summaryrefslogtreecommitdiff
path: root/pretty.c
diff options
context:
space:
mode:
Diffstat (limited to 'pretty.c')
-rw-r--r--pretty.c393
1 files changed, 256 insertions, 137 deletions
diff --git a/pretty.c b/pretty.c
index 8b1ea9ffad..eae57ad9d7 100644
--- a/pretty.c
+++ b/pretty.c
@@ -231,7 +231,7 @@ static int is_rfc822_special(char ch)
}
}
-static int has_rfc822_specials(const char *s, int len)
+static int needs_rfc822_quoting(const char *s, int len)
{
int i;
for (i = 0; i < len; i++)
@@ -240,6 +240,17 @@ static int has_rfc822_specials(const char *s, int len)
return 0;
}
+static int last_line_length(struct strbuf *sb)
+{
+ int i;
+
+ /* How many bytes are already used on the last line? */
+ for (i = sb->len - 1; i >= 0; i--)
+ if (sb->buf[i] == '\n')
+ break;
+ return sb->len - (i + 1);
+}
+
static void add_rfc822_quoted(struct strbuf *out, const char *s, int len)
{
int i;
@@ -261,57 +272,110 @@ static void add_rfc822_quoted(struct strbuf *out, const char *s, int len)
strbuf_addch(out, '"');
}
-static int is_rfc2047_special(char ch)
+enum rfc2047_type {
+ RFC2047_SUBJECT,
+ RFC2047_ADDRESS,
+};
+
+static int is_rfc2047_special(char ch, enum rfc2047_type type)
{
- return (non_ascii(ch) || (ch == '=') || (ch == '?') || (ch == '_'));
+ /*
+ * rfc2047, section 4.2:
+ *
+ * 8-bit values which correspond to printable ASCII characters other
+ * than "=", "?", and "_" (underscore), MAY be represented as those
+ * characters. (But see section 5 for restrictions.) In
+ * particular, SPACE and TAB MUST NOT be represented as themselves
+ * within encoded words.
+ */
+
+ /*
+ * rule out non-ASCII characters and non-printable characters (the
+ * non-ASCII check should be redundant as isprint() is not localized
+ * and only knows about ASCII, but be defensive about that)
+ */
+ if (non_ascii(ch) || !isprint(ch))
+ return 1;
+
+ /*
+ * rule out special printable characters (' ' should be the only
+ * whitespace character considered printable, but be defensive and use
+ * isspace())
+ */
+ if (isspace(ch) || ch == '=' || ch == '?' || ch == '_')
+ return 1;
+
+ /*
+ * rfc2047, section 5.3:
+ *
+ * As a replacement for a 'word' entity within a 'phrase', for example,
+ * one that precedes an address in a From, To, or Cc header. The ABNF
+ * definition for 'phrase' from RFC 822 thus becomes:
+ *
+ * phrase = 1*( encoded-word / word )
+ *
+ * In this case the set of characters that may be used in a "Q"-encoded
+ * 'encoded-word' is restricted to: <upper and lower case ASCII
+ * letters, decimal digits, "!", "*", "+", "-", "/", "=", and "_"
+ * (underscore, ASCII 95.)>. An 'encoded-word' that appears within a
+ * 'phrase' MUST be separated from any adjacent 'word', 'text' or
+ * 'special' by 'linear-white-space'.
+ */
+
+ if (type != RFC2047_ADDRESS)
+ return 0;
+
+ /* '=' and '_' are special cases and have been checked above */
+ return !(isalnum(ch) || ch == '!' || ch == '*' || ch == '+' || ch == '-' || ch == '/');
}
-static void add_rfc2047(struct strbuf *sb, const char *line, int len,
- const char *encoding)
+static int needs_rfc2047_encoding(const char *line, int len,
+ enum rfc2047_type type)
{
- static const int max_length = 78; /* per rfc2822 */
int i;
- int line_len;
-
- /* How many bytes are already used on the current line? */
- for (i = sb->len - 1; i >= 0; i--)
- if (sb->buf[i] == '\n')
- break;
- line_len = sb->len - (i+1);
for (i = 0; i < len; i++) {
int ch = line[i];
if (non_ascii(ch) || ch == '\n')
- goto needquote;
+ return 1;
if ((i + 1 < len) && (ch == '=' && line[i+1] == '?'))
