summaryrefslogtreecommitdiff
path: root/builtin/mailinfo.c
diff options
context:
space:
mode:
Diffstat (limited to 'builtin/mailinfo.c')
-rw-r--r--builtin/mailinfo.c124
1 files changed, 68 insertions, 56 deletions
diff --git a/builtin/mailinfo.c b/builtin/mailinfo.c
index 71e6262a87..c8a47c173d 100644
--- a/builtin/mailinfo.c
+++ b/builtin/mailinfo.c
@@ -15,18 +15,17 @@ static const char *metainfo_charset;
static struct strbuf line = STRBUF_INIT;
static struct strbuf name = STRBUF_INIT;
static struct strbuf email = STRBUF_INIT;
+static char *message_id;
static enum {
TE_DONTCARE, TE_QP, TE_BASE64
} transfer_encoding;
-static enum {
- TYPE_TEXT, TYPE_OTHER
-} message_type;
static struct strbuf charset = STRBUF_INIT;
static int patch_lines;
static struct strbuf **p_hdr_data, **s_hdr_data;
static int use_scissors;
+static int add_message_id;
static int use_inbody_headers = 1;
#define MAX_HDR_PARSED 10
@@ -160,10 +159,9 @@ static int slurp_attr(const char *line, const char *name, struct strbuf *attr)
const char *ends, *ap = strcasestr(line, name);
size_t sz;
- if (!ap) {
- strbuf_setlen(attr, 0);
+ strbuf_setlen(attr, 0);
+ if (!ap)
return 0;
- }
ap += strlen(name);
if (*ap == '"') {
ap++;
@@ -185,8 +183,6 @@ static void handle_content_type(struct strbuf *line)
struct strbuf *boundary = xmalloc(sizeof(struct strbuf));
strbuf_init(boundary, line->len);
- if (!strcasestr(line->buf, "text/"))
- message_type = TYPE_OTHER;
if (slurp_attr(line->buf, "boundary=", boundary)) {
strbuf_insert(boundary, 0, "--", 2);
if (++content_top > &content[MAX_BOUNDARIES]) {
@@ -204,6 +200,12 @@ static void handle_content_type(struct strbuf *line)
}
}
+static void handle_message_id(const struct strbuf *line)
+{
+ if (add_message_id)
+ message_id = strdup(line->buf);
+}
+
static void handle_content_transfer_encoding(const struct strbuf *line)
{
if (strcasestr(line->buf, "base64"))
@@ -232,7 +234,9 @@ static void cleanup_subject(struct strbuf *subject)
case 'r': case 'R':
if (subject->len <= at + 3)
break;
- if (!memcmp(subject->buf + at + 1, "e:", 2)) {
+ if ((subject->buf[at + 1] == 'e' ||
+ subject->buf[at + 1] == 'E') &&
+ subject->buf[at + 2] == ':') {
strbuf_remove(subject, at, 3);
continue;
}
@@ -250,8 +254,17 @@ static void cleanup_subject(struct strbuf *subject)
(7 <= remove &&
memmem(subject->buf + at, remove, "PATCH", 5)))
strbuf_remove(subject, at, remove);
- else
+ else {
at += remove;
+ /*
+ * If the input had a space after the ], keep
+ * it. We don't bother with finding the end of
+ * the space, since we later normalize it
+ * anyway.
