#define MAX_HDR_PARSED 10
#define MAX_BOUNDARIES 5
+static void cleanup_space(struct strbuf *sb);
+
+
static void get_sane_name(struct strbuf *out, struct strbuf *name, struct strbuf *email)
{
struct strbuf *src = name;
el = strcspn(at, " \n\t\r\v\f>");
strbuf_reset(&email);
strbuf_add(&email, at, el);
- strbuf_remove(&f, at - f.buf, el + 1);
+ strbuf_remove(&f, at - f.buf, el + (at[el] ? 1 : 0));
- /* The remainder is name. It could be "John Doe <john.doe@xz>"
- * or "john.doe@xz (John Doe)", but we have removed the
- * email part, so trim from both ends, possibly removing
- * the () pair at the end.
+ /* The remainder is name. It could be
+ *
+ * - "John Doe <john.doe@xz>" (a), or
+ * - "john.doe@xz (John Doe)" (b), or
+ * - "John (zzz) Doe <john.doe@xz> (Comment)" (c)
+ *
+ * but we have removed the email part, so
+ *
+ * - remove extra spaces which could stay after email (case 'c'), and
+ * - trim from both ends, possibly removing the () pair at the end
+ * (cases 'a' and 'b').
*/
+ cleanup_space(&f);
strbuf_trim(&f);
if (f.buf[0] == '(' && f.len && f.buf[f.len - 1] == ')') {
strbuf_remove(&f, 0, 1);
message_type = TYPE_OTHER;
if (slurp_attr(line->buf, "boundary=", boundary)) {
strbuf_insert(boundary, 0, "--", 2);
- if (content_top++ >= &content[MAX_BOUNDARIES]) {
+ if (++content_top > &content[MAX_BOUNDARIES]) {
fprintf(stderr, "Too many boundaries to handle\n");
exit(1);
}
static int is_multipart_boundary(const struct strbuf *line)
{
- return !strbuf_cmp(line, *content_top);
+ return (((*content_top)->len <= line->len) &&
+ !memcmp(line->buf, (*content_top)->buf, (*content_top)->len));
}
static void cleanup_subject(struct strbuf *subject)
c -= 'a' - 26;
else if ('0' <= c && c <= '9')
c -= '0' - 52;
- else if (c == '=') {
- /* padding is almost like (c == 0), except we do
- * not output NUL resulting only from it;
- * for now we just trust the data.
- */
- c = 0;
- }
else
continue; /* garbage */
switch (pos++) {
return;
out = reencode_string(line->buf, metainfo_charset, charset);
if (!out)
- die("cannot convert from %s to %s\n",
+ die("cannot convert from %s to %s",
charset, metainfo_charset);
strbuf_attach(line, out, strlen(out), strlen(out));
}
rfc2047 = 1;
if (in != ep) {
- strbuf_add(&outbuf, in, ep - in);
- in = ep;
+ /*
+ * We are about to process an encoded-word
+ * that begins at ep, but there is something
+ * before the encoded word.
+ */
+ char *scan;
+ for (scan = in; scan < ep; scan++)
+ if (!isspace(*scan))
+ break;
+
+ if (scan != ep || in == it->buf) {
+ /*
+ * We should not lose that "something",
+ * unless we have just processed an
+ * encoded-word, and there is only LWS
+ * before the one we are about to process.
+ */
+ strbuf_add(&outbuf, in, ep - in);
+ }
}
/* E.g.
* ep : "=?iso-2022-jp?B?GyR...?= foo"
static int find_boundary(void)
{
while (!strbuf_getline(&line, fin, '\n')) {
- if (is_multipart_boundary(&line))
+ if (*content_top && is_multipart_boundary(&line))
return 1;
}
return 0;
/* technically won't happen as is_multipart_boundary()
will fail first. But just in case..
*/
- if (content_top-- < content) {
+ if (--content_top < content) {
fprintf(stderr, "Detected mismatched boundaries, "
"can't recover\n");
exit(1);
check_header(&line, p_hdr_data, 0);
strbuf_release(&newline);
- /* eat the blank line after section info */
- return (strbuf_getline(&line, fin, '\n') == 0);
+ /* replenish line */
+ if (strbuf_getline(&line, fin, '\n'))
+ return 0;
+ strbuf_addch(&line, '\n');
+ return 1;
}
static inline int patchbreak(const struct strbuf *line)
/* process any boundary lines */
if (*content_top && is_multipart_boundary(&line)) {
/* flush any leftover */
- if (line.len)
- handle_filter(&line);
-
+ if (prev.len) {
+ handle_filter(&prev);
+ strbuf_reset(&prev);
+ }
if (!handle_boundary())
goto handle_body_out;
}
}
output_header_lines(fout, "Subject", hdr);
} else if (!memcmp(header[i], "From", 4)) {
+ cleanup_space(hdr);
handle_from(hdr);
fprintf(fout, "Author: %s\n", name.buf);
fprintf(fout, "Email: %s\n", email.buf);