add example for reading a line from the terminal, non-blocking

Handles utf8, and character width

3 files changed, 619 insertions, 17 deletions

diff --git a/src/term.c b/src/term.c
index f73d23f..e557a11 100644
--- a/src/term.c
+++ b/src/term.c
@@ -15,6 +15,7 @@
 
 #ifdef _WIN32
 # include <windows.h>
+# include <locale.h>
 #else
 # include <termios.h>
 # include <string.h>
@@ -22,8 +23,16 @@
 # include <fcntl.h>
 # include <sys/ioctl.h>
 # include <unistd.h>
+# include <wchar.h>
+# include <locale.h>
 #endif
 
+
+// Windows does not have a wcwidth function, so we use compatibilty code from
+// http://www.cl.cam.ac.uk/~mgk25/ucs/wcwidth.c by Markus Kuhn
+#include "wcwidth.h"
+
+
 #ifdef _WIN32
 // after an error is returned, GetLastError() result can be passed to this function to get a string
 // representation of the error on the stack.
@@ -423,7 +432,7 @@ static int lst_getconsoleflags(lua_State *L)
 // see https://github.com/luaposix/luaposix
 
 /***
-Get termios state.
+Get termios state (Posix).
 The terminal attributes is a table with the following fields:
 
 - `iflag` input flags
@@ -511,7 +520,7 @@ static int lst_tcgetattr(lua_State *L)
 
 
 /***
-Set termios state.
+Set termios state (Posix).
 This function will set the flags as given.
 
 The `I_`, `O_`, and `L_` constants are available on the module table. They are the respective
@@ -689,13 +698,28 @@ static int lst_getnonblock(lua_State *L)
  * Reading keyboard input
  *-------------------------------------------------------------------------*/
 
+#ifdef _WIN32
+// Define a static buffer for UTF-8 characters
+static char utf8_buffer[4];
+static int utf8_buffer_len = 0;
+static int utf8_buffer_index = 0;
+#endif
+
+
 /***
-Reads a key from the console non-blocking.
+Reads a key from the console non-blocking. This function should not be called
+directly, but through the `system.readkey` or `system.readansi` functions. It
+will return the next byte from the input stream, or `nil` if no key was pressed.
+
 On Posix, `io.stdin` must be set to non-blocking mode using `setnonblock`
-before calling this function. Otherwise it will block.
+before calling this function. Otherwise it will block. No conversions are
+done on Posix, so the byte read is returned as-is.
 
