#include "cache.h"
#include "commit.h"
-#include "interpolate.h"
#include "utf8.h"
#include "diff.h"
#include "revision.h"
-
-static struct cmt_fmt_map {
- const char *n;
- size_t cmp_len;
- enum cmit_fmt v;
-} cmt_fmts[] = {
- { "raw", 1, CMIT_FMT_RAW },
- { "medium", 1, CMIT_FMT_MEDIUM },
- { "short", 1, CMIT_FMT_SHORT },
- { "email", 1, CMIT_FMT_EMAIL },
- { "full", 5, CMIT_FMT_FULL },
- { "fuller", 5, CMIT_FMT_FULLER },
- { "oneline", 1, CMIT_FMT_ONELINE },
- { "format:", 7, CMIT_FMT_USERFORMAT},
-};
+#include "string-list.h"
+#include "mailmap.h"
static char *user_format;
-enum cmit_fmt get_commit_format(const char *arg)
+void get_commit_format(const char *arg, struct rev_info *rev)
{
int i;
+ static struct cmt_fmt_map {
+ const char *n;
+ size_t cmp_len;
+ enum cmit_fmt v;
+ } cmt_fmts[] = {
+ { "raw", 1, CMIT_FMT_RAW },
+ { "medium", 1, CMIT_FMT_MEDIUM },
+ { "short", 1, CMIT_FMT_SHORT },
+ { "email", 1, CMIT_FMT_EMAIL },
+ { "full", 5, CMIT_FMT_FULL },
+ { "fuller", 5, CMIT_FMT_FULLER },
+ { "oneline", 1, CMIT_FMT_ONELINE },
+ };
- if (!arg || !*arg)
- return CMIT_FMT_DEFAULT;
- if (*arg == '=')
- arg++;
- if (!prefixcmp(arg, "format:")) {
- if (user_format)
- free(user_format);
- user_format = xstrdup(arg + 7);
- return CMIT_FMT_USERFORMAT;
+ rev->use_terminator = 0;
+ if (!arg || !*arg) {
+ rev->commit_format = CMIT_FMT_DEFAULT;
+ return;
+ }
+ if (!prefixcmp(arg, "format:") || !prefixcmp(arg, "tformat:")) {
+ const char *cp = strchr(arg, ':') + 1;
+ free(user_format);
+ user_format = xstrdup(cp);
+ if (arg[0] == 't')
+ rev->use_terminator = 1;
+ rev->commit_format = CMIT_FMT_USERFORMAT;
+ return;
}
for (i = 0; i < ARRAY_SIZE(cmt_fmts); i++) {
if (!strncmp(arg, cmt_fmts[i].n, cmt_fmts[i].cmp_len) &&
- !strncmp(arg, cmt_fmts[i].n, strlen(arg)))
- return cmt_fmts[i].v;
+ !strncmp(arg, cmt_fmts[i].n, strlen(arg))) {
+ if (cmt_fmts[i].v == CMIT_FMT_ONELINE)
+ rev->use_terminator = 1;
+ rev->commit_format = cmt_fmts[i].v;
+ return;
+ }
}
die("invalid --pretty format: %s", arg);
strbuf_addstr(sb, "?=");
}
-static void add_user_info(const char *what, enum cmit_fmt fmt, struct strbuf *sb,
- const char *line, enum date_mode dmode,
- const char *encoding)
+void pp_user_info(const char *what, enum cmit_fmt fmt, struct strbuf *sb,
+ const char *line, enum date_mode dmode,
+ const char *encoding)
{
char *date;
int namelen;
return out;
}
-static void fill_person(struct interp *table, const char *msg, int len)
+static int mailmap_name(struct strbuf *sb, const char *email)
+{
+ static struct string_list *mail_map;
+ char buffer[1024];
+
+ if (!mail_map) {
+ mail_map = xcalloc(1, sizeof(*mail_map));
+ read_mailmap(mail_map, ".mailmap", NULL);
+ }
+
+ if (!mail_map->nr)
+ return -1;
+
+ if (!map_email(mail_map, email, buffer, sizeof(buffer)))
+ return -1;
+ strbuf_addstr(sb, buffer);
+ return 0;
+}
+
+static size_t format_person_part(struct strbuf *sb, char part,
+ const char *msg, int len, enum date_mode dmode)
{
+ /* currently all placeholders have same length */
+ const int placeholder_len = 2;
int start, end, tz = 0;
- unsigned long date;
+ unsigned long date = 0;
char *ep;
- /* parse name */
+ /* advance 'end' to point to email start delimiter */
for (end = 0; end < len && msg[end] != '<'; end++)
; /* do nothing */
- start = end + 1;
- while (end > 0 && isspace(msg[end - 1]))
- end--;
- table[0].value = xmemdupz(msg, end);
- if (start >= len)
- return;
+ /*
+ * When end points at the '<' that we found, it should have
+ * matching '>' later, which means 'end' must be strictly
+ * below len - 1.
