-/*
- * Another stupid program, this one parsing the headers of an
- * email to figure out authorship and subject
- */
-#define _GNU_SOURCE
-#include <stdio.h>
-#include <stdlib.h>
-#include <string.h>
-#include <ctype.h>
-#ifndef NO_ICONV
-#include <iconv.h>
-#endif
-#include "git-compat-util.h"
#include "cache.h"
+#include "utf8.h"
+#include "strbuf.h"
+#include "mailinfo.h"
-static FILE *cmitmsg, *patchfile;
-
-static int keep_subject = 0;
-static char *metainfo_charset = NULL;
-static char line[1000];
-static char date[1000];
-static char name[1000];
-static char email[1000];
-static char subject[1000];
-
-static enum {
- TE_DONTCARE, TE_QP, TE_BASE64,
-} transfer_encoding;
-static char charset[256];
-
-static char multipart_boundary[1000];
-static int multipart_boundary_len;
-static int patch_lines = 0;
+static void cleanup_space(struct strbuf *sb)
+{
+ size_t pos, cnt;
+ for (pos = 0; pos < sb->len; pos++) {
+ if (isspace(sb->buf[pos])) {
+ sb->buf[pos] = ' ';
+ for (cnt = 0; isspace(sb->buf[pos + cnt + 1]); cnt++);
+ strbuf_remove(sb, pos + 1, cnt);
+ }
+ }
+}
-static char *sanity_check(char *name, char *email)
+static void get_sane_name(struct strbuf *out, struct strbuf *name, struct strbuf *email)
{
- int len = strlen(name);
- if (len < 3 || len > 60)
- return email;
- if (strchr(name, '@') || strchr(name, '<') || strchr(name, '>'))
- return email;
- return name;
+ struct strbuf *src = name;
+ if (name->len < 3 || 60 < name->len || strchr(name->buf, '@') ||
+ strchr(name->buf, '<') || strchr(name->buf, '>'))
+ src = email;
+ else if (name == out)
+ return;
+ strbuf_reset(out);
+ strbuf_addbuf(out, src);
}
-static int bogus_from(char *line)
+static void parse_bogus_from(struct mailinfo *mi, const struct strbuf *line)
{
/* John Doe <johndoe> */
- char *bra, *ket, *dst, *cp;
+ char *bra, *ket;
/* This is fallback, so do not bother if we already have an
* e-mail address.
- */
- if (*email)
- return 0;
+ */
+ if (mi->email.len)
+ return;
- bra = strchr(line, '<');
+ bra = strchr(line->buf, '<');
if (!bra)
- return 0;
+ return;
ket = strchr(bra, '>');
if (!ket)
- return 0;
+ return;
- 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;
+ strbuf_reset(&mi->email);
+ strbuf_add(&mi->email, bra + 1, ket - bra - 1);
+
+ strbuf_reset(&mi->name);
+ strbuf_add(&mi->name, line->buf, bra - line->buf);
+ strbuf_trim(&mi->name);
+ get_sane_name(&mi->name, &mi->name, &mi->email);
}
-static int handle_from(char *in_line)
+static void handle_from(struct mailinfo *mi, const struct strbuf *from)
{
- char line[1000];
char *at;
- char *dst;
+ size_t el;
+ struct strbuf f;
- strcpy(line, in_line);
- at = strchr(line, '@');
- if (!at)
- return bogus_from(line);
+ strbuf_init(&f, from->len);
+ strbuf_addbuf(&f, from);
+
+ at = strchr(f.buf, '@');
+ if (!at) {
+ parse_bogus_from(mi, from);
+ return;
+ }
/*
* If we already have one email, don't take any confusing lines
*/
- if (*email && strchr(at+1, '@'))
- return 0;
+ if (mi->email.len && strchr(at + 1, '@')) {
+ strbuf_release(&f);
+ return;
+ }
/* Pick up the string around '@', possibly delimited with <>
- * pair; that is the email part. White them out while copying.
+ * pair; that is the email part.
*/
- while (at > line) {
+ while (at > f.buf) {
char c = at[-1];
if (isspace(c))
break;
}
at--;
}
- dst = email;
- for (;;) {
- unsigned char c = *at;
- if (!c || c == '>' || isspace(c)) {
- if (c == '>')
- *at = ' ';
- break;
- }
- *at++ = ' ';
- *dst++ = c;
- }
- *dst++ = 0;
+ el = strcspn(at, " \n\t\r\v\f>");
+ strbuf_reset(&mi->email);
+ strbuf_add(&mi->email, at, el);
+ 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 whited out 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').
*/
- at = line + strlen(line);
- while (at > line) {
- unsigned char c = *--at;
- if (!isspace(c)) {
- at[(c == ')') ? 0 : 1] = 0;
- break;
- }
+ cleanup_space(&f);
+ strbuf_trim(&f);
+ if (f.buf[0] == '(' && f.len && f.buf[f.len - 1] == ')') {
+ strbuf_remove(&f, 0, 1);
+ strbuf_setlen(&f, f.len - 1);
}
- at = line;
- for (;;) {
- unsigned char c = *at;
- if (!c || !isspace(c)) {
- if (c == '(')
- at++;
- break;
- }
- at++;
- }
- at = sanity_check(at, email);
- strcpy(name, at);
- return 1;
+ get_sane_name(&mi->name, &f, &mi->email);
+ strbuf_release(&f);
}
-static int handle_date(char *line)
+static void handle_header(struct strbuf **out, const struct strbuf *line)
{
- strcpy(date, line);
- return 0;
-}
+ if (!*out) {
+ *out = xmalloc(sizeof(struct strbuf));
+ strbuf_init(*out, line->len);
+ } else
+ strbuf_reset(*out);
-static int handle_subject(char *line)
-{
- strcpy(subject, line);
- return 0;
+ strbuf_addbuf(*out, line);
}
/* NOTE NOTE NOTE. We do not claim we do full MIME. We just attempt
* case insensitively.