-@function readkey
-@treturn[1] integer the key code of the key that was pressed
+On Windows this reads a wide character and converts it to UTF-8. Multi-byte
+sequences will be buffered internally and returned one byte at a time.
+
+@function _readkey
+@treturn[1] integer the byte read from the input stream
 @treturn[2] nil if no key was pressed
 @treturn[3] nil on error
 @treturn[3] string error message
@@ -703,20 +727,87 @@ before calling this function. Otherwise it will block.
 */
 static int lst_readkey(lua_State *L) {
 #ifdef _WIN32
-    if (_kbhit()) {
-        int ch = _getch();
-        if (ch == EOF) {
-            // Error handling for end-of-file or read error
-            lua_pushnil(L);
-            lua_pushliteral(L, "_getch error");
-            return 2;
+    if (utf8_buffer_len > 0) {
+        // Buffer not empty, return the next byte
+        lua_pushinteger(L, (unsigned char)utf8_buffer[utf8_buffer_index]);
+        utf8_buffer_index++;
+        utf8_buffer_len--;
+        // printf("returning from buffer: %d\n", luaL_checkinteger(L, -1));
+        if (utf8_buffer_len == 0) {
+            utf8_buffer_index = 0;
         }
-        lua_pushinteger(L, (unsigned char)ch);
         return 1;
     }
-    return 0;
+
+    if (!_kbhit()) {
+        return 0;
+    }
+
+    wchar_t wc = _getwch();
+    // printf("----\nread wchar_t: %x\n", wc);
+    if (wc == WEOF) {
+        lua_pushnil(L);
+        lua_pushliteral(L, "read error");
+        return 2;
+    }
+
+    if (sizeof(wchar_t) == 2) {
+        // printf("2-byte wchar_t\n");
+        // only 2 bytes wide, not 4
+        if (wc >= 0xD800 && wc <= 0xDBFF) {
+            // printf("2-byte wchar_t, received high, getting low...\n");
+
+            // we got a high surrogate, so we need to read the next one as the low surrogate
+            if (!_kbhit()) {
+                lua_pushnil(L);
+                lua_pushliteral(L, "incomplete surrogate pair");
+                return 2;
+            }
+
+            wchar_t wc2 = _getwch();
+            // printf("read wchar_t 2: %x\n", wc2);
+            if (wc2 == WEOF) {
+                lua_pushnil(L);
+                lua_pushliteral(L, "read error");
+                return 2;
+            }
+
+            if (wc2 < 0xDC00 || wc2 > 0xDFFF) {
+                lua_pushnil(L);
+                lua_pushliteral(L, "invalid surrogate pair");
+                return 2;
+            }
+            // printf("2-byte pair complete now\n");
+            wchar_t wch_pair[2] = { wc, wc2 };
+            utf8_buffer_len = WideCharToMultiByte(CP_UTF8, 0, wch_pair, 2, utf8_buffer, sizeof(utf8_buffer), NULL, NULL);
+
+        } else {
+            // printf("2-byte wchar_t, no surrogate pair\n");
+            // not a high surrogate, so we can handle just the 2 bytes directly
+            utf8_buffer_len = WideCharToMultiByte(CP_UTF8, 0, &wc, 1, utf8_buffer, sizeof(utf8_buffer), NULL, NULL);
+        }
+
+    } else {
+        // printf("4-byte wchar_t\n");
+        // 4 bytes wide, so handle as UTF-32 directly
+        utf8_buffer_len = WideCharToMultiByte(CP_UTF8, 0, &wc, 1, utf8_buffer, sizeof(utf8_buffer), NULL, NULL);
+    }
+    // printf("utf8_buffer_len: %d\n", utf8_buffer_len);
+    utf8_buffer_index = 0;
+    if (utf8_buffer_len <= 0) {
+        lua_pushnil(L);
+        lua_pushliteral(L, "UTF-8 conversion error");
+        return 2;
+    }
+
+    lua_pushinteger(L, (unsigned char)utf8_buffer[utf8_buffer_index]);
+    utf8_buffer_index++;
+    utf8_buffer_len--;
+    // printf("returning from buffer: %x\n", luaL_checkinteger(L, -1));
+    return 1;
 
 #else
+    // Posix implementation
     char ch;
     ssize_t bytes_read = read(STDIN_FILENO, &ch, 1);
     if (bytes_read > 0) {
@@ -782,6 +873,205 @@ static int lst_termsize(lua_State *L) {
 
