ewah: support platforms that require aligned reads

diff --git a/builtin/mailinfo.c b/builtin/mailinfo.c
index a50ac2256cdbacd76ed44a50804212be07f949db..24a772d8e1b7355a58088d784fdc18cd54302b7d 100644 (file)
--- a/builtin/mailinfo.c
+++ b/builtin/mailinfo.c
@@ -17,11 +17,8 @@ static struct strbuf name = STRBUF_INIT;
 static struct strbuf email = STRBUF_INIT;
 
 static enum  {
-       TE_DONTCARE, TE_QP, TE_BASE64,
+       TE_DONTCARE, TE_QP, TE_BASE64
 } transfer_encoding;
-static enum  {
-       TYPE_TEXT, TYPE_OTHER,
-} message_type;
 
 static struct strbuf charset = STRBUF_INIT;
 static int patch_lines;
@@ -160,10 +157,9 @@ static int slurp_attr(const char *line, const char *name, struct strbuf *attr)
        const char *ends, *ap = strcasestr(line, name);
        size_t sz;
 
-       if (!ap) {
-               strbuf_setlen(attr, 0);
+       strbuf_setlen(attr, 0);
+       if (!ap)
                return 0;
-       }
        ap += strlen(name);
        if (*ap == '"') {
                ap++;
@@ -185,8 +181,6 @@ static void handle_content_type(struct strbuf *line)
        struct strbuf *boundary = xmalloc(sizeof(struct strbuf));
        strbuf_init(boundary, line->len);
 
-       if (!strcasestr(line->buf, "text/"))
-                message_type = TYPE_OTHER;
        if (slurp_attr(line->buf, "boundary=", boundary)) {
                strbuf_insert(boundary, 0, "--", 2);
                if (++content_top > &content[MAX_BOUNDARIES]) {
@@ -232,7 +226,9 @@ static void cleanup_subject(struct strbuf *subject)
                case 'r': case 'R':
                        if (subject->len <= at + 3)
                                break;
-                       if (!memcmp(subject->buf + at + 1, "e:", 2)) {
+                       if ((subject->buf[at + 1] == 'e' ||
+                            subject->buf[at + 1] == 'E') &&
+                           subject->buf[at + 2] == ':') {
                                strbuf_remove(subject, at, 3);
                                continue;
                        }
@@ -250,8 +246,17 @@ static void cleanup_subject(struct strbuf *subject)
                            (7 <= remove &&
                             memmem(subject->buf + at, remove, "PATCH", 5)))
                                strbuf_remove(subject, at, remove);
-                       else
+                       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;
@@ -400,7 +405,7 @@ static int read_one_header_line(struct strbuf *line, FILE *in)
                        break;
                if (strbuf_getline(&continuation, in, '\n'))
                        break;
-               continuation.buf[0] = '\n';
+               continuation.buf[0] = ' ';
                strbuf_rtrim(&continuation);
                strbuf_addbuf(line, &continuation);
        }
@@ -472,37 +477,14 @@ static struct strbuf *decode_b_segment(const struct strbuf *b_seg)
        return out;
 }
 
-/*
- * When there is no known charset, guess.
- *
- * Right now we assume that if the target is UTF-8 (the default),
- * and it already looks like UTF-8 (which includes US-ASCII as its
- * subset, of course) then that is what it is and there is nothing
- * to do.
- *
- * Otherwise, we default to assuming it is Latin1 for historical
- * reasons.
- */
-static const char *guess_charset(const struct strbuf *line, const char *target_charset)
-{
-       if (is_encoding_utf8(target_charset)) {
-               if (is_utf8(line->buf))
-                       return NULL;
-       }
-       return "ISO8859-1";
-}
-
 static void convert_to_utf8(struct strbuf *line, const char *charset)
 {
        char *out;
 
-       if (!charset || !*charset) {
-               charset = guess_charset(line, metainfo_charset);
-               if (!charset)
-                       return;
-       }
+       if (!charset || !*charset)
+               return;
 
-       if (!strcasecmp(metainfo_charset, charset))
+       if (same_encoding(metainfo_charset, charset))
                return;
        out = reencode_string(line->buf, metainfo_charset, charset);
        if (!out)
@@ -671,7 +653,6 @@ static int handle_boundary(void)
        /* set some defaults */
        transfer_encoding = TE_DONTCARE;
        strbuf_reset(&charset);
-       message_type = TYPE_TEXT;
 
        /* slurp in this section's info */
        while (read_one_header_line(&line, fin))
@@ -746,7 +727,8 @@ static int is_scissors_line(const struct strbuf *line)
                        continue;
                }
                if (i + 1 < len &&
-                   (!memcmp(buf + i, ">8", 2) || !memcmp(buf + i, "8<", 2))) {
+                   (!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;
@@ -779,8 +761,7 @@ static int handle_commit_msg(struct strbuf *line)
                return 0;
 
        if (still_looking) {
-               strbuf_ltrim(line);
-               if (!line->len)
+               if (!line->len || (line->len == 1 && line->buf[0] == '\n'))
                        return 0;
        }
 
@@ -885,11 +866,6 @@ static void handle_body(void)
                        strbuf_insert(&line, 0, prev.buf, prev.len);
                        strbuf_reset(&prev);
 
-                       /* binary data most likely doesn't have newlines */
-                       if (message_type != TYPE_TEXT) {
-                               handle_filter(&line);
-                               break;
-                       }
                        /*
                         * This is a decoded line that may contain
                         * multiple new lines.  Pass only one chunk
@@ -1032,7 +1008,7 @@ int cmd_mailinfo(int argc, const char **argv, const char *prefix)
         */
        git_config(git_mailinfo_config, NULL);
 
-       def_charset = (git_commit_encoding ? git_commit_encoding : "UTF-8");
+       def_charset = get_commit_output_encoding();
        metainfo_charset = def_charset;
 
        while (1 < argc && argv[1][0] == '-') {