import code common to multiple projects - iomenu - interactive terminal-based selection menu
(HTM) git clone git://bitreich.org/iomenu git://enlrupgkhuxnvlhsf6lc3fziv5h2hhfrinws65d7roiv6bfj7d652fid.onion/iomenu
(DIR) Log
(DIR) Files
(DIR) Refs
(DIR) Tags
(DIR) README
(DIR) LICENSE
---
(DIR) commit 9e523e73c8f395ee7270ed2826efa3f7ffb5908d
(DIR) parent c4011c678d9f4aaa75e1bbb92a8a9e5b6180043b
(HTM) Author: Josuah Demangeon <me@josuah.net>
Date: Tue, 14 Jul 2020 17:55:23 +0200
import code common to multiple projects
Diffstat:
M Makefile | 59 +++++++++++++++++++------------
A README | 2 ++
D arg.h | 27 ---------------------------
R README -> doc/index.md | 0
R iomenu.1 -> doc/iomenu.1 | 0
M iomenu.c | 152 ++++++++++++++++---------------
A src/compat.h | 11 +++++++++++
A src/compat/strcasestr.c | 25 +++++++++++++++++++++++++
A src/compat/strsep.c | 23 +++++++++++++++++++++++
A src/compat/wcwidth.c | 309 +++++++++++++++++++++++++++++++
A src/log.c | 54 +++++++++++++++++++++++++++++++
A src/log.h | 15 +++++++++++++++
A src/mem.c | 132 +++++++++++++++++++++++++++++++
A src/mem.h | 58 ++++++++++++++++++++++++++++++
A src/str.c | 119 +++++++++++++++++++++++++++++++
A src/str.h | 26 ++++++++++++++++++++++++++
A src/utf8.c | 214 +++++++++++++++++++++++++++++++
A src/utf8.h | 13 +++++++++++++
A src/util.h | 12 ++++++++++++
D strcasestr.c | 25 -------------------------
D strsep.c | 21 ---------------------
R test.c -> t/test.c | 0
D utf8.c | 424 ------------------------------
D utf8.h | 11 -----------
D util.h | 31 -------------------------------
25 files changed, 1128 insertions(+), 635 deletions(-)
---
(DIR) diff --git a/Makefile b/Makefile
@@ -1,32 +1,45 @@
-include config.mk
+NAME = iomenu
+VERSION = 0.1
+
+SRC = src/utf8.c src/str.c src/log.c src/mem.c src/compat/strcasestr.c \
+ src/compat/strsep.c src/compat/wcwidth.c
+
+HDR = src/mem.h src/compat.h src/util.h src/str.h src/log.h src/utf8.h
+
+BIN = iomenu
-SRC = iomenu.c strcasestr.c strsep.c utf8.c
OBJ = ${SRC:.c=.o}
-all: iomenu
+LIB =
-.c.o:
- ${CC} -c -o $@ ${CFLAGS} $<
+W = -Wall -Wextra -std=c99 --pedantic
+I = -I./src
+L =
+D = -D_POSIX_C_SOURCE=200811L -DVERSION='"${VERSION}"'
+CFLAGS = $I $D $W -g
+LDFLAGS = $L -static
+PREFIX = /usr/local
+MANPREFIX = ${PREFIX}/man
-iomenu: ${OBJ}
- ${CC} -o $@ ${LFLAGS} ${OBJ}
+all: ${BIN}
-iomenu.o: iomenu.c util.h
-strcasestr.o: strcasestr.c util.h
-strsep.o: strsep.c util.h
-test.o: test.c util.h
-utf8.o: utf8.c utf8.h
+.c.o:
+ ${CC} -c ${CFLAGS} -o $@ $<
-.PHONY: test
-test: test.c
- ${CC} -o $@ ${LFLAGS} test.c utf8.c
- ./$@
+${OBJ}: ${HDR}
+${BIN}: ${OBJ} ${BIN:=.o}
+ ${CC} ${LDFLAGS} -o $@ $@.o ${OBJ} ${LIB}
clean:
- rm -f *.o *.core iomenu test
-
-install: iomenu
- mkdir -p ${MANPREFIX}/man1
- cp *.1 ${MANPREFIX}/man1
- mkdir -p ${PREFIX}/bin
- cp iomenu bin/* ${PREFIX}/bin
+ rm -rf *.o */*.o ${BIN} ${NAME}-${VERSION} *.gz
+
+install:
+ mkdir -p ${DESTDIR}${PREFIX}/bin
+ cp -rf ${BIN} ${DESTDIR}${PREFIX}/bin
+ mkdir -p ${DESTDIR}${MANPREFIX}/man1
+ cp -rf doc/*.1 ${DESTDIR}${MANPREFIX}/man1
+
+dist: clean
+ mkdir -p ${NAME}-${VERSION}
+ cp -r README Makefile doc ${SRC} ${NAME}-${VERSION}
+ tar -cf - ${NAME}-${VERSION} | gzip -c >${NAME}-${VERSION}.tar.gz
(DIR) diff --git a/README b/README
@@ -0,0 +1 @@
+doc/index.md
+\ No newline at end of file
(DIR) diff --git a/arg.h b/arg.h
@@ -1,27 +0,0 @@
-#ifndef ARG_H
-#define ARG_H
-
-extern char *argv0;
-
-#define ARGBEGIN \
- for (argv0 = *argv, argv++, argc--; \
- argv[0] != NULL && argv[0][0] == '-' && argv[0][1] != '\0'; \
- argc--, argv++) { \
- char **_argv, *_a; \
- if (argv[0][1] == '-' && argv[0][2] == '\0') { \
- argv++, argc--; \
- break; \
- } \
- for (_argv = argv, _a = *argv + 1; *_a != '\0'; _a++) { \
- switch (*_a)
-
-#define ARGEND \
- if (_argv != argv) \
- break; \
- } \
- }
-
-#define EARGF(x) \
- ((argv[1] == NULL) ? ((x), (char *)0) : (argc--, argv++, argv[0]))
-
-#endif
(DIR) diff --git a/README b/doc/index.md
(DIR) diff --git a/iomenu.1 b/doc/iomenu.1
(DIR) diff --git a/iomenu.c b/iomenu.c
@@ -1,6 +1,7 @@
#include <sys/ioctl.h>
#include <ctype.h>
+#include <errno.h>
#include <fcntl.h>
#include <limits.h>
#include <signal.h>
@@ -12,29 +13,30 @@
#include <unistd.h>
#include "utf8.h"
+#include "compat.h"
#include "util.h"
-#include "arg.h"
+#include "log.h"
#ifndef SIGWINCH
#define SIGWINCH 28
#endif
-static struct termios termios;
-struct winsize ws;
-static int linec = 0, matchc = 0, cur = 0;
-static char **linev = NULL, **matchv = NULL;
-static char input[LINE_MAX];
-static int hsflag = 0;
-char *argv0;
+static struct termios termios;
+struct winsize ws;
+static int linec = 0, matchc = 0, cur = 0;
+static char **linev = NULL, **matchv = NULL;
+static char input[LINE_MAX];
+static char *flag['z'];
+char *argv0;
/*
-** Keep the line if it match every token (in no particular order,
-** and allowed to be overlapping).
-*/
+ * Keep the line if it match every token (in no particular order,
+ * and allowed to be overlapping).
+ */
static int
match_line(char *line, char **tokv)
{
- if (hsflag && line[0] == '#')
+ if (flag['#'] && line[0] == '#')
return 2;
for (; *tokv != NULL; tokv++)
if (strcasestr(line, *tokv) == NULL)
@@ -43,38 +45,39 @@ match_line(char *line, char **tokv)
}
/*
-** Free the structures, reset the terminal state and exit with an
-** error message.
-*/
+ * Free the structures, reset the terminal state and exit with an
+ * error message.
+ */
static void
-die(const char *s)
+iomenu_die(const char *s)
{
+ int e = errno;
+
if (tcsetattr(STDERR_FILENO, TCSANOW, &termios) == -1)
- perror("tcsetattr while dying");
- close(STDERR_FILENO);
- perror(s);
- exit(EXIT_FAILURE);
+ warn("tcsetattr while dying");
+ errno = e;
+ die("%s", s);
}
/*
-** Read one key from stdin and die if it failed to prevent to read
-** in an endless loop. This caused the load average to go over 10
-** at work. :S
-*/
+ * Read one key from stdin and die if it failed to prevent to read
+ * in an endless loop. This caused the load average to go over 10
+ * at work. :S
+ */
int
getkey(void)
{
int c;
if ((c = fgetc(stdin)) == EOF)
- die("getting a key");
+ iomenu_die("getting a key");
return c;
}
/*
-** Split a buffer into an array of lines, without allocating memory for every
-** line, but using the input buffer and replacing '\n' by '\0'.
-*/
+ * Split a buffer into an array of lines, without allocating memory for every
+ * line, but using the input buffer and replacing '\n' by '\0'.
+ */
static void
split_lines(char *buf)
{
@@ -84,9 +87,9 @@ split_lines(char *buf)
for (b = buf; (b = strchr(b, '\n')) != NULL && b[1] != '\0'; b++)
linec++;
if ((lv = linev = calloc(linec + 1, sizeof(char **))) == NULL)
- die("calloc");
+ iomenu_die("calloc");
if ((mv = matchv = calloc(linec + 1, sizeof(char **))) == NULL)
- die("calloc");
+ iomenu_die("calloc");
*mv = *lv = b = buf;
while ((b = strchr(b, '\n')) != NULL) {
*b = '\0';
@@ -95,9 +98,9 @@ split_lines(char *buf)
}
/*
-** Read stdin in a single malloc-ed buffer, realloc-ed to twice its size every
-** time the previous buffer is filled.
-*/
+ * Read stdin in a single malloc-ed buffer, realloc-ed to twice its size every
+ * time the previous buffer is filled.
