2005-04-12 08:46:50 +02:00
|
|
|
/*
|
|
|
|
* Another stupid program, this one parsing the headers of an
|
|
|
|
* email to figure out authorship and subject
|
|
|
|
*/
|
2005-11-28 01:29:38 +01:00
|
|
|
#include "cache.h"
|
2006-06-13 22:21:50 +02:00
|
|
|
#include "builtin.h"
|
2006-12-24 08:36:55 +01:00
|
|
|
#include "utf8.h"
|
2005-04-12 08:46:50 +02:00
|
|
|
|
2006-06-13 22:21:50 +02:00
|
|
|
static FILE *cmitmsg, *patchfile, *fin, *fout;
|
2005-04-12 08:46:50 +02:00
|
|
|
|
2006-08-15 19:23:48 +02:00
|
|
|
static int keep_subject;
|
|
|
|
static const char *metainfo_charset;
|
2005-04-12 08:46:50 +02:00
|
|
|
static char line[1000];
|
|
|
|
static char name[1000];
|
|
|
|
static char email[1000];
|
|
|
|
|
2005-08-28 21:33:16 +02:00
|
|
|
static enum {
|
|
|
|
TE_DONTCARE, TE_QP, TE_BASE64,
|
|
|
|
} transfer_encoding;
|
2007-03-12 20:52:04 +01:00
|
|
|
static enum {
|
|
|
|
TYPE_TEXT, TYPE_OTHER,
|
|
|
|
} message_type;
|
2005-08-28 21:33:16 +02:00
|
|
|
|
2007-03-12 20:52:04 +01:00
|
|
|
static char charset[256];
|
2006-08-15 19:23:48 +02:00
|
|
|
static int patch_lines;
|
2007-03-12 20:52:04 +01:00
|
|
|
static char **p_hdr_data, **s_hdr_data;
|
|
|
|
|
|
|
|
#define MAX_HDR_PARSED 10
|
|
|
|
#define MAX_BOUNDARIES 5
|
2005-08-28 21:33:16 +02:00
|
|
|
|
2005-04-12 08:46:50 +02:00
|
|
|
static char *sanity_check(char *name, char *email)
|
|
|
|
{
|
|
|
|
int len = strlen(name);
|
|
|
|
if (len < 3 || len > 60)
|
|
|
|
return email;
|
|
|
|
if (strchr(name, '@') || strchr(name, '<') || strchr(name, '>'))
|
|
|
|
return email;
|
|
|
|
return name;
|
|
|
|
}
|
|
|
|
|
2005-12-15 01:31:06 +01:00
|
|
|
static int bogus_from(char *line)
|
|
|
|
{
|
|
|
|
/* John Doe <johndoe> */
|
|
|
|
char *bra, *ket, *dst, *cp;
|
|
|
|
|
|
|
|
/* This is fallback, so do not bother if we already have an
|
|
|
|
* e-mail address.
|
2006-06-13 22:21:50 +02:00
|
|
|
*/
|
2005-12-15 01:31:06 +01:00
|
|
|
if (*email)
|
|
|
|
return 0;
|
|
|
|
|
|
|
|
bra = strchr(line, '<');
|
|
|
|
if (!bra)
|
|
|
|
return 0;
|
|
|
|
ket = strchr(bra, '>');
|
|
|
|
if (!ket)
|
|
|
|
return 0;
|
|
|
|
|
|
|
|
for (dst = email, cp = bra+1; cp < ket; )
|
|
|
|
*dst++ = *cp++;
|
|
|
|
*dst = 0;
|
|
|
|
for (cp = line; isspace(*cp); cp++)
|
|
|
|
;
|
|
|
|
for (bra--; isspace(*bra); bra--)
|
|
|
|
*bra = 0;
|
|
|
|
cp = sanity_check(cp, email);
|
|
|
|
strcpy(name, cp);
|
|
|
|
return 1;
|
|
|
|
}
|
|
|
|
|
2006-05-23 21:58:36 +02:00
|
|
|
static int handle_from(char *in_line)
|
2005-04-12 08:46:50 +02:00
|
|
|
{
|
2006-05-23 21:58:36 +02:00
|
|
|
char line[1000];
|
|
|
|
char *at;
|
2005-04-12 08:46:50 +02:00
|
|
|
char *dst;
|
|
|
|
|
2006-05-23 21:58:36 +02:00
|
|
|
strcpy(line, in_line);
|
|
|
|
at = strchr(line, '@');
|
2005-04-12 08:46:50 +02:00
|
|
|
if (!at)
|
2005-12-15 01:31:06 +01:00
|
|
|
return bogus_from(line);
|
2005-04-12 08:46:50 +02:00
|
|
|
|
|
|
|
/*
|
|
|
|
* If we already have one email, don't take any confusing lines
|
|
|
|
*/
|
|
|
|
if (*email && strchr(at+1, '@'))
|
|
|
|
return 0;
|
|
|
|
|
2005-08-28 21:33:16 +02:00
|
|
|
/* Pick up the string around '@', possibly delimited with <>
|
|
|
|
* pair; that is the email part. White them out while copying.
|
|
|
|
*/
|
2005-04-12 08:46:50 +02:00
|
|
|
while (at > line) {
|
|
|
|
char c = at[-1];
|
2005-08-28 21:33:16 +02:00
|
|
|
if (isspace(c))
|
|
|
|
break;
|
|
|
|
if (c == '<') {
|
|
|
|
at[-1] = ' ';
|
2005-04-12 08:46:50 +02:00
|
|
|
break;
|
2005-08-28 21:33:16 +02:00
|
|
|
}
|
2005-04-12 08:46:50 +02:00
|
|
|
at--;
|
|
|
|
}
|
|
|
|
dst = email;
|
|
|
|
for (;;) {
|
|
|
|
unsigned char c = *at;
|
2005-08-28 21:33:16 +02:00
|
|
|
if (!c || c == '>' || isspace(c)) {
|
|
|
|
if (c == '>')
|
|
|
|
*at = ' ';
|
2005-04-12 08:46:50 +02:00
|
|
|
break;
|
2005-08-28 21:33:16 +02:00
|
|
|
}
|
2005-04-12 08:46:50 +02:00
|
|
|
*at++ = ' ';
|
|
|
|
*dst++ = c;
|
|
|
|
}
|
|
|
|
*dst++ = 0;
|
|
|
|
|
2005-08-28 21:33:16 +02:00
|
|
|
/* The remainder is name. It could be "John Doe <john.doe@xz>"
|
|
|
|
* or "john.doe@xz (John Doe)", but we have whited out the
|
|
|
|
* email part, so trim from both ends, possibly removing
|
|
|
|
* the () pair at the end.