*/
-static int slurp_attr(const char *line, const char *name, char *attr)
+static int slurp_attr(const char *line, const char *name, struct strbuf *attr)
{
- char *ends, *ap = strcasestr(line, name);
+ const char *ends, *ap = strcasestr(line, name);
size_t sz;
- if (!ap) {
- *attr = 0;
+ strbuf_setlen(attr, 0);
+ if (!ap)
return 0;
- }
ap += strlen(name);
if (*ap == '"') {
ap++;
else
ends = "; \t";
sz = strcspn(ap, ends);
- memcpy(attr, ap, sz);
- attr[sz] = 0;
+ strbuf_add(attr, ap, sz);
return 1;
}
-static int handle_subcontent_type(char *line)
+static void handle_content_type(struct mailinfo *mi, struct strbuf *line)
{
- /* We do not want to mess with boundary. Note that we do not
- * handle nested multipart.
- */
- if (strcasestr(line, "boundary=")) {
- fprintf(stderr, "Not handling nested multipart message.\n");
- exit(1);
+ struct strbuf *boundary = xmalloc(sizeof(struct strbuf));
+ strbuf_init(boundary, line->len);
+
+ if (slurp_attr(line->buf, "boundary=", boundary)) {
+ strbuf_insert(boundary, 0, "--", 2);
+ if (++mi->content_top >= &mi->content[MAX_BOUNDARIES]) {
+ error("Too many boundaries to handle");
+ mi->input_error = -1;
+ mi->content_top = &mi->content[MAX_BOUNDARIES] - 1;
+ return;
+ }
+ *(mi->content_top) = boundary;
+ boundary = NULL;
}
- slurp_attr(line, "charset=", charset);
- if (*charset) {
- int i, c;
- for (i = 0; (c = charset[i]) != 0; i++)
- charset[i] = tolower(c);
+ slurp_attr(line->buf, "charset=", &mi->charset);
+
+ if (boundary) {
+ strbuf_release(boundary);
+ free(boundary);
}
- return 0;
}
-static int handle_content_type(char *line)
+static void handle_message_id(struct mailinfo *mi, const struct strbuf *line)
{
- *multipart_boundary = 0;
- if (slurp_attr(line, "boundary=", multipart_boundary + 2)) {
- memcpy(multipart_boundary, "--", 2);
- multipart_boundary_len = strlen(multipart_boundary);
- }
- slurp_attr(line, "charset=", charset);
- return 0;
+ if (mi->add_message_id)
+ mi->message_id = strdup(line->buf);
}
-static int handle_content_transfer_encoding(char *line)
+static void handle_content_transfer_encoding(struct mailinfo *mi,
+ const struct strbuf *line)
{
- if (strcasestr(line, "base64"))
- transfer_encoding = TE_BASE64;
- else if (strcasestr(line, "quoted-printable"))
- transfer_encoding = TE_QP;
+ if (strcasestr(line->buf, "base64"))
+ mi->transfer_encoding = TE_BASE64;
+ else if (strcasestr(line->buf, "quoted-printable"))
+ mi->transfer_encoding = TE_QP;
else
- transfer_encoding = TE_DONTCARE;
- return 0;
+ mi->transfer_encoding = TE_DONTCARE;
}
-static int is_multipart_boundary(const char *line)
+static int is_multipart_boundary(struct mailinfo *mi, const struct strbuf *line)
{
- return (!memcmp(line, multipart_boundary, multipart_boundary_len));
-}
+ struct strbuf *content_top = *(mi->content_top);
-static int eatspace(char *line)
-{
- int len = strlen(line);
- while (len > 0 && isspace(line[len-1]))
- line[--len] = 0;
- return len;
+ return ((content_top->len <= line->len) &&
+ !memcmp(line->buf, content_top->buf, content_top->len));
}
-#define SEEN_FROM 01
-#define SEEN_DATE 02
-#define SEEN_SUBJECT 04
-#define SEEN_BOGUS_UNIX_FROM 010
-#define SEEN_PREFIX 020
-
-/* First lines of body can have From:, Date:, and Subject: or empty */
-static void handle_inbody_header(int *seen, char *line)
+static void cleanup_subject(struct mailinfo *mi, struct strbuf *subject)
{
- if (*seen & SEEN_PREFIX)
- return;
- if (isspace(*line)) {
- char *cp;
- for (cp = line + 1; *cp; cp++) {
- if (!isspace(*cp))
- break;
- }
- if (!*cp)
- return;
- }
- if (!memcmp(">From", line, 5) && isspace(line[5])) {
- if (!(*seen & SEEN_BOGUS_UNIX_FROM)) {
- *seen |= SEEN_BOGUS_UNIX_FROM;
- return;
- }
- }
- if (!memcmp("From:", line, 5) && isspace(line[5])) {
- if (!(*seen & SEEN_FROM) && handle_from(line+6)) {
- *seen |= SEEN_FROM;
- return;
- }
- }
- if (!memcmp("Date:", line, 5) && isspace(line[5])) {
- if (!(*seen & SEEN_DATE)) {
- handle_date(line+6);
- *seen |= SEEN_DATE;
- return;
- }
- }
- if (!memcmp("Subject:", line, 8) && isspace(line[8])) {
- if (!(*seen & SEEN_SUBJECT)) {
- handle_subject(line+9);
- *seen |= SEEN_SUBJECT;
- return;
- }
- }
- if (!memcmp("[PATCH]", line, 7) && isspace(line[7])) {
