From 14e1a4e1ff70aff36db3f5d2a8b806efd0134d50 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Jan=20H=2E=20Sch=C3=B6nherr?= Date: Thu, 18 Oct 2012 16:43:28 +0200 Subject: [PATCH 1/7] utf8: fix off-by-one wrapping of text MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The wrapping logic in strbuf_add_wrapped_text() does currently not allow lines that entirely fill the allowed width, instead it wraps the line one character too early. For example, the text "This is the sixth commit." formatted via "%w(11,1,2)" (wrap at 11 characters, 1 char indent of first line, 2 char indent of following lines) results in four lines: " This is", " the", " sixth", " commit." This is wrong, because " the sixth" is exactly 11 characters long, and thus allowed. Fix this by allowing the (width+1) character of a line to be a valid wrapping point if it is a whitespace character. Signed-off-by: Jan H. Schönherr Signed-off-by: Junio C Hamano --- t/t4202-log.sh | 4 ++-- utf8.c | 2 +- 2 files changed, 3 insertions(+), 3 deletions(-) diff --git a/t/t4202-log.sh b/t/t4202-log.sh index 45058cc8cb..37023e30ea 100755 --- a/t/t4202-log.sh +++ b/t/t4202-log.sh @@ -72,9 +72,9 @@ cat > expect << EOF commit. EOF -test_expect_success 'format %w(12,1,2)' ' +test_expect_success 'format %w(11,1,2)' ' - git log -2 --format="%w(12,1,2)This is the %s commit." > actual && + git log -2 --format="%w(11,1,2)This is the %s commit." > actual && test_cmp expect actual ' diff --git a/utf8.c b/utf8.c index 8acbc660d3..523a78a651 100644 --- a/utf8.c +++ b/utf8.c @@ -353,7 +353,7 @@ retry: c = *text; if (!c || isspace(c)) { - if (w < width || !space) { + if (w <= width || !space) { const char *start = bol; if (!c && text == start) return w; From 7a76e68a177720da65e7d9cfa49d702a55e2d9de Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Jan=20H=2E=20Sch=C3=B6nherr?= Date: Thu, 18 Oct 2012 16:43:29 +0200 Subject: [PATCH 2/7] format-patch: do not wrap non-rfc2047 headers too early MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Do not wrap the second and later lines of non-rfc2047-encoded headers substantially before the 78 character limit. Instead of passing the remaining length of the first line as wrapping width, use the correct maximum length and tell strbuf_add_wrapped_bytes() how many characters of the first line are already used. Signed-off-by: Jan H. Schönherr Signed-off-by: Junio C Hamano --- pretty.c | 2 +- t/t4014-format-patch.sh | 60 +++++++++++++++++++++++------------------ 2 files changed, 35 insertions(+), 27 deletions(-) diff --git a/pretty.c b/pretty.c index 8b1ea9ffad..71e4024663 100644 --- a/pretty.c +++ b/pretty.c @@ -286,7 +286,7 @@ static void add_rfc2047(struct strbuf *sb, const char *line, int len, if ((i + 1 < len) && (ch == '=' && line[i+1] == '?')) goto needquote; } - strbuf_add_wrapped_bytes(sb, line, len, 0, 1, max_length - line_len); + strbuf_add_wrapped_bytes(sb, line, len, -line_len, 1, max_length); return; needquote: diff --git a/t/t4014-format-patch.sh b/t/t4014-format-patch.sh index 959aa26ef5..d66e358301 100755 --- a/t/t4014-format-patch.sh +++ b/t/t4014-format-patch.sh @@ -752,16 +752,14 @@ M64=$M8$M8$M8$M8$M8$M8$M8$M8 M512=$M64$M64$M64$M64$M64$M64$M64$M64 cat >expect <<'EOF' Subject: [PATCH] foo bar foo bar foo bar foo bar foo bar foo bar foo bar foo - bar foo bar foo bar foo bar foo bar foo bar foo bar foo bar - foo bar foo bar foo bar foo bar foo bar foo bar foo bar foo - bar foo bar foo bar foo bar foo bar foo bar foo bar foo bar - foo bar foo bar foo bar foo bar foo bar foo bar foo bar foo - bar foo bar foo bar foo bar foo bar foo bar foo bar foo bar - foo bar foo bar foo bar foo bar foo bar foo bar foo bar foo - bar foo bar foo bar foo bar foo bar foo bar foo bar foo bar - foo bar foo bar foo bar foo bar + bar foo bar foo bar foo bar foo bar foo bar foo bar foo bar foo bar foo bar + foo bar foo bar foo bar foo bar foo bar foo bar foo bar foo bar foo bar foo + bar foo bar foo bar foo bar foo bar foo bar foo bar foo bar foo bar foo bar + foo bar foo bar foo