+ */
static void
read_stdin(void)
{
@@ -107,13 +110,13 @@ read_stdin(void)
size = BUFSIZ;
off = 0;
if ((buf = malloc(size)) == NULL)
- die("malloc");
+ iomenu_die("malloc");
while ((len = read(STDIN_FILENO, buf + off, size - off)) > 0) {
off += len;
if (off == size) {
size *= 2;
if ((buf = realloc(buf, size + 1)) == NULL)
- die("realloc");
+ iomenu_die("realloc");
}
}
buf[off] = '\0';
@@ -126,7 +129,7 @@ move(int sign)
int i;
for (i = cur + sign; 0 <= i && i < matchc; i += sign) {
- if (hsflag == 0 || matchv[i][0] != '#') {
+ if (flag['#'] == 0 || matchv[i][0] != '#') {
cur = i;
break;
}
@@ -144,10 +147,10 @@ tokenize(char **tokv, char *str)
}
/*
-** First split input into token, then match every token independently against
-** every line. The matching lines fills matchv. Matches are searched inside
-** of `searchv' of size `searchc'
-*/
+ * First split input into token, then match every token independently against
+ * every line. The matching lines fills matchv. Matches are searched inside
+ * of `searchv' of size `searchc'
+ */
static void
filter(int searchc, char **searchv)
{
@@ -163,7 +166,7 @@ filter(int searchc, char **searchv)
for (n = 0; n < searchc; n++)
if (match_line(searchv[n], tokv))
matchv[matchc++] = searchv[n];
- if (hsflag && matchv[cur][0] == '#')
+ if (flag['#'] && matchv[cur][0] == '#')
move(+1);
}
@@ -184,7 +187,7 @@ static void
move_header(signed int sign)
{
move(sign);
- if (hsflag == 0)
+ if (flag['#'] == 0)
return;
for (cur += sign; 0 <= cur; cur += sign) {
if (cur >= matchc) {
@@ -229,7 +232,7 @@ print_selection(void)
{
char **match;
- if (hsflag) {
+ if (flag['#']) {
match = matchv + cur;
while (--match >= matchv) {
if ((*match)[0] == '#') {
@@ -239,7 +242,7 @@ print_selection(void)
}
putchar('\t');
}
- if (matchc == 0 || (hsflag && matchv[cur][0] == '#'))
+ if (matchc == 0 || (flag['#'] && matchv[cur][0] == '#'))
puts(input);
else
puts(matchv[cur]);
@@ -266,46 +269,46 @@ top:
remove_word();
break;
case 127:
- case CTL('H'): /* backspace */
+ case CTL('H'): /* backspace */
input[strlen(input) - 1] = '\0';
filter(linec, linev);
break;
- case CSI('A'): /* up */
+ case CSI('A'): /* up */
case CTL('P'):
move(-1);
break;
case ALT('p'):
move_header(-1);
break;
- case CSI('B'): /* down */
+ case CSI('B'): /* down */
case CTL('N'):
move(+1);
break;
case ALT('n'):
move_header(+1);
break;
- case CSI('5'): /* page up */
+ case CSI('5'): /* page up */
if (getkey() != '~')
break;
/* FALLTHROUGH */
case ALT('v'):
move_page(-1);
break;
- case CSI('6'): /* page down */
+ case CSI('6'): /* page down */
if (getkey() != '~')
break;
/* FALLTHROUGH */
case CTL('V'):
move_page(+1);
break;
- case CTL('I'): /* tab */
+ case CTL('I'): /* tab */
if (linec > 0) {
strncpy(input, matchv[cur], sizeof(input));
input[sizeof(input) - 1] = '\0';
}
filter(matchc, matchv);
break;
- case CTL('J'): /* enter */
+ case CTL('J'):/* enter */
case CTL('M'):
print_selection();
return 0;
@@ -325,7 +328,7 @@ top:
static void
print_line(char *line, int highlight)
{
- if (hsflag && line[0] == '#')
+ if (flag['#'] && line[0] == '#')
fprintf(stderr, "\n\x1b[1m\r%.*s\x1b[m",
utf8_col(line + 1, ws.ws_col, 0), line + 1);
else if (highlight)
@@ -343,7 +346,7 @@ print_screen(void)
int p, i, c, cols, rows;
cols = ws.ws_col;
- rows = ws.ws_row - 1; /* -1 to keep one line for user input */
+ rows = ws.ws_row - 1; /* -1 to keep one line for user input */
p = c = 0;
i = cur - cur % rows;
m = matchv + i;
@@ -368,10 +371,10 @@ term_set(void)
fputs("\x1b[s\x1b[?1049h\x1b[H", stderr);
if (tcgetattr(STDERR_FILENO, &termios) == -1 ||
tcgetattr(STDERR_FILENO, &new) == -1)
- die("setting terminal");
+ iomenu_die("setting terminal");
new.c_lflag &= ~(ICANON | ECHO | IEXTEN | IGNBRK | ISIG);
if (tcsetattr(STDERR_FILENO, TCSANOW, &new) == -1)
- die("tcsetattr");
+ iomenu_die("tcsetattr");
}
/*
@@ -382,46 +385,49 @@ term_reset(void)
{
fputs("\x1b[2J\x1b[u\033[?1049l", stderr);
if (tcsetattr(STDERR_FILENO, TCSANOW, &termios))
- die("resetting terminal");
+ iomenu_die("resetting terminal");
}
static void
sigwinch(int sig)
{
if (ioctl(STDERR_FILENO, TIOCGWINSZ, &ws) == -1)
- die("ioctl");
+ iomenu_die("ioctl");
print_screen();
signal(sig, sigwinch);
}
static void
-usage(void)
+usage(char const *arg0)
{
- fputs("usage: iomenu [-#]\n", stderr);
- exit(EXIT_FAILURE);
+ fprintf(stderr, "usage: %s [-#]\n", arg0);
+ exit(1);
}
/*
-** Read stdin in a buffer, filling a table of lines, then re-open stdin to
-** /dev/tty for an interactive (raw) session to let the user filter and select
-** one line by searching words within stdin. This was inspired from dmenu.
-*/
+ * Read stdin in a buffer, filling a table of lines, then re-open stdin to
+ * /dev/tty for an interactive (raw) session to let the user filter and select
+ * one line by searching words within stdin. This was inspired from dmenu.
+ */
int
main(int argc, char *argv[])
{
- ARGBEGIN {
- case '#':
- hsflag = 1;
- break;
- default:
- usage();
- } ARGEND
+ arg0 = *argv;
+ for (int c; (c = getopt(argc, argv, "#")) > 0; flag[c] = optarg)
+ if (c == '?')
+ usage(arg0);
+ argc -= optind;
+ argv += optind;
input[0] = '\0';
+
read_stdin();
+
filter(linec, linev);
- if (freopen("/dev/tty", "r", stdin) == NULL)
- die("reopening /dev/tty as stdin");
+
+ if (!isatty(2))
+ iomenu_die("file descriptor 2 (stderr)");
+
term_set();
sigwinch(SIGWINCH);
(DIR) diff --git a/src/compat.h b/src/compat.h
@@ -0,0 +1,11 @@
+#ifndef COMPAT_H
+#define COMPAT_H
+
+#define wcwidth(c) mk_wcwidth_cjk(c)
+#define wcswidth(s, n) mk_wcwidth_cjk(s, n)
+
+/** src/compat/?*.c **/
+char * strcasestr(const char *str1, const char *str2);
+char * strsep(char **str_p, char const *sep);
+
+#endif
(DIR) diff --git a/src/compat/strcasestr.c b/src/compat/strcasestr.c
@@ -0,0 +1,25 @@
+#include <ctype.h>
+#include <stddef.h>
+
+#include "compat.h"
+
+char *
+strcasestr(const char *str1, const char *str2)
+{
+ const char *s1;
+ const char *s2;
+
+ for (;;) {
+ s1 = str1;
+ s2 = str2;
+ while (*s1 != '\0' && tolower(*s1) == tolower(*s2))
+ s1++, s2++;
+ if (*s2 == '\0')
+ return (char *) str1;
+ if (*s1 == '\0')
+ return NULL;
+ str1++;
+ }
+
+ return NULL;
+}
(DIR) diff --git a/src/compat/strsep.c b/src/compat/strsep.c
@@ -0,0 +1,23 @@
+#include <string.h>
+
+#include "compat.h"
+
+char *
+strsep(char **str_p, char const *sep)
+{
+ char *s, *prev;
+
+ if (*str_p == NULL)
+ return NULL;
+
+ for (s = prev = *str_p; strchr(sep, *s) == NULL; s++)
+ continue;
+
+ if (*s == '\0') {
+ *str_p = NULL;
+ } else {
+ *s = '\0';
+ *str_p = s + 1;
+ }
+ return prev;
+}
(DIR) diff --git a/src/compat/wcwidth.c b/src/compat/wcwidth.c
@@ -0,0 +1,309 @@
+/*
+ * This is an implementation of wcwidth() and wcswidth() (defined in
+ * IEEE Std 1002.1-2001) for Unicode.
+ *
+ * http://www.opengroup.org/onlinepubs/007904975/functions/wcwidth.html
+ * http://www.opengroup.org/onlinepubs/007904975/functions/wcswidth.html
+ *
+ * In fixed-width output devices, Latin characters all occupy a single
+ * "cell" position of equal width, whereas ideographic CJK characters
+ * occupy two such cells. Interoperability between terminal-line
+ * applications and (teletype-style) character terminals using the
+ * UTF-8 encoding requires agreement on which character should advance
+ * the cursor by how many cell positions. No established formal
+ * standards exist at present on which Unicode character shall occupy
+ * how many cell positions on character terminals. These routines are
+ * a first attempt of defining such behavior based on simple rules
+ * applied to data provided by the Unicode Consortium.
+ *
+ * For some graphical characters, the Unicode standard explicitly
+ * defines a character-cell width via the definition of the East Asian
+ * FullWidth (F), Wide (W), Half-width (H), and Narrow (Na) classes.
+ * In all these cases, there is no ambiguity about which width a
+ * terminal shall use. For characters in the East Asian Ambiguous (A)
+ * class, the width choice depends purely on a preference of backward
+ * compatibility with either historic CJK or Western practice.
+ * Choosing single-width for these characters is easy to justify as
+ * the appropriate long-term solution, as the CJK practice of
+ * displaying these characters as double-width comes from historic
+ * implementation simplicity (8-bit encoded characters were displayed
+ * single-width and 16-bit ones double-width, even for Greek,
+ * Cyrillic, etc.) and not any typographic considerations.