+ */
+ if (end >= len - 2)
+ goto skip;
+
+ if (part == 'n' || part == 'N') { /* name */
+ while (end > 0 && isspace(msg[end - 1]))
+ end--;
+ if (part != 'N' || !msg[end] || !msg[end + 1] ||
+ mailmap_name(sb, msg + end + 2) < 0)
+ strbuf_add(sb, msg, end);
+ return placeholder_len;
+ }
+ start = ++end; /* save email start position */
- /* parse email */
- for (end = start + 1; end < len && msg[end] != '>'; end++)
+ /* advance 'end' to point to email end delimiter */
+ for ( ; end < len && msg[end] != '>'; end++)
; /* do nothing */
if (end >= len)
- return;
+ goto skip;
- table[1].value = xmemdupz(msg + start, end - start);
+ if (part == 'e') { /* email */
+ strbuf_add(sb, msg + start, end - start);
+ return placeholder_len;
+ }
- /* parse date */
+ /* advance 'start' to point to date start delimiter */
for (start = end + 1; start < len && isspace(msg[start]); start++)
; /* do nothing */
if (start >= len)
- return;
+ goto skip;
date = strtoul(msg + start, &ep, 10);
if (msg + start == ep)
- return;
+ goto skip;
- table[5].value = xmemdupz(msg + start, ep - (msg + start));
+ if (part == 't') { /* date, UNIX timestamp */
+ strbuf_add(sb, msg + start, ep - (msg + start));
+ return placeholder_len;
+ }
/* parse tz */
for (start = ep - msg + 1; start < len && isspace(msg[start]); start++)
tz = -tz;
}
- interp_set_entry(table, 2, show_date(date, tz, DATE_NORMAL));
- interp_set_entry(table, 3, show_date(date, tz, DATE_RFC2822));
- interp_set_entry(table, 4, show_date(date, tz, DATE_RELATIVE));
- interp_set_entry(table, 6, show_date(date, tz, DATE_ISO8601));
+ switch (part) {
+ case 'd': /* date */
+ strbuf_addstr(sb, show_date(date, tz, dmode));
+ return placeholder_len;
+ case 'D': /* date, RFC2822 style */
+ strbuf_addstr(sb, show_date(date, tz, DATE_RFC2822));
+ return placeholder_len;
+ case 'r': /* date, relative */
+ strbuf_addstr(sb, show_date(date, tz, DATE_RELATIVE));
+ return placeholder_len;
+ case 'i': /* date, ISO 8601 */
+ strbuf_addstr(sb, show_date(date, tz, DATE_ISO8601));
+ return placeholder_len;
+ }
+
+skip:
+ /*
+ * bogus commit, 'sb' cannot be updated, but we still need to
+ * compute a valid return value.