- goto needquote;
+ return 1;
}
- strbuf_add_wrapped_bytes(sb, line, len, 0, 1, max_length - line_len);
- return;
-needquote:
+ return 0;
+}
+
+static void add_rfc2047(struct strbuf *sb, const char *line, int len,
+ const char *encoding, enum rfc2047_type type)
+{
+ static const int max_encoded_length = 76; /* per rfc2047 */
+ int i;
+ int line_len = last_line_length(sb);
+
strbuf_grow(sb, len * 3 + strlen(encoding) + 100);
strbuf_addf(sb, "=?%s?q?", encoding);
line_len += strlen(encoding) + 5; /* 5 for =??q? */
for (i = 0; i < len; i++) {
unsigned ch = line[i] & 0xFF;
+ int is_special = is_rfc2047_special(ch, type);
+
+ /*
+ * According to RFC 2047, we could encode the special character
+ * ' ' (space) with '_' (underscore) for readability. But many
+ * programs do not understand this and just leave the
+ * underscore in place. Thus, we do nothing special here, which
+ * causes ' ' to be encoded as '=20', avoiding this problem.
+ */
- if (line_len >= max_length - 2) {
+ if (line_len + 2 + (is_special ? 3 : 1) > max_encoded_length) {
strbuf_addf(sb, "?=\n =?%s?q?", encoding);
line_len = strlen(encoding) + 5 + 1; /* =??q? plus SP */
}
- /*
- * We encode ' ' using '=20' even though rfc2047
- * allows using '_' for readability. Unfortunately,
- * many programs do not understand this and just
- * leave the underscore in place.
- */
- if (is_rfc2047_special(ch) || ch == ' ' || ch == '\n') {
+ if (is_special) {
strbuf_addf(sb, "=%02X", ch);
line_len += 3;
- }
- else {
+ } else {
strbuf_addch(sb, ch);
line_len++;
}
@@ -323,53 +387,79 @@ void pp_user_info(const struct pretty_print_context *pp,
const char *what, struct strbuf *sb,
const char *line, const char *encoding)
{
- char *date;
- int namelen;
+ struct strbuf name;
+ struct strbuf mail;
+ struct ident_split ident;
+ int linelen;
+ char *line_end, *date;
+ const char *mailbuf, *namebuf;
+ size_t namelen, maillen;
+ int max_length = 78; /* per rfc2822 */
unsigned long time;
int tz;
if (pp->fmt == CMIT_FMT_ONELINE)
return;
- date = strchr(line, '>');
- if (!date)
+
+ line_end = strchr(line, '\n');
+ if (!line_end) {
+ line_end = strchr(line, '\0');
+ if (!line_end)
+ return;
+ }
+
+ linelen = ++line_end - line;
+ if (split_ident_line(&ident, line, linelen))
return;
- namelen = ++date - line;
- time = strtoul(date, &date, 10);
+
+
+ mailbuf = ident.mail_begin;
+ maillen = ident.mail_end - ident.mail_begin;
+ namebuf = ident.name_begin;
+ namelen = ident.name_end - ident.name_begin;
+
+ if (pp->mailmap)
+ map_user(pp->mailmap, &mailbuf, &maillen, &namebuf, &namelen);
+
+ strbuf_init(&mail, 0);
+ strbuf_init(&name, 0);
+
+ strbuf_add(&mail, mailbuf, maillen);
+ strbuf_add(&name, namebuf, namelen);
+
+ namelen = name.len + mail.len + 3; /* ' ' + '<' + '>' */
+ time = strtoul(ident.date_begin, &date, 10);
tz = strtol(date, NULL, 10);
if (pp->fmt == CMIT_FMT_EMAIL) {
- char *name_tail = strchr(line, '<');
- int display_name_length;
- int final_line;
- if (!name_tail)
- return;
- while (line < name_tail && isspace(name_tail[-1]))
- name_tail--;
- display_name_length = name_tail - line;
strbuf_addstr(sb, "From: ");
- if (!has_rfc822_specials(line, display_name_length)) {
- add_rfc2047(sb, line, display_name_length, encoding);
- } else {
+ if (needs_rfc2047_encoding(name.buf, name.len, RFC2047_ADDRESS)) {
+ add_rfc2047(sb, name.buf, name.len,
+ encoding, RFC2047_ADDRESS);
+ max_length = 76; /* per rfc2047 */
+ } else if (needs_rfc822_quoting(name.buf, name.len)) {
struct strbuf quoted = STRBUF_INIT;
- add_rfc822_quoted(&quoted, line, display_name_length);
- add_rfc2047(sb, quoted.buf, quoted.len, encoding);
