X-Git-Url: https://git.octo.it/?a=blobdiff_plain;f=mailinfo.c;h=b27651935db85cf0ab651d523c502943d137b7cd;hb=1b9bc5a7b7434d771726011613a00cb202bd9f44;hp=df470bb9c2296d32e3b1d2b7489c712b01c3b0ed;hpb=99977bd5fdeabbd0608a70e9411c243007ec4ea2;p=git.git diff --git a/mailinfo.c b/mailinfo.c index df470bb9..b2765193 100644 --- a/mailinfo.c +++ b/mailinfo.c @@ -7,12 +7,16 @@ #include #include #include +#ifndef NO_ICONV #include +#endif +#include "git-compat-util.h" +#include "cache.h" static FILE *cmitmsg, *patchfile; static int keep_subject = 0; -static int metainfo_utf8 = 0; +static char *metainfo_charset = NULL; static char line[1000]; static char date[1000]; static char name[1000]; @@ -38,13 +42,43 @@ static char *sanity_check(char *name, char *email) return name; } +static int bogus_from(char *line) +{ + /* John Doe */ + char *bra, *ket, *dst, *cp; + + /* This is fallback, so do not bother if we already have an + * e-mail address. + */ + 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; +} + static int handle_from(char *line) { char *at = strchr(line, '@'); char *dst; if (!at) - return 0; + return bogus_from(line); /* * If we already have one email, don't take any confusing lines @@ -371,7 +405,7 @@ static unsigned hexval(int c) return ~0; } -static int decode_q_segment(char *in, char *ot, char *ep) +static int decode_q_segment(char *in, char *ot, char *ep, int rfc2047) { int c; while ((c = *in++) != 0 && (in <= ep)) { @@ -380,9 +414,11 @@ static int decode_q_segment(char *in, char *ot, char *ep) if (d == '\n' || !d) break; /* drop trailing newline */ *ot++ = ((hexval(d) << 4) | hexval(*in++)); + continue; } - else - *ot++ = c; + if (rfc2047 && c == '_') /* rfc2047 4.2 (2) */ + c = 0x20; + *ot++ = c; } *ot = 0; return 0; @@ -437,29 +473,40 @@ static int decode_b_segment(char *in, char *ot, char *ep) static void convert_to_utf8(char *line, char *charset) { - if (*charset) { - char *in, *out; - size_t insize, outsize, nrc; - char outbuf[4096]; /* cheat */ - iconv_t conv = iconv_open("utf-8", charset); - - if (conv == (iconv_t) -1) { - fprintf(stderr, "cannot convert from %s to utf-8\n", - 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); + + 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; - return; } - 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); + 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; } + 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 } static void decode_header_bq(char *it) @@ -502,12 +549,12 @@ static void decode_header_bq(char *it) sz = decode_b_segment(cp + 3, piecebuf, ep); break; case 'q': - sz = decode_q_segment(cp + 3, piecebuf, ep); + sz = decode_q_segment(cp + 3, piecebuf, ep, 1); break; } if (sz < 0) return; - if (metainfo_utf8) + if (metainfo_charset) convert_to_utf8(piecebuf, charset_q); strcpy(out, piecebuf); out += strlen(out); @@ -524,7 +571,7 @@ static void decode_transfer_encoding(char *line) switch (transfer_encoding) { case TE_QP: ep = line + strlen(line); - decode_q_segment(line, line, ep); + decode_q_segment(line, line, ep, 0); break; case TE_BASE64: ep = line + strlen(line); @@ -586,7 +633,7 @@ static int handle_commit_msg(void) * normalize the log message to UTF-8. */ decode_transfer_encoding(line); - if (metainfo_utf8) + if (metainfo_charset) convert_to_utf8(line, charset); fputs(line, cmitmsg); } while (fgets(line, sizeof(line), stdin) != NULL); @@ -666,6 +713,9 @@ static void handle_multipart_body(void) if (!len) { if (handle_multipart_one_part() < 0) return; + /* Reset per part headers */ + transfer_encoding = TE_DONTCARE; + charset[0] = 0; } else check_subheader_line(line, len); @@ -703,27 +753,29 @@ static void handle_body(void) } static const char mailinfo_usage[] = - "git-mailinfo [-k] [-u] msg patch info"; - -static void usage(void) { - fprintf(stderr, "%s\n", mailinfo_usage); - exit(1); -} + "git-mailinfo [-k] [-u | --encoding=] msg patch info"; int main(int argc, char **argv) { + /* 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_utf8 = 1; + metainfo_charset = git_commit_encoding; + else if (!strncmp(argv[1], "--encoding=", 11)) + metainfo_charset = argv[1] + 11; else - usage(); + usage(mailinfo_usage); argc--; argv++; } if (argc != 3) - usage(); + usage(mailinfo_usage); cmitmsg = fopen(argv[1], "w"); if (!cmitmsg) { perror(argv[1]);