+ */
+ if (part == 'n' || part == 'e' || part == 't' || part == 'd'
+ || part == 'D' || part == 'r' || part == 'i')
+ return placeholder_len;
+
+ return 0; /* unknown placeholder */
}
-void format_commit_message(const struct commit *commit,
- const void *format, struct strbuf *sb)
-{
- struct interp table[] = {
- { "%H" }, /* commit hash */
- { "%h" }, /* abbreviated commit hash */
- { "%T" }, /* tree hash */
- { "%t" }, /* abbreviated tree hash */
- { "%P" }, /* parent hashes */
- { "%p" }, /* abbreviated parent hashes */
- { "%an" }, /* author name */
- { "%ae" }, /* author email */
- { "%ad" }, /* author date */
- { "%aD" }, /* author date, RFC2822 style */
- { "%ar" }, /* author date, relative */
- { "%at" }, /* author date, UNIX timestamp */
- { "%ai" }, /* author date, ISO 8601 */
- { "%cn" }, /* committer name */
- { "%ce" }, /* committer email */
- { "%cd" }, /* committer date */
- { "%cD" }, /* committer date, RFC2822 style */
- { "%cr" }, /* committer date, relative */
- { "%ct" }, /* committer date, UNIX timestamp */
- { "%ci" }, /* committer date, ISO 8601 */
- { "%e" }, /* encoding */
- { "%s" }, /* subject */
- { "%b" }, /* body */
- { "%Cred" }, /* red */
- { "%Cgreen" }, /* green */
- { "%Cblue" }, /* blue */
- { "%Creset" }, /* reset color */
- { "%n" }, /* newline */
- { "%m" }, /* left/right/bottom */
- };
- enum interp_index {
- IHASH = 0, IHASH_ABBREV,
- ITREE, ITREE_ABBREV,
- IPARENTS, IPARENTS_ABBREV,
- IAUTHOR_NAME, IAUTHOR_EMAIL,
- IAUTHOR_DATE, IAUTHOR_DATE_RFC2822, IAUTHOR_DATE_RELATIVE,
- IAUTHOR_TIMESTAMP, IAUTHOR_ISO8601,
- ICOMMITTER_NAME, ICOMMITTER_EMAIL,
- ICOMMITTER_DATE, ICOMMITTER_DATE_RFC2822,
- ICOMMITTER_DATE_RELATIVE, ICOMMITTER_TIMESTAMP,
- ICOMMITTER_ISO8601,
- IENCODING,
- ISUBJECT,
- IBODY,
- IRED, IGREEN, IBLUE, IRESET_COLOR,
- INEWLINE,
- ILEFT_RIGHT,
- };
- struct commit_list *p;
- char parents[1024];
- unsigned long len;
- int i;
- enum { HEADER, SUBJECT, BODY } state;
- const char *msg = commit->buffer;
+struct chunk {
+ size_t off;
+ size_t len;
+};
+
+struct format_commit_context {
+ const struct commit *commit;
+ enum date_mode dmode;
+
+ /* These offsets are relative to the start of the commit message. */
+ int commit_header_parsed;
+ struct chunk subject;
+ struct chunk author;
+ struct chunk committer;
+ struct chunk encoding;
+ size_t body_off;
+
+ /* The following ones are relative to the result struct strbuf. */
+ struct chunk abbrev_commit_hash;
+ struct chunk abbrev_tree_hash;
+ struct chunk abbrev_parent_hashes;
+};
- if (ILEFT_RIGHT + 1 != ARRAY_SIZE(table))
- die("invalid interp table!");
+static int add_again(struct strbuf *sb, struct chunk *chunk)
+{
+ if (chunk->len) {
+ strbuf_adddup(sb, chunk->off, chunk->len);
+ return 1;
+ }
- /* these are independent of the commit */
- interp_set_entry(table, IRED, "\033[31m");
- interp_set_entry(table, IGREEN, "\033[32m");
- interp_set_entry(table, IBLUE, "\033[34m");
- interp_set_entry(table, IRESET_COLOR, "\033[m");
- interp_set_entry(table, INEWLINE, "\n");
+ /*
+ * We haven't seen this chunk before. Our caller is surely
+ * going to add it the hard way now. Remember the most likely
+ * start of the to-be-added chunk: the current end of the
+ * struct strbuf.