+ add_rfc822_quoted(&quoted, name.buf, name.len);
+ strbuf_add_wrapped_bytes(sb, quoted.buf, quoted.len,
+ -6, 1, max_length);
strbuf_release(&quoted);
+ } else {
+ strbuf_add_wrapped_bytes(sb, name.buf, name.len,
+ -6, 1, max_length);
}
- for (final_line = 0; final_line < sb->len; final_line++)
- if (sb->buf[sb->len - final_line - 1] == '\n')
- break;
- if (namelen - display_name_length + final_line > 78) {
+ if (namelen - name.len + last_line_length(sb) > max_length)
strbuf_addch(sb, '\n');
- if (!isspace(name_tail[0]))
- strbuf_addch(sb, ' ');
- }
- strbuf_add(sb, name_tail, namelen - display_name_length);
- strbuf_addch(sb, '\n');
+
+ strbuf_addf(sb, " <%s>\n", mail.buf);
} else {
- strbuf_addf(sb, "%s: %.*s%.*s\n", what,
+ strbuf_addf(sb, "%s: %.*s%s <%s>\n", what,
(pp->fmt == CMIT_FMT_FULLER) ? 4 : 0,
- " ", namelen, line);
+ " ", name.buf, mail.buf);
}
+
+ strbuf_release(&mail);
+ strbuf_release(&name);
+
switch (pp->fmt) {
case CMIT_FMT_MEDIUM:
strbuf_addf(sb, "Date: %s\n", show_date(time, tz, pp->date_mode));
@@ -434,10 +524,11 @@ static void add_merge_info(const struct pretty_print_context *pp,
strbuf_addch(sb, '\n');
}
-static char *get_header(const struct commit *commit, const char *key)
+static char *get_header(const struct commit *commit, const char *msg,
+ const char *key)
{
int key_len = strlen(key);
- const char *line = commit->buffer;
+ const char *line = msg;
while (line) {
const char *eol = strchr(line, '\n'), *next;
@@ -498,28 +589,81 @@ char *logmsg_reencode(const struct commit *commit,
static const char *utf8 = "UTF-8";
const char *use_encoding;
char *encoding;
+ char *msg = commit->buffer;
char *out;
- if (!*output_encoding)
- return NULL;
- encoding = get_header(commit, "encoding");
+ if (!msg) {
+ enum object_type type;
+ unsigned long size;
+
+ msg = read_sha1_file(commit->object.sha1, &type, &size);
+ if (!msg)
+ die("Cannot read commit object %s",
+ sha1_to_hex(commit->object.sha1));
+ if (type != OBJ_COMMIT)
+ die("Expected commit for '%s', got %s",
+ sha1_to_hex(commit->object.sha1), typename(type));
+ }
+
+ if (!output_encoding || !*output_encoding)
+ return msg;
+ encoding = get_header(commit, msg, "encoding");
use_encoding = encoding ? encoding : utf8;
- if (!strcmp(use_encoding, output_encoding))
- if (encoding) /* we'll strip encoding header later */
- out = xstrdup(commit->buffer);
- else
- return NULL; /* nothing to do */
- else
- out = reencode_string(commit->buffer,
- output_encoding, use_encoding);
+ if (same_encoding(use_encoding, output_encoding)) {
+ /*
+ * No encoding work to be done. If we have no encoding header
+ * at all, then there's nothing to do, and we can return the
+ * message verbatim (whether newly allocated or not).
+ */
+ if (!encoding)
+ return msg;
+
+ /*
+ * Otherwise, we still want to munge the encoding header in the
+ * result, which will be done by modifying the buffer. If we
+ * are using a fresh copy, we can reuse it. But if we are using
+ * the cached copy from commit->buffer, we need to duplicate it
+ * to avoid munging commit->buffer.
+ */
+ out = msg;
+ if (out == commit->buffer)
+ out = xstrdup(out);
+ }
+ else {
+ /*
+ * There's actual encoding work to do. Do the reencoding, which
+ * still leaves the header to be replaced in the next step. At
+ * this point, we are done with msg. If we allocated a fresh
+ * copy, we can free it.
+ */
+ out = reencode_string(msg, output_encoding, use_encoding);
+ if (out && msg != commit->buffer)
+ free(msg);
+ }
+
+ /*
+ * This replacement actually consumes the buffer we hand it, so we do
+ * not have to worry about freeing the old "out" here.