+ */
+ if (isspace(subject->buf[at]))
+ at += 1;
+ }
continue;
}
break;
@@ -283,6 +296,22 @@ static inline int cmp_header(const struct strbuf *line, const char *hdr)
line->buf[len] == ':' && isspace(line->buf[len + 1]);
}
+static int is_format_patch_separator(const char *line, int len)
+{
+ static const char SAMPLE[] =
+ "From e6807f3efca28b30decfecb1732a56c7db1137ee Mon Sep 17 00:00:00 2001\n";
+ const char *cp;
+
+ if (len != strlen(SAMPLE))
+ return 0;
+ if (!skip_prefix(line, "From ", &cp))
+ return 0;
+ if (strspn(cp, "0123456789abcdef") != 40)
+ return 0;
+ cp += 40;
+ return !memcmp(SAMPLE + (cp - line), cp, strlen(SAMPLE) - (cp - line));
+}
+
static int check_header(const struct strbuf *line,
struct strbuf *hdr_data[], int overwrite)
{
@@ -321,15 +350,23 @@ static int check_header(const struct strbuf *line,
ret = 1;
goto check_header_out;
}
+ if (cmp_header(line, "Message-Id")) {
+ len = strlen("Message-Id: ");
+ strbuf_add(&sb, line->buf + len, line->len - len);
+ decode_header(&sb);
+ handle_message_id(&sb);
+ ret = 1;
+ goto check_header_out;
+ }
/* for inbody stuff */
- if (!prefixcmp(line->buf, ">From") && isspace(line->buf[5])) {
- ret = 1; /* Should this return 0? */
+ if (starts_with(line->buf, ">From") && isspace(line->buf[5])) {
+ ret = is_format_patch_separator(line->buf + 1, line->len - 1);
goto check_header_out;
}
- if (!prefixcmp(line->buf, "[PATCH]") && isspace(line->buf[7])) {
+ if (starts_with(line->buf, "[PATCH]") && isspace(line->buf[7])) {
for (i = 0; header[i]; i++) {
- if (!memcmp("Subject", header[i], 7)) {
+ if (!strcmp("Subject", header[i])) {
handle_header(&hdr_data[i], line);
ret = 1;
goto check_header_out;
@@ -356,7 +393,7 @@ static int is_rfc2822_header(const struct strbuf *line)
char *cp = line->buf;
/* Count mbox From headers as headers */
- if (!prefixcmp(cp, "From ") || !prefixcmp(cp, ">From "))
+ if (starts_with(cp, "From ") || starts_with(cp, ">From "))
return 1;
while ((ch = *cp++)) {
@@ -400,7 +437,7 @@ static int read_one_header_line(struct strbuf *line, FILE *in)
break;
if (strbuf_getline(&continuation, in, '\n'))
break;
- continuation.buf[0] = '\n';
+ continuation.buf[0] = ' ';
strbuf_rtrim(&continuation);
strbuf_addbuf(line, &continuation);
}
@@ -472,37 +509,14 @@ static struct strbuf *decode_b_segment(const struct strbuf *b_seg)
return out;
}
-/*
- * When there is no known charset, guess.
- *
- * Right now we assume that if the target is UTF-8 (the default),
- * and it already looks like UTF-8 (which includes US-ASCII as its
- * subset, of course) then that is what it is and there is nothing
- * to do.
- *
- * Otherwise, we default to assuming it is Latin1 for historical
- * reasons.