+ */
+ chunk->off = sb->len;
+ return 0;
+}
- /* these depend on the commit */
- if (!commit->object.parsed)
- parse_object(commit->object.sha1);
- interp_set_entry(table, IHASH, sha1_to_hex(commit->object.sha1));
- interp_set_entry(table, IHASH_ABBREV,
- find_unique_abbrev(commit->object.sha1,
- DEFAULT_ABBREV));
- interp_set_entry(table, ITREE, sha1_to_hex(commit->tree->object.sha1));
- interp_set_entry(table, ITREE_ABBREV,
- find_unique_abbrev(commit->tree->object.sha1,
- DEFAULT_ABBREV));
- interp_set_entry(table, ILEFT_RIGHT,
- (commit->object.flags & BOUNDARY)
- ? "-"
- : (commit->object.flags & SYMMETRIC_LEFT)
- ? "<"
- : ">");
-
- parents[1] = 0;
- for (i = 0, p = commit->parents;
- p && i < sizeof(parents) - 1;
- p = p->next)
- i += snprintf(parents + i, sizeof(parents) - i - 1, " %s",
- sha1_to_hex(p->item->object.sha1));
- interp_set_entry(table, IPARENTS, parents + 1);
-
- parents[1] = 0;
- for (i = 0, p = commit->parents;
- p && i < sizeof(parents) - 1;
- p = p->next)
- i += snprintf(parents + i, sizeof(parents) - i - 1, " %s",
- find_unique_abbrev(p->item->object.sha1,
- DEFAULT_ABBREV));
- interp_set_entry(table, IPARENTS_ABBREV, parents + 1);
+static void parse_commit_header(struct format_commit_context *context)
+{
+ const char *msg = context->commit->buffer;
+ int i;
+ enum { HEADER, SUBJECT, BODY } state;
for (i = 0, state = HEADER; msg[i] && state < BODY; i++) {
int eol;
; /* do nothing */
if (state == SUBJECT) {
- table[ISUBJECT].value = xmemdupz(msg + i, eol - i);
+ context->subject.off = i;
+ context->subject.len = eol - i;
i = eol;
}
if (i == eol) {
state++;
/* strip empty lines */
- while (msg[eol + 1] == '\n')
+ while (msg[eol] == '\n' && msg[eol + 1] == '\n')
eol++;
- } else if (!prefixcmp(msg + i, "author "))
- fill_person(table + IAUTHOR_NAME,
- msg + i + 7, eol - i - 7);
- else if (!prefixcmp(msg + i, "committer "))
- fill_person(table + ICOMMITTER_NAME,
- msg + i + 10, eol - i - 10);
- else if (!prefixcmp(msg + i, "encoding "))
- table[IENCODING].value =
- xmemdupz(msg + i + 9, eol - i - 9);
+ } else if (!prefixcmp(msg + i, "author ")) {
+ context->author.off = i + 7;
+ context->author.len = eol - i - 7;
+ } else if (!prefixcmp(msg + i, "committer ")) {
+ context->committer.off = i + 10;
+ context->committer.len = eol - i - 10;
+ } else if (!prefixcmp(msg + i, "encoding ")) {
+ context->encoding.off = i + 9;
+ context->encoding.len = eol - i - 9;
+ }
i = eol;
+ if (!msg[i])
+ break;
+ }
+ context->body_off = i;
+ context->commit_header_parsed = 1;
+}
+
+static size_t format_commit_item(struct strbuf *sb, const char *placeholder,
+ void *context)
+{
+ struct format_commit_context *c = context;
+ const struct commit *commit = c->commit;
+ const char *msg = commit->buffer;
+ struct commit_list *p;
+ int h1, h2;
+
+ /* these are independent of the commit */
+ switch (placeholder[0]) {
+ case 'C':
+ if (!prefixcmp(placeholder + 1, "red")) {
+ strbuf_addstr(sb, "\033[31m");
+ return 4;
+ } else if (!prefixcmp(placeholder + 1, "green")) {
+ strbuf_addstr(sb, "\033[32m");
+ return 6;
+ } else if (!prefixcmp(placeholder + 1, "blue")) {
+ strbuf_addstr(sb, "\033[34m");