 
 /*-------------------------------------------------------------------------
+ * utf8 conversion and support
+ *-------------------------------------------------------------------------*/
+
+// Function to convert a single UTF-8 character to a Unicode code point (uint32_t)
+// To prevent having to do codepage/locale changes, we use a custom implementation
+int utf8_to_wchar(const char *utf8, size_t len, mk_wchar_t *codepoint) {
+    if (len == 0) {
+        return -1; // No input provided
+    }
+
+    unsigned char c = (unsigned char)utf8[0];
+    if (c <= 0x7F) {
+        *codepoint = c;
+        return 1;
+    } else if ((c & 0xE0) == 0xC0) {
+        if (len < 2) return -1; // Not enough bytes
+        *codepoint = ((utf8[0] & 0x1F) << 6) | (utf8[1] & 0x3F);
+        return 2;
+    } else if ((c & 0xF0) == 0xE0) {
+        if (len < 3) return -1; // Not enough bytes
+        *codepoint = ((utf8[0] & 0x0F) << 12) | ((utf8[1] & 0x3F) << 6) | (utf8[2] & 0x3F);
+        return 3;
+    } else if ((c & 0xF8) == 0xF0) {
+        if (len < 4) return -1; // Not enough bytes
+        *codepoint = ((utf8[0] & 0x07) << 18) | ((utf8[1] & 0x3F) << 12) | ((utf8[2] & 0x3F) << 6) | (utf8[3] & 0x3F);
+        return 4;
+    } else {
+        // Invalid UTF-8 character
+        return -1;
+    }
+}
+
+
+/***
+Get the width of a utf8 character for terminal display.
+@function utf8cwidth
+@tparam string utf8_char the utf8 character to check, only the width of the first character will be returned
+@treturn[1] int the display width in columns of the first character in the string (0 for an empty string)
+@treturn[2] nil
+@treturn[2] string error message
+*/
+int lst_utf8cwidth(lua_State *L) {
+    const char *utf8_char;
+    size_t utf8_len;
+    utf8_char = luaL_checklstring(L, 1, &utf8_len);
+    int width = 0;
+
+    mk_wchar_t wc;
+
+    if (utf8_len == 0) {
+        lua_pushinteger(L, 0);
+        return 1;
+    }
+
+    // Convert the UTF-8 string to a wide character
+    int bytes_processed = utf8_to_wchar(utf8_char, utf8_len, &wc);
+    if (bytes_processed == -1) {
+        lua_pushnil(L);
+        lua_pushstring(L, "Invalid UTF-8 character");
+        return 2;
+    }
+
+    // Get the width of the wide character
+    width = mk_wcwidth(wc);
+    if (width == -1) {
+        lua_pushnil(L);
+        lua_pushstring(L, "Character width determination failed");
+        return 2;
+    }
+
+    lua_pushinteger(L, width);
+    return 1;
+}
+
+
+
+
+/***
+Get the width of a utf8 string for terminal display.
+@function utf8swidth
+@tparam string utf8_string the utf8 string to check
+@treturn[1] int the display width of the string in columns (0 for an empty string)
+@treturn[2] nil
+@treturn[2] string error message
+*/
+int lst_utf8swidth(lua_State *L) {
+    const char *utf8_str;