|
|
|
|
*/
|
2005-04-12 08:46:50 +02:00
|
|
|
at = line + strlen(line);
|
|
|
|
while (at > line) {
|
|
|
|
unsigned char c = *--at;
|
2005-08-28 21:33:16 +02:00
|
|
|
if (!isspace(c)) {
|
|
|
|
at[(c == ')') ? 0 : 1] = 0;
|
2005-04-12 08:46:50 +02:00
|
|
|
break;
|
2005-08-28 21:33:16 +02:00
|
|
|
}
|
2005-04-12 08:46:50 +02:00
|
|
|
}
|
|
|
|
|
|
|
|
at = line;
|
|
|
|
for (;;) {
|
|
|
|
unsigned char c = *at;
|
2005-08-28 21:33:16 +02:00
|
|
|
if (!c || !isspace(c)) {
|
|
|
|
if (c == '(')
|
|
|
|
at++;
|
2005-04-12 08:46:50 +02:00
|
|
|
break;
|
2005-08-28 21:33:16 +02:00
|
|
|
}
|
2005-04-12 08:46:50 +02:00
|
|
|
at++;
|
|
|
|
}
|
|
|
|
at = sanity_check(at, email);
|
|
|
|
strcpy(name, at);
|
|
|
|
return 1;
|
|
|
|
}
|
|
|
|
|
2007-03-12 20:52:04 +01:00
|
|
|
static int handle_header(char *line, char *data, int ofs)
|
2005-05-02 06:42:53 +02:00
|
|
|
{
|
2007-03-12 20:52:04 +01:00
|
|
|
if (!line || !data)
|
|
|
|
return 1;
|
|
|
|
|
|
|
|
strcpy(data, line+ofs);
|
2005-05-02 06:42:53 +02:00
|
|
|
|
2005-08-28 21:33:16 +02:00
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
/* NOTE NOTE NOTE. We do not claim we do full MIME. We just attempt
|
|
|
|
* to have enough heuristics to grok MIME encoded patches often found
|
|
|
|
* on our mailing lists. For example, we do not even treat header lines
|
|
|
|
* case insensitively.
|
|
|
|
*/
|
|
|
|
|
|
|
|
static int slurp_attr(const char *line, const char *name, char *attr)
|
|
|
|
{
|
2006-06-28 11:04:39 +02:00
|
|
|
const char *ends, *ap = strcasestr(line, name);
|
2005-08-28 21:33:16 +02:00
|
|
|
size_t sz;
|
|
|
|
|
|
|
|
if (!ap) {
|
|
|
|
*attr = 0;
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
ap += strlen(name);
|
|
|
|
if (*ap == '"') {
|
|
|
|
ap++;
|
|
|
|
ends = "\"";
|
|
|
|
}
|
|
|
|
else
|
|
|
|
ends = "; \t";
|
|
|
|
sz = strcspn(ap, ends);
|
|
|
|
memcpy(attr, ap, sz);
|
|
|
|
attr[sz] = 0;
|
|
|
|
return 1;
|
|
|
|
}
|
|
|
|
|
2007-03-12 20:52:04 +01:00
|
|
|
struct content_type {
|
|
|
|
char *boundary;
|
|
|
|
int boundary_len;
|
|
|
|
};
|
|
|
|
|
|
|
|
static struct content_type content[MAX_BOUNDARIES];
|
|
|
|
|
|
|
|
static struct content_type *content_top = content;
|
|
|
|
|
|
|
|
static int handle_content_type(char *line)
|
2005-08-28 21:33:16 +02:00
|
|
|
{
|
2007-03-12 20:52:04 +01:00
|
|
|
char boundary[256];
|
|
|
|
|
|
|
|
if (strcasestr(line, "text/") == NULL)
|
|
|
|
message_type = TYPE_OTHER;
|
|
|
|
if (slurp_attr(line, "boundary=", boundary + 2)) {
|
|
|
|
memcpy(boundary, "--", 2);
|
|
|
|
if (content_top++ >= &content[MAX_BOUNDARIES]) {
|
|
|
|
fprintf(stderr, "Too many boundaries to handle\n");
|
|
|
|
exit(1);
|
|
|
|
}
|
|
|
|
content_top->boundary_len = strlen(boundary);
|
|
|
|
content_top->boundary = xmalloc(content_top->boundary_len+1);
|
|
|
|
strcpy(content_top->boundary, boundary);
|
2005-09-07 01:46:34 +02:00
|
|
|
}
|
2007-03-12 20:52:04 +01:00
|
|
|
if (slurp_attr(line, "charset=", charset)) {
|
2005-08-28 21:33:16 +02:00
|
|
|
int i, c;
|
|
|
|
for (i = 0; (c = charset[i]) != 0; i++)
|
|
|
|
charset[i] = tolower(c);
|
|
|
|
}
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
static int handle_content_transfer_encoding(char *line)
|
|
|
|
{
|
|
|
|
if (strcasestr(line, "base64"))
|
|
|
|
transfer_encoding = TE_BASE64;
|
|
|
|
else if (strcasestr(line, "quoted-printable"))
|
|
|
|
transfer_encoding = TE_QP;
|
|
|
|
else
|
|
|
|
transfer_encoding = TE_DONTCARE;
|
|
|
|
return 0;
|
2005-04-12 08:46:50 +02:00
|
|
|
}
|
|
|
|
|
2005-08-28 21:33:16 +02:00
|
|
|
static int is_multipart_boundary(const char *line)
|
|
|
|
{
|
2007-03-12 20:52:04 +01:00
|
|
|
return (!memcmp(line, content_top->boundary, content_top->boundary_len));
|
2005-08-28 21:33:16 +02:00
|
|
|
}
|
|
|
|
|
|
|
|
static int eatspace(char *line)
|
2005-04-12 08:46:50 +02:00
|
|
|
{
|
2005-08-28 21:33:16 +02:00
|
|
|
int len = strlen(line);
|
|
|
|
while (len > 0 && isspace(line[len-1]))
|
|
|
|
line[--len] = 0;
|
|
|
|
return len;
|
2005-04-12 08:46:50 +02:00
|
|
|
}
|
|
|
|
|
2005-08-28 21:33:16 +02:00
|
|
|
static char *cleanup_subject(char *subject)
|
2005-04-12 08:46:50 +02:00
|
|
|
{
|
|
|
|
for (;;) {
|
|
|
|
char *p;
|
|
|
|
int len, remove;
|
|
|
|
switch (*subject) {
|
|
|
|
case 'r': case 'R':
|
|
|
|
if (!memcmp("e:", subject+1, 2)) {
|
2007-03-12 20:52:04 +01:00
|
|
|
subject += 3;
|
2005-04-12 08:46:50 +02:00
|
|
|
continue;
|
|
|
|
}
|
|
|
|
break;
|
|
|
|
case ' ': case '\t': case ':':
|
|
|
|
subject++;
|
|
|
|
continue;
|
|
|
|
|
|
|
|
case '[':
|
|
|
|
p = strchr(subject, ']');
|
|
|
|
if (!p) {
|
|
|
|
subject++;
|
|
|
|
continue;
|
|
|
|
}
|
|
|
|
len = strlen(p);
|
|
|
|
remove = p - subject;
|
|
|
|
if (remove <= len *2) {
|
|
|
|
subject = p+1;
|
|
|
|
continue;
|
2006-06-13 22:21:50 +02:00
|
|
|
}
|
2005-04-12 08:46:50 +02:00
|
|
|
break;
|
|
|
|
}
|
2006-06-18 01:58:51 +02:00
|
|
|
eatspace(subject);
|
2005-04-12 08:46:50 +02:00
|
|
|
return subject;
|
|
|
|
}
|
2006-06-13 22:21:50 +02:00
|
|
|
}
|
2005-04-12 08:46:50 +02:00
|
|
|
|
|
|
|
static void cleanup_space(char *buf)
|
|
|
|
{
|
|
|
|
unsigned char c;
|
|
|
|
while ((c = *buf) != 0) {
|
|
|
|
buf++;
|
|
|
|
if (isspace(c)) {
|
|
|
|
buf[-1] = ' ';
|
|
|
|
c = *buf;
|
|
|
|
while (isspace(c)) {
|
|
|
|
int len = strlen(buf);
|
|
|
|
memmove(buf, buf+1, len);
|
|
|
|
c = *buf;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2007-08-30 23:48:24 +02:00
|
|
|
static void decode_header(char *it, unsigned itsize);
|
2007-10-21 06:12:12 +02:00
|
|
|
static const char *header[MAX_HDR_PARSED] = {
|
2007-03-12 20:52:04 +01:00
|
|
|
"From","Subject","Date",
|
2005-08-28 21:33:16 +02:00
|
|
|
};
|
|
|
|
|
2007-08-30 23:48:24 +02:00
|
|
|
static int check_header(char *line, unsigned linesize, char **hdr_data, int overwrite)
|
2005-08-28 21:33:16 +02:00
|
|
|
{
|
|
|
|
int i;
|
|
|
|
|
2007-03-12 20:52:04 +01:00
|
|
|
/* search for the interesting parts */
|
|
|
|
for (i = 0; header[i]; i++) {
|
|
|
|
int len = strlen(header[i]);
|
2007-03-30 18:18:45 +02:00
|
|
|
if ((!hdr_data[i] || overwrite) &&
|
2007-03-12 20:52:04 +01:00
|
|
|
!strncasecmp(line, header[i], len) &&
|
2005-08-28 21:33:16 +02:00
|
|
|
line[len] == ':' && isspace(line[len + 1])) {
|
2006-05-23 21:45:37 +02:00
|
|
|
/* Unwrap inline B and Q encoding, and optionally
|
|
|
|
* normalize the meta information to utf8.