- if (!(*seen & SEEN_SUBJECT)) {
- handle_subject(line);
- *seen |= SEEN_SUBJECT;
- return;
- }
- }
- *seen |= SEEN_PREFIX;
-}
+ size_t at = 0;
-static char *cleanup_subject(char *subject)
-{
- if (keep_subject)
- return subject;
- for (;;) {
- char *p;
- int len, remove;
- switch (*subject) {
+ while (at < subject->len) {
+ char *pos;
+ size_t remove;
+
+ switch (subject->buf[at]) {
case 'r': case 'R':
- if (!memcmp("e:", subject+1, 2)) {
- subject +=3;
+ if (subject->len <= at + 3)
+ break;
+ if ((subject->buf[at + 1] == 'e' ||
+ subject->buf[at + 1] == 'E') &&
+ subject->buf[at + 2] == ':') {
+ strbuf_remove(subject, at, 3);
continue;
}
+ at++;
break;
case ' ': case '\t': case ':':
- subject++;
+ strbuf_remove(subject, at, 1);
continue;
-
case '[':
- p = strchr(subject, ']');
- if (!p) {
- subject++;
- continue;
- }
- len = strlen(p);
- remove = p - subject;
- if (remove <= len *2) {
- subject = p+1;
- continue;
- }
- break;
- }
- eatspace(subject);
- return subject;
- }
-}
-
-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;
+ pos = strchr(subject->buf + at, ']');
+ if (!pos)
+ break;
+ remove = pos - subject->buf + at + 1;
+ if (!mi->keep_non_patch_brackets_in_subject ||
+ (7 <= remove &&
+ memmem(subject->buf + at, remove, "PATCH", 5)))
+ strbuf_remove(subject, at, remove);
+ 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;
}
+ strbuf_trim(subject);
}
-static void decode_header_bq(char *it);
-typedef int (*header_fn_t)(char *);
-struct header_def {
- const char *name;
- header_fn_t func;
- int namelen;
+#define MAX_HDR_PARSED 10
+static const char *header[MAX_HDR_PARSED] = {
+ "From","Subject","Date",
};
-static void check_header(char *line, struct header_def *header)
+static inline int cmp_header(const struct strbuf *line, const char *hdr)
{
- int i;
-
- if (header[0].namelen <= 0) {
- for (i = 0; header[i].name; i++)
- header[i].namelen = strlen(header[i].name);
- }
- for (i = 0; header[i].name; i++) {
- int len = header[i].namelen;
- if (!strncasecmp(line, header[i].name, len) &&
- line[len] == ':' && isspace(line[len + 1])) {
- /* Unwrap inline B and Q encoding, and optionally
- * normalize the meta information to utf8.
- */
- decode_header_bq(line + len + 2);
- header[i].func(line + len + 2);
- break;
- }
- }
-}
-
-static void check_subheader_line(char *line)
-{
- static struct header_def header[] = {
- { "Content-Type", handle_subcontent_type },
- { "Content-Transfer-Encoding",
- handle_content_transfer_encoding },
- { NULL },
- };
- check_header(line, header);
-}
-static void check_header_line(char *line)
-{
- static struct header_def header[] = {
- { "From", handle_from },
- { "Date", handle_date },
- { "Subject", handle_subject },
- { "Content-Type", handle_content_type },
- { "Content-Transfer-Encoding",
- handle_content_transfer_encoding },
- { NULL },
- };
- check_header(line, header);
-}
-
-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;
- while ((ch = *cp++)) {
- if (ch == ':')
- return cp != line;
- if ((33 <= ch && ch <= 57) ||
- (59 <= ch && ch <= 126))
- continue;
- break;
- }
- return 0;
+ int len = strlen(hdr);
+ return !strncasecmp(line->buf, hdr, len) && line->len > len &&
+ line->buf[len] == ':' && isspace(line->buf[len + 1]);
}
-static int read_one_header_line(char *line, int sz, FILE *in)
+static int is_format_patch_separator(const char *line, int len)
{
- int ofs = 0;
- while (ofs < sz) {
- int peek, len;
- if (fgets(line + ofs, sz - ofs, in) == NULL)
- break;
- len = eatspace(line + ofs);
- if ((len == 0) || !is_rfc2822_header(line)) {
- /* Re-add the newline */
- line[ofs + len] = '\n';
- line[ofs + len + 1] = '\0';
- break;
- }
- ofs += len;
- /* Yuck, 2822 header "folding" */
- peek = fgetc(in); ungetc(peek, in);
- if (peek != ' ' && peek != '\t')
- break;
- }
- /* Count mbox From headers as headers */
- if (!ofs && !memcmp(line, "From ", 5))
- ofs = 1;
- return ofs;
-}
+ static const char SAMPLE[] =
+ "From e6807f3efca28b30decfecb1732a56c7db1137ee Mon Sep 17 00:00:00 2001\n";
+ const char *cp;
-static unsigned hexval(int c)
-{
- if (c >= '0' && c <= '9')
- return c - '0';
- if (c >= 'a' && c <= 'f')
- return c - 'a' + 10;
- if (c >= 'A' && c <= 'F')
- return c - 'A' + 10;
- return ~0;