bar foo bar foo bar foo bar foo bar foo bar foo bar foo + bar foo bar foo bar foo bar foo bar foo bar foo bar foo bar foo bar foo bar + foo bar foo bar foo bar foo bar foo bar foo bar foo bar foo bar foo bar EOF -test_expect_success 'format-patch wraps extremely long headers (ascii)' ' +test_expect_success 'format-patch wraps extremely long subject (ascii)' ' echo content >>file && git add file && git commit -m "$M512" && @@ -807,28 +805,12 @@ test_expect_success 'format-patch wraps extremely long headers (rfc2047)' ' test_cmp expect subject ' -M8="foo_bar_" -M64=$M8$M8$M8$M8$M8$M8$M8$M8 -cat >expect < -EOF -test_expect_success 'format-patch wraps non-quotable headers' ' - rm -rf patches/ && - echo content >>file && - git add file && - git commit -mfoo --author "$M64 " && - git format-patch --stdout -1 >patch && - sed -n "/^From: /p; /^ /p; /^$/q" from && - test_cmp expect from -' - check_author() { echo content >>file && git add file && GIT_AUTHOR_NAME=$1 git commit -m author-check && git format-patch --stdout -1 >patch && - grep ^From: patch >actual && + sed -n "/^From: /p; /^ /p; /^$/q" actual && test_cmp expect actual } @@ -853,6 +835,32 @@ test_expect_success 'rfc2047-encoded headers also double-quote 822 specials' ' check_author "Föo B. Bar" ' +cat >expect < +EOF +test_expect_success 'format-patch wraps moderately long from-header (ascii)' ' + check_author "foo_bar_foo_bar_foo_bar_foo_bar_foo_bar_foo_bar_foo_bar_foo_bar_" +' + +cat >expect <<'EOF' +From: Foo Bar Foo Bar Foo Bar Foo Bar Foo Bar Foo Bar Foo Bar Foo Bar Foo Bar + Foo Bar Foo Bar Foo Bar Foo Bar Foo Bar Foo Bar Foo Bar Foo Bar Foo Bar Foo + Bar Foo Bar Foo Bar Foo Bar +EOF +test_expect_success 'format-patch wraps extremely long from-header (ascii)' ' + check_author "Foo Bar Foo Bar Foo Bar Foo Bar Foo Bar Foo Bar Foo Bar Foo Bar Foo Bar Foo Bar Foo Bar Foo Bar Foo Bar Foo Bar Foo Bar Foo Bar Foo Bar Foo Bar Foo Bar Foo Bar Foo Bar Foo Bar" +' + +cat >expect <<'EOF' +From: "Foo.Bar Foo Bar Foo Bar Foo Bar Foo Bar Foo Bar Foo Bar Foo Bar Foo Bar + Foo Bar Foo Bar Foo Bar Foo Bar Foo Bar Foo Bar Foo Bar Foo Bar Foo Bar Foo + Bar Foo Bar Foo Bar Foo Bar" +EOF +test_expect_success 'format-patch wraps extremely long from-header (rfc822)' ' + check_author "Foo.Bar Foo Bar Foo Bar Foo Bar Foo Bar Foo Bar Foo Bar Foo Bar Foo Bar Foo Bar Foo Bar Foo Bar Foo Bar Foo Bar Foo Bar Foo Bar Foo Bar Foo Bar Foo Bar Foo Bar Foo Bar Foo Bar" +' + cat >expect <<'EOF' Subject: header with . in it EOF From 94f6cdf693c10eaec5a7fcc4f0b5cb1e0ea80f1b Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Jan=20H=2E=20Sch=C3=B6nherr?= Date: Thu, 18 Oct 2012 16:43:30 +0200 Subject: [PATCH 3/7] format-patch: do not wrap rfc2047 encoded headers too late MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Encoded characters add more than one character at once to an encoded header. Include all characters that are about to be added in the length calculation for wrapping. Additionally, RFC 2047 imposes a maximum line length of 76 characters if that line contains an rfc2047 encoded word. Signed-off-by: Jan H. Schönherr Signed-off-by: Junio C Hamano --- pretty.c | 26 +++++++++++------- t/t4014-format-patch.sh | 58 +++++++++++++++++++++++++---------------- 2 files changed, 51 insertions(+), 33 deletions(-) diff --git a/pretty.c b/pretty.c index 71e4024663..da75879999 100644 --- a/pretty.c +++ b/pretty.c @@ -263,6 +263,9 @@ static void add_rfc822_quoted(struct strbuf *out, const char *s, int len) static int is_rfc2047_special(char ch) { + if (ch == ' ' || ch == '\n') + return 1; + return (non_ascii(ch) || (ch == '=') || (ch == '?') || (ch == '_')); } @@ -270,6 +273,7 @@ static void add_rfc2047(struct strbuf *sb, const char *line, int len, const char *encoding) { static const int max_length = 78; /* per rfc2822 */ + static const int max_encoded_length = 76; /* per rfc2047 */ int i; int line_len; @@ -295,23 +299,25 @@ needquote: 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); - if (line_len >= max_length - 2) { + /* + * According to RFC 2047, we could encode the special character + * ' ' (space) with '_' (underscore) for readability. But many + * programs do not understand this and just leave the + * underscore in place. Thus, we do nothing special here, which + * causes ' ' to be encoded as '=20', avoiding this problem. + */ + + if (line_len + 2 + (is_special ? 