|
|
|
|
*/
|
2007-08-30 23:48:24 +02:00
|
|
|
decode_header(line + len + 2, linesize - len - 2);
|
2007-03-12 20:52:04 +01:00
|
|
|
hdr_data[i] = xmalloc(1000 * sizeof(char));
|
|
|
|
if (! handle_header(line, hdr_data[i], len + 2)) {
|
|
|
|
return 1;
|
|
|
|
}
|
2005-08-28 21:33:16 +02:00
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2007-03-12 20:52:04 +01:00
|
|
|
/* Content stuff */
|
|
|
|
if (!strncasecmp(line, "Content-Type", 12) &&
|
|
|
|
line[12] == ':' && isspace(line[12 + 1])) {
|
2007-08-30 23:48:24 +02:00
|
|
|
decode_header(line + 12 + 2, linesize - 12 - 2);
|
2007-03-12 20:52:04 +01:00
|
|
|
if (! handle_content_type(line)) {
|
|
|
|
return 1;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
if (!strncasecmp(line, "Content-Transfer-Encoding", 25) &&
|
|
|
|
line[25] == ':' && isspace(line[25 + 1])) {
|
2007-08-30 23:48:24 +02:00
|
|
|
decode_header(line + 25 + 2, linesize - 25 - 2);
|
2007-03-12 20:52:04 +01:00
|
|
|
if (! handle_content_transfer_encoding(line)) {
|
|
|
|
return 1;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
/* for inbody stuff */
|
|
|
|
if (!memcmp(">From", line, 5) && isspace(line[5]))
|
|
|
|
return 1;
|
|
|
|
if (!memcmp("[PATCH]", line, 7) && isspace(line[7])) {
|
|
|
|
for (i = 0; header[i]; i++) {
|
2008-07-10 23:41:33 +02:00
|
|
|
if (!memcmp("Subject", header[i], 7)) {
|
|
|
|
if (!hdr_data[i])
|
|
|
|
hdr_data[i] = xmalloc(linesize + 20);
|
2007-03-12 20:52:04 +01:00
|
|
|
if (! handle_header(line, hdr_data[i], 0)) {
|
|
|
|
return 1;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
/* no match */
|
|
|
|
return 0;
|
2005-08-28 21:33:16 +02:00
|
|
|
}
|
|
|
|
|
2006-05-26 09:46:58 +02:00
|
|
|
static int is_rfc2822_header(char *line)
|
|
|
|
{
|
|
|
|
/*
|
|
|
|
* The section that defines the loosest possible
|
|
|
|
* field name is "3.6.8 Optional fields".
|
|
|
|
*
|
|
|
|
* optional-field = field-name ":" unstructured CRLF
|
|
|
|
* field-name = 1*ftext
|
|
|
|
* ftext = %d33-57 / %59-126
|
|
|
|
*/
|
|
|
|
int ch;
|
|
|
|
char *cp = line;
|
2007-02-26 20:10:59 +01:00
|
|
|
|
|
|
|
/* Count mbox From headers as headers */
|
|
|
|
if (!memcmp(line, "From ", 5) || !memcmp(line, ">From ", 6))
|
|
|
|
return 1;
|
|
|
|
|
2006-05-26 09:46:58 +02:00
|
|
|
while ((ch = *cp++)) {
|
|
|
|
if (ch == ':')
|
|
|
|
return cp != line;
|
|
|
|
if ((33 <= ch && ch <= 57) ||
|
|
|
|
(59 <= ch && ch <= 126))
|
|
|
|
continue;
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
2007-02-26 20:10:59 +01:00
|
|
|
/*
|
|
|
|
* sz is size of 'line' buffer in bytes. Must be reasonably
|
|
|
|
* long enough to hold one physical real-world e-mail line.
|
|
|
|
*/
|
2005-08-28 21:33:16 +02:00
|
|
|
static int read_one_header_line(char *line, int sz, FILE *in)
|
|
|
|
{
|
2007-02-26 20:10:59 +01:00
|
|
|
int len;
|
|
|
|
|
|
|
|
/*
|
|
|
|
* We will read at most (sz-1) bytes and then potentially
|
|
|
|
* re-add NUL after it. Accessing line[sz] after this is safe
|
|
|
|
* and we can allow len to grow up to and including sz.
|
|
|
|
*/
|
|
|
|
sz--;
|
|
|
|
|
|
|
|
/* Get the first part of the line. */
|
|
|
|
if (!fgets(line, sz, in))
|
|
|
|
return 0;
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Is it an empty line or not a valid rfc2822 header?
|
|
|
|
* If so, stop here, and return false ("not a header")
|
|
|
|
*/
|
|
|
|
len = eatspace(line);
|
|
|
|
if (!len || !is_rfc2822_header(line)) {
|
|
|
|
/* Re-add the newline */
|
|
|
|
line[len] = '\n';
|
|
|
|
line[len + 1] = '\0';
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Now we need to eat all the continuation lines..