+ return 5;
+ } else if (!prefixcmp(placeholder + 1, "reset")) {
+ strbuf_addstr(sb, "\033[m");
+ return 6;
+ } else
+ return 0;
+ case 'n': /* newline */
+ strbuf_addch(sb, '\n');
+ return 1;
+ case 'x':
+ /* %x00 == NUL, %x0a == LF, etc. */
+ if (0 <= (h1 = hexval_table[0xff & placeholder[1]]) &&
+ h1 <= 16 &&
+ 0 <= (h2 = hexval_table[0xff & placeholder[2]]) &&
+ h2 <= 16) {
+ strbuf_addch(sb, (h1<<4)|h2);
+ return 3;
+ } else
+ return 0;
+ }
+
+ /* these depend on the commit */
+ if (!commit->object.parsed)
+ parse_object(commit->object.sha1);
+
+ switch (placeholder[0]) {
+ case 'H': /* commit hash */
+ strbuf_addstr(sb, sha1_to_hex(commit->object.sha1));
+ return 1;
+ case 'h': /* abbreviated commit hash */
+ if (add_again(sb, &c->abbrev_commit_hash))
+ return 1;
+ strbuf_addstr(sb, find_unique_abbrev(commit->object.sha1,
+ DEFAULT_ABBREV));
+ c->abbrev_commit_hash.len = sb->len - c->abbrev_commit_hash.off;
+ return 1;
+ case 'T': /* tree hash */
+ strbuf_addstr(sb, sha1_to_hex(commit->tree->object.sha1));
+ return 1;
+ case 't': /* abbreviated tree hash */
+ if (add_again(sb, &c->abbrev_tree_hash))
+ return 1;
+ strbuf_addstr(sb, find_unique_abbrev(commit->tree->object.sha1,
+ DEFAULT_ABBREV));
+ c->abbrev_tree_hash.len = sb->len - c->abbrev_tree_hash.off;
+ return 1;
+ case 'P': /* parent hashes */
+ for (p = commit->parents; p; p = p->next) {
+ if (p != commit->parents)
+ strbuf_addch(sb, ' ');
+ strbuf_addstr(sb, sha1_to_hex(p->item->object.sha1));
+ }
+ return 1;
+ case 'p': /* abbreviated parent hashes */
+ if (add_again(sb, &c->abbrev_parent_hashes))
+ return 1;
+ for (p = commit->parents; p; p = p->next) {
+ if (p != commit->parents)
+ strbuf_addch(sb, ' ');
+ strbuf_addstr(sb, find_unique_abbrev(
+ p->item->object.sha1, DEFAULT_ABBREV));
+ }
+ c->abbrev_parent_hashes.len = sb->len -
+ c->abbrev_parent_hashes.off;
+ return 1;
+ case 'm': /* left/right/bottom */
+ strbuf_addch(sb, (commit->object.flags & BOUNDARY)
+ ? '-'
+ : (commit->object.flags & SYMMETRIC_LEFT)
+ ? '<'
+ : '>');
+ return 1;
}
- if (msg[i])
- table[IBODY].value = xstrdup(msg + i);
- len = interpolate(sb->buf + sb->len, strbuf_avail(sb),
- format, table, ARRAY_SIZE(table));
- if (len > strbuf_avail(sb)) {
- strbuf_grow(sb, len);
- interpolate(sb->buf + sb->len, strbuf_avail(sb) + 1,
- format, table, ARRAY_SIZE(table));
+ /* For the rest we have to parse the commit header. */
+ if (!c->commit_header_parsed)
+ parse_commit_header(c);
+
+ switch (placeholder[0]) {
+ case 's': /* subject */
+ strbuf_add(sb, msg + c->subject.off, c->subject.len);
+ return 1;
+ case 'a': /* author ... */
+ return format_person_part(sb, placeholder[1],
+ msg + c->author.off, c->author.len,
+ c->dmode);
+ case 'c': /* committer ... */
+ return format_person_part(sb, placeholder[1],
+ msg + c->committer.off, c->committer.len,
+ c->dmode);
+ case 'e': /* encoding */
+ strbuf_add(sb, msg + c->encoding.off, c->encoding.len);
+ return 1;
+ case 'b': /* body */
+ strbuf_addstr(sb, msg + c->body_off);
+ return 1;
}
- strbuf_setlen(sb, sb->len + len);
- interp_clear_table(table, ARRAY_SIZE(table));
+ return 0; /* unknown placeholder */
+}
+