+ *
+ * Much less clear is the choice of width for the Not East Asian
+ * (Neutral) class. Existing practice does not dictate a width for any
+ * of these characters. It would nevertheless make sense
+ * typographically to allocate two character cells to characters such
+ * as for instance EM SPACE or VOLUME INTEGRAL, which cannot be
+ * represented adequately with a single-width glyph. The following
+ * routines at present merely assign a single-cell width to all
+ * neutral characters, in the interest of simplicity. This is not
+ * entirely satisfactory and should be reconsidered before
+ * establishing a formal standard in this area. At the moment, the
+ * decision which Not East Asian (Neutral) characters should be
+ * represented by double-width glyphs cannot yet be answered by
+ * applying a simple rule from the Unicode database content. Setting
+ * up a proper standard for the behavior of UTF-8 character terminals
+ * will require a careful analysis not only of each Unicode character,
+ * but also of each presentation form, something the author of these
+ * routines has avoided to do so far.
+ *
+ * http://www.unicode.org/unicode/reports/tr11/
+ *
+ * Markus Kuhn -- 2007-05-26 (Unicode 5.0)
+ *
+ * Permission to use, copy, modify, and distribute this software
+ * for any purpose and without fee is hereby granted. The author
+ * disclaims all warranties with regard to this software.
+ *
+ * Latest version: http://www.cl.cam.ac.uk/~mgk25/ucs/wcwidth.c
+ */
+
+#include <wchar.h>
+
+struct interval {
+ int first;
+ int last;
+};
+
+/* auxiliary function for binary search in interval table */
+static int bisearch(wchar_t ucs, const struct interval *table, int max) {
+ int min = 0;
+ int mid;
+
+ if (ucs < table[0].first || ucs > table[max].last)
+ return 0;
+ while (max >= min) {
+ mid = (min + max) / 2;
+ if (ucs > table[mid].last)
+ min = mid + 1;
+ else if (ucs < table[mid].first)
+ max = mid - 1;
+ else
+ return 1;
+ }
+
+ return 0;
+}
+
+
+/* The following two functions define the column width of an ISO 10646
+ * character as follows:
+ *
+ * - The null character (U+0000) has a column width of 0.
+ *
+ * - Other C0/C1 control characters and DEL will lead to a return
+ * value of -1.
+ *
+ * - Non-spacing and enclosing combining characters (general
+ * category code Mn or Me in the Unicode database) have a
+ * column width of 0.
+ *
+ * - SOFT HYPHEN (U+00AD) has a column width of 1.
+ *
+ * - Other format characters (general category code Cf in the Unicode
+ * database) and ZERO WIDTH SPACE (U+200B) have a column width of 0.
+ *
+ * - Hangul Jamo medial vowels and final consonants (U+1160-U+11FF)
+ * have a column width of 0.
+ *
+ * - Spacing characters in the East Asian Wide (W) or East Asian
+ * Full-width (F) category as defined in Unicode Technical
+ * Report #11 have a column width of 2.
+ *
+ * - All remaining characters (including all printable
+ * ISO 8859-1 and WGL4 characters, Unicode control characters,
+ * etc.) have a column width of 1.
+ *
+ * This implementation assumes that wchar_t characters are encoded
+ * in ISO 10646.
+ */
+
+int mk_wcwidth(wchar_t ucs)
+{
+ /* sorted list of non-overlapping intervals of non-spacing characters */
+ /* generated by "uniset +cat=Me +cat=Mn +cat=Cf -00AD +1160-11FF +200B c" */
+ static const struct interval combining[] = {
+ { 0x0300, 0x036F }, { 0x0483, 0x0486 }, { 0x0488, 0x0489 },
+ { 0x0591, 0x05BD }, { 0x05BF, 0x05BF }, { 0x05C1, 0x05C2 },
+ { 0x05C4, 0x05C5 }, { 0x05C7, 0x05C7 }, { 0x0600, 0x0603 },
+ { 0x0610, 0x0615 }, { 0x064B, 0x065E }, { 0x0670, 0x0670 },
+ { 0x06D6, 0x06E4 }, { 0x06E7, 0x06E8 }, { 0x06EA, 0x06ED },
+ { 0x070F, 0x070F }, { 0x0711, 0x0711 }, { 0x0730, 0x074A },
+ { 0x07A6, 0x07B0 }, { 0x07EB, 0x07F3 }, { 0x0901, 0x0902 },
+ { 0x093C, 0x093C }, { 0x0941, 0x0948 }, { 0x094D, 0x094D },
+ { 0x0951, 0x0954 }, { 0x0962, 0x0963 }, { 0x0981, 0x0981 },
+ { 0x09BC, 0x09BC }, { 0x09C1, 0x09C4 }, { 0x09CD, 0x09CD },
+ { 0x09E2, 0x09E3 }, { 0x0A01, 0x0A02 }, { 0x0A3C, 0x0A3C },
+ { 0x0A41, 0x0A42 }, { 0x0A47, 0x0A48 }, { 0x0A4B, 0x0A4D },
+ { 0x0A70, 0x0A71 }, { 0x0A81, 0x0A82 }, { 0x0ABC, 0x0ABC },
+ { 0x0AC1, 0x0AC5 }, { 0x0AC7, 0x0AC8 }, { 0x0ACD, 0x0ACD },
+ { 0x0AE2, 0x0AE3 }, { 0x0B01, 0x0B01 }, { 0x0B3C, 0x0B3C },
+ { 0x0B3F, 0x0B3F }, { 0x0B41, 0x0B43 }, { 0x0B4D, 0x0B4D },
+ { 0x0B56, 0x0B56 }, { 0x0B82, 0x0B82 }, { 0x0BC0, 0x0BC0 },
+ { 0x0BCD, 0x0BCD }, { 0x0C3E, 0x0C40 }, { 0x0C46, 0x0C48 },
+ { 0x0C4A, 0x0C4D }, { 0x0C55, 0x0C56 }, { 0x0CBC, 0x0CBC },
+ { 0x0CBF, 0x0CBF }, { 0x0CC6, 0x0CC6 }, { 0x0CCC, 0x0CCD },
+ { 0x0CE2, 0x0CE3 }, { 0x0D41, 0x0D43 }, { 0x0D4D, 0x0D4D },
+ { 0x0DCA, 0x0DCA }, { 0x0DD2, 0x0DD4 }, { 0x0DD6, 0x0DD6 },
+ { 0x0E31, 0x0E31 }, { 0x0E34, 0x0E3A }, { 0x0E47, 0x0E4E },
+ { 0x0EB1, 0x0EB1 }, { 0x0EB4, 0x0EB9 }, { 0x0EBB, 0x0EBC },
+ { 0x0EC8, 0x0ECD }, { 0x0F18, 0x0F19 }, { 0x0F35, 0x0F35 },
+ { 0x0F37, 0x0F37 }, { 0x0F39, 0x0F39 }, { 0x0F71, 0x0F7E },
+ { 0x0F80, 0x0F84 }, { 0x0F86, 0x0F87 }, { 0x0F90, 0x0F97 },
+ { 0x0F99, 0x0FBC }, { 0x0FC6, 0x0FC6 }, { 0x102D, 0x1030 },
+ { 0x1032, 0x1032 }, { 0x1036, 0x1037 }, { 0x1039, 0x1039 },
+ { 0x1058, 0x1059 }, { 0x1160, 0x11FF }, { 0x135F, 0x135F },
+ { 0x1712, 0x1714 }, { 0x1732, 0x1734 }, { 0x1752, 0x1753 },
+ { 0x1772, 0x1773 }, { 0x17B4, 0x17B5 }, { 0x17B7, 0x17BD },
+ { 0x17C6, 0x17C6 }, { 0x17C9, 0x17D3 }, { 0x17DD, 0x17DD },
+ { 0x180B, 0x180D }, { 0x18A9, 0x18A9 }, { 0x1920, 0x1922 },
+ { 0x1927, 0x1928 }, { 0x1932, 0x1932 }, { 0x1939, 0x193B },
+ { 0x1A17, 0x1A18 }, { 0x1B00, 0x1B03 }, { 0x1B34, 0x1B34 },
+ { 0x1B36, 0x1B3A }, { 0x1B3C, 0x1B3C }, { 0x1B42, 0x1B42 },
+ { 0x1B6B, 0x1B73 }, { 0x1DC0, 0x1DCA }, { 0x1DFE, 0x1DFF },
+ { 0x200B, 0x200F }, { 0x202A, 0x202E }, { 0x2060, 0x2063 },
+ { 0x206A, 0x206F }, { 0x20D0, 0x20EF }, { 0x302A, 0x302F },
+ { 0x3099, 0x309A }, { 0xA806, 0xA806 }, { 0xA80B, 0xA80B },
+ { 0xA825, 0xA826 }, { 0xFB1E, 0xFB1E }, { 0xFE00, 0xFE0F },
+ { 0xFE20, 0xFE23 }, { 0xFEFF, 0xFEFF }, { 0xFFF9, 0xFFFB },
+ { 0x10A01, 0x10A03 }, { 0x10A05, 0x10A06 }, { 0x10A0C, 0x10A0F },
+ { 0x10A38, 0x10A3A }, { 0x10A3F, 0x10A3F }, { 0x1D167, 0x1D169 },
+ { 0x1D173, 0x1D182 }, { 0x1D185, 0x1D18B }, { 0x1D1AA, 0x1D1AD },
+ { 0x1D242, 0x1D244 }, { 0xE0001, 0xE0001 }, { 0xE0020, 0xE007F },
+ { 0xE0100, 0xE01EF }
+ };
+
+ /* test for 8-bit control characters */
+ if (ucs == 0)
+ return 0;
+ if (ucs < 32 || (ucs >= 0x7f && ucs < 0xa0))
+ return -1;
+
+ /* binary search in table of non-spacing characters */
+ if (bisearch(ucs, combining,
+ sizeof(combining) / sizeof(struct interval) - 1))
+ return 0;
+
+ /* if we arrive here, ucs is not a combining or C0/C1 control character */
+
+ return 1 +
+ (ucs >= 0x1100 &&
+ (ucs <= 0x115f || /* Hangul Jamo init. consonants */
+ ucs == 0x2329 || ucs == 0x232a ||
+ (ucs >= 0x2e80 && ucs <= 0xa4cf &&
+ ucs != 0x303f) || /* CJK ... Yi */
+ (ucs >= 0xac00 && ucs <= 0xd7a3) || /* Hangul Syllables */
+ (ucs >= 0xf900 && ucs <= 0xfaff) || /* CJK Compatibility Ideographs */
+ (ucs >= 0xfe10 && ucs <= 0xfe19) || /* Vertical forms */
+ (ucs >= 0xfe30 && ucs <= 0xfe6f) || /* CJK Compatibility Forms */
+ (ucs >= 0xff00 && ucs <= 0xff60) || /* Fullwidth Forms */
+ (ucs >= 0xffe0 && ucs <= 0xffe6) ||
+ (ucs >= 0x20000 && ucs <= 0x2fffd) ||
+ (ucs >= 0x30000 && ucs <= 0x3fffd)));
+}
+
+
+int mk_wcswidth(const wchar_t *pwcs, size_t n)
+{
+ int w, width = 0;
+
+ for (;*pwcs && n-- > 0; pwcs++)
+ if ((w = mk_wcwidth(*pwcs)) < 0)
+ return -1;
+ else
+ width += w;
+
+ return width;
+}
+
+
+/*
+ * The following functions are the same as mk_wcwidth() and
+ * mk_wcswidth(), except that spacing characters in the East Asian
+ * Ambiguous (A) category as defined in Unicode Technical Report #11
+ * have a column width of 2. This variant might be useful for users of
+ * CJK legacy encodings who want to migrate to UCS without changing
+ * the traditional terminal character-width behaviour. It is not
+ * otherwise recommended for general use.
