X-Git-Url: https://git.tokkee.org/?a=blobdiff_plain;f=builtin-mailinfo.c;h=b0b5d8f6cb5107f3422d6107fd56f35ef62786f6;hb=da8ba5e7da01be597aa9417c563dbd516ea5f204;hp=dacc8ac2d0e63e46dd1aa8fee6ba949bdd319e43;hpb=a1eb73d917e15cd97314e0a39cbe857329339a96;p=git.git

diff --git a/builtin-mailinfo.c b/builtin-mailinfo.c
index dacc8ac2d..b0b5d8f6c 100644
--- a/builtin-mailinfo.c
+++ b/builtin-mailinfo.c
@@ -29,6 +29,9 @@ static struct strbuf **p_hdr_data, **s_hdr_data;
 #define MAX_HDR_PARSED 10
 #define MAX_BOUNDARIES 5
 
+static void cleanup_space(struct strbuf *sb);
+
+
 static void get_sane_name(struct strbuf *out, struct strbuf *name, struct strbuf *email)
 {
 	struct strbuf *src = name;
@@ -109,11 +112,19 @@ static void handle_from(const struct strbuf *from)
 	strbuf_add(&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 removed the
-	 * email part, so trim from both ends, possibly removing
-	 * the () pair at the end.
+	/* The remainder is name.  It could be
+	 *
+	 * - "John Doe <john.doe@xz>"			(a), or
+	 * - "john.doe@xz (John Doe)"			(b), or
+	 * - "John (zzz) Doe <john.doe@xz> (Comment)"	(c)
+	 *
+	 * but we have removed the email part, so
+	 *
+	 * - remove extra spaces which could stay after email (case 'c'), and
+	 * - trim from both ends, possibly removing the () pair at the end
+	 *   (cases 'a' and 'b').
 	 */
+	cleanup_space(&f);
 	strbuf_trim(&f);
 	if (f.buf[0] == '(' && f.len && f.buf[f.len - 1] == ')') {
 		strbuf_remove(&f, 0, 1);
@@ -182,8 +193,7 @@ static void handle_content_type(struct strbuf *line)
 		*content_top = boundary;
 		boundary = NULL;
 	}
-	if (slurp_attr(line->buf, "charset=", &charset))
-		strbuf_tolower(&charset);
+	slurp_attr(line->buf, "charset=", &charset);
 
 	if (boundary) {
 		strbuf_release(boundary);
@@ -470,7 +480,7 @@ static const char *guess_charset(const struct strbuf *line, const char *target_c
 		if (is_utf8(line->buf))
 			return NULL;
 	}
-	return "latin1";
+	return "ISO8859-1";
 }
 
 static void convert_to_utf8(struct strbuf *line, const char *charset)
@@ -483,11 +493,11 @@ static void convert_to_utf8(struct strbuf *line, const char *charset)
 			return;
 	}
 
-	if (!strcmp(metainfo_charset, charset))
+	if (!strcasecmp(metainfo_charset, charset))
 		return;
 	out = reencode_string(line->buf, metainfo_charset, charset);
 	if (!out)
-		die("cannot convert from %s to %s\n",
+		die("cannot convert from %s to %s",
 		    charset, metainfo_charset);
 	strbuf_attach(line, out, strlen(out), strlen(out));
 }
@@ -526,7 +536,6 @@ static int decode_header_bq(struct strbuf *it)
 				 */
 				strbuf_add(&outbuf, in, ep - in);
 			}
-			in = ep;
 		}
 		/* E.g.
 		 * ep : "=?iso-2022-jp?B?GyR...?= foo"
@@ -540,7 +549,6 @@ static int decode_header_bq(struct strbuf *it)
 		if (cp + 3 - it->buf > it->len)
 			goto decode_header_bq_out;
 		strbuf_add(&charset_q, ep, cp - ep);
-		strbuf_tolower(&charset_q);
 
 		encoding = cp[1];
 		if (!encoding || cp[2] != '?')
@@ -757,7 +765,6 @@ static void handle_filter(struct strbuf *line)
 
 static void handle_body(void)
 {
-	int len = 0;
 	struct strbuf prev = STRBUF_INIT;
 
 	/* Skip up to the first boundary */
@@ -767,8 +774,6 @@ static void handle_body(void)
 	}
 
 	do {
-		strbuf_setlen(&line, line.len + len);
-
 		/* process any boundary lines */
 		if (*content_top && is_multipart_boundary(&line)) {
 			/* flush any leftover */
@@ -824,10 +829,7 @@ static void handle_body(void)
 			handle_filter(&line);
 		}
 
-		strbuf_reset(&line);
-		if (strbuf_avail(&line) < 100)
-			strbuf_grow(&line, 100);
-	} while ((len = read_line_with_nul(line.buf, strbuf_avail(&line), fin)));
+	} while (!strbuf_getwholeline(&line, fin, '\n'));
 
 handle_body_out:
 	strbuf_release(&prev);
@@ -934,7 +936,7 @@ int cmd_mailinfo(int argc, const char **argv, const char *prefix)
 	 */
 	git_config(git_default_config, NULL);
 
-	def_charset = (git_commit_encoding ? git_commit_encoding : "utf-8");
+	def_charset = (git_commit_encoding ? git_commit_encoding : "UTF-8");
 	metainfo_charset = def_charset;
 
 	while (1 < argc && argv[1][0] == '-') {