+ 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 decode_q_segment(char *in, char *ot, char *ep, int rfc2047)
+static struct strbuf *decode_q_segment(const struct strbuf *q_seg, int rfc2047)
{
+ const char *in = q_seg->buf;
int c;
- while ((c = *in++) != 0 && (in <= ep)) {
+ struct strbuf *out = xmalloc(sizeof(struct strbuf));
+ strbuf_init(out, q_seg->len);
+
+ while ((c = *in++) != 0) {
if (c == '=') {
int d = *in++;
if (d == '\n' || !d)
break; /* drop trailing newline */
- *ot++ = ((hexval(d) << 4) | hexval(*in++));
+ strbuf_addch(out, (hexval(d) << 4) | hexval(*in++));
continue;
}
if (rfc2047 && c == '_') /* rfc2047 4.2 (2) */
c = 0x20;
- *ot++ = c;
+ strbuf_addch(out, c);
}
- *ot = 0;
- return 0;
+ return out;
}
-static int decode_b_segment(char *in, char *ot, char *ep)
+static struct strbuf *decode_b_segment(const struct strbuf *b_seg)
{
/* Decode in..ep, possibly in-place to ot */
int c, pos = 0, acc = 0;
+ const char *in = b_seg->buf;
+ struct strbuf *out = xmalloc(sizeof(struct strbuf));
+ strbuf_init(out, b_seg->len);
- while ((c = *in++) != 0 && (in <= ep)) {
+ while ((c = *in++) != 0) {
if (c == '+')
c = 62;
else if (c == '/')
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++) {
acc = (c << 2);
break;
case 1:
- *ot++ = (acc | (c >> 4));
+ strbuf_addch(out, (acc | (c >> 4)));
acc = (c & 15) << 4;
break;
case 2:
- *ot++ = (acc | (c >> 2));
+ strbuf_addch(out, (acc | (c >> 2)));
acc = (c & 3) << 6;
break;
case 3:
- *ot++ = (acc | c);
+ strbuf_addch(out, (acc | c));
acc = pos = 0;
break;
}
}
- *ot = 0;
- return 0;
+ return out;
}
-static void convert_to_utf8(char *line, char *charset)
+static int convert_to_utf8(struct mailinfo *mi,
+ struct strbuf *line, const char *charset)
{
-#ifndef NO_ICONV
- char *in, *out;
- size_t insize, outsize, nrc;
- char outbuf[4096]; /* cheat */
- static char latin_one[] = "latin1";
- char *input_charset = *charset ? charset : latin_one;
- iconv_t conv = iconv_open(metainfo_charset, input_charset);
+ char *out;
- if (conv == (iconv_t) -1) {
- static int warned_latin1_once = 0;
- if (input_charset != latin_one) {
- fprintf(stderr, "cannot convert from %s to %s\n",
- input_charset, metainfo_charset);
- *charset = 0;
- }
- else if (!warned_latin1_once) {
- warned_latin1_once = 1;
- fprintf(stderr, "tried to convert from %s to %s, "
- "but your iconv does not work with it.\n",
- input_charset, metainfo_charset);
- }
- return;
+ if (!mi->metainfo_charset || !charset || !*charset)
+ return 0;
+
+ if (same_encoding(mi->metainfo_charset, charset))
+ return 0;
+ out = reencode_string(line->buf, mi->metainfo_charset, charset);
+ if (!out) {
+ mi->input_error = -1;
+ return error("cannot convert from %s to %s",
+ charset, mi->metainfo_charset);
}
- in = line;
- insize = strlen(in);
- out = outbuf;
- outsize = sizeof(outbuf);
- nrc = iconv(conv, &in, &insize, &out, &outsize);
- iconv_close(conv);
- if (nrc == (size_t) -1)
- return;
- *out = 0;
- strcpy(line, outbuf);
-#endif
+ strbuf_attach(line, out, strlen(out), strlen(out));
+ return 0;
}
-static void decode_header_bq(char *it)
+static void decode_header(struct mailinfo *mi, struct strbuf *it)
{
- char *in, *out, *ep, *cp, *sp;
- char outbuf[1000];
+ char *in, *ep, *cp;
+ struct strbuf outbuf = STRBUF_INIT, *dec;
+ struct strbuf charset_q = STRBUF_INIT, piecebuf = STRBUF_INIT;
+ int found_error = 1; /* pessimism */
+
+ in = it->buf;
+ while (in - it->buf <= it->len && (ep = strstr(in, "=?")) != NULL) {
+ int encoding;
+ strbuf_reset(&charset_q);
+ strbuf_reset(&piecebuf);
- in = it;
- out = outbuf;
- while ((ep = strstr(in, "=?")) != NULL) {
- int sz, encoding;
- char charset_q[256], piecebuf[256];
if (in != ep) {
- sz = ep - in;
- memcpy(out, in, sz);
- out += sz;
- in += sz;
+ /*
+ * 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"
* ep : "=?ISO-8859-1?Q?Foo=FCbar?= baz"
*/
ep += 2;
- cp = strchr(ep, '?');
- if (!cp)
- return; /* no munging */
- for (sp = ep; sp < cp; sp++)
- charset_q[sp - ep] = tolower(*sp);
- charset_q[cp - ep] = 0;
+
+ if (ep - it->buf >= it->len || !(cp = strchr(ep, '?')))
+ goto release_return;
+
+ if (cp + 3 - it->buf > it->len)
+ goto release_return;
+ strbuf_add(&charset_q, ep, cp - ep);
+
encoding = cp[1];
if (!encoding || cp[2] != '?')
