X-Git-Url: https://git.tokkee.org/?a=blobdiff_plain;f=builtin-mailinfo.c;h=583da38b6750185eb38f04d91555aa75ee4a77b0;hb=8860fd42fcf5a7853f7d7c2198793183320293ff;hp=821642a7af97e7afa13a187af5ec68c8a67ae93c;hpb=b19beecd9456a2e6282634e5df751206b972604a;p=git.git

diff --git a/builtin-mailinfo.c b/builtin-mailinfo.c
index 821642a7a..583da38b6 100644
--- a/builtin-mailinfo.c
+++ b/builtin-mailinfo.c
@@ -2,22 +2,14 @@
  * 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 "builtin.h"
+#include "utf8.h"
 
 static FILE *cmitmsg, *patchfile, *fin, *fout;
 
-static int keep_subject = 0;
-static const char *metainfo_charset = NULL;
+static int keep_subject;
+static const char *metainfo_charset;
 static char line[1000];
 static char date[1000];
 static char name[1000];
@@ -31,7 +23,7 @@ static char charset[256];
 
 static char multipart_boundary[1000];
 static int multipart_boundary_len;
-static int patch_lines = 0;
+static int patch_lines;
 
 static char *sanity_check(char *name, char *email)
 {
@@ -165,7 +157,7 @@ static int handle_subject(char *line)
 
 static int slurp_attr(const char *line, const char *name, char *attr)
 {
-	char *ends, *ap = strcasestr(line, name);
+	const char *ends, *ap = strcasestr(line, name);
 	size_t sz;
 
 	if (!ap) {
@@ -348,7 +340,7 @@ static void cleanup_space(char *buf)
 	}
 }
 
-static void decode_header_bq(char *it);
+static void decode_header(char *it);
 typedef int (*header_fn_t)(char *);
 struct header_def {
 	const char *name;
@@ -371,7 +363,7 @@ static void check_header(char *line, struct header_def *header)
 			/* Unwrap inline B and Q encoding, and optionally
 			 * normalize the meta information to utf8.
 			 */
-			decode_header_bq(line + len + 2);
+			decode_header(line + len + 2);
 			header[i].func(line + len + 2);
 			break;
 		}
@@ -446,22 +438,11 @@ static int read_one_header_line(char *line, int sz, FILE *in)
 			break;
 	}
 	/* Count mbox From headers as headers */
-	if (!ofs && !memcmp(line, "From ", 5))
+	if (!ofs && (!memcmp(line, "From ", 5) || !memcmp(line, ">From ", 6)))
 		ofs = 1;
 	return ofs;
 }
 
-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;
-}
-
 static int decode_q_segment(char *in, char *ot, char *ep, int rfc2047)
 {
 	int c;
@@ -530,52 +511,30 @@ static int decode_b_segment(char *in, char *ot, char *ep)
 
 static void convert_to_utf8(char *line, 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);
-
-	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;
-	}
-	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
+	char *out = reencode_string(line, metainfo_charset, input_charset);
+
+	if (!out)
+		die("cannot convert from %s to %s\n",
+		    input_charset, metainfo_charset);
+	strcpy(line, out);
+	free(out);
 }
 
-static void decode_header_bq(char *it)
+static int decode_header_bq(char *it)
 {
 	char *in, *out, *ep, *cp, *sp;
 	char outbuf[1000];
+	int rfc2047 = 0;
 
 	in = it;
 	out = outbuf;
 	while ((ep = strstr(in, "=?")) != NULL) {
 		int sz, encoding;
 		char charset_q[256], piecebuf[256];
+		rfc2047 = 1;
+
 		if (in != ep) {
 			sz = ep - in;
 			memcpy(out, in, sz);
@@ -589,19 +548,19 @@ static void decode_header_bq(char *it)
 		ep += 2;
 		cp = strchr(ep, '?');
 		if (!cp)
-			return; /* no munging */
+			return rfc2047; /* no munging */
 		for (sp = ep; sp < cp; sp++)
 			charset_q[sp - ep] = tolower(*sp);
 		charset_q[cp - ep] = 0;
 		encoding = cp[1];
 		if (!encoding || cp[2] != '?')
-			return; /* no munging */
+			return rfc2047; /* no munging */
 		ep = strstr(cp + 3, "?=");
 		if (!ep)
-			return; /* no munging */
+			return rfc2047; /* no munging */
 		switch (tolower(encoding)) {
 		default:
-			return; /* no munging */
+			return rfc2047; /* no munging */
 		case 'b':
 			sz = decode_b_segment(cp + 3, piecebuf, ep);
 			break;
@@ -610,7 +569,7 @@ static void decode_header_bq(char *it)
 			break;
 		}
 		if (sz < 0)
-			return;
+			return rfc2047;
 		if (metainfo_charset)
 			convert_to_utf8(piecebuf, charset_q);
 		strcpy(out, piecebuf);
@@ -619,6 +578,19 @@ static void decode_header_bq(char *it)
 	}
 	strcpy(out, in);
 	strcpy(it, outbuf);
+	return rfc2047;
+}
+
+static void decode_header(char *it)
+{
+
+	if (decode_header_bq(it))
+		return;
+	/* otherwise "it" is a straight copy of the input.
+	 * This can be binary guck but there is no charset specified.
+	 */
+	if (metainfo_charset)
+		convert_to_utf8(it, "");
 }
 
 static void decode_transfer_encoding(char *line)
@@ -820,18 +792,25 @@ int mailinfo(FILE *in, FILE *out, int ks, const char *encoding,
 static const char mailinfo_usage[] =
 	"git-mailinfo [-k] [-u | --encoding=<encoding>] msg patch <mail >info";
 
-int cmd_mailinfo(int argc, const char **argv, char **envp)
+int cmd_mailinfo(int argc, const char **argv, const char *prefix)
 {
+	const char *def_charset;
+
 	/* NEEDSWORK: might want to do the optional .git/ directory
 	 * discovery
 	 */
 	git_config(git_default_config);
 
+	def_charset = (git_commit_encoding ? git_commit_encoding : "utf-8");
+	metainfo_charset = def_charset;
+
 	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;
+			metainfo_charset = def_charset;
+		else if (!strcmp(argv[1], "-n"))
+			metainfo_charset = NULL;
 		else if (!strncmp(argv[1], "--encoding=", 11))
 			metainfo_charset = argv[1] + 11;
 		else