+    size_t utf8_len;
+    utf8_str = luaL_checklstring(L, 1, &utf8_len);
+    int total_width = 0;
+
+    if (utf8_len == 0) {
+        lua_pushinteger(L, 0);
+        return 1;
+    }
+
+    int bytes_processed = 0;
+    size_t i = 0;
+    mk_wchar_t wc;
+
+    while (i < utf8_len) {
+        bytes_processed = utf8_to_wchar(utf8_str + i, utf8_len - i, &wc);
+        if (bytes_processed == -1) {
+            lua_pushnil(L);
+            lua_pushstring(L, "Invalid UTF-8 character");
+            return 2;
+        }
+
+        int width = mk_wcwidth(wc);
+        if (width == -1) {
+            lua_pushnil(L);
+            lua_pushstring(L, "Character width determination failed");
+            return 2;
+        }
+
+        total_width += width;
+        i += bytes_processed;
+    }
+
+    lua_pushinteger(L, total_width);
+    return 1;
+}
+
+
+
+/*-------------------------------------------------------------------------
+ * Windows codepage functions
+ *-------------------------------------------------------------------------*/
+
+
+/***
+Gets the current console code page (Windows).
+@function getconsolecp
+@treturn[1] int the current code page (always 65001 on Posix systems)
+*/
+static int lst_getconsolecp(lua_State *L) {
+    unsigned int cp = 65001;
+#ifdef _WIN32
+    cp = GetConsoleCP();
+#endif
+    lua_pushinteger(L, cp);
+    return 1;
+}
+
+
+
+/***
+Sets the current console code page (Windows).
+@function setconsolecp
+@tparam int cp the code page to set, use 65001 for UTF-8
+@treturn[1] bool `true` on success (always `true` on Posix systems)
+*/
+static int lst_setconsolecp(lua_State *L) {
+    unsigned int cp = (unsigned int)luaL_checkinteger(L, 1);
+    int success = TRUE;
+#ifdef _WIN32
+    SetConsoleCP(cp);
+#endif
+    lua_pushboolean(L, success);
+    return 1;
+}
+
+
+
+/***
+Gets the current console output code page (Windows).
+@function getconsoleoutputcp
+@treturn[1] int the current code page (always 65001 on Posix systems)
+*/
+static int lst_getconsoleoutputcp(lua_State *L) {
+    unsigned int cp = 65001;
+#ifdef _WIN32
+    cp = GetConsoleOutputCP();
+#endif
+    lua_pushinteger(L, cp);
+    return 1;
+}
+
+
+
+/***
+Sets the current console output code page (Windows).
+@function setconsoleoutputcp
+@tparam int cp the code page to set, use 65001 for UTF-8
+@treturn[1] bool `true` on success (always `true` on Posix systems)
+*/
+static int lst_setconsoleoutputcp(lua_State *L) {
+    unsigned int cp = (unsigned int)luaL_checkinteger(L, 1);
+    int success = TRUE;
+#ifdef _WIN32
+    SetConsoleOutputCP(cp);
+#endif
+    lua_pushboolean(L, success);
+    return 1;
+}
+
+
+
+/*-------------------------------------------------------------------------
  * Initializes module
  *-------------------------------------------------------------------------*/
 