- return; /* no munging */
+ goto release_return;
ep = strstr(cp + 3, "?=");
if (!ep)
- return; /* no munging */
+ goto release_return;
+ strbuf_add(&piecebuf, cp + 3, ep - cp - 3);
switch (tolower(encoding)) {
default:
- return; /* no munging */
+ goto release_return;
case 'b':
- sz = decode_b_segment(cp + 3, piecebuf, ep);
+ dec = decode_b_segment(&piecebuf);
break;
case 'q':
- sz = decode_q_segment(cp + 3, piecebuf, ep, 1);
+ dec = decode_q_segment(&piecebuf, 1);
break;
}
- if (sz < 0)
- return;
- if (metainfo_charset)
- convert_to_utf8(piecebuf, charset_q);
- strcpy(out, piecebuf);
- out += strlen(out);
+ if (convert_to_utf8(mi, dec, charset_q.buf))
+ goto release_return;
+
+ strbuf_addbuf(&outbuf, dec);
+ strbuf_release(dec);
+ free(dec);
in = ep + 2;
}
- strcpy(out, in);
- strcpy(it, outbuf);
+ strbuf_addstr(&outbuf, in);
+ strbuf_reset(it);
+ strbuf_addbuf(it, &outbuf);
+ found_error = 0;
+release_return:
+ strbuf_release(&outbuf);
+ strbuf_release(&charset_q);
+ strbuf_release(&piecebuf);
+
+ if (found_error)
+ mi->input_error = -1;
+}
+
+static int check_header(struct mailinfo *mi,
+ const struct strbuf *line,
+ struct strbuf *hdr_data[], int overwrite)
+{
+ int i, ret = 0, len;
+ struct strbuf sb = STRBUF_INIT;
+
+ /* search for the interesting parts */
+ for (i = 0; header[i]; i++) {
+ int len = strlen(header[i]);
+ if ((!hdr_data[i] || overwrite) && cmp_header(line, header[i])) {
+ /* Unwrap inline B and Q encoding, and optionally
+ * normalize the meta information to utf8.
+ */
+ strbuf_add(&sb, line->buf + len + 2, line->len - len - 2);
+ decode_header(mi, &sb);
+ handle_header(&hdr_data[i], &sb);
+ ret = 1;
+ goto check_header_out;
+ }
+ }
+
+ /* Content stuff */
+ if (cmp_header(line, "Content-Type")) {
+ len = strlen("Content-Type: ");
+ strbuf_add(&sb, line->buf + len, line->len - len);
+ decode_header(mi, &sb);
+ strbuf_insert(&sb, 0, "Content-Type: ", len);
+ handle_content_type(mi, &sb);
+ ret = 1;
+ goto check_header_out;
+ }
+ if (cmp_header(line, "Content-Transfer-Encoding")) {
+ len = strlen("Content-Transfer-Encoding: ");
+ strbuf_add(&sb, line->buf + len, line->len - len);
+ decode_header(mi, &sb);
+ handle_content_transfer_encoding(mi, &sb);
+ 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(mi, &sb);
+ handle_message_id(mi, &sb);
+ ret = 1;
+ goto check_header_out;
+ }
+
+ /* for inbody stuff */
+ 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 (starts_with(line->buf, "[PATCH]") && isspace(line->buf[7])) {
+ for (i = 0; header[i]; i++) {
+ if (!strcmp("Subject", header[i])) {
+ handle_header(&hdr_data[i], line);
+ ret = 1;
+ goto check_header_out;
+ }
+ }
+ }
+
+check_header_out:
+ strbuf_release(&sb);
+ return ret;
}
-static void decode_transfer_encoding(char *line)
+static void decode_transfer_encoding(struct mailinfo *mi, struct strbuf *line)
{
- char *ep;
+ struct strbuf *ret;
- switch (transfer_encoding) {
+ switch (mi->transfer_encoding) {
case TE_QP:
- ep = line + strlen(line);
- decode_q_segment(line, line, ep, 0);
+ ret = decode_q_segment(line, 0);
break;
case TE_BASE64:
- ep = line + strlen(line);
- decode_b_segment(line, line, ep);
+ ret = decode_b_segment(line);
break;
case TE_DONTCARE:
- break;
+ default:
+ return;
}
+ strbuf_reset(line);
+ strbuf_addbuf(line, ret);
+ strbuf_release(ret);
+ free(ret);
}
-static void handle_info(void)
+static inline int patchbreak(const struct strbuf *line)
{
- char *sub;
+ size_t i;
- sub = cleanup_subject(subject);
- cleanup_space(name);
- cleanup_space(date);
- cleanup_space(email);
- cleanup_space(sub);
+ /* Beginning of a "diff -" header? */
+ if (starts_with(line->buf, "diff -"))
+ return 1;
- printf("Author: %s\nEmail: %s\nSubject: %s\nDate: %s\n\n",
- name, email, sub, date);
-}
+ /* CVS "Index: " line? */
+ if (starts_with(line->buf, "Index: "))
+ return 1;
-/* We are inside message body and have read line[] already.
- * Spit out the commit log.
- */
-static int handle_commit_msg(int *seen)
-{
- if (!cmitmsg)
+ /*
+ * "--- <filename>" starts patches without headers
+ * "---<sp>*" is a manual separator
+ */
+ if (line->len < 4)
return 0;
- do {
- if (!memcmp("diff -", line, 6) ||
- !memcmp("---", line, 3) ||
- !memcmp("Index: ", line, 7))
- break;
- if ((multipart_boundary[0] && is_multipart_boundary(line))) {
- /* We come here when the first part had only
- * the commit message without any patch. We
- * pretend we have not seen this line yet, and
- * go back to the loop.
- */
+
+ if (starts_with(line->buf, "---")) {
+ /* space followed by a filename? */
+ if (line->buf[3] == ' ' && !isspace(line->buf[4]))
return 1;
+ /* Just whitespace? */
+ for (i = 3; i < line->len; i++) {
+ unsigned char c = line->buf[i];
+ if (c == '\n')
+ return 1;
+ if (!isspace(c))
+ break;
+ }
+ return 0;
+ }
+ return 0;
+}
+
+static int is_scissors_line(const struct strbuf *line)
+{
+ size_t i, len = line->len;
+ int scissors = 0, gap = 0;
+ int first_nonblank = -1;
+ int last_nonblank = 0, visible, perforation = 0, in_perforation = 0;
+ const char *buf = line->buf;
+
+ for (i = 0; i < len; i++) {
+ if (isspace(buf[i])) {
+ if (in_perforation) {
+ perforation++;
+ gap++;
+ }
+ continue;
+ }
+ last_nonblank = i;
+ if (first_nonblank < 0)
+ first_nonblank = i;
+ if (buf[i] == '-') {
+ in_perforation = 1;
+ perforation++;
+ continue;
}
+ if (i + 1 < len &&
+ (!memcmp(buf + i, ">8", 2) || !memcmp(buf + i, "8<", 2) ||
+ !memcmp(buf + i, ">%", 2) || !memcmp(buf + i, "%<", 2))) {
+ in_perforation = 1;
+ perforation += 2;
+ scissors += 2;
+ i++;
+ continue;
+ }
+ in_perforation = 0;
+ }
+
+ /*
+ * The mark must be at least 8 bytes long (e.g. "-- >8 --").
