILENO),
                         "Unable to use pipe as STDIN");
                 execvp(filter->cmd, filter->argv);
                 die("Unable to exec subprocess %s: %s (%d)", filter->cmd,
                         strerror(errno), errno);
         }
         close(filter->pipe_fh[0]);
         chk_non_negative(dup2(filter->pipe_fh[1], STDOUT_FILENO),
                 "Unable to use pipe as STDOUT");
         close(filter->pipe_fh[1]);
         return 0;
 }
 
 int cgit_close_filter(struct cgit_filter *filter)
 {
         chk_non_negative(dup2(filter->old_stdout, STDOUT_FILENO),
                 "Unable to restore STDOUT");
         close(filter->old_stdout);
         if (filter->pid < 0)
                 return 0;
         waitpid(filter->pid, &filter->exitstatus, 0);
         if (WIFEXITED(filter->exitstatus) && !WEXITSTATUS(filter->exitstatus))
                 return 0;
         die("Subprocess %s exited abnormally", filter->cmd);
 }
 
 /* Read the content of the specified file into a newly allocated buffer,
  * zeroterminate the buffer and return 0 on success, errno otherwise.
  */
 int readfile(const char *path, char **buf, size_t *size)
 {
         int fd, e;
         struct stat st;
 
         fd = open(path, O_RDONLY);
         if (fd == -1)
                 return errno;
         if (fstat(fd, &st)) {
                 e = errno;
                 close(fd);
                 return e;
         }
         if (!S_ISREG(st.st_mode)) {
                 close(fd);
                 return EISDIR;
         }
         *buf = xmalloc(st.st_size + 1);
         *size = read_in_full(fd, *buf, st.st_size);
         e = errno;
         (*buf)[*size] = '\0';
         close(fd);
         return (*size == st.st_size ? 0 : e);
 }
 
 int is_token_char(char c)
 {
         return isalnum(c) || c == '_';
 }
 
 /* Replace name with getenv(name), return pointer to zero-terminating char
  */
 char *expand_macro(char *name, int maxlength)
 {
         char *value;
         int len;
 
         len = 0;
         value = getenv(name);
         if (value) {
                 len = strlen(value);
                 if (len > maxlength)
                         len = maxlength;
                 strncpy(name, value, len);
         }
         return name + len;
 }
 
 #define EXPBUFSIZE (1024 * 8)
 
 /* Replace all tokens prefixed by '$' in the specified text with the
  * value of the named environment variable.
  * NB: the return value is a static buffer, i.e. it must be strdup'd
  * by the caller.
  */
 char *expand_macros(const char *txt)
 {
         static char result[EXPBUFSIZE];
         char *p, *start;
         int len;
diff --git a/ui-log.c b/ui-log.c
index 41b5225..bc0c02c 100644
--- a/ui-log.c
+++ b/ui-log.c
@@ -1,232 +1,232 @@
 /* ui-log.c: functions for log output
  *
  * Copyright (C) 2006 Lars Hjemli
  *
  * Licensed under GNU General Public License v2
  *   (see COPYING for full license text)
  */
 
 #include "cgit.h"
 #include "html.h"
 #include "ui-shared.h"
 
 int files, add_lines, rem_lines;
 
 void count_lines(char *line, int size)
 {
         if (size <= 0)
                 return;
 
         if (line[0] == '+')
                 add_lines++;
 
         else if (line[0] == '-')
                 rem_lines++;
 }
 
 void inspect_files(struct diff_filepair *pair)
 {
         unsigned long old_size = 0;
         unsigned long new_size = 0;
         int binary = 0;
 
         files++;
         if (ctx.repo->enable_log_linecount)
                 cgit_diff_files(pair->one->sha1, pair->two->sha1, &old_size,
                                 &new_size, &binary, 0, ctx.qry.ignorews,
                                 count_lines);
 }
 
 void show_commit_decorations(struct commit *commit)
 {
         struct name_decoration *deco;
         static char buf[1024];
 
         buf[sizeof(buf) - 1] = 0;
         deco = lookup_decoration(&name_decoration, &commit->object);
         while (deco) {
                 if (!prefixcmp(deco->name, "refs/heads/")) {
                         strncpy(buf, deco->name + 11, sizeof(buf) - 1);
                         cgit_log_link(buf, NULL, "branch-deco", buf, NULL,
                                       ctx.qry.vpath, 0, NULL, NULL,
                                       ctx.qry.showmsg);
                 }
                 else if (!prefixcmp(deco->name, "tag: refs/tags/")) {
                         strncpy(buf, deco->name + 15, sizeof(buf) - 1);
                         cgit_tag_link(buf, NULL, "tag-deco", ctx.qry.head, buf);
                 }
                 else if (!prefixcmp(deco->name, "refs/tags/")) {
                         strncpy(buf, deco->name + 10, sizeof(buf) - 1);
                         cgit_tag_link(buf, NULL, "tag-deco", ctx.qry.head, buf);
                 }
                 else if (!prefixcmp(deco->name, "refs/remotes/")) {
                         strncpy(buf, deco->name + 13, sizeof(buf) - 1);
                         cgit_log_link(buf, NULL, "remote-deco", NULL,
                                       sha1_to_hex(commit->object.sha1),
                                       ctx.qry.vpath, 0, NULL, NULL,
                                       ctx.qry.showmsg);
                 }
                 else {
                         strncpy(buf, deco->name, sizeof(buf) - 1);
                         cgit_commit_link(buf, NULL, "deco", ctx.qry.head,
                                          sha1_to_hex(commit->object.sha1),
                                          ctx.qry.vpath, 0);
                 }
                 deco = deco->next;
         }
 }
 