@@ -791,10 +1081,16 @@ static luaL_Reg func[] = {
     { "setconsoleflags", lst_setconsoleflags },
     { "tcgetattr", lst_tcgetattr },
     { "tcsetattr", lst_tcsetattr },
-    { "getnonblock", lst_setnonblock },
+    { "getnonblock", lst_getnonblock },
     { "setnonblock", lst_setnonblock },
-    { "readkey", lst_readkey },
+    { "_readkey", lst_readkey },
     { "termsize", lst_termsize },
+    { "utf8cwidth", lst_utf8cwidth },
+    { "utf8swidth", lst_utf8swidth },
+    { "getconsolecp", lst_getconsolecp },
+    { "setconsolecp", lst_setconsolecp },
+    { "getconsoleoutputcp", lst_getconsoleoutputcp },
+    { "setconsoleoutputcp", lst_setconsoleoutputcp },
     { NULL, NULL }
 };
 
diff --git a/src/wcwidth.c b/src/wcwidth.c
new file mode 100644
index 0000000..6032158
--- /dev/null
+++ b/src/wcwidth.c
@@ -0,0 +1,285 @@
+// This file was modified from the original versions, check "modified:" comments for details
+// Character range updates (both the table and the +1 check) were generated using ChatGPT.
+
+/*
+ * 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 "wcwidth.h"  // modified: used to define mk_wchar_t
+
+struct interval {
+  int first;
+  int last;
+};
+
+/* auxiliary function for binary search in interval table */
+static int bisearch(mk_wchar_t ucs, const struct interval *table, int max) {  // modified: use mk_wchar_t
+  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 mk_wchar_t characters are encoded
+ * in ISO 10646.
+ */
+
+int mk_wcwidth(mk_wchar_t ucs)  // modified: use mk_wchar_t
+{
+  /* 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[] = {  // modified: added new ranges to the list
+    { 0x0300, 0x036F }, { 0x0483, 0x0489 }, { 0x0591, 0x05BD },
+    { 0x05BF, 0x05BF }, { 0x05C1, 0x05C2 }, { 0x05C4, 0x05C5 },
+    { 0x05C7, 0x05C7 }, { 0x0600, 0x0605 }, { 0x0610, 0x061A },
+    { 0x061C, 0x061C }, { 0x064B, 0x065F }, { 0x0670, 0x0670 },
+    { 0x06D6, 0x06DC }, { 0x06DF, 0x06E4 }, { 0x06E7, 0x06E8 },
+    { 0x06EA, 0x06ED }, { 0x0711, 0x0711 }, { 0x0730, 0x074A },
+    { 0x07A6, 0x07B0 }, { 0x07EB, 0x07F3 }, { 0x07FD, 0x07FD },
+    { 0x0816, 0x0819 }, { 0x081B, 0x0823 }, { 0x0825, 0x0827 },
+    { 0x0829, 0x082D }, { 0x0859, 0x085B }, { 0x08D3, 0x08E1 },
+    { 0x08E3, 0x0903 }, { 0x093A, 0x093C }, { 0x093E, 0x094F },
+    { 0x0951, 0x0957 }, { 0x0962, 0x0963 }, { 0x0981, 0x0983 },
+    { 0x09BC, 0x09BC }, { 0x09BE, 0x09C4 }, { 0x09C7, 0x09C8 },
+    { 0x09CB, 0x09CD }, { 0x09D7, 0x09D7 }, { 0x09E2, 0x09E3 },
+    { 0x09FE, 0x09FE }, { 0x0A01, 0x0A03 }, { 0x0A3C, 0x0A3C },