+ */
+int mk_wcwidth_cjk(wchar_t ucs)
+{
+ /* sorted list of non-overlapping intervals of East Asian Ambiguous
+ * characters, generated by "uniset +WIDTH-A -cat=Me -cat=Mn -cat=Cf c" */
+ static const struct interval ambiguous[] = {
+ { 0x00A1, 0x00A1 }, { 0x00A4, 0x00A4 }, { 0x00A7, 0x00A8 },
+ { 0x00AA, 0x00AA }, { 0x00AE, 0x00AE }, { 0x00B0, 0x00B4 },
+ { 0x00B6, 0x00BA }, { 0x00BC, 0x00BF }, { 0x00C6, 0x00C6 },
+ { 0x00D0, 0x00D0 }, { 0x00D7, 0x00D8 }, { 0x00DE, 0x00E1 },
+ { 0x00E6, 0x00E6 }, { 0x00E8, 0x00EA }, { 0x00EC, 0x00ED },
+ { 0x00F0, 0x00F0 }, { 0x00F2, 0x00F3 }, { 0x00F7, 0x00FA },
+ { 0x00FC, 0x00FC }, { 0x00FE, 0x00FE }, { 0x0101, 0x0101 },
+ { 0x0111, 0x0111 }, { 0x0113, 0x0113 }, { 0x011B, 0x011B },
+ { 0x0126, 0x0127 }, { 0x012B, 0x012B }, { 0x0131, 0x0133 },
+ { 0x0138, 0x0138 }, { 0x013F, 0x0142 }, { 0x0144, 0x0144 },
+ { 0x0148, 0x014B }, { 0x014D, 0x014D }, { 0x0152, 0x0153 },
+ { 0x0166, 0x0167 }, { 0x016B, 0x016B }, { 0x01CE, 0x01CE },
+ { 0x01D0, 0x01D0 }, { 0x01D2, 0x01D2 }, { 0x01D4, 0x01D4 },
+ { 0x01D6, 0x01D6 }, { 0x01D8, 0x01D8 }, { 0x01DA, 0x01DA },
+ { 0x01DC, 0x01DC }, { 0x0251, 0x0251 }, { 0x0261, 0x0261 },
+ { 0x02C4, 0x02C4 }, { 0x02C7, 0x02C7 }, { 0x02C9, 0x02CB },
+ { 0x02CD, 0x02CD }, { 0x02D0, 0x02D0 }, { 0x02D8, 0x02DB },
+ { 0x02DD, 0x02DD }, { 0x02DF, 0x02DF }, { 0x0391, 0x03A1 },
+ { 0x03A3, 0x03A9 }, { 0x03B1, 0x03C1 }, { 0x03C3, 0x03C9 },
+ { 0x0401, 0x0401 }, { 0x0410, 0x044F }, { 0x0451, 0x0451 },
+ { 0x2010, 0x2010 }, { 0x2013, 0x2016 }, { 0x2018, 0x2019 },
+ { 0x201C, 0x201D }, { 0x2020, 0x2022 }, { 0x2024, 0x2027 },
+ { 0x2030, 0x2030 }, { 0x2032, 0x2033 }, { 0x2035, 0x2035 },
+ { 0x203B, 0x203B }, { 0x203E, 0x203E }, { 0x2074, 0x2074 },
+ { 0x207F, 0x207F }, { 0x2081, 0x2084 }, { 0x20AC, 0x20AC },
+ { 0x2103, 0x2103 }, { 0x2105, 0x2105 }, { 0x2109, 0x2109 },
+ { 0x2113, 0x2113 }, { 0x2116, 0x2116 }, { 0x2121, 0x2122 },
+ { 0x2126, 0x2126 }, { 0x212B, 0x212B }, { 0x2153, 0x2154 },
+ { 0x215B, 0x215E }, { 0x2160, 0x216B }, { 0x2170, 0x2179 },
+ { 0x2190, 0x2199 }, { 0x21B8, 0x21B9 }, { 0x21D2, 0x21D2 },
+ { 0x21D4, 0x21D4 }, { 0x21E7, 0x21E7 }, { 0x2200, 0x2200 },
+ { 0x2202, 0x2203 }, { 0x2207, 0x2208 }, { 0x220B, 0x220B },
+ { 0x220F, 0x220F }, { 0x2211, 0x2211 }, { 0x2215, 0x2215 },
+ { 0x221A, 0x221A }, { 0x221D, 0x2220 }, { 0x2223, 0x2223 },
+ { 0x2225, 0x2225 }, { 0x2227, 0x222C }, { 0x222E, 0x222E },
+ { 0x2234, 0x2237 }, { 0x223C, 0x223D }, { 0x2248, 0x2248 },
+ { 0x224C, 0x224C }, { 0x2252, 0x2252 }, { 0x2260, 0x2261 },
+ { 0x2264, 0x2267 }, { 0x226A, 0x226B }, { 0x226E, 0x226F },
+ { 0x2282, 0x2283 }, { 0x2286, 0x2287 }, { 0x2295, 0x2295 },
+ { 0x2299, 0x2299 }, { 0x22A5, 0x22A5 }, { 0x22BF, 0x22BF },
+ { 0x2312, 0x2312 }, { 0x2460, 0x24E9 }, { 0x24EB, 0x254B },
+ { 0x2550, 0x2573 }, { 0x2580, 0x258F }, { 0x2592, 0x2595 },
+ { 0x25A0, 0x25A1 }, { 0x25A3, 0x25A9 }, { 0x25B2, 0x25B3 },
+ { 0x25B6, 0x25B7 }, { 0x25BC, 0x25BD }, { 0x25C0, 0x25C1 },
+ { 0x25C6, 0x25C8 }, { 0x25CB, 0x25CB }, { 0x25CE, 0x25D1 },
+ { 0x25E2, 0x25E5 }, { 0x25EF, 0x25EF }, { 0x2605, 0x2606 },
+ { 0x2609, 0x2609 }, { 0x260E, 0x260F }, { 0x2614, 0x2615 },
+ { 0x261C, 0x261C }, { 0x261E, 0x261E }, { 0x2640, 0x2640 },
+ { 0x2642, 0x2642 }, { 0x2660, 0x2661 }, { 0x2663, 0x2665 },
+ { 0x2667, 0x266A }, { 0x266C, 0x266D }, { 0x266F, 0x266F },
+ { 0x273D, 0x273D }, { 0x2776, 0x277F }, { 0xE000, 0xF8FF },
+ { 0xFFFD, 0xFFFD }, { 0xF0000, 0xFFFFD }, { 0x100000, 0x10FFFD }
+ };
+
+ /* binary search in table of non-spacing characters */
+ if (bisearch(ucs, ambiguous,
+ sizeof(ambiguous) / sizeof(struct interval) - 1))
+ return 2;
+
+ return mk_wcwidth(ucs);
+}
+
+
+int mk_wcswidth_cjk(const wchar_t *pwcs, size_t n)
+{
+ int w, width = 0;
+
+ for (;*pwcs && n-- > 0; pwcs++)
+ if ((w = mk_wcwidth_cjk(*pwcs)) < 0)
+ return -1;
+ else
+ width += w;
+
+ return width;
+}
(DIR) diff --git a/src/log.c b/src/log.c
@@ -0,0 +1,54 @@
+#include "log.h"
+
+#include <assert.h>
+#include <string.h>
+
+/*
+ * log.c - log to standard error according to the log level
+ *
+ * Instead of logging to syslog, delegate logging to a separate
+ * tool, such as FreeBSD's daemon(8), POSIX's logger(1).
+ */
+
+#include <errno.h>
+#include <stdio.h>
+#include <stdlib.h>
+
+#define LOG_DEFAULT 3 /* info */
+
+char *arg0 = NULL;
+
+static int log_level = -1;
+
+void
+log_print(int level, char const *flag, char const *fmt, ...)