3 : 1) > max_encoded_length) { strbuf_addf(sb, "?=\n =?%s?q?", encoding); line_len = strlen(encoding) + 5 + 1; /* =??q? plus SP */ } - /* - * We encode ' ' using '=20' even though rfc2047 - * allows using '_' for readability. Unfortunately, - * many programs do not understand this and just - * leave the underscore in place. - */ - if (is_rfc2047_special(ch) || ch == ' ' || ch == '\n') { + if (is_special) { strbuf_addf(sb, "=%02X", ch); line_len += 3; - } - else { + } else { strbuf_addch(sb, ch); line_len++; } diff --git a/t/t4014-format-patch.sh b/t/t4014-format-patch.sh index d66e358301..1d5636d8a0 100755 --- a/t/t4014-format-patch.sh +++ b/t/t4014-format-patch.sh @@ -772,30 +772,31 @@ M8="föö bar " M64=$M8$M8$M8$M8$M8$M8$M8$M8 M512=$M64$M64$M64$M64$M64$M64$M64$M64 cat >expect <<'EOF' -Subject: [PATCH] =?UTF-8?q?f=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=B6?= - =?UTF-8?q?=C3=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=B6?= - =?UTF-8?q?=C3=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=B6?= - =?UTF-8?q?=C3=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=B6?= - =?UTF-8?q?=C3=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=B6?= - =?UTF-8?q?=C3=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=B6?= - =?UTF-8?q?=C3=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=B6?= - =?UTF-8?q?=C3=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=B6?= - =?UTF-8?q?=C3=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=B6?= - =?UTF-8?q?=C3=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=B6?= - =?UTF-8?q?=C3=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?= +Subject: [PATCH] =?UTF-8?q?f=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=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=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?= EOF -test_expect_success 'format-patch wraps extremely long headers (rfc2047)' ' +test_expect_success 'format-patch wraps extremely long subject (rfc2047)' ' rm -rf patches/ && echo content >>file && git add file && @@ -861,6 +862,17 @@ test_expect_success 'format-patch wraps extremely long from-header (rfc822)' ' check_author "Foo.Bar Foo Bar Foo Bar Foo Bar Foo Bar Foo Bar Foo Bar Foo Bar Foo Bar Foo Bar Foo Bar Foo Bar Foo Bar Foo Bar Foo Bar Foo Bar Foo Bar Foo Bar Foo Bar Foo Bar Foo Bar Foo Bar" ' +cat >expect <<'EOF' +From: =?UTF-8?q?Fo=C3=B6=20Bar=20Foo=20Bar=20Foo=20Bar=20Foo=20Bar=20Foo?= + =?UTF-8?q?=20Bar=20Foo=20Bar=20Foo=20Bar=20Foo=20Bar=20Foo=20Bar=20Foo=20?= + =?UTF-8?q?Bar=20Foo=20Bar=20Foo=20Bar=20Foo=20Bar=20Foo=20Bar=20Foo=20Bar?= + =?UTF-8?q?=20Foo=20Bar=20Foo=20Bar=20Foo=20Bar=20Foo=20Bar=20Foo=20Bar=20?= + =?UTF-8?q?Foo=20Bar=20Foo=20Bar?= +EOF +test_expect_success 'format-patch wraps extremely long from-header (rfc2047)' ' + check_author "Foö Bar Foo Bar Foo Bar Foo Bar Foo Bar Foo Bar Foo Bar Foo Bar Foo Bar Foo Bar Foo Bar Foo Bar Foo Bar Foo Bar Foo Bar Foo Bar Foo Bar Foo Bar Foo Bar Foo Bar Foo Bar Foo Bar" +' + cat >expect <<'EOF' Subject: header with . in it EOF From f9b7204b6d10a1429271fde8cbcdee56beb0e035 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Jan=20H=2E=20Sch=C3=B6nherr?