|
|
|
|
* Yuck, 2822 header "folding"
|
|
|
|
*/
|
|
|
|
for (;;) {
|
|
|
|
int peek, addlen;
|
|
|
|
static char continuation[1000];
|
|
|
|
|
2006-05-23 21:53:20 +02:00
|
|
|
peek = fgetc(in); ungetc(peek, in);
|
|
|
|
if (peek != ' ' && peek != '\t')
|
|
|
|
break;
|
2007-02-26 20:10:59 +01:00
|
|
|
if (!fgets(continuation, sizeof(continuation), in))
|
|
|
|
break;
|
|
|
|
addlen = eatspace(continuation);
|
|
|
|
if (len < sz - 1) {
|
|
|
|
if (addlen >= sz - len)
|
|
|
|
addlen = sz - len - 1;
|
|
|
|
memcpy(line + len, continuation, addlen);
|
2007-07-29 02:57:25 +02:00
|
|
|
line[len] = '\n';
|
2007-02-26 20:10:59 +01:00
|
|
|
len += addlen;
|
|
|
|
}
|
2005-08-28 21:33:16 +02:00
|
|
|
}
|
2007-02-26 20:10:59 +01:00
|
|
|
line[len] = 0;
|
|
|
|
|
|
|
|
return 1;
|
2005-08-28 21:33:16 +02:00
|
|
|
}
|
|
|
|
|
2007-08-30 23:48:24 +02:00
|
|
|
static int decode_q_segment(char *in, char *ot, unsigned otsize, char *ep, int rfc2047)
|
2005-08-28 21:33:16 +02:00
|
|
|
{
|
2008-05-25 10:16:05 +02:00
|
|
|
char *otbegin = ot;
|
2007-08-30 23:48:24 +02:00
|
|
|
char *otend = ot + otsize;
|
2005-08-28 21:33:16 +02:00
|
|
|
int c;
|
|
|
|
while ((c = *in++) != 0 && (in <= ep)) {
|
2007-08-30 23:48:24 +02:00
|
|
|
if (ot == otend) {
|
|
|
|
*--ot = '\0';
|
|
|
|
return -1;
|
|
|
|
}
|
2005-08-28 21:33:16 +02:00
|
|
|
if (c == '=') {
|
|
|
|
int d = *in++;
|
|
|
|
if (d == '\n' || !d)
|
|
|
|
break; /* drop trailing newline */
|
|
|
|
*ot++ = ((hexval(d) << 4) | hexval(*in++));
|
2006-04-21 09:06:58 +02:00
|
|
|
continue;
|
2005-08-28 21:33:16 +02:00
|
|
|
}
|
2006-04-21 09:06:58 +02:00
|
|
|
if (rfc2047 && c == '_') /* rfc2047 4.2 (2) */
|
|
|
|
c = 0x20;
|
|
|
|
*ot++ = c;
|
2005-08-28 21:33:16 +02:00
|
|
|
}
|
|
|
|
*ot = 0;
|
2008-05-25 10:16:05 +02:00
|
|
|
return (ot - otbegin);
|
2005-08-28 21:33:16 +02:00
|
|
|
}
|
|
|
|
|
2007-08-30 23:48:24 +02:00
|
|
|
static int decode_b_segment(char *in, char *ot, unsigned otsize, char *ep)
|
2005-08-28 21:33:16 +02:00
|
|
|
{
|
|
|
|
/* Decode in..ep, possibly in-place to ot */
|
|
|
|
int c, pos = 0, acc = 0;
|
2008-05-25 10:16:05 +02:00
|
|
|
char *otbegin = ot;
|
2007-08-30 23:48:24 +02:00
|
|
|
char *otend = ot + otsize;
|
2005-08-28 21:33:16 +02:00
|
|
|
|
|
|
|
while ((c = *in++) != 0 && (in <= ep)) {
|
2007-08-30 23:48:24 +02:00
|
|
|
if (ot == otend) {
|
|
|
|
*--ot = '\0';
|
|
|
|
return -1;
|
|
|
|
}
|
2005-08-28 21:33:16 +02:00
|
|
|
if (c == '+')
|
|
|
|
c = 62;
|
|
|
|
else if (c == '/')
|
|
|
|
c = 63;
|
|
|
|
else if ('A' <= c && c <= 'Z')
|
|
|
|
c -= 'A';
|
|
|
|
else if ('a' <= c && c <= 'z')
|
|
|
|
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++) {
|
|
|
|
case 0:
|
|
|
|
acc = (c << 2);
|
|
|
|
break;
|
|
|
|
case 1:
|
|
|
|
*ot++ = (acc | (c >> 4));
|
|
|
|
acc = (c & 15) << 4;
|
|
|
|
break;
|
|
|
|
case 2:
|
|
|
|
*ot++ = (acc | (c >> 2));
|
|
|
|
acc = (c & 3) << 6;
|
|
|
|
break;
|
|
|
|
case 3:
|
|
|
|
*ot++ = (acc | c);
|
|
|
|
acc = pos = 0;
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
*ot = 0;
|
2008-05-25 10:16:05 +02:00
|
|
|
return (ot - otbegin);
|
2005-08-28 21:33:16 +02:00
|
|
|
}
|
|
|
|
|
Do a better job at guessing unknown character sets
At least in the kernel development community, we're generally slowly
converting to UTF-8 everywhere, and the old default of Latin1 in emails is
being supplanted by UTF-8, and it doesn't necessarily show up as such in
the mail headers (because, quite frankly, when people send patches
around, they want the email client to do as little as humanly possible
about the patch)
Despite that, it's often the case that email addresses etc still have
Latin1, so I've seen emails where this is a mixed bag, with Signed-off
parts being copied from email (and containing Latin1 characters), and the
rest of the email being a patch in UTF-8.
So this suggests a very natural change: if the target character set is
utf-8 (the default), and if the source already looks like utf-8, just
assume that it doesn't need any conversion at all.
Only assume that it needs conversion if it isn't already valid utf-8, in
which case we (for historical reasons) will assume it's Latin1.
Basically no really _valid_ latin1 will ever look like utf-8, so while
this changes our historical behaviour, it doesn't do so in practice, and
makes the default behaviour saner for the case where the input was already
in proper format.
We could do a more fancy guess, of course, but this correctly handled a
series of patches I just got from Andrew that had a mixture of Latin1 and
UTF-8 (in different emails, but without any character set indication).
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Junio C Hamano <gitster@pobox.com>
2007-07-17 19:34:44 +02:00
|
|
|
/*
|
|
|
|
* 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 char *line, const char *target_charset)
|
|
|
|
{
|
|
|
|
if (is_encoding_utf8(target_charset)) {
|
|
|
|
if (is_utf8(line))
|
|
|
|
return NULL;
|
|
|
|
}
|
|
|
|
return "latin1";
|
|
|
|
}
|
|
|
|
|
2007-08-30 23:48:24 +02:00
|
|
|
static void convert_to_utf8(char *line, unsigned linesize, const char *charset)
|
2005-08-28 21:33:16 +02:00
|
|
|
{
|
Do a better job at guessing unknown character sets
At least in the kernel development community, we're generally slowly
converting to UTF-8 everywhere, and the old default of Latin1 in emails is
being supplanted by UTF-8, and it doesn't necessarily show up as such in
the mail headers (because, quite frankly, when people send patches
around, they want the email client to do as little as humanly possible
about the patch)
Despite that, it's often the case that email addresses etc still have
Latin1, so I've seen emails where this is a mixed bag, with Signed-off
parts being copied from email (and containing Latin1 characters), and the
rest of the email being a patch in UTF-8.
So this suggests a very natural change: if the target character set is
utf-8 (the default), and if the source already looks like utf-8, just
assume that it doesn't need any conversion at all.
Only assume that it needs conversion if it isn't already valid utf-8, in
which case we (for historical reasons) will assume it's Latin1.
Basically no really _valid_ latin1 will ever look like utf-8, so while
this changes our historical behaviour, it doesn't do so in practice, and
makes the default behaviour saner for the case where the input was already
in proper format.
We could do a more fancy guess, of course, but this correctly handled a
series of patches I just got from Andrew that had a mixture of Latin1 and
UTF-8 (in different emails, but without any character set indication).
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Junio C Hamano <gitster@pobox.com>
2007-07-17 19:34:44 +02:00
|
|
|
char *out;
|
|
|
|
|
|
|
|
if (!charset || !*charset) {
|
|
|
|
charset = guess_charset(line, metainfo_charset);
|
|
|
|
if (!charset)
|
|
|
|
return;
|
|
|
|
}
|
2006-12-24 08:36:55 +01:00
|
|
|
|
2007-07-24 02:03:26 +02:00
|
|
|
if (!strcmp(metainfo_charset, charset))
|
|
|
|
return;
|
Do a better job at guessing unknown character sets
At least in the kernel development community, we're generally slowly
converting to UTF-8 everywhere, and the old default of Latin1 in emails is
being supplanted by UTF-8, and it doesn't necessarily show up as such in
the mail headers (because, quite frankly, when people send patches
around, they want the email client to do as little as humanly possible
about the patch)
Despite that, it's often the case that email addresses etc still have
Latin1, so I've seen emails where this is a mixed bag, with Signed-off
parts being copied from email (and containing Latin1 characters), and the
rest of the email being a patch in UTF-8.