+{
+ va_list va;
+ char *env;
+ int old_errno = errno;
+
+ va_start(va, fmt);
+
+ if (log_level < 0) {
+ env = getenv("LOG");
+ log_level = (env == NULL) ? 0 : atoi(env);
+ if (log_level == 0)
+ log_level = LOG_DEFAULT;
+ }
+
+ if (log_level < level)
+ return;
+
+ if (arg0 != NULL)
+ fprintf(stderr, "%s: ", arg0);
+
+ fprintf(stderr, "%s: ", flag);
+ vfprintf(stderr, fmt, va);
+
+ if (old_errno != 0)
+ fprintf(stderr, ": %s", strerror(old_errno));
+
+ fprintf(stderr, "\n");
+ fflush(stderr);
+ va_end(va);
+}
(DIR) diff --git a/src/log.h b/src/log.h
@@ -0,0 +1,15 @@
+#ifndef LOG_H
+#define LOG_H
+
+#include <stdarg.h>
+
+/** src/log.c **/
+char *arg0;
+void log_print(int level, char const *flag, char const *fmt, ...);
+
+#define die(...) (log_print(1, "error", __VA_ARGS__), exit(1))
+#define warn(...) log_print(2, "warn", __VA_ARGS__)
+#define info(...) log_print(3, "info", __VA_ARGS__)
+#define debug(...) log_print(4, "debug", __VA_ARGS__)
+
+#endif
(DIR) diff --git a/src/mem.c b/src/mem.c
@@ -0,0 +1,132 @@
+#include "mem.h"
+
+#include <assert.h>
+#include <stdlib.h>
+#include <string.h>
+#include <stdint.h>
+#include <errno.h>
+
+static struct mem_block *
+mem_block(void *v)
+{
+ struct mem_block *block = (void *)((char *)v - sizeof *block);
+
+ assert(memcmp(block->magic, MEM_BLOCK_MAGIC, 8) == 0);
+ return block;
+}
+
+void *
+mem_alloc(struct mem_pool *pool, size_t len)
+{
+ struct mem_block *block;
+
+ block = calloc(1, sizeof *block + len);
+ if (block == NULL)
+ return NULL;
+ memcpy(block->magic, MEM_BLOCK_MAGIC, 8);
+
+ block->len = len;
+ block->pool = pool;
+ block->prev = NULL;
+ block->next = pool->head;
+ if (pool->head != NULL)
+ pool->head->prev = block;
+ pool->head = block;
+
+ return block->buf;
+}
+
+int
+mem_resize(void **pp, size_t len)
+{
+ struct mem_block *block = mem_block(*pp);
+ int is_first = (block == block->pool->head);
+ int is_same;
+ void *v;
+
+ v = realloc(block, sizeof *block + len);
+ if (v == NULL)
+ return -1;
+ is_same = (block == v);
+ block = v;
+
+ block->len = len;
+
+ if (is_same)
+ return 0;
+
+ if (block->prev != NULL)
+ block->prev->next = v;
+ if (block->next != NULL)
+ block->next->prev = v;
+ if (is_first)
+ block->pool->head = v;
+ *pp = block->buf;
+
+ assert(memcmp(block->magic, MEM_BLOCK_MAGIC, 8) == 0);
+ return 0;
+}
+
+int
+mem_grow(void **pp, size_t len)
+{
+ assert(SIZE_MAX - len >= mem_block(*pp)->len);
+
+ return mem_resize(pp, mem_length(*pp) + len);
+}
+
+int
+mem_shrink(void **pp, size_t len)
+{
+ assert(mem_block(*pp)->len >= len);
+
+ return mem_resize(pp, mem_length(*pp) - len);
+}
+
+size_t
+mem_length(void *v)
+{
+ return mem_block(v)->len;
+}
+
+int
+mem_append(void **pp, char const *buf, size_t len)
+{
+ size_t old_len = mem_length(*pp);
+ struct mem_block *block;
+
+ if (mem_grow(pp, len) < 0)
+ return -1;
+ block = mem_block(*pp);
+ memcpy((char *)block->buf + old_len, buf, len);
+
+ assert(memcmp(block->magic, MEM_BLOCK_MAGIC, 8) == 0);
+ return 0;
+}
+
+void
+mem_delete(void *v)
+{
+ struct mem_block *block = mem_block(v);;
+
+ if (block == block->pool->head)
+ block->pool->head = block->next;
+ if (block->next != NULL)
+ block->next->prev = block->prev;
+ if (block->prev != NULL)
+ block->prev->next = block->next;
+ memset(block, 0, sizeof *block);
+ free(block);
+}
+
+void
+mem_free(struct mem_pool *pool)
+{
+ struct mem_block *block, *next;
+
+ for (block = pool->head; block != NULL; block = next) {
+ next = block->next;
+ memset(block, 0, sizeof *block);
+ free(block);
+ }
+}
(DIR) diff --git a/src/mem.h b/src/mem.h
@@ -0,0 +1,58 @@
+#ifndef MEM_H
+#define MEM_H
+
+/*
+ * Lightweight wrapper over malloc, that permit to define a memory pool of
+ * multiple buffers, and free them all at once.
+ *
+ * *──────────┐
+ * │ mem_pool │
+ * ├──────────┤
+ * │*head │
+ * └┬─────────┘
+ * v
+ * NULL< *───────────┐< >*───────────┐< >*───────────┐< >*───────────┐ >NULL
+ * \ │ mem_block │ \/ │ mem_block │ \/ │ mem_block │ \/ │ mem_block │ /
+ * \ ├───────────┤ /\ ├───────────┤ /\ ├───────────┤ /\ ├───────────┤ /
+ * `┤*prev *next├' `┤*prev *next├' `┤*prev *next├' `┤*prev *next├'
+ * │len │ │len │ │len │ │len │
+ * ├─┴─magic───┤ ├─┴─magic───┤ ├─┴─magic───┤ ├─┴─magic───┤
+ * │///////////│ │///////////│ │///////////│ │///////////│
+ * │///////////│ │///////////│ │///////////│ │///////////│
+ * │///////////│ │///////////│ │///////////│ └───────────┘
+ * └───────────┘ │///////////│ │///////////│
+ * │///////////│ └───────────┘
+ * └───────────┘
+ *
+ * This permits the type checker to still work on all operations while
+ * providing generic memory management functions for all types of data
+ * structures and keep track of each object's length.
+ */
+
+#include <stddef.h>
+
+#define MEM_BLOCK_MAGIC "\xcc\x68\x23\xd7\x9b\x7d\x39\xb9"
+
+struct mem_pool {
+ struct mem_block *head;
+};
+
+struct mem_block {
+ struct mem_pool *pool;
+ struct mem_block *prev, *next;
+ size_t len;
+ char magic[8]; /* at the end to detect buffer underflow */
+ char buf[];
+};
+
+/** src/mem.c **/
+void * mem_alloc(struct mem_pool *pool, size_t len);
+int mem_resize(void **pp, size_t len);
+int mem_grow(void **pp, size_t len);
+int mem_shrink(void **pp, size_t len);
+size_t mem_length(void *v);
+int mem_append(void **pp, char const *buf, size_t len);
+void mem_delete(void *v);
+void mem_free(struct mem_pool *pool);
+
+#endif
(DIR) diff --git a/src/str.c b/src/str.c
@@ -0,0 +1,119 @@
+#include "str.h"
+
+#include <assert.h>
+#include <errno.h>
+#include <stdarg.h>
+#include <stdint.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+
+#include "mem.h"
+
+/*
+ * It is heavy on assert as an inexpensive way to detect memory corruption from
+ * code around: underflows are checked through the magic header, overflow are
+ * checked through the '\0' byte.
+ */
+
+size_t
+str_length(struct str *str)
+{
+ return mem_length(str->mem) - sizeof "";
+}
+
+int
+str_init(struct str *str, struct mem_pool *pool)
+{
+ str->mem = mem_alloc(pool, 1);
+ if (str->mem == NULL)
+ return -1;
+
+ assert(str->mem[0] == '\0');
+ assert(str_length(str) == 0);
+ assert(mem_length(str->mem) == 1);
+ return 0;
+}
+
+void
+str_truncate(struct str *str, size_t len)
+{
+ assert(str->mem[str_length(str)] == '\0');
+
+ if (mem_length(str->mem) > len)
+ str->mem[len] = '\0';
+ mem_resize((void **)&str->mem, len + 1);
+
+ assert(str->mem[str_length(str)] == '\0');
+}
+
+int
+str_append_mem(struct str *str, char const *buf, size_t len)
+{
+ void **pp = (void **)&str->mem;
+ size_t old_sz;
+
+ assert((old_sz = mem_length(str->mem)) > 0);
+ assert(memchr(buf, '\0', len) == NULL);
+ assert(str->mem[str_length(str)] == '\0');
+
+ if (mem_shrink(pp, 1)) /* strip '\0' */
+ return -1;
+ if (mem_append(pp, buf, len) < 0)
+ return -1;
+ if (mem_append(pp, "", 1) < 0)
+ return -1;
+
+ assert(memcmp(str->mem + old_sz-1, buf, len) == 0);
+ assert(str->mem[old_sz-1 + len] == '\0');
+ assert(str->mem[str_length(str)] == '\0');
+ return 0;
+}
+
+int
+str_append_string(struct str *str, char const *s)
+{
+ assert(str->mem[str_length(str)] == '\0');
+
+ return str_append_mem(str, s, strlen(s));
+}
+
+int
+str_append_char(struct str *str, char c)
+{
+ assert(str->mem[str_length(str)] == '\0');
+
+ str_c(str)[str_length(str)] = c;
+ if (mem_append((void **)str->mem, "", 1) < 0)
+ return -1;
+
+ assert(str->mem[str_length(str)] == '\0');
+ return 0;
+}
+
+int
+str_append_fmt(struct str *str, char const *fmt, ...)
+{
+ va_list va;
+ int n;
+
+ assert(str->mem[str_length(str)] == '\0');
+
+ va_start(va, fmt);
+ n = vsnprintf(NULL, 0, fmt, va);
+ assert(n > 0);
+ if (mem_grow((void **)&str->mem, n + 1) < 0)
+ return -1;
+ vsprintf(str->mem, fmt, va);
+ va_end(va);
+
+ assert(str->mem[str_length(str)] == '\0');
+ return 0;
+}
+
+char *
+str_c(struct str *str)
+{
+ assert(str->mem[str_length(str)] == '\0');
+ return str->mem;
+}
(DIR) diff --git a/src/str.h b/src/str.h
@@ -0,0 +1,26 @@
+#ifndef STR_H
+#define STR_H
+
+#include <stddef.h>
+
+#include "mem.h"
+
+/*
+ * Length kept by struct mem_block.
