From: Junio C Hamano Date: Mon, 25 Mar 2013 21:00:46 +0000 (-0700) Subject: Merge branch 'ks/rfc2047-one-char-at-a-time' X-Git-Tag: v1.8.3-rc0~180 X-Git-Url: https://git.lorimer.id.au/gitweb.git/diff_plain/573f1a9cf163365637a36a6d95c670883a918352?hp=-c Merge branch 'ks/rfc2047-one-char-at-a-time' When "format-patch" quoted a non-ascii strings on the header files, it incorrectly applied rfc2047 and chopped a single character in the middle of it. * ks/rfc2047-one-char-at-a-time: format-patch: RFC 2047 says multi-octet character may not be split --- 573f1a9cf163365637a36a6d95c670883a918352 diff --combined pretty.c index b57adefdd2,cccee87026..41f04e669d --- a/pretty.c +++ b/pretty.c @@@ -345,7 -345,7 +345,7 @@@ static int needs_rfc2047_encoding(cons return 0; } - static void add_rfc2047(struct strbuf *sb, const char *line, int len, + static void add_rfc2047(struct strbuf *sb, const char *line, size_t len, const char *encoding, enum rfc2047_type type) { static const int max_encoded_length = 76; /* per rfc2047 */ @@@ -355,9 -355,22 +355,22 @@@ strbuf_grow(sb, len * 3 + strlen(encoding) + 100); strbuf_addf(sb, "=?%s?q?", encoding); line_len += strlen(encoding) + 5; /* 5 for =??q? */ - for (i = 0; i < len; i++) { - unsigned ch = line[i] & 0xFF; - int is_special = is_rfc2047_special(ch, type); + + while (len) { + /* + * RFC 2047, section 5 (3): + * + * Each 'encoded-word' MUST represent an integral number of + * characters. A multi-octet character may not be split across + * adjacent 'encoded- word's. + */ + const unsigned char *p = (const unsigned char *)line; + int chrlen = mbs_chrlen(&line, &len, encoding); + int is_special = (chrlen > 1) || is_rfc2047_special(*p, type); + + /* "=%02X" * chrlen, or the byte itself */ + const char *encoded_fmt = is_special ? "=%02X" : "%c"; + int encoded_len = is_special ? 3 * chrlen : 1; /* * According to RFC 2047, we could encode the special character @@@ -367,18 -380,15 +380,15 @@@ * causes ' ' to be encoded as '=20', avoiding this problem. */ - if (line_len + 2 + (is_special ? 3 : 1) > max_encoded_length) { + if (line_len + encoded_len + 2 > max_encoded_length) { + /* It won't fit with trailing "?=" --- break the line */ strbuf_addf(sb, "?=\n =?%s?q?", encoding); line_len = strlen(encoding) + 5 + 1; /* =??q? plus SP */ } - if (is_special) { - strbuf_addf(sb, "=%02X", ch); - line_len += 3; - } else { - strbuf_addch(sb, ch); - line_len++; - } + for (i = 0; i < chrlen; i++) + strbuf_addf(sb, encoded_fmt, p[i]); + line_len += encoded_len; } strbuf_addstr(sb, "?="); } @@@ -387,79 -397,56 +397,79 @@@ void pp_user_info(const struct pretty_p const char *what, struct strbuf *sb, const char *line, const char *encoding) { + struct strbuf name; + struct strbuf mail; + struct ident_split ident; + int linelen; + char *line_end, *date; + const char *mailbuf, *namebuf; + size_t namelen, maillen; int max_length = 78; /* per rfc2822 */ - char *date; - int namelen; unsigned long time; int tz; if (pp->fmt == CMIT_FMT_ONELINE) return; - date = strchr(line, '>'); - if (!date) + + line_end = strchr(line, '\n'); + if (!line_end) { + line_end = strchr(line, '\0'); + if (!line_end) + return; + } + + linelen = ++line_end - line; + if (split_ident_line(&ident, line, linelen)) return; - namelen = ++date - line; - time = strtoul(date, &date, 10); + + + mailbuf = ident.mail_begin; + maillen = ident.mail_end - ident.mail_begin; + namebuf = ident.name_begin; + namelen = ident.name_end - ident.name_begin; + + if (pp->mailmap) + map_user(pp->mailmap, &mailbuf, &maillen, &namebuf, &namelen); + + strbuf_init(&mail, 