+void format_commit_message(const struct commit *commit,
+ const void *format, struct strbuf *sb,
+ enum date_mode dmode)
+{
+ struct format_commit_context context;
+
+ memset(&context, 0, sizeof(context));
+ context.commit = commit;
+ context.dmode = dmode;
+ strbuf_expand(sb, format, format_commit_item, &context);
}
static void pp_header(enum cmit_fmt fmt,
*/
if (!memcmp(line, "author ", 7)) {
strbuf_grow(sb, linelen + 80);
- add_user_info("Author", fmt, sb, line + 7, dmode, encoding);
+ pp_user_info("Author", fmt, sb, line + 7, dmode, encoding);
}
if (!memcmp(line, "committer ", 10) &&
(fmt == CMIT_FMT_FULL || fmt == CMIT_FMT_FULLER)) {
strbuf_grow(sb, linelen + 80);
- add_user_info("Commit", fmt, sb, line + 10, dmode, encoding);
+ pp_user_info("Commit", fmt, sb, line + 10, dmode, encoding);
}
}
}
-static void pp_title_line(enum cmit_fmt fmt,
- const char **msg_p,
- struct strbuf *sb,
- const char *subject,
- const char *after_subject,
- const char *encoding,
- int plain_non_ascii)
+void pp_title_line(enum cmit_fmt fmt,
+ const char **msg_p,
+ struct strbuf *sb,
+ const char *subject,
+ const char *after_subject,
+ const char *encoding,
+ int need_8bit_cte)
{
struct strbuf title;
}
strbuf_addch(sb, '\n');
- if (plain_non_ascii) {
+ if (need_8bit_cte > 0) {
const char *header_fmt =
"MIME-Version: 1.0\n"
"Content-Type: text/plain; charset=%s\n"
strbuf_release(&title);
}
-static void pp_remainder(enum cmit_fmt fmt,
- const char **msg_p,
- struct strbuf *sb,
- int indent)
+void pp_remainder(enum cmit_fmt fmt,
+ const char **msg_p,
+ struct strbuf *sb,
+ int indent)
{
int first = 1;
for (;;) {
}
void pretty_print_commit(enum cmit_fmt fmt, const struct commit *commit,
- struct strbuf *sb, int abbrev,
- const char *subject, const char *after_subject,
- enum date_mode dmode, int plain_non_ascii)
+ struct strbuf *sb, int abbrev,
+ const char *subject, const char *after_subject,
+ enum date_mode dmode, int need_8bit_cte)
{
unsigned long beginning_of_body;
int indent = 4;
const char *encoding;
if (fmt == CMIT_FMT_USERFORMAT) {
- format_commit_message(commit, user_format, sb);
+ format_commit_message(commit, user_format, sb, dmode);
return;
}
if (fmt == CMIT_FMT_ONELINE || fmt == CMIT_FMT_EMAIL)
indent = 0;
- /* After-subject is used to pass in Content-Type: multipart
- * MIME header; in that case we do not have to do the
- * plaintext content type even if the commit message has
- * non 7-bit ASCII character. Otherwise, check if we need
- * to say this is not a 7-bit ASCII.
+ /*
+ * We need to check and emit Content-type: to mark it
+ * as 8-bit if we haven't done so.
*/
- if (fmt == CMIT_FMT_EMAIL && !after_subject) {
+ if (fmt == CMIT_FMT_EMAIL && need_8bit_cte == 0) {
int i, ch, in_body;
for (in_body = i = 0; (ch = msg[i]); i++) {
in_body = 1;
}
else if (non_ascii(ch)) {
- plain_non_ascii = 1;
+ need_8bit_cte = 1;
break;
}
}
/* These formats treat the title line specially. */
if (fmt == CMIT_FMT_ONELINE || fmt == CMIT_FMT_EMAIL)
pp_title_line(fmt, &msg, sb, subject,
- after_subject, encoding, plain_non_ascii);
+ after_subject, encoding, need_8bit_cte);
beginning_of_body = sb->len;
if (fmt != CMIT_FMT_ONELINE)