+ */
+
+struct str {
+ char *mem;
+};
+
+/** src/str.c **/
+size_t str_length(struct str *str);
+int str_init(struct str *str, struct mem_pool *pool);
+void str_truncate(struct str *str, size_t len);
+int str_append_mem(struct str *str, char const *buf, size_t len);
+int str_append_string(struct str *str, char const *s);
+int str_append_char(struct str *str, char c);
+int str_append_fmt(struct str *str, char const *fmt, ...);
+char * str_c(struct str *str);
+
+#endif
(DIR) diff --git a/src/utf8.c b/src/utf8.c
@@ -0,0 +1,214 @@
+/*
+ * ASCII all have a leading '0' byte:
+ *
+ * 0xxxxxxx
+ *
+ * UTF-8 have one leading '1' and as many following '1' as there are
+ * continuation bytes (with leading '1' and '0').
+ *
+ * 0xxxxxxx
+ * 110xxxxx 10xxxxxx
+ * 1110xxxx 10xxxxxx 10xxxxxx
+ * 11110xxx 10xxxxxx 10xxxxxx 10xxxxxx
+ * 111110xx 10xxxxxx 10xxxxxx 10xxxxxx 10xxxxxx
+ * 1111110x 10xxxxxx 10xxxxxx 10xxxxxx 10xxxxxx 10xxxxxx
+ *
+ * There is up to 3 continuation bytes -- up to 4 bytes per runes.
+ */
+
+#include <ctype.h>
+#include <stddef.h>
+#include <stdlib.h>
+#include <string.h>
+#include <stdio.h>
+
+#include "utf8.h"
+
+static int
+utflen(char const *str)
+{
+ int i, len;
+ unsigned char const *s;
+
+ s = (unsigned char const *)str;
+ len = (*s < 0x80) ? 1 : /* 0xxxxxxx < *s < 10000000 */
+ (*s < 0xc0) ? 0 : /* 10xxxxxx < *s < 11000000 */
+ (*s < 0xe0) ? 2 : /* 110xxxxx < *s < 11100000 */
+ (*s < 0xf0) ? 3 : /* 1110xxxx < *s < 11110000 */
+ (*s < 0xf8) ? 4 : /* 11110xxx < *s < 11111000 */
+ (*s < 0xfc) ? 5 : /* 111110xx < *s < 11111100 */
+ (*s < 0xfe) ? 6 : /* 1111110x < *s < 11111110 */
+ (*s < 0xff) ? 7 : /* 11111110 < *s < 11111111 */
+ 0;
+
+ /* check continuation bytes and '\0' */
+ for (s++, i = 1; i < len; i++, s++) {
+ if ((*s & 0xc0) != 0x80) /* 10xxxxxx & 11000000 */
+ return 0;
+ }
+
+ return len;
+}
+
+static long
+torune(char const **str, size_t len)
+{
+ long rune;
+ int n;
+ char mask[] = { 0x00, 0x7f, 0x1f, 0x0f, 0x07, 0x03, 0x01 };
+
+ if (len == 0 || len > 6)
+ return 0;
+
+ /* first byte */
+ rune = *(*str)++ & mask[len];
+
+ /* continuation bytes */
+ for (n = len - 1; n > 0; n--, (*str)++)
+ rune = (rune << 6) | (**str & 0x3f); /* 10xxxxxx */
+
+ return rune;
+}
+
+/*
+ * Return the number of bytes required to encode <rune> into UTF-8, or
+ * 0 if rune is too long.
+ */
+int
+utf8_runelen(long rune)
+{
+ return (rune <= 0x0000007f) ? 1 :
+ (rune <= 0x000007ff) ? 2 :
+ (rune <= 0x0000ffff) ? 3 :
+ (rune <= 0x001fffff) ? 4 :
+ (rune <= 0x03ffffff) ? 5 :
+ (rune <= 0x7fffffff) ? 6 :
+ 0;
+}
+
+/*
+ * Return the number of bytes in rune for the next char in <s>, or 0 if
+ * is misencoded or if it is '\0'.
+ */
+int
+utf8_utflen(char const *str)
+{
+ long rune;
+ int len = utflen(str);
+
+ rune = torune(&str, len);
+ if (len != utf8_runelen(rune))
+ return 0;
+
+ return len;
+}
+
+/*
+ * Return a rune corresponding to the firsts bytes of <str> or -1 if
+ * the rune is invalid, and set <str> to the beginning of the next rune.
+ */
+long
+utf8_torune(char const **str)
+{
+ long rune;
+ int len;
+
+ len = utflen(*str);
+ rune = torune(str, len);
+ if (len != utf8_runelen(rune))
+ return -1;
+
+ return rune;
+}
+
+/*
+ * Encode the rune <rune> in UTF-8 in <str>, null-terminated, then return the
+ * number of bytes written, 0 if <rune> is invalid.
+ *
+ * Thanks to Connor Lane Smith for the idea of combining switches and
+ * binary masks.
+ */
+int
+utf8_tostr(char *str, long rune)
+{
+ switch (utf8_runelen(rune)) {
+ case 1:
+ str[0] = rune; /* 0xxxxxxx */
+ str[1] = '\0';
+ return 1;
+ case 2:
+ str[0] = 0xc0 | (0x1f & (rune >> 6)); /* 110xxxxx */
+ str[1] = 0x80 | (0x3f & (rune)); /* 10xxxxxx */
+ str[2] = '\0';
+ return 2;
+ case 3:
+ str[0] = 0xe0 | (0x0f & (rune >> 12)); /* 1110xxxx */
+ str[1] = 0x80 | (0x3f & (rune >> 6)); /* 10xxxxxx */
+ str[2] = 0x80 | (0x3f & (rune)); /* 10xxxxxx */
+ str[3] = '\0';
+ return 3;
+ case 4:
+ str[0] = 0xf0 | (0x07 & (rune >> 18)); /* 11110xxx */
+ str[1] = 0x80 | (0x3f & (rune >> 12)); /* 10xxxxxx */
+ str[2] = 0x80 | (0x3f & (rune >> 6)); /* 10xxxxxx */
+ str[3] = 0x80 | (0x3f & (rune)); /* 10xxxxxx */
+ str[4] = '\0';
+ return 4;
+ case 5:
+ str[0] = 0xf8 | (0x03 & (rune >> 24)); /* 111110xx */
+ str[1] = 0x80 | (0x3f & (rune >> 18)); /* 10xxxxxx */
+ str[2] = 0x80 | (0x3f & (rune >> 12)); /* 10xxxxxx */
+ str[3] = 0x80 | (0x3f & (rune >> 6)); /* 10xxxxxx */
+ str[4] = 0x80 | (0x3f & (rune)); /* 10xxxxxx */
+ str[5] = '\0';
+ return 5;
+ case 6:
+ str[0] = 0xfc | (0x01 & (rune >> 30)); /* 1111110x */
+ str[1] = 0x80 | (0x3f & (rune >> 24)); /* 10xxxxxx */
+ str[2] = 0x80 | (0x3f & (rune >> 18)); /* 10xxxxxx */
+ str[3] = 0x80 | (0x3f & (rune >> 12)); /* 10xxxxxx */
+ str[4] = 0x80 | (0x3f & (rune >> 6)); /* 10xxxxxx */
+ str[5] = 0x80 | (0x3f & (rune)); /* 10xxxxxx */
+ str[6] = '\0';
+ return 6;
+ default:
+ str[0] = '\0';
+ return 0;
+ }
+}
+
+/*
+ * Return 1 if the rune is a printable character, and 0 otherwise.
+ */
+int
+utf8_isprint(long rune)
+{
+ return (0x1f < rune && rune != 0x7f && rune < 0x80) || 0x9f < rune;
+}
+
+/*
+ * Return a pointer to the next rune in <str> or next byte if the rune
+ * is invalid.
+ */
+char const *
+utf8_nextrune(char const *str)
+{
+ int len;
+
+ len = utf8_utflen(str);
+ return (len == 0) ? str + 1 : str + len;
+}
+
+/*
+ * Return a pointer to the prev rune in <str> or prev byte if the rune
+ * is invalid.
+ */
+char const *
+utf8_prevrune(char const *str)
+{
+ char const *s;
+
+ for (s = str; (*s & 0x80) != 0; s--)
+ ;
+ return (utf8_utflen(s) != 0) ? s : str - 1;
+}
(DIR) diff --git a/src/utf8.h b/src/utf8.h
@@ -0,0 +1,13 @@
+#ifndef UTF8_H
+#define UTF8_H
+
+/** src/utf8.c **/
+int utf8_runelen(long rune);
+int utf8_utflen(char const *str);
+long utf8_torune(char const **str);
+int utf8_tostr(char *str, long rune);
+int utf8_isprint(long rune);
+char const * utf8_nextrune(char const *str);
+char const * utf8_prevrune(char const *str);
+
+#endif
(DIR) diff --git a/src/util.h b/src/util.h
@@ -0,0 +1,12 @@
+#ifndef UTIL_H
+#define UTIL_H
+
+#define ESC 0x1b /* Esc key */
+#define CTL(c) ((c) & ~0x40) /* Ctr + (c) key */
+#define ALT(c) ((c) + 0x80) /* Alt + (c) key */
+#define CSI(c) ((c) + 0x80 + 0x80) /* Escape + '[' + (c) code */
+#define MIN(x, y) (((x) < (y)) ? (x) : (y))
+#define MAX(x, y) (((x) > (y)) ? (x) : (y))
+#define LEN(x) (sizeof(x) / sizeof(*(x)))
+
+#endif
(DIR) diff --git a/strcasestr.c b/strcasestr.c
@@ -1,25 +0,0 @@
-#include <ctype.h>
-#include <stddef.h>
-
-#include "util.h"
-
-char *
-strcasesstr(const char *str1, const char *str2)
-{
- const char *s1;
- const char *s2;
-
- for (;;) {
- s1 = str1;
- s2 = str2;
- while (*s1 != '\0' && tolower(*s1) == tolower(*s2))
- s1++, s2++;
- if (*s2 == '\0')
- return (char *) str1;
- if (*s1 == '\0')
- return NULL;
- str1++;
- }
-
- return NULL;
-}
(DIR) diff --git a/strsep.c b/strsep.c
@@ -1,21 +0,0 @@
-#include <string.h>
-
-char *
-strsep(char **strp, const char *delim)
-{
- char *s, *oldp;
-
- if (*strp == NULL)
- return NULL;
- for (s = oldp = *strp; ; s++) {
- if (*s == '\0') {
- *strp = NULL;
- return oldp;
- } else if (strchr(delim, *s) != NULL) {
- break;
- }
- }
- *s = '\0';
- *strp = s + 1;
- return oldp;
-}
(DIR) diff --git a/test.c b/t/test.c
(DIR) diff --git a/utf8.c b/utf8.c
@@ -1,424 +0,0 @@
-/*
-** ASCII all have a leading '0' byte:
-**
-** 0xxxxxxx
-**
-** UTF-8 have one leading '1' and as many following '1' as there are
-** continuation bytes (with leading '1' and '0').