+ */
if (out)
out = replace_encoding_header(out, output_encoding);
free(encoding);
- return out;
+ /*
+ * If the re-encoding failed, out might be NULL here; in that
+ * case we just return the commit message verbatim.
+ */
+ return out ? out : msg;
}
-static int mailmap_name(char *email, int email_len, char *name, int name_len)
+void logmsg_free(char *msg, const struct commit *commit)
+{
+ if (msg != commit->buffer)
+ free(msg);
+}
+
+static int mailmap_name(const char **email, size_t *email_len,
+ const char **name, size_t *name_len)
{
static struct string_list *mail_map;
if (!mail_map) {
@@ -536,36 +680,26 @@ static size_t format_person_part(struct strbuf *sb, char part,
const int placeholder_len = 2;
int tz;
unsigned long date = 0;
- char person_name[1024];
- char person_mail[1024];
struct ident_split s;
- const char *name_start, *name_end, *mail_start, *mail_end;
+ const char *name, *mail;
+ size_t maillen, namelen;
if (split_ident_line(&s, msg, len) < 0)
goto skip;
- name_start = s.name_begin;
- name_end = s.name_end;
- mail_start = s.mail_begin;
- mail_end = s.mail_end;
-
- if (part == 'N' || part == 'E') { /* mailmap lookup */
- snprintf(person_name, sizeof(person_name), "%.*s",
- (int)(name_end - name_start), name_start);
- snprintf(person_mail, sizeof(person_mail), "%.*s",
- (int)(mail_end - mail_start), mail_start);
- mailmap_name(person_mail, sizeof(person_mail), person_name, sizeof(person_name));
- name_start = person_name;
- name_end = name_start + strlen(person_name);
- mail_start = person_mail;
- mail_end = mail_start + strlen(person_mail);
- }
+ name = s.name_begin;
+ namelen = s.name_end - s.name_begin;
+ mail = s.mail_begin;
+ maillen = s.mail_end - s.mail_begin;
+
+ if (part == 'N' || part == 'E') /* mailmap lookup */
+ mailmap_name(&mail, &maillen, &name, &namelen);
if (part == 'n' || part == 'N') { /* name */
- strbuf_add(sb, name_start, name_end-name_start);
+ strbuf_add(sb, name, namelen);
return placeholder_len;
}
if (part == 'e' || part == 'E') { /* email */
- strbuf_add(sb, mail_start, mail_end-mail_start);
+ strbuf_add(sb, mail, maillen);
return placeholder_len;
}
@@ -893,12 +1027,19 @@ static size_t format_commit_one(struct strbuf *sb, const char *placeholder,
switch (placeholder[0]) {
case 'C':
if (placeholder[1] == '(') {
- const char *end = strchr(placeholder + 2, ')');
+ const char *begin = placeholder + 2;
+ const char *end = strchr(begin, ')');
char color[COLOR_MAXLEN];
+
if (!end)
return 0;
- color_parse_mem(placeholder + 2,
- end - (placeholder + 2),
+ if (!prefixcmp(begin, "auto,")) {
+ if (!want_color(c->pretty_ctx->color))
+ return end - placeholder + 1;
+ begin += 5;
+ }
+ color_parse_mem(begin,
+ end - begin,
"--pretty format", color);
strbuf_addstr(sb, color);
return end - placeholder + 1;
@@ -1033,9 +1174,8 @@ static size_t format_commit_one(struct strbuf *sb, const char *placeholder,
}
return 0; /* unknown %g placeholder */
case 'N':
- if (c->pretty_ctx->show_notes) {
- format_display_notes(commit->object.sha1, sb,
- get_log_output_encoding(), 0);
+ if (c->pretty_ctx->notes_message) {
+ strbuf_addstr(sb, c->pretty_ctx->notes_message);
return 1;
}
return 0;
@@ -1184,29 +1324,18 @@ void format_commit_message(const struct commit *commit,
const struct pretty_print_context *pretty_ctx)
{
struct format_commit_context context;
- static const char utf8[] = "UTF-8";
const char *output_enc = pretty_ctx->output_encoding;
memset(&context, 0, sizeof(context));
context.commit = commit;
context.pretty_ctx = pretty_ctx;
context.wrap_start = sb->len;
- context.message = commit->buffer;
- if (output_enc) {
- char *enc = get_header(commit, "encoding");
- if (strcmp(enc ? enc : utf8, output_enc)) {
- context.message = logmsg_reencode(commit, output_enc);
- if (!context.message)
- context.message = commit->buffer;
- }
- free(enc);
- }
+ context.message = logmsg_reencode(commit, output_enc);
strbuf_expand(sb, format, format_commit_item, &context);
rewrap_message_tail(sb, &context, 0, 0, 0);
- if (context.message != commit->buffer)
- free(context.message);
+ logmsg_free(context.message, commit);
free(context.signature.gpg_output);
free(context.signature.signer);
}
@@ -1236,7 +1365,7 @@ static void pp_header(const struct pretty_print_context *pp,
continue;
}
- if (!memcmp(line, "parent ", 7)) {
+ if (!prefixcmp(line, "parent ")) {
if (linelen != 48)
die("bad parent line in commit");
continue;
@@ -1260,11 +1389,11 @@ static void pp_header(const struct pretty_print_context *pp,
* FULL shows both authors but not dates.