= Date: Thu, 18 Oct 2012 16:43:31 +0200 Subject: [PATCH 4/7] format-patch: introduce helper function last_line_length() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Currently, an open-coded loop to calculate the length of the last line of a string buffer is used in multiple places. Move that code into a function of its own. Signed-off-by: Jan H. Schönherr Signed-off-by: Junio C Hamano --- pretty.c | 25 +++++++++++++------------ 1 file changed, 13 insertions(+), 12 deletions(-) diff --git a/pretty.c b/pretty.c index da75879999..482402d283 100644 --- a/pretty.c +++ b/pretty.c @@ -240,6 +240,17 @@ static int has_rfc822_specials(const char *s, int len) return 0; } +static int last_line_length(struct strbuf *sb) +{ + int i; + + /* How many bytes are already used on the last line? */ + for (i = sb->len - 1; i >= 0; i--) + if (sb->buf[i] == '\n') + break; + return sb->len - (i + 1); +} + static void add_rfc822_quoted(struct strbuf *out, const char *s, int len) { int i; @@ -275,13 +286,7 @@ static void add_rfc2047(struct strbuf *sb, const char *line, int len, static const int max_length = 78; /* per rfc2822 */ static const int max_encoded_length = 76; /* per rfc2047 */ int i; - int line_len; - - /* How many bytes are already used on the current line? */ - for (i = sb->len - 1; i >= 0; i--) - if (sb->buf[i] == '\n') - break; - line_len = sb->len - (i+1); + int line_len = last_line_length(sb); for (i = 0; i < len; i++) { int ch = line[i]; @@ -346,7 +351,6 @@ void pp_user_info(const struct pretty_print_context *pp, if (pp->fmt == CMIT_FMT_EMAIL) { char *name_tail = strchr(line, '<'); int display_name_length; - int final_line; if (!name_tail) return; while (line < name_tail && isspace(name_tail[-1])) @@ -361,10 +365,7 @@ void pp_user_info(const struct pretty_print_context *pp, add_rfc2047(sb, quoted.buf, quoted.len, encoding); strbuf_release("ed); } - for (final_line = 0; final_line < sb->len; final_line++) - if (sb->buf[sb->len - final_line - 1] == '\n') - break; - if (namelen - display_name_length + final_line > 78) { + if (namelen - display_name_length + last_line_length(sb) > 78) { strbuf_addch(sb, '\n'); if (!isspace(name_tail[0])) strbuf_addch(sb, ' '); From 0fcec2ce5467740eb613da6a977deca3e7e866ba Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Jan=20H=2E=20Sch=C3=B6nherr?= Date: Thu, 18 Oct 2012 16:43:32 +0200 Subject: [PATCH 5/7] format-patch: make rfc2047 encoding more strict MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit RFC 2047 requires more characters to be encoded than it is currently done. Especially, RFC 2047 distinguishes between allowed remaining characters in encoded words in addresses (From, To, etc.) and other headers, such as Subject. Make add_rfc2047() and is_rfc2047_special() location dependent and include all non-allowed characters to hopefully be RFC 2047 conformant. This especially fixes a problem, where RFC 822 specials (e. g. ".") were left unencoded in addresses, which was solved with a non-standard-conforming workaround in the past (which is going to be removed in a follow-up patch). Signed-off-by: Jan H. Schönherr Signed-off-by: Junio C Hamano --- git-compat-util.h | 2 ++ pretty.c | 67 ++++++++++++++++++++++++++++++++++++----- t/t4014-format-patch.sh | 15 ++++++--- 3 files changed, 72 insertions(+), 12 deletions(-) diff --git a/git-compat-util.h b/git-compat-util.h index 5bd9ad7d2a..f011a8d7bb 100644 --- a/git-compat-util.h +++ b/git-compat-util.h @@ -466,6 +466,7 @@ extern const char tolower_trans_tbl[256]; #undef isdigit #undef isalpha #undef isalnum +#undef isprint #undef islower #undef isupper #undef tolower @@ -483,6 +484,7 @@ extern unsigned char sane_ctype[256]; #define isdigit(x) sane_istest(x,GIT_DIGIT) #define isalpha(x) sane_istest(x,GIT_ALPHA) #define isalnum(x) sane_istest(x,GIT_ALPHA | GIT_DIGIT) +#define isprint(x) ((x) >= 0x20 && (x) <= 0x7e) #define islower(x) sane_iscase(x, 1) #define isupper(x) sane_iscase(x, 0) #define is_glob_special(x) sane_istest(x,GIT_GLOB_SPECIAL) diff --git a/pretty.c b/pretty.c index 482402d283..613e4eab0d 100644 --- a/pretty.c +++ b/pretty.c @@ -272,16 +272,65 @@ static void add_rfc822_quoted(struct strbuf *out, const char *s, int len) strbuf_addch(out, '"'); } -static int is_rfc2047_special(char ch) +enum rfc2047_type { + RFC2047_SUBJECT, + RFC2047_ADDRESS, +}; + +static int is_rfc2047_special(char ch, enum rfc2047_type type) { - if (ch == ' ' || ch == '\n') + /* + * rfc2047, section 4.2: + * + * 8-bit values which correspond to printable ASCII characters other + * than "=", "?", and "_" (underscore), MAY be represented as those + * characters. (But see section 5 for restrictions.) In + * particular, SPACE and TAB MUST NOT be represented as themselves + * within encoded words. + */ + + /* + * rule out non-ASCII characters and non-printable characters (the + * non-ASCII check should be redundant as isprint() is not localized + * and only knows about ASCII, but be defensive about that) + */ + if (non_ascii(ch) || !isprint(ch)) return 1; - return (non_ascii(ch) || (ch == '=') || (ch == '?') || (ch == '_')); + /* + * rule out special printable characters (' ' should be the only + * whitespace character considered printable, but be defensive and use + * isspace()) + */ + if (isspace(ch) || ch == '=' || ch == '?' || ch == '_') + return 1; + + /* + * rfc2047, section 5.3: + * + * As a replacement for a 'word' entity within a 'phrase', for example, + * one that precedes an address in a From, To, or Cc header. The ABNF + * definition for 'phrase' from RFC 822 thus becomes: + * + * phrase = 1*( encoded-word / word ) + * + * In this case the set of characters that may be used in a "Q"-encoded + * 'encoded-word' is restricted to: . An 'encoded-word' that appears within a + * 'phrase' MUST be separated from any adjacent 'word', 'text' or + * 'special' by 'linear-white-space'. + */ + + if (type != RFC2047_ADDRESS) + return 0; + + /* '=' and '_' are special cases and have been checked above */ + return !(isalnum(ch) || ch == '!' || ch == '*' || ch == '+' || ch == '-' || ch == '/'); } static void add_rfc2047(struct strbuf *sb, const char *line, int len, - const char *encoding) + const char *encoding, enum rfc2047_type type) { static const int max_length = 78; /* per rfc2822 */ static const int max_encoded_length = 76; /* per rfc2047 */ @@ -304,7 +353,7 @@ needquote: 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); + int is_special = is_rfc2047_special(ch, type); /* * According to RFC 2047, we could encode the special character @@ -358,11 +407,13 @@ void pp_user_info(const struct pretty_print_context *pp, display_name_length = name_tail - line; strbuf_addstr(sb, "From: "); if (!has_rfc822_specials(line, display_name_length)) { - add_rfc2047(sb, line, display_name_length, encoding); + add_rfc2047(sb, line, display_name_length, + encoding, RFC2047_ADDRESS); } else { struct strbuf quoted = STRBUF_INIT; add_rfc822_quoted("ed, line, display_name_length); - add_rfc2047(sb, quoted.buf, quoted.len, encoding); + add_rfc2047(sb, quoted.buf, quoted.len, + encoding, RFC2047_ADDRESS); strbuf_release("ed); } if (namelen - display_name_length + last_line_length(sb) > 78) { @@ -1294,7 +1345,7 @@ void pp_title_line(const struct pretty_print_context *pp, strbuf_grow(sb, title.len + 1024); if (pp->subject) { strbuf_addstr(sb, pp->subject); - add_rfc2047(sb, title.buf, title.len, encoding); + add_rfc2047(sb, title.buf, title.len, encoding, RFC2047_SUBJECT); } else { strbuf_addbuf(sb, &title); } diff --git a/t/t4014-format-patch.sh b/t/t4014-format-patch.sh index 1d5636d8a0..727d606884 100755 --- a/t/t4014-format-patch.sh +++ b/t/t4014-format-patch.sh @@ -818,21 +818,28 @@ check_author() { cat >expect <<'EOF' From: "Foo B. Bar" EOF -test_expect_success 'format-patch quotes dot in headers' ' +test_expect_success 'format-patch quotes dot in from-headers' ' check_author "Foo B. Bar" ' cat >expect <<'EOF' From: "Foo \"The Baz\" Bar" EOF -test_expect_success 'format-patch quotes double-quote in headers' ' +test_expect_success 'format-patch quotes double-quote in from-headers' ' check_author "Foo \"The Baz\" Bar" ' cat >expect <<'EOF' -From: =?UTF-8?q?"F=C3=B6o=20B.=20Bar"?= +From: =?UTF-8?q?F=C3=B6o=20Bar?= EOF -test_expect_success 'rfc2047-encoded headers also double-quote 822 specials' ' +test_expect_success 'format-patch uses rfc2047-encoded from-headers when necessary' ' + check_author "Föo Bar" +' + +cat >expect <<'EOF' +From: =?UTF-8?q?F=C3=B6o=20B=2E=20Bar?