-**
-** 0xxxxxxx
-** 110xxxxx 10xxxxxx
-** 1110xxxx 10xxxxxx 10xxxxxx
-** 11110xxx 10xxxxxx 10xxxxxx 10xxxxxx
-** 111110xx 10xxxxxx 10xxxxxx 10xxxxxx 10xxxxxx
-** 1111110x 10xxxxxx 10xxxxxx 10xxxxxx 10xxxxxx 10xxxxxx
-**
-** There is up to 3 continuation bytes -- up to 4 bytes per runes.
-*/
-
-#include <ctype.h>
-#include <stddef.h>
-#include <stdlib.h>
-#include <string.h>
-#include <stdio.h>
-
-#include "utf8.h"
-
-static int
-utflen(char const *str)
-{
- int i, len;
- unsigned char const *s;
-
- s = (unsigned char const *)str;
- len = (*s < 0x80) ? 1 : /* 0xxxxxxx < *s < 10000000 */
- (*s < 0xc0) ? 0 : /* 10xxxxxx < *s < 11000000 */
- (*s < 0xe0) ? 2 : /* 110xxxxx < *s < 11100000 */
- (*s < 0xf0) ? 3 : /* 1110xxxx < *s < 11110000 */
- (*s < 0xf8) ? 4 : /* 11110xxx < *s < 11111000 */
- (*s < 0xfc) ? 5 : /* 111110xx < *s < 11111100 */
- (*s < 0xfe) ? 6 : /* 1111110x < *s < 11111110 */
- (*s < 0xff) ? 7 : /* 11111110 < *s < 11111111 */
- 0;
-
- /* check continuation bytes and '\0' */
- for (s++, i = 1; i < len; i++, s++) {
- if ((*s & 0xc0) != 0x80) /* 10xxxxxx & 11000000 */
- return 0;
- }
-
- return len;
-}
-
-static long
-torune(char const **str, size_t len)
-{
- long rune;
- int n;
- char mask[] = { 0x00, 0x7f, 0x1f, 0x0f, 0x07, 0x03, 0x01 };
-
- if (len == 0 || len > 6)
- return 0;
-
- /* first byte */
- rune = *(*str)++ & mask[len];
-
- /* continuation bytes */
- for (n = len - 1; n > 0; n--, (*str)++)
- rune = (rune << 6) | (**str & 0x3f); /* 10xxxxxx */
-
- return rune;
-}
-
-/*
-** Return the number of bytes required to encode <rune> into UTF-8, or
-** 0 if rune is too long.
-*/
-int
-utf8_runelen(long rune)
-{
- return (rune <= 0x0000007f) ? 1 :
- (rune <= 0x000007ff) ? 2 :
- (rune <= 0x0000ffff) ? 3 :
- (rune <= 0x001fffff) ? 4 :
- (rune <= 0x03ffffff) ? 5 :
- (rune <= 0x7fffffff) ? 6 :
- 0;
-}
-
-/*
-** Return the number of bytes in rune for the next char in <s>, or 0 if
-** is misencoded or if it is '\0'.
-*/
-int
-utf8_utflen(char const *str)
-{
- long rune;
- int len;
-
- len = utflen(str);
- rune = torune(&str, len);
- if (len != utf8_runelen(rune))
- return 0;
-
- return len;
-}
-
-/*
-** Return a rune corresponding to the firsts bytes of <str> or -1 if
-** the rune is invalid, and set <str> to the beginning of the next rune.
-*/
-long
-utf8_torune(char const **str)
-{
- long rune;
- int len;
-
- len = utflen(*str);
- rune = torune(str, len);
- if (len != utf8_runelen(rune))
- return -1;
-
- return rune;
-}
-
-/*
-** Encode the rune <rune> in UTF-8 in <str>, null-terminated, then return the
-** number of bytes written, 0 if <rune> is invalid.
-**
-** Thanks to Connor Lane Smith for the idea of combining switches and
-** binary masks.
-*/
-int
-utf8_tostr(char *str, long rune)
-{
- switch (utf8_runelen(rune)) {
- case 1:
- str[0] = rune; /* 0xxxxxxx */
- str[1] = '\0';
- return 1;
- case 2:
- str[0] = 0xc0 | (0x1f & (rune >> 6)); /* 110xxxxx */
- str[1] = 0x80 | (0x3f & (rune)); /* 10xxxxxx */
- str[2] = '\0';
- return 2;
- case 3:
- str[0] = 0xe0 | (0x0f & (rune >> 12)); /* 1110xxxx */
- str[1] = 0x80 | (0x3f & (rune >> 6)); /* 10xxxxxx */
- str[2] = 0x80 | (0x3f & (rune)); /* 10xxxxxx */
- str[3] = '\0';
- return 3;
- case 4:
- str[0] = 0xf0 | (0x07 & (rune >> 18)); /* 11110xxx */
- str[1] = 0x80 | (0x3f & (rune >> 12)); /* 10xxxxxx */
- str[2] = 0x80 | (0x3f & (rune >> 6)); /* 10xxxxxx */
- str[3] = 0x80 | (0x3f & (rune)); /* 10xxxxxx */
- str[4] = '\0';
- return 4;
- case 5:
- str[0] = 0xf8 | (0x03 & (rune >> 24)); /* 111110xx */
- str[1] = 0x80 | (0x3f & (rune >> 18)); /* 10xxxxxx */
- str[2] = 0x80 | (0x3f & (rune >> 12)); /* 10xxxxxx */
- str[3] = 0x80 | (0x3f & (rune >> 6)); /* 10xxxxxx */
- str[4] = 0x80 | (0x3f & (rune)); /* 10xxxxxx */
- str[5] = '\0';
- return 5;
- case 6:
- str[0] = 0xfc | (0x01 & (rune >> 30)); /* 1111110x */
- str[1] = 0x80 | (0x3f & (rune >> 24)); /* 10xxxxxx */
- str[2] = 0x80 | (0x3f & (rune >> 18)); /* 10xxxxxx */
- str[3] = 0x80 | (0x3f & (rune >> 12)); /* 10xxxxxx */
- str[4] = 0x80 | (0x3f & (rune >> 6)); /* 10xxxxxx */
- str[5] = 0x80 | (0x3f & (rune)); /* 10xxxxxx */
- str[6] = '\0';
- return 6;
- default:
- str[0] = '\0';
- return 0;
- }
-}
-
-/*
-** Return 1 if the rune is a printable character, and 0 otherwise.
-*/
-int
-utf8_isprint(long rune)
-{
- return (0x1f < rune && rune != 0x7f && rune < 0x80) || 0x9f < rune;
-}
-
-/*
-** Markus Kuhn -- 2007-05-26 (Unicode 5.0)
-**
-** Permission to use, copy, modify, and distribute this software
-** for any purpose and without fee is hereby granted. The author
-** disclaims all warranties with regard to this software.
-**
-** Latest version: http://www.cl.cam.ac.uk/~mgk25/ucs/wcwidth.c
-*/
-
-struct interval {
- int first;
- int last;
-};
-
-/*
-** Auxiliary function for binary search in interval table.
-*/
-static int
-bisearch(long ucs, struct interval const *table, int max)
-{
- int min = 0;
- int mid;
-
- if (ucs < table[0].first || ucs > table[max].last)
- return 0;
- while (max >= min) {
- mid = (min + max) / 2;
- if (ucs > table[mid].last)
- min = mid + 1;
- else if (ucs < table[mid].first)
- max = mid - 1;
- else
- return 1;
- }
-
- return 0;
-}
-
-/* The following two functions define the column width of an ISO 10646
-** character as follows:
-**
-** - The null character (U+0000) has a column width of 0.
-**
-** - Other C0/C1 control characters and DEL will lead to a return
-** value of -1.
-**
-** - Non-spacing and enclosing combining characters (general
-** category code Mn or Me in the Unicode database) have a
-** column width of 0.
-**
-** - SOFT HYPHEN (U+00AD) has a column width of 1.
-**
-** - Other format characters (general category code Cf in the Unicode
-** database) and ZERO WIDTH SPACE (U+200B) have a column width of 0.
-**
-** - Hangul Jamo medial vowels and final consonants (U+1160-U+11FF)
-** have a column width of 0.
-**
-** - Spacing characters in the East Asian Wide (W) or East Asian
-** Full-width (F) category as defined in Unicode Technical
-** Report #11 have a column width of 2.
-**
-** - All remaining characters (including all printable
-** ISO 8859-1 and WGL4 characters, Unicode control characters,
-** etc.) have a column width of 1.
-**
-** This implementation was assuming that long characters are encoded
-** in ISO 10646.