+ * Even though there can be arbitrary cruft on the same line
+ * (e.g. "cut here"), in order to avoid misidentification, the
+ * perforation must occupy more than a third of the visible
+ * width of the line, and dashes and scissors must occupy more
+ * than half of the perforation.
+ */
+
+ visible = last_nonblank - first_nonblank + 1;
+ return (scissors && 8 <= visible &&
+ visible < perforation * 3 &&
+ gap * 2 < perforation);
+}
+
+static int handle_commit_msg(struct mailinfo *mi, struct strbuf *line)
+{
+ assert(!mi->filter_stage);
+
+ if (mi->header_stage) {
+ if (!line->len || (line->len == 1 && line->buf[0] == '\n'))
+ return 0;
+ }
- /* Unwrap transfer encoding and optionally
- * normalize the log message to UTF-8.
+ if (mi->use_inbody_headers && mi->header_stage) {
+ mi->header_stage = check_header(mi, line, mi->s_hdr_data, 0);
+ if (mi->header_stage)
+ return 0;
+ } else
+ /* Only trim the first (blank) line of the commit message
+ * when ignoring in-body headers.
*/
- decode_transfer_encoding(line);
- if (metainfo_charset)
- convert_to_utf8(line, charset);
+ mi->header_stage = 0;
- handle_inbody_header(seen, line);
- if (!(*seen & SEEN_PREFIX))
- continue;
+ /* normalize the log message to UTF-8. */
+ if (convert_to_utf8(mi, line, mi->charset.buf))
+ return 0; /* mi->input_error already set */
- fputs(line, cmitmsg);
- } while (fgets(line, sizeof(line), stdin) != NULL);
- fclose(cmitmsg);
- cmitmsg = NULL;
+ if (mi->use_scissors && is_scissors_line(line)) {
+ int i;
+
+ strbuf_setlen(&mi->log_message, 0);
+ mi->header_stage = 1;
+
+ /*
+ * We may have already read "secondary headers"; purge
+ * them to give ourselves a clean restart.
+ */
+ for (i = 0; header[i]; i++) {
+ if (mi->s_hdr_data[i])
+ strbuf_release(mi->s_hdr_data[i]);
+ mi->s_hdr_data[i] = NULL;
+ }
+ return 0;
+ }
+
+ if (patchbreak(line)) {
+ if (mi->message_id)
+ strbuf_addf(&mi->log_message,
+ "Message-Id: %s\n", mi->message_id);
+ return 1;
+ }
+
+ strbuf_addbuf(&mi->log_message, line);
return 0;
}
-/* We have done the commit message and have the first
- * line of the patch in line[].
- */
-static void handle_patch(void)
+static void handle_patch(struct mailinfo *mi, const struct strbuf *line)
{
- do {
- if (multipart_boundary[0] && is_multipart_boundary(line))
+ fwrite(line->buf, 1, line->len, mi->patchfile);
+ mi->patch_lines++;
+}
+
+static void handle_filter(struct mailinfo *mi, struct strbuf *line)
+{
+ switch (mi->filter_stage) {
+ case 0:
+ if (!handle_commit_msg(mi, line))
break;
- /* Only unwrap transfer encoding but otherwise do not
- * do anything. We do *NOT* want UTF-8 conversion
- * here; we are dealing with the user payload.
- */
- decode_transfer_encoding(line);
- fputs(line, patchfile);
- patch_lines++;
- } while (fgets(line, sizeof(line), stdin) != NULL);
+ mi->filter_stage++;
+ case 1:
+ handle_patch(mi, line);
+ break;
+ }
}
-/* multipart boundary and transfer encoding are set up for us, and we
- * are at the end of the sub header. do equivalent of handle_body up
- * to the next boundary without closing patchfile --- we will expect
- * that the first part to contain commit message and a patch, and
- * handle other parts as pure patches.
- */
-static int handle_multipart_one_part(int *seen)
+static int is_rfc2822_header(const struct strbuf *line)
{
- int n = 0;
+ /*
+ * 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->buf;
- while (fgets(line, sizeof(line), stdin) != NULL) {
- again:
- n++;
- if (is_multipart_boundary(line))
- break;
- if (handle_commit_msg(seen))
- goto again;
- handle_patch();
+ /* Count mbox From headers as headers */
+ if (starts_with(cp, "From ") || starts_with(cp, ">From "))
+ return 1;
+
+ while ((ch = *cp++)) {
+ if (ch == ':')
+ return 1;
+ if ((33 <= ch && ch <= 57) ||
+ (59 <= ch && ch <= 126))
+ continue;
break;
}
- if (n == 0)
- return -1;
return 0;
}
-static void handle_multipart_body(void)
+static int read_one_header_line(struct strbuf *line, FILE *in)
{
- int seen = 0;
- int part_num = 0;
+ struct strbuf continuation = STRBUF_INIT;
- /* Skip up to the first boundary */
- while (fgets(line, sizeof(line), stdin) != NULL)
- if (is_multipart_boundary(line)) {
- part_num = 1;
+ /* Get the first part of the line. */
+ if (strbuf_getline(line, in, '\n'))
+ return 0;
+
+ /*
+ * Is it an empty line or not a valid rfc2822 header?