0); + strbuf_init(&name, 0); + + strbuf_add(&mail, mailbuf, maillen); + strbuf_add(&name, namebuf, namelen); + + namelen = name.len + mail.len + 3; /* ' ' + '<' + '>' */ + time = strtoul(ident.date_begin, &date, 10); tz = strtol(date, NULL, 10); if (pp->fmt == CMIT_FMT_EMAIL) { - char *name_tail = strchr(line, '<'); - int display_name_length; - if (!name_tail) - return; - while (line < name_tail && isspace(name_tail[-1])) - name_tail--; - display_name_length = name_tail - line; strbuf_addstr(sb, "From: "); - if (needs_rfc2047_encoding(line, display_name_length, RFC2047_ADDRESS)) { - add_rfc2047(sb, line, display_name_length, - encoding, RFC2047_ADDRESS); + if (needs_rfc2047_encoding(name.buf, name.len, RFC2047_ADDRESS)) { + add_rfc2047(sb, name.buf, name.len, + encoding, RFC2047_ADDRESS); max_length = 76; /* per rfc2047 */ - } else if (needs_rfc822_quoting(line, display_name_length)) { + } else if (needs_rfc822_quoting(name.buf, name.len)) { struct strbuf quoted = STRBUF_INIT; - add_rfc822_quoted("ed, line, display_name_length); + add_rfc822_quoted("ed, name.buf, name.len); strbuf_add_wrapped_bytes(sb, quoted.buf, quoted.len, -6, 1, max_length); strbuf_release("ed); } else { - strbuf_add_wrapped_bytes(sb, line, display_name_length, - -6, 1, max_length); + strbuf_add_wrapped_bytes(sb, name.buf, name.len, + -6, 1, max_length); } - if (namelen - display_name_length + last_line_length(sb) > max_length) { + if (namelen - name.len + last_line_length(sb) > max_length) strbuf_addch(sb, '\n'); - if (!isspace(name_tail[0])) - strbuf_addch(sb, ' '); - } - strbuf_add(sb, name_tail, namelen - display_name_length); - strbuf_addch(sb, '\n'); + + strbuf_addf(sb, " <%s>\n", mail.buf); } else { - strbuf_addf(sb, "%s: %.*s%.*s\n", what, + strbuf_addf(sb, "%s: %.*s%s <%s>\n", what, (pp->fmt == CMIT_FMT_FULLER) ? 4 : 0, - " ", namelen, line); + " ", name.buf, mail.buf); } + + strbuf_release(&mail); + strbuf_release(&name); + switch (pp->fmt) { case CMIT_FMT_MEDIUM: strbuf_addf(sb, "Date: %s\n", show_date(time, tz, pp->date_mode)); @@@ -524,11 -511,10 +534,11 @@@ static void add_merge_info(const struc strbuf_addch(sb, '\n'); } -static char *get_header(const struct commit *commit, const char *key) +static char *get_header(const struct commit *commit, const char *msg, + const char *key) { int key_len = strlen(key); - const char *line = commit->buffer; + const char *line = msg; while (line) { const char *eol = strchr(line, '\n'), *next; @@@ -589,81 -575,28 +599,81 @@@ char *logmsg_reencode(const struct comm static const char *utf8 = "UTF-8"; const char *use_encoding; char *encoding; + char *msg = commit->buffer; char *out; - if (!*output_encoding) - return NULL; - encoding = get_header(commit, "encoding"); + if (!msg) { + enum object_type type; + unsigned long size; + + msg = read_sha1_file(commit->object.sha1, &type, &size); + if (!msg) + die("Cannot read commit object %s", + sha1_to_hex(commit->object.sha1)); + if (type != OBJ_COMMIT) + die("Expected commit for '%s', got %s", + sha1_to_hex(commit->object.sha1), typename(type)); + } + + if (!output_encoding || !