So this suggests a very natural change: if the target character set is
utf-8 (the default), and if the source already looks like utf-8, just
assume that it doesn't need any conversion at all.
Only assume that it needs conversion if it isn't already valid utf-8, in
which case we (for historical reasons) will assume it's Latin1.
Basically no really _valid_ latin1 will ever look like utf-8, so while
this changes our historical behaviour, it doesn't do so in practice, and
makes the default behaviour saner for the case where the input was already
in proper format.
We could do a more fancy guess, of course, but this correctly handled a
series of patches I just got from Andrew that had a mixture of Latin1 and
UTF-8 (in different emails, but without any character set indication).
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Junio C Hamano <gitster@pobox.com>
2007-07-17 19:34:44 +02:00
|
|
|
out = reencode_string(line, metainfo_charset, charset);
|
2007-01-10 06:31:36 +01:00
|
|
|
if (!out)
|
|
|
|
die("cannot convert from %s to %s\n",
|
Do a better job at guessing unknown character sets
At least in the kernel development community, we're generally slowly
converting to UTF-8 everywhere, and the old default of Latin1 in emails is
being supplanted by UTF-8, and it doesn't necessarily show up as such in
the mail headers (because, quite frankly, when people send patches
around, they want the email client to do as little as humanly possible
about the patch)
Despite that, it's often the case that email addresses etc still have
Latin1, so I've seen emails where this is a mixed bag, with Signed-off
parts being copied from email (and containing Latin1 characters), and the
rest of the email being a patch in UTF-8.
So this suggests a very natural change: if the target character set is
utf-8 (the default), and if the source already looks like utf-8, just
assume that it doesn't need any conversion at all.
Only assume that it needs conversion if it isn't already valid utf-8, in
which case we (for historical reasons) will assume it's Latin1.
Basically no really _valid_ latin1 will ever look like utf-8, so while
this changes our historical behaviour, it doesn't do so in practice, and
makes the default behaviour saner for the case where the input was already
in proper format.
We could do a more fancy guess, of course, but this correctly handled a
series of patches I just got from Andrew that had a mixture of Latin1 and
UTF-8 (in different emails, but without any character set indication).
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Junio C Hamano <gitster@pobox.com>
2007-07-17 19:34:44 +02:00
|
|
|
charset, metainfo_charset);
|
2007-08-30 23:48:24 +02:00
|
|
|
strlcpy(line, out, linesize);
|
2006-12-24 08:36:55 +01:00
|
|
|
free(out);
|
2005-08-28 21:33:16 +02:00
|
|
|
}
|
|
|
|
|
2007-08-30 23:48:24 +02:00
|
|
|
static int decode_header_bq(char *it, unsigned itsize)
|
2005-08-28 21:33:16 +02:00
|
|
|
{
|
|
|
|
char *in, *out, *ep, *cp, *sp;
|
|
|
|
char outbuf[1000];
|
2006-07-05 23:17:49 +02:00
|
|
|
int rfc2047 = 0;
|
2005-08-28 21:33:16 +02:00
|
|
|
|
|
|
|
in = it;
|
|
|
|
out = outbuf;
|
|
|
|
while ((ep = strstr(in, "=?")) != NULL) {
|
|
|
|
int sz, encoding;
|
|
|
|
char charset_q[256], piecebuf[256];
|
2006-07-05 23:17:49 +02:00
|
|
|
rfc2047 = 1;
|
|
|
|
|
2005-08-28 21:33:16 +02:00
|
|
|
if (in != ep) {
|
|
|
|
sz = ep - in;
|
|
|
|
memcpy(out, in, sz);
|
|
|
|
out += sz;
|
|
|
|
in += sz;
|
|
|
|
}
|
|
|
|
/* E.g.
|
|
|
|
* ep : "=?iso-2022-jp?B?GyR...?= foo"
|
|
|
|
* ep : "=?ISO-8859-1?Q?Foo=FCbar?= baz"
|
|
|
|
*/
|
|
|
|
ep += 2;
|
|
|
|
cp = strchr(ep, '?');
|
|
|
|
if (!cp)
|
2006-07-05 23:17:49 +02:00
|
|
|
return rfc2047; /* no munging */
|
2005-08-28 21:33:16 +02:00
|
|
|
for (sp = ep; sp < cp; sp++)
|
|
|
|
charset_q[sp - ep] = tolower(*sp);
|
|
|
|
charset_q[cp - ep] = 0;
|
|
|
|
encoding = cp[1];
|
|
|
|
if (!encoding || cp[2] != '?')
|
2006-07-05 23:17:49 +02:00
|
|
|
return rfc2047; /* no munging */
|
2005-08-28 21:33:16 +02:00
|
|
|
ep = strstr(cp + 3, "?=");
|
|
|
|
if (!ep)
|
2006-07-05 23:17:49 +02:00
|
|
|
return rfc2047; /* no munging */
|
2005-08-28 21:33:16 +02:00
|
|
|
switch (tolower(encoding)) {
|
|
|
|
default:
|
2006-07-05 23:17:49 +02:00
|
|
|
return rfc2047; /* no munging */
|
2005-08-28 21:33:16 +02:00
|
|
|
case 'b':
|
2007-08-30 23:48:24 +02:00
|
|
|
sz = decode_b_segment(cp + 3, piecebuf, sizeof(piecebuf), ep);
|
2005-08-28 21:33:16 +02:00
|
|
|
break;
|
|
|
|
case 'q':
|
2007-08-30 23:48:24 +02:00
|
|
|
sz = decode_q_segment(cp + 3, piecebuf, sizeof(piecebuf), ep, 1);
|
2005-08-28 21:33:16 +02:00
|
|
|
break;
|
|
|
|
}
|
|
|
|
if (sz < 0)
|
2006-07-05 23:17:49 +02:00
|
|
|
return rfc2047;
|
2005-11-28 01:22:16 +01:00
|
|
|
if (metainfo_charset)
|
2007-08-30 23:48:24 +02:00
|
|
|
convert_to_utf8(piecebuf, sizeof(piecebuf), charset_q);
|
|
|
|
|
|
|
|
sz = strlen(piecebuf);
|
|
|
|
if (outbuf + sizeof(outbuf) <= out + sz)
|
|
|
|
return rfc2047; /* no munging */
|
2005-08-28 21:33:16 +02:00
|
|
|
strcpy(out, piecebuf);
|
2007-08-30 23:48:24 +02:00
|
|
|
out += sz;
|
2005-08-28 21:33:16 +02:00
|
|
|
in = ep + 2;
|
|
|
|
}
|
|
|
|
strcpy(out, in);
|
2007-08-30 23:48:24 +02:00
|
|
|
strlcpy(it, outbuf, itsize);
|
2006-07-05 23:17:49 +02:00
|
|
|
return rfc2047;
|
|
|
|
}
|
|
|
|
|
2007-08-30 23:48:24 +02:00
|
|
|
static void decode_header(char *it, unsigned itsize)
|
2006-07-05 23:17:49 +02:00
|
|
|
{
|
|
|
|
|
2007-08-30 23:48:24 +02:00
|
|
|
if (decode_header_bq(it, itsize))
|
2006-07-05 23:17:49 +02:00
|
|
|
return;
|
|
|
|
/* otherwise "it" is a straight copy of the input.