+    { 0x0A3E, 0x0A42 }, { 0x0A47, 0x0A48 }, { 0x0A4B, 0x0A4D },
+    { 0x0A51, 0x0A51 }, { 0x0A70, 0x0A71 }, { 0x0A75, 0x0A75 },
+    { 0x0A81, 0x0A83 }, { 0x0ABC, 0x0ABC }, { 0x0ABE, 0x0AC5 },
+    { 0x0AC7, 0x0AC9 }, { 0x0ACB, 0x0ACD }, { 0x0AE2, 0x0AE3 },
+    { 0x0AFA, 0x0AFF }, { 0x0B01, 0x0B03 }, { 0x0B3C, 0x0B3C },
+    { 0x0B3E, 0x0B44 }, { 0x0B47, 0x0B48 }, { 0x0B4B, 0x0B4D },
+    { 0x0B55, 0x0B57 }, { 0x0B62, 0x0B63 }, { 0x0B82, 0x0B82 },
+    { 0x0BBE, 0x0BC2 }, { 0x0BC6, 0x0BC8 }, { 0x0BCA, 0x0BCD },
+    { 0x0BD7, 0x0BD7 }, { 0x0C00, 0x0C04 }, { 0x0C3E, 0x0C44 },
+    { 0x0C46, 0x0C48 }, { 0x0C4A, 0x0C4D }, { 0x0C55, 0x0C56 },
+    { 0x0C62, 0x0C63 }, { 0x0C81, 0x0C83 }, { 0x0CBC, 0x0CBC },
+    { 0x0CBE, 0x0CC4 }, { 0x0CC6, 0x0CC8 }, { 0x0CCA, 0x0CCD },
+    { 0x0CD5, 0x0CD6 }, { 0x0CE2, 0x0CE3 }, { 0x0D00, 0x0D03 },
+    { 0x0D3B, 0x0D3C }, { 0x0D3E, 0x0D44 }, { 0x0D46, 0x0D48 },
+    { 0x0D4A, 0x0D4D }, { 0x0D57, 0x0D57 }, { 0x0D62, 0x0D63 },
+    { 0x0D82, 0x0D83 }, { 0x0DCF, 0x0DD4 }, { 0x0DD6, 0x0DD6 },
+    { 0x0DD8, 0x0DDF }, { 0x0DF2, 0x0DF3 }, { 0x0E31, 0x0E31 },
+    { 0x0E34, 0x0E3A }, { 0x0E47, 0x0E4E }, { 0x0EB1, 0x0EB1 },
+    { 0x0EB4, 0x0EBC }, { 0x0EC8, 0x0ECD }, { 0x0F18, 0x0F19 },
+    { 0x0F35, 0x0F35 }, { 0x0F37, 0x0F37 }, { 0x0F39, 0x0F39 },
+    { 0x0F71, 0x0F7E }, { 0x0F80, 0x0F84 }, { 0x0F86, 0x0F87 },
+    { 0x0F8D, 0x0F97 }, { 0x0F99, 0x0FBC }, { 0x0FC6, 0x0FC6 },
+    { 0x102D, 0x1030 }, { 0x1032, 0x1037 }, { 0x1039, 0x103A },
+    { 0x103D, 0x103E }, { 0x1058, 0x1059 }, { 0x105E, 0x1060 },
+    { 0x1071, 0x1074 }, { 0x1082, 0x1082 }, { 0x1085, 0x1086 },
+    { 0x108D, 0x108D }, { 0x109D, 0x109D }, { 0x135D, 0x135F },
+    { 0x1712, 0x1714 }, { 0x1732, 0x1734 }, { 0x1752, 0x1753 },
+    { 0x1772, 0x1773 }, { 0x17B4, 0x17B5 }, { 0x17B7, 0x17BD },
+    { 0x17C6, 0x17C6 }, { 0x17C9, 0x17D3 }, { 0x17DD, 0x17DD },
+    { 0x180B, 0x180E }, { 0x1885, 0x1886 }, { 0x18A9, 0x18A9 },
+    { 0x1920, 0x1922 }, { 0x1927, 0x1928 }, { 0x1932, 0x1932 },
+    { 0x1939, 0x193B }, { 0x1A17, 0x1A18 }, { 0x1A1B, 0x1A1B },
+    { 0x1A56, 0x1A56 }, { 0x1A58, 0x1A5E }, { 0x1A60, 0x1A60 },
+    { 0x1A62, 0x1A62 }, { 0x1A65, 0x1A6C }, { 0x1A73, 0x1A7C },
+    { 0x1A7F, 0x1A7F }, { 0x1AB0, 0x1ACE }, { 0x1B00, 0x1B03 },
+    { 0x1B34, 0x1B34 }, { 0x1B36, 0x1B3A }, { 0x1B3C, 0x1B3C },
+    { 0x1B42, 0x1B42 }, { 0x1B6B, 0x1B73 }, { 0x1B80, 0x1B82 },
+    { 0x1BA1, 0x1BA1 }, { 0x1BA6, 0x1BA7 }, { 0x1BAA, 0x1BAA },
+    { 0x1BAB, 0x1BAD }, { 0x1BE6, 0x1BE6 }, { 0x1BE8, 0x1BE9 },