+ * If so, stop here, and return false ("not a header")
+ */
+ strbuf_rtrim(line);
+ if (!line->len || !is_rfc2822_header(line)) {
+ /* Re-add the newline */
+ strbuf_addch(line, '\n');
+ return 0;
+ }
+
+ /*
+ * Now we need to eat all the continuation lines..
+ * Yuck, 2822 header "folding"
+ */
+ for (;;) {
+ int peek;
+
+ peek = fgetc(in); ungetc(peek, in);
+ if (peek != ' ' && peek != '\t')
break;
- }
- if (!part_num)
- return;
- /* We are on boundary line. Start slurping the subhead. */
- while (1) {
- int hdr = read_one_header_line(line, sizeof(line), stdin);
- if (!hdr) {
- if (handle_multipart_one_part(&seen) < 0)
- return;
- /* Reset per part headers */
- transfer_encoding = TE_DONTCARE;
- charset[0] = 0;
- }
- else
- check_subheader_line(line);
+ if (strbuf_getline(&continuation, in, '\n'))
+ break;
+ continuation.buf[0] = ' ';
+ strbuf_rtrim(&continuation);
+ strbuf_addbuf(line, &continuation);
+ }
+ strbuf_release(&continuation);
+
+ return 1;
+}
+
+static int find_boundary(struct mailinfo *mi, struct strbuf *line)
+{
+ while (!strbuf_getline(line, mi->input, '\n')) {
+ if (*(mi->content_top) && is_multipart_boundary(mi, line))
+ return 1;
}
- fclose(patchfile);
- if (!patch_lines) {
- fprintf(stderr, "No patch found\n");
- exit(1);
+ return 0;
+}
+
+static int handle_boundary(struct mailinfo *mi, struct strbuf *line)
+{
+ struct strbuf newline = STRBUF_INIT;
+
+ strbuf_addch(&newline, '\n');
+again:
+ if (line->len >= (*(mi->content_top))->len + 2 &&
+ !memcmp(line->buf + (*(mi->content_top))->len, "--", 2)) {
+ /* we hit an end boundary */
+ /* pop the current boundary off the stack */
+ strbuf_release(*(mi->content_top));
+ free(*(mi->content_top));
+ *(mi->content_top) = NULL;
+
+ /* technically won't happen as is_multipart_boundary()
+ will fail first. But just in case..
+ */
+ if (--mi->content_top < mi->content) {
+ error("Detected mismatched boundaries, can't recover");
+ mi->input_error = -1;
+ mi->content_top = mi->content;
+ return 0;
+ }
+ handle_filter(mi, &newline);
+ strbuf_release(&newline);
+ if (mi->input_error)
+ return 0;
+
+ /* skip to the next boundary */
+ if (!find_boundary(mi, line))
+ return 0;
+ goto again;
}
+
+ /* set some defaults */
+ mi->transfer_encoding = TE_DONTCARE;
+ strbuf_reset(&mi->charset);
+
+ /* slurp in this section's info */
+ while (read_one_header_line(line, mi->input))
+ check_header(mi, line, mi->p_hdr_data, 0);
+
+ strbuf_release(&newline);
+ /* replenish line */
+ if (strbuf_getline(line, mi->input, '\n'))
+ return 0;
+ strbuf_addch(line, '\n');
+ return 1;
}
-/* Non multipart message */
-static void handle_body(void)
+static void handle_body(struct mailinfo *mi, struct strbuf *line)
{
- int seen = 0;
+ struct strbuf prev = STRBUF_INIT;
- handle_commit_msg(&seen);
- handle_patch();
- fclose(patchfile);
- if (!patch_lines) {
- fprintf(stderr, "No patch found\n");
- exit(1);
+ /* Skip up to the first boundary */
+ if (*(mi->content_top)) {
+ if (!find_boundary(mi, line))
+ goto handle_body_out;
}
+
+ do {
+ /* process any boundary lines */
+ if (*(mi->content_top) && is_multipart_boundary(mi, line)) {
+ /* flush any leftover */
+ if (prev.len) {
+ handle_filter(mi, &prev);
+ strbuf_reset(&prev);
+ }
+ if (!handle_boundary(mi, line))
+ goto handle_body_out;
+ }
+
+ /* Unwrap transfer encoding */
+ decode_transfer_encoding(mi, line);
+
+ switch (mi->transfer_encoding) {
+ case TE_BASE64:
+ case TE_QP:
+ {
+ struct strbuf **lines, **it, *sb;
+
+ /* Prepend any previous partial lines */
+ strbuf_insert(line, 0, prev.buf, prev.len);
+ strbuf_reset(&prev);
+
+ /*
+ * This is a decoded line that may contain
+ * multiple new lines. Pass only one chunk
+ * at a time to handle_filter()
+ */
+ lines = strbuf_split(line, '\n');
+ for (it = lines; (sb = *it); it++) {
+ if (*(it + 1) == NULL) /* The last line */
+ if (sb->buf[sb->len - 1] != '\n') {
+ /* Partial line, save it for later. */
+ strbuf_addbuf(&prev, sb);
+ break;
+ }
+ handle_filter(mi, sb);
+ }
+ /*
+ * The partial chunk is saved in "prev" and will be
+ * appended by the next iteration of read_line_with_nul().