= +EOF +test_expect_failure 'rfc2047-encoded from-headers leave no rfc822 specials' ' check_author "Föo B. Bar" ' From 41dd00bad3d7614be7e8a41ed3f31878af86758b Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Jan=20H=2E=20Sch=C3=B6nherr?= Date: Thu, 18 Oct 2012 16:43:33 +0200 Subject: [PATCH 6/7] format-patch: fix rfc2047 address encoding with respect to rfc822 specials MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit According to RFC 2047 and RFC 822, rfc2047 encoded words and and rfc822 quoted strings do not mix. Since add_rfc2047() no longer leaves RFC 822 specials behind, the quoting is also no longer necessary to create a standard-conforming mail. Remove the quoting, when RFC 2047 encoding takes place. This actually requires to refactor add_rfc2047() a bit, so that the different cases can be distinguished. With this patch, my own name gets correctly decoded as Jan H. Schönherr (without quotes) and not as "Jan H. Schönherr" (with quotes). Signed-off-by: Jan H. Schönherr Signed-off-by: Junio C Hamano --- pretty.c | 49 +++++++++++++++++++++++++++-------------- t/t4014-format-patch.sh | 2 +- 2 files changed, 33 insertions(+), 18 deletions(-) diff --git a/pretty.c b/pretty.c index 613e4eab0d..413e7587b6 100644 --- a/pretty.c +++ b/pretty.c @@ -231,7 +231,7 @@ static int is_rfc822_special(char ch) } } -static int has_rfc822_specials(const char *s, int len) +static int needs_rfc822_quoting(const char *s, int len) { int i; for (i = 0; i < len; i++) @@ -329,25 +329,29 @@ static int is_rfc2047_special(char ch, enum rfc2047_type type) return !(isalnum(ch) || ch == '!' || ch == '*' || ch == '+' || ch == '-' || ch == '/'); } -static void add_rfc2047(struct strbuf *sb, const char *line, int len, - const char *encoding, enum rfc2047_type type) +static int needs_rfc2047_encoding(const char *line, int len, + enum rfc2047_type type) { - static const int max_length = 78; /* per rfc2822 */ - static const int max_encoded_length = 76; /* per rfc2047 */ int i; - int line_len = last_line_length(sb); for (i = 0; i < len; i++) { int ch = line[i]; if (non_ascii(ch) || ch == '\n') - goto needquote; + return 1; if ((i + 1 < len) && (ch == '=' && line[i+1] == '?')) - goto needquote; + return 1; } - strbuf_add_wrapped_bytes(sb, line, len, -line_len, 1, max_length); - return; -needquote: + return 0; +} + +static void add_rfc2047(struct strbuf *sb, const char *line, int len, + const char *encoding, enum rfc2047_type type) +{ + static const int max_encoded_length = 76; /* per rfc2047 */ + int i; + int line_len = last_line_length(sb); + strbuf_grow(sb, len * 3 + strlen(encoding) + 100); strbuf_addf(sb, "=?%s?q?", encoding); line_len += strlen(encoding) + 5; /* 5 for =??q? */ @@ -383,6 +387,7 @@ void pp_user_info(const struct pretty_print_context *pp, const char *what, struct strbuf *sb, const char *line, const char *encoding) { + int max_length = 78; /* per rfc2822 */ char *date; int namelen; unsigned long time; @@ -406,17 +411,21 @@ void pp_user_info(const struct pretty_print_context *pp, name_tail--; display_name_length = name_tail - line; strbuf_addstr(sb, "From: "); - if (!has_rfc822_specials(line, display_name_length)) { + if (needs_rfc2047_encoding(line, display_name_length, RFC2047_ADDRESS)) { add_rfc2047(sb, line, display_name_length, encoding, RFC2047_ADDRESS); - } else { + max_length = 76; /* per rfc2047 */ + } else if (needs_rfc822_quoting(line, display_name_length)) { struct strbuf quoted = STRBUF_INIT; add_rfc822_quoted("ed, line, display_name_length); - add_rfc2047(sb, quoted.buf, quoted.len, - encoding, RFC2047_ADDRESS); + 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); } - if (namelen - display_name_length + last_line_length(sb) > 78) { + if (namelen - display_name_length + last_line_length(sb) > max_length) { strbuf_addch(sb, '\n'); if (!isspace(name_tail[0])) strbuf_addch(sb, ' '); @@ -1336,6 +1345,7 @@ void pp_title_line(const struct pretty_print_context *pp, const char *encoding, int need_8bit_cte) { + static const int max_length = 78; /* per rfc2047 */ struct strbuf title; strbuf_init(&title, 80); @@ -1345,7 +1355,12 @@ void pp_title_line(const