+    { 0x1BED, 0x1BED }, { 0x1BEF, 0x1BF1 }, { 0x1C2C, 0x1C33 },
+    { 0x1C36, 0x1C37 }, { 0x1CD0, 0x1CD2 }, { 0x1CD4, 0x1CE8 },
+    { 0x1CED, 0x1CED }, { 0x1CF4, 0x1CF4 }, { 0x1CF8, 0x1CF9 },
+    { 0x1DC0, 0x1DF9 }, { 0x1DFB, 0x1DFF }, { 0x20D0, 0x20DC },
+    { 0x20E1, 0x20E1 }, { 0x20E5, 0x20F0 }, { 0x2CEF, 0x2CF1 },
+    { 0x2D7F, 0x2D7F }, { 0x2DE0, 0x2DFF }, { 0x302A, 0x302D },
+    { 0x3099, 0x309A }, { 0xA66F, 0xA672 }, { 0xA674, 0xA67D },
+    { 0xA69E, 0xA69F }, { 0xA6F0, 0xA6F1 }, { 0xA802, 0xA802 },
+    { 0xA806, 0xA806 }, { 0xA80B, 0xA80B }, { 0xA825, 0xA826 },
+    { 0xA82C, 0xA82C }, { 0xA8C4, 0xA8C5 }, { 0xA8E0, 0xA8F1 },
+    { 0xA8FF, 0xA8FF }, { 0xA926, 0xA92D }, { 0xA947, 0xA951 },
+    { 0xA980, 0xA982 }, { 0xA9B3, 0xA9B3 }, { 0xA9B6, 0xA9B9 },
+    { 0xA9BC, 0xA9BD }, { 0xA9E5, 0xA9E5 }, { 0xAA29, 0xAA2E },
+    { 0xAA31, 0xAA32 }, { 0xAA35, 0xAA36 }, { 0xAA43, 0xAA43 },
+    { 0xAA4C, 0xAA4C }, { 0xAA7C, 0xAA7C }, { 0xAAB0, 0xAAB0 },
+    { 0xAAB2, 0xAAB4 }, { 0xAAB7, 0xAAB8 }, { 0xAABE, 0xAABF },
+    { 0xAAC1, 0xAAC1 }, { 0xAAEB, 0xAAEB }, { 0xAAEE, 0xAAEF },
+    { 0xAAF5, 0xAAF6 }, { 0xABE3, 0xABE4 }, { 0xABE6, 0xABE7 },
+    { 0xABE9, 0xABEA }, { 0xABEC, 0xABED }, { 0xFB1E, 0xFB1E },
+    { 0xFE00, 0xFE0F }, { 0xFE20, 0xFE2F }, { 0x101FD, 0x101FD },
+    { 0x102E0, 0x102E0 }, { 0x10376, 0x1037A }, { 0x10A01, 0x10A03 },
+    { 0x10A05, 0x10A06 }, { 0x10A0C, 0x10A0F }, { 0x10A38, 0x10A3A },
+    { 0x10A3F, 0x10A3F }, { 0x10AE5, 0x10AE6 }, { 0x10D24, 0x10D27 },
+    { 0x10EAB, 0x10EAC }, { 0x10F46, 0x10F50 }, { 0x10F82, 0x10F85 },
+    { 0x11000, 0x11002 }, { 0x11038, 0x11046 }, { 0x1107F, 0x11082 },
+    { 0x110B0, 0x110BA }, { 0x11100, 0x11102 }, { 0x11127, 0x11134 },
+    { 0x11145, 0x11146 }, { 0x11173, 0x11173 }, { 0x11180, 0x11182 },
+    { 0x111B3, 0x111C0 }, { 0x111C9, 0x111CC }, { 0x1122C, 0x11237 },
+    { 0x1123E, 0x1123E }, { 0x112DF, 0x112EA }, { 0x11300, 0x11303 },
+    { 0x1133B, 0x1133C }, { 0x1133E, 0x11344 }, { 0x11347, 0x11348 },
+    { 0x1134B, 0x1134D }, { 0x11357, 0x11357 }, { 0x11362, 0x11363 },
+    { 0x11435, 0x11446 }, { 0x1145E, 0x1145E }, { 0x114B0, 0x114C3 },
+    { 0x115AF, 0x115B5 }, { 0x115B8, 0x115C0 }, { 0x115DC, 0x115DD },
+    { 0x11630, 0x11640 }, { 0x116AB, 0x116B7 }, { 0x1171D, 0x1172B },
+    { 0x1182C, 0x1183A }, { 0x11930, 0x11935 }, { 0x11937, 0x11938 },
+    { 0x1193B, 0x1193E }, { 0x11940, 0x11940 }, { 0x11942, 0x11942 },
+    { 0x119D1, 0x119D7 }, { 0x119DA, 0x119E0 }, { 0x11A01, 0x11A0A },