|
|
|
|
* This can be binary guck but there is no charset specified.
|
|
|
|
*/
|
|
|
|
if (metainfo_charset)
|
2007-08-30 23:48:24 +02:00
|
|
|
convert_to_utf8(it, itsize, "");
|
2005-08-28 21:33:16 +02:00
|
|
|
}
|
|
|
|
|
2008-05-25 10:16:05 +02:00
|
|
|
static int decode_transfer_encoding(char *line, unsigned linesize, int inputlen)
|
2005-08-28 21:33:16 +02:00
|
|
|
{
|
|
|
|
char *ep;
|
|
|
|
|
|
|
|
switch (transfer_encoding) {
|
|
|
|
case TE_QP:
|
2008-05-25 10:16:05 +02:00
|
|
|
ep = line + inputlen;
|
|
|
|
return decode_q_segment(line, line, linesize, ep, 0);
|
2005-08-28 21:33:16 +02:00
|
|
|
case TE_BASE64:
|
2008-05-25 10:16:05 +02:00
|
|
|
ep = line + inputlen;
|
|
|
|
return decode_b_segment(line, line, linesize, ep);
|
2005-08-28 21:33:16 +02:00
|
|
|
case TE_DONTCARE:
|
2008-05-25 10:16:05 +02:00
|
|
|
default:
|
|
|
|
return inputlen;
|
2005-08-28 21:33:16 +02:00
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2008-05-16 15:03:30 +02:00
|
|
|
static int handle_filter(char *line, unsigned linesize, int linelen);
|
2007-03-12 20:52:04 +01:00
|
|
|
|
|
|
|
static int find_boundary(void)
|
2005-04-12 08:46:50 +02:00
|
|
|
{
|
2007-03-12 20:52:04 +01:00
|
|
|
while(fgets(line, sizeof(line), fin) != NULL) {
|
|
|
|
if (is_multipart_boundary(line))
|
|
|
|
return 1;
|
|
|
|
}
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
static int handle_boundary(void)
|
|
|
|
{
|
2007-03-30 18:18:45 +02:00
|
|
|
char newline[]="\n";
|
2007-03-12 20:52:04 +01:00
|
|
|
again:
|
|
|
|
if (!memcmp(line+content_top->boundary_len, "--", 2)) {
|
|
|
|
/* we hit an end boundary */
|
|
|
|
/* pop the current boundary off the stack */
|
|
|
|
free(content_top->boundary);
|
|
|
|
|
|
|
|
/* technically won't happen as is_multipart_boundary()
|
|
|
|
will fail first. But just in case..
|
|
|
|
*/
|
|
|
|
if (content_top-- < content) {
|
|
|
|
fprintf(stderr, "Detected mismatched boundaries, "
|
|
|
|
"can't recover\n");
|
|
|
|
exit(1);
|
|
|
|
}
|
2008-05-16 15:03:30 +02:00
|
|
|
handle_filter(newline, sizeof(newline), strlen(newline));
|
2007-03-12 20:52:04 +01:00
|
|
|
|
|
|
|
/* skip to the next boundary */
|
|
|
|
if (!find_boundary())
|
|
|
|
return 0;
|
|
|
|
goto again;
|
|
|
|
}
|
|
|
|
|
|
|
|
/* set some defaults */
|
|
|
|
transfer_encoding = TE_DONTCARE;
|
|
|
|
charset[0] = 0;
|
|
|
|
message_type = TYPE_TEXT;
|
2005-08-28 21:33:16 +02:00
|
|
|
|
2007-03-12 20:52:04 +01:00
|
|
|
/* slurp in this section's info */
|
|
|
|
while (read_one_header_line(line, sizeof(line), fin))
|
2007-08-30 23:48:24 +02:00
|
|
|
check_header(line, sizeof(line), p_hdr_data, 0);
|
2005-04-12 08:46:50 +02:00
|
|
|
|
2007-03-12 20:52:04 +01:00
|
|
|
/* eat the blank line after section info */
|
|
|
|
return (fgets(line, sizeof(line), fin) != NULL);
|
2005-08-28 21:33:16 +02:00
|
|
|
}
|
|
|
|
|
2007-03-12 20:52:06 +01:00
|
|
|
static inline int patchbreak(const char *line)
|
|
|
|
{
|
|
|
|
/* Beginning of a "diff -" header? */
|
|
|
|
if (!memcmp("diff -", line, 6))
|
|
|
|
return 1;
|
|
|
|
|
|
|
|
/* CVS "Index: " line? */
|
|
|
|
if (!memcmp("Index: ", line, 7))
|
|
|
|
return 1;
|
|
|
|
|
|
|
|
/*
|
|
|
|
* "--- <filename>" starts patches without headers
|
|
|
|
* "---<sp>*" is a manual separator
|
|
|
|
*/
|
|
|
|
if (!memcmp("---", line, 3)) {
|
|
|
|
line += 3;
|
|
|
|
/* space followed by a filename? */
|
|
|
|
if (line[0] == ' ' && !isspace(line[1]))
|
|
|
|
return 1;
|
|
|
|
/* Just whitespace? */
|
|
|
|
for (;;) {
|
|
|
|
unsigned char c = *line++;
|
|
|
|
if (c == '\n')
|
|
|
|
return 1;
|
|
|
|
if (!isspace(c))
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
|
2007-08-30 23:48:24 +02:00
|
|
|
static int handle_commit_msg(char *line, unsigned linesize)
|
2005-08-28 21:33:16 +02:00
|
|
|
{
|
2007-03-12 20:52:04 +01:00
|
|
|
static int still_looking = 1;
|
2007-08-30 23:48:24 +02:00
|
|
|
char *endline = line + linesize;
|
2007-03-12 20:52:04 +01:00
|
|
|
|
2005-08-28 21:33:16 +02:00
|
|
|
if (!cmitmsg)
|
|
|
|
return 0;
|
2005-04-12 08:46:50 +02:00
|
|
|
|
2007-03-12 20:52:04 +01:00
|
|
|
if (still_looking) {
|
|
|
|
char *cp = line;
|
|
|
|
if (isspace(*line)) {
|
|
|
|
for (cp = line + 1; *cp; cp++) {
|
|
|
|
if (!isspace(*cp))
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
if (!*cp)
|
|
|
|
return 0;
|
|
|
|
}
|
2007-08-30 23:48:24 +02:00
|
|
|
if ((still_looking = check_header(cp, endline - cp, s_hdr_data, 0)) != 0)