struct pretty_print_context *pp, strbuf_grow(sb, title.len + 1024); if (pp->subject) { strbuf_addstr(sb, pp->subject); - add_rfc2047(sb, title.buf, title.len, encoding, RFC2047_SUBJECT); + if (needs_rfc2047_encoding(title.buf, title.len, RFC2047_SUBJECT)) + add_rfc2047(sb, title.buf, title.len, + encoding, RFC2047_SUBJECT); + else + strbuf_add_wrapped_bytes(sb, title.buf, title.len, + -last_line_length(sb), 1, max_length); } else { strbuf_addbuf(sb, &title); } diff --git a/t/t4014-format-patch.sh b/t/t4014-format-patch.sh index 727d606884..e024eb8f50 100755 --- a/t/t4014-format-patch.sh +++ b/t/t4014-format-patch.sh @@ -839,7 +839,7 @@ test_expect_success 'format-patch uses rfc2047-encoded from-headers when necessa cat >expect <<'EOF' From: =?UTF-8?q?F=C3=B6o=20B=2E=20Bar?= EOF -test_expect_failure 'rfc2047-encoded from-headers leave no rfc822 specials' ' +test_expect_success 'rfc2047-encoded from-headers leave no rfc822 specials' ' check_author "Föo B. Bar" ' From 25dc8dad3a7c9f5426f549701e22eec1f894fec8 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Jan=20H=2E=20Sch=C3=B6nherr?= Date: Thu, 18 Oct 2012 16:43:34 +0200 Subject: [PATCH 7/7] format-patch tests: check quoting/encoding in To: and Cc: headers MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit git-format-patch does currently not parse user supplied extra header values (e. g., --cc, --add-header) and just replays them. That forces users to add them RFC 2822/2047 conform in encoded form, e.g. --cc '=?UTF-8?q?Jan=20H=2E=20Sch=C3=B6nherr?= <...>' which is inconvenient. We would want to update git-format-patch to accept human-readable input --cc 'Jan H. Schönherr <...>' and handle the encoding, wrapping and quoting internally in the future, similar to what is already done in git-send-email. The necessary code should mostly exist in the code paths that handle the From: and Subject: headers. Whether we want to do this only for the git-format-patch options --to and --cc (and the corresponding config options) or also for user supplied headers via --add-header, is open for discussion. For now, add test_expect_failure tests for To: and Cc: headers as a reminder and fix tests that would otherwise fail should this get implemented. Signed-off-by: Jan H. Schönherr Signed-off-by: Junio C Hamano --- t/t4014-format-patch.sh | 100 +++++++++++++++++++++++++++------------- 1 file changed, 67 insertions(+), 33 deletions(-) diff --git a/t/t4014-format-patch.sh b/t/t4014-format-patch.sh index e024eb8f50..ad9f69e607 100755 --- a/t/t4014-format-patch.sh +++ b/t/t4014-format-patch.sh @@ -110,73 +110,107 @@ test_expect_success 'replay did not screw up the log message' ' test_expect_success 'extra headers' ' - git config format.headers "To: R. E. Cipient + git config format.headers "To: R E Cipient " && - git config --add format.headers "Cc: S. E. Cipient + git config --add format.headers "Cc: S E Cipient " && git format-patch --stdout master..side > patch2 && sed -e "/^\$/q" patch2 > hdrs2 && - grep "^To: R. E. Cipient \$" hdrs2 && - grep "^Cc: S. E. Cipient \$" hdrs2 + grep "^To: R E Cipient \$" hdrs2 && + grep "^Cc: S E Cipient \$" hdrs2 ' test_expect_success 'extra headers without newlines' ' - git config --replace-all format.headers "To: R. E. Cipient " && - git config --add format.headers "Cc: S. E. Cipient " && + git config --replace-all format.headers "To: R E Cipient " && + git config --add format.headers "Cc: S E Cipient " && git format-patch --stdout master..side >patch3 && sed -e "/^\$/q" patch3 > hdrs3 && - grep "^To: R. E. Cipient \$" hdrs3 && - grep "^Cc: S. E. Cipient \$" hdrs3 + grep "^To: R E Cipient \$" hdrs3 && + grep "^Cc: S E Cipient \$" hdrs3 ' test_expect_success 'extra headers with multiple To:s' ' - git config --replace-all format.headers "To: R. E. Cipient " && - git config --add format.headers "To: S. E. Cipient " && + git config --replace-all format.headers "To: R E Cipient " && + git config --add format.headers "To: S E Cipient " && git format-patch --stdout master..side > patch4 && sed -e "/^\$/q" patch4 > hdrs4 && - grep "^To: R. E. Cipient ,\$" hdrs4 && - grep "^ *S. E. Cipient \$" hdrs4 + grep "^To: R E Cipient ,\$" hdrs4 && + grep "^ *S E Cipient \$" hdrs4 ' -test_expect_success 'additional command line cc' ' +test_expect_success 'additional command line cc (ascii)' ' - git config --replace-all format.headers "Cc: R. E. Cipient " && + 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 +' + +test_expect_failure 'additional command line cc (rfc822)' ' + + 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 "^Cc: R E Cipient ,\$" patch5 && + grep "^ *"S. E. Cipient" \$" patch5 ' test_expect_success 'command line headers' ' git config --unset-all format.headers && - git format-patch --add-header="Cc: R. E. Cipient " --stdout master..side | sed -e "/^\$/q" >patch6 && - grep "^Cc: R. E. Cipient \$" patch6 + git format-patch --add-header="Cc: R E Cipient " --stdout master..side | sed -e "/^\$/q" >patch6 && + grep "^Cc: R E Cipient \$" patch6 ' test_expect_success 'configuration headers and command line headers' ' - git config --replace-all format.headers "Cc: R. E. Cipient " && - git format-patch --add-header="Cc: S. E. Cipient " --stdout master..side | sed -e "/^\$/q" >patch7 && - grep "^Cc: R. E. Cipient ,\$" patch7 && - grep "^ *S. E. Cipient \$" patch7 + git config --replace-all format.headers "Cc: R E Cipient " && + git format-patch --add-header="Cc: S E Cipient " --stdout master..side | sed -e "/^\$/q" >patch7 && + grep "^Cc: R E Cipient ,\$" patch7 && + grep "^ *S E Cipient \$" patch7 ' -test_expect_success 'command line To: header' ' +test_expect_success 'command line To: header (ascii)' ' git config --unset-all format.headers && - git format-patch --to="R. E. Cipient " --stdout master..side | sed -e "/^\$/q" >patch8 && - grep "^To: R. E. Cipient \$" patch8 + git format-patch --to="R E Cipient " --stdout master..side | sed -e "/^\$/q" >patch8 && + grep "^To: R E Cipient \$" patch8 ' -test_expect_success 'configuration To: header' ' +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 +' + +test_expect_failure 'command line To: header (rfc2047)' ' + + git format-patch --to="R Ä Cipient " --stdout master..side | sed -e "/^\$/q" >patch8 && + grep "^To: =?UTF-8?q?R=20=C3=84=20Cipient?= \$" patch8 +' + +test_expect_success 'configuration To: header (ascii)' ' + + git config format.to "R E Cipient " && + git format-patch --stdout master..side | sed -e "/^\$/q" >patch9 && + grep "^To: R E Cipient \$" patch9 +' + +test_expect_failure 'configuration To: header (rfc822)' ' 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)' ' + + git config format.to "R Ä Cipient " && + git format-patch --stdout master..side | sed -e "/^\$/q" >patch9 && + grep "^To: =?UTF-8?q?R=20=C3=84=20Cipient?= \$" patch9 ' # check_patch : Verify that looks like a half-sane @@ -190,11 +224,11 @@ check_patch () { test_expect_success '--no-to overrides config.to' ' git config --replace-all format.to \ - "R. E. Cipient " && + "R E Cipient " && git format-patch --no-to --stdout master..side | sed -e "/^\$/q" >patch10 && check_patch patch10 && - ! grep "^To: R. E. Cipient \$" patch10 + ! grep "^To: R E Cipient \$" patch10 ' test_expect_success '--no-to and --to replaces config.to' ' @@ -212,21 +246,21 @@ test_expect_success '--no-to and --to replaces config.to' ' test_expect_success '--no-cc overrides config.cc' ' git config --replace-all format.cc \ - "C. E. Cipient " && + "C E Cipient " && git format-patch --no-cc --stdout master..side | sed -e "/^\$/q" >patch12 && check_patch patch12 && - ! grep "^Cc: C. E. Cipient \$" patch12 + ! grep "^Cc: C E Cipient \$" patch12 ' test_expect_success '--no-add-header overrides config.headers' ' git config --replace-all format.headers \ - "Header1: B. E. Cipient " && + "Header1: B E Cipient " && git format-patch --no-add-header --stdout master..side | sed -e "/^\$/q" >patch13 && check_patch patch13 && - ! grep "^Header1: B. E. Cipient \$" patch13 + ! grep "^Header1: B E Cipient \$" patch13 ' test_expect_success 'multiple files' '