+    { 0x11A33, 0x11A39 }, { 0x11A3B, 0x11A3E }, { 0x11A47, 0x11A47 },
+    { 0x11A51, 0x11A5B }, { 0x11A8A, 0x11A96 }, { 0x11A98, 0x11A99 },
+    { 0x11C30, 0x11C36 }, { 0x11C38, 0x11C3D }, { 0x11C3F, 0x11C3F },
+    { 0x11C92, 0x11CA7 }, { 0x11CAA, 0x11CB0 }, { 0x11CB2, 0x11CB3 },
+    { 0x11CB5, 0x11CB6 }, { 0x11D31, 0x11D36 }, { 0x11D3A, 0x11D3A },
+    { 0x11D3C, 0x11D3D }, { 0x11D3F, 0x11D45 }, { 0x11D47, 0x11D47 },
+    { 0x11D90, 0x11D91 }, { 0x11D95, 0x11D95 }, { 0x11D97, 0x11D97 },
+    { 0x11EF3, 0x11EF4 }, { 0x13430, 0x13438 }, { 0x16AF0, 0x16AF4 },
+    { 0x16B30, 0x16B36 }, { 0x16F4F, 0x16F4F }, { 0x16F8F, 0x16F92 },
+    { 0x1BC9D, 0x1BC9E }, { 0x1BCA0, 0x1BCA3 }, { 0x1D167, 0x1D169 },
+    { 0x1D173, 0x1D182 }, { 0x1D185, 0x1D18B }, { 0x1D1AA, 0x1D1AD },
+    { 0x1D242, 0x1D244 }, { 0x1DA00, 0x1DA36 }, { 0x1DA3B, 0x1DA6C },
+    { 0x1DA75, 0x1DA75 }, { 0x1DA84, 0x1DA84 }, { 0x1DA9B, 0x1DA9F },
+    { 0x1DAA1, 0x1DAAF }, { 0x1E000, 0x1E006 }, { 0x1E008, 0x1E018 },
+    { 0x1E01B, 0x1E021 }, { 0x1E023, 0x1E024 }, { 0x1E026, 0x1E02A },
+    { 0x1E130, 0x1E136 }, { 0x1E2AE, 0x1E2AE }, { 0x1E2EC, 0x1E2EF },
+    { 0x1E4EC, 0x1E4EF }, { 0x1E8D0, 0x1E8D6 }, { 0x1E944, 0x1E94A },
+    { 0x1E947, 0x1E94A }, { 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 >= 0x1f300 && ucs <= 0x1f64f) || /* modified: added Emoticons */
+      (ucs >= 0x1f680 && ucs <= 0x1f6ff) || /* modified: added Transport and Map Symbols */
+      (ucs >= 0x1f900 && ucs <= 0x1f9ff) || /* modified: added Supplemental Symbols and Pictographs */
+      (ucs >= 0x20000 && ucs <= 0x2fffd) ||
+      (ucs >= 0x30000 && ucs <= 0x3fffd)));
+}
+
+
+int mk_wcswidth(const mk_wchar_t *pwcs, size_t n)  // modified: use mk_wchar_t
+{
+  int w, width = 0;
+
+  for (;*pwcs && n-- > 0; pwcs++)
+    if ((w = mk_wcwidth(*pwcs)) < 0)
+      return -1;
+    else
+      width += w;
+
+  return width;
+}
+
diff --git a/src/wcwidth.h b/src/wcwidth.h
new file mode 100644
index 0000000..f2fee11
--- /dev/null
+++ b/src/wcwidth.h
@@ -0,0 +1,21 @@
+// wcwidth.h
+
+// Windows does not have a wcwidth function, so we use compatibilty code from
+// http://www.cl.cam.ac.uk/~mgk25/ucs/wcwidth.c by Markus Kuhn
+
+#ifndef MK_WCWIDTH_H
+#define MK_WCWIDTH_H
+
+
+#ifdef _WIN32
+#include <stdint.h>
+typedef uint32_t mk_wchar_t; // Windows wchar_t can be 16-bit, we need 32-bit
+#else
+#include <wchar.h>
+typedef wchar_t mk_wchar_t;  // Posix wchar_t is 32-bit so just use that
+#endif
+
+int mk_wcwidth(mk_wchar_t ucs);
+int mk_wcswidth(const mk_wchar_t *pwcs, size_t n);
+
+#endif // MK_WCWIDTH_H