|
2007-03-12 20:52:04 +01:00
|
|
|
return 0;
|
|
|
|
}
|
2006-05-23 21:47:28 +02:00
|
|
|
|
2007-03-30 18:18:45 +02:00
|
|
|
/* normalize the log message to UTF-8. */
|
|
|
|
if (metainfo_charset)
|
2007-08-30 23:48:24 +02:00
|
|
|
convert_to_utf8(line, endline - line, charset);
|
2007-03-30 18:18:45 +02:00
|
|
|
|
2007-03-12 20:52:06 +01:00
|
|
|
if (patchbreak(line)) {
|
2007-03-12 20:52:04 +01:00
|
|
|
fclose(cmitmsg);
|
|
|
|
cmitmsg = NULL;
|
|
|
|
return 1;
|
|
|
|
}
|
2006-05-23 21:47:28 +02:00
|
|
|
|
2007-03-12 20:52:04 +01:00
|
|
|
fputs(line, cmitmsg);
|
2005-08-28 21:33:16 +02:00
|
|
|
return 0;
|
2005-04-12 08:46:50 +02:00
|
|
|
}
|
|
|
|
|
2008-05-16 15:03:30 +02:00
|
|
|
static int handle_patch(char *line, int len)
|
2005-04-12 08:46:50 +02:00
|
|
|
{
|
2008-05-16 15:03:30 +02:00
|
|
|
fwrite(line, 1, len, patchfile);
|
2007-03-12 20:52:04 +01:00
|
|
|
patch_lines++;
|
|
|
|
return 0;
|
2005-04-12 08:46:50 +02:00
|
|
|
}
|
|
|
|
|
2008-05-16 15:03:30 +02:00
|
|
|
static int handle_filter(char *line, unsigned linesize, int linelen)
|
2005-04-12 08:46:50 +02:00
|
|
|
{
|
2007-03-12 20:52:04 +01:00
|
|
|
static int filter = 0;
|
2005-04-12 08:46:50 +02:00
|
|
|
|
2007-03-12 20:52:04 +01:00
|
|
|
/* filter tells us which part we left off on
|
|
|
|
* a non-zero return indicates we hit a filter point
|
|
|
|
*/
|
|
|
|
switch (filter) {
|
|
|
|
case 0:
|
2007-08-30 23:48:24 +02:00
|
|
|
if (!handle_commit_msg(line, linesize))
|
2005-08-28 21:33:16 +02:00
|
|
|
break;
|
2007-03-12 20:52:04 +01:00
|
|
|
filter++;
|
|
|
|
case 1:
|
2008-05-16 15:03:30 +02:00
|
|
|
if (!handle_patch(line, linelen))
|
2007-03-12 20:52:04 +01:00
|
|
|
break;
|
|
|
|
filter++;
|
|
|
|
default:
|
|
|
|
return 1;
|
2005-04-12 08:46:50 +02:00
|
|
|
}
|
2007-03-12 20:52:04 +01:00
|
|
|
|
2005-08-28 21:33:16 +02:00
|
|
|
return 0;
|
2005-04-12 08:46:50 +02:00
|
|
|
}
|
|
|
|
|
2007-03-12 20:52:04 +01:00
|
|
|
static void handle_body(void)
|
2005-07-23 11:10:31 +02:00
|
|
|
{
|
2007-03-12 20:52:04 +01:00
|
|
|
int rc = 0;
|
|
|
|
static char newline[2000];
|
|
|
|
static char *np = newline;
|
2008-05-16 15:03:30 +02:00
|
|
|
int len = strlen(line);
|
2005-08-28 21:33:16 +02:00
|
|
|
|
|
|
|
/* Skip up to the first boundary */
|
2007-03-12 20:52:04 +01:00
|
|
|
if (content_top->boundary) {
|
|
|
|
if (!find_boundary())
|
|
|
|
return;
|
|
|
|
}
|
|
|
|
|
|
|
|
do {
|
|
|
|
/* process any boundary lines */
|
|
|
|
if (content_top->boundary && is_multipart_boundary(line)) {
|
|
|
|
/* flush any leftover */
|
2008-05-25 10:16:05 +02:00
|
|
|
if (np != newline)
|
2008-05-16 15:03:30 +02:00
|
|
|
handle_filter(newline, sizeof(newline),
|
2008-05-25 10:16:05 +02:00
|
|
|
np - newline);
|
2007-03-12 20:52:04 +01:00
|
|
|
if (!handle_boundary())
|
|
|
|
return;
|
2008-07-07 07:26:45 +02:00
|
|
|
len = strlen(line);
|
2007-03-12 20:52:04 +01:00
|
|
|
}
|
|
|
|
|
2007-03-30 18:18:45 +02:00
|
|
|
/* Unwrap transfer encoding */
|
2008-05-25 10:16:05 +02:00
|
|
|
len = decode_transfer_encoding(line, sizeof(line), len);
|
|
|
|
if (len < 0) {
|
|
|
|
error("Malformed input line");
|
|
|
|
return;
|
|
|
|
}
|
2007-03-12 20:52:04 +01:00
|
|
|
|
|
|
|
switch (transfer_encoding) {
|
|
|
|
case TE_BASE64:
|
2008-02-15 22:53:36 +01:00
|
|
|
case TE_QP:
|
2007-03-12 20:52:04 +01:00
|
|
|
{
|
|
|
|
char *op = line;
|
|
|
|
|
|
|
|
/* binary data most likely doesn't have newlines */
|
|
|
|
if (message_type != TYPE_TEXT) {
|
2008-05-16 15:03:30 +02:00
|
|
|
rc = handle_filter(line, sizeof(line), len);
|
2007-03-12 20:52:04 +01:00
|
|
|
break;
|
|
|
|
}
|
|
|
|
|
2008-05-25 10:16:05 +02:00
|
|
|
/*
|
|
|
|
* This is a decoded line that may contain
|
2007-03-12 20:52:04 +01:00
|
|
|
* multiple new lines. Pass only one chunk
|
|
|
|
* at a time to handle_filter()
|
|
|
|
*/
|
|
|
|
do {
|
2008-05-25 10:16:05 +02:00
|
|
|
while (op < line + len && *op != '\n')
|
2007-03-12 20:52:04 +01:00
|
|
|
*np++ = *op++;
|
|
|
|
*np = *op;
|
|
|
|
if (*np != 0) {
|
|
|
|
/* should be sitting on a new line */
|
|
|
|
*(++np) = 0;
|
|
|
|
op++;
|
2008-05-16 15:03:30 +02:00
|
|
|
rc = handle_filter(newline, sizeof(newline), np - newline);
|
2007-03-12 20:52:04 +01:00
|
|
|
np = newline;
|
|
|
|
}
|
2008-05-25 10:16:05 +02:00
|
|
|
} while (op < line + len);
|
|
|
|
/*
|
|
|
|
* The partial chunk is saved in newline and will be
|
|
|
|
* appended by the next iteration of read_line_with_nul().
