Merge branch 'maint'

diff --git a/builtin-mailinfo.c b/builtin-mailinfo.c
index f7c8c08b320c99d8bf96443ae57aa33c1de7e8c0..92637ac0bae82d0b88e267b572a51a75299cda5c 100644 (file)
--- 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);
@@ -430,13 +440,6 @@ static struct strbuf *decode_b_segment(const struct strbuf *b_seg)
                        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++) {
@@ -477,7 +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)
@@ -490,7 +493,7 @@ 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)
@@ -514,8 +517,25 @@ static int decode_header_bq(struct strbuf *it)
                rfc2047 = 1;
 
                if (in != ep) {
-                       strbuf_add(&outbuf, in, ep - in);
-                       in = ep;
+                       /*
+                        * 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"
@@ -529,7 +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] != '?')
@@ -860,6 +879,7 @@ static void handle_info(void)
                        }
                        output_header_lines(fout, "Subject", hdr);
                } else if (!memcmp(header[i], "From", 4)) {
+                       cleanup_space(hdr);
                        handle_from(hdr);
                        fprintf(fout, "Author: %s\n", name.buf);
                        fprintf(fout, "Email: %s\n", email.buf);
@@ -922,7 +942,7 @@ 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] == '-') {