- */
-static const char *guess_charset(const struct strbuf *line, const char *target_charset)
-{
- if (is_encoding_utf8(target_charset)) {
- if (is_utf8(line->buf))
- return NULL;
- }
- return "ISO8859-1";
-}
-
static void convert_to_utf8(struct strbuf *line, const char *charset)
{
char *out;
- if (!charset || !*charset) {
- charset = guess_charset(line, metainfo_charset);
- if (!charset)
- return;
- }
+ if (!charset || !*charset)
+ return;
- if (!strcasecmp(metainfo_charset, charset))
+ if (same_encoding(metainfo_charset, charset))
return;
out = reencode_string(line->buf, metainfo_charset, charset);
if (!out)
@@ -671,7 +685,6 @@ again:
/* set some defaults */
transfer_encoding = TE_DONTCARE;
strbuf_reset(&charset);
- message_type = TYPE_TEXT;
/* slurp in this section's info */
while (read_one_header_line(&line, fin))
@@ -690,11 +703,11 @@ static inline int patchbreak(const struct strbuf *line)
size_t i;
/* Beginning of a "diff -" header? */
- if (!prefixcmp(line->buf, "diff -"))
+ if (starts_with(line->buf, "diff -"))
return 1;
/* CVS "Index: " line? */
- if (!prefixcmp(line->buf, "Index: "))
+ if (starts_with(line->buf, "Index: "))
return 1;
/*
@@ -704,7 +717,7 @@ static inline int patchbreak(const struct strbuf *line)
if (line->len < 4)
return 0;
- if (!prefixcmp(line->buf, "---")) {
+ if (starts_with(line->buf, "---")) {
/* space followed by a filename? */
if (line->buf[3] == ' ' && !isspace(line->buf[4]))
return 1;
@@ -819,6 +832,8 @@ static int handle_commit_msg(struct strbuf *line)
}
if (patchbreak(line)) {
+ if (message_id)
+ fprintf(cmitmsg, "Message-Id: %s\n", message_id);
fclose(cmitmsg);
cmitmsg = NULL;
return 1;
@@ -885,11 +900,6 @@ static void handle_body(void)
strbuf_insert(&line, 0, prev.buf, prev.len);
strbuf_reset(&prev);
- /* binary data most likely doesn't have newlines */
- if (message_type != TYPE_TEXT) {
- handle_filter(&line);
- break;
- }
/*
* This is a decoded line that may contain
* multiple new lines. Pass only one chunk
@@ -953,13 +963,13 @@ static void handle_info(void)
else
continue;
- if (!memcmp(header[i], "Subject", 7)) {
+ if (!strcmp(header[i], "Subject")) {
if (!keep_subject) {
cleanup_subject(hdr);
cleanup_space(hdr);
}
output_header_lines(fout, "Subject", hdr);
- } else if (!memcmp(header[i], "From", 4)) {
+ } else if (!strcmp(header[i], "From")) {
cleanup_space(hdr);
handle_from(hdr);
fprintf(fout, "Author: %s\n", name.buf);
@@ -1010,7 +1020,7 @@ static int mailinfo(FILE *in, FILE *out, const char *msg, const char *patch)
static int git_mailinfo_config(const char *var, const char *value, void *unused)
{
- if (prefixcmp(var, "mailinfo."))
+ if (!starts_with(var, "mailinfo."))
return git_default_config(var, value, unused);
if (!strcmp(var, "mailinfo.scissors")) {
use_scissors = git_config_bool(var, value);
@@ -1021,7 +1031,7 @@ static int git_mailinfo_config(const char *var, const char *value, void *unused)
}
static const char mailinfo_usage[] =
- "git mailinfo [-k|-b] [-u | --encoding=<encoding> | -n] [--scissors | --no-scissors] msg patch < mail >info";
+ "git mailinfo [-k|-b] [-m | --message-id] [-u | --encoding=<encoding> | -n] [--scissors | --no-scissors] msg patch < mail >info";
int cmd_mailinfo(int argc, const char **argv, const char *prefix)
{
@@ -1040,11 +1050,13 @@ int cmd_mailinfo(int argc, const char **argv, const char *prefix)
keep_subject = 1;
else if (!strcmp(argv[1], "-b"))
keep_non_patch_brackets_in_subject = 1;
+ else if (!strcmp(argv[1], "-m") || !strcmp(argv[1], "--message-id"))
+ add_message_id = 1;
else if (!strcmp(argv[1], "-u"))
metainfo_charset = def_charset;
else if (!strcmp(argv[1], "-n"))
metainfo_charset = NULL;
- else if (!prefixcmp(argv[1], "--encoding="))
+ else if (starts_with(argv[1], "--encoding="))
metainfo_charset = argv[1] + 11;
else if (!strcmp(argv[1], "--scissors"))
use_scissors = 1;
generated by cgit v1.2.3 (git 2.25.1) at 2024-11-18 18:46:54 +0000