*output_encoding) + return msg; + encoding = get_header(commit, msg, "encoding"); use_encoding = encoding ? encoding : utf8; - if (same_encoding(use_encoding, output_encoding)) - if (encoding) /* we'll strip encoding header later */ - out = xstrdup(commit->buffer); - else - return NULL; /* nothing to do */ - else - out = reencode_string(commit->buffer, - output_encoding, use_encoding); + if (same_encoding(use_encoding, output_encoding)) { + /* + * No encoding work to be done. If we have no encoding header + * at all, then there's nothing to do, and we can return the + * message verbatim (whether newly allocated or not). + */ + if (!encoding) + return msg; + + /* + * Otherwise, we still want to munge the encoding header in the + * result, which will be done by modifying the buffer. If we + * are using a fresh copy, we can reuse it. But if we are using + * the cached copy from commit->buffer, we need to duplicate it + * to avoid munging commit->buffer. + */ + out = msg; + if (out == commit->buffer) + out = xstrdup(out); + } + else { + /* + * There's actual encoding work to do. Do the reencoding, which + * still leaves the header to be replaced in the next step. At + * this point, we are done with msg. If we allocated a fresh + * copy, we can free it. + */ + out = reencode_string(msg, output_encoding, use_encoding); + if (out && msg != commit->buffer) + free(msg); + } + + /* + * This replacement actually consumes the buffer we hand it, so we do + * not have to worry about freeing the old "out" here. + */ if (out) out = replace_encoding_header(out, output_encoding); free(encoding); - return out; + /* + * If the re-encoding failed, out might be NULL here; in that + * case we just return the commit message verbatim. + */ + return out ? out : msg; +} + +void logmsg_free(char *msg, const struct commit *commit) +{ + if (msg != commit->buffer) + free(msg); } -static int mailmap_name(char *email, int email_len, char *name, int name_len) +static int mailmap_name(const char **email, size_t *email_len, + const char **name, size_t *name_len) { static struct string_list *mail_map; if (!mail_map) { @@@ -680,26 -613,36 +690,26 @@@ static size_t format_person_part(struc const int placeholder_len = 2; int tz; unsigned long date = 0; - char person_name[1024]; - char person_mail[1024]; struct ident_split s; - const char *name_start, *name_end, *mail_start, *mail_end; + const char *name, *mail; + size_t maillen, namelen; if (split_ident_line(&s, msg, len) < 0) goto skip; - name_start = s.name_begin; - name_end = s.name_end; - mail_start = s.mail_begin; - mail_end = s.mail_end; - - if (part == 'N' || part == 'E') { /* mailmap lookup */ - snprintf(person_name, sizeof(person_name), "%.*s", - (int)(name_end - name_start), name_start); - snprintf(person_mail, sizeof(person_mail), "%.*s", - (int)(mail_end - mail_start), mail_start); - mailmap_name(person_mail, sizeof(person_mail), person_name, sizeof(person_name)); - name_start = person_name; - name_end = name_start + strlen(person_name); - mail_start = person_mail; - mail_end = mail_start + strlen(person_mail); - } + name = s.name_begin; + namelen = s.name_end - s.name_begin; + mail = s.mail_begin; + maillen = s.mail_end - s.mail_begin; + + if (part == 'N' || part == 'E') /* mailmap lookup */ + mailmap_name(&mail, &maillen, &name, &namelen); if (part == 'n' || part == 'N') { /* name */ - strbuf_add(sb, name_start, name_end-name_start); + strbuf_add(sb, name, namelen); return placeholder_len; } if (part == 'e' || part == 'E') { /* email */ - strbuf_add(sb, mail_start, mail_end-mail_start); + strbuf_add(sb, mail, maillen); return placeholder_len; } @@@ -759,10 -702,8 +769,10 @@@ struct format_commit_context unsigned commit_signature_parsed:1; struct { char *gpg_output; + char *gpg_status; char good_bad; char *signer; + char *key; } signature; char *message; size_t width, indent1, indent2; @@@ -950,13 -891,13 +960,13 @@@ static struct char result; const char *check; } signature_check[] = { - { 