summaryrefslogtreecommitdiff
path: root/utf8.c
diff options
context:
space:
mode:
Diffstat (limited to 'utf8.c')
-rw-r--r--utf8.c122
1 files changed, 103 insertions, 19 deletions
diff --git a/utf8.c b/utf8.c
index dc3735364f..84cfc72e6d 100644
--- a/utf8.c
+++ b/utf8.c
@@ -1,4 +1,5 @@
#include "git-compat-util.h"
+#include "strbuf.h"
#include "utf8.h"
/* This code is originally from http://www.cl.cam.ac.uk/~mgk25/ucs/ */
@@ -162,7 +163,7 @@ static int git_wcwidth(ucs_char_t ch)
* If the string was not a valid UTF-8, *start pointer is set to NULL
* and the return value is undefined.
*/
-ucs_char_t pick_one_utf8_char(const char **start, size_t *remainder_p)
+static ucs_char_t pick_one_utf8_char(const char **start, size_t *remainder_p)
{
unsigned char *s = (unsigned char *)*start;
ucs_char_t ch;
@@ -246,6 +247,25 @@ int utf8_width(const char **start, size_t *remainder_p)
return git_wcwidth(ch);
}
+/*
+ * Returns the total number of columns required by a null-terminated
+ * string, assuming that the string is utf8. Returns strlen() instead
+ * if the string does not look like a valid utf8 string.
+ */
+int utf8_strwidth(const char *string)
+{
+ int width = 0;
+ const char *orig = string;
+
+ while (1) {
+ if (!string)
+ return strlen(orig);
+ if (!*string)
+ return width;
+ width += utf8_width(&string, NULL);
+ }
+}
+
int is_utf8(const char *text)
{
while (*text) {
@@ -260,14 +280,41 @@ int is_utf8(const char *text)
return 1;
}
-static void print_spaces(int count)
+static void strbuf_addchars(struct strbuf *sb, int c, size_t n)
+{
+ strbuf_grow(sb, n);
+ memset(sb->buf + sb->len, c, n);
+ strbuf_setlen(sb, sb->len + n);
+}
+
+static void strbuf_add_indented_text(struct strbuf *buf, const char *text,
+ int indent, int indent2)
{
- static const char s[] = " ";
- while (count >= sizeof(s)) {
- fwrite(s, sizeof(s) - 1, 1, stdout);
- count -= sizeof(s) - 1;
+ if (indent < 0)
+ indent = 0;
+ while (*text) {
+ const char *eol = strchrnul(text, '\n');
+ if (*eol == '\n')
+ eol++;
+ strbuf_addchars(buf, ' ', indent);
+ strbuf_add(buf, text, eol - text);
+ text = eol;
+ indent = indent2;
}
- fwrite(s, count, 1, stdout);
+}
+
+static size_t display_mode_esc_sequence_len(const char *s)
+{
+ const char *p = s;
+ if (*p++ != '\033')
+ return 0;
+ if (*p++ != '[')
+ return 0;
+ while (isdigit(*p) || *p == ';')
+ p++;
+ if (*p++ != 'm')
+ return 0;
+ return p - s;
}
/*
@@ -276,45 +323,82 @@ static void print_spaces(int count)
* If indent is negative, assume that already -indent columns have been
* consumed (and no extra indent is necessary for the first line).
*/
-int print_wrapped_text(const char *text, int indent, int indent2, int width)
+int strbuf_add_wrapped_text(struct strbuf *buf,
+ const char *text, int indent1, int indent2, int width)
{
- int w = indent, assume_utf8 = is_utf8(text);
- const char *bol = text, *space = NULL;
+ int indent, w, assume_utf8 = 1;
+ const char *bol, *space, *start = text;
+ size_t orig_len = buf->len;
+
+ if (width <= 0) {
+ strbuf_add_indented_text(buf, text, indent1, indent2);
+ return 1;
+ }
+retry:
+ bol = text;
+ w = indent = indent1;
+ space = NULL;
if (indent < 0) {
w = -indent;
space = text;
}
for (;;) {
- char c = *text;
+ char c;
+ size_t skip;
+
+ while ((skip = display_mode_esc_sequence_len(text)))
+ text += skip;
+
+ c = *text;
if (!c || isspace(c)) {
if (w < width || !space) {
const char *start = bol;
+ if (!c && text == start)
+ return w;
if (space)
start = space;
else
- print_spaces(indent);
- fwrite(start, text - start, 1, stdout);
+ strbuf_addchars(buf, ' ', indent);
+ strbuf_add(buf, start, text - start);
if (!c)
return w;
- else if (c == '\t')
- w |= 0x07;
space = text;
+ if (c == '\t')
+ w |= 0x07;
+ else if (c == '\n') {
+ space++;
+ if (*space == '\n') {
+ strbuf_addch(buf, '\n');
+ goto new_line;
+ }
+ else if (!isalnum(*space))
+ goto new_line;
+ else
+ strbuf_addch(buf, ' ');
+ }
w++;
text++;
}
else {
- putchar('\n');
+new_line:
+ strbuf_addch(buf, '\n');
text = bol = space + isspace(*space);
space = NULL;
w = indent = indent2;
}
continue;
}
- if (assume_utf8)
+ if (assume_utf8) {
w += utf8_width(&text, NULL);
- else {
+ if (!text) {
+ assume_utf8 = 0;
+ text = start;
+ strbuf_setlen(buf, orig_len);
+ goto retry;
+ }
+ } else {
w++;
text++;
}
@@ -335,7 +419,7 @@ int is_encoding_utf8(const char *name)
* with iconv. If the conversion fails, returns NULL.
*/
#ifndef NO_ICONV
-#ifdef OLD_ICONV
+#if defined(OLD_ICONV) || (defined(__sun__) && !defined(_XPG6))
typedef const char * iconv_ibp;
#else
typedef char * iconv_ibp;