-*/
-int
-utf8_wcwidth(long ucs)
-{
- /* sorted list of non-overlapping intervals of non-spacing characters */
- /* generated by "uniset +cat=Me +cat=Mn +cat=Cf -00AD +1160-11FF +200B c" */
- static struct interval const combining[] = {
- { 0x0300, 0x036F }, { 0x0483, 0x0486 }, { 0x0488, 0x0489 },
- { 0x0591, 0x05BD }, { 0x05BF, 0x05BF }, { 0x05C1, 0x05C2 },
- { 0x05C4, 0x05C5 }, { 0x05C7, 0x05C7 }, { 0x0600, 0x0603 },
- { 0x0610, 0x0615 }, { 0x064B, 0x065E }, { 0x0670, 0x0670 },
- { 0x06D6, 0x06E4 }, { 0x06E7, 0x06E8 }, { 0x06EA, 0x06ED },
- { 0x070F, 0x070F }, { 0x0711, 0x0711 }, { 0x0730, 0x074A },
- { 0x07A6, 0x07B0 }, { 0x07EB, 0x07F3 }, { 0x0901, 0x0902 },
- { 0x093C, 0x093C }, { 0x0941, 0x0948 }, { 0x094D, 0x094D },
- { 0x0951, 0x0954 }, { 0x0962, 0x0963 }, { 0x0981, 0x0981 },
- { 0x09BC, 0x09BC }, { 0x09C1, 0x09C4 }, { 0x09CD, 0x09CD },
- { 0x09E2, 0x09E3 }, { 0x0A01, 0x0A02 }, { 0x0A3C, 0x0A3C },
- { 0x0A41, 0x0A42 }, { 0x0A47, 0x0A48 }, { 0x0A4B, 0x0A4D },
- { 0x0A70, 0x0A71 }, { 0x0A81, 0x0A82 }, { 0x0ABC, 0x0ABC },
- { 0x0AC1, 0x0AC5 }, { 0x0AC7, 0x0AC8 }, { 0x0ACD, 0x0ACD },
- { 0x0AE2, 0x0AE3 }, { 0x0B01, 0x0B01 }, { 0x0B3C, 0x0B3C },
- { 0x0B3F, 0x0B3F }, { 0x0B41, 0x0B43 }, { 0x0B4D, 0x0B4D },
- { 0x0B56, 0x0B56 }, { 0x0B82, 0x0B82 }, { 0x0BC0, 0x0BC0 },
- { 0x0BCD, 0x0BCD }, { 0x0C3E, 0x0C40 }, { 0x0C46, 0x0C48 },
- { 0x0C4A, 0x0C4D }, { 0x0C55, 0x0C56 }, { 0x0CBC, 0x0CBC },
- { 0x0CBF, 0x0CBF }, { 0x0CC6, 0x0CC6 }, { 0x0CCC, 0x0CCD },
- { 0x0CE2, 0x0CE3 }, { 0x0D41, 0x0D43 }, { 0x0D4D, 0x0D4D },
- { 0x0DCA, 0x0DCA }, { 0x0DD2, 0x0DD4 }, { 0x0DD6, 0x0DD6 },
- { 0x0E31, 0x0E31 }, { 0x0E34, 0x0E3A }, { 0x0E47, 0x0E4E },
- { 0x0EB1, 0x0EB1 }, { 0x0EB4, 0x0EB9 }, { 0x0EBB, 0x0EBC },
- { 0x0EC8, 0x0ECD }, { 0x0F18, 0x0F19 }, { 0x0F35, 0x0F35 },
- { 0x0F37, 0x0F37 }, { 0x0F39, 0x0F39 }, { 0x0F71, 0x0F7E },
- { 0x0F80, 0x0F84 }, { 0x0F86, 0x0F87 }, { 0x0F90, 0x0F97 },
- { 0x0F99, 0x0FBC }, { 0x0FC6, 0x0FC6 }, { 0x102D, 0x1030 },
- { 0x1032, 0x1032 }, { 0x1036, 0x1037 }, { 0x1039, 0x1039 },
- { 0x1058, 0x1059 }, { 0x1160, 0x11FF }, { 0x135F, 0x135F },
- { 0x1712, 0x1714 }, { 0x1732, 0x1734 }, { 0x1752, 0x1753 },
- { 0x1772, 0x1773 }, { 0x17B4, 0x17B5 }, { 0x17B7, 0x17BD },
- { 0x17C6, 0x17C6 }, { 0x17C9, 0x17D3 }, { 0x17DD, 0x17DD },
- { 0x180B, 0x180D }, { 0x18A9, 0x18A9 }, { 0x1920, 0x1922 },
- { 0x1927, 0x1928 }, { 0x1932, 0x1932 }, { 0x1939, 0x193B },
- { 0x1A17, 0x1A18 }, { 0x1B00, 0x1B03 }, { 0x1B34, 0x1B34 },
- { 0x1B36, 0x1B3A }, { 0x1B3C, 0x1B3C }, { 0x1B42, 0x1B42 },
- { 0x1B6B, 0x1B73 }, { 0x1DC0, 0x1DCA }, { 0x1DFE, 0x1DFF },
- { 0x200B, 0x200F }, { 0x202A, 0x202E }, { 0x2060, 0x2063 },
- { 0x206A, 0x206F }, { 0x20D0, 0x20EF }, { 0x302A, 0x302F },
- { 0x3099, 0x309A }, { 0xA806, 0xA806 }, { 0xA80B, 0xA80B },
- { 0xA825, 0xA826 }, { 0xFB1E, 0xFB1E }, { 0xFE00, 0xFE0F },
- { 0xFE20, 0xFE23 }, { 0xFEFF, 0xFEFF }, { 0xFFF9, 0xFFFB },
- { 0x10A01, 0x10A03 }, { 0x10A05, 0x10A06 }, { 0x10A0C, 0x10A0F },
- { 0x10A38, 0x10A3A }, { 0x10A3F, 0x10A3F }, { 0x1D167, 0x1D169 },
- { 0x1D173, 0x1D182 }, { 0x1D185, 0x1D18B }, { 0x1D1AA, 0x1D1AD },
- { 0x1D242, 0x1D244 }, { 0xE0001, 0xE0001 }, { 0xE0020, 0xE007F },
- { 0xE0100, 0xE01EF }
- };
-
- /* test for 8-bit control characters */
- if (ucs == 0)
- return 0;
- if (ucs < 32 || (ucs >= 0x7f && ucs < 0xa0))
- return -1;
-
- /* binary search in table of non-spacing characters */
- if (bisearch(ucs, combining, sizeof(combining) /
- sizeof(struct interval) - 1))
- return 0;
-
- /* if we arrive here, ucs is not a combining or C0/C1 control character */
-
- return 1 + (ucs >= 0x1100 &&
- (ucs <= 0x115f || /* Hangul Jamo init. consonants */
- ucs == 0x2329 || ucs == 0x232a ||
- (ucs >= 0x2e80 && ucs <= 0xa4cf &&
- ucs != 0x303f) || /* CJK ... Yi */
- (ucs >= 0xac00 && ucs <= 0xd7a3) || /* Hangul Syllables */
- (ucs >= 0xf900 && ucs <= 0xfaff) || /* CJK Compatibility Ideographs */
- (ucs >= 0xfe10 && ucs <= 0xfe19) || /* Vertical forms */
- (ucs >= 0xfe30 && ucs <= 0xfe6f) || /* CJK Compatibility Forms */
- (ucs >= 0xff00 && ucs <= 0xff60) || /* Fullwidth Forms */
- (ucs >= 0xffe0 && ucs <= 0xffe6) ||
- (ucs >= 0x20000 && ucs <= 0x2fffd) ||
- (ucs >= 0x30000 && ucs <= 0x3fffd)));
-}
-
-/*
-** Return the width of <rune> with tabs as displayed from position <off>.
-*/
-int
-utf8_runewidth(long rune, size_t off)
-{
- return (rune == '\t') ? (int)(8 - (off % 8)) : utf8_wcwidth(rune);
-}
-
-/*
-** Return a index of the first byte of a character of <s> that would be rendered
-** at the <col>-th column in a terminal, or NULL if the whole string fit. In
-** order to format tabs properly, the string must start with an offset of <off>
-** columns.
-*/
-int
-utf8_col(char const *str, size_t col, size_t off)
-{
- long rune;
- char const *pos, *s;
-
- for (s = str; off <= col;) {
- pos = s;
- if (*s == '\0')
- break;
-
- rune = utf8_torune(&s);
- off += utf8_runewidth(rune, off);
- }
-
- return pos - str;
-}
-
-/*
-** Print <rune> to <fp> if it is less wide than <maxwidth> and return
-** the number of columns of the rune printed or a negative value if
-** nothing was printed: -1 if the rune is invalid, and -2 if no width
-** is left. If the rune is tab, the width is calculated usin <off>
-** as column offset.
-*/
-int
-utf8_putrune(long rune, int maxwidth, int off, FILE *fp)
-{
- int width;
- char str[8];
-
- if ((width = utf8_runewidth(rune, off)) > maxwidth)
- return -2;
- if (utf8_tostr(str, rune) == 0)
- return -1;
- fputs(str, fp);
-
- return width;
-}
-
-/*
-** Return a pointer to the next rune in <str> or next byte if the rune
-** is invalid.
-*/
-char const *
-utf8_nextrune(char const *str)
-{
- int len;
-
- len = utf8_utflen(str);
- return (len == 0) ? str + 1 : str + len;
-}
-
-/*
-** Return a pointer to the prev rune in <str> or prev byte if the rune
-** is invalid.
-*/
-char const *
-utf8_prevrune(char const *str)
-{
- char const *s;
-
- for (s = str; (*s & 0x80) != 0; s--)
- ;
- return (utf8_utflen(s) != 0) ? s : str - 1;
-}
(DIR) diff --git a/utf8.h b/utf8.h
@@ -1,11 +0,0 @@
-int utf8_runelen (long);
-int utf8_utflen (char const *);
-long utf8_torune (char const **);
-int utf8_tostr (char *, long);
-int utf8_isprint (long);
-int utf8_wcwidth (long);
-int utf8_runewidth (long, size_t);
-int utf8_col (char const *, size_t, size_t);
-int utf8_putrune (long, int, int, FILE *);
-char const *utf8_nextrune (char const *);
-char const *utf8_prevrune (char const *);
(DIR) diff --git a/util.h b/util.h
@@ -1,31 +0,0 @@
-/*
-** EPITECH PROJECT, 2017
-** util
-** File description:
-** util
-*/
-
-#ifndef UTIL_H
-#define UTIL_H
-
-#include <stdarg.h>
-
-#define ESC 0x1b /* Esc key */
-#define CTL(c) ((c) & ~0x40) /* Ctr + (c) key */
-#define ALT(c) ((c) + 0x80) /* Alt + (c) key */
-#define CSI(c) ((c) + 0x80 + 0x80) /* Escape + '[' + (c) code */
-#define MIN(x, y) (((x) < (y)) ? (x) : (y))
-#define MAX(x, y) (((x) > (y)) ? (x) : (y))
-#define LEN(x) (sizeof(x) / sizeof(*(x)))
-
-/* string */
-char *strcasestr(const char *, const char *);
-size_t strlcpy(char *, const char *, size_t);
-char *strsep(char **, const char *);
-
-/* error */
-void err(int, const char *, ...);
-void vwarn(const char *, va_list);
-void warn(const char *, ...);
-
-#endif