 void print_commit(struct commit *commit)
 {
         struct commitinfo *info;
         char *tmp;
         int cols = 2;
 
         info = cgit_parse_commit(commit);
         htmlf("<tr%s><td>",
                 ctx.qry.showmsg ? " class='logheader'" : "");
         tmp = fmt("id=%s", sha1_to_hex(commit->object.sha1));
         tmp = cgit_fileurl(ctx.repo->url, "commit", ctx.qry.vpath, tmp);
         html_link_open(tmp, NULL, NULL);
         cgit_print_age(commit->date, TM_WEEK * 2, FMT_SHORTDATE);
         html_link_close();
         htmlf("</td><td%s>",
                 ctx.qry.showmsg ? " class='logsubject'" : "");
         cgit_commit_link(info->subject, NULL, NULL, ctx.qry.head,
                          sha1_to_hex(commit->object.sha1), ctx.qry.vpath, 0);
         show_commit_decorations(commit);
         html("</td><td>");
         html_txt(info->author);
         if (ctx.repo->enable_log_filecount) {
                 files = 0;
                 add_lines = 0;
                 rem_lines = 0;
-                cgit_diff_commit(commit, inspect_files);
+                cgit_diff_commit(commit, inspect_files, ctx.qry.vpath);
                 html("</td><td>");
                 htmlf("%d", files);
                 if (ctx.repo->enable_log_linecount) {
                         html("</td><td>");
                         htmlf("-%d/+%d", rem_lines, add_lines);
                 }
         }
         html("</td></tr>\n");
         if (ctx.qry.showmsg) {
                 struct strbuf notes = STRBUF_INIT;
                 format_note(NULL, commit->object.sha1, &notes, PAGE_ENCODING, 0);
 
                 if (ctx.repo->enable_log_filecount) {
                         cols++;
                         if (ctx.repo->enable_log_linecount)
                                 cols++;
                 }
                 htmlf("<tr class='nohover'><td/><td colspan='%d' class='logmsg'>",
                         cols);
                 html_txt(info->msg);
                 html("</td></tr>\n");
                 if (notes.len != 0) {
                         html("<tr class='nohover'>");
                         html("<td class='lognotes-label'>Notes:</td>");
                         htmlf("<td colspan='%d' class='lognotes'>",
                                 cols);
                         html_txt(notes.buf);
                         html("</td></tr>\n");
                 }
                 strbuf_release(&notes);
         }
         cgit_free_commitinfo(info);
 }
 
 static const char *disambiguate_ref(const char *ref)
 {
         unsigned char sha1[20];
         const char *longref;
 
         longref = fmt("refs/heads/%s", ref);
         if (get_sha1(longref, sha1) == 0)
                 return longref;
 
         return ref;
 }
 
 void cgit_print_log(const char *tip, int ofs, int cnt, char *grep, char *pattern,
                     char *path, int pager)
 {
         struct rev_info rev;
         struct commit *commit;
         const char *argv[] = {NULL, NULL, NULL, NULL, NULL};
         int argc = 2;
         int i, columns = 3;
 
         if (!tip)
                 tip = ctx.qry.head;
 
         argv[1] = disambiguate_ref(tip);
 
         if (grep && pattern) {
                 if (!strcmp(grep, "grep") || !strcmp(grep, "author") ||
                     !strcmp(grep, "committer"))
                         argv[argc++] = fmt("--%s=%s", grep, pattern);
                 if (!strcmp(grep, "range"))
                         argv[1] = pattern;
         }
 
         if (path) {
                 argv[argc++] = "--";
                 argv[argc++] = path;
         }
         init_revisions(&rev, NULL);
         rev.abbrev = DEFAULT_ABBREV;
         rev.commit_format = CMIT_FMT_DEFAULT;
         rev.verbose_header = 1;
         rev.show_root_diff = 0;
         setup_revisions(argc, argv, &rev, NULL);
         load_ref_decorations(DECORATE_FULL_REFS);
         rev.show_decorations = 1;
         rev.grep_filter.regflags |= REG_ICASE;
         compile_grep_patterns(&rev.grep_filter);
         prepare_revision_walk(&rev);
 
         if (pager)
                 html("<table class='list nowrap'>");
 
         html("<tr class='nohover'><th class='left'>Age</th>"
               "<th class='left'>Commit message");
         if (pager) {
                 html(" (");
                 cgit_log_link(ctx.qry.showmsg ? "Collapse" : "Expand", NULL,
                               NULL, ctx.qry.head, ctx.qry.sha1,
                               ctx.qry.vpath, ctx.qry.ofs, ctx.qry.grep,
                               ctx.qry.search, ctx.qry.showmsg ? 0 : 1);
                 html(")");
         }
         html("</th><th class='left'>Author</th>");
         if (ctx.repo->enable_log_filecount) {
                 html("<th class='left'>Files</th>");
                 columns++;
                 if (ctx.repo->enable_log_linecount) {
                         html("<th class='left'>Lines</th>");
                         columns++;
                 }
         }
         html("</tr>\n");
 
         if (ofs<0)
                 ofs = 0;
 
         for (i = 0; i < ofs && (commit = get_revision(&rev)) != NULL; i++) {
                 free(commit->buffer);
                 commit->buffer = NULL;
                 free_commit_list(commit->parents);
                 commit->parents = NULL;
         }
 
         for (i = 0; i < cnt && (commit = get_revision(&rev)) != NULL; i++) {
                 print_commit(commit);
                 free(commit->buffer);
                 commit->buffer = NULL;
                 free_commit_list(commit->parents);
                 commit->parents = NULL;
         }
         if (pager) {
                 html("</table><div class='pager'>");
                 if (ofs > 0) {