|
2007-03-12 20:52:04 +01:00
|
|
|
*/
|
2005-08-28 21:33:16 +02:00
|
|
|
break;
|
2005-07-23 11:10:31 +02:00
|
|
|
}
|
2007-03-12 20:52:04 +01:00
|
|
|
default:
|
2008-05-16 15:03:30 +02:00
|
|
|
rc = handle_filter(line, sizeof(line), len);
|
2005-08-28 21:33:16 +02:00
|
|
|
}
|
2007-03-12 20:52:04 +01:00
|
|
|
if (rc)
|
|
|
|
/* nothing left to filter */
|
|
|
|
break;
|
2008-05-16 15:03:30 +02:00
|
|
|
} while ((len = read_line_with_nul(line, sizeof(line), fin)));
|
2007-03-12 20:52:04 +01:00
|
|
|
|
|
|
|
return;
|
2005-07-23 11:10:31 +02:00
|
|
|
}
|
|
|
|
|
2007-07-29 02:57:25 +02:00
|
|
|
static void output_header_lines(FILE *fout, const char *hdr, char *data)
|
|
|
|
{
|
|
|
|
while (1) {
|
|
|
|
char *ep = strchr(data, '\n');
|
|
|
|
int len;
|
|
|
|
if (!ep)
|
|
|
|
len = strlen(data);
|
|
|
|
else
|
|
|
|
len = ep - data;
|
|
|
|
fprintf(fout, "%s: %.*s\n", hdr, len, data);
|
|
|
|
if (!ep)
|
|
|
|
break;
|
|
|
|
data = ep + 1;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2007-03-12 20:52:04 +01:00
|
|
|
static void handle_info(void)
|
2005-04-12 08:46:50 +02:00
|
|
|
{
|
2007-03-12 20:52:04 +01:00
|
|
|
char *sub;
|
|
|
|
char *hdr;
|
|
|
|
int i;
|
|
|
|
|
|
|
|
for (i = 0; header[i]; i++) {
|
|
|
|
|
|
|
|
/* only print inbody headers if we output a patch file */
|
|
|
|
if (patch_lines && s_hdr_data[i])
|
|
|
|
hdr = s_hdr_data[i];
|
|
|
|
else if (p_hdr_data[i])
|
|
|
|
hdr = p_hdr_data[i];
|
|
|
|
else
|
|
|
|
continue;
|
|
|
|
|
|
|
|
if (!memcmp(header[i], "Subject", 7)) {
|
2007-07-29 02:57:25 +02:00
|
|
|
if (keep_subject)
|
|
|
|
sub = hdr;
|
|
|
|
else {
|
|
|
|
sub = cleanup_subject(hdr);
|
|
|
|
cleanup_space(sub);
|
|
|
|
}
|
|
|
|
output_header_lines(fout, "Subject", sub);
|
2007-03-12 20:52:04 +01:00
|
|
|
} else if (!memcmp(header[i], "From", 4)) {
|
|
|
|
handle_from(hdr);
|
|
|
|
fprintf(fout, "Author: %s\n", name);
|
|
|
|
fprintf(fout, "Email: %s\n", email);
|
|
|
|
} else {
|
|
|
|
cleanup_space(hdr);
|
|
|
|
fprintf(fout, "%s: %s\n", header[i], hdr);
|
|
|
|
}
|
2005-08-28 21:33:16 +02:00
|
|
|
}
|
2007-03-12 20:52:04 +01:00
|
|
|
fprintf(fout, "\n");
|
2005-04-12 08:46:50 +02:00
|
|
|
}
|
|
|
|
|
2007-06-08 11:22:56 +02:00
|
|
|
static int mailinfo(FILE *in, FILE *out, int ks, const char *encoding,
|
|
|
|
const char *msg, const char *patch)
|
2006-06-13 22:21:50 +02:00
|
|
|
{
|
2007-11-01 23:57:45 +01:00
|
|
|
int peek;
|
2006-06-13 22:21:50 +02:00
|
|
|
keep_subject = ks;
|
|
|
|
metainfo_charset = encoding;
|
|
|
|
fin = in;
|
|
|
|
fout = out;
|
|
|
|
|
|
|
|
cmitmsg = fopen(msg, "w");
|
|
|
|
if (!cmitmsg) {
|
|
|
|
perror(msg);
|
|
|
|
return -1;
|
|
|
|
}
|
|
|
|
patchfile = fopen(patch, "w");
|
|
|
|
if (!patchfile) {
|
|
|
|
perror(patch);
|
|
|
|
fclose(cmitmsg);
|
|
|
|
return -1;
|
|
|
|
}
|
2007-03-12 20:52:04 +01:00
|
|
|
|
|
|
|
p_hdr_data = xcalloc(MAX_HDR_PARSED, sizeof(char *));
|
|
|
|
s_hdr_data = xcalloc(MAX_HDR_PARSED, sizeof(char *));
|
|
|
|
|
2007-11-01 23:57:45 +01:00
|
|
|
do {
|
|
|
|
peek = fgetc(in);
|
|
|
|
} while (isspace(peek));
|
|
|
|
ungetc(peek, in);
|
|
|
|
|
2007-03-12 20:52:04 +01:00
|
|
|
/* process the email header */
|
|
|
|
while (read_one_header_line(line, sizeof(line), fin))
|
2007-08-30 23:48:24 +02:00
|
|
|
check_header(line, sizeof(line), p_hdr_data, 1);
|
2007-03-12 20:52:04 +01:00
|
|
|
|
|
|
|
handle_body();
|
|
|
|
handle_info();
|
2006-06-13 22:21:50 +02:00
|
|
|
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
2005-08-17 07:18:27 +02:00
|
|
|
static const char mailinfo_usage[] =
|
2008-07-10 23:36:28 +02:00
|
|
|
"git-mailinfo [-k] [-u | --encoding=<encoding> | -n] msg patch <mail >info";
|
2005-08-28 21:33:16 +02:00
|
|
|
|
2006-07-29 07:44:25 +02:00
|
|
|
int cmd_mailinfo(int argc, const char **argv, const char *prefix)
|
2005-04-12 08:46:50 +02:00
|
|
|
{
|
2007-01-10 06:31:36 +01:00
|
|
|
const char *def_charset;
|
|
|
|
|
2005-11-28 01:29:38 +01:00
|
|
|
/* NEEDSWORK: might want to do the optional .git/ directory
|
|
|
|
* discovery
|
|
|
|
*/
|
2008-05-14 19:46:53 +02:00
|
|
|
git_config(git_default_config, NULL);
|
2005-11-28 01:29:38 +01:00
|
|
|
|
2007-01-10 06:31:36 +01:00
|
|
|
def_charset = (git_commit_encoding ? git_commit_encoding : "utf-8");
|
|
|
|
metainfo_charset = def_charset;
|
|
|
|
|
2005-08-17 07:18:27 +02:00
|
|
|
while (1 < argc && argv[1][0] == '-') {
|
|
|
|
if (!strcmp(argv[1], "-k"))
|
|
|
|
keep_subject = 1;
|
2005-08-28 21:33:16 +02:00
|
|
|
else if (!strcmp(argv[1], "-u"))
|
2007-01-10 06:31:36 +01:00
|
|
|
metainfo_charset = def_charset;
|
|
|
|
else if (!strcmp(argv[1], "-n"))
|
|
|
|
metainfo_charset = NULL;
|
Mechanical conversion to use prefixcmp()
This mechanically converts strncmp() to use prefixcmp(), but only when
the parameters match specific patterns, so that they can be verified
easily. Leftover from this will be fixed in a separate step, including
idiotic conversions like
if (!strncmp("foo", arg, 3))
=>
if (!(-prefixcmp(arg, "foo")))
This was done by using this script in px.perl
#!/usr/bin/perl -i.bak -p
if (/strncmp\(([^,]+), "([^\\"]*)", (\d+)\)/ && (length($2) == $3)) {
s|strncmp\(([^,]+), "([^\\"]*)", (\d+)\)|prefixcmp($1, "$2")|;
}
if (/strncmp\("([^\\"]*)", ([^,]+), (\d+)\)/ && (length($1) == $3)) {
s|strncmp\("([^\\"]*)", ([^,]+), (\d+)\)|(-prefixcmp($2, "$1"))|;
}
and running:
$ git grep -l strncmp -- '*.c' | xargs perl px.perl
Signed-off-by: Junio C Hamano <junkio@cox.net>
2007-02-20 10:53:29 +01:00
|
|
|
else if (!prefixcmp(argv[1], "--encoding="))
|
2005-11-28 10:29:52 +01:00
|
|
|
metainfo_charset = argv[1] + 11;
|
2005-08-28 21:33:16 +02:00
|
|
|
else
|
2005-11-28 01:29:38 +01:00
|
|
|
usage(mailinfo_usage);
|
2005-08-17 07:18:27 +02:00
|
|
|
argc--; argv++;
|
|
|
|
}
|
|
|
|
|
2005-06-23 18:40:23 +02:00
|
|
|
if (argc != 3)
|
2005-11-28 01:29:38 +01:00
|
|
|
usage(mailinfo_usage);
|
2006-06-13 22:21:50 +02:00
|
|
|
|
|
|
|
return !!mailinfo(stdin, stdout, keep_subject, metainfo_charset, argv[1], argv[2]);
|
2005-04-12 08:46:50 +02:00
|
|
|
}
|