static void add_rfc2047(struct strbuf *sb, const char *line, int len,
const char *encoding)
{
int i, last;
for (i = 0; i < len; i++) {
int ch = line[i];
if (non_ascii(ch))
goto needquote;
if ((i + 1 < len) && (ch == '=' && line[i+1] == '?'))
goto needquote;
}
strbuf_add(sb, line, len);
return;
needquote:
strbuf_grow(sb, len * 3 + strlen(encoding) + 100);
strbuf_addf(sb, "=?%s?q?", encoding);
for (i = last = 0; i < len; i++) {
unsigned ch = line[i] & 0xFF;
/*
* 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 == ' ') {
strbuf_add(sb, line + last, i - last);
strbuf_addf(sb, "=%02X", ch);
last = i + 1;
}
}
strbuf_add(sb, line + last, len - last);
strbuf_addstr(sb, "?=");
}
int has_non_ascii(const char *s)
{
int ch;
if (!s)
return 0;
while ((ch = *s++) != '\0') {
if (non_ascii(ch))
return 1;
}
return 0;
}
static void add_rfc2047(struct strbuf *sb, const char *line, int len,
const char *encoding)
{
static const int max_length = 78; /* per rfc2822 */
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);
for (i = 0; i < len; i++) {
int ch = line[i];
if (non_ascii(ch) || ch == '\n')
goto needquote;
if ((i + 1 < len) && (ch == '=' && line[i+1] == '?'))
goto needquote;
}
strbuf_add_wrapped_bytes(sb, line, len, 0, 1, max_length - line_len);
return;
needquote:
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;
if (line_len >= max_length - 2) {
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') {
strbuf_addf(sb, "=%02X", ch);
line_len += 3;
}
else {
strbuf_addch(sb, ch);
line_len++;
}
}
strbuf_addstr(sb, "?=");
}
static int is_rfc2047_special(char ch, enum rfc2047_type type)
{
/*
* 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;
/*
* 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: <upper and lower case ASCII
* letters, decimal digits, "!", "*", "+", "-", "/", "=", and "_"
* (underscore, ASCII 95.)>. 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 int needs_rfc2047_encoding(const char *line, int len,
enum rfc2047_type type)
{
int i;
for (i = 0; i < len; i++) {
int ch = line[i];
if (non_ascii(ch) || ch == '\n')
return 1;
if ((i + 1 < len) && (ch == '=' && line[i+1] == '?'))
return 1;
}
return 0;
}
void ascii_check::inspect(
const string & library_name,
const path & full_path, // example: c:/foo/boost/filesystem/path.hpp
const string & contents ) // contents of file to be inspected
{
if (contents.find( "hpxinspect:" "noascii" ) != string::npos) return;
string::const_iterator bad_char = std::find_if ( contents.begin (),
contents.end (), non_ascii ());
if ( bad_char != contents.end ())
{
++m_files_with_errors;
std::size_t ln = std::count( contents.begin(), bad_char, '\n' ) + 1;
string the_line = find_line ( contents, bad_char );
error( library_name, full_path, "Non-ASCII: ", ln);
}
}
void pretty_print_commit(struct pretty_print_context *pp,
const struct commit *commit,
struct strbuf *sb)
{
unsigned long beginning_of_body;
int indent = 4;
const char *msg;
const char *reencoded;
const char *encoding;
int need_8bit_cte = pp->need_8bit_cte;
if (pp->fmt == CMIT_FMT_USERFORMAT) {
format_commit_message(commit, user_format, sb, pp);
return;
}
encoding = get_log_output_encoding();
msg = reencoded = logmsg_reencode(commit, NULL, encoding);
if (pp->fmt == CMIT_FMT_ONELINE || pp->fmt == CMIT_FMT_EMAIL)
indent = 0;
/*
* We need to check and emit Content-type: to mark it
* as 8-bit if we haven't done so.
*/
if (pp->fmt == CMIT_FMT_EMAIL && need_8bit_cte == 0) {
int i, ch, in_body;
for (in_body = i = 0; (ch = msg[i]); i++) {
if (!in_body) {
/* author could be non 7-bit ASCII but
* the log may be so; skip over the
* header part first.
*/
if (ch == '\n' && msg[i+1] == '\n')
in_body = 1;
}
else if (non_ascii(ch)) {
need_8bit_cte = 1;
break;
}
}
}
pp_header(pp, encoding, commit, &msg, sb);
if (pp->fmt != CMIT_FMT_ONELINE && !pp->subject) {
strbuf_addch(sb, '\n');
}
/* Skip excess blank lines at the beginning of body, if any... */
msg = skip_empty_lines(msg);
/* These formats treat the title line specially. */
if (pp->fmt == CMIT_FMT_ONELINE || pp->fmt == CMIT_FMT_EMAIL)
pp_title_line(pp, &msg, sb, encoding, need_8bit_cte);
beginning_of_body = sb->len;
if (pp->fmt != CMIT_FMT_ONELINE)
pp_remainder(pp, &msg, sb, indent);
strbuf_rtrim(sb);
/* Make sure there is an EOLN for the non-oneline case */
if (pp->fmt != CMIT_FMT_ONELINE)
strbuf_addch(sb, '\n');
/*
* The caller may append additional body text in e-mail
* format. Make sure we did not strip the blank line
* between the header and the body.