* FULLER shows both authors and dates.
*/
- if (!memcmp(line, "author ", 7)) {
+ if (!prefixcmp(line, "author ")) {
strbuf_grow(sb, linelen + 80);
pp_user_info(pp, "Author", sb, line + 7, encoding);
}
- if (!memcmp(line, "committer ", 10) &&
+ if (!prefixcmp(line, "committer ") &&
(pp->fmt == CMIT_FMT_FULL || pp->fmt == CMIT_FMT_FULLER)) {
strbuf_grow(sb, linelen + 80);
pp_user_info(pp, "Commit", sb, line + 10, encoding);
@@ -1278,6 +1407,7 @@ void pp_title_line(const struct pretty_print_context *pp,
const char *encoding,
int need_8bit_cte)
{
+ static const int max_length = 78; /* per rfc2047 */
struct strbuf title;
strbuf_init(&title, 80);
@@ -1287,7 +1417,12 @@ void pp_title_line(const struct pretty_print_context *pp,
strbuf_grow(sb, title.len + 1024);
if (pp->subject) {
strbuf_addstr(sb, pp->subject);
- add_rfc2047(sb, title.buf, title.len, encoding);
+ if (needs_rfc2047_encoding(title.buf, title.len, RFC2047_SUBJECT))
+ add_rfc2047(sb, title.buf, title.len,
+ encoding, RFC2047_SUBJECT);
+ else
+ strbuf_add_wrapped_bytes(sb, title.buf, title.len,
+ -last_line_length(sb), 1, max_length);
} else {
strbuf_addbuf(sb, &title);
}
@@ -1341,23 +1476,13 @@ void pp_remainder(const struct pretty_print_context *pp,
}
}
-char *reencode_commit_message(const struct commit *commit, const char **encoding_p)
-{
- const char *encoding;
-
- encoding = get_log_output_encoding();
- if (encoding_p)
- *encoding_p = encoding;
- return logmsg_reencode(commit, encoding);
-}
-
void pretty_print_commit(const struct pretty_print_context *pp,
const struct commit *commit,
struct strbuf *sb)
{
unsigned long beginning_of_body;
int indent = 4;
- const char *msg = commit->buffer;
+ const char *msg;
char *reencoded;
const char *encoding;
int need_8bit_cte = pp->need_8bit_cte;
@@ -1367,10 +1492,8 @@ void pretty_print_commit(const struct pretty_print_context *pp,
return;
}
- reencoded = reencode_commit_message(commit, &encoding);
- if (reencoded) {
- msg = reencoded;
- }
+ encoding = get_log_output_encoding();
+ msg = reencoded = logmsg_reencode(commit, encoding);
if (pp->fmt == CMIT_FMT_ONELINE || pp->fmt == CMIT_FMT_EMAIL)
indent = 0;
@@ -1427,11 +1550,7 @@ void pretty_print_commit(const struct pretty_print_context *pp,
if (pp->fmt == CMIT_FMT_EMAIL && sb->len <= beginning_of_body)
strbuf_addch(sb, '\n');
- if (pp->show_notes)
- format_display_notes(commit->object.sha1, sb, encoding,
- NOTES_SHOW_HEADER | NOTES_INDENT);
-
- free(reencoded);
+ logmsg_free(reencoded, commit);
}
void pp_commit_easy(enum cmit_fmt fmt, const struct commit *commit,
generated by cgit v1.2.3 (git 2.25.1) at 2024-11-12 20:26:11 +0000