'G', ": Good signature from " }, - { 'B', ": BAD signature from " }, + { 'G', "\n[GNUPG:] GOODSIG " }, + { 'B', "\n[GNUPG:] BADSIG " }, }; static void parse_signature_lines(struct format_commit_context *ctx) { - const char *buf = ctx->signature.gpg_output; + const char *buf = ctx->signature.gpg_status; int i; for (i = 0; i < ARRAY_SIZE(signature_check); i++) { @@@ -966,8 -907,6 +976,8 @@@ continue; ctx->signature.good_bad = signature_check[i].result; found += strlen(signature_check[i].check); + ctx->signature.key = xmemdupz(found, 16); + found += 17; next = strchrnul(found, '\n'); ctx->signature.signer = xmemdupz(found, next - found); break; @@@ -979,7 -918,6 +989,7 @@@ static void parse_commit_signature(stru struct strbuf payload = STRBUF_INIT; struct strbuf signature = STRBUF_INIT; struct strbuf gpg_output = STRBUF_INIT; + struct strbuf gpg_status = STRBUF_INIT; int status; ctx->commit_signature_parsed = 1; @@@ -989,15 -927,13 +999,15 @@@ goto out; status = verify_signed_buffer(payload.buf, payload.len, signature.buf, signature.len, - &gpg_output); + &gpg_output, &gpg_status); if (status && !gpg_output.len) goto out; ctx->signature.gpg_output = strbuf_detach(&gpg_output, NULL); + ctx->signature.gpg_status = strbuf_detach(&gpg_status, NULL); parse_signature_lines(ctx); out: + strbuf_release(&gpg_status); strbuf_release(&gpg_output); strbuf_release(&payload); strbuf_release(&signature); @@@ -1034,19 -970,12 +1044,19 @@@ static size_t format_commit_one(struct switch (placeholder[0]) { case 'C': if (placeholder[1] == '(') { - const char *end = strchr(placeholder + 2, ')'); + const char *begin = placeholder + 2; + const char *end = strchr(begin, ')'); char color[COLOR_MAXLEN]; + if (!end) return 0; - color_parse_mem(placeholder + 2, - end - (placeholder + 2), + if (!prefixcmp(begin, "auto,")) { + if (!want_color(c->pretty_ctx->color)) + return end - placeholder + 1; + begin += 5; + } + color_parse_mem(begin, + end - begin, "--pretty format", color); strbuf_addstr(sb, color); return end - placeholder + 1; @@@ -1181,8 -1110,9 +1191,8 @@@ } return 0; /* unknown %g placeholder */ case 'N': - if (c->pretty_ctx->show_notes) { - format_display_notes(commit->object.sha1, sb, - get_log_output_encoding(), 0); + if (c->pretty_ctx->notes_message) { + strbuf_addstr(sb, c->pretty_ctx->notes_message); return 1; } return 0; @@@ -1207,10 -1137,6 +1217,10 @@@ if (c->signature.signer) strbuf_addstr(sb, c->signature.signer); break; + case 'K': + if (c->signature.key) + strbuf_addstr(sb, c->signature.key); + break; } return 2; } @@@ -1335,18 -1261,29 +1345,18 @@@ void format_commit_message(const struc const struct pretty_print_context *pretty_ctx) { struct format_commit_context context; - static const char utf8[] = "UTF-8"; const char *output_enc = pretty_ctx->output_encoding; memset(&context, 0, sizeof(context)); context.commit = commit; context.pretty_ctx = pretty_ctx; context.wrap_start = sb->len; - context.message = commit->buffer; - if (output_enc) { - char *enc = get_header(commit, "encoding"); - if (strcmp(enc ? enc : utf8, output_enc)) { - context.message = logmsg_reencode(commit, output_enc); - if (!context.message) - context.message = commit->buffer; - } - free(enc); - } + context.message = logmsg_reencode(commit, output_enc); strbuf_expand(sb, format, format_commit_item, &context); rewrap_message_tail(sb, &context, 0, 0, 0); - if (context.message != commit->buffer) - free(context.message); + logmsg_free(context.message, commit); free(context.signature.gpg_output); free(context.signature.signer); } @@@ -1376,7 -1313,7 +1386,7 @@@ static void pp_header(const struct pret continue; } - if (!memcmp(line, "parent ", 7)) { + if (!prefixcmp(line, "parent ")) { if (linelen != 48) die("bad parent line in commit"); continue; @@@ -1400,11 -1337,11 +1410,11 @@@ * FULL shows both authors but not dates. * FULLER shows both authors and dates. */ - if (!memcmp(line, "author ", 7)) { + if (!prefixcmp(line, "author ")) { strbuf_grow(sb, linelen + 80); pp_user_info(pp, "Author", sb, line + 7, encoding); } - if (!memcmp(line, "committer ", 10) && + if (!prefixcmp(line, "committer ") && (pp->fmt == CMIT_FMT_FULL || pp->fmt == CMIT_FMT_FULLER)) { strbuf_grow(sb, linelen + 80); pp_user_info(pp, "Commit", sb, line + 10, encoding); @@@ -1487,13 -1424,23 +1497,13 @@@ void pp_remainder(const struct pretty_p } } -char *reencode_commit_message(const struct commit *commit, const char **encoding_p) -{ - const char *encoding; - - encoding = get_log_output_encoding(); - if (encoding_p) - *encoding_p = encoding; - return logmsg_reencode(commit, encoding); -} - void pretty_print_commit(const struct pretty_print_context *pp, const struct commit *commit, struct strbuf *sb) { unsigned long beginning_of_body; int indent = 4; - const char *msg = commit->buffer; + const char *msg; char *reencoded; const char *encoding; int need_8bit_cte = pp->need_8bit_cte; @@@ -1503,8 -1450,10 +1513,8 @@@ return; } - reencoded = reencode_commit_message(commit, &encoding); - if (reencoded) { - msg = reencoded; - } + encoding = get_log_output_encoding(); + msg = reencoded = logmsg_reencode(commit, encoding); if (pp->fmt == CMIT_FMT_ONELINE || pp->fmt == CMIT_FMT_EMAIL) indent = 0; @@@ -1561,7 -1510,11 +1571,7 @@@ if (pp->fmt == CMIT_FMT_EMAIL && sb->len <= beginning_of_body) strbuf_addch(sb, '\n'); - if (pp->show_notes) - format_display_notes(commit->object.sha1, sb, encoding, - NOTES_SHOW_HEADER | NOTES_INDENT); - - free(reencoded); + logmsg_free(reencoded, commit); } void pp_commit_easy(enum cmit_fmt fmt, const struct commit *commit, diff --combined t/t4014-format-patch.sh index 7fa3647514,ba437379bc..bb1fc47fe8 --- a/t/t4014-format-patch.sh +++ b/t/t4014-format-patch.sh @@@ -155,7 -155,7 +155,7 @@@ test_expect_failure 'additional comman git config --replace-all format.headers "Cc: R E Cipient " && git format-patch --cc="S. E. Cipient " --stdout master..side | sed -e "/^\$/q" >patch5 && grep "^Cc: R E Cipient ,\$" patch5 && - grep "^ *"S. E. Cipient" \$" patch5 + grep "^ *\"S. E. Cipient\" \$" patch5 ' test_expect_success 'command line headers' ' @@@ -183,7 -183,7 +183,7 @@@ test_expect_success 'command line To: h test_expect_failure 'command line To: header (rfc822)' ' git format-patch --to="R. E. Cipient " --stdout master..side | sed -e "/^\$/q" >patch8 && - grep "^To: "R. E. Cipient" \$" patch8 + grep "^To: \"R. E. Cipient\" \$" patch8 ' test_expect_failure 'command line To: header (rfc2047)' ' @@@ -203,7 -203,7 +203,7 @@@ test_expect_failure 'configuration To: git config format.to "R. E. Cipient " && git format-patch --stdout master..side | sed -e "/^\$/q" >patch9 && - grep "^To: "R. E. Cipient" \$" patch9 + grep "^To: \"R. E. Cipient\" \$" patch9 ' test_expect_failure 'configuration To: header (rfc2047)' ' @@@ -271,22 -271,6 +271,22 @@@ test_expect_success 'multiple files' ls patches/0001-Side-changes-1.patch patches/0002-Side-changes-2.patch patches/0003-Side-changes-3-with-n-backslash-n-in-it.patch ' +test_expect_success 'reroll count' ' + rm -fr patches && + git format-patch -o patches --cover-letter --reroll-count 4 master..side >list && + ! grep -v "^patches/v4-000[0-3]-" list && + sed -n -e "/^Subject: /p" $(cat list) >subjects && + ! grep -v "^Subject: \[PATCH v4 [0-3]/3\] " subjects +' + +test_expect_success 'reroll count (-v)' ' + rm -fr patches && + git format-patch -o patches --cover-letter -v4 master..side >list && + ! grep -v "^patches/v4-000[0-3]-" list && + sed -n -e "/^Subject: /p" $(cat list) >subjects && + ! grep -v "^Subject: \[PATCH v4 [0-3]/3\] " subjects +' + check_threading () { expect="$1" && shift && @@@ -666,19 -650,8 +666,19 @@@ test_expect_success 'format-patch --in- ' test_expect_success 'format-patch --signoff' ' - git format-patch -1 --signoff --stdout | - grep "^Signed-off-by: $GIT_COMMITTER_NAME <$GIT_COMMITTER_EMAIL>" + git format-patch -1 --signoff --stdout >out && + grep "^Signed-off-by: $GIT_COMMITTER_NAME <$GIT_COMMITTER_EMAIL>" out +' + +test_expect_success 'format-patch --notes --signoff' ' + git notes --ref test add -m "test message" HEAD && + git format-patch -1 --signoff --stdout --notes=test >out && + # Three dashes must come after S-o-b + ! sed "/^Signed-off-by: /q" out | grep "test message" && + sed "1,/^Signed-off-by: /d" out | grep "test message" && + # Notes message must come after three dashes + ! sed "/^---$/q" out | grep "test message" && + sed "1,/^---$/d" out | grep "test message" ' echo "fatal: --name-only does not make sense" > expect.name-only @@@ -837,25 -810,26 +837,26 @@@ Subject: [PATCH] =?UTF-8?q?f=C3=B6=C3=B =?UTF-8?q?=C3=B6=C3=B6=20bar=20f=C3=B6=C3=B6=20bar=20f=C3=B6=C3=B6=20bar?= =?UTF-8?q?=20f=C3=B6=C3=B6=20bar=20f=C3=B6=C3=B6=20bar=20f=C3=B6=C3=B6=20?= =?UTF-8?q?bar=20f=C3=B6=C3=B6=20bar=20f=C3=B6=C3=B6=20bar=20f=C3=B6=C3=B6?= - =?UTF-8?q?=20bar=20f=C3=B6=C3=B6=20bar=20f=C3=B6=C3=B6=20bar=20f=C3=B6=C3?= - =?UTF-8?q?=B6=20bar=20f=C3=B6=C3=B6=20bar=20f=C3=B6=C3=B6=20bar=20f=C3=B6?= - =?UTF-8?q?=C3=B6=20bar=20f=C3=B6=C3=B6=20bar=20f=C3=B6=C3=B6=20bar=20f=C3?= - =?UTF-8?q?=B6=C3=B6=20bar=20f=C3=B6=C3=B6=20bar=20f=C3=B6=C3=B6=20bar=20f?= + =?UTF-8?q?=20bar=20f=C3=B6=C3=B6=20bar=20f=C3=B6=C3=B6=20bar=20f=C3=B6?= + =?UTF-8?q?=C3=B6=20bar=20f=C3=B6=C3=B6=20bar=20f=C3=B6=C3=B6=20bar=20f?= =?UTF-8?q?=C3=B6=C3=B6=20bar=20f=C3=B6=C3=B6=20bar=20f=C3=B6=C3=B6=20bar?= =?UTF-8?q?=20f=C3=B6=C3=B6=20bar=20f=C3=B6=C3=B6=20bar=20f=C3=B6=C3=B6=20?= =?UTF-8?q?bar=20f=C3=B6=C3=B6=20bar=20f=C3=B6=C3=B6=20bar=20f=C3=B6=C3=B6?= - =?UTF-8?q?=20bar=20f=C3=B6=C3=B6=20bar=20f=C3=B6=C3=B6=20bar=20f=C3=B6=C3?= - =?UTF-8?q?=B6=20bar=20f=C3=B6=C3=B6=20bar=20f=C3=B6=C3=B6=20bar=20f=C3=B6?= - =?UTF-8?q?=C3=B6=20bar=20f=C3=B6=C3=B6=20bar=20f=C3=B6=C3=B6=20bar=20f=C3?= - =?UTF-8?q?=B6=C3=B6=20bar=20f=C3=B6=C3=B6=20bar=20f=C3=B6=C3=B6=20bar=20f?= + =?UTF-8?q?=20bar=20f=C3=B6=C3=B6=20bar=20f=C3=B6=C3=B6=20bar=20f=C3=B6?= + =?UTF-8?q?=C3=B6=20bar=20f=C3=B6=C3=B6=20bar=20f=C3=B6=C3=B6=20bar=20f?= =?UTF-8?q?=C3=B6=C3=B6=20bar=20f=C3=B6=C3=B6=20bar=20f=C3=B6=C3=B6=20bar?= =?UTF-8?q?=20f=C3=B6=C3=B6=20bar=20f=C3=B6=C3=B6=20bar=20f=C3=B6=C3=B6=20?= =?UTF-8?q?bar=20f=C3=B6=C3=B6=20bar=20f=C3=B6=C3=B6=20bar=20f=C3=B6=C3=B6?= - =?UTF-8?q?=20bar=20f=C3=B6=C3=B6=20bar=20f=C3=B6=C3=B6=20bar=20f=C3=B6=C3?= - =?UTF-8?q?=B6=20bar=20f=C3=B6=C3=B6=20bar=20f=C3=B6=C3=B6=20bar=20f=C3=B6?= - =?UTF-8?q?=C3=B6=20bar=20f=C3=B6=C3=B6=20bar=20f=C3=B6=C3=B6=20bar=20f=C3?= - =?UTF-8?q?=B6=C3=B6=20bar=20f=C3=B6=C3=B6=20bar=20f=C3=B6=C3=B6=20bar=20f?= - =?UTF-8?q?=C3=B6=C3=B6=20bar=20f=C3=B6=C3=B6=20bar?= + =?UTF-8?q?=20bar=20f=C3=B6=C3=B6=20bar=20f=C3=B6=C3=B6=20bar=20f=C3=B6?= + =?UTF-8?q?