*/
if (pp->fmt == CMIT_FMT_EMAIL && sb->len <= beginning_of_body)
strbuf_addch(sb, '\n');
unuse_commit_buffer(commit, reencoded);
}
static int is_rfc2047_special(char ch)
{
return (non_ascii(ch) || (ch == '=') || (ch == '?') || (ch == '_'));
}
void pretty_print_commit(enum cmit_fmt fmt, const struct commit *commit,
struct strbuf *sb,
const struct pretty_print_context *context)
{
unsigned long beginning_of_body;
int indent = 4;
const char *msg = commit->buffer;
char *reencoded;
const char *encoding;
int need_8bit_cte = context->need_8bit_cte;
if (fmt == CMIT_FMT_USERFORMAT) {
format_commit_message(commit, user_format, sb, context);
return;
}
reencoded = reencode_commit_message(commit, &encoding);
if (reencoded) {
msg = reencoded;
}
if (fmt == CMIT_FMT_ONELINE || fmt == CMIT_FMT_EMAIL)
indent = 0;
/*
* We need to check and emit Content-type: to mark it
* as 8-bit if we haven't done so.
*/
if (fmt == CMIT_FMT_EMAIL && need_8bit_cte == 0) {
int i, ch, in_body;
for (in_body = i = 0; (ch = msg[i]); i++) {
if (!in_body) {
/* author could be non 7-bit ASCII but
* the log may be so; skip over the
* header part first.
*/
if (ch == '\n' && msg[i+1] == '\n')
in_body = 1;
}
else if (non_ascii(ch)) {
need_8bit_cte = 1;
break;
}
}
}
pp_header(fmt, context->abbrev, context->date_mode, encoding,
commit, &msg, sb);
if (fmt != CMIT_FMT_ONELINE && !context->subject) {
strbuf_addch(sb, '\n');
}
/* Skip excess blank lines at the beginning of body, if any... */
msg = skip_empty_lines(msg);
/* These formats treat the title line specially. */
if (fmt == CMIT_FMT_ONELINE || fmt == CMIT_FMT_EMAIL)
pp_title_line(fmt, &msg, sb, context->subject,
context->after_subject, encoding, need_8bit_cte);
beginning_of_body = sb->len;
if (fmt != CMIT_FMT_ONELINE)
pp_remainder(fmt, &msg, sb, indent);
strbuf_rtrim(sb);
/* Make sure there is an EOLN for the non-oneline case */
if (fmt != CMIT_FMT_ONELINE)
strbuf_addch(sb, '\n');
/*
* The caller may append additional body text in e-mail
* format. Make sure we did not strip the blank line
* between the header and the body.
*/
if (fmt == CMIT_FMT_EMAIL && sb->len <= beginning_of_body)
strbuf_addch(sb, '\n');
if (context->show_notes)
format_display_notes(commit->object.sha1, sb, encoding,
NOTES_SHOW_HEADER | NOTES_INDENT);
free(reencoded);
}
void pretty_print_commit(enum cmit_fmt fmt, const struct commit *commit,
struct strbuf *sb, int abbrev,
const char *subject, const char *after_subject,
enum date_mode dmode, int need_8bit_cte)
{
unsigned long beginning_of_body;
int indent = 4;
const char *msg = commit->buffer;
char *reencoded;
const char *encoding;
if (fmt == CMIT_FMT_USERFORMAT) {
format_commit_message(commit, user_format, sb);
return;
}
encoding = (git_log_output_encoding
? git_log_output_encoding
: git_commit_encoding);
if (!encoding)
encoding = "utf-8";
reencoded = logmsg_reencode(commit, encoding);
if (reencoded) {
msg = reencoded;
}
if (fmt == CMIT_FMT_ONELINE || fmt == CMIT_FMT_EMAIL)
indent = 0;
/*
* We need to check and emit Content-type: to mark it
* as 8-bit if we haven't done so.
*/
if (fmt == CMIT_FMT_EMAIL && need_8bit_cte == 0) {
int i, ch, in_body;
for (in_body = i = 0; (ch = msg[i]); i++) {
if (!in_body) {
/* author could be non 7-bit ASCII but
* the log may be so; skip over the
* header part first.
*/
if (ch == '\n' && msg[i+1] == '\n')
in_body = 1;
}
else if (non_ascii(ch)) {
need_8bit_cte = 1;
break;
}
}
}
pp_header(fmt, abbrev, dmode, encoding, commit, &msg, sb);
if (fmt != CMIT_FMT_ONELINE && !subject) {
strbuf_addch(sb, '\n');
}
/* Skip excess blank lines at the beginning of body, if any... */
for (;;) {
int linelen = get_one_line(msg);
int ll = linelen;
if (!linelen)
break;
if (!is_empty_line(msg, &ll))
break;
msg += linelen;
}
/* These formats treat the title line specially. */
if (fmt == CMIT_FMT_ONELINE || fmt == CMIT_FMT_EMAIL)
pp_title_line(fmt, &msg, sb, subject,
after_subject, encoding, need_8bit_cte);
beginning_of_body = sb->len;
if (fmt != CMIT_FMT_ONELINE)
pp_remainder(fmt, &msg, sb, indent);
strbuf_rtrim(sb);
/* Make sure there is an EOLN for the non-oneline case */
if (fmt != CMIT_FMT_ONELINE)
strbuf_addch(sb, '\n');
/*
* The caller may append additional body text in e-mail
* format. Make sure we did not strip the blank line
* between the header and the body.
*/
if (fmt == CMIT_FMT_EMAIL && sb->len <= beginning_of_body)
strbuf_addch(sb, '\n');
free(reencoded);
}