+ */
+ strbuf_list_free(lines);
+ break;
+ }
+ default:
+ handle_filter(mi, line);
+ }
+
+ if (mi->input_error)
+ break;
+ } while (!strbuf_getwholeline(line, mi->input, '\n'));
+
+handle_body_out:
+ strbuf_release(&prev);
}
-static const char mailinfo_usage[] =
- "git-mailinfo [-k] [-u | --encoding=<encoding>] msg patch <mail >info";
+static void output_header_lines(FILE *fout, const char *hdr, const struct strbuf *data)
+{
+ const char *sp = data->buf;
+ while (1) {
+ char *ep = strchr(sp, '\n');
+ int len;
+ if (!ep)
+ len = strlen(sp);
+ else
+ len = ep - sp;
+ fprintf(fout, "%s: %.*s\n", hdr, len, sp);
+ if (!ep)
+ break;
+ sp = ep + 1;
+ }
+}
-int main(int argc, char **argv)
+static void handle_info(struct mailinfo *mi)
{
- /* NEEDSWORK: might want to do the optional .git/ directory
- * discovery
- */
- git_config(git_default_config);
-
- while (1 < argc && argv[1][0] == '-') {
- if (!strcmp(argv[1], "-k"))
- keep_subject = 1;
- else if (!strcmp(argv[1], "-u"))
- metainfo_charset = git_commit_encoding;
- else if (!strncmp(argv[1], "--encoding=", 11))
- metainfo_charset = argv[1] + 11;
+ struct strbuf *hdr;
+ int i;
+
+ for (i = 0; header[i]; i++) {
+ /* only print inbody headers if we output a patch file */
+ if (mi->patch_lines && mi->s_hdr_data[i])
+ hdr = mi->s_hdr_data[i];
+ else if (mi->p_hdr_data[i])
+ hdr = mi->p_hdr_data[i];
else
- usage(mailinfo_usage);
- argc--; argv++;
+ continue;
+
+ if (!strcmp(header[i], "Subject")) {
+ if (!mi->keep_subject) {
+ cleanup_subject(mi, hdr);
+ cleanup_space(hdr);
+ }
+ output_header_lines(mi->output, "Subject", hdr);
+ } else if (!strcmp(header[i], "From")) {
+ cleanup_space(hdr);
+ handle_from(mi, hdr);
+ fprintf(mi->output, "Author: %s\n", mi->name.buf);
+ fprintf(mi->output, "Email: %s\n", mi->email.buf);
+ } else {
+ cleanup_space(hdr);
+ fprintf(mi->output, "%s: %s\n", header[i], hdr->buf);
+ }
}
+ fprintf(mi->output, "\n");
+}
- if (argc != 3)
- usage(mailinfo_usage);
- cmitmsg = fopen(argv[1], "w");
+int mailinfo(struct mailinfo *mi, const char *msg, const char *patch)
+{
+ FILE *cmitmsg;
+ int peek;
+ struct strbuf line = STRBUF_INIT;
+
+ cmitmsg = fopen(msg, "w");
if (!cmitmsg) {
- perror(argv[1]);
- exit(1);
+ perror(msg);
+ return -1;
}
- patchfile = fopen(argv[2], "w");
- if (!patchfile) {
- perror(argv[2]);
- exit(1);
+ mi->patchfile = fopen(patch, "w");
+ if (!mi->patchfile) {
+ perror(patch);
+ fclose(cmitmsg);
+ return -1;
}
- while (1) {
- int hdr = read_one_header_line(line, sizeof(line), stdin);
- if (!hdr) {
- if (multipart_boundary[0])
- handle_multipart_body();
- else
- handle_body();
- handle_info();
- break;
- }
- check_header_line(line);
+
+ mi->p_hdr_data = xcalloc(MAX_HDR_PARSED, sizeof(*(mi->p_hdr_data)));
+ mi->s_hdr_data = xcalloc(MAX_HDR_PARSED, sizeof(*(mi->s_hdr_data)));
+
+ do {
+ peek = fgetc(mi->input);
+ } while (isspace(peek));
+ ungetc(peek, mi->input);
+
+ /* process the email header */
+ while (read_one_header_line(&line, mi->input))
+ check_header(mi, &line, mi->p_hdr_data, 1);
+
+ handle_body(mi, &line);
+ fwrite(mi->log_message.buf, 1, mi->log_message.len, cmitmsg);
+ fclose(cmitmsg);
+ fclose(mi->patchfile);
+
+ handle_info(mi);
+ strbuf_release(&line);
+ return mi->input_error;
+}
+
+static int git_mailinfo_config(const char *var, const char *value, void *mi_)
+{
+ struct mailinfo *mi = mi_;
+
+ if (!starts_with(var, "mailinfo."))
+ return git_default_config(var, value, NULL);
+ if (!strcmp(var, "mailinfo.scissors")) {
+ mi->use_scissors = git_config_bool(var, value);
+ return 0;
}
+ /* perhaps others here */
return 0;
}
+
+void setup_mailinfo(struct mailinfo *mi)
+{
+ memset(mi, 0, sizeof(*mi));
+ strbuf_init(&mi->name, 0);
+ strbuf_init(&mi->email, 0);
+ strbuf_init(&mi->charset, 0);
+ strbuf_init(&mi->log_message, 0);
+ mi->header_stage = 1;
+ mi->use_inbody_headers = 1;
+ mi->content_top = mi->content;
+ git_config(git_mailinfo_config, mi);
+}
+
+void clear_mailinfo(struct mailinfo *mi)
+{
+ int i;
+
+ strbuf_release(&mi->name);
+ strbuf_release(&mi->email);
+ strbuf_release(&mi->charset);
+ free(mi->message_id);
+
+ for (i = 0; mi->p_hdr_data[i]; i++)
+ strbuf_release(mi->p_hdr_data[i]);
+ free(mi->p_hdr_data);
+ for (i = 0; mi->s_hdr_data[i]; i++)
+ strbuf_release(mi->s_hdr_data[i]);
+ free(mi->s_hdr_data);
+
+ while (mi->content < mi->content_top) {
+ free(*(mi->content_top));
+ mi->content_top--;
+ }
+
+ strbuf_release(&mi->log_message);
+}