=C3=B6=20bar=20f=C3=B6=C3=B6=20bar=20f=C3=B6=C3=B6=20bar=20f?= + =?UTF-8?q?=C3=B6=C3=B6=20bar=20f=C3=B6=C3=B6=20bar=20f=C3=B6=C3=B6=20bar?= + =?UTF-8?q?=20f=C3=B6=C3=B6=20bar=20f=C3=B6=C3=B6=20bar=20f=C3=B6=C3=B6=20?= + =?UTF-8?q?bar=20f=C3=B6=C3=B6=20bar=20f=C3=B6=C3=B6=20bar=20f=C3=B6=C3=B6?= + =?UTF-8?q?=20bar=20f=C3=B6=C3=B6=20bar=20f=C3=B6=C3=B6=20bar=20f=C3=B6?= + =?UTF-8?q?=C3=B6=20bar=20f=C3=B6=C3=B6=20bar=20f=C3=B6=C3=B6=20bar=20f?= + =?UTF-8?q?=C3=B6=C3=B6=20bar=20f=C3=B6=C3=B6=20bar=20f=C3=B6=C3=B6=20bar?= + =?UTF-8?q?=20f=C3=B6=C3=B6=20bar=20f=C3=B6=C3=B6=20bar=20f=C3=B6=C3=B6=20?= + =?UTF-8?q?bar?= EOF test_expect_success 'format-patch wraps extremely long subject (rfc2047)' ' rm -rf patches/ && @@@ -979,46 -953,4 +980,46 @@@ test_expect_success 'format patch ignor test_cmp expect actual ' +test_expect_success 'cover letter using branch description (1)' ' + git checkout rebuild-1 && + test_config branch.rebuild-1.description hello && + git format-patch --stdout --cover-letter master >actual && + grep hello actual >/dev/null +' + +test_expect_success 'cover letter using branch description (2)' ' + git checkout rebuild-1 && + test_config branch.rebuild-1.description hello && + git format-patch --stdout --cover-letter rebuild-1~2..rebuild-1 >actual && + grep hello actual >/dev/null +' + +test_expect_success 'cover letter using branch description (3)' ' + git checkout rebuild-1 && + test_config branch.rebuild-1.description hello && + git format-patch --stdout --cover-letter ^master rebuild-1 >actual && + grep hello actual >/dev/null +' + +test_expect_success 'cover letter using branch description (4)' ' + git checkout rebuild-1 && + test_config branch.rebuild-1.description hello && + git format-patch --stdout --cover-letter master.. >actual && + grep hello actual >/dev/null +' + +test_expect_success 'cover letter using branch description (5)' ' + git checkout rebuild-1 && + test_config branch.rebuild-1.description hello && + git format-patch --stdout --cover-letter -2 HEAD >actual && + grep hello actual >/dev/null +' + +test_expect_success 'cover letter using branch description (6)' ' + git checkout rebuild-1 && + test_config branch.rebuild-1.description hello && + git format-patch --stdout --cover-letter -2 >actual && + grep hello actual >/dev/null +' + test_done diff --combined utf8.c index 8f6e84b7b3,0b30b54847..7f648574a5 --- a/utf8.c +++ b/utf8.c @@@ -323,7 -323,7 +323,7 @@@ static size_t display_mode_esc_sequence * If indent is negative, assume that already -indent columns have been * consumed (and no extra indent is necessary for the first line). */ -int strbuf_add_wrapped_text(struct strbuf *buf, +void strbuf_add_wrapped_text(struct strbuf *buf, const char *text, int indent1, int indent2, int width) { int indent, w, assume_utf8 = 1; @@@ -332,7 -332,7 +332,7 @@@ if (width <= 0) { strbuf_add_indented_text(buf, text, indent1, indent2); - return 1; + return; } retry: @@@ -356,14 -356,14 +356,14 @@@ if (w <= width || !space) { const char *start = bol; if (!c && text == start) - return w; + return; if (space) start = space; else strbuf_addchars(buf, ' ', indent); strbuf_add(buf, start, text - start); if (!c) - return w; + return; space = text; if (c == '\t') w |= 0x07; @@@ -405,12 -405,13 +405,12 @@@ new_line } } -int strbuf_add_wrapped_bytes(struct strbuf *buf, const char *data, int len, +void strbuf_add_wrapped_bytes(struct strbuf *buf, const char *data, int len, int indent, int indent2, int width) { char *tmp = xstrndup(data, len); - int r = strbuf_add_wrapped_text(buf, tmp, indent, indent2, width); + strbuf_add_wrapped_text(buf, tmp, indent, indent2, width); free(tmp); - return r; } int is_encoding_utf8(const char *name) @@@ -429,27 -430,6 +429,27 @@@ int same_encoding(const char *src, cons return !strcasecmp(src, dst); } +/* + * Wrapper for fprintf and returns the total number of columns required + * for the printed string, assuming that the string is utf8. + */ +int utf8_fprintf(FILE *stream, const char *format, ...) +{ + struct strbuf buf = STRBUF_INIT; + va_list arg; + int columns; + + va_start(arg, format); + strbuf_vaddf(&buf, format, arg); + va_end(arg); + + columns = fputs(buf.buf, stream); + if (0 <= columns) /* keep the error from the I/O */ + columns = utf8_strwidth(buf.buf); + strbuf_release(&buf); + return columns; +} + /* * Given a buffer and its encoding, return it re-encoded * with iconv. If the conversion fails, returns NULL. @@@ -507,27 -487,50 +507,66 @@@ char *reencode_string(const char *in, c if (!in_encoding) return NULL; + conv = iconv_open(out_encoding, in_encoding); - if (conv == (iconv_t) -1) - return NULL; + if (conv == (iconv_t) -1) { + /* + * Some platforms do not have the variously spelled variants of + * UTF-8, so let's fall back to trying the most official + * spelling. We do so only as a fallback in case the platform + * does understand the user's spelling, but not our official + * one. + */ + if (is_encoding_utf8(in_encoding)) + in_encoding = "UTF-8"; + if (is_encoding_utf8(out_encoding)) + out_encoding = "UTF-8"; + conv = iconv_open(out_encoding, in_encoding); + if (conv == (iconv_t) -1) + return NULL; + } + out = reencode_string_iconv(in, strlen(in), conv); iconv_close(conv); return out; } #endif + + /* + * Returns first character length in bytes for multi-byte `text` according to + * `encoding`. + * + * - The `text` pointer is updated to point at the next character. + * - When `remainder_p` is not NULL, on entry `*remainder_p` is how much bytes + * we can consume from text, and on exit `*remainder_p` is reduced by returned + * character length. Otherwise `text` is treated as limited by NUL. + */ + int mbs_chrlen(const char **text, size_t *remainder_p, const char *encoding) + { + int chrlen; + const char *p = *text; + size_t r = (remainder_p ? *remainder_p : SIZE_MAX); + + if (r < 1) + return 0; + + if (is_encoding_utf8(encoding)) { + pick_one_utf8_char(&p, &r); + + chrlen = p ? (p - *text) + : 1 /* not valid UTF-8 -> raw byte sequence */; + } + else { + /* + * TODO use iconv to decode one char and obtain its chrlen + * for now, let's treat encodings != UTF-8 as one-byte + */ + chrlen = 1; + } + + *text += chrlen; + if (remainder_p) + *remainder_p -= chrlen; + + return chrlen; + } diff --combined utf8.h index 501b2bd9c4,465c01d8c3..1f8ecad1e8 --- a/utf8.h +++ b/utf8.h @@@ -8,11 -8,10 +8,11 @@@ int utf8_strwidth(const char *string) int is_utf8(const char *text); int is_encoding_utf8(const char *name); int same_encoding(const char *, const char *); +int utf8_fprintf(FILE *, const char *, ...); -int strbuf_add_wrapped_text(struct strbuf *buf, +void strbuf_add_wrapped_text(struct strbuf *buf, const char *text, int indent, int indent2, int width); -int strbuf_add_wrapped_bytes(struct strbuf *buf, const char *data, int len, +void strbuf_add_wrapped_bytes(struct strbuf *buf, const char *data, int len, int indent, int indent2, int width); #ifndef NO_ICONV @@@ -22,4 -21,6 +22,6 @@@ char *reencode_string(const char *in, c #define reencode_string(a,b,c) NULL #endif + int mbs_chrlen(const char **text, size_t *remainder_p, const char *encoding); + #endif